Upload model

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: b1_math_top_2_3k
+  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. -->
+
+# b1_math_top_2_3k
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/b1_math_top_2_3k 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: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 24
+- total_train_batch_size: 96
+- total_eval_batch_size: 32
+- 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: 7.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.6.0a0+ecf3bae40a.nv25.01
+- Datasets 3.5.0
+- 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": 6.850632911392405,
+    "total_flos": 3.3605374365505946e+17,
+    "train_loss": 0.30083318214331356,
+    "train_runtime": 14587.34,
+    "train_samples_per_second": 1.516,
+    "train_steps_per_second": 0.015
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/p/data1/mmlaion/dcft/hub/models--Qwen--Qwen2.5-7B-Instruct/snapshots/a09a35458c702b33eeacc393d103063234e8bc28",
+  "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": null,
+  "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": 1.05,
+  "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:de8e56336d99faabd0ecd01ec1d93727b706d72388284b8409338e4464b7e45f
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d5038afbd3d2f34dd5750ee2fa3945f1c060db3075bf7aa0b65552aa719549d
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee880330c1ed7b8e1bc958ec86836690808ccd97cd1f3727a804c61cc27d558a
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4584d02d4fb29516bde9f5b213d8058983f5fe50f984935fffd751a29c77d63
+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"
+  }
+}

runs/Apr19_07-15-48_jpbot-001-45.jupiter.internal/events.out.tfevents.1745039780.jpbot-001-45.jupiter.internal.3083685.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0c1c0d0c726c9ed4ae315f695be89c0f4cb1c284ed508d5a171c93b0b5e6901
+size 52625

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
+  }
+}

start_end.json

@@ -0,0 +1 @@
+{"start_time": "2025-04-19 07:15:48", "end_time": "2025-04-19 11:19:33"}

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": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.850632911392405,
+    "total_flos": 3.3605374365505946e+17,
+    "train_loss": 0.30083318214331356,
+    "train_runtime": 14587.34,
+    "train_samples_per_second": 1.516,
+    "train_steps_per_second": 0.015
+}

trainer_log.jsonl

@@ -0,0 +1,225 @@
+{"current_steps": 1, "total_steps": 224, "loss": 0.7917, "lr": 8.695652173913044e-07, "epoch": 0.030379746835443037, "percentage": 0.45, "elapsed_time": "0:01:05", "remaining_time": "4:05:09"}
+{"current_steps": 2, "total_steps": 224, "loss": 0.8352, "lr": 1.7391304347826088e-06, "epoch": 0.060759493670886074, "percentage": 0.89, "elapsed_time": "0:02:14", "remaining_time": "4:08:03"}
+{"current_steps": 3, "total_steps": 224, "loss": 0.8056, "lr": 2.6086956521739132e-06, "epoch": 0.09113924050632911, "percentage": 1.34, "elapsed_time": "0:03:28", "remaining_time": "4:15:27"}
+{"current_steps": 4, "total_steps": 224, "loss": 0.7998, "lr": 3.4782608695652175e-06, "epoch": 0.12151898734177215, "percentage": 1.79, "elapsed_time": "0:04:38", "remaining_time": "4:15:15"}
+{"current_steps": 5, "total_steps": 224, "loss": 0.7966, "lr": 4.347826086956522e-06, "epoch": 0.1518987341772152, "percentage": 2.23, "elapsed_time": "0:05:34", "remaining_time": "4:03:49"}
+{"current_steps": 6, "total_steps": 224, "loss": 0.7432, "lr": 5.2173913043478265e-06, "epoch": 0.18227848101265823, "percentage": 2.68, "elapsed_time": "0:06:57", "remaining_time": "4:12:57"}
+{"current_steps": 7, "total_steps": 224, "loss": 0.738, "lr": 6.086956521739132e-06, "epoch": 0.21265822784810126, "percentage": 3.12, "elapsed_time": "0:08:12", "remaining_time": "4:14:16"}
+{"current_steps": 8, "total_steps": 224, "loss": 0.7192, "lr": 6.956521739130435e-06, "epoch": 0.2430379746835443, "percentage": 3.57, "elapsed_time": "0:09:29", "remaining_time": "4:16:06"}
+{"current_steps": 9, "total_steps": 224, "loss": 0.698, "lr": 7.82608695652174e-06, "epoch": 0.27341772151898736, "percentage": 4.02, "elapsed_time": "0:10:36", "remaining_time": "4:13:13"}
+{"current_steps": 10, "total_steps": 224, "loss": 0.6933, "lr": 8.695652173913044e-06, "epoch": 0.3037974683544304, "percentage": 4.46, "elapsed_time": "0:11:22", "remaining_time": "4:03:20"}
+{"current_steps": 11, "total_steps": 224, "loss": 0.6662, "lr": 9.565217391304349e-06, "epoch": 0.3341772151898734, "percentage": 4.91, "elapsed_time": "0:12:42", "remaining_time": "4:06:09"}
+{"current_steps": 12, "total_steps": 224, "loss": 0.641, "lr": 1.0434782608695653e-05, "epoch": 0.36455696202531646, "percentage": 5.36, "elapsed_time": "0:13:38", "remaining_time": "4:00:58"}
+{"current_steps": 13, "total_steps": 224, "loss": 0.6131, "lr": 1.1304347826086957e-05, "epoch": 0.3949367088607595, "percentage": 5.8, "elapsed_time": "0:14:36", "remaining_time": "3:57:10"}
+{"current_steps": 14, "total_steps": 224, "loss": 0.6092, "lr": 1.2173913043478263e-05, "epoch": 0.4253164556962025, "percentage": 6.25, "elapsed_time": "0:15:38", "remaining_time": "3:54:33"}
+{"current_steps": 15, "total_steps": 224, "loss": 0.5987, "lr": 1.3043478260869566e-05, "epoch": 0.45569620253164556, "percentage": 6.7, "elapsed_time": "0:16:25", "remaining_time": "3:48:46"}
+{"current_steps": 16, "total_steps": 224, "loss": 0.561, "lr": 1.391304347826087e-05, "epoch": 0.4860759493670886, "percentage": 7.14, "elapsed_time": "0:17:29", "remaining_time": "3:47:24"}
+{"current_steps": 17, "total_steps": 224, "loss": 0.5766, "lr": 1.4782608695652174e-05, "epoch": 0.5164556962025316, "percentage": 7.59, "elapsed_time": "0:18:31", "remaining_time": "3:45:29"}
+{"current_steps": 18, "total_steps": 224, "loss": 0.566, "lr": 1.565217391304348e-05, "epoch": 0.5468354430379747, "percentage": 8.04, "elapsed_time": "0:19:16", "remaining_time": "3:40:39"}
+{"current_steps": 19, "total_steps": 224, "loss": 0.5672, "lr": 1.6521739130434785e-05, "epoch": 0.5772151898734177, "percentage": 8.48, "elapsed_time": "0:20:17", "remaining_time": "3:39:00"}
+{"current_steps": 20, "total_steps": 224, "loss": 0.599, "lr": 1.739130434782609e-05, "epoch": 0.6075949367088608, "percentage": 8.93, "elapsed_time": "0:21:34", "remaining_time": "3:40:03"}
+{"current_steps": 21, "total_steps": 224, "loss": 0.529, "lr": 1.8260869565217393e-05, "epoch": 0.6379746835443038, "percentage": 9.38, "elapsed_time": "0:22:52", "remaining_time": "3:41:08"}
+{"current_steps": 22, "total_steps": 224, "loss": 0.5438, "lr": 1.9130434782608697e-05, "epoch": 0.6683544303797468, "percentage": 9.82, "elapsed_time": "0:23:57", "remaining_time": "3:40:02"}
+{"current_steps": 23, "total_steps": 224, "loss": 0.5391, "lr": 2e-05, "epoch": 0.6987341772151898, "percentage": 10.27, "elapsed_time": "0:25:03", "remaining_time": "3:38:58"}
+{"current_steps": 24, "total_steps": 224, "loss": 0.5525, "lr": 1.999877856940653e-05, "epoch": 0.7291139240506329, "percentage": 10.71, "elapsed_time": "0:26:09", "remaining_time": "3:37:59"}
+{"current_steps": 25, "total_steps": 224, "loss": 0.5144, "lr": 1.999511457600466e-05, "epoch": 0.759493670886076, "percentage": 11.16, "elapsed_time": "0:27:07", "remaining_time": "3:35:52"}
+{"current_steps": 26, "total_steps": 224, "loss": 0.5047, "lr": 1.9989008914857115e-05, "epoch": 0.789873417721519, "percentage": 11.61, "elapsed_time": "0:28:01", "remaining_time": "3:33:28"}
+{"current_steps": 27, "total_steps": 224, "loss": 0.5478, "lr": 1.998046307749216e-05, "epoch": 0.8202531645569621, "percentage": 12.05, "elapsed_time": "0:29:10", "remaining_time": "3:32:51"}
+{"current_steps": 28, "total_steps": 224, "loss": 0.5212, "lr": 1.9969479151539238e-05, "epoch": 0.850632911392405, "percentage": 12.5, "elapsed_time": "0:30:07", "remaining_time": "3:30:54"}
+{"current_steps": 29, "total_steps": 224, "loss": 0.5033, "lr": 1.9956059820218982e-05, "epoch": 0.8810126582278481, "percentage": 12.95, "elapsed_time": "0:31:09", "remaining_time": "3:29:28"}
+{"current_steps": 30, "total_steps": 224, "loss": 0.5258, "lr": 1.9940208361687762e-05, "epoch": 0.9113924050632911, "percentage": 13.39, "elapsed_time": "0:32:14", "remaining_time": "3:28:27"}
+{"current_steps": 31, "total_steps": 224, "loss": 0.4979, "lr": 1.9921928648236855e-05, "epoch": 0.9417721518987342, "percentage": 13.84, "elapsed_time": "0:33:21", "remaining_time": "3:27:39"}
+{"current_steps": 32, "total_steps": 224, "loss": 0.5248, "lr": 1.990122514534651e-05, "epoch": 0.9721518987341772, "percentage": 14.29, "elapsed_time": "0:34:24", "remaining_time": "3:26:28"}
+{"current_steps": 33, "total_steps": 224, "loss": 0.6827, "lr": 1.9878102910595097e-05, "epoch": 1.010126582278481, "percentage": 14.73, "elapsed_time": "0:36:04", "remaining_time": "3:28:50"}
+{"current_steps": 34, "total_steps": 224, "loss": 0.469, "lr": 1.985256759242359e-05, "epoch": 1.040506329113924, "percentage": 15.18, "elapsed_time": "0:37:01", "remaining_time": "3:26:53"}
+{"current_steps": 35, "total_steps": 224, "loss": 0.4372, "lr": 1.982462542875576e-05, "epoch": 1.070886075949367, "percentage": 15.62, "elapsed_time": "0:37:50", "remaining_time": "3:24:19"}
+{"current_steps": 36, "total_steps": 224, "loss": 0.4661, "lr": 1.979428324547432e-05, "epoch": 1.1012658227848102, "percentage": 16.07, "elapsed_time": "0:38:52", "remaining_time": "3:23:02"}
+{"current_steps": 37, "total_steps": 224, "loss": 0.3946, "lr": 1.9761548454753455e-05, "epoch": 1.1316455696202532, "percentage": 16.52, "elapsed_time": "0:39:59", "remaining_time": "3:22:08"}
+{"current_steps": 38, "total_steps": 224, "loss": 0.5268, "lr": 1.972642905324813e-05, "epoch": 1.1620253164556962, "percentage": 16.96, "elapsed_time": "0:41:04", "remaining_time": "3:21:04"}
+{"current_steps": 39, "total_steps": 224, "loss": 0.4601, "lr": 1.9688933620140638e-05, "epoch": 1.1924050632911392, "percentage": 17.41, "elapsed_time": "0:42:01", "remaining_time": "3:19:20"}
+{"current_steps": 40, "total_steps": 224, "loss": 0.4591, "lr": 1.96490713150448e-05, "epoch": 1.2227848101265824, "percentage": 17.86, "elapsed_time": "0:43:15", "remaining_time": "3:18:57"}
+{"current_steps": 41, "total_steps": 224, "loss": 0.4329, "lr": 1.9606851875768404e-05, "epoch": 1.2531645569620253, "percentage": 18.3, "elapsed_time": "0:44:24", "remaining_time": "3:18:12"}
+{"current_steps": 42, "total_steps": 224, "loss": 0.4572, "lr": 1.956228561593441e-05, "epoch": 1.2835443037974683, "percentage": 18.75, "elapsed_time": "0:45:26", "remaining_time": "3:16:53"}
+{"current_steps": 43, "total_steps": 224, "loss": 0.4369, "lr": 1.9515383422461457e-05, "epoch": 1.3139240506329113, "percentage": 19.2, "elapsed_time": "0:46:25", "remaining_time": "3:15:23"}
+{"current_steps": 44, "total_steps": 224, "loss": 0.4316, "lr": 1.9466156752904344e-05, "epoch": 1.3443037974683545, "percentage": 19.64, "elapsed_time": "0:47:34", "remaining_time": "3:14:36"}
+{"current_steps": 45, "total_steps": 224, "loss": 0.4249, "lr": 1.9414617632655114e-05, "epoch": 1.3746835443037975, "percentage": 20.09, "elapsed_time": "0:48:40", "remaining_time": "3:13:38"}
+{"current_steps": 46, "total_steps": 224, "loss": 0.4741, "lr": 1.9360778652005416e-05, "epoch": 1.4050632911392404, "percentage": 20.54, "elapsed_time": "0:49:47", "remaining_time": "3:12:42"}
+{"current_steps": 47, "total_steps": 224, "loss": 0.4113, "lr": 1.9304652963070868e-05, "epoch": 1.4354430379746836, "percentage": 20.98, "elapsed_time": "0:50:45", "remaining_time": "3:11:08"}
+{"current_steps": 48, "total_steps": 224, "loss": 0.4209, "lr": 1.9246254276578175e-05, "epoch": 1.4658227848101266, "percentage": 21.43, "elapsed_time": "0:51:50", "remaining_time": "3:10:04"}
+{"current_steps": 49, "total_steps": 224, "loss": 0.4852, "lr": 1.9185596858515797e-05, "epoch": 1.4962025316455696, "percentage": 21.88, "elapsed_time": "0:52:56", "remaining_time": "3:09:06"}
+{"current_steps": 50, "total_steps": 224, "loss": 0.3972, "lr": 1.9122695526648968e-05, "epoch": 1.5265822784810128, "percentage": 22.32, "elapsed_time": "0:54:03", "remaining_time": "3:08:05"}
+{"current_steps": 51, "total_steps": 224, "loss": 0.4913, "lr": 1.905756564689991e-05, "epoch": 1.5569620253164556, "percentage": 22.77, "elapsed_time": "0:55:02", "remaining_time": "3:06:42"}
+{"current_steps": 52, "total_steps": 224, "loss": 0.4621, "lr": 1.8990223129594146e-05, "epoch": 1.5873417721518988, "percentage": 23.21, "elapsed_time": "0:56:09", "remaining_time": "3:05:44"}
+{"current_steps": 53, "total_steps": 224, "loss": 0.418, "lr": 1.8920684425573865e-05, "epoch": 1.6177215189873417, "percentage": 23.66, "elapsed_time": "0:57:09", "remaining_time": "3:04:23"}
+{"current_steps": 54, "total_steps": 224, "loss": 0.4546, "lr": 1.884896652217917e-05, "epoch": 1.6481012658227847, "percentage": 24.11, "elapsed_time": "0:58:09", "remaining_time": "3:03:06"}
+{"current_steps": 55, "total_steps": 224, "loss": 0.4214, "lr": 1.877508693909831e-05, "epoch": 1.678481012658228, "percentage": 24.55, "elapsed_time": "0:59:10", "remaining_time": "3:01:49"}
+{"current_steps": 56, "total_steps": 224, "loss": 0.4144, "lr": 1.8699063724087905e-05, "epoch": 1.7088607594936709, "percentage": 25.0, "elapsed_time": "1:00:07", "remaining_time": "3:00:22"}
+{"current_steps": 57, "total_steps": 224, "loss": 0.4226, "lr": 1.862091544856407e-05, "epoch": 1.7392405063291139, "percentage": 25.45, "elapsed_time": "1:01:06", "remaining_time": "2:59:02"}
+{"current_steps": 58, "total_steps": 224, "loss": 0.3996, "lr": 1.854066120306571e-05, "epoch": 1.769620253164557, "percentage": 25.89, "elapsed_time": "1:01:56", "remaining_time": "2:57:17"}
+{"current_steps": 59, "total_steps": 224, "loss": 0.4603, "lr": 1.8458320592590976e-05, "epoch": 1.8, "percentage": 26.34, "elapsed_time": "1:03:06", "remaining_time": "2:56:29"}
+{"current_steps": 60, "total_steps": 224, "loss": 0.4323, "lr": 1.837391373180801e-05, "epoch": 1.830379746835443, "percentage": 26.79, "elapsed_time": "1:03:57", "remaining_time": "2:54:48"}
+{"current_steps": 61, "total_steps": 224, "loss": 0.4237, "lr": 1.8287461240141217e-05, "epoch": 1.8607594936708862, "percentage": 27.23, "elapsed_time": "1:05:02", "remaining_time": "2:53:46"}
+{"current_steps": 62, "total_steps": 224, "loss": 0.3994, "lr": 1.8198984236734246e-05, "epoch": 1.891139240506329, "percentage": 27.68, "elapsed_time": "1:05:59", "remaining_time": "2:52:27"}
+{"current_steps": 63, "total_steps": 224, "loss": 0.4519, "lr": 1.8108504335290852e-05, "epoch": 1.9215189873417722, "percentage": 28.12, "elapsed_time": "1:07:10", "remaining_time": "2:51:41"}
+{"current_steps": 64, "total_steps": 224, "loss": 0.4467, "lr": 1.8016043638794975e-05, "epoch": 1.9518987341772152, "percentage": 28.57, "elapsed_time": "1:08:16", "remaining_time": "2:50:40"}
+{"current_steps": 65, "total_steps": 224, "loss": 0.5046, "lr": 1.7921624734111292e-05, "epoch": 1.9822784810126581, "percentage": 29.02, "elapsed_time": "1:09:34", "remaining_time": "2:50:11"}
+{"current_steps": 66, "total_steps": 224, "loss": 0.4692, "lr": 1.7825270686467567e-05, "epoch": 2.020253164556962, "percentage": 29.46, "elapsed_time": "1:11:13", "remaining_time": "2:50:30"}
+{"current_steps": 67, "total_steps": 224, "loss": 0.3942, "lr": 1.7727005033820117e-05, "epoch": 2.050632911392405, "percentage": 29.91, "elapsed_time": "1:12:16", "remaining_time": "2:49:21"}
+{"current_steps": 68, "total_steps": 224, "loss": 0.3286, "lr": 1.762685178110382e-05, "epoch": 2.081012658227848, "percentage": 30.36, "elapsed_time": "1:13:04", "remaining_time": "2:47:37"}
+{"current_steps": 69, "total_steps": 224, "loss": 0.3418, "lr": 1.752483539436807e-05, "epoch": 2.1113924050632913, "percentage": 30.8, "elapsed_time": "1:14:00", "remaining_time": "2:46:15"}
+{"current_steps": 70, "total_steps": 224, "loss": 0.3328, "lr": 1.7420980794800013e-05, "epoch": 2.141772151898734, "percentage": 31.25, "elapsed_time": "1:14:59", "remaining_time": "2:44:59"}
+{"current_steps": 71, "total_steps": 224, "loss": 0.3394, "lr": 1.731531335263669e-05, "epoch": 2.1721518987341772, "percentage": 31.7, "elapsed_time": "1:16:17", "remaining_time": "2:44:24"}
+{"current_steps": 72, "total_steps": 224, "loss": 0.3315, "lr": 1.720785888096743e-05, "epoch": 2.2025316455696204, "percentage": 32.14, "elapsed_time": "1:17:26", "remaining_time": "2:43:28"}
+{"current_steps": 73, "total_steps": 224, "loss": 0.3865, "lr": 1.7098643629428035e-05, "epoch": 2.232911392405063, "percentage": 32.59, "elapsed_time": "1:18:27", "remaining_time": "2:42:17"}
+{"current_steps": 74, "total_steps": 224, "loss": 0.3154, "lr": 1.698769427778842e-05, "epoch": 2.2632911392405064, "percentage": 33.04, "elapsed_time": "1:19:35", "remaining_time": "2:41:19"}
+{"current_steps": 75, "total_steps": 224, "loss": 0.3249, "lr": 1.687503792943506e-05, "epoch": 2.293670886075949, "percentage": 33.48, "elapsed_time": "1:20:42", "remaining_time": "2:40:20"}
+{"current_steps": 76, "total_steps": 224, "loss": 0.3314, "lr": 1.6760702104750046e-05, "epoch": 2.3240506329113924, "percentage": 33.93, "elapsed_time": "1:21:50", "remaining_time": "2:39:21"}
+{"current_steps": 77, "total_steps": 224, "loss": 0.3774, "lr": 1.664471473438822e-05, "epoch": 2.3544303797468356, "percentage": 34.38, "elapsed_time": "1:23:00", "remaining_time": "2:38:29"}
+{"current_steps": 78, "total_steps": 224, "loss": 0.2784, "lr": 1.6527104152454096e-05, "epoch": 2.3848101265822783, "percentage": 34.82, "elapsed_time": "1:23:57", "remaining_time": "2:37:09"}
+{"current_steps": 79, "total_steps": 224, "loss": 0.383, "lr": 1.6407899089580263e-05, "epoch": 2.4151898734177215, "percentage": 35.27, "elapsed_time": "1:25:05", "remaining_time": "2:36:10"}
+{"current_steps": 80, "total_steps": 224, "loss": 0.3565, "lr": 1.628712866590885e-05, "epoch": 2.4455696202531647, "percentage": 35.71, "elapsed_time": "1:26:07", "remaining_time": "2:35:01"}
+{"current_steps": 81, "total_steps": 224, "loss": 0.3569, "lr": 1.6164822383977912e-05, "epoch": 2.4759493670886075, "percentage": 36.16, "elapsed_time": "1:27:06", "remaining_time": "2:33:47"}
+{"current_steps": 82, "total_steps": 224, "loss": 0.3209, "lr": 1.604101012151436e-05, "epoch": 2.5063291139240507, "percentage": 36.61, "elapsed_time": "1:28:05", "remaining_time": "2:32:32"}
+{"current_steps": 83, "total_steps": 224, "loss": 0.3297, "lr": 1.5915722124135227e-05, "epoch": 2.536708860759494, "percentage": 37.05, "elapsed_time": "1:29:07", "remaining_time": "2:31:24"}
+{"current_steps": 84, "total_steps": 224, "loss": 0.3044, "lr": 1.5788988997959115e-05, "epoch": 2.5670886075949366, "percentage": 37.5, "elapsed_time": "1:30:13", "remaining_time": "2:30:21"}
+{"current_steps": 85, "total_steps": 224, "loss": 0.4127, "lr": 1.5660841702129533e-05, "epoch": 2.59746835443038, "percentage": 37.95, "elapsed_time": "1:31:18", "remaining_time": "2:29:19"}
+{"current_steps": 86, "total_steps": 224, "loss": 0.3065, "lr": 1.5531311541251995e-05, "epoch": 2.6278481012658226, "percentage": 38.39, "elapsed_time": "1:32:22", "remaining_time": "2:28:13"}
+{"current_steps": 87, "total_steps": 224, "loss": 0.3341, "lr": 1.540043015774676e-05, "epoch": 2.6582278481012658, "percentage": 38.84, "elapsed_time": "1:33:20", "remaining_time": "2:26:59"}
+{"current_steps": 88, "total_steps": 224, "loss": 0.3202, "lr": 1.5268229524119007e-05, "epoch": 2.688607594936709, "percentage": 39.29, "elapsed_time": "1:34:16", "remaining_time": "2:25:42"}
+{"current_steps": 89, "total_steps": 224, "loss": 0.3673, "lr": 1.513474193514842e-05, "epoch": 2.7189873417721517, "percentage": 39.73, "elapsed_time": "1:35:16", "remaining_time": "2:24:31"}
+{"current_steps": 90, "total_steps": 224, "loss": 0.3352, "lr": 1.5000000000000002e-05, "epoch": 2.749367088607595, "percentage": 40.18, "elapsed_time": "1:36:25", "remaining_time": "2:23:34"}
+{"current_steps": 91, "total_steps": 224, "loss": 0.3649, "lr": 1.4864036634258112e-05, "epoch": 2.779746835443038, "percentage": 40.62, "elapsed_time": "1:37:17", "remaining_time": "2:22:11"}
+{"current_steps": 92, "total_steps": 224, "loss": 0.3465, "lr": 1.4726885051885654e-05, "epoch": 2.810126582278481, "percentage": 41.07, "elapsed_time": "1:38:17", "remaining_time": "2:21:01"}
+{"current_steps": 93, "total_steps": 224, "loss": 0.3312, "lr": 1.4588578757110359e-05, "epoch": 2.840506329113924, "percentage": 41.52, "elapsed_time": "1:39:23", "remaining_time": "2:20:00"}
+{"current_steps": 94, "total_steps": 224, "loss": 0.3389, "lr": 1.4449151536240167e-05, "epoch": 2.8708860759493673, "percentage": 41.96, "elapsed_time": "1:40:34", "remaining_time": "2:19:05"}
+{"current_steps": 95, "total_steps": 224, "loss": 0.2892, "lr": 1.4308637449409705e-05, "epoch": 2.90126582278481, "percentage": 42.41, "elapsed_time": "1:41:27", "remaining_time": "2:17:46"}
+{"current_steps": 96, "total_steps": 224, "loss": 0.3889, "lr": 1.4167070822259868e-05, "epoch": 2.9316455696202532, "percentage": 42.86, "elapsed_time": "1:42:45", "remaining_time": "2:17:00"}
+{"current_steps": 97, "total_steps": 224, "loss": 0.3382, "lr": 1.402448623755254e-05, "epoch": 2.962025316455696, "percentage": 43.3, "elapsed_time": "1:44:00", "remaining_time": "2:16:10"}
+{"current_steps": 98, "total_steps": 224, "loss": 0.4444, "lr": 1.3880918526722497e-05, "epoch": 2.992405063291139, "percentage": 43.75, "elapsed_time": "1:45:08", "remaining_time": "2:15:10"}
+{"current_steps": 99, "total_steps": 224, "loss": 0.2592, "lr": 1.3736402761368597e-05, "epoch": 3.030379746835443, "percentage": 44.2, "elapsed_time": "1:46:45", "remaining_time": "2:14:47"}
+{"current_steps": 100, "total_steps": 224, "loss": 0.2547, "lr": 1.3590974244686248e-05, "epoch": 3.060759493670886, "percentage": 44.64, "elapsed_time": "1:47:45", "remaining_time": "2:13:36"}
+{"current_steps": 101, "total_steps": 224, "loss": 0.273, "lr": 1.344466850284333e-05, "epoch": 3.091139240506329, "percentage": 45.09, "elapsed_time": "1:48:59", "remaining_time": "2:12:44"}
+{"current_steps": 102, "total_steps": 224, "loss": 0.2575, "lr": 1.3297521276301666e-05, "epoch": 3.1215189873417724, "percentage": 45.54, "elapsed_time": "1:50:12", "remaining_time": "2:11:48"}
+{"current_steps": 103, "total_steps": 224, "loss": 0.2552, "lr": 1.3149568511086104e-05, "epoch": 3.151898734177215, "percentage": 45.98, "elapsed_time": "1:51:16", "remaining_time": "2:10:43"}
+{"current_steps": 104, "total_steps": 224, "loss": 0.2552, "lr": 1.300084635000341e-05, "epoch": 3.1822784810126583, "percentage": 46.43, "elapsed_time": "1:52:12", "remaining_time": "2:09:28"}
+{"current_steps": 105, "total_steps": 224, "loss": 0.2392, "lr": 1.2851391123813075e-05, "epoch": 3.212658227848101, "percentage": 46.88, "elapsed_time": "1:53:11", "remaining_time": "2:08:16"}
+{"current_steps": 106, "total_steps": 224, "loss": 0.2267, "lr": 1.2701239342352223e-05, "epoch": 3.2430379746835443, "percentage": 47.32, "elapsed_time": "1:54:00", "remaining_time": "2:06:55"}
+{"current_steps": 107, "total_steps": 224, "loss": 0.2518, "lr": 1.2550427685616767e-05, "epoch": 3.2734177215189875, "percentage": 47.77, "elapsed_time": "1:55:10", "remaining_time": "2:05:56"}
+{"current_steps": 108, "total_steps": 224, "loss": 0.2554, "lr": 1.239899299480098e-05, "epoch": 3.3037974683544302, "percentage": 48.21, "elapsed_time": "1:56:22", "remaining_time": "2:05:00"}
+{"current_steps": 109, "total_steps": 224, "loss": 0.2353, "lr": 1.2246972263297718e-05, "epoch": 3.3341772151898734, "percentage": 48.66, "elapsed_time": "1:57:29", "remaining_time": "2:03:58"}
+{"current_steps": 110, "total_steps": 224, "loss": 0.244, "lr": 1.2094402627661447e-05, "epoch": 3.3645569620253166, "percentage": 49.11, "elapsed_time": "1:58:30", "remaining_time": "2:02:48"}
+{"current_steps": 111, "total_steps": 224, "loss": 0.2399, "lr": 1.1941321358536278e-05, "epoch": 3.3949367088607594, "percentage": 49.55, "elapsed_time": "1:59:31", "remaining_time": "2:01:40"}
+{"current_steps": 112, "total_steps": 224, "loss": 0.2323, "lr": 1.1787765851551296e-05, "epoch": 3.4253164556962026, "percentage": 50.0, "elapsed_time": "2:00:26", "remaining_time": "2:00:26"}
+{"current_steps": 113, "total_steps": 224, "loss": 0.2554, "lr": 1.1633773618185302e-05, "epoch": 3.4556962025316453, "percentage": 50.45, "elapsed_time": "2:01:45", "remaining_time": "1:59:35"}
+{"current_steps": 114, "total_steps": 224, "loss": 0.2401, "lr": 1.14793822766033e-05, "epoch": 3.4860759493670885, "percentage": 50.89, "elapsed_time": "2:02:55", "remaining_time": "1:58:36"}
+{"current_steps": 115, "total_steps": 224, "loss": 0.2656, "lr": 1.132462954246688e-05, "epoch": 3.5164556962025317, "percentage": 51.34, "elapsed_time": "2:04:16", "remaining_time": "1:57:47"}
+{"current_steps": 116, "total_steps": 224, "loss": 0.2516, "lr": 1.1169553219720828e-05, "epoch": 3.546835443037975, "percentage": 51.79, "elapsed_time": "2:05:23", "remaining_time": "1:56:44"}
+{"current_steps": 117, "total_steps": 224, "loss": 0.2543, "lr": 1.1014191191358118e-05, "epoch": 3.5772151898734177, "percentage": 52.23, "elapsed_time": "2:06:28", "remaining_time": "1:55:39"}
+{"current_steps": 118, "total_steps": 224, "loss": 0.2456, "lr": 1.085858141016566e-05, "epoch": 3.607594936708861, "percentage": 52.68, "elapsed_time": "2:07:32", "remaining_time": "1:54:34"}
+{"current_steps": 119, "total_steps": 224, "loss": 0.257, "lr": 1.070276188945293e-05, "epoch": 3.6379746835443036, "percentage": 53.12, "elapsed_time": "2:08:36", "remaining_time": "1:53:28"}
+{"current_steps": 120, "total_steps": 224, "loss": 0.2309, "lr": 1.0546770693765859e-05, "epoch": 3.668354430379747, "percentage": 53.57, "elapsed_time": "2:09:48", "remaining_time": "1:52:29"}
+{"current_steps": 121, "total_steps": 224, "loss": 0.2567, "lr": 1.0390645929588197e-05, "epoch": 3.69873417721519, "percentage": 54.02, "elapsed_time": "2:10:53", "remaining_time": "1:51:24"}
+{"current_steps": 122, "total_steps": 224, "loss": 0.2461, "lr": 1.0234425736032607e-05, "epoch": 3.729113924050633, "percentage": 54.46, "elapsed_time": "2:11:53", "remaining_time": "1:50:16"}
+{"current_steps": 123, "total_steps": 224, "loss": 0.266, "lr": 1.007814827552384e-05, "epoch": 3.759493670886076, "percentage": 54.91, "elapsed_time": "2:13:11", "remaining_time": "1:49:22"}
+{"current_steps": 124, "total_steps": 224, "loss": 0.2462, "lr": 9.92185172447616e-06, "epoch": 3.7898734177215188, "percentage": 55.36, "elapsed_time": "2:14:15", "remaining_time": "1:48:16"}
+{"current_steps": 125, "total_steps": 224, "loss": 0.2473, "lr": 9.765574263967397e-06, "epoch": 3.820253164556962, "percentage": 55.8, "elapsed_time": "2:15:07", "remaining_time": "1:47:01"}
+{"current_steps": 126, "total_steps": 224, "loss": 0.2449, "lr": 9.609354070411807e-06, "epoch": 3.850632911392405, "percentage": 56.25, "elapsed_time": "2:16:08", "remaining_time": "1:45:53"}
+{"current_steps": 127, "total_steps": 224, "loss": 0.2557, "lr": 9.453229306234143e-06, "epoch": 3.8810126582278484, "percentage": 56.7, "elapsed_time": "2:17:08", "remaining_time": "1:44:45"}
+{"current_steps": 128, "total_steps": 224, "loss": 0.2663, "lr": 9.297238110547075e-06, "epoch": 3.911392405063291, "percentage": 57.14, "elapsed_time": "2:17:50", "remaining_time": "1:43:22"}
+{"current_steps": 129, "total_steps": 224, "loss": 0.2361, "lr": 9.14141858983434e-06, "epoch": 3.9417721518987343, "percentage": 57.59, "elapsed_time": "2:18:53", "remaining_time": "1:42:17"}
+{"current_steps": 130, "total_steps": 224, "loss": 0.2569, "lr": 8.985808808641883e-06, "epoch": 3.972151898734177, "percentage": 58.04, "elapsed_time": "2:19:59", "remaining_time": "1:41:13"}
+{"current_steps": 131, "total_steps": 224, "loss": 0.3476, "lr": 8.830446780279175e-06, "epoch": 4.010126582278481, "percentage": 58.48, "elapsed_time": "2:21:36", "remaining_time": "1:40:31"}
+{"current_steps": 132, "total_steps": 224, "loss": 0.1681, "lr": 8.675370457533122e-06, "epoch": 4.040506329113924, "percentage": 58.93, "elapsed_time": "2:22:38", "remaining_time": "1:39:24"}
+{"current_steps": 133, "total_steps": 224, "loss": 0.1743, "lr": 8.520617723396702e-06, "epoch": 4.0708860759493675, "percentage": 59.38, "elapsed_time": "2:23:42", "remaining_time": "1:38:19"}
+{"current_steps": 134, "total_steps": 224, "loss": 0.174, "lr": 8.366226381814698e-06, "epoch": 4.10126582278481, "percentage": 59.82, "elapsed_time": "2:24:46", "remaining_time": "1:37:14"}
+{"current_steps": 135, "total_steps": 224, "loss": 0.1844, "lr": 8.212234148448708e-06, "epoch": 4.131645569620253, "percentage": 60.27, "elapsed_time": "2:26:09", "remaining_time": "1:36:21"}
+{"current_steps": 136, "total_steps": 224, "loss": 0.2071, "lr": 8.058678641463724e-06, "epoch": 4.162025316455696, "percentage": 60.71, "elapsed_time": "2:27:19", "remaining_time": "1:35:19"}
+{"current_steps": 137, "total_steps": 224, "loss": 0.1633, "lr": 7.905597372338558e-06, "epoch": 4.192405063291139, "percentage": 61.16, "elapsed_time": "2:28:26", "remaining_time": "1:34:15"}
+{"current_steps": 138, "total_steps": 224, "loss": 0.1691, "lr": 7.753027736702283e-06, "epoch": 4.222784810126583, "percentage": 61.61, "elapsed_time": "2:29:24", "remaining_time": "1:33:06"}
+{"current_steps": 139, "total_steps": 224, "loss": 0.184, "lr": 7.601007005199022e-06, "epoch": 4.253164556962025, "percentage": 62.05, "elapsed_time": "2:30:33", "remaining_time": "1:32:04"}
+{"current_steps": 140, "total_steps": 224, "loss": 0.1629, "lr": 7.449572314383237e-06, "epoch": 4.283544303797468, "percentage": 62.5, "elapsed_time": "2:31:36", "remaining_time": "1:30:57"}
+{"current_steps": 141, "total_steps": 224, "loss": 0.1738, "lr": 7.298760657647779e-06, "epoch": 4.313924050632911, "percentage": 62.95, "elapsed_time": "2:32:53", "remaining_time": "1:30:00"}
+{"current_steps": 142, "total_steps": 224, "loss": 0.1742, "lr": 7.148608876186931e-06, "epoch": 4.3443037974683545, "percentage": 63.39, "elapsed_time": "2:33:57", "remaining_time": "1:28:54"}
+{"current_steps": 143, "total_steps": 224, "loss": 0.1832, "lr": 6.999153649996595e-06, "epoch": 4.374683544303798, "percentage": 63.84, "elapsed_time": "2:35:05", "remaining_time": "1:27:51"}
+{"current_steps": 144, "total_steps": 224, "loss": 0.1682, "lr": 6.8504314889138956e-06, "epoch": 4.405063291139241, "percentage": 64.29, "elapsed_time": "2:36:21", "remaining_time": "1:26:52"}
+{"current_steps": 145, "total_steps": 224, "loss": 0.164, "lr": 6.702478723698336e-06, "epoch": 4.435443037974683, "percentage": 64.73, "elapsed_time": "2:37:27", "remaining_time": "1:25:47"}
+{"current_steps": 146, "total_steps": 224, "loss": 0.168, "lr": 6.555331497156671e-06, "epoch": 4.465822784810126, "percentage": 65.18, "elapsed_time": "2:38:30", "remaining_time": "1:24:41"}
+{"current_steps": 147, "total_steps": 224, "loss": 0.174, "lr": 6.4090257553137566e-06, "epoch": 4.49620253164557, "percentage": 65.62, "elapsed_time": "2:39:36", "remaining_time": "1:23:36"}
+{"current_steps": 148, "total_steps": 224, "loss": 0.1665, "lr": 6.263597238631405e-06, "epoch": 4.526582278481013, "percentage": 66.07, "elapsed_time": "2:40:43", "remaining_time": "1:22:31"}
+{"current_steps": 149, "total_steps": 224, "loss": 0.2019, "lr": 6.119081473277502e-06, "epoch": 4.556962025316456, "percentage": 66.52, "elapsed_time": "2:41:44", "remaining_time": "1:21:24"}
+{"current_steps": 150, "total_steps": 224, "loss": 0.1534, "lr": 5.975513762447465e-06, "epoch": 4.587341772151898, "percentage": 66.96, "elapsed_time": "2:42:28", "remaining_time": "1:20:09"}
+{"current_steps": 151, "total_steps": 224, "loss": 0.1527, "lr": 5.832929177740134e-06, "epoch": 4.6177215189873415, "percentage": 67.41, "elapsed_time": "2:43:20", "remaining_time": "1:18:58"}
+{"current_steps": 152, "total_steps": 224, "loss": 0.1818, "lr": 5.6913625505902966e-06, "epoch": 4.648101265822785, "percentage": 67.86, "elapsed_time": "2:44:23", "remaining_time": "1:17:52"}
+{"current_steps": 153, "total_steps": 224, "loss": 0.1666, "lr": 5.550848463759835e-06, "epoch": 4.678481012658228, "percentage": 68.3, "elapsed_time": "2:45:26", "remaining_time": "1:16:46"}
+{"current_steps": 154, "total_steps": 224, "loss": 0.1803, "lr": 5.411421242889643e-06, "epoch": 4.708860759493671, "percentage": 68.75, "elapsed_time": "2:46:29", "remaining_time": "1:15:40"}
+{"current_steps": 155, "total_steps": 224, "loss": 0.1732, "lr": 5.273114948114346e-06, "epoch": 4.739240506329114, "percentage": 69.2, "elapsed_time": "2:47:30", "remaining_time": "1:14:34"}
+{"current_steps": 156, "total_steps": 224, "loss": 0.178, "lr": 5.135963365741892e-06, "epoch": 4.769620253164557, "percentage": 69.64, "elapsed_time": "2:48:37", "remaining_time": "1:13:29"}
+{"current_steps": 157, "total_steps": 224, "loss": 0.1566, "lr": 5.000000000000003e-06, "epoch": 4.8, "percentage": 70.09, "elapsed_time": "2:49:54", "remaining_time": "1:12:30"}
+{"current_steps": 158, "total_steps": 224, "loss": 0.1735, "lr": 4.865258064851579e-06, "epoch": 4.830379746835443, "percentage": 70.54, "elapsed_time": "2:50:47", "remaining_time": "1:11:20"}
+{"current_steps": 159, "total_steps": 224, "loss": 0.1789, "lr": 4.731770475880995e-06, "epoch": 4.860759493670886, "percentage": 70.98, "elapsed_time": "2:51:37", "remaining_time": "1:10:09"}
+{"current_steps": 160, "total_steps": 224, "loss": 0.1603, "lr": 4.599569842253244e-06, "epoch": 4.891139240506329, "percentage": 71.43, "elapsed_time": "2:52:31", "remaining_time": "1:09:00"}
+{"current_steps": 161, "total_steps": 224, "loss": 0.1741, "lr": 4.468688458748006e-06, "epoch": 4.921518987341772, "percentage": 71.88, "elapsed_time": "2:53:28", "remaining_time": "1:07:52"}
+{"current_steps": 162, "total_steps": 224, "loss": 0.1932, "lr": 4.339158297870469e-06, "epoch": 4.951898734177215, "percentage": 72.32, "elapsed_time": "2:54:35", "remaining_time": "1:06:49"}
+{"current_steps": 163, "total_steps": 224, "loss": 0.2334, "lr": 4.211011002040885e-06, "epoch": 4.982278481012658, "percentage": 72.77, "elapsed_time": "2:55:50", "remaining_time": "1:05:48"}
+{"current_steps": 164, "total_steps": 224, "loss": 0.1724, "lr": 4.084277875864776e-06, "epoch": 5.020253164556962, "percentage": 73.21, "elapsed_time": "2:57:31", "remaining_time": "1:04:56"}
+{"current_steps": 165, "total_steps": 224, "loss": 0.1182, "lr": 3.958989878485644e-06, "epoch": 5.050632911392405, "percentage": 73.66, "elapsed_time": "2:58:30", "remaining_time": "1:03:49"}
+{"current_steps": 166, "total_steps": 224, "loss": 0.1102, "lr": 3.83517761602209e-06, "epoch": 5.0810126582278485, "percentage": 74.11, "elapsed_time": "2:59:29", "remaining_time": "1:02:42"}
+{"current_steps": 167, "total_steps": 224, "loss": 0.1421, "lr": 3.712871334091154e-06, "epoch": 5.111392405063291, "percentage": 74.55, "elapsed_time": "3:00:47", "remaining_time": "1:01:42"}
+{"current_steps": 168, "total_steps": 224, "loss": 0.1144, "lr": 3.592100910419738e-06, "epoch": 5.141772151898734, "percentage": 75.0, "elapsed_time": "3:01:41", "remaining_time": "1:00:33"}
+{"current_steps": 169, "total_steps": 224, "loss": 0.1236, "lr": 3.4728958475459052e-06, "epoch": 5.172151898734177, "percentage": 75.45, "elapsed_time": "3:02:37", "remaining_time": "0:59:25"}
+{"current_steps": 170, "total_steps": 224, "loss": 0.1456, "lr": 3.355285265611784e-06, "epoch": 5.2025316455696204, "percentage": 75.89, "elapsed_time": "3:03:54", "remaining_time": "0:58:25"}
+{"current_steps": 171, "total_steps": 224, "loss": 0.1286, "lr": 3.2392978952499553e-06, "epoch": 5.232911392405064, "percentage": 76.34, "elapsed_time": "3:05:02", "remaining_time": "0:57:21"}
+{"current_steps": 172, "total_steps": 224, "loss": 0.1355, "lr": 3.1249620705649417e-06, "epoch": 5.263291139240506, "percentage": 76.79, "elapsed_time": "3:06:19", "remaining_time": "0:56:19"}
+{"current_steps": 173, "total_steps": 224, "loss": 0.1131, "lr": 3.0123057222115835e-06, "epoch": 5.293670886075949, "percentage": 77.23, "elapsed_time": "3:07:17", "remaining_time": "0:55:12"}
+{"current_steps": 174, "total_steps": 224, "loss": 0.1419, "lr": 2.9013563705719673e-06, "epoch": 5.324050632911392, "percentage": 77.68, "elapsed_time": "3:08:30", "remaining_time": "0:54:10"}
+{"current_steps": 175, "total_steps": 224, "loss": 0.1366, "lr": 2.7921411190325753e-06, "epoch": 5.3544303797468356, "percentage": 78.12, "elapsed_time": "3:09:32", "remaining_time": "0:53:04"}
+{"current_steps": 176, "total_steps": 224, "loss": 0.1095, "lr": 2.6846866473633126e-06, "epoch": 5.384810126582279, "percentage": 78.57, "elapsed_time": "3:10:30", "remaining_time": "0:51:57"}
+{"current_steps": 177, "total_steps": 224, "loss": 0.1325, "lr": 2.579019205199992e-06, "epoch": 5.415189873417722, "percentage": 79.02, "elapsed_time": "3:11:38", "remaining_time": "0:50:53"}
+{"current_steps": 178, "total_steps": 224, "loss": 0.1153, "lr": 2.4751646056319334e-06, "epoch": 5.445569620253164, "percentage": 79.46, "elapsed_time": "3:12:39", "remaining_time": "0:49:47"}
+{"current_steps": 179, "total_steps": 224, "loss": 0.131, "lr": 2.373148218896182e-06, "epoch": 5.4759493670886075, "percentage": 79.91, "elapsed_time": "3:13:47", "remaining_time": "0:48:43"}
+{"current_steps": 180, "total_steps": 224, "loss": 0.1127, "lr": 2.2729949661798876e-06, "epoch": 5.506329113924051, "percentage": 80.36, "elapsed_time": "3:14:42", "remaining_time": "0:47:35"}
+{"current_steps": 181, "total_steps": 224, "loss": 0.1315, "lr": 2.174729313532433e-06, "epoch": 5.536708860759494, "percentage": 80.8, "elapsed_time": "3:15:59", "remaining_time": "0:46:33"}
+{"current_steps": 182, "total_steps": 224, "loss": 0.1264, "lr": 2.078375265888707e-06, "epoch": 5.567088607594937, "percentage": 81.25, "elapsed_time": "3:17:13", "remaining_time": "0:45:30"}
+{"current_steps": 183, "total_steps": 224, "loss": 0.1058, "lr": 1.9839563612050273e-06, "epoch": 5.597468354430379, "percentage": 81.7, "elapsed_time": "3:18:10", "remaining_time": "0:44:23"}
+{"current_steps": 184, "total_steps": 224, "loss": 0.1349, "lr": 1.8914956647091497e-06, "epoch": 5.627848101265823, "percentage": 82.14, "elapsed_time": "3:19:09", "remaining_time": "0:43:17"}
+{"current_steps": 185, "total_steps": 224, "loss": 0.0931, "lr": 1.8010157632657544e-06, "epoch": 5.658227848101266, "percentage": 82.59, "elapsed_time": "3:19:55", "remaining_time": "0:42:08"}
+{"current_steps": 186, "total_steps": 224, "loss": 0.1324, "lr": 1.7125387598587862e-06, "epoch": 5.688607594936709, "percentage": 83.04, "elapsed_time": "3:21:06", "remaining_time": "0:41:05"}
+{"current_steps": 187, "total_steps": 224, "loss": 0.1155, "lr": 1.6260862681919965e-06, "epoch": 5.718987341772152, "percentage": 83.48, "elapsed_time": "3:22:14", "remaining_time": "0:40:00"}
+{"current_steps": 188, "total_steps": 224, "loss": 0.1266, "lr": 1.5416794074090258e-06, "epoch": 5.749367088607595, "percentage": 83.93, "elapsed_time": "3:23:19", "remaining_time": "0:38:56"}
+{"current_steps": 189, "total_steps": 224, "loss": 0.1401, "lr": 1.459338796934293e-06, "epoch": 5.779746835443038, "percentage": 84.38, "elapsed_time": "3:24:41", "remaining_time": "0:37:54"}
+{"current_steps": 190, "total_steps": 224, "loss": 0.1179, "lr": 1.3790845514359363e-06, "epoch": 5.810126582278481, "percentage": 84.82, "elapsed_time": "3:25:29", "remaining_time": "0:36:46"}
+{"current_steps": 191, "total_steps": 224, "loss": 0.1041, "lr": 1.300936275912098e-06, "epoch": 5.840506329113924, "percentage": 85.27, "elapsed_time": "3:26:26", "remaining_time": "0:35:40"}
+{"current_steps": 192, "total_steps": 224, "loss": 0.1193, "lr": 1.224913060901688e-06, "epoch": 5.870886075949367, "percentage": 85.71, "elapsed_time": "3:27:27", "remaining_time": "0:34:34"}
+{"current_steps": 193, "total_steps": 224, "loss": 0.1186, "lr": 1.1510334778208332e-06, "epoch": 5.9012658227848105, "percentage": 86.16, "elapsed_time": "3:28:29", "remaining_time": "0:33:29"}
+{"current_steps": 194, "total_steps": 224, "loss": 0.1214, "lr": 1.0793155744261352e-06, "epoch": 5.931645569620253, "percentage": 86.61, "elapsed_time": "3:29:20", "remaining_time": "0:32:22"}
+{"current_steps": 195, "total_steps": 224, "loss": 0.1428, "lr": 1.0097768704058542e-06, "epoch": 5.962025316455696, "percentage": 87.05, "elapsed_time": "3:30:22", "remaining_time": "0:31:17"}
+{"current_steps": 196, "total_steps": 224, "loss": 0.1609, "lr": 9.424343531000968e-07, "epoch": 5.992405063291139, "percentage": 87.5, "elapsed_time": "3:31:27", "remaining_time": "0:30:12"}
+{"current_steps": 197, "total_steps": 224, "loss": 0.0996, "lr": 8.773044733510338e-07, "epoch": 6.030379746835443, "percentage": 87.95, "elapsed_time": "3:33:07", "remaining_time": "0:29:12"}
+{"current_steps": 198, "total_steps": 224, "loss": 0.1127, "lr": 8.144031414842012e-07, "epoch": 6.060759493670886, "percentage": 88.39, "elapsed_time": "3:34:09", "remaining_time": "0:28:07"}
+{"current_steps": 199, "total_steps": 224, "loss": 0.1123, "lr": 7.537457234218271e-07, "epoch": 6.091139240506329, "percentage": 88.84, "elapsed_time": "3:35:09", "remaining_time": "0:27:01"}
+{"current_steps": 200, "total_steps": 224, "loss": 0.106, "lr": 6.953470369291349e-07, "epoch": 6.121518987341772, "percentage": 89.29, "elapsed_time": "3:36:26", "remaining_time": "0:25:58"}
+{"current_steps": 201, "total_steps": 224, "loss": 0.0966, "lr": 6.392213479945852e-07, "epoch": 6.151898734177215, "percentage": 89.73, "elapsed_time": "3:37:23", "remaining_time": "0:24:52"}
+{"current_steps": 202, "total_steps": 224, "loss": 0.1012, "lr": 5.853823673448877e-07, "epoch": 6.182278481012658, "percentage": 90.18, "elapsed_time": "3:38:37", "remaining_time": "0:23:48"}
+{"current_steps": 203, "total_steps": 224, "loss": 0.1017, "lr": 5.33843247095659e-07, "epoch": 6.2126582278481015, "percentage": 90.62, "elapsed_time": "3:39:39", "remaining_time": "0:22:43"}
+{"current_steps": 204, "total_steps": 224, "loss": 0.1053, "lr": 4.846165775385459e-07, "epoch": 6.243037974683545, "percentage": 91.07, "elapsed_time": "3:40:38", "remaining_time": "0:21:37"}
+{"current_steps": 205, "total_steps": 224, "loss": 0.1128, "lr": 4.3771438406559173e-07, "epoch": 6.273417721518987, "percentage": 91.52, "elapsed_time": "3:41:50", "remaining_time": "0:20:33"}
+{"current_steps": 206, "total_steps": 224, "loss": 0.0992, "lr": 3.931481242315993e-07, "epoch": 6.30379746835443, "percentage": 91.96, "elapsed_time": "3:43:00", "remaining_time": "0:19:29"}
+{"current_steps": 207, "total_steps": 224, "loss": 0.1047, "lr": 3.5092868495520294e-07, "epoch": 6.334177215189873, "percentage": 92.41, "elapsed_time": "3:44:03", "remaining_time": "0:18:24"}
+{"current_steps": 208, "total_steps": 224, "loss": 0.1037, "lr": 3.110663798593616e-07, "epoch": 6.364556962025317, "percentage": 92.86, "elapsed_time": "3:45:00", "remaining_time": "0:17:18"}
+{"current_steps": 209, "total_steps": 224, "loss": 0.1025, "lr": 2.735709467518699e-07, "epoch": 6.39493670886076, "percentage": 93.3, "elapsed_time": "3:45:54", "remaining_time": "0:16:12"}
+{"current_steps": 210, "total_steps": 224, "loss": 0.1022, "lr": 2.384515452465475e-07, "epoch": 6.425316455696202, "percentage": 93.75, "elapsed_time": "3:47:06", "remaining_time": "0:15:08"}
+{"current_steps": 211, "total_steps": 224, "loss": 0.091, "lr": 2.0571675452567997e-07, "epoch": 6.455696202531645, "percentage": 94.2, "elapsed_time": "3:47:54", "remaining_time": "0:14:02"}
+{"current_steps": 212, "total_steps": 224, "loss": 0.0965, "lr": 1.7537457124423896e-07, "epoch": 6.4860759493670885, "percentage": 94.64, "elapsed_time": "3:48:57", "remaining_time": "0:12:57"}
+{"current_steps": 213, "total_steps": 224, "loss": 0.1106, "lr": 1.474324075764111e-07, "epoch": 6.516455696202532, "percentage": 95.09, "elapsed_time": "3:49:56", "remaining_time": "0:11:52"}
+{"current_steps": 214, "total_steps": 224, "loss": 0.1049, "lr": 1.2189708940490653e-07, "epoch": 6.546835443037975, "percentage": 95.54, "elapsed_time": "3:51:00", "remaining_time": "0:10:47"}
+{"current_steps": 215, "total_steps": 224, "loss": 0.1036, "lr": 9.877485465349057e-08, "epoch": 6.577215189873417, "percentage": 95.98, "elapsed_time": "3:52:05", "remaining_time": "0:09:42"}
+{"current_steps": 216, "total_steps": 224, "loss": 0.1022, "lr": 7.807135176314707e-08, "epoch": 6.6075949367088604, "percentage": 96.43, "elapsed_time": "3:53:14", "remaining_time": "0:08:38"}
+{"current_steps": 217, "total_steps": 224, "loss": 0.1095, "lr": 5.979163831223988e-08, "epoch": 6.637974683544304, "percentage": 96.88, "elapsed_time": "3:54:19", "remaining_time": "0:07:33"}
+{"current_steps": 218, "total_steps": 224, "loss": 0.0987, "lr": 4.394017978101905e-08, "epoch": 6.668354430379747, "percentage": 97.32, "elapsed_time": "3:55:11", "remaining_time": "0:06:28"}
+{"current_steps": 219, "total_steps": 224, "loss": 0.1153, "lr": 3.0520848460765525e-08, "epoch": 6.69873417721519, "percentage": 97.77, "elapsed_time": "3:56:18", "remaining_time": "0:05:23"}
+{"current_steps": 220, "total_steps": 224, "loss": 0.1203, "lr": 1.9536922507841227e-08, "epoch": 6.729113924050633, "percentage": 98.21, "elapsed_time": "3:57:35", "remaining_time": "0:04:19"}
+{"current_steps": 221, "total_steps": 224, "loss": 0.101, "lr": 1.099108514288627e-08, "epoch": 6.759493670886076, "percentage": 98.66, "elapsed_time": "3:58:45", "remaining_time": "0:03:14"}
+{"current_steps": 222, "total_steps": 224, "loss": 0.1063, "lr": 4.885423995341088e-09, "epoch": 6.789873417721519, "percentage": 99.11, "elapsed_time": "3:59:53", "remaining_time": "0:02:09"}
+{"current_steps": 223, "total_steps": 224, "loss": 0.1022, "lr": 1.2214305934699078e-09, "epoch": 6.820253164556962, "percentage": 99.55, "elapsed_time": "4:01:03", "remaining_time": "0:01:04"}
+{"current_steps": 224, "total_steps": 224, "loss": 0.108, "lr": 0.0, "epoch": 6.850632911392405, "percentage": 100.0, "elapsed_time": "4:02:03", "remaining_time": "0:00:00"}
+{"current_steps": 224, "total_steps": 224, "epoch": 6.850632911392405, "percentage": 100.0, "elapsed_time": "4:03:05", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1610 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.850632911392405,
+  "eval_steps": 500,
+  "global_step": 224,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.030379746835443037,
+      "grad_norm": 6.006213471081438,
+      "learning_rate": 8.695652173913044e-07,
+      "loss": 0.7917,
+      "step": 1
+    },
+    {
+      "epoch": 0.060759493670886074,
+      "grad_norm": 6.2254607837063265,
+      "learning_rate": 1.7391304347826088e-06,
+      "loss": 0.8352,
+      "step": 2
+    },
+    {
+      "epoch": 0.09113924050632911,
+      "grad_norm": 6.033293241527638,
+      "learning_rate": 2.6086956521739132e-06,
+      "loss": 0.8056,
+      "step": 3
+    },
+    {
+      "epoch": 0.12151898734177215,
+      "grad_norm": 5.6177843051297724,
+      "learning_rate": 3.4782608695652175e-06,
+      "loss": 0.7998,
+      "step": 4
+    },
+    {
+      "epoch": 0.1518987341772152,
+      "grad_norm": 4.723227334218072,
+      "learning_rate": 4.347826086956522e-06,
+      "loss": 0.7966,
+      "step": 5
+    },
+    {
+      "epoch": 0.18227848101265823,
+      "grad_norm": 2.5374960923382606,
+      "learning_rate": 5.2173913043478265e-06,
+      "loss": 0.7432,
+      "step": 6
+    },
+    {
+      "epoch": 0.21265822784810126,
+      "grad_norm": 2.126329485485419,
+      "learning_rate": 6.086956521739132e-06,
+      "loss": 0.738,
+      "step": 7
+    },
+    {
+      "epoch": 0.2430379746835443,
+      "grad_norm": 3.873369258557868,
+      "learning_rate": 6.956521739130435e-06,
+      "loss": 0.7192,
+      "step": 8
+    },
+    {
+      "epoch": 0.27341772151898736,
+      "grad_norm": 3.899288948622671,
+      "learning_rate": 7.82608695652174e-06,
+      "loss": 0.698,
+      "step": 9
+    },
+    {
+      "epoch": 0.3037974683544304,
+      "grad_norm": 4.121150199216906,
+      "learning_rate": 8.695652173913044e-06,
+      "loss": 0.6933,
+      "step": 10
+    },
+    {
+      "epoch": 0.3341772151898734,
+      "grad_norm": 4.253897850285379,
+      "learning_rate": 9.565217391304349e-06,
+      "loss": 0.6662,
+      "step": 11
+    },
+    {
+      "epoch": 0.36455696202531646,
+      "grad_norm": 3.503928981732218,
+      "learning_rate": 1.0434782608695653e-05,
+      "loss": 0.641,
+      "step": 12
+    },
+    {
+      "epoch": 0.3949367088607595,
+      "grad_norm": 2.1797633391983697,
+      "learning_rate": 1.1304347826086957e-05,
+      "loss": 0.6131,
+      "step": 13
+    },
+    {
+      "epoch": 0.4253164556962025,
+      "grad_norm": 1.9144365807987356,
+      "learning_rate": 1.2173913043478263e-05,
+      "loss": 0.6092,
+      "step": 14
+    },
+    {
+      "epoch": 0.45569620253164556,
+      "grad_norm": 2.4090527409072395,
+      "learning_rate": 1.3043478260869566e-05,
+      "loss": 0.5987,
+      "step": 15
+    },
+    {
+      "epoch": 0.4860759493670886,
+      "grad_norm": 2.1201232027340455,
+      "learning_rate": 1.391304347826087e-05,
+      "loss": 0.561,
+      "step": 16
+    },
+    {
+      "epoch": 0.5164556962025316,
+      "grad_norm": 1.2244003008036553,
+      "learning_rate": 1.4782608695652174e-05,
+      "loss": 0.5766,
+      "step": 17
+    },
+    {
+      "epoch": 0.5468354430379747,
+      "grad_norm": 1.146399280795341,
+      "learning_rate": 1.565217391304348e-05,
+      "loss": 0.566,
+      "step": 18
+    },
+    {
+      "epoch": 0.5772151898734177,
+      "grad_norm": 1.3934479350243683,
+      "learning_rate": 1.6521739130434785e-05,
+      "loss": 0.5672,
+      "step": 19
+    },
+    {
+      "epoch": 0.6075949367088608,
+      "grad_norm": 0.974415129473555,
+      "learning_rate": 1.739130434782609e-05,
+      "loss": 0.599,
+      "step": 20
+    },
+    {
+      "epoch": 0.6379746835443038,
+      "grad_norm": 0.9919902220679716,
+      "learning_rate": 1.8260869565217393e-05,
+      "loss": 0.529,
+      "step": 21
+    },
+    {
+      "epoch": 0.6683544303797468,
+      "grad_norm": 1.040576121443834,
+      "learning_rate": 1.9130434782608697e-05,
+      "loss": 0.5438,
+      "step": 22
+    },
+    {
+      "epoch": 0.6987341772151898,
+      "grad_norm": 0.7352410276728014,
+      "learning_rate": 2e-05,
+      "loss": 0.5391,
+      "step": 23
+    },
+    {
+      "epoch": 0.7291139240506329,
+      "grad_norm": 0.828148529201473,
+      "learning_rate": 1.999877856940653e-05,
+      "loss": 0.5525,
+      "step": 24
+    },
+    {
+      "epoch": 0.759493670886076,
+      "grad_norm": 0.8269176543378692,
+      "learning_rate": 1.999511457600466e-05,
+      "loss": 0.5144,
+      "step": 25
+    },
+    {
+      "epoch": 0.789873417721519,
+      "grad_norm": 0.6869010086082622,
+      "learning_rate": 1.9989008914857115e-05,
+      "loss": 0.5047,
+      "step": 26
+    },
+    {
+      "epoch": 0.8202531645569621,
+      "grad_norm": 0.7689050169156533,
+      "learning_rate": 1.998046307749216e-05,
+      "loss": 0.5478,
+      "step": 27
+    },
+    {
+      "epoch": 0.850632911392405,
+      "grad_norm": 0.6354264694082578,
+      "learning_rate": 1.9969479151539238e-05,
+      "loss": 0.5212,
+      "step": 28
+    },
+    {
+      "epoch": 0.8810126582278481,
+      "grad_norm": 0.6922907069132699,
+      "learning_rate": 1.9956059820218982e-05,
+      "loss": 0.5033,
+      "step": 29
+    },
+    {
+      "epoch": 0.9113924050632911,
+      "grad_norm": 0.6323752752121719,
+      "learning_rate": 1.9940208361687762e-05,
+      "loss": 0.5258,
+      "step": 30
+    },
+    {
+      "epoch": 0.9417721518987342,
+      "grad_norm": 0.5593183327477625,
+      "learning_rate": 1.9921928648236855e-05,
+      "loss": 0.4979,
+      "step": 31
+    },
+    {
+      "epoch": 0.9721518987341772,
+      "grad_norm": 0.6622551856194377,
+      "learning_rate": 1.990122514534651e-05,
+      "loss": 0.5248,
+      "step": 32
+    },
+    {
+      "epoch": 1.010126582278481,
+      "grad_norm": 0.6764945387024673,
+      "learning_rate": 1.9878102910595097e-05,
+      "loss": 0.6827,
+      "step": 33
+    },
+    {
+      "epoch": 1.040506329113924,
+      "grad_norm": 0.6561499543200164,
+      "learning_rate": 1.985256759242359e-05,
+      "loss": 0.469,
+      "step": 34
+    },
+    {
+      "epoch": 1.070886075949367,
+      "grad_norm": 0.5298141480802675,
+      "learning_rate": 1.982462542875576e-05,
+      "loss": 0.4372,
+      "step": 35
+    },
+    {
+      "epoch": 1.1012658227848102,
+      "grad_norm": 0.5505361666397994,
+      "learning_rate": 1.979428324547432e-05,
+      "loss": 0.4661,
+      "step": 36
+    },
+    {
+      "epoch": 1.1316455696202532,
+      "grad_norm": 0.5105637977979922,
+      "learning_rate": 1.9761548454753455e-05,
+      "loss": 0.3946,
+      "step": 37
+    },
+    {
+      "epoch": 1.1620253164556962,
+      "grad_norm": 0.6434975406027199,
+      "learning_rate": 1.972642905324813e-05,
+      "loss": 0.5268,
+      "step": 38
+    },
+    {
+      "epoch": 1.1924050632911392,
+      "grad_norm": 0.6008580032405805,
+      "learning_rate": 1.9688933620140638e-05,
+      "loss": 0.4601,
+      "step": 39
+    },
+    {
+      "epoch": 1.2227848101265824,
+      "grad_norm": 0.5959585981147149,
+      "learning_rate": 1.96490713150448e-05,
+      "loss": 0.4591,
+      "step": 40
+    },
+    {
+      "epoch": 1.2531645569620253,
+      "grad_norm": 0.546478161597411,
+      "learning_rate": 1.9606851875768404e-05,
+      "loss": 0.4329,
+      "step": 41
+    },
+    {
+      "epoch": 1.2835443037974683,
+      "grad_norm": 0.6283874355809709,
+      "learning_rate": 1.956228561593441e-05,
+      "loss": 0.4572,
+      "step": 42
+    },
+    {
+      "epoch": 1.3139240506329113,
+      "grad_norm": 0.5615002194011511,
+      "learning_rate": 1.9515383422461457e-05,
+      "loss": 0.4369,
+      "step": 43
+    },
+    {
+      "epoch": 1.3443037974683545,
+      "grad_norm": 0.6258423268174595,
+      "learning_rate": 1.9466156752904344e-05,
+      "loss": 0.4316,
+      "step": 44
+    },
+    {
+      "epoch": 1.3746835443037975,
+      "grad_norm": 0.5534904501954303,
+      "learning_rate": 1.9414617632655114e-05,
+      "loss": 0.4249,
+      "step": 45
+    },
+    {
+      "epoch": 1.4050632911392404,
+      "grad_norm": 0.669119095568495,
+      "learning_rate": 1.9360778652005416e-05,
+      "loss": 0.4741,
+      "step": 46
+    },
+    {
+      "epoch": 1.4354430379746836,
+      "grad_norm": 0.5093735104578105,
+      "learning_rate": 1.9304652963070868e-05,
+      "loss": 0.4113,
+      "step": 47
+    },
+    {
+      "epoch": 1.4658227848101266,
+      "grad_norm": 0.6286618048992411,
+      "learning_rate": 1.9246254276578175e-05,
+      "loss": 0.4209,
+      "step": 48
+    },
+    {
+      "epoch": 1.4962025316455696,
+      "grad_norm": 0.686238431846376,
+      "learning_rate": 1.9185596858515797e-05,
+      "loss": 0.4852,
+      "step": 49
+    },
+    {
+      "epoch": 1.5265822784810128,
+      "grad_norm": 0.5083899652707847,
+      "learning_rate": 1.9122695526648968e-05,
+      "loss": 0.3972,
+      "step": 50
+    },
+    {
+      "epoch": 1.5569620253164556,
+      "grad_norm": 0.5598850359421916,
+      "learning_rate": 1.905756564689991e-05,
+      "loss": 0.4913,
+      "step": 51
+    },
+    {
+      "epoch": 1.5873417721518988,
+      "grad_norm": 0.5766825647521311,
+      "learning_rate": 1.8990223129594146e-05,
+      "loss": 0.4621,
+      "step": 52
+    },
+    {
+      "epoch": 1.6177215189873417,
+      "grad_norm": 0.5086207648877343,
+      "learning_rate": 1.8920684425573865e-05,
+      "loss": 0.418,
+      "step": 53
+    },
+    {
+      "epoch": 1.6481012658227847,
+      "grad_norm": 0.5873176022167675,
+      "learning_rate": 1.884896652217917e-05,
+      "loss": 0.4546,
+      "step": 54
+    },
+    {
+      "epoch": 1.678481012658228,
+      "grad_norm": 0.5303690045849334,
+      "learning_rate": 1.877508693909831e-05,
+      "loss": 0.4214,
+      "step": 55
+    },
+    {
+      "epoch": 1.7088607594936709,
+      "grad_norm": 0.49337675464597536,
+      "learning_rate": 1.8699063724087905e-05,
+      "loss": 0.4144,
+      "step": 56
+    },
+    {
+      "epoch": 1.7392405063291139,
+      "grad_norm": 0.5223857062364483,
+      "learning_rate": 1.862091544856407e-05,
+      "loss": 0.4226,
+      "step": 57
+    },
+    {
+      "epoch": 1.769620253164557,
+      "grad_norm": 0.4568296082068541,
+      "learning_rate": 1.854066120306571e-05,
+      "loss": 0.3996,
+      "step": 58
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.548700809584534,
+      "learning_rate": 1.8458320592590976e-05,
+      "loss": 0.4603,
+      "step": 59
+    },
+    {
+      "epoch": 1.830379746835443,
+      "grad_norm": 0.4657778954869675,
+      "learning_rate": 1.837391373180801e-05,
+      "loss": 0.4323,
+      "step": 60
+    },
+    {
+      "epoch": 1.8607594936708862,
+      "grad_norm": 0.5585461501887276,
+      "learning_rate": 1.8287461240141217e-05,
+      "loss": 0.4237,
+      "step": 61
+    },
+    {
+      "epoch": 1.891139240506329,
+      "grad_norm": 0.5017239451917875,
+      "learning_rate": 1.8198984236734246e-05,
+      "loss": 0.3994,
+      "step": 62
+    },
+    {
+      "epoch": 1.9215189873417722,
+      "grad_norm": 0.48711586534451035,
+      "learning_rate": 1.8108504335290852e-05,
+      "loss": 0.4519,
+      "step": 63
+    },
+    {
+      "epoch": 1.9518987341772152,
+      "grad_norm": 0.48646155441739797,
+      "learning_rate": 1.8016043638794975e-05,
+      "loss": 0.4467,
+      "step": 64
+    },
+    {
+      "epoch": 1.9822784810126581,
+      "grad_norm": 0.6897580966520201,
+      "learning_rate": 1.7921624734111292e-05,
+      "loss": 0.5046,
+      "step": 65
+    },
+    {
+      "epoch": 2.020253164556962,
+      "grad_norm": 0.5631698052635786,
+      "learning_rate": 1.7825270686467567e-05,
+      "loss": 0.4692,
+      "step": 66
+    },
+    {
+      "epoch": 2.050632911392405,
+      "grad_norm": 0.6468306572972523,
+      "learning_rate": 1.7727005033820117e-05,
+      "loss": 0.3942,
+      "step": 67
+    },
+    {
+      "epoch": 2.081012658227848,
+      "grad_norm": 0.5218203561260673,
+      "learning_rate": 1.762685178110382e-05,
+      "loss": 0.3286,
+      "step": 68
+    },
+    {
+      "epoch": 2.1113924050632913,
+      "grad_norm": 0.7071640994190285,
+      "learning_rate": 1.752483539436807e-05,
+      "loss": 0.3418,
+      "step": 69
+    },
+    {
+      "epoch": 2.141772151898734,
+      "grad_norm": 0.5968775859817312,
+      "learning_rate": 1.7420980794800013e-05,
+      "loss": 0.3328,
+      "step": 70
+    },
+    {
+      "epoch": 2.1721518987341772,
+      "grad_norm": 0.6417220025244813,
+      "learning_rate": 1.731531335263669e-05,
+      "loss": 0.3394,
+      "step": 71
+    },
+    {
+      "epoch": 2.2025316455696204,
+      "grad_norm": 0.5311259420709453,
+      "learning_rate": 1.720785888096743e-05,
+      "loss": 0.3315,
+      "step": 72
+    },
+    {
+      "epoch": 2.232911392405063,
+      "grad_norm": 0.6830204026929048,
+      "learning_rate": 1.7098643629428035e-05,
+      "loss": 0.3865,
+      "step": 73
+    },
+    {
+      "epoch": 2.2632911392405064,
+      "grad_norm": 0.47877101908626185,
+      "learning_rate": 1.698769427778842e-05,
+      "loss": 0.3154,
+      "step": 74
+    },
+    {
+      "epoch": 2.293670886075949,
+      "grad_norm": 0.4643666155507386,
+      "learning_rate": 1.687503792943506e-05,
+      "loss": 0.3249,
+      "step": 75
+    },
+    {
+      "epoch": 2.3240506329113924,
+      "grad_norm": 0.5212861098993654,
+      "learning_rate": 1.6760702104750046e-05,
+      "loss": 0.3314,
+      "step": 76
+    },
+    {
+      "epoch": 2.3544303797468356,
+      "grad_norm": 0.5422090304154028,
+      "learning_rate": 1.664471473438822e-05,
+      "loss": 0.3774,
+      "step": 77
+    },
+    {
+      "epoch": 2.3848101265822783,
+      "grad_norm": 0.40218697770413736,
+      "learning_rate": 1.6527104152454096e-05,
+      "loss": 0.2784,
+      "step": 78
+    },
+    {
+      "epoch": 2.4151898734177215,
+      "grad_norm": 0.6589258015531194,
+      "learning_rate": 1.6407899089580263e-05,
+      "loss": 0.383,
+      "step": 79
+    },
+    {
+      "epoch": 2.4455696202531647,
+      "grad_norm": 0.5430798030074878,
+      "learning_rate": 1.628712866590885e-05,
+      "loss": 0.3565,
+      "step": 80
+    },
+    {
+      "epoch": 2.4759493670886075,
+      "grad_norm": 0.5073906623339022,
+      "learning_rate": 1.6164822383977912e-05,
+      "loss": 0.3569,
+      "step": 81
+    },
+    {
+      "epoch": 2.5063291139240507,
+      "grad_norm": 0.5050027438908327,
+      "learning_rate": 1.604101012151436e-05,
+      "loss": 0.3209,
+      "step": 82
+    },
+    {
+      "epoch": 2.536708860759494,
+      "grad_norm": 0.4765935907526067,
+      "learning_rate": 1.5915722124135227e-05,
+      "loss": 0.3297,
+      "step": 83
+    },
+    {
+      "epoch": 2.5670886075949366,
+      "grad_norm": 0.46207789314346887,
+      "learning_rate": 1.5788988997959115e-05,
+      "loss": 0.3044,
+      "step": 84
+    },
+    {
+      "epoch": 2.59746835443038,
+      "grad_norm": 0.5752561163345511,
+      "learning_rate": 1.5660841702129533e-05,
+      "loss": 0.4127,
+      "step": 85
+    },
+    {
+      "epoch": 2.6278481012658226,
+      "grad_norm": 0.5137987799240195,
+      "learning_rate": 1.5531311541251995e-05,
+      "loss": 0.3065,
+      "step": 86
+    },
+    {
+      "epoch": 2.6582278481012658,
+      "grad_norm": 0.49228750648377373,
+      "learning_rate": 1.540043015774676e-05,
+      "loss": 0.3341,
+      "step": 87
+    },
+    {
+      "epoch": 2.688607594936709,
+      "grad_norm": 0.6814522876949816,
+      "learning_rate": 1.5268229524119007e-05,
+      "loss": 0.3202,
+      "step": 88
+    },
+    {
+      "epoch": 2.7189873417721517,
+      "grad_norm": 0.537936998473839,
+      "learning_rate": 1.513474193514842e-05,
+      "loss": 0.3673,
+      "step": 89
+    },
+    {
+      "epoch": 2.749367088607595,
+      "grad_norm": 0.4995308807561755,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.3352,
+      "step": 90
+    },
+    {
+      "epoch": 2.779746835443038,
+      "grad_norm": 0.5042144418218611,
+      "learning_rate": 1.4864036634258112e-05,
+      "loss": 0.3649,
+      "step": 91
+    },
+    {
+      "epoch": 2.810126582278481,
+      "grad_norm": 0.4810205529248607,
+      "learning_rate": 1.4726885051885654e-05,
+      "loss": 0.3465,
+      "step": 92
+    },
+    {
+      "epoch": 2.840506329113924,
+      "grad_norm": 0.46777668763063673,
+      "learning_rate": 1.4588578757110359e-05,
+      "loss": 0.3312,
+      "step": 93
+    },
+    {
+      "epoch": 2.8708860759493673,
+      "grad_norm": 0.46595629768395286,
+      "learning_rate": 1.4449151536240167e-05,
+      "loss": 0.3389,
+      "step": 94
+    },
+    {
+      "epoch": 2.90126582278481,
+      "grad_norm": 0.40013868400765945,
+      "learning_rate": 1.4308637449409705e-05,
+      "loss": 0.2892,
+      "step": 95
+    },
+    {
+      "epoch": 2.9316455696202532,
+      "grad_norm": 0.524326098641433,
+      "learning_rate": 1.4167070822259868e-05,
+      "loss": 0.3889,
+      "step": 96
+    },
+    {
+      "epoch": 2.962025316455696,
+      "grad_norm": 0.4417005423165919,
+      "learning_rate": 1.402448623755254e-05,
+      "loss": 0.3382,
+      "step": 97
+    },
+    {
+      "epoch": 2.992405063291139,
+      "grad_norm": 0.6032209387187255,
+      "learning_rate": 1.3880918526722497e-05,
+      "loss": 0.4444,
+      "step": 98
+    },
+    {
+      "epoch": 3.030379746835443,
+      "grad_norm": 0.6573238334500671,
+      "learning_rate": 1.3736402761368597e-05,
+      "loss": 0.2592,
+      "step": 99
+    },
+    {
+      "epoch": 3.060759493670886,
+      "grad_norm": 0.5605144807167273,
+      "learning_rate": 1.3590974244686248e-05,
+      "loss": 0.2547,
+      "step": 100
+    },
+    {
+      "epoch": 3.091139240506329,
+      "grad_norm": 0.6531233040095235,
+      "learning_rate": 1.344466850284333e-05,
+      "loss": 0.273,
+      "step": 101
+    },
+    {
+      "epoch": 3.1215189873417724,
+      "grad_norm": 0.9334210522962539,
+      "learning_rate": 1.3297521276301666e-05,
+      "loss": 0.2575,
+      "step": 102
+    },
+    {
+      "epoch": 3.151898734177215,
+      "grad_norm": 0.5559069460326249,
+      "learning_rate": 1.3149568511086104e-05,
+      "loss": 0.2552,
+      "step": 103
+    },
+    {
+      "epoch": 3.1822784810126583,
+      "grad_norm": 0.6492722466526953,
+      "learning_rate": 1.300084635000341e-05,
+      "loss": 0.2552,
+      "step": 104
+    },
+    {
+      "epoch": 3.212658227848101,
+      "grad_norm": 0.5510778935673912,
+      "learning_rate": 1.2851391123813075e-05,
+      "loss": 0.2392,
+      "step": 105
+    },
+    {
+      "epoch": 3.2430379746835443,
+      "grad_norm": 0.5525434722803316,
+      "learning_rate": 1.2701239342352223e-05,
+      "loss": 0.2267,
+      "step": 106
+    },
+    {
+      "epoch": 3.2734177215189875,
+      "grad_norm": 0.5405856149923781,
+      "learning_rate": 1.2550427685616767e-05,
+      "loss": 0.2518,
+      "step": 107
+    },
+    {
+      "epoch": 3.3037974683544302,
+      "grad_norm": 0.5645935517029098,
+      "learning_rate": 1.239899299480098e-05,
+      "loss": 0.2554,
+      "step": 108
+    },
+    {
+      "epoch": 3.3341772151898734,
+      "grad_norm": 0.4962295976875595,
+      "learning_rate": 1.2246972263297718e-05,
+      "loss": 0.2353,
+      "step": 109
+    },
+    {
+      "epoch": 3.3645569620253166,
+      "grad_norm": 0.5724199030679713,
+      "learning_rate": 1.2094402627661447e-05,
+      "loss": 0.244,
+      "step": 110
+    },
+    {
+      "epoch": 3.3949367088607594,
+      "grad_norm": 0.5112070197263711,
+      "learning_rate": 1.1941321358536278e-05,
+      "loss": 0.2399,
+      "step": 111
+    },
+    {
+      "epoch": 3.4253164556962026,
+      "grad_norm": 0.5440312743755955,
+      "learning_rate": 1.1787765851551296e-05,
+      "loss": 0.2323,
+      "step": 112
+    },
+    {
+      "epoch": 3.4556962025316453,
+      "grad_norm": 0.48627544442489706,
+      "learning_rate": 1.1633773618185302e-05,
+      "loss": 0.2554,
+      "step": 113
+    },
+    {
+      "epoch": 3.4860759493670885,
+      "grad_norm": 0.5021444870802758,
+      "learning_rate": 1.14793822766033e-05,
+      "loss": 0.2401,
+      "step": 114
+    },
+    {
+      "epoch": 3.5164556962025317,
+      "grad_norm": 0.46169404742804154,
+      "learning_rate": 1.132462954246688e-05,
+      "loss": 0.2656,
+      "step": 115
+    },
+    {
+      "epoch": 3.546835443037975,
+      "grad_norm": 0.48245585451376644,
+      "learning_rate": 1.1169553219720828e-05,
+      "loss": 0.2516,
+      "step": 116
+    },
+    {
+      "epoch": 3.5772151898734177,
+      "grad_norm": 0.4598449307989322,
+      "learning_rate": 1.1014191191358118e-05,
+      "loss": 0.2543,
+      "step": 117
+    },
+    {
+      "epoch": 3.607594936708861,
+      "grad_norm": 0.4479409796343516,
+      "learning_rate": 1.085858141016566e-05,
+      "loss": 0.2456,
+      "step": 118
+    },
+    {
+      "epoch": 3.6379746835443036,
+      "grad_norm": 0.45462564739248734,
+      "learning_rate": 1.070276188945293e-05,
+      "loss": 0.257,
+      "step": 119
+    },
+    {
+      "epoch": 3.668354430379747,
+      "grad_norm": 0.4015595416578657,
+      "learning_rate": 1.0546770693765859e-05,
+      "loss": 0.2309,
+      "step": 120
+    },
+    {
+      "epoch": 3.69873417721519,
+      "grad_norm": 0.45494954606499216,
+      "learning_rate": 1.0390645929588197e-05,
+      "loss": 0.2567,
+      "step": 121
+    },
+    {
+      "epoch": 3.729113924050633,
+      "grad_norm": 0.41059230945366637,
+      "learning_rate": 1.0234425736032607e-05,
+      "loss": 0.2461,
+      "step": 122
+    },
+    {
+      "epoch": 3.759493670886076,
+      "grad_norm": 0.46432852862870677,
+      "learning_rate": 1.007814827552384e-05,
+      "loss": 0.266,
+      "step": 123
+    },
+    {
+      "epoch": 3.7898734177215188,
+      "grad_norm": 0.40805606299951863,
+      "learning_rate": 9.92185172447616e-06,
+      "loss": 0.2462,
+      "step": 124
+    },
+    {
+      "epoch": 3.820253164556962,
+      "grad_norm": 0.43921004324299806,
+      "learning_rate": 9.765574263967397e-06,
+      "loss": 0.2473,
+      "step": 125
+    },
+    {
+      "epoch": 3.850632911392405,
+      "grad_norm": 0.44473479159040624,
+      "learning_rate": 9.609354070411807e-06,
+      "loss": 0.2449,
+      "step": 126
+    },
+    {
+      "epoch": 3.8810126582278484,
+      "grad_norm": 0.44748351943942116,
+      "learning_rate": 9.453229306234143e-06,
+      "loss": 0.2557,
+      "step": 127
+    },
+    {
+      "epoch": 3.911392405063291,
+      "grad_norm": 0.518560853267675,
+      "learning_rate": 9.297238110547075e-06,
+      "loss": 0.2663,
+      "step": 128
+    },
+    {
+      "epoch": 3.9417721518987343,
+      "grad_norm": 0.4246648781720374,
+      "learning_rate": 9.14141858983434e-06,
+      "loss": 0.2361,
+      "step": 129
+    },
+    {
+      "epoch": 3.972151898734177,
+      "grad_norm": 0.41423647843411554,
+      "learning_rate": 8.985808808641883e-06,
+      "loss": 0.2569,
+      "step": 130
+    },
+    {
+      "epoch": 4.010126582278481,
+      "grad_norm": 0.6163458043061125,
+      "learning_rate": 8.830446780279175e-06,
+      "loss": 0.3476,
+      "step": 131
+    },
+    {
+      "epoch": 4.040506329113924,
+      "grad_norm": 0.5914798912668137,
+      "learning_rate": 8.675370457533122e-06,
+      "loss": 0.1681,
+      "step": 132
+    },
+    {
+      "epoch": 4.0708860759493675,
+      "grad_norm": 0.44321978876286244,
+      "learning_rate": 8.520617723396702e-06,
+      "loss": 0.1743,
+      "step": 133
+    },
+    {
+      "epoch": 4.10126582278481,
+      "grad_norm": 0.4646965237711949,
+      "learning_rate": 8.366226381814698e-06,
+      "loss": 0.174,
+      "step": 134
+    },
+    {
+      "epoch": 4.131645569620253,
+      "grad_norm": 0.7248155117716496,
+      "learning_rate": 8.212234148448708e-06,
+      "loss": 0.1844,
+      "step": 135
+    },
+    {
+      "epoch": 4.162025316455696,
+      "grad_norm": 0.6109335002816132,
+      "learning_rate": 8.058678641463724e-06,
+      "loss": 0.2071,
+      "step": 136
+    },
+    {
+      "epoch": 4.192405063291139,
+      "grad_norm": 0.42282157241586654,
+      "learning_rate": 7.905597372338558e-06,
+      "loss": 0.1633,
+      "step": 137
+    },
+    {
+      "epoch": 4.222784810126583,
+      "grad_norm": 0.5014368521052023,
+      "learning_rate": 7.753027736702283e-06,
+      "loss": 0.1691,
+      "step": 138
+    },
+    {
+      "epoch": 4.253164556962025,
+      "grad_norm": 0.4837752367217211,
+      "learning_rate": 7.601007005199022e-06,
+      "loss": 0.184,
+      "step": 139
+    },
+    {
+      "epoch": 4.283544303797468,
+      "grad_norm": 0.43213740691333613,
+      "learning_rate": 7.449572314383237e-06,
+      "loss": 0.1629,
+      "step": 140
+    },
+    {
+      "epoch": 4.313924050632911,
+      "grad_norm": 0.403652454589129,
+      "learning_rate": 7.298760657647779e-06,
+      "loss": 0.1738,
+      "step": 141
+    },
+    {
+      "epoch": 4.3443037974683545,
+      "grad_norm": 0.421582562547759,
+      "learning_rate": 7.148608876186931e-06,
+      "loss": 0.1742,
+      "step": 142
+    },
+    {
+      "epoch": 4.374683544303798,
+      "grad_norm": 0.44518835218880165,
+      "learning_rate": 6.999153649996595e-06,
+      "loss": 0.1832,
+      "step": 143
+    },
+    {
+      "epoch": 4.405063291139241,
+      "grad_norm": 0.4546106780236523,
+      "learning_rate": 6.8504314889138956e-06,
+      "loss": 0.1682,
+      "step": 144
+    },
+    {
+      "epoch": 4.435443037974683,
+      "grad_norm": 0.43761106153770857,
+      "learning_rate": 6.702478723698336e-06,
+      "loss": 0.164,
+      "step": 145
+    },
+    {
+      "epoch": 4.465822784810126,
+      "grad_norm": 0.4310227803893202,
+      "learning_rate": 6.555331497156671e-06,
+      "loss": 0.168,
+      "step": 146
+    },
+    {
+      "epoch": 4.49620253164557,
+      "grad_norm": 0.45481355409412405,
+      "learning_rate": 6.4090257553137566e-06,
+      "loss": 0.174,
+      "step": 147
+    },
+    {
+      "epoch": 4.526582278481013,
+      "grad_norm": 0.3957283319952441,
+      "learning_rate": 6.263597238631405e-06,
+      "loss": 0.1665,
+      "step": 148
+    },
+    {
+      "epoch": 4.556962025316456,
+      "grad_norm": 0.4552678978797154,
+      "learning_rate": 6.119081473277502e-06,
+      "loss": 0.2019,
+      "step": 149
+    },
+    {
+      "epoch": 4.587341772151898,
+      "grad_norm": 0.3928335896952226,
+      "learning_rate": 5.975513762447465e-06,
+      "loss": 0.1534,
+      "step": 150
+    },
+    {
+      "epoch": 4.6177215189873415,
+      "grad_norm": 0.4015668482093742,
+      "learning_rate": 5.832929177740134e-06,
+      "loss": 0.1527,
+      "step": 151
+    },
+    {
+      "epoch": 4.648101265822785,
+      "grad_norm": 0.4204491043436094,
+      "learning_rate": 5.6913625505902966e-06,
+      "loss": 0.1818,
+      "step": 152
+    },
+    {
+      "epoch": 4.678481012658228,
+      "grad_norm": 0.3731008292524761,
+      "learning_rate": 5.550848463759835e-06,
+      "loss": 0.1666,
+      "step": 153
+    },
+    {
+      "epoch": 4.708860759493671,
+      "grad_norm": 0.4133162907889197,
+      "learning_rate": 5.411421242889643e-06,
+      "loss": 0.1803,
+      "step": 154
+    },
+    {
+      "epoch": 4.739240506329114,
+      "grad_norm": 0.43836732632578446,
+      "learning_rate": 5.273114948114346e-06,
+      "loss": 0.1732,
+      "step": 155
+    },
+    {
+      "epoch": 4.769620253164557,
+      "grad_norm": 0.4191158440787698,
+      "learning_rate": 5.135963365741892e-06,
+      "loss": 0.178,
+      "step": 156
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.3761936549445521,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.1566,
+      "step": 157
+    },
+    {
+      "epoch": 4.830379746835443,
+      "grad_norm": 0.3741682566256842,
+      "learning_rate": 4.865258064851579e-06,
+      "loss": 0.1735,
+      "step": 158
+    },
+    {
+      "epoch": 4.860759493670886,
+      "grad_norm": 0.40744096092794163,
+      "learning_rate": 4.731770475880995e-06,
+      "loss": 0.1789,
+      "step": 159
+    },
+    {
+      "epoch": 4.891139240506329,
+      "grad_norm": 0.3732566845318827,
+      "learning_rate": 4.599569842253244e-06,
+      "loss": 0.1603,
+      "step": 160
+    },
+    {
+      "epoch": 4.921518987341772,
+      "grad_norm": 0.4104311075804241,
+      "learning_rate": 4.468688458748006e-06,
+      "loss": 0.1741,
+      "step": 161
+    },
+    {
+      "epoch": 4.951898734177215,
+      "grad_norm": 0.4174241773674738,
+      "learning_rate": 4.339158297870469e-06,
+      "loss": 0.1932,
+      "step": 162
+    },
+    {
+      "epoch": 4.982278481012658,
+      "grad_norm": 0.4960747398972354,
+      "learning_rate": 4.211011002040885e-06,
+      "loss": 0.2334,
+      "step": 163
+    },
+    {
+      "epoch": 5.020253164556962,
+      "grad_norm": 0.49311557726904276,
+      "learning_rate": 4.084277875864776e-06,
+      "loss": 0.1724,
+      "step": 164
+    },
+    {
+      "epoch": 5.050632911392405,
+      "grad_norm": 0.4219724136306463,
+      "learning_rate": 3.958989878485644e-06,
+      "loss": 0.1182,
+      "step": 165
+    },
+    {
+      "epoch": 5.0810126582278485,
+      "grad_norm": 0.3575965523976325,
+      "learning_rate": 3.83517761602209e-06,
+      "loss": 0.1102,
+      "step": 166
+    },
+    {
+      "epoch": 5.111392405063291,
+      "grad_norm": 0.3819441296997781,
+      "learning_rate": 3.712871334091154e-06,
+      "loss": 0.1421,
+      "step": 167
+    },
+    {
+      "epoch": 5.141772151898734,
+      "grad_norm": 0.36755760720758723,
+      "learning_rate": 3.592100910419738e-06,
+      "loss": 0.1144,
+      "step": 168
+    },
+    {
+      "epoch": 5.172151898734177,
+      "grad_norm": 0.4970308078631468,
+      "learning_rate": 3.4728958475459052e-06,
+      "loss": 0.1236,
+      "step": 169
+    },
+    {
+      "epoch": 5.2025316455696204,
+      "grad_norm": 0.5309873101289584,
+      "learning_rate": 3.355285265611784e-06,
+      "loss": 0.1456,
+      "step": 170
+    },
+    {
+      "epoch": 5.232911392405064,
+      "grad_norm": 0.4603253927514517,
+      "learning_rate": 3.2392978952499553e-06,
+      "loss": 0.1286,
+      "step": 171
+    },
+    {
+      "epoch": 5.263291139240506,
+      "grad_norm": 0.3952284019691279,
+      "learning_rate": 3.1249620705649417e-06,
+      "loss": 0.1355,
+      "step": 172
+    },
+    {
+      "epoch": 5.293670886075949,
+      "grad_norm": 0.362838535477914,
+      "learning_rate": 3.0123057222115835e-06,
+      "loss": 0.1131,
+      "step": 173
+    },
+    {
+      "epoch": 5.324050632911392,
+      "grad_norm": 0.3945869010422975,
+      "learning_rate": 2.9013563705719673e-06,
+      "loss": 0.1419,
+      "step": 174
+    },
+    {
+      "epoch": 5.3544303797468356,
+      "grad_norm": 0.4052553677032924,
+      "learning_rate": 2.7921411190325753e-06,
+      "loss": 0.1366,
+      "step": 175
+    },
+    {
+      "epoch": 5.384810126582279,
+      "grad_norm": 0.3457865463376092,
+      "learning_rate": 2.6846866473633126e-06,
+      "loss": 0.1095,
+      "step": 176
+    },
+    {
+      "epoch": 5.415189873417722,
+      "grad_norm": 0.40994146296011247,
+      "learning_rate": 2.579019205199992e-06,
+      "loss": 0.1325,
+      "step": 177
+    },
+    {
+      "epoch": 5.445569620253164,
+      "grad_norm": 0.35229875639507074,
+      "learning_rate": 2.4751646056319334e-06,
+      "loss": 0.1153,
+      "step": 178
+    },
+    {
+      "epoch": 5.4759493670886075,
+      "grad_norm": 0.3501790972555334,
+      "learning_rate": 2.373148218896182e-06,
+      "loss": 0.131,
+      "step": 179
+    },
+    {
+      "epoch": 5.506329113924051,
+      "grad_norm": 0.33458569532699606,
+      "learning_rate": 2.2729949661798876e-06,
+      "loss": 0.1127,
+      "step": 180
+    },
+    {
+      "epoch": 5.536708860759494,
+      "grad_norm": 0.3613754567991387,
+      "learning_rate": 2.174729313532433e-06,
+      "loss": 0.1315,
+      "step": 181
+    },
+    {
+      "epoch": 5.567088607594937,
+      "grad_norm": 0.36482185521540356,
+      "learning_rate": 2.078375265888707e-06,
+      "loss": 0.1264,
+      "step": 182
+    },
+    {
+      "epoch": 5.597468354430379,
+      "grad_norm": 0.3537624081643742,
+      "learning_rate": 1.9839563612050273e-06,
+      "loss": 0.1058,
+      "step": 183
+    },
+    {
+      "epoch": 5.627848101265823,
+      "grad_norm": 0.41078850995506017,
+      "learning_rate": 1.8914956647091497e-06,
+      "loss": 0.1349,
+      "step": 184
+    },
+    {
+      "epoch": 5.658227848101266,
+      "grad_norm": 0.3415708757919234,
+      "learning_rate": 1.8010157632657544e-06,
+      "loss": 0.0931,
+      "step": 185
+    },
+    {
+      "epoch": 5.688607594936709,
+      "grad_norm": 0.3738318856202389,
+      "learning_rate": 1.7125387598587862e-06,
+      "loss": 0.1324,
+      "step": 186
+    },
+    {
+      "epoch": 5.718987341772152,
+      "grad_norm": 0.3201115593014112,
+      "learning_rate": 1.6260862681919965e-06,
+      "loss": 0.1155,
+      "step": 187
+    },
+    {
+      "epoch": 5.749367088607595,
+      "grad_norm": 0.3193124066196814,
+      "learning_rate": 1.5416794074090258e-06,
+      "loss": 0.1266,
+      "step": 188
+    },
+    {
+      "epoch": 5.779746835443038,
+      "grad_norm": 0.352658463840024,
+      "learning_rate": 1.459338796934293e-06,
+      "loss": 0.1401,
+      "step": 189
+    },
+    {
+      "epoch": 5.810126582278481,
+      "grad_norm": 0.35577963695957643,
+      "learning_rate": 1.3790845514359363e-06,
+      "loss": 0.1179,
+      "step": 190
+    },
+    {
+      "epoch": 5.840506329113924,
+      "grad_norm": 0.3046690367490559,
+      "learning_rate": 1.300936275912098e-06,
+      "loss": 0.1041,
+      "step": 191
+    },
+    {
+      "epoch": 5.870886075949367,
+      "grad_norm": 0.3253967100229279,
+      "learning_rate": 1.224913060901688e-06,
+      "loss": 0.1193,
+      "step": 192
+    },
+    {
+      "epoch": 5.9012658227848105,
+      "grad_norm": 0.3355585754343889,
+      "learning_rate": 1.1510334778208332e-06,
+      "loss": 0.1186,
+      "step": 193
+    },
+    {
+      "epoch": 5.931645569620253,
+      "grad_norm": 0.347764998604189,
+      "learning_rate": 1.0793155744261352e-06,
+      "loss": 0.1214,
+      "step": 194
+    },
+    {
+      "epoch": 5.962025316455696,
+      "grad_norm": 0.3623556898310986,
+      "learning_rate": 1.0097768704058542e-06,
+      "loss": 0.1428,
+      "step": 195
+    },
+    {
+      "epoch": 5.992405063291139,
+      "grad_norm": 0.4545442024513848,
+      "learning_rate": 9.424343531000968e-07,
+      "loss": 0.1609,
+      "step": 196
+    },
+    {
+      "epoch": 6.030379746835443,
+      "grad_norm": 0.387114634683258,
+      "learning_rate": 8.773044733510338e-07,
+      "loss": 0.0996,
+      "step": 197
+    },
+    {
+      "epoch": 6.060759493670886,
+      "grad_norm": 0.36921391920746444,
+      "learning_rate": 8.144031414842012e-07,
+      "loss": 0.1127,
+      "step": 198
+    },
+    {
+      "epoch": 6.091139240506329,
+      "grad_norm": 0.3642487093341055,
+      "learning_rate": 7.537457234218271e-07,
+      "loss": 0.1123,
+      "step": 199
+    },
+    {
+      "epoch": 6.121518987341772,
+      "grad_norm": 0.30930492840971036,
+      "learning_rate": 6.953470369291349e-07,
+      "loss": 0.106,
+      "step": 200
+    },
+    {
+      "epoch": 6.151898734177215,
+      "grad_norm": 0.32464631965147894,
+      "learning_rate": 6.392213479945852e-07,
+      "loss": 0.0966,
+      "step": 201
+    },
+    {
+      "epoch": 6.182278481012658,
+      "grad_norm": 0.29283184192001643,
+      "learning_rate": 5.853823673448877e-07,
+      "loss": 0.1012,
+      "step": 202
+    },
+    {
+      "epoch": 6.2126582278481015,
+      "grad_norm": 0.3094164314460087,
+      "learning_rate": 5.33843247095659e-07,
+      "loss": 0.1017,
+      "step": 203
+    },
+    {
+      "epoch": 6.243037974683545,
+      "grad_norm": 0.3302230130000344,
+      "learning_rate": 4.846165775385459e-07,
+      "loss": 0.1053,
+      "step": 204
+    },
+    {
+      "epoch": 6.273417721518987,
+      "grad_norm": 0.3046311548899495,
+      "learning_rate": 4.3771438406559173e-07,
+      "loss": 0.1128,
+      "step": 205
+    },
+    {
+      "epoch": 6.30379746835443,
+      "grad_norm": 0.31482728266911736,
+      "learning_rate": 3.931481242315993e-07,
+      "loss": 0.0992,
+      "step": 206
+    },
+    {
+      "epoch": 6.334177215189873,
+      "grad_norm": 0.3119001336132193,
+      "learning_rate": 3.5092868495520294e-07,
+      "loss": 0.1047,
+      "step": 207
+    },
+    {
+      "epoch": 6.364556962025317,
+      "grad_norm": 0.3566508941703967,
+      "learning_rate": 3.110663798593616e-07,
+      "loss": 0.1037,
+      "step": 208
+    },
+    {
+      "epoch": 6.39493670886076,
+      "grad_norm": 0.3178470550954623,
+      "learning_rate": 2.735709467518699e-07,
+      "loss": 0.1025,
+      "step": 209
+    },
+    {
+      "epoch": 6.425316455696202,
+      "grad_norm": 0.3083171094133544,
+      "learning_rate": 2.384515452465475e-07,
+      "loss": 0.1022,
+      "step": 210
+    },
+    {
+      "epoch": 6.455696202531645,
+      "grad_norm": 0.30792921087733777,
+      "learning_rate": 2.0571675452567997e-07,
+      "loss": 0.091,
+      "step": 211
+    },
+    {
+      "epoch": 6.4860759493670885,
+      "grad_norm": 0.31286644898467275,
+      "learning_rate": 1.7537457124423896e-07,
+      "loss": 0.0965,
+      "step": 212
+    },
+    {
+      "epoch": 6.516455696202532,
+      "grad_norm": 0.32575239630053976,
+      "learning_rate": 1.474324075764111e-07,
+      "loss": 0.1106,
+      "step": 213
+    },
+    {
+      "epoch": 6.546835443037975,
+      "grad_norm": 0.3164925601374238,
+      "learning_rate": 1.2189708940490653e-07,
+      "loss": 0.1049,
+      "step": 214
+    },
+    {
+      "epoch": 6.577215189873417,
+      "grad_norm": 0.3006576850076976,
+      "learning_rate": 9.877485465349057e-08,
+      "loss": 0.1036,
+      "step": 215
+    },
+    {
+      "epoch": 6.6075949367088604,
+      "grad_norm": 0.30959763059509177,
+      "learning_rate": 7.807135176314707e-08,
+      "loss": 0.1022,
+      "step": 216
+    },
+    {
+      "epoch": 6.637974683544304,
+      "grad_norm": 0.32718766109021413,
+      "learning_rate": 5.979163831223988e-08,
+      "loss": 0.1095,
+      "step": 217
+    },
+    {
+      "epoch": 6.668354430379747,
+      "grad_norm": 0.31611073824806707,
+      "learning_rate": 4.394017978101905e-08,
+      "loss": 0.0987,
+      "step": 218
+    },
+    {
+      "epoch": 6.69873417721519,
+      "grad_norm": 0.3226117308334687,
+      "learning_rate": 3.0520848460765525e-08,
+      "loss": 0.1153,
+      "step": 219
+    },
+    {
+      "epoch": 6.729113924050633,
+      "grad_norm": 0.3188247426029841,
+      "learning_rate": 1.9536922507841227e-08,
+      "loss": 0.1203,
+      "step": 220
+    },
+    {
+      "epoch": 6.759493670886076,
+      "grad_norm": 0.2918096040036267,
+      "learning_rate": 1.099108514288627e-08,
+      "loss": 0.101,
+      "step": 221
+    },
+    {
+      "epoch": 6.789873417721519,
+      "grad_norm": 0.3006475270572043,
+      "learning_rate": 4.885423995341088e-09,
+      "loss": 0.1063,
+      "step": 222
+    },
+    {
+      "epoch": 6.820253164556962,
+      "grad_norm": 0.3084749992680357,
+      "learning_rate": 1.2214305934699078e-09,
+      "loss": 0.1022,
+      "step": 223
+    },
+    {
+      "epoch": 6.850632911392405,
+      "grad_norm": 0.30755613849148156,
+      "learning_rate": 0.0,
+      "loss": 0.108,
+      "step": 224
+    },
+    {
+      "epoch": 6.850632911392405,
+      "step": 224,
+      "total_flos": 3.3605374365505946e+17,
+      "train_loss": 0.30083318214331356,
+      "train_runtime": 14587.34,
+      "train_samples_per_second": 1.516,
+      "train_steps_per_second": 0.015
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 224,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.3605374365505946e+17,
+  "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:b414837497c3063af6aa68a331d9a6d5b1b0b0e85452ac674763be4836812eb5
+size 7352