Upload model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: b1_math_top_16_1k
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# b1_math_top_16_1k
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/b1_math_top_16_1k dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 24
+- total_train_batch_size: 96
+- total_eval_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 7.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.6.0a0+ecf3bae40a.nv25.01
+- Datasets 3.5.0
+- Tokenizers 0.20.3

added_tokens.json

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

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.72,
+    "total_flos": 8.502394284199117e+16,
+    "train_loss": 0.39509621262550354,
+    "train_runtime": 3677.0494,
+    "train_samples_per_second": 1.904,
+    "train_steps_per_second": 0.019
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/p/data1/mmlaion/dcft/hub/models--Qwen--Qwen2.5-7B-Instruct/snapshots/a09a35458c702b33eeacc393d103063234e8bc28",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef67810232e85c626add5170b71381ef8d1bb5c67e0aa13066d8ef6a43cb36ae
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3175e3c8b27b3bf1de37f4a705b6f1397cabd1096e7f1c368ef6035884893524
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e4304d6dc5f094c1435de755cce0dafa45750cec538d74e7c8c5344036f2e80
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a75eb5d84505bbc2932d6a8d6ad2602719b3e6537c61a35c261a53513b24055
+size 1089994880

model.safetensors.index.json

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

runs/Apr19_06-56-28_jpbot-001-31.jupiter.internal/events.out.tfevents.1745038607.jpbot-001-31.jupiter.internal.3177905.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5afd6e9ad70decb3a4bf331ea6100aa2d274df1cf9ff18e46e9bf60e801a4a62
+size 20357

special_tokens_map.json

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

start_end.json

@@ -0,0 +1 @@
+{"start_time": "2025-04-19 06:56:28", "end_time": "2025-04-19 07:58:11"}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.72,
+    "total_flos": 8.502394284199117e+16,
+    "train_loss": 0.39509621262550354,
+    "train_runtime": 3677.0494,
+    "train_samples_per_second": 1.904,
+    "train_steps_per_second": 0.019
+}

trainer_log.jsonl

@@ -0,0 +1,71 @@
+{"current_steps": 1, "total_steps": 70, "loss": 0.8223, "lr": 2.8571428571428573e-06, "epoch": 0.096, "percentage": 1.43, "elapsed_time": "0:01:05", "remaining_time": "1:15:18"}
+{"current_steps": 2, "total_steps": 70, "loss": 0.9064, "lr": 5.7142857142857145e-06, "epoch": 0.192, "percentage": 2.86, "elapsed_time": "0:02:03", "remaining_time": "1:09:54"}
+{"current_steps": 3, "total_steps": 70, "loss": 0.8361, "lr": 8.571428571428571e-06, "epoch": 0.288, "percentage": 4.29, "elapsed_time": "0:02:55", "remaining_time": "1:05:25"}
+{"current_steps": 4, "total_steps": 70, "loss": 0.7737, "lr": 1.1428571428571429e-05, "epoch": 0.384, "percentage": 5.71, "elapsed_time": "0:03:39", "remaining_time": "1:00:27"}
+{"current_steps": 5, "total_steps": 70, "loss": 0.7292, "lr": 1.4285714285714287e-05, "epoch": 0.48, "percentage": 7.14, "elapsed_time": "0:04:25", "remaining_time": "0:57:36"}
+{"current_steps": 6, "total_steps": 70, "loss": 0.7259, "lr": 1.7142857142857142e-05, "epoch": 0.576, "percentage": 8.57, "elapsed_time": "0:05:23", "remaining_time": "0:57:28"}
+{"current_steps": 7, "total_steps": 70, "loss": 0.7306, "lr": 2e-05, "epoch": 0.672, "percentage": 10.0, "elapsed_time": "0:06:16", "remaining_time": "0:56:24"}
+{"current_steps": 8, "total_steps": 70, "loss": 0.6249, "lr": 1.9987569212189224e-05, "epoch": 0.768, "percentage": 11.43, "elapsed_time": "0:06:52", "remaining_time": "0:53:13"}
+{"current_steps": 9, "total_steps": 70, "loss": 0.6402, "lr": 1.9950307753654016e-05, "epoch": 0.864, "percentage": 12.86, "elapsed_time": "0:07:33", "remaining_time": "0:51:14"}
+{"current_steps": 10, "total_steps": 70, "loss": 0.637, "lr": 1.9888308262251286e-05, "epoch": 0.96, "percentage": 14.29, "elapsed_time": "0:08:25", "remaining_time": "0:50:34"}
+{"current_steps": 11, "total_steps": 70, "loss": 0.9078, "lr": 1.9801724878485438e-05, "epoch": 1.056, "percentage": 15.71, "elapsed_time": "0:09:50", "remaining_time": "0:52:49"}
+{"current_steps": 12, "total_steps": 70, "loss": 0.5496, "lr": 1.969077286229078e-05, "epoch": 1.152, "percentage": 17.14, "elapsed_time": "0:10:40", "remaining_time": "0:51:34"}
+{"current_steps": 13, "total_steps": 70, "loss": 0.5214, "lr": 1.955572805786141e-05, "epoch": 1.248, "percentage": 18.57, "elapsed_time": "0:11:27", "remaining_time": "0:50:15"}
+{"current_steps": 14, "total_steps": 70, "loss": 0.6063, "lr": 1.9396926207859085e-05, "epoch": 1.3439999999999999, "percentage": 20.0, "elapsed_time": "0:12:10", "remaining_time": "0:48:43"}
+{"current_steps": 15, "total_steps": 70, "loss": 0.5045, "lr": 1.921476211870408e-05, "epoch": 1.44, "percentage": 21.43, "elapsed_time": "0:12:54", "remaining_time": "0:47:20"}
+{"current_steps": 16, "total_steps": 70, "loss": 0.5812, "lr": 1.900968867902419e-05, "epoch": 1.536, "percentage": 22.86, "elapsed_time": "0:13:43", "remaining_time": "0:46:19"}
+{"current_steps": 17, "total_steps": 70, "loss": 0.51, "lr": 1.8782215733702286e-05, "epoch": 1.6320000000000001, "percentage": 24.29, "elapsed_time": "0:14:27", "remaining_time": "0:45:05"}
+{"current_steps": 18, "total_steps": 70, "loss": 0.5524, "lr": 1.8532908816321557e-05, "epoch": 1.728, "percentage": 25.71, "elapsed_time": "0:15:18", "remaining_time": "0:44:12"}
+{"current_steps": 19, "total_steps": 70, "loss": 0.5609, "lr": 1.826238774315995e-05, "epoch": 1.8239999999999998, "percentage": 27.14, "elapsed_time": "0:16:11", "remaining_time": "0:43:27"}
+{"current_steps": 20, "total_steps": 70, "loss": 0.5104, "lr": 1.7971325072229227e-05, "epoch": 1.92, "percentage": 28.57, "elapsed_time": "0:17:03", "remaining_time": "0:42:39"}
+{"current_steps": 21, "total_steps": 70, "loss": 0.7431, "lr": 1.766044443118978e-05, "epoch": 2.016, "percentage": 30.0, "elapsed_time": "0:18:16", "remaining_time": "0:42:39"}
+{"current_steps": 22, "total_steps": 70, "loss": 0.4681, "lr": 1.7330518718298263e-05, "epoch": 2.112, "percentage": 31.43, "elapsed_time": "0:18:54", "remaining_time": "0:41:14"}
+{"current_steps": 23, "total_steps": 70, "loss": 0.4039, "lr": 1.698236818086073e-05, "epoch": 2.208, "percentage": 32.86, "elapsed_time": "0:19:28", "remaining_time": "0:39:47"}
+{"current_steps": 24, "total_steps": 70, "loss": 0.4515, "lr": 1.6616858375968596e-05, "epoch": 2.304, "percentage": 34.29, "elapsed_time": "0:20:22", "remaining_time": "0:39:02"}
+{"current_steps": 25, "total_steps": 70, "loss": 0.4472, "lr": 1.6234898018587336e-05, "epoch": 2.4, "percentage": 35.71, "elapsed_time": "0:21:13", "remaining_time": "0:38:12"}
+{"current_steps": 26, "total_steps": 70, "loss": 0.3706, "lr": 1.5837436722347902e-05, "epoch": 2.496, "percentage": 37.14, "elapsed_time": "0:21:58", "remaining_time": "0:37:11"}
+{"current_steps": 27, "total_steps": 70, "loss": 0.4153, "lr": 1.5425462638657597e-05, "epoch": 2.592, "percentage": 38.57, "elapsed_time": "0:22:44", "remaining_time": "0:36:12"}
+{"current_steps": 28, "total_steps": 70, "loss": 0.3905, "lr": 1.5000000000000002e-05, "epoch": 2.6879999999999997, "percentage": 40.0, "elapsed_time": "0:23:31", "remaining_time": "0:35:17"}
+{"current_steps": 29, "total_steps": 70, "loss": 0.4035, "lr": 1.4562106573531632e-05, "epoch": 2.784, "percentage": 41.43, "elapsed_time": "0:24:21", "remaining_time": "0:34:26"}
+{"current_steps": 30, "total_steps": 70, "loss": 0.3833, "lr": 1.4112871031306118e-05, "epoch": 2.88, "percentage": 42.86, "elapsed_time": "0:25:17", "remaining_time": "0:33:43"}
+{"current_steps": 31, "total_steps": 70, "loss": 0.5817, "lr": 1.3653410243663953e-05, "epoch": 2.976, "percentage": 44.29, "elapsed_time": "0:26:21", "remaining_time": "0:33:09"}
+{"current_steps": 32, "total_steps": 70, "loss": 0.4479, "lr": 1.3184866502516846e-05, "epoch": 3.072, "percentage": 45.71, "elapsed_time": "0:27:52", "remaining_time": "0:33:06"}
+{"current_steps": 33, "total_steps": 70, "loss": 0.2776, "lr": 1.2708404681430054e-05, "epoch": 3.168, "percentage": 47.14, "elapsed_time": "0:28:28", "remaining_time": "0:31:55"}
+{"current_steps": 34, "total_steps": 70, "loss": 0.3218, "lr": 1.2225209339563144e-05, "epoch": 3.2640000000000002, "percentage": 48.57, "elapsed_time": "0:29:11", "remaining_time": "0:30:54"}
+{"current_steps": 35, "total_steps": 70, "loss": 0.3469, "lr": 1.1736481776669307e-05, "epoch": 3.36, "percentage": 50.0, "elapsed_time": "0:30:07", "remaining_time": "0:30:07"}
+{"current_steps": 36, "total_steps": 70, "loss": 0.3056, "lr": 1.1243437046474854e-05, "epoch": 3.456, "percentage": 51.43, "elapsed_time": "0:30:52", "remaining_time": "0:29:09"}
+{"current_steps": 37, "total_steps": 70, "loss": 0.318, "lr": 1.0747300935864245e-05, "epoch": 3.552, "percentage": 52.86, "elapsed_time": "0:31:42", "remaining_time": "0:28:17"}
+{"current_steps": 38, "total_steps": 70, "loss": 0.3006, "lr": 1.0249306917380731e-05, "epoch": 3.648, "percentage": 54.29, "elapsed_time": "0:32:25", "remaining_time": "0:27:18"}
+{"current_steps": 39, "total_steps": 70, "loss": 0.2904, "lr": 9.750693082619274e-06, "epoch": 3.7439999999999998, "percentage": 55.71, "elapsed_time": "0:33:12", "remaining_time": "0:26:24"}
+{"current_steps": 40, "total_steps": 70, "loss": 0.2758, "lr": 9.252699064135759e-06, "epoch": 3.84, "percentage": 57.14, "elapsed_time": "0:34:00", "remaining_time": "0:25:30"}
+{"current_steps": 41, "total_steps": 70, "loss": 0.3024, "lr": 8.756562953525151e-06, "epoch": 3.936, "percentage": 58.57, "elapsed_time": "0:34:57", "remaining_time": "0:24:43"}
+{"current_steps": 42, "total_steps": 70, "loss": 0.4741, "lr": 8.263518223330698e-06, "epoch": 4.032, "percentage": 60.0, "elapsed_time": "0:36:28", "remaining_time": "0:24:18"}
+{"current_steps": 43, "total_steps": 70, "loss": 0.2283, "lr": 7.774790660436857e-06, "epoch": 4.128, "percentage": 61.43, "elapsed_time": "0:37:09", "remaining_time": "0:23:19"}
+{"current_steps": 44, "total_steps": 70, "loss": 0.2591, "lr": 7.291595318569951e-06, "epoch": 4.224, "percentage": 62.86, "elapsed_time": "0:38:05", "remaining_time": "0:22:30"}
+{"current_steps": 45, "total_steps": 70, "loss": 0.2228, "lr": 6.815133497483157e-06, "epoch": 4.32, "percentage": 64.29, "elapsed_time": "0:38:40", "remaining_time": "0:21:29"}
+{"current_steps": 46, "total_steps": 70, "loss": 0.2378, "lr": 6.34658975633605e-06, "epoch": 4.416, "percentage": 65.71, "elapsed_time": "0:39:34", "remaining_time": "0:20:38"}
+{"current_steps": 47, "total_steps": 70, "loss": 0.2421, "lr": 5.887128968693887e-06, "epoch": 4.5120000000000005, "percentage": 67.14, "elapsed_time": "0:40:30", "remaining_time": "0:19:49"}
+{"current_steps": 48, "total_steps": 70, "loss": 0.1956, "lr": 5.43789342646837e-06, "epoch": 4.608, "percentage": 68.57, "elapsed_time": "0:41:19", "remaining_time": "0:18:56"}
+{"current_steps": 49, "total_steps": 70, "loss": 0.2117, "lr": 5.000000000000003e-06, "epoch": 4.704, "percentage": 70.0, "elapsed_time": "0:42:11", "remaining_time": "0:18:04"}
+{"current_steps": 50, "total_steps": 70, "loss": 0.2107, "lr": 4.5745373613424075e-06, "epoch": 4.8, "percentage": 71.43, "elapsed_time": "0:42:57", "remaining_time": "0:17:10"}
+{"current_steps": 51, "total_steps": 70, "loss": 0.2235, "lr": 4.162563277652104e-06, "epoch": 4.896, "percentage": 72.86, "elapsed_time": "0:43:43", "remaining_time": "0:16:17"}
+{"current_steps": 52, "total_steps": 70, "loss": 0.3392, "lr": 3.7651019814126656e-06, "epoch": 4.992, "percentage": 74.29, "elapsed_time": "0:44:42", "remaining_time": "0:15:28"}
+{"current_steps": 53, "total_steps": 70, "loss": 0.2085, "lr": 3.3831416240314085e-06, "epoch": 5.088, "percentage": 75.71, "elapsed_time": "0:46:08", "remaining_time": "0:14:47"}
+{"current_steps": 54, "total_steps": 70, "loss": 0.1647, "lr": 3.017631819139273e-06, "epoch": 5.184, "percentage": 77.14, "elapsed_time": "0:46:45", "remaining_time": "0:13:51"}
+{"current_steps": 55, "total_steps": 70, "loss": 0.2038, "lr": 2.669481281701739e-06, "epoch": 5.28, "percentage": 78.57, "elapsed_time": "0:47:40", "remaining_time": "0:13:00"}
+{"current_steps": 56, "total_steps": 70, "loss": 0.1924, "lr": 2.339555568810221e-06, "epoch": 5.376, "percentage": 80.0, "elapsed_time": "0:48:24", "remaining_time": "0:12:06"}
+{"current_steps": 57, "total_steps": 70, "loss": 0.1747, "lr": 2.0286749277707783e-06, "epoch": 5.4719999999999995, "percentage": 81.43, "elapsed_time": "0:49:13", "remaining_time": "0:11:13"}
+{"current_steps": 58, "total_steps": 70, "loss": 0.1816, "lr": 1.7376122568400533e-06, "epoch": 5.568, "percentage": 82.86, "elapsed_time": "0:50:06", "remaining_time": "0:10:22"}
+{"current_steps": 59, "total_steps": 70, "loss": 0.1988, "lr": 1.467091183678444e-06, "epoch": 5.664, "percentage": 84.29, "elapsed_time": "0:51:02", "remaining_time": "0:09:31"}
+{"current_steps": 60, "total_steps": 70, "loss": 0.1782, "lr": 1.2177842662977136e-06, "epoch": 5.76, "percentage": 85.71, "elapsed_time": "0:51:51", "remaining_time": "0:08:38"}
+{"current_steps": 61, "total_steps": 70, "loss": 0.1954, "lr": 9.903113209758098e-07, "epoch": 5.856, "percentage": 87.14, "elapsed_time": "0:52:33", "remaining_time": "0:07:45"}
+{"current_steps": 62, "total_steps": 70, "loss": 0.1875, "lr": 7.852378812959227e-07, "epoch": 5.952, "percentage": 88.57, "elapsed_time": "0:53:19", "remaining_time": "0:06:52"}
+{"current_steps": 63, "total_steps": 70, "loss": 0.2588, "lr": 6.030737921409169e-07, "epoch": 6.048, "percentage": 90.0, "elapsed_time": "0:54:36", "remaining_time": "0:06:04"}
+{"current_steps": 64, "total_steps": 70, "loss": 0.2096, "lr": 4.4427194213859216e-07, "epoch": 6.144, "percentage": 91.43, "elapsed_time": "0:55:23", "remaining_time": "0:05:11"}
+{"current_steps": 65, "total_steps": 70, "loss": 0.1612, "lr": 3.0922713770922155e-07, "epoch": 6.24, "percentage": 92.86, "elapsed_time": "0:56:14", "remaining_time": "0:04:19"}
+{"current_steps": 66, "total_steps": 70, "loss": 0.1427, "lr": 1.9827512151456175e-07, "epoch": 6.336, "percentage": 94.29, "elapsed_time": "0:56:52", "remaining_time": "0:03:26"}
+{"current_steps": 67, "total_steps": 70, "loss": 0.1454, "lr": 1.1169173774871478e-07, "epoch": 6.432, "percentage": 95.71, "elapsed_time": "0:57:27", "remaining_time": "0:02:34"}
+{"current_steps": 68, "total_steps": 70, "loss": 0.1759, "lr": 4.9692246345985905e-08, "epoch": 6.5280000000000005, "percentage": 97.14, "elapsed_time": "0:58:16", "remaining_time": "0:01:42"}
+{"current_steps": 69, "total_steps": 70, "loss": 0.1636, "lr": 1.2430787810776556e-08, "epoch": 6.624, "percentage": 98.57, "elapsed_time": "0:59:03", "remaining_time": "0:00:51"}
+{"current_steps": 70, "total_steps": 70, "loss": 0.1921, "lr": 0.0, "epoch": 6.72, "percentage": 100.0, "elapsed_time": "1:00:09", "remaining_time": "0:00:00"}
+{"current_steps": 70, "total_steps": 70, "epoch": 6.72, "percentage": 100.0, "elapsed_time": "1:01:15", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,532 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.72,
+  "eval_steps": 500,
+  "global_step": 70,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.096,
+      "grad_norm": 5.875209823488684,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 0.8223,
+      "step": 1
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 6.401085652087478,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 0.9064,
+      "step": 2
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 5.423130353195221,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.8361,
+      "step": 3
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 2.7444206455643907,
+      "learning_rate": 1.1428571428571429e-05,
+      "loss": 0.7737,
+      "step": 4
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 3.6540525709001344,
+      "learning_rate": 1.4285714285714287e-05,
+      "loss": 0.7292,
+      "step": 5
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 4.127246350432441,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 0.7259,
+      "step": 6
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 4.8994627919049725,
+      "learning_rate": 2e-05,
+      "loss": 0.7306,
+      "step": 7
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 3.1739625335448234,
+      "learning_rate": 1.9987569212189224e-05,
+      "loss": 0.6249,
+      "step": 8
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 2.813165793768344,
+      "learning_rate": 1.9950307753654016e-05,
+      "loss": 0.6402,
+      "step": 9
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.415982183277189,
+      "learning_rate": 1.9888308262251286e-05,
+      "loss": 0.637,
+      "step": 10
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 2.277593774459836,
+      "learning_rate": 1.9801724878485438e-05,
+      "loss": 0.9078,
+      "step": 11
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 1.250132023778524,
+      "learning_rate": 1.969077286229078e-05,
+      "loss": 0.5496,
+      "step": 12
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 1.659657924292621,
+      "learning_rate": 1.955572805786141e-05,
+      "loss": 0.5214,
+      "step": 13
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 1.0338366374799572,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.6063,
+      "step": 14
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 1.0817016248202054,
+      "learning_rate": 1.921476211870408e-05,
+      "loss": 0.5045,
+      "step": 15
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 1.2037539192984923,
+      "learning_rate": 1.900968867902419e-05,
+      "loss": 0.5812,
+      "step": 16
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "grad_norm": 0.6638269351287072,
+      "learning_rate": 1.8782215733702286e-05,
+      "loss": 0.51,
+      "step": 17
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 1.0215282984109142,
+      "learning_rate": 1.8532908816321557e-05,
+      "loss": 0.5524,
+      "step": 18
+    },
+    {
+      "epoch": 1.8239999999999998,
+      "grad_norm": 0.8009304822932776,
+      "learning_rate": 1.826238774315995e-05,
+      "loss": 0.5609,
+      "step": 19
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.8075577065441922,
+      "learning_rate": 1.7971325072229227e-05,
+      "loss": 0.5104,
+      "step": 20
+    },
+    {
+      "epoch": 2.016,
+      "grad_norm": 1.1649996157849678,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.7431,
+      "step": 21
+    },
+    {
+      "epoch": 2.112,
+      "grad_norm": 0.8001784634931127,
+      "learning_rate": 1.7330518718298263e-05,
+      "loss": 0.4681,
+      "step": 22
+    },
+    {
+      "epoch": 2.208,
+      "grad_norm": 0.7146005121655944,
+      "learning_rate": 1.698236818086073e-05,
+      "loss": 0.4039,
+      "step": 23
+    },
+    {
+      "epoch": 2.304,
+      "grad_norm": 0.6912699623960966,
+      "learning_rate": 1.6616858375968596e-05,
+      "loss": 0.4515,
+      "step": 24
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.625769587185304,
+      "learning_rate": 1.6234898018587336e-05,
+      "loss": 0.4472,
+      "step": 25
+    },
+    {
+      "epoch": 2.496,
+      "grad_norm": 0.7329624058829434,
+      "learning_rate": 1.5837436722347902e-05,
+      "loss": 0.3706,
+      "step": 26
+    },
+    {
+      "epoch": 2.592,
+      "grad_norm": 0.8425030696427563,
+      "learning_rate": 1.5425462638657597e-05,
+      "loss": 0.4153,
+      "step": 27
+    },
+    {
+      "epoch": 2.6879999999999997,
+      "grad_norm": 0.5305621860425499,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.3905,
+      "step": 28
+    },
+    {
+      "epoch": 2.784,
+      "grad_norm": 0.6422160704559803,
+      "learning_rate": 1.4562106573531632e-05,
+      "loss": 0.4035,
+      "step": 29
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.5705621161502886,
+      "learning_rate": 1.4112871031306118e-05,
+      "loss": 0.3833,
+      "step": 30
+    },
+    {
+      "epoch": 2.976,
+      "grad_norm": 0.762730804564728,
+      "learning_rate": 1.3653410243663953e-05,
+      "loss": 0.5817,
+      "step": 31
+    },
+    {
+      "epoch": 3.072,
+      "grad_norm": 0.6417481550190923,
+      "learning_rate": 1.3184866502516846e-05,
+      "loss": 0.4479,
+      "step": 32
+    },
+    {
+      "epoch": 3.168,
+      "grad_norm": 0.4718585775498429,
+      "learning_rate": 1.2708404681430054e-05,
+      "loss": 0.2776,
+      "step": 33
+    },
+    {
+      "epoch": 3.2640000000000002,
+      "grad_norm": 0.5498335812511644,
+      "learning_rate": 1.2225209339563144e-05,
+      "loss": 0.3218,
+      "step": 34
+    },
+    {
+      "epoch": 3.36,
+      "grad_norm": 0.6043846675662422,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.3469,
+      "step": 35
+    },
+    {
+      "epoch": 3.456,
+      "grad_norm": 0.5712271932059264,
+      "learning_rate": 1.1243437046474854e-05,
+      "loss": 0.3056,
+      "step": 36
+    },
+    {
+      "epoch": 3.552,
+      "grad_norm": 0.5810983302999997,
+      "learning_rate": 1.0747300935864245e-05,
+      "loss": 0.318,
+      "step": 37
+    },
+    {
+      "epoch": 3.648,
+      "grad_norm": 0.5669367492815897,
+      "learning_rate": 1.0249306917380731e-05,
+      "loss": 0.3006,
+      "step": 38
+    },
+    {
+      "epoch": 3.7439999999999998,
+      "grad_norm": 0.510166452470905,
+      "learning_rate": 9.750693082619274e-06,
+      "loss": 0.2904,
+      "step": 39
+    },
+    {
+      "epoch": 3.84,
+      "grad_norm": 0.5342556234908464,
+      "learning_rate": 9.252699064135759e-06,
+      "loss": 0.2758,
+      "step": 40
+    },
+    {
+      "epoch": 3.936,
+      "grad_norm": 0.5309160061404321,
+      "learning_rate": 8.756562953525151e-06,
+      "loss": 0.3024,
+      "step": 41
+    },
+    {
+      "epoch": 4.032,
+      "grad_norm": 0.8453612193977333,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.4741,
+      "step": 42
+    },
+    {
+      "epoch": 4.128,
+      "grad_norm": 0.48774892477134996,
+      "learning_rate": 7.774790660436857e-06,
+      "loss": 0.2283,
+      "step": 43
+    },
+    {
+      "epoch": 4.224,
+      "grad_norm": 0.5322269437377908,
+      "learning_rate": 7.291595318569951e-06,
+      "loss": 0.2591,
+      "step": 44
+    },
+    {
+      "epoch": 4.32,
+      "grad_norm": 0.48189601016551853,
+      "learning_rate": 6.815133497483157e-06,
+      "loss": 0.2228,
+      "step": 45
+    },
+    {
+      "epoch": 4.416,
+      "grad_norm": 0.5264106862201609,
+      "learning_rate": 6.34658975633605e-06,
+      "loss": 0.2378,
+      "step": 46
+    },
+    {
+      "epoch": 4.5120000000000005,
+      "grad_norm": 0.6467128793843824,
+      "learning_rate": 5.887128968693887e-06,
+      "loss": 0.2421,
+      "step": 47
+    },
+    {
+      "epoch": 4.608,
+      "grad_norm": 0.4666823747697115,
+      "learning_rate": 5.43789342646837e-06,
+      "loss": 0.1956,
+      "step": 48
+    },
+    {
+      "epoch": 4.704,
+      "grad_norm": 0.416814605318022,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.2117,
+      "step": 49
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.42236198592016266,
+      "learning_rate": 4.5745373613424075e-06,
+      "loss": 0.2107,
+      "step": 50
+    },
+    {
+      "epoch": 4.896,
+      "grad_norm": 0.4621579712676406,
+      "learning_rate": 4.162563277652104e-06,
+      "loss": 0.2235,
+      "step": 51
+    },
+    {
+      "epoch": 4.992,
+      "grad_norm": 0.7416611747223166,
+      "learning_rate": 3.7651019814126656e-06,
+      "loss": 0.3392,
+      "step": 52
+    },
+    {
+      "epoch": 5.088,
+      "grad_norm": 0.518674661043119,
+      "learning_rate": 3.3831416240314085e-06,
+      "loss": 0.2085,
+      "step": 53
+    },
+    {
+      "epoch": 5.184,
+      "grad_norm": 0.4729569000113997,
+      "learning_rate": 3.017631819139273e-06,
+      "loss": 0.1647,
+      "step": 54
+    },
+    {
+      "epoch": 5.28,
+      "grad_norm": 0.4619783594403714,
+      "learning_rate": 2.669481281701739e-06,
+      "loss": 0.2038,
+      "step": 55
+    },
+    {
+      "epoch": 5.376,
+      "grad_norm": 0.4769346388305184,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.1924,
+      "step": 56
+    },
+    {
+      "epoch": 5.4719999999999995,
+      "grad_norm": 0.44383967828923593,
+      "learning_rate": 2.0286749277707783e-06,
+      "loss": 0.1747,
+      "step": 57
+    },
+    {
+      "epoch": 5.568,
+      "grad_norm": 0.4358857668413504,
+      "learning_rate": 1.7376122568400533e-06,
+      "loss": 0.1816,
+      "step": 58
+    },
+    {
+      "epoch": 5.664,
+      "grad_norm": 0.4039608607584127,
+      "learning_rate": 1.467091183678444e-06,
+      "loss": 0.1988,
+      "step": 59
+    },
+    {
+      "epoch": 5.76,
+      "grad_norm": 0.4128153102226709,
+      "learning_rate": 1.2177842662977136e-06,
+      "loss": 0.1782,
+      "step": 60
+    },
+    {
+      "epoch": 5.856,
+      "grad_norm": 0.42435406620245963,
+      "learning_rate": 9.903113209758098e-07,
+      "loss": 0.1954,
+      "step": 61
+    },
+    {
+      "epoch": 5.952,
+      "grad_norm": 0.4073769832263173,
+      "learning_rate": 7.852378812959227e-07,
+      "loss": 0.1875,
+      "step": 62
+    },
+    {
+      "epoch": 6.048,
+      "grad_norm": 0.6882368185291928,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.2588,
+      "step": 63
+    },
+    {
+      "epoch": 6.144,
+      "grad_norm": 0.42923031160913827,
+      "learning_rate": 4.4427194213859216e-07,
+      "loss": 0.2096,
+      "step": 64
+    },
+    {
+      "epoch": 6.24,
+      "grad_norm": 0.3732424615260984,
+      "learning_rate": 3.0922713770922155e-07,
+      "loss": 0.1612,
+      "step": 65
+    },
+    {
+      "epoch": 6.336,
+      "grad_norm": 0.3896684153843582,
+      "learning_rate": 1.9827512151456175e-07,
+      "loss": 0.1427,
+      "step": 66
+    },
+    {
+      "epoch": 6.432,
+      "grad_norm": 0.3186757187044867,
+      "learning_rate": 1.1169173774871478e-07,
+      "loss": 0.1454,
+      "step": 67
+    },
+    {
+      "epoch": 6.5280000000000005,
+      "grad_norm": 0.3632618095985351,
+      "learning_rate": 4.9692246345985905e-08,
+      "loss": 0.1759,
+      "step": 68
+    },
+    {
+      "epoch": 6.624,
+      "grad_norm": 0.3387770968444363,
+      "learning_rate": 1.2430787810776556e-08,
+      "loss": 0.1636,
+      "step": 69
+    },
+    {
+      "epoch": 6.72,
+      "grad_norm": 0.35966621652637387,
+      "learning_rate": 0.0,
+      "loss": 0.1921,
+      "step": 70
+    },
+    {
+      "epoch": 6.72,
+      "step": 70,
+      "total_flos": 8.502394284199117e+16,
+      "train_loss": 0.39509621262550354,
+      "train_runtime": 3677.0494,
+      "train_samples_per_second": 1.904,
+      "train_steps_per_second": 0.019
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 70,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.502394284199117e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5858f95cd86b7d291dc26df552fe928667705bd7cba9d9b8b1a1e544bbfb6289
+size 7352