Upload folder using huggingface_hub

.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

@@ -1,3 +1,75 @@
----
-license: apache-2.0
----
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: ideaassistant_qwen2_7b
+  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. -->
+
+# ideaassistant_qwen2_7b
+
+This model is a fine-tuned version of [Qwen/Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-Instruct) on the idea_sharegpt_format dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4394
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 2
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- total_eval_batch_size: 8
+- optimizer: Use 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: 1.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.0484        | 0.0955 | 200  | 1.0037          |
+| 0.9828        | 0.1910 | 400  | 0.9110          |
+| 0.8785        | 0.2865 | 600  | 0.8167          |
+| 0.7863        | 0.3820 | 800  | 0.7238          |
+| 0.7073        | 0.4776 | 1000 | 0.6407          |
+| 0.6143        | 0.5731 | 1200 | 0.5672          |
+| 0.5726        | 0.6686 | 1400 | 0.5096          |
+| 0.5623        | 0.7641 | 1600 | 0.4683          |
+| 0.5206        | 0.8596 | 1800 | 0.4465          |
+| 0.5054        | 0.9551 | 2000 | 0.4396          |
+
+
+### Framework versions
+
+- Transformers 4.50.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.4.1
+- Tokenizers 0.21.0

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.4393579959869385,
+    "eval_runtime": 534.2651,
+    "eval_samples_per_second": 27.87,
+    "eval_steps_per_second": 3.485,
+    "total_flos": 985274787299328.0,
+    "train_loss": 0.7358792713970487,
+    "train_runtime": 28849.9475,
+    "train_samples_per_second": 4.645,
+    "train_steps_per_second": 0.073
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.4393579959869385,
+    "eval_runtime": 534.2651,
+    "eval_samples_per_second": 27.87,
+    "eval_steps_per_second": 3.485
+}

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": "4.50.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c6aee5d20fa9a0dc1bfef370d2fd400837714c7cf586fb748b2a2d656ec4bad
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab06a6a05df0ce149a2e2ceef9cce715d4b2caadbca077a6b700a96c340a87fc
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf9b9da015353abee9a4903dd91c3d0fb086cd3f46f5aa733bddc2d119d146b3
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcbb423005c5cb3dd483c10af534638f640637ddbb75f0ff02d8c5026a283787
+size 1089994880

model.safetensors.index.json

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

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "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": 1.0,
+    "total_flos": 985274787299328.0,
+    "train_loss": 0.7358792713970487,
+    "train_runtime": 28849.9475,
+    "train_samples_per_second": 4.645,
+    "train_steps_per_second": 0.073
+}

trainer_log.jsonl

@@ -0,0 +1,220 @@
+{"current_steps": 10, "total_steps": 2094, "loss": 1.1507, "lr": 4.7619047619047623e-07, "epoch": 0.004775549188156638, "percentage": 0.48, "elapsed_time": "0:01:52", "remaining_time": "6:29:13"}
+{"current_steps": 20, "total_steps": 2094, "loss": 1.1084, "lr": 9.523809523809525e-07, "epoch": 0.009551098376313277, "percentage": 0.96, "elapsed_time": "0:03:43", "remaining_time": "6:26:27"}
+{"current_steps": 30, "total_steps": 2094, "loss": 1.0874, "lr": 1.4285714285714286e-06, "epoch": 0.014326647564469915, "percentage": 1.43, "elapsed_time": "0:05:35", "remaining_time": "6:24:42"}
+{"current_steps": 40, "total_steps": 2094, "loss": 1.1068, "lr": 1.904761904761905e-06, "epoch": 0.019102196752626553, "percentage": 1.91, "elapsed_time": "0:07:29", "remaining_time": "6:24:35"}
+{"current_steps": 50, "total_steps": 2094, "loss": 1.1152, "lr": 2.380952380952381e-06, "epoch": 0.02387774594078319, "percentage": 2.39, "elapsed_time": "0:09:14", "remaining_time": "6:17:32"}
+{"current_steps": 60, "total_steps": 2094, "loss": 1.0964, "lr": 2.8571428571428573e-06, "epoch": 0.02865329512893983, "percentage": 2.87, "elapsed_time": "0:11:00", "remaining_time": "6:13:18"}
+{"current_steps": 70, "total_steps": 2094, "loss": 1.1005, "lr": 3.3333333333333333e-06, "epoch": 0.033428844317096466, "percentage": 3.34, "elapsed_time": "0:12:52", "remaining_time": "6:12:11"}
+{"current_steps": 80, "total_steps": 2094, "loss": 1.0933, "lr": 3.80952380952381e-06, "epoch": 0.038204393505253106, "percentage": 3.82, "elapsed_time": "0:14:41", "remaining_time": "6:09:49"}
+{"current_steps": 90, "total_steps": 2094, "loss": 1.0397, "lr": 4.2857142857142855e-06, "epoch": 0.04297994269340974, "percentage": 4.3, "elapsed_time": "0:16:39", "remaining_time": "6:11:03"}
+{"current_steps": 100, "total_steps": 2094, "loss": 1.0723, "lr": 4.761904761904762e-06, "epoch": 0.04775549188156638, "percentage": 4.78, "elapsed_time": "0:18:33", "remaining_time": "6:10:08"}
+{"current_steps": 110, "total_steps": 2094, "loss": 1.0753, "lr": 5.2380952380952384e-06, "epoch": 0.05253104106972302, "percentage": 5.25, "elapsed_time": "0:20:22", "remaining_time": "6:07:36"}
+{"current_steps": 120, "total_steps": 2094, "loss": 1.0604, "lr": 5.7142857142857145e-06, "epoch": 0.05730659025787966, "percentage": 5.73, "elapsed_time": "0:22:03", "remaining_time": "6:02:43"}
+{"current_steps": 130, "total_steps": 2094, "loss": 1.0844, "lr": 6.1904761904761914e-06, "epoch": 0.06208213944603629, "percentage": 6.21, "elapsed_time": "0:23:55", "remaining_time": "6:01:23"}
+{"current_steps": 140, "total_steps": 2094, "loss": 1.0738, "lr": 6.666666666666667e-06, "epoch": 0.06685768863419293, "percentage": 6.69, "elapsed_time": "0:25:53", "remaining_time": "6:01:26"}
+{"current_steps": 150, "total_steps": 2094, "loss": 1.0638, "lr": 7.1428571428571436e-06, "epoch": 0.07163323782234957, "percentage": 7.16, "elapsed_time": "0:27:48", "remaining_time": "6:00:23"}
+{"current_steps": 160, "total_steps": 2094, "loss": 1.089, "lr": 7.61904761904762e-06, "epoch": 0.07640878701050621, "percentage": 7.64, "elapsed_time": "0:29:41", "remaining_time": "5:58:52"}
+{"current_steps": 170, "total_steps": 2094, "loss": 1.0215, "lr": 8.095238095238097e-06, "epoch": 0.08118433619866285, "percentage": 8.12, "elapsed_time": "0:31:32", "remaining_time": "5:57:01"}
+{"current_steps": 180, "total_steps": 2094, "loss": 1.0489, "lr": 8.571428571428571e-06, "epoch": 0.08595988538681948, "percentage": 8.6, "elapsed_time": "0:33:24", "remaining_time": "5:55:10"}
+{"current_steps": 190, "total_steps": 2094, "loss": 1.047, "lr": 9.047619047619049e-06, "epoch": 0.09073543457497613, "percentage": 9.07, "elapsed_time": "0:35:19", "remaining_time": "5:53:56"}
+{"current_steps": 200, "total_steps": 2094, "loss": 1.0484, "lr": 9.523809523809525e-06, "epoch": 0.09551098376313276, "percentage": 9.55, "elapsed_time": "0:37:13", "remaining_time": "5:52:32"}
+{"current_steps": 200, "total_steps": 2094, "eval_loss": 1.0037423372268677, "epoch": 0.09551098376313276, "percentage": 9.55, "elapsed_time": "0:46:07", "remaining_time": "7:16:52"}
+{"current_steps": 210, "total_steps": 2094, "loss": 1.0786, "lr": 1e-05, "epoch": 0.10028653295128939, "percentage": 10.03, "elapsed_time": "0:48:26", "remaining_time": "7:14:37"}
+{"current_steps": 220, "total_steps": 2094, "loss": 1.0568, "lr": 9.99930486701988e-06, "epoch": 0.10506208213944604, "percentage": 10.51, "elapsed_time": "0:50:23", "remaining_time": "7:09:14"}
+{"current_steps": 230, "total_steps": 2094, "loss": 1.0264, "lr": 9.99721966136347e-06, "epoch": 0.10983763132760267, "percentage": 10.98, "elapsed_time": "0:52:22", "remaining_time": "7:04:26"}
+{"current_steps": 240, "total_steps": 2094, "loss": 1.0093, "lr": 9.99374496282885e-06, "epoch": 0.11461318051575932, "percentage": 11.46, "elapsed_time": "0:54:10", "remaining_time": "6:58:32"}
+{"current_steps": 250, "total_steps": 2094, "loss": 1.0172, "lr": 9.988881737567046e-06, "epoch": 0.11938872970391595, "percentage": 11.94, "elapsed_time": "0:56:04", "remaining_time": "6:53:35"}
+{"current_steps": 260, "total_steps": 2094, "loss": 1.0369, "lr": 9.982631337813363e-06, "epoch": 0.12416427889207259, "percentage": 12.42, "elapsed_time": "0:57:54", "remaining_time": "6:48:28"}
+{"current_steps": 270, "total_steps": 2094, "loss": 0.998, "lr": 9.974995501511404e-06, "epoch": 0.12893982808022922, "percentage": 12.89, "elapsed_time": "0:59:43", "remaining_time": "6:43:26"}
+{"current_steps": 280, "total_steps": 2094, "loss": 1.0232, "lr": 9.965976351829827e-06, "epoch": 0.13371537726838587, "percentage": 13.37, "elapsed_time": "1:01:30", "remaining_time": "6:38:26"}
+{"current_steps": 290, "total_steps": 2094, "loss": 1.0093, "lr": 9.95557639657199e-06, "epoch": 0.1384909264565425, "percentage": 13.85, "elapsed_time": "1:03:20", "remaining_time": "6:34:04"}
+{"current_steps": 300, "total_steps": 2094, "loss": 1.0048, "lr": 9.943798527478652e-06, "epoch": 0.14326647564469913, "percentage": 14.33, "elapsed_time": "1:05:19", "remaining_time": "6:30:38"}
+{"current_steps": 310, "total_steps": 2094, "loss": 0.9838, "lr": 9.930646019423909e-06, "epoch": 0.14804202483285578, "percentage": 14.8, "elapsed_time": "1:07:07", "remaining_time": "6:26:19"}
+{"current_steps": 320, "total_steps": 2094, "loss": 0.9935, "lr": 9.916122529504605e-06, "epoch": 0.15281757402101243, "percentage": 15.28, "elapsed_time": "1:08:56", "remaining_time": "6:22:08"}
+{"current_steps": 330, "total_steps": 2094, "loss": 0.9834, "lr": 9.900232096023478e-06, "epoch": 0.15759312320916904, "percentage": 15.76, "elapsed_time": "1:10:46", "remaining_time": "6:18:17"}
+{"current_steps": 340, "total_steps": 2094, "loss": 0.9638, "lr": 9.882979137366275e-06, "epoch": 0.1623686723973257, "percentage": 16.24, "elapsed_time": "1:12:37", "remaining_time": "6:14:38"}
+{"current_steps": 350, "total_steps": 2094, "loss": 0.983, "lr": 9.864368450773227e-06, "epoch": 0.16714422158548234, "percentage": 16.71, "elapsed_time": "1:14:31", "remaining_time": "6:11:22"}
+{"current_steps": 360, "total_steps": 2094, "loss": 0.9759, "lr": 9.844405211005145e-06, "epoch": 0.17191977077363896, "percentage": 17.19, "elapsed_time": "1:16:21", "remaining_time": "6:07:47"}
+{"current_steps": 370, "total_steps": 2094, "loss": 0.9927, "lr": 9.823094968904572e-06, "epoch": 0.1766953199617956, "percentage": 17.67, "elapsed_time": "1:18:09", "remaining_time": "6:04:09"}
+{"current_steps": 380, "total_steps": 2094, "loss": 0.985, "lr": 9.800443649852347e-06, "epoch": 0.18147086914995225, "percentage": 18.15, "elapsed_time": "1:20:01", "remaining_time": "6:00:57"}
+{"current_steps": 390, "total_steps": 2094, "loss": 0.9578, "lr": 9.776457552120034e-06, "epoch": 0.18624641833810887, "percentage": 18.62, "elapsed_time": "1:21:50", "remaining_time": "5:57:35"}
+{"current_steps": 400, "total_steps": 2094, "loss": 0.9828, "lr": 9.751143345118675e-06, "epoch": 0.19102196752626552, "percentage": 19.1, "elapsed_time": "1:23:38", "remaining_time": "5:54:11"}
+{"current_steps": 400, "total_steps": 2094, "eval_loss": 0.911033034324646, "epoch": 0.19102196752626552, "percentage": 19.1, "elapsed_time": "1:32:32", "remaining_time": "6:31:53"}
+{"current_steps": 410, "total_steps": 2094, "loss": 0.9593, "lr": 9.724508067544328e-06, "epoch": 0.19579751671442217, "percentage": 19.58, "elapsed_time": "1:34:50", "remaining_time": "6:29:32"}
+{"current_steps": 420, "total_steps": 2094, "loss": 0.9342, "lr": 9.696559125420949e-06, "epoch": 0.20057306590257878, "percentage": 20.06, "elapsed_time": "1:36:42", "remaining_time": "6:25:26"}
+{"current_steps": 430, "total_steps": 2094, "loss": 0.9182, "lr": 9.667304290041102e-06, "epoch": 0.20534861509073543, "percentage": 20.53, "elapsed_time": "1:38:39", "remaining_time": "6:21:47"}
+{"current_steps": 440, "total_steps": 2094, "loss": 0.9399, "lr": 9.636751695805154e-06, "epoch": 0.21012416427889208, "percentage": 21.01, "elapsed_time": "1:40:29", "remaining_time": "6:17:43"}
+{"current_steps": 450, "total_steps": 2094, "loss": 0.9546, "lr": 9.604909837959456e-06, "epoch": 0.2148997134670487, "percentage": 21.49, "elapsed_time": "1:42:14", "remaining_time": "6:13:33"}
+{"current_steps": 460, "total_steps": 2094, "loss": 0.9493, "lr": 9.57178757023422e-06, "epoch": 0.21967526265520534, "percentage": 21.97, "elapsed_time": "1:43:58", "remaining_time": "6:09:21"}
+{"current_steps": 470, "total_steps": 2094, "loss": 0.951, "lr": 9.537394102381719e-06, "epoch": 0.224450811843362, "percentage": 22.45, "elapsed_time": "1:45:52", "remaining_time": "6:05:48"}
+{"current_steps": 480, "total_steps": 2094, "loss": 0.902, "lr": 9.501738997615471e-06, "epoch": 0.22922636103151864, "percentage": 22.92, "elapsed_time": "1:47:42", "remaining_time": "6:02:10"}
+{"current_steps": 490, "total_steps": 2094, "loss": 0.9121, "lr": 9.464832169951171e-06, "epoch": 0.23400191021967526, "percentage": 23.4, "elapsed_time": "1:49:36", "remaining_time": "5:58:47"}
+{"current_steps": 500, "total_steps": 2094, "loss": 0.9149, "lr": 9.426683881450058e-06, "epoch": 0.2387774594078319, "percentage": 23.88, "elapsed_time": "1:51:23", "remaining_time": "5:55:05"}
+{"current_steps": 510, "total_steps": 2094, "loss": 0.9141, "lr": 9.387304739365524e-06, "epoch": 0.24355300859598855, "percentage": 24.36, "elapsed_time": "1:53:23", "remaining_time": "5:52:10"}
+{"current_steps": 520, "total_steps": 2094, "loss": 0.9046, "lr": 9.346705693193722e-06, "epoch": 0.24832855778414517, "percentage": 24.83, "elapsed_time": "1:55:12", "remaining_time": "5:48:44"}
+{"current_steps": 530, "total_steps": 2094, "loss": 0.907, "lr": 9.304898031629038e-06, "epoch": 0.2531041069723018, "percentage": 25.31, "elapsed_time": "1:57:02", "remaining_time": "5:45:23"}
+{"current_steps": 540, "total_steps": 2094, "loss": 0.9095, "lr": 9.261893379425218e-06, "epoch": 0.25787965616045844, "percentage": 25.79, "elapsed_time": "1:58:48", "remaining_time": "5:41:54"}
+{"current_steps": 550, "total_steps": 2094, "loss": 0.8811, "lr": 9.217703694163083e-06, "epoch": 0.2626552053486151, "percentage": 26.27, "elapsed_time": "2:00:41", "remaining_time": "5:38:48"}
+{"current_steps": 560, "total_steps": 2094, "loss": 0.8743, "lr": 9.172341262925675e-06, "epoch": 0.26743075453677173, "percentage": 26.74, "elapsed_time": "2:02:34", "remaining_time": "5:35:47"}
+{"current_steps": 570, "total_steps": 2094, "loss": 0.8659, "lr": 9.125818698881798e-06, "epoch": 0.2722063037249284, "percentage": 27.22, "elapsed_time": "2:04:24", "remaining_time": "5:32:36"}
+{"current_steps": 580, "total_steps": 2094, "loss": 0.906, "lr": 9.078148937778889e-06, "epoch": 0.276981852913085, "percentage": 27.7, "elapsed_time": "2:06:14", "remaining_time": "5:29:31"}
+{"current_steps": 590, "total_steps": 2094, "loss": 0.8859, "lr": 9.029345234346183e-06, "epoch": 0.2817574021012416, "percentage": 28.18, "elapsed_time": "2:08:07", "remaining_time": "5:26:36"}
+{"current_steps": 600, "total_steps": 2094, "loss": 0.8785, "lr": 8.979421158609206e-06, "epoch": 0.28653295128939826, "percentage": 28.65, "elapsed_time": "2:09:55", "remaining_time": "5:23:31"}
+{"current_steps": 600, "total_steps": 2094, "eval_loss": 0.8167237639427185, "epoch": 0.28653295128939826, "percentage": 28.65, "elapsed_time": "2:18:50", "remaining_time": "5:45:41"}
+{"current_steps": 610, "total_steps": 2094, "loss": 0.8539, "lr": 8.928390592116576e-06, "epoch": 0.2913085004775549, "percentage": 29.13, "elapsed_time": "2:21:01", "remaining_time": "5:43:05"}
+{"current_steps": 620, "total_steps": 2094, "loss": 0.8527, "lr": 8.876267724080197e-06, "epoch": 0.29608404966571156, "percentage": 29.61, "elapsed_time": "2:22:47", "remaining_time": "5:39:29"}
+{"current_steps": 630, "total_steps": 2094, "loss": 0.8683, "lr": 8.823067047429908e-06, "epoch": 0.3008595988538682, "percentage": 30.09, "elapsed_time": "2:24:35", "remaining_time": "5:35:59"}
+{"current_steps": 640, "total_steps": 2094, "loss": 0.8649, "lr": 8.768803354783668e-06, "epoch": 0.30563514804202485, "percentage": 30.56, "elapsed_time": "2:26:19", "remaining_time": "5:32:26"}
+{"current_steps": 650, "total_steps": 2094, "loss": 0.8622, "lr": 8.71349173433443e-06, "epoch": 0.3104106972301815, "percentage": 31.04, "elapsed_time": "2:28:06", "remaining_time": "5:29:01"}
+{"current_steps": 660, "total_steps": 2094, "loss": 0.8359, "lr": 8.65714756565482e-06, "epoch": 0.3151862464183381, "percentage": 31.52, "elapsed_time": "2:29:51", "remaining_time": "5:25:35"}
+{"current_steps": 670, "total_steps": 2094, "loss": 0.8569, "lr": 8.599786515420789e-06, "epoch": 0.31996179560649474, "percentage": 32.0, "elapsed_time": "2:31:42", "remaining_time": "5:22:26"}
+{"current_steps": 680, "total_steps": 2094, "loss": 0.8458, "lr": 8.541424533055455e-06, "epoch": 0.3247373447946514, "percentage": 32.47, "elapsed_time": "2:33:32", "remaining_time": "5:19:16"}
+{"current_steps": 690, "total_steps": 2094, "loss": 0.8447, "lr": 8.48207784629431e-06, "epoch": 0.32951289398280803, "percentage": 32.95, "elapsed_time": "2:35:23", "remaining_time": "5:16:11"}
+{"current_steps": 700, "total_steps": 2094, "loss": 0.8365, "lr": 8.421762956673043e-06, "epoch": 0.3342884431709647, "percentage": 33.43, "elapsed_time": "2:37:16", "remaining_time": "5:13:13"}
+{"current_steps": 710, "total_steps": 2094, "loss": 0.8335, "lr": 8.360496634939243e-06, "epoch": 0.3390639923591213, "percentage": 33.91, "elapsed_time": "2:39:07", "remaining_time": "5:10:11"}
+{"current_steps": 720, "total_steps": 2094, "loss": 0.8458, "lr": 8.298295916389234e-06, "epoch": 0.3438395415472779, "percentage": 34.38, "elapsed_time": "2:41:01", "remaining_time": "5:07:17"}
+{"current_steps": 730, "total_steps": 2094, "loss": 0.8185, "lr": 8.235178096131355e-06, "epoch": 0.34861509073543456, "percentage": 34.86, "elapsed_time": "2:42:50", "remaining_time": "5:04:16"}
+{"current_steps": 740, "total_steps": 2094, "loss": 0.8009, "lr": 8.171160724277005e-06, "epoch": 0.3533906399235912, "percentage": 35.34, "elapsed_time": "2:44:38", "remaining_time": "5:01:15"}
+{"current_steps": 750, "total_steps": 2094, "loss": 0.8277, "lr": 8.106261601060773e-06, "epoch": 0.35816618911174786, "percentage": 35.82, "elapsed_time": "2:46:27", "remaining_time": "4:58:16"}
+{"current_steps": 760, "total_steps": 2094, "loss": 0.8432, "lr": 8.040498771891031e-06, "epoch": 0.3629417382999045, "percentage": 36.29, "elapsed_time": "2:48:16", "remaining_time": "4:55:21"}
+{"current_steps": 770, "total_steps": 2094, "loss": 0.7933, "lr": 7.973890522332348e-06, "epoch": 0.36771728748806115, "percentage": 36.77, "elapsed_time": "2:50:04", "remaining_time": "4:52:26"}
+{"current_steps": 780, "total_steps": 2094, "loss": 0.8122, "lr": 7.90645537302113e-06, "epoch": 0.37249283667621774, "percentage": 37.25, "elapsed_time": "2:52:03", "remaining_time": "4:49:51"}
+{"current_steps": 790, "total_steps": 2094, "loss": 0.7713, "lr": 7.838212074515899e-06, "epoch": 0.3772683858643744, "percentage": 37.73, "elapsed_time": "2:53:57", "remaining_time": "4:47:08"}
+{"current_steps": 800, "total_steps": 2094, "loss": 0.7863, "lr": 7.769179602083642e-06, "epoch": 0.38204393505253104, "percentage": 38.2, "elapsed_time": "2:55:49", "remaining_time": "4:44:24"}
+{"current_steps": 800, "total_steps": 2094, "eval_loss": 0.7238086462020874, "epoch": 0.38204393505253104, "percentage": 38.2, "elapsed_time": "3:04:44", "remaining_time": "4:58:48"}
+{"current_steps": 810, "total_steps": 2094, "loss": 0.7703, "lr": 7.699377150423673e-06, "epoch": 0.3868194842406877, "percentage": 38.68, "elapsed_time": "3:07:00", "remaining_time": "4:56:26"}
+{"current_steps": 820, "total_steps": 2094, "loss": 0.7651, "lr": 7.628824128330485e-06, "epoch": 0.39159503342884433, "percentage": 39.16, "elapsed_time": "3:08:49", "remaining_time": "4:53:22"}
+{"current_steps": 830, "total_steps": 2094, "loss": 0.777, "lr": 7.557540153297086e-06, "epoch": 0.396370582617001, "percentage": 39.64, "elapsed_time": "3:10:32", "remaining_time": "4:50:10"}
+{"current_steps": 840, "total_steps": 2094, "loss": 0.7659, "lr": 7.485545046060272e-06, "epoch": 0.40114613180515757, "percentage": 40.11, "elapsed_time": "3:12:26", "remaining_time": "4:47:17"}
+{"current_steps": 850, "total_steps": 2094, "loss": 0.7422, "lr": 7.412858825089423e-06, "epoch": 0.4059216809933142, "percentage": 40.59, "elapsed_time": "3:14:14", "remaining_time": "4:44:16"}
+{"current_steps": 860, "total_steps": 2094, "loss": 0.7812, "lr": 7.3395017010202965e-06, "epoch": 0.41069723018147086, "percentage": 41.07, "elapsed_time": "3:16:05", "remaining_time": "4:41:21"}
+{"current_steps": 870, "total_steps": 2094, "loss": 0.7461, "lr": 7.265494071035401e-06, "epoch": 0.4154727793696275, "percentage": 41.55, "elapsed_time": "3:17:56", "remaining_time": "4:38:28"}
+{"current_steps": 880, "total_steps": 2094, "loss": 0.7475, "lr": 7.19085651319249e-06, "epoch": 0.42024832855778416, "percentage": 42.02, "elapsed_time": "3:19:50", "remaining_time": "4:35:40"}
+{"current_steps": 890, "total_steps": 2094, "loss": 0.7485, "lr": 7.115609780702767e-06, "epoch": 0.4250238777459408, "percentage": 42.5, "elapsed_time": "3:21:46", "remaining_time": "4:32:57"}
+{"current_steps": 900, "total_steps": 2094, "loss": 0.7502, "lr": 7.039774796160391e-06, "epoch": 0.4297994269340974, "percentage": 42.98, "elapsed_time": "3:23:38", "remaining_time": "4:30:10"}
+{"current_steps": 910, "total_steps": 2094, "loss": 0.7307, "lr": 6.9633726457248864e-06, "epoch": 0.43457497612225404, "percentage": 43.46, "elapsed_time": "3:25:34", "remaining_time": "4:27:29"}
+{"current_steps": 920, "total_steps": 2094, "loss": 0.7407, "lr": 6.886424573258057e-06, "epoch": 0.4393505253104107, "percentage": 43.94, "elapsed_time": "3:27:26", "remaining_time": "4:24:43"}
+{"current_steps": 930, "total_steps": 2094, "loss": 0.7232, "lr": 6.808951974417077e-06, "epoch": 0.44412607449856734, "percentage": 44.41, "elapsed_time": "3:29:15", "remaining_time": "4:21:55"}
+{"current_steps": 940, "total_steps": 2094, "loss": 0.7217, "lr": 6.73097639070535e-06, "epoch": 0.448901623686724, "percentage": 44.89, "elapsed_time": "3:31:04", "remaining_time": "4:19:07"}
+{"current_steps": 950, "total_steps": 2094, "loss": 0.7275, "lr": 6.652519503482829e-06, "epoch": 0.45367717287488063, "percentage": 45.37, "elapsed_time": "3:32:55", "remaining_time": "4:16:24"}
+{"current_steps": 960, "total_steps": 2094, "loss": 0.7244, "lr": 6.573603127937443e-06, "epoch": 0.4584527220630373, "percentage": 45.85, "elapsed_time": "3:34:42", "remaining_time": "4:13:37"}
+{"current_steps": 970, "total_steps": 2094, "loss": 0.7184, "lr": 6.494249207019317e-06, "epoch": 0.46322827125119387, "percentage": 46.32, "elapsed_time": "3:36:41", "remaining_time": "4:11:05"}
+{"current_steps": 980, "total_steps": 2094, "loss": 0.6887, "lr": 6.414479805339465e-06, "epoch": 0.4680038204393505, "percentage": 46.8, "elapsed_time": "3:38:35", "remaining_time": "4:08:29"}
+{"current_steps": 990, "total_steps": 2094, "loss": 0.6858, "lr": 6.3343171030346525e-06, "epoch": 0.47277936962750716, "percentage": 47.28, "elapsed_time": "3:40:16", "remaining_time": "4:05:38"}
+{"current_steps": 1000, "total_steps": 2094, "loss": 0.7073, "lr": 6.253783389600136e-06, "epoch": 0.4775549188156638, "percentage": 47.76, "elapsed_time": "3:42:08", "remaining_time": "4:03:01"}
+{"current_steps": 1000, "total_steps": 2094, "eval_loss": 0.6407110095024109, "epoch": 0.4775549188156638, "percentage": 47.76, "elapsed_time": "3:51:02", "remaining_time": "4:12:46"}
+{"current_steps": 1010, "total_steps": 2094, "loss": 0.7207, "lr": 6.172901057692007e-06, "epoch": 0.48233046800382046, "percentage": 48.23, "elapsed_time": "3:53:18", "remaining_time": "4:10:24"}
+{"current_steps": 1020, "total_steps": 2094, "loss": 0.7363, "lr": 6.0916925969008275e-06, "epoch": 0.4871060171919771, "percentage": 48.71, "elapsed_time": "3:55:05", "remaining_time": "4:07:32"}
+{"current_steps": 1030, "total_steps": 2094, "loss": 0.6729, "lr": 6.010180587498347e-06, "epoch": 0.4918815663801337, "percentage": 49.19, "elapsed_time": "3:56:53", "remaining_time": "4:04:42"}
+{"current_steps": 1040, "total_steps": 2094, "loss": 0.6956, "lr": 5.928387694158968e-06, "epoch": 0.49665711556829034, "percentage": 49.67, "elapsed_time": "3:58:47", "remaining_time": "4:02:00"}
+{"current_steps": 1050, "total_steps": 2094, "loss": 0.6896, "lr": 5.8463366596577706e-06, "epoch": 0.501432664756447, "percentage": 50.14, "elapsed_time": "4:00:34", "remaining_time": "3:59:12"}
+{"current_steps": 1060, "total_steps": 2094, "loss": 0.6861, "lr": 5.764050298546808e-06, "epoch": 0.5062082139446036, "percentage": 50.62, "elapsed_time": "4:02:19", "remaining_time": "3:56:22"}
+{"current_steps": 1070, "total_steps": 2094, "loss": 0.6762, "lr": 5.68155149081145e-06, "epoch": 0.5109837631327603, "percentage": 51.1, "elapsed_time": "4:04:10", "remaining_time": "3:53:40"}
+{"current_steps": 1080, "total_steps": 2094, "loss": 0.6717, "lr": 5.598863175508526e-06, "epoch": 0.5157593123209169, "percentage": 51.58, "elapsed_time": "4:06:02", "remaining_time": "3:50:59"}
+{"current_steps": 1090, "total_steps": 2094, "loss": 0.6825, "lr": 5.516008344388053e-06, "epoch": 0.5205348615090736, "percentage": 52.05, "elapsed_time": "4:07:55", "remaining_time": "3:48:21"}
+{"current_steps": 1100, "total_steps": 2094, "loss": 0.6771, "lr": 5.433010035500299e-06, "epoch": 0.5253104106972302, "percentage": 52.53, "elapsed_time": "4:09:48", "remaining_time": "3:45:44"}
+{"current_steps": 1110, "total_steps": 2094, "loss": 0.674, "lr": 5.3498913267899864e-06, "epoch": 0.5300859598853869, "percentage": 53.01, "elapsed_time": "4:11:44", "remaining_time": "3:43:09"}
+{"current_steps": 1120, "total_steps": 2094, "loss": 0.6662, "lr": 5.2666753296793895e-06, "epoch": 0.5348615090735435, "percentage": 53.49, "elapsed_time": "4:13:26", "remaining_time": "3:40:23"}
+{"current_steps": 1130, "total_steps": 2094, "loss": 0.6765, "lr": 5.183385182642136e-06, "epoch": 0.5396370582617, "percentage": 53.96, "elapsed_time": "4:15:16", "remaining_time": "3:37:46"}
+{"current_steps": 1140, "total_steps": 2094, "loss": 0.6682, "lr": 5.100044044769472e-06, "epoch": 0.5444126074498568, "percentage": 54.44, "elapsed_time": "4:17:07", "remaining_time": "3:35:10"}
+{"current_steps": 1150, "total_steps": 2094, "loss": 0.6583, "lr": 5.016675089330817e-06, "epoch": 0.5491881566380133, "percentage": 54.92, "elapsed_time": "4:18:56", "remaining_time": "3:32:33"}
+{"current_steps": 1160, "total_steps": 2094, "loss": 0.6456, "lr": 4.933301497330344e-06, "epoch": 0.55396370582617, "percentage": 55.4, "elapsed_time": "4:20:46", "remaining_time": "3:29:58"}
+{"current_steps": 1170, "total_steps": 2094, "loss": 0.673, "lr": 4.849946451061444e-06, "epoch": 0.5587392550143266, "percentage": 55.87, "elapsed_time": "4:22:40", "remaining_time": "3:27:26"}
+{"current_steps": 1180, "total_steps": 2094, "loss": 0.6372, "lr": 4.766633127660805e-06, "epoch": 0.5635148042024832, "percentage": 56.35, "elapsed_time": "4:24:30", "remaining_time": "3:24:52"}
+{"current_steps": 1190, "total_steps": 2094, "loss": 0.6352, "lr": 4.683384692663937e-06, "epoch": 0.5682903533906399, "percentage": 56.83, "elapsed_time": "4:26:21", "remaining_time": "3:22:20"}
+{"current_steps": 1200, "total_steps": 2094, "loss": 0.6143, "lr": 4.600224293563926e-06, "epoch": 0.5730659025787965, "percentage": 57.31, "elapsed_time": "4:28:13", "remaining_time": "3:19:49"}
+{"current_steps": 1200, "total_steps": 2094, "eval_loss": 0.5672308206558228, "epoch": 0.5730659025787965, "percentage": 57.31, "elapsed_time": "4:37:08", "remaining_time": "3:26:27"}
+{"current_steps": 1210, "total_steps": 2094, "loss": 0.6482, "lr": 4.517175053375191e-06, "epoch": 0.5778414517669532, "percentage": 57.78, "elapsed_time": "4:39:20", "remaining_time": "3:24:04"}
+{"current_steps": 1220, "total_steps": 2094, "loss": 0.6244, "lr": 4.434260064204067e-06, "epoch": 0.5826170009551098, "percentage": 58.26, "elapsed_time": "4:41:08", "remaining_time": "3:21:24"}
+{"current_steps": 1230, "total_steps": 2094, "loss": 0.6231, "lr": 4.351502380827959e-06, "epoch": 0.5873925501432665, "percentage": 58.74, "elapsed_time": "4:42:56", "remaining_time": "3:18:44"}
+{"current_steps": 1240, "total_steps": 2094, "loss": 0.6515, "lr": 4.268925014284898e-06, "epoch": 0.5921680993314231, "percentage": 59.22, "elapsed_time": "4:44:47", "remaining_time": "3:16:08"}
+{"current_steps": 1250, "total_steps": 2094, "loss": 0.6027, "lr": 4.18655092547524e-06, "epoch": 0.5969436485195797, "percentage": 59.69, "elapsed_time": "4:46:36", "remaining_time": "3:13:31"}
+{"current_steps": 1260, "total_steps": 2094, "loss": 0.636, "lr": 4.104403018777323e-06, "epoch": 0.6017191977077364, "percentage": 60.17, "elapsed_time": "4:48:28", "remaining_time": "3:10:56"}
+{"current_steps": 1270, "total_steps": 2094, "loss": 0.6356, "lr": 4.022504135678822e-06, "epoch": 0.606494746895893, "percentage": 60.65, "elapsed_time": "4:50:21", "remaining_time": "3:08:23"}
+{"current_steps": 1280, "total_steps": 2094, "loss": 0.6303, "lr": 3.94087704842561e-06, "epoch": 0.6112702960840497, "percentage": 61.13, "elapsed_time": "4:52:07", "remaining_time": "3:05:46"}
+{"current_steps": 1290, "total_steps": 2094, "loss": 0.6181, "lr": 3.859544453689853e-06, "epoch": 0.6160458452722063, "percentage": 61.6, "elapsed_time": "4:54:06", "remaining_time": "3:03:18"}
+{"current_steps": 1300, "total_steps": 2094, "loss": 0.6075, "lr": 3.778528966259137e-06, "epoch": 0.620821394460363, "percentage": 62.08, "elapsed_time": "4:55:54", "remaining_time": "3:00:44"}
+{"current_steps": 1310, "total_steps": 2094, "loss": 0.6106, "lr": 3.697853112748345e-06, "epoch": 0.6255969436485196, "percentage": 62.56, "elapsed_time": "4:57:50", "remaining_time": "2:58:15"}
+{"current_steps": 1320, "total_steps": 2094, "loss": 0.599, "lr": 3.6175393253360704e-06, "epoch": 0.6303724928366762, "percentage": 63.04, "elapsed_time": "4:59:44", "remaining_time": "2:55:45"}
+{"current_steps": 1330, "total_steps": 2094, "loss": 0.5996, "lr": 3.537609935527264e-06, "epoch": 0.6351480420248329, "percentage": 63.51, "elapsed_time": "5:01:34", "remaining_time": "2:53:13"}
+{"current_steps": 1340, "total_steps": 2094, "loss": 0.5867, "lr": 3.458087167943905e-06, "epoch": 0.6399235912129895, "percentage": 63.99, "elapsed_time": "5:03:30", "remaining_time": "2:50:46"}
+{"current_steps": 1350, "total_steps": 2094, "loss": 0.614, "lr": 3.3789931341453564e-06, "epoch": 0.6446991404011462, "percentage": 64.47, "elapsed_time": "5:05:24", "remaining_time": "2:48:18"}
+{"current_steps": 1360, "total_steps": 2094, "loss": 0.5858, "lr": 3.3003498264801915e-06, "epoch": 0.6494746895893028, "percentage": 64.95, "elapsed_time": "5:07:09", "remaining_time": "2:45:46"}
+{"current_steps": 1370, "total_steps": 2094, "loss": 0.6073, "lr": 3.2221791119711372e-06, "epoch": 0.6542502387774594, "percentage": 65.43, "elapsed_time": "5:08:56", "remaining_time": "2:43:16"}
+{"current_steps": 1380, "total_steps": 2094, "loss": 0.598, "lr": 3.144502726234889e-06, "epoch": 0.6590257879656161, "percentage": 65.9, "elapsed_time": "5:10:49", "remaining_time": "2:40:49"}
+{"current_steps": 1390, "total_steps": 2094, "loss": 0.5864, "lr": 3.067342267438446e-06, "epoch": 0.6638013371537727, "percentage": 66.38, "elapsed_time": "5:12:44", "remaining_time": "2:38:23"}
+{"current_steps": 1400, "total_steps": 2094, "loss": 0.5726, "lr": 2.9907191902936773e-06, "epoch": 0.6685768863419294, "percentage": 66.86, "elapsed_time": "5:14:38", "remaining_time": "2:35:58"}
+{"current_steps": 1400, "total_steps": 2094, "eval_loss": 0.5096372961997986, "epoch": 0.6685768863419294, "percentage": 66.86, "elapsed_time": "5:23:32", "remaining_time": "2:40:23"}
+{"current_steps": 1410, "total_steps": 2094, "loss": 0.5678, "lr": 2.914654800091768e-06, "epoch": 0.673352435530086, "percentage": 67.34, "elapsed_time": "5:25:50", "remaining_time": "2:38:04"}
+{"current_steps": 1420, "total_steps": 2094, "loss": 0.5875, "lr": 2.8391702467792137e-06, "epoch": 0.6781279847182426, "percentage": 67.81, "elapsed_time": "5:27:46", "remaining_time": "2:35:34"}
+{"current_steps": 1430, "total_steps": 2094, "loss": 0.5745, "lr": 2.764286519077014e-06, "epoch": 0.6829035339063992, "percentage": 68.29, "elapsed_time": "5:29:35", "remaining_time": "2:33:02"}
+{"current_steps": 1440, "total_steps": 2094, "loss": 0.5748, "lr": 2.6900244386446903e-06, "epoch": 0.6876790830945558, "percentage": 68.77, "elapsed_time": "5:31:24", "remaining_time": "2:30:30"}
+{"current_steps": 1450, "total_steps": 2094, "loss": 0.582, "lr": 2.616404654290752e-06, "epoch": 0.6924546322827125, "percentage": 69.25, "elapsed_time": "5:33:17", "remaining_time": "2:28:01"}
+{"current_steps": 1460, "total_steps": 2094, "loss": 0.5859, "lr": 2.5434476362312375e-06, "epoch": 0.6972301814708691, "percentage": 69.72, "elapsed_time": "5:35:11", "remaining_time": "2:25:33"}
+{"current_steps": 1470, "total_steps": 2094, "loss": 0.5778, "lr": 2.4711736703979015e-06, "epoch": 0.7020057306590258, "percentage": 70.2, "elapsed_time": "5:37:12", "remaining_time": "2:23:08"}
+{"current_steps": 1480, "total_steps": 2094, "loss": 0.5833, "lr": 2.399602852797647e-06, "epoch": 0.7067812798471824, "percentage": 70.68, "elapsed_time": "5:39:03", "remaining_time": "2:20:39"}
+{"current_steps": 1490, "total_steps": 2094, "loss": 0.5677, "lr": 2.3287550839247625e-06, "epoch": 0.711556829035339, "percentage": 71.16, "elapsed_time": "5:40:56", "remaining_time": "2:18:12"}
+{"current_steps": 1500, "total_steps": 2094, "loss": 0.5501, "lr": 2.2586500632275333e-06, "epoch": 0.7163323782234957, "percentage": 71.63, "elapsed_time": "5:42:50", "remaining_time": "2:15:46"}
+{"current_steps": 1510, "total_steps": 2094, "loss": 0.5432, "lr": 2.1893072836307433e-06, "epoch": 0.7211079274116523, "percentage": 72.11, "elapsed_time": "5:44:44", "remaining_time": "2:13:19"}
+{"current_steps": 1520, "total_steps": 2094, "loss": 0.6017, "lr": 2.1207460261156066e-06, "epoch": 0.725883476599809, "percentage": 72.59, "elapsed_time": "5:46:35", "remaining_time": "2:10:53"}
+{"current_steps": 1530, "total_steps": 2094, "loss": 0.5361, "lr": 2.052985354358622e-06, "epoch": 0.7306590257879656, "percentage": 73.07, "elapsed_time": "5:48:26", "remaining_time": "2:08:26"}
+{"current_steps": 1540, "total_steps": 2094, "loss": 0.544, "lr": 1.986044109430869e-06, "epoch": 0.7354345749761223, "percentage": 73.54, "elapsed_time": "5:50:15", "remaining_time": "2:05:59"}
+{"current_steps": 1550, "total_steps": 2094, "loss": 0.5544, "lr": 1.91994090455918e-06, "epoch": 0.7402101241642789, "percentage": 74.02, "elapsed_time": "5:52:04", "remaining_time": "2:03:34"}
+{"current_steps": 1560, "total_steps": 2094, "loss": 0.5743, "lr": 1.8546941199506752e-06, "epoch": 0.7449856733524355, "percentage": 74.5, "elapsed_time": "5:53:57", "remaining_time": "2:01:09"}
+{"current_steps": 1570, "total_steps": 2094, "loss": 0.5516, "lr": 1.790321897682083e-06, "epoch": 0.7497612225405922, "percentage": 74.98, "elapsed_time": "5:55:45", "remaining_time": "1:58:44"}
+{"current_steps": 1580, "total_steps": 2094, "loss": 0.5598, "lr": 1.7268421366552851e-06, "epoch": 0.7545367717287488, "percentage": 75.45, "elapsed_time": "5:57:38", "remaining_time": "1:56:20"}
+{"current_steps": 1590, "total_steps": 2094, "loss": 0.5457, "lr": 1.6642724876204658e-06, "epoch": 0.7593123209169055, "percentage": 75.93, "elapsed_time": "5:59:27", "remaining_time": "1:53:56"}
+{"current_steps": 1600, "total_steps": 2094, "loss": 0.5623, "lr": 1.602630348268267e-06, "epoch": 0.7640878701050621, "percentage": 76.41, "elapsed_time": "6:01:14", "remaining_time": "1:51:32"}
+{"current_steps": 1600, "total_steps": 2094, "eval_loss": 0.46827441453933716, "epoch": 0.7640878701050621, "percentage": 76.41, "elapsed_time": "6:10:08", "remaining_time": "1:54:16"}
+{"current_steps": 1610, "total_steps": 2094, "loss": 0.5522, "lr": 1.541932858392296e-06, "epoch": 0.7688634192932188, "percentage": 76.89, "elapsed_time": "6:12:23", "remaining_time": "1:51:57"}
+{"current_steps": 1620, "total_steps": 2094, "loss": 0.5321, "lr": 1.482196895123364e-06, "epoch": 0.7736389684813754, "percentage": 77.36, "elapsed_time": "6:14:19", "remaining_time": "1:49:31"}
+{"current_steps": 1630, "total_steps": 2094, "loss": 0.5789, "lr": 1.423439068236736e-06, "epoch": 0.778414517669532, "percentage": 77.84, "elapsed_time": "6:16:08", "remaining_time": "1:47:04"}
+{"current_steps": 1640, "total_steps": 2094, "loss": 0.5628, "lr": 1.3656757155337413e-06, "epoch": 0.7831900668576887, "percentage": 78.32, "elapsed_time": "6:17:59", "remaining_time": "1:44:38"}
+{"current_steps": 1650, "total_steps": 2094, "loss": 0.5139, "lr": 1.3089228982989771e-06, "epoch": 0.7879656160458453, "percentage": 78.8, "elapsed_time": "6:19:46", "remaining_time": "1:42:11"}
+{"current_steps": 1660, "total_steps": 2094, "loss": 0.5229, "lr": 1.2531963968344346e-06, "epoch": 0.792741165234002, "percentage": 79.27, "elapsed_time": "6:21:36", "remaining_time": "1:39:46"}
+{"current_steps": 1670, "total_steps": 2094, "loss": 0.5184, "lr": 1.1985117060717278e-06, "epoch": 0.7975167144221585, "percentage": 79.75, "elapsed_time": "6:23:33", "remaining_time": "1:37:22"}
+{"current_steps": 1680, "total_steps": 2094, "loss": 0.5248, "lr": 1.1448840312636812e-06, "epoch": 0.8022922636103151, "percentage": 80.23, "elapsed_time": "6:25:21", "remaining_time": "1:34:57"}
+{"current_steps": 1690, "total_steps": 2094, "loss": 0.5451, "lr": 1.0923282837564537e-06, "epoch": 0.8070678127984718, "percentage": 80.71, "elapsed_time": "6:27:18", "remaining_time": "1:32:35"}
+{"current_steps": 1700, "total_steps": 2094, "loss": 0.522, "lr": 1.0408590768434018e-06, "epoch": 0.8118433619866284, "percentage": 81.18, "elapsed_time": "6:29:11", "remaining_time": "1:30:12"}
+{"current_steps": 1710, "total_steps": 2094, "loss": 0.5143, "lr": 9.904907217018e-07, "epoch": 0.8166189111747851, "percentage": 81.66, "elapsed_time": "6:31:01", "remaining_time": "1:27:48"}
+{"current_steps": 1720, "total_steps": 2094, "loss": 0.5339, "lr": 9.412372234135753e-07, "epoch": 0.8213944603629417, "percentage": 82.14, "elapsed_time": "6:32:50", "remaining_time": "1:25:25"}
+{"current_steps": 1730, "total_steps": 2094, "loss": 0.5326, "lr": 8.931122770711425e-07, "epoch": 0.8261700095510984, "percentage": 82.62, "elapsed_time": "6:34:43", "remaining_time": "1:23:03"}
+{"current_steps": 1740, "total_steps": 2094, "loss": 0.5308, "lr": 8.461292639694519e-07, "epoch": 0.830945558739255, "percentage": 83.09, "elapsed_time": "6:36:40", "remaining_time": "1:20:42"}
+{"current_steps": 1750, "total_steps": 2094, "loss": 0.4943, "lr": 8.003012478852679e-07, "epoch": 0.8357211079274116, "percentage": 83.57, "elapsed_time": "6:38:26", "remaining_time": "1:18:19"}
+{"current_steps": 1760, "total_steps": 2094, "loss": 0.5474, "lr": 7.556409714447488e-07, "epoch": 0.8404966571155683, "percentage": 84.05, "elapsed_time": "6:40:19", "remaining_time": "1:15:58"}
+{"current_steps": 1770, "total_steps": 2094, "loss": 0.5301, "lr": 7.121608525803142e-07, "epoch": 0.8452722063037249, "percentage": 84.53, "elapsed_time": "6:42:09", "remaining_time": "1:13:36"}
+{"current_steps": 1780, "total_steps": 2094, "loss": 0.5302, "lr": 6.698729810778065e-07, "epoch": 0.8500477554918816, "percentage": 85.0, "elapsed_time": "6:44:05", "remaining_time": "1:11:17"}
+{"current_steps": 1790, "total_steps": 2094, "loss": 0.5075, "lr": 6.287891152148823e-07, "epoch": 0.8548233046800382, "percentage": 85.48, "elapsed_time": "6:45:50", "remaining_time": "1:08:55"}
+{"current_steps": 1800, "total_steps": 2094, "loss": 0.5206, "lr": 5.889206784915863e-07, "epoch": 0.8595988538681948, "percentage": 85.96, "elapsed_time": "6:47:43", "remaining_time": "1:06:35"}
+{"current_steps": 1800, "total_steps": 2094, "eval_loss": 0.44646286964416504, "epoch": 0.8595988538681948, "percentage": 85.96, "elapsed_time": "6:56:37", "remaining_time": "1:08:02"}
+{"current_steps": 1810, "total_steps": 2094, "loss": 0.5305, "lr": 5.502787564540102e-07, "epoch": 0.8643744030563515, "percentage": 86.44, "elapsed_time": "6:58:49", "remaining_time": "1:05:42"}
+{"current_steps": 1820, "total_steps": 2094, "loss": 0.5115, "lr": 5.128740936119242e-07, "epoch": 0.8691499522445081, "percentage": 86.91, "elapsed_time": "7:00:41", "remaining_time": "1:03:20"}
+{"current_steps": 1830, "total_steps": 2094, "loss": 0.501, "lr": 4.7671709045122914e-07, "epoch": 0.8739255014326648, "percentage": 87.39, "elapsed_time": "7:02:29", "remaining_time": "1:00:56"}
+{"current_steps": 1840, "total_steps": 2094, "loss": 0.5316, "lr": 4.4181780054206925e-07, "epoch": 0.8787010506208214, "percentage": 87.87, "elapsed_time": "7:04:25", "remaining_time": "0:58:35"}
+{"current_steps": 1850, "total_steps": 2094, "loss": 0.5084, "lr": 4.081859277434025e-07, "epoch": 0.8834765998089781, "percentage": 88.35, "elapsed_time": "7:06:14", "remaining_time": "0:56:13"}
+{"current_steps": 1860, "total_steps": 2094, "loss": 0.4988, "lr": 3.758308235048158e-07, "epoch": 0.8882521489971347, "percentage": 88.83, "elapsed_time": "7:07:58", "remaining_time": "0:53:50"}
+{"current_steps": 1870, "total_steps": 2094, "loss": 0.5248, "lr": 3.4476148426632215e-07, "epoch": 0.8930276981852913, "percentage": 89.3, "elapsed_time": "7:09:54", "remaining_time": "0:51:29"}
+{"current_steps": 1880, "total_steps": 2094, "loss": 0.5263, "lr": 3.1498654895687095e-07, "epoch": 0.897803247373448, "percentage": 89.78, "elapsed_time": "7:11:47", "remaining_time": "0:49:09"}
+{"current_steps": 1890, "total_steps": 2094, "loss": 0.5129, "lr": 2.8651429659226906e-07, "epoch": 0.9025787965616046, "percentage": 90.26, "elapsed_time": "7:13:39", "remaining_time": "0:46:48"}
+{"current_steps": 1900, "total_steps": 2094, "loss": 0.5033, "lr": 2.593526439731697e-07, "epoch": 0.9073543457497613, "percentage": 90.74, "elapsed_time": "7:15:34", "remaining_time": "0:44:28"}
+{"current_steps": 1910, "total_steps": 2094, "loss": 0.5157, "lr": 2.3350914348378606e-07, "epoch": 0.9121298949379179, "percentage": 91.21, "elapsed_time": "7:17:21", "remaining_time": "0:42:07"}
+{"current_steps": 1920, "total_steps": 2094, "loss": 0.5158, "lr": 2.0899098099192273e-07, "epoch": 0.9169054441260746, "percentage": 91.69, "elapsed_time": "7:19:05", "remaining_time": "0:39:47"}
+{"current_steps": 1930, "total_steps": 2094, "loss": 0.5145, "lr": 1.8580497385092376e-07, "epoch": 0.9216809933142311, "percentage": 92.17, "elapsed_time": "7:20:54", "remaining_time": "0:37:27"}
+{"current_steps": 1940, "total_steps": 2094, "loss": 0.5321, "lr": 1.6395756900408454e-07, "epoch": 0.9264565425023877, "percentage": 92.65, "elapsed_time": "7:22:44", "remaining_time": "0:35:08"}
+{"current_steps": 1950, "total_steps": 2094, "loss": 0.5065, "lr": 1.4345484119206222e-07, "epoch": 0.9312320916905444, "percentage": 93.12, "elapsed_time": "7:24:35", "remaining_time": "0:32:49"}
+{"current_steps": 1960, "total_steps": 2094, "loss": 0.54, "lr": 1.2430249126376913e-07, "epoch": 0.936007640878701, "percentage": 93.6, "elapsed_time": "7:26:22", "remaining_time": "0:30:31"}
+{"current_steps": 1970, "total_steps": 2094, "loss": 0.5084, "lr": 1.065058445912398e-07, "epoch": 0.9407831900668577, "percentage": 94.08, "elapsed_time": "7:28:15", "remaining_time": "0:28:12"}
+{"current_steps": 1980, "total_steps": 2094, "loss": 0.527, "lr": 9.006984958888742e-08, "epoch": 0.9455587392550143, "percentage": 94.56, "elapsed_time": "7:30:05", "remaining_time": "0:25:54"}
+{"current_steps": 1990, "total_steps": 2094, "loss": 0.4929, "lr": 7.499907633758797e-08, "epoch": 0.9503342884431709, "percentage": 95.03, "elapsed_time": "7:31:56", "remaining_time": "0:23:37"}
+{"current_steps": 2000, "total_steps": 2094, "loss": 0.5054, "lr": 6.129771531395045e-08, "epoch": 0.9551098376313276, "percentage": 95.51, "elapsed_time": "7:33:45", "remaining_time": "0:21:19"}
+{"current_steps": 2000, "total_steps": 2094, "eval_loss": 0.43961772322654724, "epoch": 0.9551098376313276, "percentage": 95.51, "elapsed_time": "7:42:39", "remaining_time": "0:21:44"}
+{"current_steps": 2010, "total_steps": 2094, "loss": 0.4983, "lr": 4.896957622514298e-08, "epoch": 0.9598853868194842, "percentage": 95.99, "elapsed_time": "7:44:52", "remaining_time": "0:19:25"}
+{"current_steps": 2020, "total_steps": 2094, "loss": 0.5219, "lr": 3.801808694959053e-08, "epoch": 0.9646609360076409, "percentage": 96.47, "elapsed_time": "7:46:45", "remaining_time": "0:17:05"}
+{"current_steps": 2030, "total_steps": 2094, "loss": 0.5397, "lr": 2.8446292583844126e-08, "epoch": 0.9694364851957975, "percentage": 96.94, "elapsed_time": "7:48:34", "remaining_time": "0:14:46"}
+{"current_steps": 2040, "total_steps": 2094, "loss": 0.525, "lr": 2.025685459588145e-08, "epoch": 0.9742120343839542, "percentage": 97.42, "elapsed_time": "7:50:29", "remaining_time": "0:12:27"}
+{"current_steps": 2050, "total_steps": 2094, "loss": 0.5086, "lr": 1.3452050085075441e-08, "epoch": 0.9789875835721108, "percentage": 97.9, "elapsed_time": "7:52:19", "remaining_time": "0:10:08"}
+{"current_steps": 2060, "total_steps": 2094, "loss": 0.5122, "lr": 8.033771149041913e-09, "epoch": 0.9837631327602674, "percentage": 98.38, "elapsed_time": "7:54:07", "remaining_time": "0:07:49"}
+{"current_steps": 2070, "total_steps": 2094, "loss": 0.5168, "lr": 4.003524357534261e-09, "epoch": 0.9885386819484241, "percentage": 98.85, "elapsed_time": "7:55:59", "remaining_time": "0:05:31"}
+{"current_steps": 2080, "total_steps": 2094, "loss": 0.5155, "lr": 1.3624303335380006e-09, "epoch": 0.9933142311365807, "percentage": 99.33, "elapsed_time": "7:57:50", "remaining_time": "0:03:12"}
+{"current_steps": 2090, "total_steps": 2094, "loss": 0.5051, "lr": 1.1122344167613374e-10, "epoch": 0.9980897803247374, "percentage": 99.81, "elapsed_time": "7:59:41", "remaining_time": "0:00:55"}
+{"current_steps": 2094, "total_steps": 2094, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "8:00:49", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1586 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 200,
+  "global_step": 2094,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004775549188156638,
+      "grad_norm": 1.5947464157895972,
+      "learning_rate": 4.7619047619047623e-07,
+      "loss": 1.1507,
+      "step": 10
+    },
+    {
+      "epoch": 0.009551098376313277,
+      "grad_norm": 1.0799275908070096,
+      "learning_rate": 9.523809523809525e-07,
+      "loss": 1.1084,
+      "step": 20
+    },
+    {
+      "epoch": 0.014326647564469915,
+      "grad_norm": 0.8982107389870104,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 1.0874,
+      "step": 30
+    },
+    {
+      "epoch": 0.019102196752626553,
+      "grad_norm": 0.7755204372056955,
+      "learning_rate": 1.904761904761905e-06,
+      "loss": 1.1068,
+      "step": 40
+    },
+    {
+      "epoch": 0.02387774594078319,
+      "grad_norm": 0.7764375006527714,
+      "learning_rate": 2.380952380952381e-06,
+      "loss": 1.1152,
+      "step": 50
+    },
+    {
+      "epoch": 0.02865329512893983,
+      "grad_norm": 0.8635581450994269,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 1.0964,
+      "step": 60
+    },
+    {
+      "epoch": 0.033428844317096466,
+      "grad_norm": 0.7474505965610809,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.1005,
+      "step": 70
+    },
+    {
+      "epoch": 0.038204393505253106,
+      "grad_norm": 0.7625379001449059,
+      "learning_rate": 3.80952380952381e-06,
+      "loss": 1.0933,
+      "step": 80
+    },
+    {
+      "epoch": 0.04297994269340974,
+      "grad_norm": 0.7457628875786683,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 1.0397,
+      "step": 90
+    },
+    {
+      "epoch": 0.04775549188156638,
+      "grad_norm": 0.7668973425259701,
+      "learning_rate": 4.761904761904762e-06,
+      "loss": 1.0723,
+      "step": 100
+    },
+    {
+      "epoch": 0.05253104106972302,
+      "grad_norm": 0.7418999154350163,
+      "learning_rate": 5.2380952380952384e-06,
+      "loss": 1.0753,
+      "step": 110
+    },
+    {
+      "epoch": 0.05730659025787966,
+      "grad_norm": 0.7536046873082832,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 1.0604,
+      "step": 120
+    },
+    {
+      "epoch": 0.06208213944603629,
+      "grad_norm": 0.7126742899879043,
+      "learning_rate": 6.1904761904761914e-06,
+      "loss": 1.0844,
+      "step": 130
+    },
+    {
+      "epoch": 0.06685768863419293,
+      "grad_norm": 0.7388477971520834,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.0738,
+      "step": 140
+    },
+    {
+      "epoch": 0.07163323782234957,
+      "grad_norm": 0.7063263241327802,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 1.0638,
+      "step": 150
+    },
+    {
+      "epoch": 0.07640878701050621,
+      "grad_norm": 0.7435364320190926,
+      "learning_rate": 7.61904761904762e-06,
+      "loss": 1.089,
+      "step": 160
+    },
+    {
+      "epoch": 0.08118433619866285,
+      "grad_norm": 0.7196795649504337,
+      "learning_rate": 8.095238095238097e-06,
+      "loss": 1.0215,
+      "step": 170
+    },
+    {
+      "epoch": 0.08595988538681948,
+      "grad_norm": 0.792285178872838,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 1.0489,
+      "step": 180
+    },
+    {
+      "epoch": 0.09073543457497613,
+      "grad_norm": 0.8765129377706619,
+      "learning_rate": 9.047619047619049e-06,
+      "loss": 1.047,
+      "step": 190
+    },
+    {
+      "epoch": 0.09551098376313276,
+      "grad_norm": 0.6926043469847205,
+      "learning_rate": 9.523809523809525e-06,
+      "loss": 1.0484,
+      "step": 200
+    },
+    {
+      "epoch": 0.09551098376313276,
+      "eval_loss": 1.0037423372268677,
+      "eval_runtime": 534.236,
+      "eval_samples_per_second": 27.872,
+      "eval_steps_per_second": 3.485,
+      "step": 200
+    },
+    {
+      "epoch": 0.10028653295128939,
+      "grad_norm": 0.7189100769671237,
+      "learning_rate": 1e-05,
+      "loss": 1.0786,
+      "step": 210
+    },
+    {
+      "epoch": 0.10506208213944604,
+      "grad_norm": 0.6530269733207105,
+      "learning_rate": 9.99930486701988e-06,
+      "loss": 1.0568,
+      "step": 220
+    },
+    {
+      "epoch": 0.10983763132760267,
+      "grad_norm": 0.7951921984643434,
+      "learning_rate": 9.99721966136347e-06,
+      "loss": 1.0264,
+      "step": 230
+    },
+    {
+      "epoch": 0.11461318051575932,
+      "grad_norm": 0.7425556549789157,
+      "learning_rate": 9.99374496282885e-06,
+      "loss": 1.0093,
+      "step": 240
+    },
+    {
+      "epoch": 0.11938872970391595,
+      "grad_norm": 0.7965678052101759,
+      "learning_rate": 9.988881737567046e-06,
+      "loss": 1.0172,
+      "step": 250
+    },
+    {
+      "epoch": 0.12416427889207259,
+      "grad_norm": 0.6836841577113884,
+      "learning_rate": 9.982631337813363e-06,
+      "loss": 1.0369,
+      "step": 260
+    },
+    {
+      "epoch": 0.12893982808022922,
+      "grad_norm": 0.7403849280275662,
+      "learning_rate": 9.974995501511404e-06,
+      "loss": 0.998,
+      "step": 270
+    },
+    {
+      "epoch": 0.13371537726838587,
+      "grad_norm": 0.8090595134087124,
+      "learning_rate": 9.965976351829827e-06,
+      "loss": 1.0232,
+      "step": 280
+    },
+    {
+      "epoch": 0.1384909264565425,
+      "grad_norm": 0.7595821597209347,
+      "learning_rate": 9.95557639657199e-06,
+      "loss": 1.0093,
+      "step": 290
+    },
+    {
+      "epoch": 0.14326647564469913,
+      "grad_norm": 0.6967946094456987,
+      "learning_rate": 9.943798527478652e-06,
+      "loss": 1.0048,
+      "step": 300
+    },
+    {
+      "epoch": 0.14804202483285578,
+      "grad_norm": 0.8063573400514253,
+      "learning_rate": 9.930646019423909e-06,
+      "loss": 0.9838,
+      "step": 310
+    },
+    {
+      "epoch": 0.15281757402101243,
+      "grad_norm": 0.8442835891928957,
+      "learning_rate": 9.916122529504605e-06,
+      "loss": 0.9935,
+      "step": 320
+    },
+    {
+      "epoch": 0.15759312320916904,
+      "grad_norm": 0.781371439165008,
+      "learning_rate": 9.900232096023478e-06,
+      "loss": 0.9834,
+      "step": 330
+    },
+    {
+      "epoch": 0.1623686723973257,
+      "grad_norm": 0.8183448490469395,
+      "learning_rate": 9.882979137366275e-06,
+      "loss": 0.9638,
+      "step": 340
+    },
+    {
+      "epoch": 0.16714422158548234,
+      "grad_norm": 0.7604900553397272,
+      "learning_rate": 9.864368450773227e-06,
+      "loss": 0.983,
+      "step": 350
+    },
+    {
+      "epoch": 0.17191977077363896,
+      "grad_norm": 0.8396013068852565,
+      "learning_rate": 9.844405211005145e-06,
+      "loss": 0.9759,
+      "step": 360
+    },
+    {
+      "epoch": 0.1766953199617956,
+      "grad_norm": 0.8365439774930438,
+      "learning_rate": 9.823094968904572e-06,
+      "loss": 0.9927,
+      "step": 370
+    },
+    {
+      "epoch": 0.18147086914995225,
+      "grad_norm": 0.7930078729758488,
+      "learning_rate": 9.800443649852347e-06,
+      "loss": 0.985,
+      "step": 380
+    },
+    {
+      "epoch": 0.18624641833810887,
+      "grad_norm": 0.6951067649253269,
+      "learning_rate": 9.776457552120034e-06,
+      "loss": 0.9578,
+      "step": 390
+    },
+    {
+      "epoch": 0.19102196752626552,
+      "grad_norm": 0.7758966278638689,
+      "learning_rate": 9.751143345118675e-06,
+      "loss": 0.9828,
+      "step": 400
+    },
+    {
+      "epoch": 0.19102196752626552,
+      "eval_loss": 0.911033034324646,
+      "eval_runtime": 534.1402,
+      "eval_samples_per_second": 27.877,
+      "eval_steps_per_second": 3.486,
+      "step": 400
+    },
+    {
+      "epoch": 0.19579751671442217,
+      "grad_norm": 0.8178388178466306,
+      "learning_rate": 9.724508067544328e-06,
+      "loss": 0.9593,
+      "step": 410
+    },
+    {
+      "epoch": 0.20057306590257878,
+      "grad_norm": 0.7948626800066163,
+      "learning_rate": 9.696559125420949e-06,
+      "loss": 0.9342,
+      "step": 420
+    },
+    {
+      "epoch": 0.20534861509073543,
+      "grad_norm": 0.7690821022431013,
+      "learning_rate": 9.667304290041102e-06,
+      "loss": 0.9182,
+      "step": 430
+    },
+    {
+      "epoch": 0.21012416427889208,
+      "grad_norm": 0.8011672592566321,
+      "learning_rate": 9.636751695805154e-06,
+      "loss": 0.9399,
+      "step": 440
+    },
+    {
+      "epoch": 0.2148997134670487,
+      "grad_norm": 0.7896064611214817,
+      "learning_rate": 9.604909837959456e-06,
+      "loss": 0.9546,
+      "step": 450
+    },
+    {
+      "epoch": 0.21967526265520534,
+      "grad_norm": 0.8683971543565645,
+      "learning_rate": 9.57178757023422e-06,
+      "loss": 0.9493,
+      "step": 460
+    },
+    {
+      "epoch": 0.224450811843362,
+      "grad_norm": 0.7840423345877752,
+      "learning_rate": 9.537394102381719e-06,
+      "loss": 0.951,
+      "step": 470
+    },
+    {
+      "epoch": 0.22922636103151864,
+      "grad_norm": 0.8816713401350009,
+      "learning_rate": 9.501738997615471e-06,
+      "loss": 0.902,
+      "step": 480
+    },
+    {
+      "epoch": 0.23400191021967526,
+      "grad_norm": 0.7272663417426294,
+      "learning_rate": 9.464832169951171e-06,
+      "loss": 0.9121,
+      "step": 490
+    },
+    {
+      "epoch": 0.2387774594078319,
+      "grad_norm": 0.8166914666826738,
+      "learning_rate": 9.426683881450058e-06,
+      "loss": 0.9149,
+      "step": 500
+    },
+    {
+      "epoch": 0.24355300859598855,
+      "grad_norm": 0.806333386634663,
+      "learning_rate": 9.387304739365524e-06,
+      "loss": 0.9141,
+      "step": 510
+    },
+    {
+      "epoch": 0.24832855778414517,
+      "grad_norm": 0.8500670140915615,
+      "learning_rate": 9.346705693193722e-06,
+      "loss": 0.9046,
+      "step": 520
+    },
+    {
+      "epoch": 0.2531041069723018,
+      "grad_norm": 0.8536991575306397,
+      "learning_rate": 9.304898031629038e-06,
+      "loss": 0.907,
+      "step": 530
+    },
+    {
+      "epoch": 0.25787965616045844,
+      "grad_norm": 0.7805889795178423,
+      "learning_rate": 9.261893379425218e-06,
+      "loss": 0.9095,
+      "step": 540
+    },
+    {
+      "epoch": 0.2626552053486151,
+      "grad_norm": 0.983470886698574,
+      "learning_rate": 9.217703694163083e-06,
+      "loss": 0.8811,
+      "step": 550
+    },
+    {
+      "epoch": 0.26743075453677173,
+      "grad_norm": 0.8247344852185301,
+      "learning_rate": 9.172341262925675e-06,
+      "loss": 0.8743,
+      "step": 560
+    },
+    {
+      "epoch": 0.2722063037249284,
+      "grad_norm": 0.7947362543336306,
+      "learning_rate": 9.125818698881798e-06,
+      "loss": 0.8659,
+      "step": 570
+    },
+    {
+      "epoch": 0.276981852913085,
+      "grad_norm": 0.7251555329092241,
+      "learning_rate": 9.078148937778889e-06,
+      "loss": 0.906,
+      "step": 580
+    },
+    {
+      "epoch": 0.2817574021012416,
+      "grad_norm": 0.789421032185164,
+      "learning_rate": 9.029345234346183e-06,
+      "loss": 0.8859,
+      "step": 590
+    },
+    {
+      "epoch": 0.28653295128939826,
+      "grad_norm": 0.8701223156155673,
+      "learning_rate": 8.979421158609206e-06,
+      "loss": 0.8785,
+      "step": 600
+    },
+    {
+      "epoch": 0.28653295128939826,
+      "eval_loss": 0.8167237639427185,
+      "eval_runtime": 534.2082,
+      "eval_samples_per_second": 27.873,
+      "eval_steps_per_second": 3.486,
+      "step": 600
+    },
+    {
+      "epoch": 0.2913085004775549,
+      "grad_norm": 0.8629003851548017,
+      "learning_rate": 8.928390592116576e-06,
+      "loss": 0.8539,
+      "step": 610
+    },
+    {
+      "epoch": 0.29608404966571156,
+      "grad_norm": 0.8486389448069024,
+      "learning_rate": 8.876267724080197e-06,
+      "loss": 0.8527,
+      "step": 620
+    },
+    {
+      "epoch": 0.3008595988538682,
+      "grad_norm": 0.762838712746454,
+      "learning_rate": 8.823067047429908e-06,
+      "loss": 0.8683,
+      "step": 630
+    },
+    {
+      "epoch": 0.30563514804202485,
+      "grad_norm": 0.8625392396534273,
+      "learning_rate": 8.768803354783668e-06,
+      "loss": 0.8649,
+      "step": 640
+    },
+    {
+      "epoch": 0.3104106972301815,
+      "grad_norm": 0.8333540473972623,
+      "learning_rate": 8.71349173433443e-06,
+      "loss": 0.8622,
+      "step": 650
+    },
+    {
+      "epoch": 0.3151862464183381,
+      "grad_norm": 0.7664644528325345,
+      "learning_rate": 8.65714756565482e-06,
+      "loss": 0.8359,
+      "step": 660
+    },
+    {
+      "epoch": 0.31996179560649474,
+      "grad_norm": 0.8563484088758611,
+      "learning_rate": 8.599786515420789e-06,
+      "loss": 0.8569,
+      "step": 670
+    },
+    {
+      "epoch": 0.3247373447946514,
+      "grad_norm": 0.8053932610453219,
+      "learning_rate": 8.541424533055455e-06,
+      "loss": 0.8458,
+      "step": 680
+    },
+    {
+      "epoch": 0.32951289398280803,
+      "grad_norm": 0.8666024535787029,
+      "learning_rate": 8.48207784629431e-06,
+      "loss": 0.8447,
+      "step": 690
+    },
+    {
+      "epoch": 0.3342884431709647,
+      "grad_norm": 0.8868169973573014,
+      "learning_rate": 8.421762956673043e-06,
+      "loss": 0.8365,
+      "step": 700
+    },
+    {
+      "epoch": 0.3390639923591213,
+      "grad_norm": 0.8954608340327667,
+      "learning_rate": 8.360496634939243e-06,
+      "loss": 0.8335,
+      "step": 710
+    },
+    {
+      "epoch": 0.3438395415472779,
+      "grad_norm": 0.7784372366116787,
+      "learning_rate": 8.298295916389234e-06,
+      "loss": 0.8458,
+      "step": 720
+    },
+    {
+      "epoch": 0.34861509073543456,
+      "grad_norm": 0.8749905429657314,
+      "learning_rate": 8.235178096131355e-06,
+      "loss": 0.8185,
+      "step": 730
+    },
+    {
+      "epoch": 0.3533906399235912,
+      "grad_norm": 0.8021513738690056,
+      "learning_rate": 8.171160724277005e-06,
+      "loss": 0.8009,
+      "step": 740
+    },
+    {
+      "epoch": 0.35816618911174786,
+      "grad_norm": 0.8463663258199511,
+      "learning_rate": 8.106261601060773e-06,
+      "loss": 0.8277,
+      "step": 750
+    },
+    {
+      "epoch": 0.3629417382999045,
+      "grad_norm": 0.8443067155200391,
+      "learning_rate": 8.040498771891031e-06,
+      "loss": 0.8432,
+      "step": 760
+    },
+    {
+      "epoch": 0.36771728748806115,
+      "grad_norm": 0.8612360765810276,
+      "learning_rate": 7.973890522332348e-06,
+      "loss": 0.7933,
+      "step": 770
+    },
+    {
+      "epoch": 0.37249283667621774,
+      "grad_norm": 0.7566639910663036,
+      "learning_rate": 7.90645537302113e-06,
+      "loss": 0.8122,
+      "step": 780
+    },
+    {
+      "epoch": 0.3772683858643744,
+      "grad_norm": 0.8598522471784897,
+      "learning_rate": 7.838212074515899e-06,
+      "loss": 0.7713,
+      "step": 790
+    },
+    {
+      "epoch": 0.38204393505253104,
+      "grad_norm": 0.8264097384771215,
+      "learning_rate": 7.769179602083642e-06,
+      "loss": 0.7863,
+      "step": 800
+    },
+    {
+      "epoch": 0.38204393505253104,
+      "eval_loss": 0.7238086462020874,
+      "eval_runtime": 534.3413,
+      "eval_samples_per_second": 27.866,
+      "eval_steps_per_second": 3.485,
+      "step": 800
+    },
+    {
+      "epoch": 0.3868194842406877,
+      "grad_norm": 0.8302298544450823,
+      "learning_rate": 7.699377150423673e-06,
+      "loss": 0.7703,
+      "step": 810
+    },
+    {
+      "epoch": 0.39159503342884433,
+      "grad_norm": 0.9074490770748711,
+      "learning_rate": 7.628824128330485e-06,
+      "loss": 0.7651,
+      "step": 820
+    },
+    {
+      "epoch": 0.396370582617001,
+      "grad_norm": 0.9084786994105255,
+      "learning_rate": 7.557540153297086e-06,
+      "loss": 0.777,
+      "step": 830
+    },
+    {
+      "epoch": 0.40114613180515757,
+      "grad_norm": 0.7941270341446054,
+      "learning_rate": 7.485545046060272e-06,
+      "loss": 0.7659,
+      "step": 840
+    },
+    {
+      "epoch": 0.4059216809933142,
+      "grad_norm": 0.8418275807952966,
+      "learning_rate": 7.412858825089423e-06,
+      "loss": 0.7422,
+      "step": 850
+    },
+    {
+      "epoch": 0.41069723018147086,
+      "grad_norm": 0.8272295917894095,
+      "learning_rate": 7.3395017010202965e-06,
+      "loss": 0.7812,
+      "step": 860
+    },
+    {
+      "epoch": 0.4154727793696275,
+      "grad_norm": 0.8505418063106487,
+      "learning_rate": 7.265494071035401e-06,
+      "loss": 0.7461,
+      "step": 870
+    },
+    {
+      "epoch": 0.42024832855778416,
+      "grad_norm": 0.8254281894571944,
+      "learning_rate": 7.19085651319249e-06,
+      "loss": 0.7475,
+      "step": 880
+    },
+    {
+      "epoch": 0.4250238777459408,
+      "grad_norm": 0.7405023384966558,
+      "learning_rate": 7.115609780702767e-06,
+      "loss": 0.7485,
+      "step": 890
+    },
+    {
+      "epoch": 0.4297994269340974,
+      "grad_norm": 0.8069701422330396,
+      "learning_rate": 7.039774796160391e-06,
+      "loss": 0.7502,
+      "step": 900
+    },
+    {
+      "epoch": 0.43457497612225404,
+      "grad_norm": 0.7893053819873398,
+      "learning_rate": 6.9633726457248864e-06,
+      "loss": 0.7307,
+      "step": 910
+    },
+    {
+      "epoch": 0.4393505253104107,
+      "grad_norm": 0.8684426658728022,
+      "learning_rate": 6.886424573258057e-06,
+      "loss": 0.7407,
+      "step": 920
+    },
+    {
+      "epoch": 0.44412607449856734,
+      "grad_norm": 0.8806215484013901,
+      "learning_rate": 6.808951974417077e-06,
+      "loss": 0.7232,
+      "step": 930
+    },
+    {
+      "epoch": 0.448901623686724,
+      "grad_norm": 1.0078825768218607,
+      "learning_rate": 6.73097639070535e-06,
+      "loss": 0.7217,
+      "step": 940
+    },
+    {
+      "epoch": 0.45367717287488063,
+      "grad_norm": 0.820169166397048,
+      "learning_rate": 6.652519503482829e-06,
+      "loss": 0.7275,
+      "step": 950
+    },
+    {
+      "epoch": 0.4584527220630373,
+      "grad_norm": 0.9615211451349941,
+      "learning_rate": 6.573603127937443e-06,
+      "loss": 0.7244,
+      "step": 960
+    },
+    {
+      "epoch": 0.46322827125119387,
+      "grad_norm": 0.9105145919711279,
+      "learning_rate": 6.494249207019317e-06,
+      "loss": 0.7184,
+      "step": 970
+    },
+    {
+      "epoch": 0.4680038204393505,
+      "grad_norm": 0.8720579325571185,
+      "learning_rate": 6.414479805339465e-06,
+      "loss": 0.6887,
+      "step": 980
+    },
+    {
+      "epoch": 0.47277936962750716,
+      "grad_norm": 0.8869722170599964,
+      "learning_rate": 6.3343171030346525e-06,
+      "loss": 0.6858,
+      "step": 990
+    },
+    {
+      "epoch": 0.4775549188156638,
+      "grad_norm": 0.8820354385866871,
+      "learning_rate": 6.253783389600136e-06,
+      "loss": 0.7073,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4775549188156638,
+      "eval_loss": 0.6407110095024109,
+      "eval_runtime": 534.1565,
+      "eval_samples_per_second": 27.876,
+      "eval_steps_per_second": 3.486,
+      "step": 1000
+    },
+    {
+      "epoch": 0.48233046800382046,
+      "grad_norm": 0.9876137273298787,
+      "learning_rate": 6.172901057692007e-06,
+      "loss": 0.7207,
+      "step": 1010
+    },
+    {
+      "epoch": 0.4871060171919771,
+      "grad_norm": 0.8646444637817178,
+      "learning_rate": 6.0916925969008275e-06,
+      "loss": 0.7363,
+      "step": 1020
+    },
+    {
+      "epoch": 0.4918815663801337,
+      "grad_norm": 0.8847812706441835,
+      "learning_rate": 6.010180587498347e-06,
+      "loss": 0.6729,
+      "step": 1030
+    },
+    {
+      "epoch": 0.49665711556829034,
+      "grad_norm": 0.7915082131571504,
+      "learning_rate": 5.928387694158968e-06,
+      "loss": 0.6956,
+      "step": 1040
+    },
+    {
+      "epoch": 0.501432664756447,
+      "grad_norm": 1.046517690383018,
+      "learning_rate": 5.8463366596577706e-06,
+      "loss": 0.6896,
+      "step": 1050
+    },
+    {
+      "epoch": 0.5062082139446036,
+      "grad_norm": 0.8847177405317377,
+      "learning_rate": 5.764050298546808e-06,
+      "loss": 0.6861,
+      "step": 1060
+    },
+    {
+      "epoch": 0.5109837631327603,
+      "grad_norm": 0.8672793826369924,
+      "learning_rate": 5.68155149081145e-06,
+      "loss": 0.6762,
+      "step": 1070
+    },
+    {
+      "epoch": 0.5157593123209169,
+      "grad_norm": 0.9340453072759527,
+      "learning_rate": 5.598863175508526e-06,
+      "loss": 0.6717,
+      "step": 1080
+    },
+    {
+      "epoch": 0.5205348615090736,
+      "grad_norm": 0.8259949274241196,
+      "learning_rate": 5.516008344388053e-06,
+      "loss": 0.6825,
+      "step": 1090
+    },
+    {
+      "epoch": 0.5253104106972302,
+      "grad_norm": 0.9029867272763249,
+      "learning_rate": 5.433010035500299e-06,
+      "loss": 0.6771,
+      "step": 1100
+    },
+    {
+      "epoch": 0.5300859598853869,
+      "grad_norm": 0.800953127657272,
+      "learning_rate": 5.3498913267899864e-06,
+      "loss": 0.674,
+      "step": 1110
+    },
+    {
+      "epoch": 0.5348615090735435,
+      "grad_norm": 0.9245770325043161,
+      "learning_rate": 5.2666753296793895e-06,
+      "loss": 0.6662,
+      "step": 1120
+    },
+    {
+      "epoch": 0.5396370582617,
+      "grad_norm": 0.8502150053204679,
+      "learning_rate": 5.183385182642136e-06,
+      "loss": 0.6765,
+      "step": 1130
+    },
+    {
+      "epoch": 0.5444126074498568,
+      "grad_norm": 1.5468980444160696,
+      "learning_rate": 5.100044044769472e-06,
+      "loss": 0.6682,
+      "step": 1140
+    },
+    {
+      "epoch": 0.5491881566380133,
+      "grad_norm": 1.0568604331225828,
+      "learning_rate": 5.016675089330817e-06,
+      "loss": 0.6583,
+      "step": 1150
+    },
+    {
+      "epoch": 0.55396370582617,
+      "grad_norm": 0.9277335589404493,
+      "learning_rate": 4.933301497330344e-06,
+      "loss": 0.6456,
+      "step": 1160
+    },
+    {
+      "epoch": 0.5587392550143266,
+      "grad_norm": 0.9015066761493195,
+      "learning_rate": 4.849946451061444e-06,
+      "loss": 0.673,
+      "step": 1170
+    },
+    {
+      "epoch": 0.5635148042024832,
+      "grad_norm": 0.916248819386327,
+      "learning_rate": 4.766633127660805e-06,
+      "loss": 0.6372,
+      "step": 1180
+    },
+    {
+      "epoch": 0.5682903533906399,
+      "grad_norm": 0.9944122764504796,
+      "learning_rate": 4.683384692663937e-06,
+      "loss": 0.6352,
+      "step": 1190
+    },
+    {
+      "epoch": 0.5730659025787965,
+      "grad_norm": 0.8995871939871956,
+      "learning_rate": 4.600224293563926e-06,
+      "loss": 0.6143,
+      "step": 1200
+    },
+    {
+      "epoch": 0.5730659025787965,
+      "eval_loss": 0.5672308206558228,
+      "eval_runtime": 534.5729,
+      "eval_samples_per_second": 27.854,
+      "eval_steps_per_second": 3.483,
+      "step": 1200
+    },
+    {
+      "epoch": 0.5778414517669532,
+      "grad_norm": 0.9029828803944917,
+      "learning_rate": 4.517175053375191e-06,
+      "loss": 0.6482,
+      "step": 1210
+    },
+    {
+      "epoch": 0.5826170009551098,
+      "grad_norm": 0.9997552015425194,
+      "learning_rate": 4.434260064204067e-06,
+      "loss": 0.6244,
+      "step": 1220
+    },
+    {
+      "epoch": 0.5873925501432665,
+      "grad_norm": 0.8505066146958208,
+      "learning_rate": 4.351502380827959e-06,
+      "loss": 0.6231,
+      "step": 1230
+    },
+    {
+      "epoch": 0.5921680993314231,
+      "grad_norm": 0.9601951382006098,
+      "learning_rate": 4.268925014284898e-06,
+      "loss": 0.6515,
+      "step": 1240
+    },
+    {
+      "epoch": 0.5969436485195797,
+      "grad_norm": 0.858109652878112,
+      "learning_rate": 4.18655092547524e-06,
+      "loss": 0.6027,
+      "step": 1250
+    },
+    {
+      "epoch": 0.6017191977077364,
+      "grad_norm": 1.0279381548988882,
+      "learning_rate": 4.104403018777323e-06,
+      "loss": 0.636,
+      "step": 1260
+    },
+    {
+      "epoch": 0.606494746895893,
+      "grad_norm": 0.8684044204496176,
+      "learning_rate": 4.022504135678822e-06,
+      "loss": 0.6356,
+      "step": 1270
+    },
+    {
+      "epoch": 0.6112702960840497,
+      "grad_norm": 1.2002839065266542,
+      "learning_rate": 3.94087704842561e-06,
+      "loss": 0.6303,
+      "step": 1280
+    },
+    {
+      "epoch": 0.6160458452722063,
+      "grad_norm": 1.0212819754078601,
+      "learning_rate": 3.859544453689853e-06,
+      "loss": 0.6181,
+      "step": 1290
+    },
+    {
+      "epoch": 0.620821394460363,
+      "grad_norm": 1.1643909557826269,
+      "learning_rate": 3.778528966259137e-06,
+      "loss": 0.6075,
+      "step": 1300
+    },
+    {
+      "epoch": 0.6255969436485196,
+      "grad_norm": 0.8318901215082086,
+      "learning_rate": 3.697853112748345e-06,
+      "loss": 0.6106,
+      "step": 1310
+    },
+    {
+      "epoch": 0.6303724928366762,
+      "grad_norm": 0.9063102495466279,
+      "learning_rate": 3.6175393253360704e-06,
+      "loss": 0.599,
+      "step": 1320
+    },
+    {
+      "epoch": 0.6351480420248329,
+      "grad_norm": 0.9567097209608001,
+      "learning_rate": 3.537609935527264e-06,
+      "loss": 0.5996,
+      "step": 1330
+    },
+    {
+      "epoch": 0.6399235912129895,
+      "grad_norm": 0.939453389364599,
+      "learning_rate": 3.458087167943905e-06,
+      "loss": 0.5867,
+      "step": 1340
+    },
+    {
+      "epoch": 0.6446991404011462,
+      "grad_norm": 0.9944415765925527,
+      "learning_rate": 3.3789931341453564e-06,
+      "loss": 0.614,
+      "step": 1350
+    },
+    {
+      "epoch": 0.6494746895893028,
+      "grad_norm": 0.8911567397377756,
+      "learning_rate": 3.3003498264801915e-06,
+      "loss": 0.5858,
+      "step": 1360
+    },
+    {
+      "epoch": 0.6542502387774594,
+      "grad_norm": 0.9190740572643366,
+      "learning_rate": 3.2221791119711372e-06,
+      "loss": 0.6073,
+      "step": 1370
+    },
+    {
+      "epoch": 0.6590257879656161,
+      "grad_norm": 0.8722067899669511,
+      "learning_rate": 3.144502726234889e-06,
+      "loss": 0.598,
+      "step": 1380
+    },
+    {
+      "epoch": 0.6638013371537727,
+      "grad_norm": 0.8704883954915125,
+      "learning_rate": 3.067342267438446e-06,
+      "loss": 0.5864,
+      "step": 1390
+    },
+    {
+      "epoch": 0.6685768863419294,
+      "grad_norm": 0.9586746506286237,
+      "learning_rate": 2.9907191902936773e-06,
+      "loss": 0.5726,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6685768863419294,
+      "eval_loss": 0.5096372961997986,
+      "eval_runtime": 534.0593,
+      "eval_samples_per_second": 27.881,
+      "eval_steps_per_second": 3.487,
+      "step": 1400
+    },
+    {
+      "epoch": 0.673352435530086,
+      "grad_norm": 0.9771151805675299,
+      "learning_rate": 2.914654800091768e-06,
+      "loss": 0.5678,
+      "step": 1410
+    },
+    {
+      "epoch": 0.6781279847182426,
+      "grad_norm": 0.9844163415808749,
+      "learning_rate": 2.8391702467792137e-06,
+      "loss": 0.5875,
+      "step": 1420
+    },
+    {
+      "epoch": 0.6829035339063992,
+      "grad_norm": 0.936929121667794,
+      "learning_rate": 2.764286519077014e-06,
+      "loss": 0.5745,
+      "step": 1430
+    },
+    {
+      "epoch": 0.6876790830945558,
+      "grad_norm": 0.9581940513551886,
+      "learning_rate": 2.6900244386446903e-06,
+      "loss": 0.5748,
+      "step": 1440
+    },
+    {
+      "epoch": 0.6924546322827125,
+      "grad_norm": 0.9382097505155865,
+      "learning_rate": 2.616404654290752e-06,
+      "loss": 0.582,
+      "step": 1450
+    },
+    {
+      "epoch": 0.6972301814708691,
+      "grad_norm": 0.9458807920061071,
+      "learning_rate": 2.5434476362312375e-06,
+      "loss": 0.5859,
+      "step": 1460
+    },
+    {
+      "epoch": 0.7020057306590258,
+      "grad_norm": 0.8536247554325601,
+      "learning_rate": 2.4711736703979015e-06,
+      "loss": 0.5778,
+      "step": 1470
+    },
+    {
+      "epoch": 0.7067812798471824,
+      "grad_norm": 0.8896142850001317,
+      "learning_rate": 2.399602852797647e-06,
+      "loss": 0.5833,
+      "step": 1480
+    },
+    {
+      "epoch": 0.711556829035339,
+      "grad_norm": 0.9369088545555486,
+      "learning_rate": 2.3287550839247625e-06,
+      "loss": 0.5677,
+      "step": 1490
+    },
+    {
+      "epoch": 0.7163323782234957,
+      "grad_norm": 0.9352682466004876,
+      "learning_rate": 2.2586500632275333e-06,
+      "loss": 0.5501,
+      "step": 1500
+    },
+    {
+      "epoch": 0.7211079274116523,
+      "grad_norm": 0.9291292330708577,
+      "learning_rate": 2.1893072836307433e-06,
+      "loss": 0.5432,
+      "step": 1510
+    },
+    {
+      "epoch": 0.725883476599809,
+      "grad_norm": 1.1278542414631672,
+      "learning_rate": 2.1207460261156066e-06,
+      "loss": 0.6017,
+      "step": 1520
+    },
+    {
+      "epoch": 0.7306590257879656,
+      "grad_norm": 0.8496342199267922,
+      "learning_rate": 2.052985354358622e-06,
+      "loss": 0.5361,
+      "step": 1530
+    },
+    {
+      "epoch": 0.7354345749761223,
+      "grad_norm": 0.8448590719351696,
+      "learning_rate": 1.986044109430869e-06,
+      "loss": 0.544,
+      "step": 1540
+    },
+    {
+      "epoch": 0.7402101241642789,
+      "grad_norm": 1.0014560087074114,
+      "learning_rate": 1.91994090455918e-06,
+      "loss": 0.5544,
+      "step": 1550
+    },
+    {
+      "epoch": 0.7449856733524355,
+      "grad_norm": 0.9943362148840331,
+      "learning_rate": 1.8546941199506752e-06,
+      "loss": 0.5743,
+      "step": 1560
+    },
+    {
+      "epoch": 0.7497612225405922,
+      "grad_norm": 0.9488632116893986,
+      "learning_rate": 1.790321897682083e-06,
+      "loss": 0.5516,
+      "step": 1570
+    },
+    {
+      "epoch": 0.7545367717287488,
+      "grad_norm": 0.9282545781122443,
+      "learning_rate": 1.7268421366552851e-06,
+      "loss": 0.5598,
+      "step": 1580
+    },
+    {
+      "epoch": 0.7593123209169055,
+      "grad_norm": 0.893009147729329,
+      "learning_rate": 1.6642724876204658e-06,
+      "loss": 0.5457,
+      "step": 1590
+    },
+    {
+      "epoch": 0.7640878701050621,
+      "grad_norm": 0.8952401614954113,
+      "learning_rate": 1.602630348268267e-06,
+      "loss": 0.5623,
+      "step": 1600
+    },
+    {
+      "epoch": 0.7640878701050621,
+      "eval_loss": 0.46827441453933716,
+      "eval_runtime": 534.0896,
+      "eval_samples_per_second": 27.879,
+      "eval_steps_per_second": 3.486,
+      "step": 1600
+    },
+    {
+      "epoch": 0.7688634192932188,
+      "grad_norm": 0.9378147502660392,
+      "learning_rate": 1.541932858392296e-06,
+      "loss": 0.5522,
+      "step": 1610
+    },
+    {
+      "epoch": 0.7736389684813754,
+      "grad_norm": 0.8793552837932004,
+      "learning_rate": 1.482196895123364e-06,
+      "loss": 0.5321,
+      "step": 1620
+    },
+    {
+      "epoch": 0.778414517669532,
+      "grad_norm": 0.8650313644836122,
+      "learning_rate": 1.423439068236736e-06,
+      "loss": 0.5789,
+      "step": 1630
+    },
+    {
+      "epoch": 0.7831900668576887,
+      "grad_norm": 0.9837452596609937,
+      "learning_rate": 1.3656757155337413e-06,
+      "loss": 0.5628,
+      "step": 1640
+    },
+    {
+      "epoch": 0.7879656160458453,
+      "grad_norm": 1.0526446379669654,
+      "learning_rate": 1.3089228982989771e-06,
+      "loss": 0.5139,
+      "step": 1650
+    },
+    {
+      "epoch": 0.792741165234002,
+      "grad_norm": 0.9071660119485095,
+      "learning_rate": 1.2531963968344346e-06,
+      "loss": 0.5229,
+      "step": 1660
+    },
+    {
+      "epoch": 0.7975167144221585,
+      "grad_norm": 0.8509970739173898,
+      "learning_rate": 1.1985117060717278e-06,
+      "loss": 0.5184,
+      "step": 1670
+    },
+    {
+      "epoch": 0.8022922636103151,
+      "grad_norm": 0.8689645530199235,
+      "learning_rate": 1.1448840312636812e-06,
+      "loss": 0.5248,
+      "step": 1680
+    },
+    {
+      "epoch": 0.8070678127984718,
+      "grad_norm": 0.8888334350846111,
+      "learning_rate": 1.0923282837564537e-06,
+      "loss": 0.5451,
+      "step": 1690
+    },
+    {
+      "epoch": 0.8118433619866284,
+      "grad_norm": 1.0944895277253541,
+      "learning_rate": 1.0408590768434018e-06,
+      "loss": 0.522,
+      "step": 1700
+    },
+    {
+      "epoch": 0.8166189111747851,
+      "grad_norm": 1.0504131852344616,
+      "learning_rate": 9.904907217018e-07,
+      "loss": 0.5143,
+      "step": 1710
+    },
+    {
+      "epoch": 0.8213944603629417,
+      "grad_norm": 0.9813714332571194,
+      "learning_rate": 9.412372234135753e-07,
+      "loss": 0.5339,
+      "step": 1720
+    },
+    {
+      "epoch": 0.8261700095510984,
+      "grad_norm": 0.8392110216415885,
+      "learning_rate": 8.931122770711425e-07,
+      "loss": 0.5326,
+      "step": 1730
+    },
+    {
+      "epoch": 0.830945558739255,
+      "grad_norm": 0.883891691537776,
+      "learning_rate": 8.461292639694519e-07,
+      "loss": 0.5308,
+      "step": 1740
+    },
+    {
+      "epoch": 0.8357211079274116,
+      "grad_norm": 0.9330631339104432,
+      "learning_rate": 8.003012478852679e-07,
+      "loss": 0.4943,
+      "step": 1750
+    },
+    {
+      "epoch": 0.8404966571155683,
+      "grad_norm": 0.9077272187489582,
+      "learning_rate": 7.556409714447488e-07,
+      "loss": 0.5474,
+      "step": 1760
+    },
+    {
+      "epoch": 0.8452722063037249,
+      "grad_norm": 0.8412019707689536,
+      "learning_rate": 7.121608525803142e-07,
+      "loss": 0.5301,
+      "step": 1770
+    },
+    {
+      "epoch": 0.8500477554918816,
+      "grad_norm": 1.0343479774517594,
+      "learning_rate": 6.698729810778065e-07,
+      "loss": 0.5302,
+      "step": 1780
+    },
+    {
+      "epoch": 0.8548233046800382,
+      "grad_norm": 0.9838478459223126,
+      "learning_rate": 6.287891152148823e-07,
+      "loss": 0.5075,
+      "step": 1790
+    },
+    {
+      "epoch": 0.8595988538681948,
+      "grad_norm": 1.009194175526722,
+      "learning_rate": 5.889206784915863e-07,
+      "loss": 0.5206,
+      "step": 1800
+    },
+    {
+      "epoch": 0.8595988538681948,
+      "eval_loss": 0.44646286964416504,
+      "eval_runtime": 534.2652,
+      "eval_samples_per_second": 27.87,
+      "eval_steps_per_second": 3.485,
+      "step": 1800
+    },
+    {
+      "epoch": 0.8643744030563515,
+      "grad_norm": 0.8387985123574973,
+      "learning_rate": 5.502787564540102e-07,
+      "loss": 0.5305,
+      "step": 1810
+    },
+    {
+      "epoch": 0.8691499522445081,
+      "grad_norm": 0.9238833740564283,
+      "learning_rate": 5.128740936119242e-07,
+      "loss": 0.5115,
+      "step": 1820
+    },
+    {
+      "epoch": 0.8739255014326648,
+      "grad_norm": 0.8643626924619122,
+      "learning_rate": 4.7671709045122914e-07,
+      "loss": 0.501,
+      "step": 1830
+    },
+    {
+      "epoch": 0.8787010506208214,
+      "grad_norm": 0.8843512593283425,
+      "learning_rate": 4.4181780054206925e-07,
+      "loss": 0.5316,
+      "step": 1840
+    },
+    {
+      "epoch": 0.8834765998089781,
+      "grad_norm": 1.0280116743208123,
+      "learning_rate": 4.081859277434025e-07,
+      "loss": 0.5084,
+      "step": 1850
+    },
+    {
+      "epoch": 0.8882521489971347,
+      "grad_norm": 0.9217334180362886,
+      "learning_rate": 3.758308235048158e-07,
+      "loss": 0.4988,
+      "step": 1860
+    },
+    {
+      "epoch": 0.8930276981852913,
+      "grad_norm": 0.9278902432782374,
+      "learning_rate": 3.4476148426632215e-07,
+      "loss": 0.5248,
+      "step": 1870
+    },
+    {
+      "epoch": 0.897803247373448,
+      "grad_norm": 0.8498974666627348,
+      "learning_rate": 3.1498654895687095e-07,
+      "loss": 0.5263,
+      "step": 1880
+    },
+    {
+      "epoch": 0.9025787965616046,
+      "grad_norm": 0.914856710615246,
+      "learning_rate": 2.8651429659226906e-07,
+      "loss": 0.5129,
+      "step": 1890
+    },
+    {
+      "epoch": 0.9073543457497613,
+      "grad_norm": 0.9485264410476115,
+      "learning_rate": 2.593526439731697e-07,
+      "loss": 0.5033,
+      "step": 1900
+    },
+    {
+      "epoch": 0.9121298949379179,
+      "grad_norm": 0.922810539225268,
+      "learning_rate": 2.3350914348378606e-07,
+      "loss": 0.5157,
+      "step": 1910
+    },
+    {
+      "epoch": 0.9169054441260746,
+      "grad_norm": 0.956199326320254,
+      "learning_rate": 2.0899098099192273e-07,
+      "loss": 0.5158,
+      "step": 1920
+    },
+    {
+      "epoch": 0.9216809933142311,
+      "grad_norm": 0.8741702574957524,
+      "learning_rate": 1.8580497385092376e-07,
+      "loss": 0.5145,
+      "step": 1930
+    },
+    {
+      "epoch": 0.9264565425023877,
+      "grad_norm": 0.9941012086649309,
+      "learning_rate": 1.6395756900408454e-07,
+      "loss": 0.5321,
+      "step": 1940
+    },
+    {
+      "epoch": 0.9312320916905444,
+      "grad_norm": 0.8582163500365767,
+      "learning_rate": 1.4345484119206222e-07,
+      "loss": 0.5065,
+      "step": 1950
+    },
+    {
+      "epoch": 0.936007640878701,
+      "grad_norm": 0.9879634600102223,
+      "learning_rate": 1.2430249126376913e-07,
+      "loss": 0.54,
+      "step": 1960
+    },
+    {
+      "epoch": 0.9407831900668577,
+      "grad_norm": 0.9616760638465843,
+      "learning_rate": 1.065058445912398e-07,
+      "loss": 0.5084,
+      "step": 1970
+    },
+    {
+      "epoch": 0.9455587392550143,
+      "grad_norm": 1.0543325130204897,
+      "learning_rate": 9.006984958888742e-08,
+      "loss": 0.527,
+      "step": 1980
+    },
+    {
+      "epoch": 0.9503342884431709,
+      "grad_norm": 0.8916780720938148,
+      "learning_rate": 7.499907633758797e-08,
+      "loss": 0.4929,
+      "step": 1990
+    },
+    {
+      "epoch": 0.9551098376313276,
+      "grad_norm": 0.8743144782771384,
+      "learning_rate": 6.129771531395045e-08,
+      "loss": 0.5054,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9551098376313276,
+      "eval_loss": 0.43961772322654724,
+      "eval_runtime": 534.3343,
+      "eval_samples_per_second": 27.866,
+      "eval_steps_per_second": 3.485,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9598853868194842,
+      "grad_norm": 0.9030091469256598,
+      "learning_rate": 4.896957622514298e-08,
+      "loss": 0.4983,
+      "step": 2010
+    },
+    {
+      "epoch": 0.9646609360076409,
+      "grad_norm": 0.9300966338414236,
+      "learning_rate": 3.801808694959053e-08,
+      "loss": 0.5219,
+      "step": 2020
+    },
+    {
+      "epoch": 0.9694364851957975,
+      "grad_norm": 0.9956560344691349,
+      "learning_rate": 2.8446292583844126e-08,
+      "loss": 0.5397,
+      "step": 2030
+    },
+    {
+      "epoch": 0.9742120343839542,
+      "grad_norm": 0.944281751372382,
+      "learning_rate": 2.025685459588145e-08,
+      "loss": 0.525,
+      "step": 2040
+    },
+    {
+      "epoch": 0.9789875835721108,
+      "grad_norm": 0.8939170547532904,
+      "learning_rate": 1.3452050085075441e-08,
+      "loss": 0.5086,
+      "step": 2050
+    },
+    {
+      "epoch": 0.9837631327602674,
+      "grad_norm": 0.8895914526936296,
+      "learning_rate": 8.033771149041913e-09,
+      "loss": 0.5122,
+      "step": 2060
+    },
+    {
+      "epoch": 0.9885386819484241,
+      "grad_norm": 0.8484510879585117,
+      "learning_rate": 4.003524357534261e-09,
+      "loss": 0.5168,
+      "step": 2070
+    },
+    {
+      "epoch": 0.9933142311365807,
+      "grad_norm": 0.9676882963530836,
+      "learning_rate": 1.3624303335380006e-09,
+      "loss": 0.5155,
+      "step": 2080
+    },
+    {
+      "epoch": 0.9980897803247374,
+      "grad_norm": 0.8272201128188289,
+      "learning_rate": 1.1122344167613374e-10,
+      "loss": 0.5051,
+      "step": 2090
+    },
+    {
+      "epoch": 1.0,
+      "step": 2094,
+      "total_flos": 985274787299328.0,
+      "train_loss": 0.7358792713970487,
+      "train_runtime": 28849.9475,
+      "train_samples_per_second": 4.645,
+      "train_steps_per_second": 0.073
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2094,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 985274787299328.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad93b5c94e2609eb9bf91665fab08b3b0f0685612e426e17e0895898cf6681e0
+size 7480