upload testing qwen_code_7B_test_swe_reasoning

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-168/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: qwen_code_7B_test_swe_reasoning
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# qwen_code_7B_test_swe_reasoning
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) on the SWE-BENCH-400-reasoning dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 12
+- total_train_batch_size: 24
+- total_eval_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.5.1+cu124
+- Datasets 2.20.0
+- Tokenizers 0.20.3

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9822485207100593,
+    "total_flos": 6.46489842951127e+16,
+    "train_loss": 0.5384191712808042,
+    "train_runtime": 12683.2217,
+    "train_samples_per_second": 0.32,
+    "train_steps_per_second": 0.013
+}

checkpoint-168/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-168/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 4.0,
+    "original_max_position_embeddings": 32768,
+    "rope_type": "yarn",
+    "type": "yarn"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

checkpoint-168/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}

checkpoint-168/global_step168/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f5c49ed6d30f0224e5dfba1040159eb6d37e9f192f066aafed76fc9ae921250
+size 45693706641

checkpoint-168/global_step168/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:973e5dc636234664edf706bf92baa3a3a93c54fabcaeafc1a6fcdd4bea74892d
+size 45693706641

checkpoint-168/global_step168/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ac0d545911813b6e2ac27d6de44c048a288d1ea6396efa2ff68444967a30761
+size 167061

checkpoint-168/global_step168/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed3fbb08314ca07e886042dccaaef134bc87b0604d163c9a5ced6ca4affb3de2
+size 167061

checkpoint-168/latest

@@ -0,0 +1 @@
+global_step168

checkpoint-168/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4cfd49ea0839e3cdf3c036166ce8cc74c6e768f2b0f07647c37cddb7d666ca6
+size 4877660776

checkpoint-168/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21ca47f177887947b4ec6bb5245680de14ab5231b6a168d01907cc8bb3dec29b
+size 4932751008

checkpoint-168/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7606962298038a8743fba57f52a2badd8f04359e4bc5990dcd9697d0a726b56
+size 4330865200

checkpoint-168/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a8068c2d7641289e6943409a862d931117fade24b219093d561f103986f8753
+size 1089994880

checkpoint-168/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

checkpoint-168/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34bcae41c589c7e4cab7b2ef263b878c90c2741404a6af11994dc31537b2319b
+size 14512

checkpoint-168/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d05dc84075e8f7dd1191c36f3be9dda12073208e12f7d2cef433c38d6336774a
+size 14512

checkpoint-168/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51a52eee3e882e21c7ac2df7614de1ba362df4493f48602000880895cdf6df39
+size 1064

checkpoint-168/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-168/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoint-168/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-168/trainer_state.json

@@ -0,0 +1,1209 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9822485207100593,
+  "eval_steps": 500,
+  "global_step": 168,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01775147928994083,
+      "grad_norm": 2.533238649368286,
+      "learning_rate": 5.882352941176471e-07,
+      "loss": 0.924,
+      "step": 1
+    },
+    {
+      "epoch": 0.03550295857988166,
+      "grad_norm": 2.927447557449341,
+      "learning_rate": 1.1764705882352942e-06,
+      "loss": 1.0731,
+      "step": 2
+    },
+    {
+      "epoch": 0.05325443786982249,
+      "grad_norm": 2.820338726043701,
+      "learning_rate": 1.7647058823529414e-06,
+      "loss": 0.9836,
+      "step": 3
+    },
+    {
+      "epoch": 0.07100591715976332,
+      "grad_norm": 2.642514228820801,
+      "learning_rate": 2.3529411764705885e-06,
+      "loss": 0.9904,
+      "step": 4
+    },
+    {
+      "epoch": 0.08875739644970414,
+      "grad_norm": 2.659113883972168,
+      "learning_rate": 2.9411764705882355e-06,
+      "loss": 0.9903,
+      "step": 5
+    },
+    {
+      "epoch": 0.10650887573964497,
+      "grad_norm": 2.257899522781372,
+      "learning_rate": 3.529411764705883e-06,
+      "loss": 0.9045,
+      "step": 6
+    },
+    {
+      "epoch": 0.1242603550295858,
+      "grad_norm": 1.839630365371704,
+      "learning_rate": 4.11764705882353e-06,
+      "loss": 0.9406,
+      "step": 7
+    },
+    {
+      "epoch": 0.14201183431952663,
+      "grad_norm": 1.631960391998291,
+      "learning_rate": 4.705882352941177e-06,
+      "loss": 0.8611,
+      "step": 8
+    },
+    {
+      "epoch": 0.15976331360946747,
+      "grad_norm": 1.4379936456680298,
+      "learning_rate": 5.294117647058824e-06,
+      "loss": 0.8991,
+      "step": 9
+    },
+    {
+      "epoch": 0.17751479289940827,
+      "grad_norm": 1.5505577325820923,
+      "learning_rate": 5.882352941176471e-06,
+      "loss": 0.9153,
+      "step": 10
+    },
+    {
+      "epoch": 0.1952662721893491,
+      "grad_norm": 1.5041471719741821,
+      "learning_rate": 6.470588235294119e-06,
+      "loss": 0.9025,
+      "step": 11
+    },
+    {
+      "epoch": 0.21301775147928995,
+      "grad_norm": 1.1657485961914062,
+      "learning_rate": 7.058823529411766e-06,
+      "loss": 0.8255,
+      "step": 12
+    },
+    {
+      "epoch": 0.23076923076923078,
+      "grad_norm": 1.60923433303833,
+      "learning_rate": 7.647058823529411e-06,
+      "loss": 0.7197,
+      "step": 13
+    },
+    {
+      "epoch": 0.2485207100591716,
+      "grad_norm": 1.6407514810562134,
+      "learning_rate": 8.23529411764706e-06,
+      "loss": 0.7522,
+      "step": 14
+    },
+    {
+      "epoch": 0.26627218934911245,
+      "grad_norm": 1.4880717992782593,
+      "learning_rate": 8.823529411764707e-06,
+      "loss": 0.7343,
+      "step": 15
+    },
+    {
+      "epoch": 0.28402366863905326,
+      "grad_norm": 1.2115110158920288,
+      "learning_rate": 9.411764705882354e-06,
+      "loss": 0.7614,
+      "step": 16
+    },
+    {
+      "epoch": 0.30177514792899407,
+      "grad_norm": 0.9123843312263489,
+      "learning_rate": 1e-05,
+      "loss": 0.6835,
+      "step": 17
+    },
+    {
+      "epoch": 0.31952662721893493,
+      "grad_norm": 1.1175857782363892,
+      "learning_rate": 9.998917893031615e-06,
+      "loss": 0.7777,
+      "step": 18
+    },
+    {
+      "epoch": 0.33727810650887574,
+      "grad_norm": 1.0061542987823486,
+      "learning_rate": 9.995672040508656e-06,
+      "loss": 0.7068,
+      "step": 19
+    },
+    {
+      "epoch": 0.35502958579881655,
+      "grad_norm": 0.8296826481819153,
+      "learning_rate": 9.990263847374976e-06,
+      "loss": 0.6594,
+      "step": 20
+    },
+    {
+      "epoch": 0.3727810650887574,
+      "grad_norm": 0.7384388446807861,
+      "learning_rate": 9.982695654527966e-06,
+      "loss": 0.6521,
+      "step": 21
+    },
+    {
+      "epoch": 0.3905325443786982,
+      "grad_norm": 0.9570622444152832,
+      "learning_rate": 9.972970737805312e-06,
+      "loss": 0.729,
+      "step": 22
+    },
+    {
+      "epoch": 0.40828402366863903,
+      "grad_norm": 0.6549481153488159,
+      "learning_rate": 9.961093306567076e-06,
+      "loss": 0.6251,
+      "step": 23
+    },
+    {
+      "epoch": 0.4260355029585799,
+      "grad_norm": 0.7221797108650208,
+      "learning_rate": 9.947068501873702e-06,
+      "loss": 0.6779,
+      "step": 24
+    },
+    {
+      "epoch": 0.4437869822485207,
+      "grad_norm": 0.6575434803962708,
+      "learning_rate": 9.930902394260746e-06,
+      "loss": 0.6849,
+      "step": 25
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 0.5789452791213989,
+      "learning_rate": 9.912601981111287e-06,
+      "loss": 0.5844,
+      "step": 26
+    },
+    {
+      "epoch": 0.47928994082840237,
+      "grad_norm": 0.6969165205955505,
+      "learning_rate": 9.892175183627161e-06,
+      "loss": 0.6698,
+      "step": 27
+    },
+    {
+      "epoch": 0.4970414201183432,
+      "grad_norm": 0.7126699686050415,
+      "learning_rate": 9.869630843400331e-06,
+      "loss": 0.6847,
+      "step": 28
+    },
+    {
+      "epoch": 0.514792899408284,
+      "grad_norm": 0.6048182845115662,
+      "learning_rate": 9.844978718585855e-06,
+      "loss": 0.6191,
+      "step": 29
+    },
+    {
+      "epoch": 0.5325443786982249,
+      "grad_norm": 0.6467904448509216,
+      "learning_rate": 9.81822947967816e-06,
+      "loss": 0.6409,
+      "step": 30
+    },
+    {
+      "epoch": 0.5502958579881657,
+      "grad_norm": 0.6857551336288452,
+      "learning_rate": 9.789394704892364e-06,
+      "loss": 0.6316,
+      "step": 31
+    },
+    {
+      "epoch": 0.5680473372781065,
+      "grad_norm": 0.7137037515640259,
+      "learning_rate": 9.758486875152766e-06,
+      "loss": 0.6325,
+      "step": 32
+    },
+    {
+      "epoch": 0.5857988165680473,
+      "grad_norm": 0.6259506940841675,
+      "learning_rate": 9.725519368690539e-06,
+      "loss": 0.6478,
+      "step": 33
+    },
+    {
+      "epoch": 0.6035502958579881,
+      "grad_norm": 0.5821611881256104,
+      "learning_rate": 9.690506455253073e-06,
+      "loss": 0.6117,
+      "step": 34
+    },
+    {
+      "epoch": 0.621301775147929,
+      "grad_norm": 0.6482532024383545,
+      "learning_rate": 9.65346328992741e-06,
+      "loss": 0.6164,
+      "step": 35
+    },
+    {
+      "epoch": 0.6390532544378699,
+      "grad_norm": 0.6187491416931152,
+      "learning_rate": 9.614405906580486e-06,
+      "loss": 0.567,
+      "step": 36
+    },
+    {
+      "epoch": 0.6568047337278107,
+      "grad_norm": 0.6659966111183167,
+      "learning_rate": 9.573351210918976e-06,
+      "loss": 0.6044,
+      "step": 37
+    },
+    {
+      "epoch": 0.6745562130177515,
+      "grad_norm": 0.6486673951148987,
+      "learning_rate": 9.53031697317178e-06,
+      "loss": 0.5811,
+      "step": 38
+    },
+    {
+      "epoch": 0.6923076923076923,
+      "grad_norm": 0.6228745579719543,
+      "learning_rate": 9.485321820398321e-06,
+      "loss": 0.6137,
+      "step": 39
+    },
+    {
+      "epoch": 0.7100591715976331,
+      "grad_norm": 0.5413960814476013,
+      "learning_rate": 9.43838522842594e-06,
+      "loss": 0.5736,
+      "step": 40
+    },
+    {
+      "epoch": 0.727810650887574,
+      "grad_norm": 0.5927128195762634,
+      "learning_rate": 9.389527513419935e-06,
+      "loss": 0.6567,
+      "step": 41
+    },
+    {
+      "epoch": 0.7455621301775148,
+      "grad_norm": 0.5900639295578003,
+      "learning_rate": 9.338769823089853e-06,
+      "loss": 0.6382,
+      "step": 42
+    },
+    {
+      "epoch": 0.7633136094674556,
+      "grad_norm": 0.6012625098228455,
+      "learning_rate": 9.286134127535859e-06,
+      "loss": 0.6525,
+      "step": 43
+    },
+    {
+      "epoch": 0.7810650887573964,
+      "grad_norm": 0.5634270906448364,
+      "learning_rate": 9.231643209739128e-06,
+      "loss": 0.5819,
+      "step": 44
+    },
+    {
+      "epoch": 0.7988165680473372,
+      "grad_norm": 0.5087092518806458,
+      "learning_rate": 9.175320655700407e-06,
+      "loss": 0.5681,
+      "step": 45
+    },
+    {
+      "epoch": 0.8165680473372781,
+      "grad_norm": 0.5246061682701111,
+      "learning_rate": 9.117190844230971e-06,
+      "loss": 0.5408,
+      "step": 46
+    },
+    {
+      "epoch": 0.834319526627219,
+      "grad_norm": 0.5206530094146729,
+      "learning_rate": 9.057278936400453e-06,
+      "loss": 0.5804,
+      "step": 47
+    },
+    {
+      "epoch": 0.8520710059171598,
+      "grad_norm": 0.5596741437911987,
+      "learning_rate": 8.99561086464603e-06,
+      "loss": 0.5521,
+      "step": 48
+    },
+    {
+      "epoch": 0.8698224852071006,
+      "grad_norm": 0.5072557330131531,
+      "learning_rate": 8.932213321547769e-06,
+      "loss": 0.5277,
+      "step": 49
+    },
+    {
+      "epoch": 0.8875739644970414,
+      "grad_norm": 0.5525227785110474,
+      "learning_rate": 8.86711374827494e-06,
+      "loss": 0.6031,
+      "step": 50
+    },
+    {
+      "epoch": 0.9053254437869822,
+      "grad_norm": 0.6006079316139221,
+      "learning_rate": 8.800340322708291e-06,
+      "loss": 0.5698,
+      "step": 51
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.5963747501373291,
+      "learning_rate": 8.73192194724347e-06,
+      "loss": 0.6289,
+      "step": 52
+    },
+    {
+      "epoch": 0.9408284023668639,
+      "grad_norm": 0.5696894526481628,
+      "learning_rate": 8.661888236280813e-06,
+      "loss": 0.5918,
+      "step": 53
+    },
+    {
+      "epoch": 0.9585798816568047,
+      "grad_norm": 0.6133765578269958,
+      "learning_rate": 8.590269503406986e-06,
+      "loss": 0.6514,
+      "step": 54
+    },
+    {
+      "epoch": 0.9763313609467456,
+      "grad_norm": 0.6414260864257812,
+      "learning_rate": 8.517096748273951e-06,
+      "loss": 0.5686,
+      "step": 55
+    },
+    {
+      "epoch": 0.9940828402366864,
+      "grad_norm": 0.6260319948196411,
+      "learning_rate": 8.442401643181e-06,
+      "loss": 0.5175,
+      "step": 56
+    },
+    {
+      "epoch": 1.0118343195266273,
+      "grad_norm": 1.199350118637085,
+      "learning_rate": 8.366216519365623e-06,
+      "loss": 0.9417,
+      "step": 57
+    },
+    {
+      "epoch": 1.029585798816568,
+      "grad_norm": 0.6130478978157043,
+      "learning_rate": 8.288574353009164e-06,
+      "loss": 0.4821,
+      "step": 58
+    },
+    {
+      "epoch": 1.047337278106509,
+      "grad_norm": 0.6134289503097534,
+      "learning_rate": 8.20950875096333e-06,
+      "loss": 0.4782,
+      "step": 59
+    },
+    {
+      "epoch": 1.0650887573964498,
+      "grad_norm": 0.7462955117225647,
+      "learning_rate": 8.129053936203688e-06,
+      "loss": 0.5882,
+      "step": 60
+    },
+    {
+      "epoch": 1.0828402366863905,
+      "grad_norm": 0.6716148257255554,
+      "learning_rate": 8.04724473301652e-06,
+      "loss": 0.5487,
+      "step": 61
+    },
+    {
+      "epoch": 1.1005917159763314,
+      "grad_norm": 0.5907769799232483,
+      "learning_rate": 7.964116551925365e-06,
+      "loss": 0.4711,
+      "step": 62
+    },
+    {
+      "epoch": 1.1183431952662721,
+      "grad_norm": 0.6688742637634277,
+      "learning_rate": 7.879705374363831e-06,
+      "loss": 0.4645,
+      "step": 63
+    },
+    {
+      "epoch": 1.136094674556213,
+      "grad_norm": 0.6526861786842346,
+      "learning_rate": 7.794047737101298e-06,
+      "loss": 0.5206,
+      "step": 64
+    },
+    {
+      "epoch": 1.1538461538461537,
+      "grad_norm": 0.5595381855964661,
+      "learning_rate": 7.707180716428237e-06,
+      "loss": 0.4313,
+      "step": 65
+    },
+    {
+      "epoch": 1.1715976331360947,
+      "grad_norm": 0.6181778311729431,
+      "learning_rate": 7.619141912108008e-06,
+      "loss": 0.564,
+      "step": 66
+    },
+    {
+      "epoch": 1.1893491124260356,
+      "grad_norm": 0.614881157875061,
+      "learning_rate": 7.529969431102063e-06,
+      "loss": 0.5041,
+      "step": 67
+    },
+    {
+      "epoch": 1.2071005917159763,
+      "grad_norm": 0.6447051763534546,
+      "learning_rate": 7.4397018710756415e-06,
+      "loss": 0.5046,
+      "step": 68
+    },
+    {
+      "epoch": 1.2248520710059172,
+      "grad_norm": 0.5753356218338013,
+      "learning_rate": 7.34837830369103e-06,
+      "loss": 0.4534,
+      "step": 69
+    },
+    {
+      "epoch": 1.242603550295858,
+      "grad_norm": 0.5938759446144104,
+      "learning_rate": 7.2560382576956875e-06,
+      "loss": 0.4369,
+      "step": 70
+    },
+    {
+      "epoch": 1.2603550295857988,
+      "grad_norm": 0.6178358793258667,
+      "learning_rate": 7.162721701812506e-06,
+      "loss": 0.4949,
+      "step": 71
+    },
+    {
+      "epoch": 1.2781065088757395,
+      "grad_norm": 0.6533629894256592,
+      "learning_rate": 7.068469027439642e-06,
+      "loss": 0.4816,
+      "step": 72
+    },
+    {
+      "epoch": 1.2958579881656804,
+      "grad_norm": 0.6626835465431213,
+      "learning_rate": 6.9733210311673826e-06,
+      "loss": 0.5976,
+      "step": 73
+    },
+    {
+      "epoch": 1.3136094674556213,
+      "grad_norm": 0.5293806195259094,
+      "learning_rate": 6.8773188971196515e-06,
+      "loss": 0.4124,
+      "step": 74
+    },
+    {
+      "epoch": 1.331360946745562,
+      "grad_norm": 0.6411221623420715,
+      "learning_rate": 6.780504179127735e-06,
+      "loss": 0.5081,
+      "step": 75
+    },
+    {
+      "epoch": 1.349112426035503,
+      "grad_norm": 0.6326239109039307,
+      "learning_rate": 6.682918782744033e-06,
+      "loss": 0.5123,
+      "step": 76
+    },
+    {
+      "epoch": 1.3668639053254439,
+      "grad_norm": 0.6738696098327637,
+      "learning_rate": 6.584604947103515e-06,
+      "loss": 0.499,
+      "step": 77
+    },
+    {
+      "epoch": 1.3846153846153846,
+      "grad_norm": 0.5083363652229309,
+      "learning_rate": 6.4856052266408375e-06,
+      "loss": 0.4522,
+      "step": 78
+    },
+    {
+      "epoch": 1.4023668639053255,
+      "grad_norm": 0.6393911838531494,
+      "learning_rate": 6.385962472670953e-06,
+      "loss": 0.4685,
+      "step": 79
+    },
+    {
+      "epoch": 1.4201183431952662,
+      "grad_norm": 0.6106072664260864,
+      "learning_rate": 6.28571981484123e-06,
+      "loss": 0.4942,
+      "step": 80
+    },
+    {
+      "epoch": 1.4378698224852071,
+      "grad_norm": 0.5104251503944397,
+      "learning_rate": 6.184920642463095e-06,
+      "loss": 0.4625,
+      "step": 81
+    },
+    {
+      "epoch": 1.4556213017751478,
+      "grad_norm": 0.587416410446167,
+      "learning_rate": 6.083608585731283e-06,
+      "loss": 0.5671,
+      "step": 82
+    },
+    {
+      "epoch": 1.4733727810650887,
+      "grad_norm": 0.5419860482215881,
+      "learning_rate": 5.9818274968388225e-06,
+      "loss": 0.516,
+      "step": 83
+    },
+    {
+      "epoch": 1.4911242603550297,
+      "grad_norm": 0.6191542744636536,
+      "learning_rate": 5.879621430995927e-06,
+      "loss": 0.4823,
+      "step": 84
+    },
+    {
+      "epoch": 1.5088757396449703,
+      "grad_norm": 0.5240432620048523,
+      "learning_rate": 5.777034627361025e-06,
+      "loss": 0.3751,
+      "step": 85
+    },
+    {
+      "epoch": 1.5266272189349113,
+      "grad_norm": 0.6388912200927734,
+      "learning_rate": 5.674111489892144e-06,
+      "loss": 0.5432,
+      "step": 86
+    },
+    {
+      "epoch": 1.5443786982248522,
+      "grad_norm": 0.6531295776367188,
+      "learning_rate": 5.570896568126994e-06,
+      "loss": 0.5527,
+      "step": 87
+    },
+    {
+      "epoch": 1.5621301775147929,
+      "grad_norm": 0.5705211758613586,
+      "learning_rate": 5.4674345379e-06,
+      "loss": 0.4588,
+      "step": 88
+    },
+    {
+      "epoch": 1.5798816568047336,
+      "grad_norm": 0.5820942521095276,
+      "learning_rate": 5.36377018200472e-06,
+      "loss": 0.4563,
+      "step": 89
+    },
+    {
+      "epoch": 1.5976331360946747,
+      "grad_norm": 0.6194245219230652,
+      "learning_rate": 5.259948370809902e-06,
+      "loss": 0.5123,
+      "step": 90
+    },
+    {
+      "epoch": 1.6153846153846154,
+      "grad_norm": 0.5981638431549072,
+      "learning_rate": 5.156014042837696e-06,
+      "loss": 0.4979,
+      "step": 91
+    },
+    {
+      "epoch": 1.6331360946745561,
+      "grad_norm": 0.7485818862915039,
+      "learning_rate": 5.052012185312322e-06,
+      "loss": 0.5863,
+      "step": 92
+    },
+    {
+      "epoch": 1.650887573964497,
+      "grad_norm": 0.5108672380447388,
+      "learning_rate": 4.94798781468768e-06,
+      "loss": 0.398,
+      "step": 93
+    },
+    {
+      "epoch": 1.668639053254438,
+      "grad_norm": 0.6520046591758728,
+      "learning_rate": 4.843985957162304e-06,
+      "loss": 0.6246,
+      "step": 94
+    },
+    {
+      "epoch": 1.6863905325443787,
+      "grad_norm": 0.4945230484008789,
+      "learning_rate": 4.740051629190099e-06,
+      "loss": 0.3286,
+      "step": 95
+    },
+    {
+      "epoch": 1.7041420118343196,
+      "grad_norm": 0.613183319568634,
+      "learning_rate": 4.636229817995281e-06,
+      "loss": 0.4692,
+      "step": 96
+    },
+    {
+      "epoch": 1.7218934911242605,
+      "grad_norm": 0.6236385107040405,
+      "learning_rate": 4.532565462099999e-06,
+      "loss": 0.5258,
+      "step": 97
+    },
+    {
+      "epoch": 1.7396449704142012,
+      "grad_norm": 0.5453357100486755,
+      "learning_rate": 4.429103431873009e-06,
+      "loss": 0.4714,
+      "step": 98
+    },
+    {
+      "epoch": 1.7573964497041419,
+      "grad_norm": 0.5440649390220642,
+      "learning_rate": 4.3258885101078565e-06,
+      "loss": 0.4571,
+      "step": 99
+    },
+    {
+      "epoch": 1.7751479289940828,
+      "grad_norm": 0.6320599913597107,
+      "learning_rate": 4.2229653726389765e-06,
+      "loss": 0.4783,
+      "step": 100
+    },
+    {
+      "epoch": 1.7928994082840237,
+      "grad_norm": 0.5469642281532288,
+      "learning_rate": 4.120378569004074e-06,
+      "loss": 0.4467,
+      "step": 101
+    },
+    {
+      "epoch": 1.8106508875739644,
+      "grad_norm": 0.5750222206115723,
+      "learning_rate": 4.018172503161179e-06,
+      "loss": 0.5032,
+      "step": 102
+    },
+    {
+      "epoch": 1.8284023668639053,
+      "grad_norm": 0.5565685629844666,
+      "learning_rate": 3.9163914142687185e-06,
+      "loss": 0.482,
+      "step": 103
+    },
+    {
+      "epoch": 1.8461538461538463,
+      "grad_norm": 0.6028342247009277,
+      "learning_rate": 3.815079357536907e-06,
+      "loss": 0.4609,
+      "step": 104
+    },
+    {
+      "epoch": 1.863905325443787,
+      "grad_norm": 0.6078227758407593,
+      "learning_rate": 3.714280185158771e-06,
+      "loss": 0.5237,
+      "step": 105
+    },
+    {
+      "epoch": 1.8816568047337277,
+      "grad_norm": 0.5719071626663208,
+      "learning_rate": 3.614037527329048e-06,
+      "loss": 0.4206,
+      "step": 106
+    },
+    {
+      "epoch": 1.8994082840236688,
+      "grad_norm": 0.5875373482704163,
+      "learning_rate": 3.5143947733591633e-06,
+      "loss": 0.4779,
+      "step": 107
+    },
+    {
+      "epoch": 1.9171597633136095,
+      "grad_norm": 0.5589243769645691,
+      "learning_rate": 3.4153950528964867e-06,
+      "loss": 0.5056,
+      "step": 108
+    },
+    {
+      "epoch": 1.9349112426035502,
+      "grad_norm": 0.5471234917640686,
+      "learning_rate": 3.3170812172559695e-06,
+      "loss": 0.4929,
+      "step": 109
+    },
+    {
+      "epoch": 1.952662721893491,
+      "grad_norm": 0.5713181495666504,
+      "learning_rate": 3.2194958208722656e-06,
+      "loss": 0.4785,
+      "step": 110
+    },
+    {
+      "epoch": 1.970414201183432,
+      "grad_norm": 0.553081750869751,
+      "learning_rate": 3.1226811028803514e-06,
+      "loss": 0.4389,
+      "step": 111
+    },
+    {
+      "epoch": 1.9881656804733727,
+      "grad_norm": 0.5729470252990723,
+      "learning_rate": 3.0266789688326187e-06,
+      "loss": 0.4665,
+      "step": 112
+    },
+    {
+      "epoch": 2.0059171597633134,
+      "grad_norm": 1.2184429168701172,
+      "learning_rate": 2.9315309725603596e-06,
+      "loss": 0.7849,
+      "step": 113
+    },
+    {
+      "epoch": 2.0236686390532546,
+      "grad_norm": 0.522588849067688,
+      "learning_rate": 2.8372782981874964e-06,
+      "loss": 0.3366,
+      "step": 114
+    },
+    {
+      "epoch": 2.0414201183431953,
+      "grad_norm": 0.6389386057853699,
+      "learning_rate": 2.7439617423043146e-06,
+      "loss": 0.4961,
+      "step": 115
+    },
+    {
+      "epoch": 2.059171597633136,
+      "grad_norm": 0.6419571042060852,
+      "learning_rate": 2.6516216963089698e-06,
+      "loss": 0.4662,
+      "step": 116
+    },
+    {
+      "epoch": 2.076923076923077,
+      "grad_norm": 0.6015217900276184,
+      "learning_rate": 2.560298128924358e-06,
+      "loss": 0.4298,
+      "step": 117
+    },
+    {
+      "epoch": 2.094674556213018,
+      "grad_norm": 0.5608621835708618,
+      "learning_rate": 2.470030568897938e-06,
+      "loss": 0.3721,
+      "step": 118
+    },
+    {
+      "epoch": 2.1124260355029585,
+      "grad_norm": 0.6403945684432983,
+      "learning_rate": 2.3808580878919948e-06,
+      "loss": 0.4947,
+      "step": 119
+    },
+    {
+      "epoch": 2.1301775147928996,
+      "grad_norm": 0.4906422793865204,
+      "learning_rate": 2.2928192835717642e-06,
+      "loss": 0.3607,
+      "step": 120
+    },
+    {
+      "epoch": 2.1479289940828403,
+      "grad_norm": 0.5612274408340454,
+      "learning_rate": 2.205952262898704e-06,
+      "loss": 0.4134,
+      "step": 121
+    },
+    {
+      "epoch": 2.165680473372781,
+      "grad_norm": 0.587371289730072,
+      "learning_rate": 2.120294625636171e-06,
+      "loss": 0.4862,
+      "step": 122
+    },
+    {
+      "epoch": 2.1834319526627217,
+      "grad_norm": 0.5207931399345398,
+      "learning_rate": 2.0358834480746363e-06,
+      "loss": 0.3613,
+      "step": 123
+    },
+    {
+      "epoch": 2.201183431952663,
+      "grad_norm": 0.6090331673622131,
+      "learning_rate": 1.9527552669834797e-06,
+      "loss": 0.4493,
+      "step": 124
+    },
+    {
+      "epoch": 2.2189349112426036,
+      "grad_norm": 0.5700682401657104,
+      "learning_rate": 1.8709460637963123e-06,
+      "loss": 0.4133,
+      "step": 125
+    },
+    {
+      "epoch": 2.2366863905325443,
+      "grad_norm": 0.4857932925224304,
+      "learning_rate": 1.7904912490366723e-06,
+      "loss": 0.3573,
+      "step": 126
+    },
+    {
+      "epoch": 2.2544378698224854,
+      "grad_norm": 0.6004585027694702,
+      "learning_rate": 1.711425646990838e-06,
+      "loss": 0.4517,
+      "step": 127
+    },
+    {
+      "epoch": 2.272189349112426,
+      "grad_norm": 0.5605913996696472,
+      "learning_rate": 1.6337834806343783e-06,
+      "loss": 0.4134,
+      "step": 128
+    },
+    {
+      "epoch": 2.289940828402367,
+      "grad_norm": 0.6110245585441589,
+      "learning_rate": 1.557598356819e-06,
+      "loss": 0.4579,
+      "step": 129
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 0.5302851796150208,
+      "learning_rate": 1.482903251726049e-06,
+      "loss": 0.3641,
+      "step": 130
+    },
+    {
+      "epoch": 2.3254437869822486,
+      "grad_norm": 0.6419249176979065,
+      "learning_rate": 1.409730496593016e-06,
+      "loss": 0.5007,
+      "step": 131
+    },
+    {
+      "epoch": 2.3431952662721893,
+      "grad_norm": 0.5336579084396362,
+      "learning_rate": 1.3381117637191887e-06,
+      "loss": 0.3433,
+      "step": 132
+    },
+    {
+      "epoch": 2.36094674556213,
+      "grad_norm": 0.5869147777557373,
+      "learning_rate": 1.2680780527565313e-06,
+      "loss": 0.4898,
+      "step": 133
+    },
+    {
+      "epoch": 2.378698224852071,
+      "grad_norm": 0.4657803475856781,
+      "learning_rate": 1.1996596772917091e-06,
+      "loss": 0.3326,
+      "step": 134
+    },
+    {
+      "epoch": 2.396449704142012,
+      "grad_norm": 0.6105607748031616,
+      "learning_rate": 1.132886251725061e-06,
+      "loss": 0.4423,
+      "step": 135
+    },
+    {
+      "epoch": 2.4142011834319526,
+      "grad_norm": 0.5837461948394775,
+      "learning_rate": 1.0677866784522317e-06,
+      "loss": 0.4593,
+      "step": 136
+    },
+    {
+      "epoch": 2.4319526627218933,
+      "grad_norm": 0.6025368571281433,
+      "learning_rate": 1.004389135353972e-06,
+      "loss": 0.4215,
+      "step": 137
+    },
+    {
+      "epoch": 2.4497041420118344,
+      "grad_norm": 0.5407091379165649,
+      "learning_rate": 9.427210635995482e-07,
+      "loss": 0.3988,
+      "step": 138
+    },
+    {
+      "epoch": 2.467455621301775,
+      "grad_norm": 0.5298522114753723,
+      "learning_rate": 8.828091557690288e-07,
+      "loss": 0.4313,
+      "step": 139
+    },
+    {
+      "epoch": 2.485207100591716,
+      "grad_norm": 0.5403129458427429,
+      "learning_rate": 8.246793442995954e-07,
+      "loss": 0.4222,
+      "step": 140
+    },
+    {
+      "epoch": 2.502958579881657,
+      "grad_norm": 0.5571721792221069,
+      "learning_rate": 7.68356790260873e-07,
+      "loss": 0.4143,
+      "step": 141
+    },
+    {
+      "epoch": 2.5207100591715976,
+      "grad_norm": 0.5758110284805298,
+      "learning_rate": 7.138658724641417e-07,
+      "loss": 0.4597,
+      "step": 142
+    },
+    {
+      "epoch": 2.5384615384615383,
+      "grad_norm": 0.5439177751541138,
+      "learning_rate": 6.612301769101464e-07,
+      "loss": 0.4078,
+      "step": 143
+    },
+    {
+      "epoch": 2.556213017751479,
+      "grad_norm": 0.6059474349021912,
+      "learning_rate": 6.104724865800665e-07,
+      "loss": 0.4234,
+      "step": 144
+    },
+    {
+      "epoch": 2.57396449704142,
+      "grad_norm": 0.5578750371932983,
+      "learning_rate": 5.616147715740611e-07,
+      "loss": 0.3722,
+      "step": 145
+    },
+    {
+      "epoch": 2.591715976331361,
+      "grad_norm": 0.5182917714118958,
+      "learning_rate": 5.146781796016798e-07,
+      "loss": 0.3592,
+      "step": 146
+    },
+    {
+      "epoch": 2.609467455621302,
+      "grad_norm": 0.5251271724700928,
+      "learning_rate": 4.696830268282204e-07,
+      "loss": 0.4132,
+      "step": 147
+    },
+    {
+      "epoch": 2.6272189349112427,
+      "grad_norm": 0.5910128951072693,
+      "learning_rate": 4.2664878908102556e-07,
+      "loss": 0.4721,
+      "step": 148
+    },
+    {
+      "epoch": 2.6449704142011834,
+      "grad_norm": 0.5311455130577087,
+      "learning_rate": 3.855940934195146e-07,
+      "loss": 0.4011,
+      "step": 149
+    },
+    {
+      "epoch": 2.662721893491124,
+      "grad_norm": 0.5455037951469421,
+      "learning_rate": 3.4653671007259084e-07,
+      "loss": 0.4317,
+      "step": 150
+    },
+    {
+      "epoch": 2.6804733727810652,
+      "grad_norm": 0.521126389503479,
+      "learning_rate": 3.0949354474692937e-07,
+      "loss": 0.4071,
+      "step": 151
+    },
+    {
+      "epoch": 2.698224852071006,
+      "grad_norm": 0.5334401726722717,
+      "learning_rate": 2.7448063130946224e-07,
+      "loss": 0.3797,
+      "step": 152
+    },
+    {
+      "epoch": 2.7159763313609466,
+      "grad_norm": 0.6030508875846863,
+      "learning_rate": 2.4151312484723465e-07,
+      "loss": 0.4331,
+      "step": 153
+    },
+    {
+      "epoch": 2.7337278106508878,
+      "grad_norm": 0.47127389907836914,
+      "learning_rate": 2.106052951076365e-07,
+      "loss": 0.3481,
+      "step": 154
+    },
+    {
+      "epoch": 2.7514792899408285,
+      "grad_norm": 0.5236401557922363,
+      "learning_rate": 1.8177052032184285e-07,
+      "loss": 0.3702,
+      "step": 155
+    },
+    {
+      "epoch": 2.769230769230769,
+      "grad_norm": 0.5896205902099609,
+      "learning_rate": 1.5502128141414496e-07,
+      "loss": 0.4371,
+      "step": 156
+    },
+    {
+      "epoch": 2.78698224852071,
+      "grad_norm": 0.5283501148223877,
+      "learning_rate": 1.303691565996712e-07,
+      "loss": 0.3741,
+      "step": 157
+    },
+    {
+      "epoch": 2.804733727810651,
+      "grad_norm": 0.5836403369903564,
+      "learning_rate": 1.0782481637284014e-07,
+      "loss": 0.4289,
+      "step": 158
+    },
+    {
+      "epoch": 2.8224852071005917,
+      "grad_norm": 0.64845210313797,
+      "learning_rate": 8.739801888871468e-08,
+      "loss": 0.4927,
+      "step": 159
+    },
+    {
+      "epoch": 2.8402366863905324,
+      "grad_norm": 0.5165106654167175,
+      "learning_rate": 6.909760573925561e-08,
+      "loss": 0.3382,
+      "step": 160
+    },
+    {
+      "epoch": 2.8579881656804735,
+      "grad_norm": 0.5744462609291077,
+      "learning_rate": 5.2931498126298495e-08,
+      "loss": 0.4541,
+      "step": 161
+    },
+    {
+      "epoch": 2.8757396449704142,
+      "grad_norm": 0.5389672517776489,
+      "learning_rate": 3.890669343292464e-08,
+      "loss": 0.4203,
+      "step": 162
+    },
+    {
+      "epoch": 2.893491124260355,
+      "grad_norm": 0.43833690881729126,
+      "learning_rate": 2.702926219468882e-08,
+      "loss": 0.3555,
+      "step": 163
+    },
+    {
+      "epoch": 2.9112426035502956,
+      "grad_norm": 0.48717668652534485,
+      "learning_rate": 1.7304345472035634e-08,
+      "loss": 0.4286,
+      "step": 164
+    },
+    {
+      "epoch": 2.9289940828402368,
+      "grad_norm": 0.5516893267631531,
+      "learning_rate": 9.73615262502503e-09,
+      "loss": 0.4472,
+      "step": 165
+    },
+    {
+      "epoch": 2.9467455621301775,
+      "grad_norm": 0.44991251826286316,
+      "learning_rate": 4.327959491344791e-09,
+      "loss": 0.3565,
+      "step": 166
+    },
+    {
+      "epoch": 2.9644970414201186,
+      "grad_norm": 0.5328838229179382,
+      "learning_rate": 1.082106968385288e-09,
+      "loss": 0.45,
+      "step": 167
+    },
+    {
+      "epoch": 2.9822485207100593,
+      "grad_norm": 0.5235728621482849,
+      "learning_rate": 0.0,
+      "loss": 0.3742,
+      "step": 168
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 168,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 600,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.46489842951127e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-168/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de6325e72c3868304d85e73b0bbb2e56d92a2ad6a528d89735ec37de3f4c440b
+size 7544

checkpoint-168/zero_to_fp32.py

@@ -0,0 +1,674 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import json
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering Sharded Weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        state_dict_split = split_torch_state_dict_into_shards(state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors}
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard, output_path)
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 4.0,
+    "original_max_position_embeddings": 32768,
+    "rope_type": "yarn",
+    "type": "yarn"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4cfd49ea0839e3cdf3c036166ce8cc74c6e768f2b0f07647c37cddb7d666ca6
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21ca47f177887947b4ec6bb5245680de14ab5231b6a168d01907cc8bb3dec29b
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7606962298038a8743fba57f52a2badd8f04359e4bc5990dcd9697d0a726b56
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a8068c2d7641289e6943409a862d931117fade24b219093d561f103986f8753
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9822485207100593,
+    "total_flos": 6.46489842951127e+16,
+    "train_loss": 0.5384191712808042,
+    "train_runtime": 12683.2217,
+    "train_samples_per_second": 0.32,
+    "train_steps_per_second": 0.013
+}

trainer_log.jsonl

@@ -0,0 +1,169 @@
+{"current_steps": 1, "total_steps": 168, "loss": 0.924, "lr": 5.882352941176471e-07, "epoch": 0.01775147928994083, "percentage": 0.6, "elapsed_time": "0:01:35", "remaining_time": "4:24:50"}
+{"current_steps": 2, "total_steps": 168, "loss": 1.0731, "lr": 1.1764705882352942e-06, "epoch": 0.03550295857988166, "percentage": 1.19, "elapsed_time": "0:02:46", "remaining_time": "3:49:52"}
+{"current_steps": 3, "total_steps": 168, "loss": 0.9836, "lr": 1.7647058823529414e-06, "epoch": 0.05325443786982249, "percentage": 1.79, "elapsed_time": "0:03:54", "remaining_time": "3:34:49"}
+{"current_steps": 4, "total_steps": 168, "loss": 0.9904, "lr": 2.3529411764705885e-06, "epoch": 0.07100591715976332, "percentage": 2.38, "elapsed_time": "0:05:05", "remaining_time": "3:28:35"}
+{"current_steps": 5, "total_steps": 168, "loss": 0.9903, "lr": 2.9411764705882355e-06, "epoch": 0.08875739644970414, "percentage": 2.98, "elapsed_time": "0:06:15", "remaining_time": "3:24:10"}
+{"current_steps": 6, "total_steps": 168, "loss": 0.9045, "lr": 3.529411764705883e-06, "epoch": 0.10650887573964497, "percentage": 3.57, "elapsed_time": "0:07:25", "remaining_time": "3:20:32"}
+{"current_steps": 7, "total_steps": 168, "loss": 0.9406, "lr": 4.11764705882353e-06, "epoch": 0.1242603550295858, "percentage": 4.17, "elapsed_time": "0:08:43", "remaining_time": "3:20:31"}
+{"current_steps": 8, "total_steps": 168, "loss": 0.8611, "lr": 4.705882352941177e-06, "epoch": 0.14201183431952663, "percentage": 4.76, "elapsed_time": "0:10:03", "remaining_time": "3:21:14"}
+{"current_steps": 9, "total_steps": 168, "loss": 0.8991, "lr": 5.294117647058824e-06, "epoch": 0.15976331360946747, "percentage": 5.36, "elapsed_time": "0:11:11", "remaining_time": "3:17:44"}
+{"current_steps": 10, "total_steps": 168, "loss": 0.9153, "lr": 5.882352941176471e-06, "epoch": 0.17751479289940827, "percentage": 5.95, "elapsed_time": "0:12:26", "remaining_time": "3:16:34"}
+{"current_steps": 11, "total_steps": 168, "loss": 0.9025, "lr": 6.470588235294119e-06, "epoch": 0.1952662721893491, "percentage": 6.55, "elapsed_time": "0:13:47", "remaining_time": "3:16:49"}
+{"current_steps": 12, "total_steps": 168, "loss": 0.8255, "lr": 7.058823529411766e-06, "epoch": 0.21301775147928995, "percentage": 7.14, "elapsed_time": "0:15:03", "remaining_time": "3:15:45"}
+{"current_steps": 13, "total_steps": 168, "loss": 0.7197, "lr": 7.647058823529411e-06, "epoch": 0.23076923076923078, "percentage": 7.74, "elapsed_time": "0:16:21", "remaining_time": "3:14:57"}
+{"current_steps": 14, "total_steps": 168, "loss": 0.7522, "lr": 8.23529411764706e-06, "epoch": 0.2485207100591716, "percentage": 8.33, "elapsed_time": "0:17:29", "remaining_time": "3:12:27"}
+{"current_steps": 15, "total_steps": 168, "loss": 0.7343, "lr": 8.823529411764707e-06, "epoch": 0.26627218934911245, "percentage": 8.93, "elapsed_time": "0:18:40", "remaining_time": "3:10:32"}
+{"current_steps": 16, "total_steps": 168, "loss": 0.7614, "lr": 9.411764705882354e-06, "epoch": 0.28402366863905326, "percentage": 9.52, "elapsed_time": "0:19:57", "remaining_time": "3:09:36"}
+{"current_steps": 17, "total_steps": 168, "loss": 0.6835, "lr": 1e-05, "epoch": 0.30177514792899407, "percentage": 10.12, "elapsed_time": "0:21:09", "remaining_time": "3:07:52"}
+{"current_steps": 18, "total_steps": 168, "loss": 0.7777, "lr": 9.998917893031615e-06, "epoch": 0.31952662721893493, "percentage": 10.71, "elapsed_time": "0:22:24", "remaining_time": "3:06:47"}
+{"current_steps": 19, "total_steps": 168, "loss": 0.7068, "lr": 9.995672040508656e-06, "epoch": 0.33727810650887574, "percentage": 11.31, "elapsed_time": "0:23:45", "remaining_time": "3:06:21"}
+{"current_steps": 20, "total_steps": 168, "loss": 0.6594, "lr": 9.990263847374976e-06, "epoch": 0.35502958579881655, "percentage": 11.9, "elapsed_time": "0:25:01", "remaining_time": "3:05:09"}
+{"current_steps": 21, "total_steps": 168, "loss": 0.6521, "lr": 9.982695654527966e-06, "epoch": 0.3727810650887574, "percentage": 12.5, "elapsed_time": "0:26:13", "remaining_time": "3:03:36"}
+{"current_steps": 22, "total_steps": 168, "loss": 0.729, "lr": 9.972970737805312e-06, "epoch": 0.3905325443786982, "percentage": 13.1, "elapsed_time": "0:27:30", "remaining_time": "3:02:31"}
+{"current_steps": 23, "total_steps": 168, "loss": 0.6251, "lr": 9.961093306567076e-06, "epoch": 0.40828402366863903, "percentage": 13.69, "elapsed_time": "0:28:48", "remaining_time": "3:01:36"}
+{"current_steps": 24, "total_steps": 168, "loss": 0.6779, "lr": 9.947068501873702e-06, "epoch": 0.4260355029585799, "percentage": 14.29, "elapsed_time": "0:30:02", "remaining_time": "3:00:17"}
+{"current_steps": 25, "total_steps": 168, "loss": 0.6849, "lr": 9.930902394260746e-06, "epoch": 0.4437869822485207, "percentage": 14.88, "elapsed_time": "0:31:24", "remaining_time": "2:59:38"}
+{"current_steps": 26, "total_steps": 168, "loss": 0.5844, "lr": 9.912601981111287e-06, "epoch": 0.46153846153846156, "percentage": 15.48, "elapsed_time": "0:32:51", "remaining_time": "2:59:25"}
+{"current_steps": 27, "total_steps": 168, "loss": 0.6698, "lr": 9.892175183627161e-06, "epoch": 0.47928994082840237, "percentage": 16.07, "elapsed_time": "0:34:09", "remaining_time": "2:58:23"}
+{"current_steps": 28, "total_steps": 168, "loss": 0.6847, "lr": 9.869630843400331e-06, "epoch": 0.4970414201183432, "percentage": 16.67, "elapsed_time": "0:35:25", "remaining_time": "2:57:08"}
+{"current_steps": 29, "total_steps": 168, "loss": 0.6191, "lr": 9.844978718585855e-06, "epoch": 0.514792899408284, "percentage": 17.26, "elapsed_time": "0:36:52", "remaining_time": "2:56:44"}
+{"current_steps": 30, "total_steps": 168, "loss": 0.6409, "lr": 9.81822947967816e-06, "epoch": 0.5325443786982249, "percentage": 17.86, "elapsed_time": "0:38:04", "remaining_time": "2:55:09"}
+{"current_steps": 31, "total_steps": 168, "loss": 0.6316, "lr": 9.789394704892364e-06, "epoch": 0.5502958579881657, "percentage": 18.45, "elapsed_time": "0:39:18", "remaining_time": "2:53:41"}
+{"current_steps": 32, "total_steps": 168, "loss": 0.6325, "lr": 9.758486875152766e-06, "epoch": 0.5680473372781065, "percentage": 19.05, "elapsed_time": "0:40:28", "remaining_time": "2:51:59"}
+{"current_steps": 33, "total_steps": 168, "loss": 0.6478, "lr": 9.725519368690539e-06, "epoch": 0.5857988165680473, "percentage": 19.64, "elapsed_time": "0:41:40", "remaining_time": "2:50:28"}
+{"current_steps": 34, "total_steps": 168, "loss": 0.6117, "lr": 9.690506455253073e-06, "epoch": 0.6035502958579881, "percentage": 20.24, "elapsed_time": "0:42:52", "remaining_time": "2:48:59"}
+{"current_steps": 35, "total_steps": 168, "loss": 0.6164, "lr": 9.65346328992741e-06, "epoch": 0.621301775147929, "percentage": 20.83, "elapsed_time": "0:44:10", "remaining_time": "2:47:51"}
+{"current_steps": 36, "total_steps": 168, "loss": 0.567, "lr": 9.614405906580486e-06, "epoch": 0.6390532544378699, "percentage": 21.43, "elapsed_time": "0:45:19", "remaining_time": "2:46:10"}
+{"current_steps": 37, "total_steps": 168, "loss": 0.6044, "lr": 9.573351210918976e-06, "epoch": 0.6568047337278107, "percentage": 22.02, "elapsed_time": "0:46:35", "remaining_time": "2:44:56"}
+{"current_steps": 38, "total_steps": 168, "loss": 0.5811, "lr": 9.53031697317178e-06, "epoch": 0.6745562130177515, "percentage": 22.62, "elapsed_time": "0:47:49", "remaining_time": "2:43:35"}
+{"current_steps": 39, "total_steps": 168, "loss": 0.6137, "lr": 9.485321820398321e-06, "epoch": 0.6923076923076923, "percentage": 23.21, "elapsed_time": "0:49:05", "remaining_time": "2:42:22"}
+{"current_steps": 40, "total_steps": 168, "loss": 0.5736, "lr": 9.43838522842594e-06, "epoch": 0.7100591715976331, "percentage": 23.81, "elapsed_time": "0:50:39", "remaining_time": "2:42:07"}
+{"current_steps": 41, "total_steps": 168, "loss": 0.6567, "lr": 9.389527513419935e-06, "epoch": 0.727810650887574, "percentage": 24.4, "elapsed_time": "0:51:51", "remaining_time": "2:40:37"}
+{"current_steps": 42, "total_steps": 168, "loss": 0.6382, "lr": 9.338769823089853e-06, "epoch": 0.7455621301775148, "percentage": 25.0, "elapsed_time": "0:53:02", "remaining_time": "2:39:07"}
+{"current_steps": 43, "total_steps": 168, "loss": 0.6525, "lr": 9.286134127535859e-06, "epoch": 0.7633136094674556, "percentage": 25.6, "elapsed_time": "0:54:10", "remaining_time": "2:37:30"}
+{"current_steps": 44, "total_steps": 168, "loss": 0.5819, "lr": 9.231643209739128e-06, "epoch": 0.7810650887573964, "percentage": 26.19, "elapsed_time": "0:55:18", "remaining_time": "2:35:52"}
+{"current_steps": 45, "total_steps": 168, "loss": 0.5681, "lr": 9.175320655700407e-06, "epoch": 0.7988165680473372, "percentage": 26.79, "elapsed_time": "0:56:37", "remaining_time": "2:34:46"}
+{"current_steps": 46, "total_steps": 168, "loss": 0.5408, "lr": 9.117190844230971e-06, "epoch": 0.8165680473372781, "percentage": 27.38, "elapsed_time": "0:58:00", "remaining_time": "2:33:50"}
+{"current_steps": 47, "total_steps": 168, "loss": 0.5804, "lr": 9.057278936400453e-06, "epoch": 0.834319526627219, "percentage": 27.98, "elapsed_time": "0:59:11", "remaining_time": "2:32:22"}
+{"current_steps": 48, "total_steps": 168, "loss": 0.5521, "lr": 8.99561086464603e-06, "epoch": 0.8520710059171598, "percentage": 28.57, "elapsed_time": "1:00:29", "remaining_time": "2:31:13"}
+{"current_steps": 49, "total_steps": 168, "loss": 0.5277, "lr": 8.932213321547769e-06, "epoch": 0.8698224852071006, "percentage": 29.17, "elapsed_time": "1:01:57", "remaining_time": "2:30:28"}
+{"current_steps": 50, "total_steps": 168, "loss": 0.6031, "lr": 8.86711374827494e-06, "epoch": 0.8875739644970414, "percentage": 29.76, "elapsed_time": "1:03:11", "remaining_time": "2:29:09"}
+{"current_steps": 51, "total_steps": 168, "loss": 0.5698, "lr": 8.800340322708291e-06, "epoch": 0.9053254437869822, "percentage": 30.36, "elapsed_time": "1:04:12", "remaining_time": "2:27:17"}
+{"current_steps": 52, "total_steps": 168, "loss": 0.6289, "lr": 8.73192194724347e-06, "epoch": 0.9230769230769231, "percentage": 30.95, "elapsed_time": "1:05:40", "remaining_time": "2:26:30"}
+{"current_steps": 53, "total_steps": 168, "loss": 0.5918, "lr": 8.661888236280813e-06, "epoch": 0.9408284023668639, "percentage": 31.55, "elapsed_time": "1:06:51", "remaining_time": "2:25:04"}
+{"current_steps": 54, "total_steps": 168, "loss": 0.6514, "lr": 8.590269503406986e-06, "epoch": 0.9585798816568047, "percentage": 32.14, "elapsed_time": "1:07:57", "remaining_time": "2:23:27"}
+{"current_steps": 55, "total_steps": 168, "loss": 0.5686, "lr": 8.517096748273951e-06, "epoch": 0.9763313609467456, "percentage": 32.74, "elapsed_time": "1:09:04", "remaining_time": "2:21:55"}
+{"current_steps": 56, "total_steps": 168, "loss": 0.5175, "lr": 8.442401643181e-06, "epoch": 0.9940828402366864, "percentage": 33.33, "elapsed_time": "1:10:10", "remaining_time": "2:20:20"}
+{"current_steps": 57, "total_steps": 168, "loss": 0.9417, "lr": 8.366216519365623e-06, "epoch": 1.0118343195266273, "percentage": 33.93, "elapsed_time": "1:11:27", "remaining_time": "2:19:08"}
+{"current_steps": 58, "total_steps": 168, "loss": 0.4821, "lr": 8.288574353009164e-06, "epoch": 1.029585798816568, "percentage": 34.52, "elapsed_time": "1:12:42", "remaining_time": "2:17:53"}
+{"current_steps": 59, "total_steps": 168, "loss": 0.4782, "lr": 8.20950875096333e-06, "epoch": 1.047337278106509, "percentage": 35.12, "elapsed_time": "1:13:54", "remaining_time": "2:16:31"}
+{"current_steps": 60, "total_steps": 168, "loss": 0.5882, "lr": 8.129053936203688e-06, "epoch": 1.0650887573964498, "percentage": 35.71, "elapsed_time": "1:15:05", "remaining_time": "2:15:10"}
+{"current_steps": 61, "total_steps": 168, "loss": 0.5487, "lr": 8.04724473301652e-06, "epoch": 1.0828402366863905, "percentage": 36.31, "elapsed_time": "1:16:24", "remaining_time": "2:14:01"}
+{"current_steps": 62, "total_steps": 168, "loss": 0.4711, "lr": 7.964116551925365e-06, "epoch": 1.1005917159763314, "percentage": 36.9, "elapsed_time": "1:17:31", "remaining_time": "2:12:33"}
+{"current_steps": 63, "total_steps": 168, "loss": 0.4645, "lr": 7.879705374363831e-06, "epoch": 1.1183431952662721, "percentage": 37.5, "elapsed_time": "1:18:30", "remaining_time": "2:10:51"}
+{"current_steps": 64, "total_steps": 168, "loss": 0.5206, "lr": 7.794047737101298e-06, "epoch": 1.136094674556213, "percentage": 38.1, "elapsed_time": "1:19:52", "remaining_time": "2:09:47"}
+{"current_steps": 65, "total_steps": 168, "loss": 0.4313, "lr": 7.707180716428237e-06, "epoch": 1.1538461538461537, "percentage": 38.69, "elapsed_time": "1:21:13", "remaining_time": "2:08:42"}
+{"current_steps": 66, "total_steps": 168, "loss": 0.564, "lr": 7.619141912108008e-06, "epoch": 1.1715976331360947, "percentage": 39.29, "elapsed_time": "1:22:28", "remaining_time": "2:07:28"}
+{"current_steps": 67, "total_steps": 168, "loss": 0.5041, "lr": 7.529969431102063e-06, "epoch": 1.1893491124260356, "percentage": 39.88, "elapsed_time": "1:23:49", "remaining_time": "2:06:22"}
+{"current_steps": 68, "total_steps": 168, "loss": 0.5046, "lr": 7.4397018710756415e-06, "epoch": 1.2071005917159763, "percentage": 40.48, "elapsed_time": "1:24:59", "remaining_time": "2:04:59"}
+{"current_steps": 69, "total_steps": 168, "loss": 0.4534, "lr": 7.34837830369103e-06, "epoch": 1.2248520710059172, "percentage": 41.07, "elapsed_time": "1:26:07", "remaining_time": "2:03:34"}
+{"current_steps": 70, "total_steps": 168, "loss": 0.4369, "lr": 7.2560382576956875e-06, "epoch": 1.242603550295858, "percentage": 41.67, "elapsed_time": "1:27:14", "remaining_time": "2:02:07"}
+{"current_steps": 71, "total_steps": 168, "loss": 0.4949, "lr": 7.162721701812506e-06, "epoch": 1.2603550295857988, "percentage": 42.26, "elapsed_time": "1:28:27", "remaining_time": "2:00:50"}
+{"current_steps": 72, "total_steps": 168, "loss": 0.4816, "lr": 7.068469027439642e-06, "epoch": 1.2781065088757395, "percentage": 42.86, "elapsed_time": "1:29:44", "remaining_time": "1:59:39"}
+{"current_steps": 73, "total_steps": 168, "loss": 0.5976, "lr": 6.9733210311673826e-06, "epoch": 1.2958579881656804, "percentage": 43.45, "elapsed_time": "1:31:09", "remaining_time": "1:58:37"}
+{"current_steps": 74, "total_steps": 168, "loss": 0.4124, "lr": 6.8773188971196515e-06, "epoch": 1.3136094674556213, "percentage": 44.05, "elapsed_time": "1:32:19", "remaining_time": "1:57:17"}
+{"current_steps": 75, "total_steps": 168, "loss": 0.5081, "lr": 6.780504179127735e-06, "epoch": 1.331360946745562, "percentage": 44.64, "elapsed_time": "1:33:39", "remaining_time": "1:56:08"}
+{"current_steps": 76, "total_steps": 168, "loss": 0.5123, "lr": 6.682918782744033e-06, "epoch": 1.349112426035503, "percentage": 45.24, "elapsed_time": "1:34:42", "remaining_time": "1:54:39"}
+{"current_steps": 77, "total_steps": 168, "loss": 0.499, "lr": 6.584604947103515e-06, "epoch": 1.3668639053254439, "percentage": 45.83, "elapsed_time": "1:35:54", "remaining_time": "1:53:20"}
+{"current_steps": 78, "total_steps": 168, "loss": 0.4522, "lr": 6.4856052266408375e-06, "epoch": 1.3846153846153846, "percentage": 46.43, "elapsed_time": "1:37:09", "remaining_time": "1:52:05"}
+{"current_steps": 79, "total_steps": 168, "loss": 0.4685, "lr": 6.385962472670953e-06, "epoch": 1.4023668639053255, "percentage": 47.02, "elapsed_time": "1:38:27", "remaining_time": "1:50:54"}
+{"current_steps": 80, "total_steps": 168, "loss": 0.4942, "lr": 6.28571981484123e-06, "epoch": 1.4201183431952662, "percentage": 47.62, "elapsed_time": "1:39:43", "remaining_time": "1:49:42"}
+{"current_steps": 81, "total_steps": 168, "loss": 0.4625, "lr": 6.184920642463095e-06, "epoch": 1.4378698224852071, "percentage": 48.21, "elapsed_time": "1:40:56", "remaining_time": "1:48:24"}
+{"current_steps": 82, "total_steps": 168, "loss": 0.5671, "lr": 6.083608585731283e-06, "epoch": 1.4556213017751478, "percentage": 48.81, "elapsed_time": "1:42:23", "remaining_time": "1:47:23"}
+{"current_steps": 83, "total_steps": 168, "loss": 0.516, "lr": 5.9818274968388225e-06, "epoch": 1.4733727810650887, "percentage": 49.4, "elapsed_time": "1:43:35", "remaining_time": "1:46:05"}
+{"current_steps": 84, "total_steps": 168, "loss": 0.4823, "lr": 5.879621430995927e-06, "epoch": 1.4911242603550297, "percentage": 50.0, "elapsed_time": "1:44:48", "remaining_time": "1:44:48"}
+{"current_steps": 85, "total_steps": 168, "loss": 0.3751, "lr": 5.777034627361025e-06, "epoch": 1.5088757396449703, "percentage": 50.6, "elapsed_time": "1:45:54", "remaining_time": "1:43:24"}
+{"current_steps": 86, "total_steps": 168, "loss": 0.5432, "lr": 5.674111489892144e-06, "epoch": 1.5266272189349113, "percentage": 51.19, "elapsed_time": "1:47:22", "remaining_time": "1:42:23"}
+{"current_steps": 87, "total_steps": 168, "loss": 0.5527, "lr": 5.570896568126994e-06, "epoch": 1.5443786982248522, "percentage": 51.79, "elapsed_time": "1:48:29", "remaining_time": "1:41:00"}
+{"current_steps": 88, "total_steps": 168, "loss": 0.4588, "lr": 5.4674345379e-06, "epoch": 1.5621301775147929, "percentage": 52.38, "elapsed_time": "1:49:36", "remaining_time": "1:39:38"}
+{"current_steps": 89, "total_steps": 168, "loss": 0.4563, "lr": 5.36377018200472e-06, "epoch": 1.5798816568047336, "percentage": 52.98, "elapsed_time": "1:50:40", "remaining_time": "1:38:14"}
+{"current_steps": 90, "total_steps": 168, "loss": 0.5123, "lr": 5.259948370809902e-06, "epoch": 1.5976331360946747, "percentage": 53.57, "elapsed_time": "1:51:54", "remaining_time": "1:36:59"}
+{"current_steps": 91, "total_steps": 168, "loss": 0.4979, "lr": 5.156014042837696e-06, "epoch": 1.6153846153846154, "percentage": 54.17, "elapsed_time": "1:53:05", "remaining_time": "1:35:41"}
+{"current_steps": 92, "total_steps": 168, "loss": 0.5863, "lr": 5.052012185312322e-06, "epoch": 1.6331360946745561, "percentage": 54.76, "elapsed_time": "1:54:24", "remaining_time": "1:34:30"}
+{"current_steps": 93, "total_steps": 168, "loss": 0.398, "lr": 4.94798781468768e-06, "epoch": 1.650887573964497, "percentage": 55.36, "elapsed_time": "1:55:37", "remaining_time": "1:33:15"}
+{"current_steps": 94, "total_steps": 168, "loss": 0.6246, "lr": 4.843985957162304e-06, "epoch": 1.668639053254438, "percentage": 55.95, "elapsed_time": "1:57:02", "remaining_time": "1:32:08"}
+{"current_steps": 95, "total_steps": 168, "loss": 0.3286, "lr": 4.740051629190099e-06, "epoch": 1.6863905325443787, "percentage": 56.55, "elapsed_time": "1:58:09", "remaining_time": "1:30:47"}
+{"current_steps": 96, "total_steps": 168, "loss": 0.4692, "lr": 4.636229817995281e-06, "epoch": 1.7041420118343196, "percentage": 57.14, "elapsed_time": "1:59:16", "remaining_time": "1:29:27"}
+{"current_steps": 97, "total_steps": 168, "loss": 0.5258, "lr": 4.532565462099999e-06, "epoch": 1.7218934911242605, "percentage": 57.74, "elapsed_time": "2:00:29", "remaining_time": "1:28:12"}
+{"current_steps": 98, "total_steps": 168, "loss": 0.4714, "lr": 4.429103431873009e-06, "epoch": 1.7396449704142012, "percentage": 58.33, "elapsed_time": "2:01:59", "remaining_time": "1:27:07"}
+{"current_steps": 99, "total_steps": 168, "loss": 0.4571, "lr": 4.3258885101078565e-06, "epoch": 1.7573964497041419, "percentage": 58.93, "elapsed_time": "2:03:14", "remaining_time": "1:25:53"}
+{"current_steps": 100, "total_steps": 168, "loss": 0.4783, "lr": 4.2229653726389765e-06, "epoch": 1.7751479289940828, "percentage": 59.52, "elapsed_time": "2:04:25", "remaining_time": "1:24:36"}
+{"current_steps": 101, "total_steps": 168, "loss": 0.4467, "lr": 4.120378569004074e-06, "epoch": 1.7928994082840237, "percentage": 60.12, "elapsed_time": "2:05:44", "remaining_time": "1:23:24"}
+{"current_steps": 102, "total_steps": 168, "loss": 0.5032, "lr": 4.018172503161179e-06, "epoch": 1.8106508875739644, "percentage": 60.71, "elapsed_time": "2:07:14", "remaining_time": "1:22:20"}
+{"current_steps": 103, "total_steps": 168, "loss": 0.482, "lr": 3.9163914142687185e-06, "epoch": 1.8284023668639053, "percentage": 61.31, "elapsed_time": "2:08:36", "remaining_time": "1:21:09"}
+{"current_steps": 104, "total_steps": 168, "loss": 0.4609, "lr": 3.815079357536907e-06, "epoch": 1.8461538461538463, "percentage": 61.9, "elapsed_time": "2:09:46", "remaining_time": "1:19:51"}
+{"current_steps": 105, "total_steps": 168, "loss": 0.5237, "lr": 3.714280185158771e-06, "epoch": 1.863905325443787, "percentage": 62.5, "elapsed_time": "2:11:03", "remaining_time": "1:18:38"}
+{"current_steps": 106, "total_steps": 168, "loss": 0.4206, "lr": 3.614037527329048e-06, "epoch": 1.8816568047337277, "percentage": 63.1, "elapsed_time": "2:12:13", "remaining_time": "1:17:20"}
+{"current_steps": 107, "total_steps": 168, "loss": 0.4779, "lr": 3.5143947733591633e-06, "epoch": 1.8994082840236688, "percentage": 63.69, "elapsed_time": "2:13:27", "remaining_time": "1:16:05"}
+{"current_steps": 108, "total_steps": 168, "loss": 0.5056, "lr": 3.4153950528964867e-06, "epoch": 1.9171597633136095, "percentage": 64.29, "elapsed_time": "2:14:46", "remaining_time": "1:14:52"}
+{"current_steps": 109, "total_steps": 168, "loss": 0.4929, "lr": 3.3170812172559695e-06, "epoch": 1.9349112426035502, "percentage": 64.88, "elapsed_time": "2:16:04", "remaining_time": "1:13:39"}
+{"current_steps": 110, "total_steps": 168, "loss": 0.4785, "lr": 3.2194958208722656e-06, "epoch": 1.952662721893491, "percentage": 65.48, "elapsed_time": "2:17:24", "remaining_time": "1:12:26"}
+{"current_steps": 111, "total_steps": 168, "loss": 0.4389, "lr": 3.1226811028803514e-06, "epoch": 1.970414201183432, "percentage": 66.07, "elapsed_time": "2:18:31", "remaining_time": "1:11:08"}
+{"current_steps": 112, "total_steps": 168, "loss": 0.4665, "lr": 3.0266789688326187e-06, "epoch": 1.9881656804733727, "percentage": 66.67, "elapsed_time": "2:19:47", "remaining_time": "1:09:53"}
+{"current_steps": 113, "total_steps": 168, "loss": 0.7849, "lr": 2.9315309725603596e-06, "epoch": 2.0059171597633134, "percentage": 67.26, "elapsed_time": "2:21:02", "remaining_time": "1:08:38"}
+{"current_steps": 114, "total_steps": 168, "loss": 0.3366, "lr": 2.8372782981874964e-06, "epoch": 2.0236686390532546, "percentage": 67.86, "elapsed_time": "2:22:08", "remaining_time": "1:07:20"}
+{"current_steps": 115, "total_steps": 168, "loss": 0.4961, "lr": 2.7439617423043146e-06, "epoch": 2.0414201183431953, "percentage": 68.45, "elapsed_time": "2:23:30", "remaining_time": "1:06:08"}
+{"current_steps": 116, "total_steps": 168, "loss": 0.4662, "lr": 2.6516216963089698e-06, "epoch": 2.059171597633136, "percentage": 69.05, "elapsed_time": "2:24:40", "remaining_time": "1:04:51"}
+{"current_steps": 117, "total_steps": 168, "loss": 0.4298, "lr": 2.560298128924358e-06, "epoch": 2.076923076923077, "percentage": 69.64, "elapsed_time": "2:25:56", "remaining_time": "1:03:37"}
+{"current_steps": 118, "total_steps": 168, "loss": 0.3721, "lr": 2.470030568897938e-06, "epoch": 2.094674556213018, "percentage": 70.24, "elapsed_time": "2:27:07", "remaining_time": "1:02:20"}
+{"current_steps": 119, "total_steps": 168, "loss": 0.4947, "lr": 2.3808580878919948e-06, "epoch": 2.1124260355029585, "percentage": 70.83, "elapsed_time": "2:28:29", "remaining_time": "1:01:08"}
+{"current_steps": 120, "total_steps": 168, "loss": 0.3607, "lr": 2.2928192835717642e-06, "epoch": 2.1301775147928996, "percentage": 71.43, "elapsed_time": "2:29:47", "remaining_time": "0:59:54"}
+{"current_steps": 121, "total_steps": 168, "loss": 0.4134, "lr": 2.205952262898704e-06, "epoch": 2.1479289940828403, "percentage": 72.02, "elapsed_time": "2:30:58", "remaining_time": "0:58:38"}
+{"current_steps": 122, "total_steps": 168, "loss": 0.4862, "lr": 2.120294625636171e-06, "epoch": 2.165680473372781, "percentage": 72.62, "elapsed_time": "2:32:26", "remaining_time": "0:57:28"}
+{"current_steps": 123, "total_steps": 168, "loss": 0.3613, "lr": 2.0358834480746363e-06, "epoch": 2.1834319526627217, "percentage": 73.21, "elapsed_time": "2:33:40", "remaining_time": "0:56:13"}
+{"current_steps": 124, "total_steps": 168, "loss": 0.4493, "lr": 1.9527552669834797e-06, "epoch": 2.201183431952663, "percentage": 73.81, "elapsed_time": "2:35:05", "remaining_time": "0:55:01"}
+{"current_steps": 125, "total_steps": 168, "loss": 0.4133, "lr": 1.8709460637963123e-06, "epoch": 2.2189349112426036, "percentage": 74.4, "elapsed_time": "2:36:20", "remaining_time": "0:53:47"}
+{"current_steps": 126, "total_steps": 168, "loss": 0.3573, "lr": 1.7904912490366723e-06, "epoch": 2.2366863905325443, "percentage": 75.0, "elapsed_time": "2:37:49", "remaining_time": "0:52:36"}
+{"current_steps": 127, "total_steps": 168, "loss": 0.4517, "lr": 1.711425646990838e-06, "epoch": 2.2544378698224854, "percentage": 75.6, "elapsed_time": "2:39:07", "remaining_time": "0:51:22"}
+{"current_steps": 128, "total_steps": 168, "loss": 0.4134, "lr": 1.6337834806343783e-06, "epoch": 2.272189349112426, "percentage": 76.19, "elapsed_time": "2:40:26", "remaining_time": "0:50:08"}
+{"current_steps": 129, "total_steps": 168, "loss": 0.4579, "lr": 1.557598356819e-06, "epoch": 2.289940828402367, "percentage": 76.79, "elapsed_time": "2:41:38", "remaining_time": "0:48:52"}
+{"current_steps": 130, "total_steps": 168, "loss": 0.3641, "lr": 1.482903251726049e-06, "epoch": 2.3076923076923075, "percentage": 77.38, "elapsed_time": "2:42:43", "remaining_time": "0:47:34"}
+{"current_steps": 131, "total_steps": 168, "loss": 0.5007, "lr": 1.409730496593016e-06, "epoch": 2.3254437869822486, "percentage": 77.98, "elapsed_time": "2:44:01", "remaining_time": "0:46:19"}
+{"current_steps": 132, "total_steps": 168, "loss": 0.3433, "lr": 1.3381117637191887e-06, "epoch": 2.3431952662721893, "percentage": 78.57, "elapsed_time": "2:45:12", "remaining_time": "0:45:03"}
+{"current_steps": 133, "total_steps": 168, "loss": 0.4898, "lr": 1.2680780527565313e-06, "epoch": 2.36094674556213, "percentage": 79.17, "elapsed_time": "2:46:28", "remaining_time": "0:43:48"}
+{"current_steps": 134, "total_steps": 168, "loss": 0.3326, "lr": 1.1996596772917091e-06, "epoch": 2.378698224852071, "percentage": 79.76, "elapsed_time": "2:47:38", "remaining_time": "0:42:32"}
+{"current_steps": 135, "total_steps": 168, "loss": 0.4423, "lr": 1.132886251725061e-06, "epoch": 2.396449704142012, "percentage": 80.36, "elapsed_time": "2:48:42", "remaining_time": "0:41:14"}
+{"current_steps": 136, "total_steps": 168, "loss": 0.4593, "lr": 1.0677866784522317e-06, "epoch": 2.4142011834319526, "percentage": 80.95, "elapsed_time": "2:49:56", "remaining_time": "0:39:59"}
+{"current_steps": 137, "total_steps": 168, "loss": 0.4215, "lr": 1.004389135353972e-06, "epoch": 2.4319526627218933, "percentage": 81.55, "elapsed_time": "2:51:01", "remaining_time": "0:38:41"}
+{"current_steps": 138, "total_steps": 168, "loss": 0.3988, "lr": 9.427210635995482e-07, "epoch": 2.4497041420118344, "percentage": 82.14, "elapsed_time": "2:52:15", "remaining_time": "0:37:26"}
+{"current_steps": 139, "total_steps": 168, "loss": 0.4313, "lr": 8.828091557690288e-07, "epoch": 2.467455621301775, "percentage": 82.74, "elapsed_time": "2:53:37", "remaining_time": "0:36:13"}
+{"current_steps": 140, "total_steps": 168, "loss": 0.4222, "lr": 8.246793442995954e-07, "epoch": 2.485207100591716, "percentage": 83.33, "elapsed_time": "2:54:51", "remaining_time": "0:34:58"}
+{"current_steps": 141, "total_steps": 168, "loss": 0.4143, "lr": 7.68356790260873e-07, "epoch": 2.502958579881657, "percentage": 83.93, "elapsed_time": "2:56:09", "remaining_time": "0:33:44"}
+{"current_steps": 142, "total_steps": 168, "loss": 0.4597, "lr": 7.138658724641417e-07, "epoch": 2.5207100591715976, "percentage": 84.52, "elapsed_time": "2:57:32", "remaining_time": "0:32:30"}
+{"current_steps": 143, "total_steps": 168, "loss": 0.4078, "lr": 6.612301769101464e-07, "epoch": 2.5384615384615383, "percentage": 85.12, "elapsed_time": "2:58:44", "remaining_time": "0:31:14"}
+{"current_steps": 144, "total_steps": 168, "loss": 0.4234, "lr": 6.104724865800665e-07, "epoch": 2.556213017751479, "percentage": 85.71, "elapsed_time": "2:59:53", "remaining_time": "0:29:58"}
+{"current_steps": 145, "total_steps": 168, "loss": 0.3722, "lr": 5.616147715740611e-07, "epoch": 2.57396449704142, "percentage": 86.31, "elapsed_time": "3:00:53", "remaining_time": "0:28:41"}
+{"current_steps": 146, "total_steps": 168, "loss": 0.3592, "lr": 5.146781796016798e-07, "epoch": 2.591715976331361, "percentage": 86.9, "elapsed_time": "3:01:57", "remaining_time": "0:27:25"}
+{"current_steps": 147, "total_steps": 168, "loss": 0.4132, "lr": 4.696830268282204e-07, "epoch": 2.609467455621302, "percentage": 87.5, "elapsed_time": "3:03:09", "remaining_time": "0:26:09"}
+{"current_steps": 148, "total_steps": 168, "loss": 0.4721, "lr": 4.2664878908102556e-07, "epoch": 2.6272189349112427, "percentage": 88.1, "elapsed_time": "3:04:26", "remaining_time": "0:24:55"}
+{"current_steps": 149, "total_steps": 168, "loss": 0.4011, "lr": 3.855940934195146e-07, "epoch": 2.6449704142011834, "percentage": 88.69, "elapsed_time": "3:05:31", "remaining_time": "0:23:39"}
+{"current_steps": 150, "total_steps": 168, "loss": 0.4317, "lr": 3.4653671007259084e-07, "epoch": 2.662721893491124, "percentage": 89.29, "elapsed_time": "3:06:52", "remaining_time": "0:22:25"}
+{"current_steps": 151, "total_steps": 168, "loss": 0.4071, "lr": 3.0949354474692937e-07, "epoch": 2.6804733727810652, "percentage": 89.88, "elapsed_time": "3:08:15", "remaining_time": "0:21:11"}
+{"current_steps": 152, "total_steps": 168, "loss": 0.3797, "lr": 2.7448063130946224e-07, "epoch": 2.698224852071006, "percentage": 90.48, "elapsed_time": "3:09:22", "remaining_time": "0:19:56"}
+{"current_steps": 153, "total_steps": 168, "loss": 0.4331, "lr": 2.4151312484723465e-07, "epoch": 2.7159763313609466, "percentage": 91.07, "elapsed_time": "3:10:37", "remaining_time": "0:18:41"}
+{"current_steps": 154, "total_steps": 168, "loss": 0.3481, "lr": 2.106052951076365e-07, "epoch": 2.7337278106508878, "percentage": 91.67, "elapsed_time": "3:11:50", "remaining_time": "0:17:26"}
+{"current_steps": 155, "total_steps": 168, "loss": 0.3702, "lr": 1.8177052032184285e-07, "epoch": 2.7514792899408285, "percentage": 92.26, "elapsed_time": "3:13:09", "remaining_time": "0:16:12"}
+{"current_steps": 156, "total_steps": 168, "loss": 0.4371, "lr": 1.5502128141414496e-07, "epoch": 2.769230769230769, "percentage": 92.86, "elapsed_time": "3:14:19", "remaining_time": "0:14:56"}
+{"current_steps": 157, "total_steps": 168, "loss": 0.3741, "lr": 1.303691565996712e-07, "epoch": 2.78698224852071, "percentage": 93.45, "elapsed_time": "3:15:27", "remaining_time": "0:13:41"}
+{"current_steps": 158, "total_steps": 168, "loss": 0.4289, "lr": 1.0782481637284014e-07, "epoch": 2.804733727810651, "percentage": 94.05, "elapsed_time": "3:16:42", "remaining_time": "0:12:26"}
+{"current_steps": 159, "total_steps": 168, "loss": 0.4927, "lr": 8.739801888871468e-08, "epoch": 2.8224852071005917, "percentage": 94.64, "elapsed_time": "3:17:59", "remaining_time": "0:11:12"}
+{"current_steps": 160, "total_steps": 168, "loss": 0.3382, "lr": 6.909760573925561e-08, "epoch": 2.8402366863905324, "percentage": 95.24, "elapsed_time": "3:19:17", "remaining_time": "0:09:57"}
+{"current_steps": 161, "total_steps": 168, "loss": 0.4541, "lr": 5.2931498126298495e-08, "epoch": 2.8579881656804735, "percentage": 95.83, "elapsed_time": "3:20:39", "remaining_time": "0:08:43"}
+{"current_steps": 162, "total_steps": 168, "loss": 0.4203, "lr": 3.890669343292464e-08, "epoch": 2.8757396449704142, "percentage": 96.43, "elapsed_time": "3:21:52", "remaining_time": "0:07:28"}
+{"current_steps": 163, "total_steps": 168, "loss": 0.3555, "lr": 2.702926219468882e-08, "epoch": 2.893491124260355, "percentage": 97.02, "elapsed_time": "3:23:15", "remaining_time": "0:06:14"}
+{"current_steps": 164, "total_steps": 168, "loss": 0.4286, "lr": 1.7304345472035634e-08, "epoch": 2.9112426035502956, "percentage": 97.62, "elapsed_time": "3:24:35", "remaining_time": "0:04:59"}
+{"current_steps": 165, "total_steps": 168, "loss": 0.4472, "lr": 9.73615262502503e-09, "epoch": 2.9289940828402368, "percentage": 98.21, "elapsed_time": "3:25:52", "remaining_time": "0:03:44"}
+{"current_steps": 166, "total_steps": 168, "loss": 0.3565, "lr": 4.327959491344791e-09, "epoch": 2.9467455621301775, "percentage": 98.81, "elapsed_time": "3:27:08", "remaining_time": "0:02:29"}
+{"current_steps": 167, "total_steps": 168, "loss": 0.45, "lr": 1.082106968385288e-09, "epoch": 2.9644970414201186, "percentage": 99.4, "elapsed_time": "3:28:28", "remaining_time": "0:01:14"}
+{"current_steps": 168, "total_steps": 168, "loss": 0.3742, "lr": 0.0, "epoch": 2.9822485207100593, "percentage": 100.0, "elapsed_time": "3:29:35", "remaining_time": "0:00:00"}
+{"current_steps": 168, "total_steps": 168, "epoch": 2.9822485207100593, "percentage": 100.0, "elapsed_time": "3:31:22", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1218 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9822485207100593,
+  "eval_steps": 500,
+  "global_step": 168,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01775147928994083,
+      "grad_norm": 2.533238649368286,
+      "learning_rate": 5.882352941176471e-07,
+      "loss": 0.924,
+      "step": 1
+    },
+    {
+      "epoch": 0.03550295857988166,
+      "grad_norm": 2.927447557449341,
+      "learning_rate": 1.1764705882352942e-06,
+      "loss": 1.0731,
+      "step": 2
+    },
+    {
+      "epoch": 0.05325443786982249,
+      "grad_norm": 2.820338726043701,
+      "learning_rate": 1.7647058823529414e-06,
+      "loss": 0.9836,
+      "step": 3
+    },
+    {
+      "epoch": 0.07100591715976332,
+      "grad_norm": 2.642514228820801,
+      "learning_rate": 2.3529411764705885e-06,
+      "loss": 0.9904,
+      "step": 4
+    },
+    {
+      "epoch": 0.08875739644970414,
+      "grad_norm": 2.659113883972168,
+      "learning_rate": 2.9411764705882355e-06,
+      "loss": 0.9903,
+      "step": 5
+    },
+    {
+      "epoch": 0.10650887573964497,
+      "grad_norm": 2.257899522781372,
+      "learning_rate": 3.529411764705883e-06,
+      "loss": 0.9045,
+      "step": 6
+    },
+    {
+      "epoch": 0.1242603550295858,
+      "grad_norm": 1.839630365371704,
+      "learning_rate": 4.11764705882353e-06,
+      "loss": 0.9406,
+      "step": 7
+    },
+    {
+      "epoch": 0.14201183431952663,
+      "grad_norm": 1.631960391998291,
+      "learning_rate": 4.705882352941177e-06,
+      "loss": 0.8611,
+      "step": 8
+    },
+    {
+      "epoch": 0.15976331360946747,
+      "grad_norm": 1.4379936456680298,
+      "learning_rate": 5.294117647058824e-06,
+      "loss": 0.8991,
+      "step": 9
+    },
+    {
+      "epoch": 0.17751479289940827,
+      "grad_norm": 1.5505577325820923,
+      "learning_rate": 5.882352941176471e-06,
+      "loss": 0.9153,
+      "step": 10
+    },
+    {
+      "epoch": 0.1952662721893491,
+      "grad_norm": 1.5041471719741821,
+      "learning_rate": 6.470588235294119e-06,
+      "loss": 0.9025,
+      "step": 11
+    },
+    {
+      "epoch": 0.21301775147928995,
+      "grad_norm": 1.1657485961914062,
+      "learning_rate": 7.058823529411766e-06,
+      "loss": 0.8255,
+      "step": 12
+    },
+    {
+      "epoch": 0.23076923076923078,
+      "grad_norm": 1.60923433303833,
+      "learning_rate": 7.647058823529411e-06,
+      "loss": 0.7197,
+      "step": 13
+    },
+    {
+      "epoch": 0.2485207100591716,
+      "grad_norm": 1.6407514810562134,
+      "learning_rate": 8.23529411764706e-06,
+      "loss": 0.7522,
+      "step": 14
+    },
+    {
+      "epoch": 0.26627218934911245,
+      "grad_norm": 1.4880717992782593,
+      "learning_rate": 8.823529411764707e-06,
+      "loss": 0.7343,
+      "step": 15
+    },
+    {
+      "epoch": 0.28402366863905326,
+      "grad_norm": 1.2115110158920288,
+      "learning_rate": 9.411764705882354e-06,
+      "loss": 0.7614,
+      "step": 16
+    },
+    {
+      "epoch": 0.30177514792899407,
+      "grad_norm": 0.9123843312263489,
+      "learning_rate": 1e-05,
+      "loss": 0.6835,
+      "step": 17
+    },
+    {
+      "epoch": 0.31952662721893493,
+      "grad_norm": 1.1175857782363892,
+      "learning_rate": 9.998917893031615e-06,
+      "loss": 0.7777,
+      "step": 18
+    },
+    {
+      "epoch": 0.33727810650887574,
+      "grad_norm": 1.0061542987823486,
+      "learning_rate": 9.995672040508656e-06,
+      "loss": 0.7068,
+      "step": 19
+    },
+    {
+      "epoch": 0.35502958579881655,
+      "grad_norm": 0.8296826481819153,
+      "learning_rate": 9.990263847374976e-06,
+      "loss": 0.6594,
+      "step": 20
+    },
+    {
+      "epoch": 0.3727810650887574,
+      "grad_norm": 0.7384388446807861,
+      "learning_rate": 9.982695654527966e-06,
+      "loss": 0.6521,
+      "step": 21
+    },
+    {
+      "epoch": 0.3905325443786982,
+      "grad_norm": 0.9570622444152832,
+      "learning_rate": 9.972970737805312e-06,
+      "loss": 0.729,
+      "step": 22
+    },
+    {
+      "epoch": 0.40828402366863903,
+      "grad_norm": 0.6549481153488159,
+      "learning_rate": 9.961093306567076e-06,
+      "loss": 0.6251,
+      "step": 23
+    },
+    {
+      "epoch": 0.4260355029585799,
+      "grad_norm": 0.7221797108650208,
+      "learning_rate": 9.947068501873702e-06,
+      "loss": 0.6779,
+      "step": 24
+    },
+    {
+      "epoch": 0.4437869822485207,
+      "grad_norm": 0.6575434803962708,
+      "learning_rate": 9.930902394260746e-06,
+      "loss": 0.6849,
+      "step": 25
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 0.5789452791213989,
+      "learning_rate": 9.912601981111287e-06,
+      "loss": 0.5844,
+      "step": 26
+    },
+    {
+      "epoch": 0.47928994082840237,
+      "grad_norm": 0.6969165205955505,
+      "learning_rate": 9.892175183627161e-06,
+      "loss": 0.6698,
+      "step": 27
+    },
+    {
+      "epoch": 0.4970414201183432,
+      "grad_norm": 0.7126699686050415,
+      "learning_rate": 9.869630843400331e-06,
+      "loss": 0.6847,
+      "step": 28
+    },
+    {
+      "epoch": 0.514792899408284,
+      "grad_norm": 0.6048182845115662,
+      "learning_rate": 9.844978718585855e-06,
+      "loss": 0.6191,
+      "step": 29
+    },
+    {
+      "epoch": 0.5325443786982249,
+      "grad_norm": 0.6467904448509216,
+      "learning_rate": 9.81822947967816e-06,
+      "loss": 0.6409,
+      "step": 30
+    },
+    {
+      "epoch": 0.5502958579881657,
+      "grad_norm": 0.6857551336288452,
+      "learning_rate": 9.789394704892364e-06,
+      "loss": 0.6316,
+      "step": 31
+    },
+    {
+      "epoch": 0.5680473372781065,
+      "grad_norm": 0.7137037515640259,
+      "learning_rate": 9.758486875152766e-06,
+      "loss": 0.6325,
+      "step": 32
+    },
+    {
+      "epoch": 0.5857988165680473,
+      "grad_norm": 0.6259506940841675,
+      "learning_rate": 9.725519368690539e-06,
+      "loss": 0.6478,
+      "step": 33
+    },
+    {
+      "epoch": 0.6035502958579881,
+      "grad_norm": 0.5821611881256104,
+      "learning_rate": 9.690506455253073e-06,
+      "loss": 0.6117,
+      "step": 34
+    },
+    {
+      "epoch": 0.621301775147929,
+      "grad_norm": 0.6482532024383545,
+      "learning_rate": 9.65346328992741e-06,
+      "loss": 0.6164,
+      "step": 35
+    },
+    {
+      "epoch": 0.6390532544378699,
+      "grad_norm": 0.6187491416931152,
+      "learning_rate": 9.614405906580486e-06,
+      "loss": 0.567,
+      "step": 36
+    },
+    {
+      "epoch": 0.6568047337278107,
+      "grad_norm": 0.6659966111183167,
+      "learning_rate": 9.573351210918976e-06,
+      "loss": 0.6044,
+      "step": 37
+    },
+    {
+      "epoch": 0.6745562130177515,
+      "grad_norm": 0.6486673951148987,
+      "learning_rate": 9.53031697317178e-06,
+      "loss": 0.5811,
+      "step": 38
+    },
+    {
+      "epoch": 0.6923076923076923,
+      "grad_norm": 0.6228745579719543,
+      "learning_rate": 9.485321820398321e-06,
+      "loss": 0.6137,
+      "step": 39
+    },
+    {
+      "epoch": 0.7100591715976331,
+      "grad_norm": 0.5413960814476013,
+      "learning_rate": 9.43838522842594e-06,
+      "loss": 0.5736,
+      "step": 40
+    },
+    {
+      "epoch": 0.727810650887574,
+      "grad_norm": 0.5927128195762634,
+      "learning_rate": 9.389527513419935e-06,
+      "loss": 0.6567,
+      "step": 41
+    },
+    {
+      "epoch": 0.7455621301775148,
+      "grad_norm": 0.5900639295578003,
+      "learning_rate": 9.338769823089853e-06,
+      "loss": 0.6382,
+      "step": 42
+    },
+    {
+      "epoch": 0.7633136094674556,
+      "grad_norm": 0.6012625098228455,
+      "learning_rate": 9.286134127535859e-06,
+      "loss": 0.6525,
+      "step": 43
+    },
+    {
+      "epoch": 0.7810650887573964,
+      "grad_norm": 0.5634270906448364,
+      "learning_rate": 9.231643209739128e-06,
+      "loss": 0.5819,
+      "step": 44
+    },
+    {
+      "epoch": 0.7988165680473372,
+      "grad_norm": 0.5087092518806458,
+      "learning_rate": 9.175320655700407e-06,
+      "loss": 0.5681,
+      "step": 45
+    },
+    {
+      "epoch": 0.8165680473372781,
+      "grad_norm": 0.5246061682701111,
+      "learning_rate": 9.117190844230971e-06,
+      "loss": 0.5408,
+      "step": 46
+    },
+    {
+      "epoch": 0.834319526627219,
+      "grad_norm": 0.5206530094146729,
+      "learning_rate": 9.057278936400453e-06,
+      "loss": 0.5804,
+      "step": 47
+    },
+    {
+      "epoch": 0.8520710059171598,
+      "grad_norm": 0.5596741437911987,
+      "learning_rate": 8.99561086464603e-06,
+      "loss": 0.5521,
+      "step": 48
+    },
+    {
+      "epoch": 0.8698224852071006,
+      "grad_norm": 0.5072557330131531,
+      "learning_rate": 8.932213321547769e-06,
+      "loss": 0.5277,
+      "step": 49
+    },
+    {
+      "epoch": 0.8875739644970414,
+      "grad_norm": 0.5525227785110474,
+      "learning_rate": 8.86711374827494e-06,
+      "loss": 0.6031,
+      "step": 50
+    },
+    {
+      "epoch": 0.9053254437869822,
+      "grad_norm": 0.6006079316139221,
+      "learning_rate": 8.800340322708291e-06,
+      "loss": 0.5698,
+      "step": 51
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.5963747501373291,
+      "learning_rate": 8.73192194724347e-06,
+      "loss": 0.6289,
+      "step": 52
+    },
+    {
+      "epoch": 0.9408284023668639,
+      "grad_norm": 0.5696894526481628,
+      "learning_rate": 8.661888236280813e-06,
+      "loss": 0.5918,
+      "step": 53
+    },
+    {
+      "epoch": 0.9585798816568047,
+      "grad_norm": 0.6133765578269958,
+      "learning_rate": 8.590269503406986e-06,
+      "loss": 0.6514,
+      "step": 54
+    },
+    {
+      "epoch": 0.9763313609467456,
+      "grad_norm": 0.6414260864257812,
+      "learning_rate": 8.517096748273951e-06,
+      "loss": 0.5686,
+      "step": 55
+    },
+    {
+      "epoch": 0.9940828402366864,
+      "grad_norm": 0.6260319948196411,
+      "learning_rate": 8.442401643181e-06,
+      "loss": 0.5175,
+      "step": 56
+    },
+    {
+      "epoch": 1.0118343195266273,
+      "grad_norm": 1.199350118637085,
+      "learning_rate": 8.366216519365623e-06,
+      "loss": 0.9417,
+      "step": 57
+    },
+    {
+      "epoch": 1.029585798816568,
+      "grad_norm": 0.6130478978157043,
+      "learning_rate": 8.288574353009164e-06,
+      "loss": 0.4821,
+      "step": 58
+    },
+    {
+      "epoch": 1.047337278106509,
+      "grad_norm": 0.6134289503097534,
+      "learning_rate": 8.20950875096333e-06,
+      "loss": 0.4782,
+      "step": 59
+    },
+    {
+      "epoch": 1.0650887573964498,
+      "grad_norm": 0.7462955117225647,
+      "learning_rate": 8.129053936203688e-06,
+      "loss": 0.5882,
+      "step": 60
+    },
+    {
+      "epoch": 1.0828402366863905,
+      "grad_norm": 0.6716148257255554,
+      "learning_rate": 8.04724473301652e-06,
+      "loss": 0.5487,
+      "step": 61
+    },
+    {
+      "epoch": 1.1005917159763314,
+      "grad_norm": 0.5907769799232483,
+      "learning_rate": 7.964116551925365e-06,
+      "loss": 0.4711,
+      "step": 62
+    },
+    {
+      "epoch": 1.1183431952662721,
+      "grad_norm": 0.6688742637634277,
+      "learning_rate": 7.879705374363831e-06,
+      "loss": 0.4645,
+      "step": 63
+    },
+    {
+      "epoch": 1.136094674556213,
+      "grad_norm": 0.6526861786842346,
+      "learning_rate": 7.794047737101298e-06,
+      "loss": 0.5206,
+      "step": 64
+    },
+    {
+      "epoch": 1.1538461538461537,
+      "grad_norm": 0.5595381855964661,
+      "learning_rate": 7.707180716428237e-06,
+      "loss": 0.4313,
+      "step": 65
+    },
+    {
+      "epoch": 1.1715976331360947,
+      "grad_norm": 0.6181778311729431,
+      "learning_rate": 7.619141912108008e-06,
+      "loss": 0.564,
+      "step": 66
+    },
+    {
+      "epoch": 1.1893491124260356,
+      "grad_norm": 0.614881157875061,
+      "learning_rate": 7.529969431102063e-06,
+      "loss": 0.5041,
+      "step": 67
+    },
+    {
+      "epoch": 1.2071005917159763,
+      "grad_norm": 0.6447051763534546,
+      "learning_rate": 7.4397018710756415e-06,
+      "loss": 0.5046,
+      "step": 68
+    },
+    {
+      "epoch": 1.2248520710059172,
+      "grad_norm": 0.5753356218338013,
+      "learning_rate": 7.34837830369103e-06,
+      "loss": 0.4534,
+      "step": 69
+    },
+    {
+      "epoch": 1.242603550295858,
+      "grad_norm": 0.5938759446144104,
+      "learning_rate": 7.2560382576956875e-06,
+      "loss": 0.4369,
+      "step": 70
+    },
+    {
+      "epoch": 1.2603550295857988,
+      "grad_norm": 0.6178358793258667,
+      "learning_rate": 7.162721701812506e-06,
+      "loss": 0.4949,
+      "step": 71
+    },
+    {
+      "epoch": 1.2781065088757395,
+      "grad_norm": 0.6533629894256592,
+      "learning_rate": 7.068469027439642e-06,
+      "loss": 0.4816,
+      "step": 72
+    },
+    {
+      "epoch": 1.2958579881656804,
+      "grad_norm": 0.6626835465431213,
+      "learning_rate": 6.9733210311673826e-06,
+      "loss": 0.5976,
+      "step": 73
+    },
+    {
+      "epoch": 1.3136094674556213,
+      "grad_norm": 0.5293806195259094,
+      "learning_rate": 6.8773188971196515e-06,
+      "loss": 0.4124,
+      "step": 74
+    },
+    {
+      "epoch": 1.331360946745562,
+      "grad_norm": 0.6411221623420715,
+      "learning_rate": 6.780504179127735e-06,
+      "loss": 0.5081,
+      "step": 75
+    },
+    {
+      "epoch": 1.349112426035503,
+      "grad_norm": 0.6326239109039307,
+      "learning_rate": 6.682918782744033e-06,
+      "loss": 0.5123,
+      "step": 76
+    },
+    {
+      "epoch": 1.3668639053254439,
+      "grad_norm": 0.6738696098327637,
+      "learning_rate": 6.584604947103515e-06,
+      "loss": 0.499,
+      "step": 77
+    },
+    {
+      "epoch": 1.3846153846153846,
+      "grad_norm": 0.5083363652229309,
+      "learning_rate": 6.4856052266408375e-06,
+      "loss": 0.4522,
+      "step": 78
+    },
+    {
+      "epoch": 1.4023668639053255,
+      "grad_norm": 0.6393911838531494,
+      "learning_rate": 6.385962472670953e-06,
+      "loss": 0.4685,
+      "step": 79
+    },
+    {
+      "epoch": 1.4201183431952662,
+      "grad_norm": 0.6106072664260864,
+      "learning_rate": 6.28571981484123e-06,
+      "loss": 0.4942,
+      "step": 80
+    },
+    {
+      "epoch": 1.4378698224852071,
+      "grad_norm": 0.5104251503944397,
+      "learning_rate": 6.184920642463095e-06,
+      "loss": 0.4625,
+      "step": 81
+    },
+    {
+      "epoch": 1.4556213017751478,
+      "grad_norm": 0.587416410446167,
+      "learning_rate": 6.083608585731283e-06,
+      "loss": 0.5671,
+      "step": 82
+    },
+    {
+      "epoch": 1.4733727810650887,
+      "grad_norm": 0.5419860482215881,
+      "learning_rate": 5.9818274968388225e-06,
+      "loss": 0.516,
+      "step": 83
+    },
+    {
+      "epoch": 1.4911242603550297,
+      "grad_norm": 0.6191542744636536,
+      "learning_rate": 5.879621430995927e-06,
+      "loss": 0.4823,
+      "step": 84
+    },
+    {
+      "epoch": 1.5088757396449703,
+      "grad_norm": 0.5240432620048523,
+      "learning_rate": 5.777034627361025e-06,
+      "loss": 0.3751,
+      "step": 85
+    },
+    {
+      "epoch": 1.5266272189349113,
+      "grad_norm": 0.6388912200927734,
+      "learning_rate": 5.674111489892144e-06,
+      "loss": 0.5432,
+      "step": 86
+    },
+    {
+      "epoch": 1.5443786982248522,
+      "grad_norm": 0.6531295776367188,
+      "learning_rate": 5.570896568126994e-06,
+      "loss": 0.5527,
+      "step": 87
+    },
+    {
+      "epoch": 1.5621301775147929,
+      "grad_norm": 0.5705211758613586,
+      "learning_rate": 5.4674345379e-06,
+      "loss": 0.4588,
+      "step": 88
+    },
+    {
+      "epoch": 1.5798816568047336,
+      "grad_norm": 0.5820942521095276,
+      "learning_rate": 5.36377018200472e-06,
+      "loss": 0.4563,
+      "step": 89
+    },
+    {
+      "epoch": 1.5976331360946747,
+      "grad_norm": 0.6194245219230652,
+      "learning_rate": 5.259948370809902e-06,
+      "loss": 0.5123,
+      "step": 90
+    },
+    {
+      "epoch": 1.6153846153846154,
+      "grad_norm": 0.5981638431549072,
+      "learning_rate": 5.156014042837696e-06,
+      "loss": 0.4979,
+      "step": 91
+    },
+    {
+      "epoch": 1.6331360946745561,
+      "grad_norm": 0.7485818862915039,
+      "learning_rate": 5.052012185312322e-06,
+      "loss": 0.5863,
+      "step": 92
+    },
+    {
+      "epoch": 1.650887573964497,
+      "grad_norm": 0.5108672380447388,
+      "learning_rate": 4.94798781468768e-06,
+      "loss": 0.398,
+      "step": 93
+    },
+    {
+      "epoch": 1.668639053254438,
+      "grad_norm": 0.6520046591758728,
+      "learning_rate": 4.843985957162304e-06,
+      "loss": 0.6246,
+      "step": 94
+    },
+    {
+      "epoch": 1.6863905325443787,
+      "grad_norm": 0.4945230484008789,
+      "learning_rate": 4.740051629190099e-06,
+      "loss": 0.3286,
+      "step": 95
+    },
+    {
+      "epoch": 1.7041420118343196,
+      "grad_norm": 0.613183319568634,
+      "learning_rate": 4.636229817995281e-06,
+      "loss": 0.4692,
+      "step": 96
+    },
+    {
+      "epoch": 1.7218934911242605,
+      "grad_norm": 0.6236385107040405,
+      "learning_rate": 4.532565462099999e-06,
+      "loss": 0.5258,
+      "step": 97
+    },
+    {
+      "epoch": 1.7396449704142012,
+      "grad_norm": 0.5453357100486755,
+      "learning_rate": 4.429103431873009e-06,
+      "loss": 0.4714,
+      "step": 98
+    },
+    {
+      "epoch": 1.7573964497041419,
+      "grad_norm": 0.5440649390220642,
+      "learning_rate": 4.3258885101078565e-06,
+      "loss": 0.4571,
+      "step": 99
+    },
+    {
+      "epoch": 1.7751479289940828,
+      "grad_norm": 0.6320599913597107,
+      "learning_rate": 4.2229653726389765e-06,
+      "loss": 0.4783,
+      "step": 100
+    },
+    {
+      "epoch": 1.7928994082840237,
+      "grad_norm": 0.5469642281532288,
+      "learning_rate": 4.120378569004074e-06,
+      "loss": 0.4467,
+      "step": 101
+    },
+    {
+      "epoch": 1.8106508875739644,
+      "grad_norm": 0.5750222206115723,
+      "learning_rate": 4.018172503161179e-06,
+      "loss": 0.5032,
+      "step": 102
+    },
+    {
+      "epoch": 1.8284023668639053,
+      "grad_norm": 0.5565685629844666,
+      "learning_rate": 3.9163914142687185e-06,
+      "loss": 0.482,
+      "step": 103
+    },
+    {
+      "epoch": 1.8461538461538463,
+      "grad_norm": 0.6028342247009277,
+      "learning_rate": 3.815079357536907e-06,
+      "loss": 0.4609,
+      "step": 104
+    },
+    {
+      "epoch": 1.863905325443787,
+      "grad_norm": 0.6078227758407593,
+      "learning_rate": 3.714280185158771e-06,
+      "loss": 0.5237,
+      "step": 105
+    },
+    {
+      "epoch": 1.8816568047337277,
+      "grad_norm": 0.5719071626663208,
+      "learning_rate": 3.614037527329048e-06,
+      "loss": 0.4206,
+      "step": 106
+    },
+    {
+      "epoch": 1.8994082840236688,
+      "grad_norm": 0.5875373482704163,
+      "learning_rate": 3.5143947733591633e-06,
+      "loss": 0.4779,
+      "step": 107
+    },
+    {
+      "epoch": 1.9171597633136095,
+      "grad_norm": 0.5589243769645691,
+      "learning_rate": 3.4153950528964867e-06,
+      "loss": 0.5056,
+      "step": 108
+    },
+    {
+      "epoch": 1.9349112426035502,
+      "grad_norm": 0.5471234917640686,
+      "learning_rate": 3.3170812172559695e-06,
+      "loss": 0.4929,
+      "step": 109
+    },
+    {
+      "epoch": 1.952662721893491,
+      "grad_norm": 0.5713181495666504,
+      "learning_rate": 3.2194958208722656e-06,
+      "loss": 0.4785,
+      "step": 110
+    },
+    {
+      "epoch": 1.970414201183432,
+      "grad_norm": 0.553081750869751,
+      "learning_rate": 3.1226811028803514e-06,
+      "loss": 0.4389,
+      "step": 111
+    },
+    {
+      "epoch": 1.9881656804733727,
+      "grad_norm": 0.5729470252990723,
+      "learning_rate": 3.0266789688326187e-06,
+      "loss": 0.4665,
+      "step": 112
+    },
+    {
+      "epoch": 2.0059171597633134,
+      "grad_norm": 1.2184429168701172,
+      "learning_rate": 2.9315309725603596e-06,
+      "loss": 0.7849,
+      "step": 113
+    },
+    {
+      "epoch": 2.0236686390532546,
+      "grad_norm": 0.522588849067688,
+      "learning_rate": 2.8372782981874964e-06,
+      "loss": 0.3366,
+      "step": 114
+    },
+    {
+      "epoch": 2.0414201183431953,
+      "grad_norm": 0.6389386057853699,
+      "learning_rate": 2.7439617423043146e-06,
+      "loss": 0.4961,
+      "step": 115
+    },
+    {
+      "epoch": 2.059171597633136,
+      "grad_norm": 0.6419571042060852,
+      "learning_rate": 2.6516216963089698e-06,
+      "loss": 0.4662,
+      "step": 116
+    },
+    {
+      "epoch": 2.076923076923077,
+      "grad_norm": 0.6015217900276184,
+      "learning_rate": 2.560298128924358e-06,
+      "loss": 0.4298,
+      "step": 117
+    },
+    {
+      "epoch": 2.094674556213018,
+      "grad_norm": 0.5608621835708618,
+      "learning_rate": 2.470030568897938e-06,
+      "loss": 0.3721,
+      "step": 118
+    },
+    {
+      "epoch": 2.1124260355029585,
+      "grad_norm": 0.6403945684432983,
+      "learning_rate": 2.3808580878919948e-06,
+      "loss": 0.4947,
+      "step": 119
+    },
+    {
+      "epoch": 2.1301775147928996,
+      "grad_norm": 0.4906422793865204,
+      "learning_rate": 2.2928192835717642e-06,
+      "loss": 0.3607,
+      "step": 120
+    },
+    {
+      "epoch": 2.1479289940828403,
+      "grad_norm": 0.5612274408340454,
+      "learning_rate": 2.205952262898704e-06,
+      "loss": 0.4134,
+      "step": 121
+    },
+    {
+      "epoch": 2.165680473372781,
+      "grad_norm": 0.587371289730072,
+      "learning_rate": 2.120294625636171e-06,
+      "loss": 0.4862,
+      "step": 122
+    },
+    {
+      "epoch": 2.1834319526627217,
+      "grad_norm": 0.5207931399345398,
+      "learning_rate": 2.0358834480746363e-06,
+      "loss": 0.3613,
+      "step": 123
+    },
+    {
+      "epoch": 2.201183431952663,
+      "grad_norm": 0.6090331673622131,
+      "learning_rate": 1.9527552669834797e-06,
+      "loss": 0.4493,
+      "step": 124
+    },
+    {
+      "epoch": 2.2189349112426036,
+      "grad_norm": 0.5700682401657104,
+      "learning_rate": 1.8709460637963123e-06,
+      "loss": 0.4133,
+      "step": 125
+    },
+    {
+      "epoch": 2.2366863905325443,
+      "grad_norm": 0.4857932925224304,
+      "learning_rate": 1.7904912490366723e-06,
+      "loss": 0.3573,
+      "step": 126
+    },
+    {
+      "epoch": 2.2544378698224854,
+      "grad_norm": 0.6004585027694702,
+      "learning_rate": 1.711425646990838e-06,
+      "loss": 0.4517,
+      "step": 127
+    },
+    {
+      "epoch": 2.272189349112426,
+      "grad_norm": 0.5605913996696472,
+      "learning_rate": 1.6337834806343783e-06,
+      "loss": 0.4134,
+      "step": 128
+    },
+    {
+      "epoch": 2.289940828402367,
+      "grad_norm": 0.6110245585441589,
+      "learning_rate": 1.557598356819e-06,
+      "loss": 0.4579,
+      "step": 129
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 0.5302851796150208,
+      "learning_rate": 1.482903251726049e-06,
+      "loss": 0.3641,
+      "step": 130
+    },
+    {
+      "epoch": 2.3254437869822486,
+      "grad_norm": 0.6419249176979065,
+      "learning_rate": 1.409730496593016e-06,
+      "loss": 0.5007,
+      "step": 131
+    },
+    {
+      "epoch": 2.3431952662721893,
+      "grad_norm": 0.5336579084396362,
+      "learning_rate": 1.3381117637191887e-06,
+      "loss": 0.3433,
+      "step": 132
+    },
+    {
+      "epoch": 2.36094674556213,
+      "grad_norm": 0.5869147777557373,
+      "learning_rate": 1.2680780527565313e-06,
+      "loss": 0.4898,
+      "step": 133
+    },
+    {
+      "epoch": 2.378698224852071,
+      "grad_norm": 0.4657803475856781,
+      "learning_rate": 1.1996596772917091e-06,
+      "loss": 0.3326,
+      "step": 134
+    },
+    {
+      "epoch": 2.396449704142012,
+      "grad_norm": 0.6105607748031616,
+      "learning_rate": 1.132886251725061e-06,
+      "loss": 0.4423,
+      "step": 135
+    },
+    {
+      "epoch": 2.4142011834319526,
+      "grad_norm": 0.5837461948394775,
+      "learning_rate": 1.0677866784522317e-06,
+      "loss": 0.4593,
+      "step": 136
+    },
+    {
+      "epoch": 2.4319526627218933,
+      "grad_norm": 0.6025368571281433,
+      "learning_rate": 1.004389135353972e-06,
+      "loss": 0.4215,
+      "step": 137
+    },
+    {
+      "epoch": 2.4497041420118344,
+      "grad_norm": 0.5407091379165649,
+      "learning_rate": 9.427210635995482e-07,
+      "loss": 0.3988,
+      "step": 138
+    },
+    {
+      "epoch": 2.467455621301775,
+      "grad_norm": 0.5298522114753723,
+      "learning_rate": 8.828091557690288e-07,
+      "loss": 0.4313,
+      "step": 139
+    },
+    {
+      "epoch": 2.485207100591716,
+      "grad_norm": 0.5403129458427429,
+      "learning_rate": 8.246793442995954e-07,
+      "loss": 0.4222,
+      "step": 140
+    },
+    {
+      "epoch": 2.502958579881657,
+      "grad_norm": 0.5571721792221069,
+      "learning_rate": 7.68356790260873e-07,
+      "loss": 0.4143,
+      "step": 141
+    },
+    {
+      "epoch": 2.5207100591715976,
+      "grad_norm": 0.5758110284805298,
+      "learning_rate": 7.138658724641417e-07,
+      "loss": 0.4597,
+      "step": 142
+    },
+    {
+      "epoch": 2.5384615384615383,
+      "grad_norm": 0.5439177751541138,
+      "learning_rate": 6.612301769101464e-07,
+      "loss": 0.4078,
+      "step": 143
+    },
+    {
+      "epoch": 2.556213017751479,
+      "grad_norm": 0.6059474349021912,
+      "learning_rate": 6.104724865800665e-07,
+      "loss": 0.4234,
+      "step": 144
+    },
+    {
+      "epoch": 2.57396449704142,
+      "grad_norm": 0.5578750371932983,
+      "learning_rate": 5.616147715740611e-07,
+      "loss": 0.3722,
+      "step": 145
+    },
+    {
+      "epoch": 2.591715976331361,
+      "grad_norm": 0.5182917714118958,
+      "learning_rate": 5.146781796016798e-07,
+      "loss": 0.3592,
+      "step": 146
+    },
+    {
+      "epoch": 2.609467455621302,
+      "grad_norm": 0.5251271724700928,
+      "learning_rate": 4.696830268282204e-07,
+      "loss": 0.4132,
+      "step": 147
+    },
+    {
+      "epoch": 2.6272189349112427,
+      "grad_norm": 0.5910128951072693,
+      "learning_rate": 4.2664878908102556e-07,
+      "loss": 0.4721,
+      "step": 148
+    },
+    {
+      "epoch": 2.6449704142011834,
+      "grad_norm": 0.5311455130577087,
+      "learning_rate": 3.855940934195146e-07,
+      "loss": 0.4011,
+      "step": 149
+    },
+    {
+      "epoch": 2.662721893491124,
+      "grad_norm": 0.5455037951469421,
+      "learning_rate": 3.4653671007259084e-07,
+      "loss": 0.4317,
+      "step": 150
+    },
+    {
+      "epoch": 2.6804733727810652,
+      "grad_norm": 0.521126389503479,
+      "learning_rate": 3.0949354474692937e-07,
+      "loss": 0.4071,
+      "step": 151
+    },
+    {
+      "epoch": 2.698224852071006,
+      "grad_norm": 0.5334401726722717,
+      "learning_rate": 2.7448063130946224e-07,
+      "loss": 0.3797,
+      "step": 152
+    },
+    {
+      "epoch": 2.7159763313609466,
+      "grad_norm": 0.6030508875846863,
+      "learning_rate": 2.4151312484723465e-07,
+      "loss": 0.4331,
+      "step": 153
+    },
+    {
+      "epoch": 2.7337278106508878,
+      "grad_norm": 0.47127389907836914,
+      "learning_rate": 2.106052951076365e-07,
+      "loss": 0.3481,
+      "step": 154
+    },
+    {
+      "epoch": 2.7514792899408285,
+      "grad_norm": 0.5236401557922363,
+      "learning_rate": 1.8177052032184285e-07,
+      "loss": 0.3702,
+      "step": 155
+    },
+    {
+      "epoch": 2.769230769230769,
+      "grad_norm": 0.5896205902099609,
+      "learning_rate": 1.5502128141414496e-07,
+      "loss": 0.4371,
+      "step": 156
+    },
+    {
+      "epoch": 2.78698224852071,
+      "grad_norm": 0.5283501148223877,
+      "learning_rate": 1.303691565996712e-07,
+      "loss": 0.3741,
+      "step": 157
+    },
+    {
+      "epoch": 2.804733727810651,
+      "grad_norm": 0.5836403369903564,
+      "learning_rate": 1.0782481637284014e-07,
+      "loss": 0.4289,
+      "step": 158
+    },
+    {
+      "epoch": 2.8224852071005917,
+      "grad_norm": 0.64845210313797,
+      "learning_rate": 8.739801888871468e-08,
+      "loss": 0.4927,
+      "step": 159
+    },
+    {
+      "epoch": 2.8402366863905324,
+      "grad_norm": 0.5165106654167175,
+      "learning_rate": 6.909760573925561e-08,
+      "loss": 0.3382,
+      "step": 160
+    },
+    {
+      "epoch": 2.8579881656804735,
+      "grad_norm": 0.5744462609291077,
+      "learning_rate": 5.2931498126298495e-08,
+      "loss": 0.4541,
+      "step": 161
+    },
+    {
+      "epoch": 2.8757396449704142,
+      "grad_norm": 0.5389672517776489,
+      "learning_rate": 3.890669343292464e-08,
+      "loss": 0.4203,
+      "step": 162
+    },
+    {
+      "epoch": 2.893491124260355,
+      "grad_norm": 0.43833690881729126,
+      "learning_rate": 2.702926219468882e-08,
+      "loss": 0.3555,
+      "step": 163
+    },
+    {
+      "epoch": 2.9112426035502956,
+      "grad_norm": 0.48717668652534485,
+      "learning_rate": 1.7304345472035634e-08,
+      "loss": 0.4286,
+      "step": 164
+    },
+    {
+      "epoch": 2.9289940828402368,
+      "grad_norm": 0.5516893267631531,
+      "learning_rate": 9.73615262502503e-09,
+      "loss": 0.4472,
+      "step": 165
+    },
+    {
+      "epoch": 2.9467455621301775,
+      "grad_norm": 0.44991251826286316,
+      "learning_rate": 4.327959491344791e-09,
+      "loss": 0.3565,
+      "step": 166
+    },
+    {
+      "epoch": 2.9644970414201186,
+      "grad_norm": 0.5328838229179382,
+      "learning_rate": 1.082106968385288e-09,
+      "loss": 0.45,
+      "step": 167
+    },
+    {
+      "epoch": 2.9822485207100593,
+      "grad_norm": 0.5235728621482849,
+      "learning_rate": 0.0,
+      "loss": 0.3742,
+      "step": 168
+    },
+    {
+      "epoch": 2.9822485207100593,
+      "step": 168,
+      "total_flos": 6.46489842951127e+16,
+      "train_loss": 0.5384191712808042,
+      "train_runtime": 12683.2217,
+      "train_samples_per_second": 0.32,
+      "train_steps_per_second": 0.013
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 168,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 600,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.46489842951127e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de6325e72c3868304d85e73b0bbb2e56d92a2ad6a528d89735ec37de3f4c440b
+size 7544