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

@@ -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: saves_rlsft
+  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. -->
+
+# saves_rlsft
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the openr1_random 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: 4e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 128
+- total_eval_batch_size: 32
+- 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_with_min_lr
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 5.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.52.1
+- Pytorch 2.5.1+cu121
+- Datasets 3.6.0
+- Tokenizers 0.21.1

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": 5.0,
+    "total_flos": 1.3964481498657587e+17,
+    "train_loss": 0.3644733558098475,
+    "train_runtime": 19998.7035,
+    "train_samples_per_second": 0.375,
+    "train_steps_per_second": 0.003
+}

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,28 @@
+{
+  "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": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.1",
+  "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": "4.52.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cf579e35c7ea14391094216bc67ffc03a4b59fd699dc709acf759d02cce6ec7
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1533bc163479231983329202a3238d633b91cb42801ec40a01b359c30d7e7443
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0b00141d0d2456219069490f1941e2cdca9a591cc1c7b1a570295fa06fca8d3
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1351c78e1ba894997eb4ca0abfdef12e859f86d197002a2ea14b53cc21f2317
+size 1089994880

model.safetensors.index.json

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

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+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,
+  "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": 5.0,
+    "total_flos": 1.3964481498657587e+17,
+    "train_loss": 0.3644733558098475,
+    "train_runtime": 19998.7035,
+    "train_samples_per_second": 0.375,
+    "train_steps_per_second": 0.003
+}

trainer_log.jsonl

@@ -0,0 +1,61 @@
+{"current_steps": 1, "total_steps": 60, "loss": 0.7634, "lr": 0.0, "epoch": 0.08533333333333333, "percentage": 1.67, "elapsed_time": "0:06:50", "remaining_time": "6:43:18"}
+{"current_steps": 2, "total_steps": 60, "loss": 0.8049, "lr": 2e-05, "epoch": 0.17066666666666666, "percentage": 3.33, "elapsed_time": "0:11:47", "remaining_time": "5:42:11"}
+{"current_steps": 3, "total_steps": 60, "loss": 0.7336, "lr": 4e-05, "epoch": 0.256, "percentage": 5.0, "elapsed_time": "0:18:04", "remaining_time": "5:43:32"}
+{"current_steps": 4, "total_steps": 60, "loss": 0.7447, "lr": 3.997360144932023e-05, "epoch": 0.3413333333333333, "percentage": 6.67, "elapsed_time": "0:24:08", "remaining_time": "5:38:04"}
+{"current_steps": 5, "total_steps": 60, "loss": 0.6817, "lr": 3.989448322877848e-05, "epoch": 0.4266666666666667, "percentage": 8.33, "elapsed_time": "0:29:48", "remaining_time": "5:27:52"}
+{"current_steps": 6, "total_steps": 60, "loss": 0.6266, "lr": 3.976287740574748e-05, "epoch": 0.512, "percentage": 10.0, "elapsed_time": "0:35:14", "remaining_time": "5:17:07"}
+{"current_steps": 7, "total_steps": 60, "loss": 0.5836, "lr": 3.957917000278156e-05, "epoch": 0.5973333333333334, "percentage": 11.67, "elapsed_time": "0:41:10", "remaining_time": "5:11:42"}
+{"current_steps": 8, "total_steps": 60, "loss": 0.577, "lr": 3.9343899865346015e-05, "epoch": 0.6826666666666666, "percentage": 13.33, "elapsed_time": "0:46:14", "remaining_time": "5:00:32"}
+{"current_steps": 9, "total_steps": 60, "loss": 0.6045, "lr": 3.905775708129045e-05, "epoch": 0.768, "percentage": 15.0, "elapsed_time": "0:51:10", "remaining_time": "4:49:59"}
+{"current_steps": 10, "total_steps": 60, "loss": 0.6023, "lr": 3.872158095670225e-05, "epoch": 0.8533333333333334, "percentage": 16.67, "elapsed_time": "0:55:58", "remaining_time": "4:39:51"}
+{"current_steps": 11, "total_steps": 60, "loss": 0.544, "lr": 3.833635755407723e-05, "epoch": 0.9386666666666666, "percentage": 18.33, "elapsed_time": "1:01:33", "remaining_time": "4:34:11"}
+{"current_steps": 12, "total_steps": 60, "loss": 0.3686, "lr": 3.7903216800028416e-05, "epoch": 1.0, "percentage": 20.0, "elapsed_time": "1:05:49", "remaining_time": "4:23:17"}
+{"current_steps": 13, "total_steps": 60, "loss": 0.4892, "lr": 3.742342917101661e-05, "epoch": 1.0853333333333333, "percentage": 21.67, "elapsed_time": "1:11:02", "remaining_time": "4:16:49"}
+{"current_steps": 14, "total_steps": 60, "loss": 0.4911, "lr": 3.6898401966824035e-05, "epoch": 1.1706666666666667, "percentage": 23.33, "elapsed_time": "1:16:11", "remaining_time": "4:10:22"}
+{"current_steps": 15, "total_steps": 60, "loss": 0.4668, "lr": 3.632967518270159e-05, "epoch": 1.256, "percentage": 25.0, "elapsed_time": "1:21:40", "remaining_time": "4:05:01"}
+{"current_steps": 16, "total_steps": 60, "loss": 0.4744, "lr": 3.5718916992297456e-05, "epoch": 1.3413333333333333, "percentage": 26.67, "elapsed_time": "1:27:37", "remaining_time": "4:00:57"}
+{"current_steps": 17, "total_steps": 60, "loss": 0.4314, "lr": 3.506791885461636e-05, "epoch": 1.4266666666666667, "percentage": 28.33, "elapsed_time": "1:32:42", "remaining_time": "3:54:29"}
+{"current_steps": 18, "total_steps": 60, "loss": 0.4361, "lr": 3.4378590259361626e-05, "epoch": 1.512, "percentage": 30.0, "elapsed_time": "1:38:44", "remaining_time": "3:50:23"}
+{"current_steps": 19, "total_steps": 60, "loss": 0.4458, "lr": 3.36529531260729e-05, "epoch": 1.5973333333333333, "percentage": 31.67, "elapsed_time": "1:44:48", "remaining_time": "3:46:09"}
+{"current_steps": 20, "total_steps": 60, "loss": 0.4447, "lr": 3.289313587348778e-05, "epoch": 1.6826666666666665, "percentage": 33.33, "elapsed_time": "1:50:40", "remaining_time": "3:41:20"}
+{"current_steps": 21, "total_steps": 60, "loss": 0.4357, "lr": 3.2101367176522886e-05, "epoch": 1.768, "percentage": 35.0, "elapsed_time": "1:56:46", "remaining_time": "3:36:51"}
+{"current_steps": 22, "total_steps": 60, "loss": 0.4195, "lr": 3.12799694291864e-05, "epoch": 1.8533333333333335, "percentage": 36.67, "elapsed_time": "2:02:53", "remaining_time": "3:32:15"}
+{"current_steps": 23, "total_steps": 60, "loss": 0.4234, "lr": 3.043135193259623e-05, "epoch": 1.9386666666666668, "percentage": 38.33, "elapsed_time": "2:08:23", "remaining_time": "3:26:32"}
+{"current_steps": 24, "total_steps": 60, "loss": 0.3177, "lr": 2.9558003828084768e-05, "epoch": 2.0, "percentage": 40.0, "elapsed_time": "2:11:54", "remaining_time": "3:17:51"}
+{"current_steps": 25, "total_steps": 60, "loss": 0.3824, "lr": 2.866248679611846e-05, "epoch": 2.0853333333333333, "percentage": 41.67, "elapsed_time": "2:17:50", "remaining_time": "3:12:58"}
+{"current_steps": 26, "total_steps": 60, "loss": 0.34, "lr": 2.774742754244764e-05, "epoch": 2.1706666666666665, "percentage": 43.33, "elapsed_time": "2:23:38", "remaining_time": "3:07:49"}
+{"current_steps": 27, "total_steps": 60, "loss": 0.3577, "lr": 2.681551009352598e-05, "epoch": 2.2560000000000002, "percentage": 45.0, "elapsed_time": "2:30:36", "remaining_time": "3:04:04"}
+{"current_steps": 28, "total_steps": 60, "loss": 0.3519, "lr": 2.586946792379844e-05, "epoch": 2.3413333333333335, "percentage": 46.67, "elapsed_time": "2:36:38", "remaining_time": "2:59:00"}
+{"current_steps": 29, "total_steps": 60, "loss": 0.3251, "lr": 2.491207593794977e-05, "epoch": 2.4266666666666667, "percentage": 48.33, "elapsed_time": "2:42:01", "remaining_time": "2:53:11"}
+{"current_steps": 30, "total_steps": 60, "loss": 0.3098, "lr": 2.3946142331630955e-05, "epoch": 2.512, "percentage": 50.0, "elapsed_time": "2:46:34", "remaining_time": "2:46:34"}
+{"current_steps": 31, "total_steps": 60, "loss": 0.3443, "lr": 2.297450035453752e-05, "epoch": 2.5973333333333333, "percentage": 51.67, "elapsed_time": "2:53:24", "remaining_time": "2:42:13"}
+{"current_steps": 32, "total_steps": 60, "loss": 0.3295, "lr": 2.2000000000000003e-05, "epoch": 2.6826666666666665, "percentage": 53.33, "elapsed_time": "2:59:07", "remaining_time": "2:36:44"}
+{"current_steps": 33, "total_steps": 60, "loss": 0.3137, "lr": 2.1025499645462485e-05, "epoch": 2.768, "percentage": 55.0, "elapsed_time": "3:05:01", "remaining_time": "2:31:22"}
+{"current_steps": 34, "total_steps": 60, "loss": 0.3115, "lr": 2.0053857668369054e-05, "epoch": 2.8533333333333335, "percentage": 56.67, "elapsed_time": "3:10:02", "remaining_time": "2:25:19"}
+{"current_steps": 35, "total_steps": 60, "loss": 0.2944, "lr": 1.9087924062050235e-05, "epoch": 2.9386666666666668, "percentage": 58.33, "elapsed_time": "3:15:00", "remaining_time": "2:19:17"}
+{"current_steps": 36, "total_steps": 60, "loss": 0.2286, "lr": 1.8130532076201567e-05, "epoch": 3.0, "percentage": 60.0, "elapsed_time": "3:18:42", "remaining_time": "2:12:28"}
+{"current_steps": 37, "total_steps": 60, "loss": 0.2556, "lr": 1.7184489906474028e-05, "epoch": 3.0853333333333333, "percentage": 61.67, "elapsed_time": "3:25:24", "remaining_time": "2:07:41"}
+{"current_steps": 38, "total_steps": 60, "loss": 0.2486, "lr": 1.6252572457552366e-05, "epoch": 3.1706666666666665, "percentage": 63.33, "elapsed_time": "3:30:55", "remaining_time": "2:02:06"}
+{"current_steps": 39, "total_steps": 60, "loss": 0.248, "lr": 1.533751320388154e-05, "epoch": 3.2560000000000002, "percentage": 65.0, "elapsed_time": "3:36:13", "remaining_time": "1:56:25"}
+{"current_steps": 40, "total_steps": 60, "loss": 0.2427, "lr": 1.4441996171915241e-05, "epoch": 3.3413333333333335, "percentage": 66.67, "elapsed_time": "3:42:33", "remaining_time": "1:51:16"}
+{"current_steps": 41, "total_steps": 60, "loss": 0.2313, "lr": 1.356864806740378e-05, "epoch": 3.4266666666666667, "percentage": 68.33, "elapsed_time": "3:48:01", "remaining_time": "1:45:40"}
+{"current_steps": 42, "total_steps": 60, "loss": 0.2651, "lr": 1.2720030570813608e-05, "epoch": 3.512, "percentage": 70.0, "elapsed_time": "3:53:24", "remaining_time": "1:40:02"}
+{"current_steps": 43, "total_steps": 60, "loss": 0.2382, "lr": 1.1898632823477121e-05, "epoch": 3.5973333333333333, "percentage": 71.67, "elapsed_time": "3:58:51", "remaining_time": "1:34:25"}
+{"current_steps": 44, "total_steps": 60, "loss": 0.2628, "lr": 1.1106864126512233e-05, "epoch": 3.6826666666666665, "percentage": 73.33, "elapsed_time": "4:04:11", "remaining_time": "1:28:47"}
+{"current_steps": 45, "total_steps": 60, "loss": 0.2228, "lr": 1.0347046873927104e-05, "epoch": 3.768, "percentage": 75.0, "elapsed_time": "4:09:12", "remaining_time": "1:23:04"}
+{"current_steps": 46, "total_steps": 60, "loss": 0.2264, "lr": 9.62140974063838e-06, "epoch": 3.8533333333333335, "percentage": 76.67, "elapsed_time": "4:14:45", "remaining_time": "1:17:32"}
+{"current_steps": 47, "total_steps": 60, "loss": 0.2317, "lr": 8.93208114538365e-06, "epoch": 3.9386666666666668, "percentage": 78.33, "elapsed_time": "4:20:44", "remaining_time": "1:12:07"}
+{"current_steps": 48, "total_steps": 60, "loss": 0.1773, "lr": 8.281083007702546e-06, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "4:25:55", "remaining_time": "1:06:28"}
+{"current_steps": 49, "total_steps": 60, "loss": 0.218, "lr": 7.670324817298414e-06, "epoch": 4.085333333333334, "percentage": 81.67, "elapsed_time": "4:32:31", "remaining_time": "1:01:10"}
+{"current_steps": 50, "total_steps": 60, "loss": 0.1968, "lr": 7.101598033175973e-06, "epoch": 4.1706666666666665, "percentage": 83.33, "elapsed_time": "4:38:21", "remaining_time": "0:55:40"}
+{"current_steps": 51, "total_steps": 60, "loss": 0.2085, "lr": 6.576570828983397e-06, "epoch": 4.256, "percentage": 85.0, "elapsed_time": "4:44:56", "remaining_time": "0:50:17"}
+{"current_steps": 52, "total_steps": 60, "loss": 0.1927, "lr": 6.0967831999715895e-06, "epoch": 4.341333333333333, "percentage": 86.67, "elapsed_time": "4:51:28", "remaining_time": "0:44:50"}
+{"current_steps": 53, "total_steps": 60, "loss": 0.1836, "lr": 5.663642445922777e-06, "epoch": 4.426666666666667, "percentage": 88.33, "elapsed_time": "4:56:26", "remaining_time": "0:39:09"}
+{"current_steps": 54, "total_steps": 60, "loss": 0.187, "lr": 5.278419043297756e-06, "epoch": 4.5120000000000005, "percentage": 90.0, "elapsed_time": "5:01:49", "remaining_time": "0:33:32"}
+{"current_steps": 55, "total_steps": 60, "loss": 0.1733, "lr": 4.9422429187095586e-06, "epoch": 4.597333333333333, "percentage": 91.67, "elapsed_time": "5:06:28", "remaining_time": "0:27:51"}
+{"current_steps": 56, "total_steps": 60, "loss": 0.1885, "lr": 4.656100134653988e-06, "epoch": 4.682666666666667, "percentage": 93.33, "elapsed_time": "5:12:22", "remaining_time": "0:22:18"}
+{"current_steps": 57, "total_steps": 60, "loss": 0.1717, "lr": 4.420829997218441e-06, "epoch": 4.768, "percentage": 95.0, "elapsed_time": "5:17:26", "remaining_time": "0:16:42"}
+{"current_steps": 58, "total_steps": 60, "loss": 0.1904, "lr": 4.23712259425253e-06, "epoch": 4.8533333333333335, "percentage": 96.67, "elapsed_time": "5:22:06", "remaining_time": "0:11:06"}
+{"current_steps": 59, "total_steps": 60, "loss": 0.1567, "lr": 4.105516771221528e-06, "epoch": 4.938666666666666, "percentage": 98.33, "elapsed_time": "5:27:22", "remaining_time": "0:05:32"}
+{"current_steps": 60, "total_steps": 60, "loss": 0.151, "lr": 4.026398550679772e-06, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "5:32:19", "remaining_time": "0:00:00"}
+{"current_steps": 60, "total_steps": 60, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "5:33:17", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,463 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08533333333333333,
+      "grad_norm": 5.823124698748474,
+      "learning_rate": 0.0,
+      "loss": 0.7634,
+      "step": 1
+    },
+    {
+      "epoch": 0.17066666666666666,
+      "grad_norm": 6.263118239866239,
+      "learning_rate": 2e-05,
+      "loss": 0.8049,
+      "step": 2
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 4.592831158098326,
+      "learning_rate": 4e-05,
+      "loss": 0.7336,
+      "step": 3
+    },
+    {
+      "epoch": 0.3413333333333333,
+      "grad_norm": 7.435996456081825,
+      "learning_rate": 3.997360144932023e-05,
+      "loss": 0.7447,
+      "step": 4
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 4.9930199194954845,
+      "learning_rate": 3.989448322877848e-05,
+      "loss": 0.6817,
+      "step": 5
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 2.7882960279288187,
+      "learning_rate": 3.976287740574748e-05,
+      "loss": 0.6266,
+      "step": 6
+    },
+    {
+      "epoch": 0.5973333333333334,
+      "grad_norm": 2.289976818179644,
+      "learning_rate": 3.957917000278156e-05,
+      "loss": 0.5836,
+      "step": 7
+    },
+    {
+      "epoch": 0.6826666666666666,
+      "grad_norm": 2.0583597935795557,
+      "learning_rate": 3.9343899865346015e-05,
+      "loss": 0.577,
+      "step": 8
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 13.050076851975552,
+      "learning_rate": 3.905775708129045e-05,
+      "loss": 0.6045,
+      "step": 9
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 2.783967024609478,
+      "learning_rate": 3.872158095670225e-05,
+      "loss": 0.6023,
+      "step": 10
+    },
+    {
+      "epoch": 0.9386666666666666,
+      "grad_norm": 1.163643128396933,
+      "learning_rate": 3.833635755407723e-05,
+      "loss": 0.544,
+      "step": 11
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.163643128396933,
+      "learning_rate": 3.7903216800028416e-05,
+      "loss": 0.3686,
+      "step": 12
+    },
+    {
+      "epoch": 1.0853333333333333,
+      "grad_norm": 1.5234410523189195,
+      "learning_rate": 3.742342917101661e-05,
+      "loss": 0.4892,
+      "step": 13
+    },
+    {
+      "epoch": 1.1706666666666667,
+      "grad_norm": 1.483688268087892,
+      "learning_rate": 3.6898401966824035e-05,
+      "loss": 0.4911,
+      "step": 14
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 1.2000288439558042,
+      "learning_rate": 3.632967518270159e-05,
+      "loss": 0.4668,
+      "step": 15
+    },
+    {
+      "epoch": 1.3413333333333333,
+      "grad_norm": 1.072884798409246,
+      "learning_rate": 3.5718916992297456e-05,
+      "loss": 0.4744,
+      "step": 16
+    },
+    {
+      "epoch": 1.4266666666666667,
+      "grad_norm": 0.95741338622577,
+      "learning_rate": 3.506791885461636e-05,
+      "loss": 0.4314,
+      "step": 17
+    },
+    {
+      "epoch": 1.512,
+      "grad_norm": 0.8196543627260083,
+      "learning_rate": 3.4378590259361626e-05,
+      "loss": 0.4361,
+      "step": 18
+    },
+    {
+      "epoch": 1.5973333333333333,
+      "grad_norm": 0.9870975955862293,
+      "learning_rate": 3.36529531260729e-05,
+      "loss": 0.4458,
+      "step": 19
+    },
+    {
+      "epoch": 1.6826666666666665,
+      "grad_norm": 0.7238930039506358,
+      "learning_rate": 3.289313587348778e-05,
+      "loss": 0.4447,
+      "step": 20
+    },
+    {
+      "epoch": 1.768,
+      "grad_norm": 1.0705050070030169,
+      "learning_rate": 3.2101367176522886e-05,
+      "loss": 0.4357,
+      "step": 21
+    },
+    {
+      "epoch": 1.8533333333333335,
+      "grad_norm": 0.8320969342312032,
+      "learning_rate": 3.12799694291864e-05,
+      "loss": 0.4195,
+      "step": 22
+    },
+    {
+      "epoch": 1.9386666666666668,
+      "grad_norm": 0.841619379612519,
+      "learning_rate": 3.043135193259623e-05,
+      "loss": 0.4234,
+      "step": 23
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.7955715839135618,
+      "learning_rate": 2.9558003828084768e-05,
+      "loss": 0.3177,
+      "step": 24
+    },
+    {
+      "epoch": 2.0853333333333333,
+      "grad_norm": 0.8659929753748914,
+      "learning_rate": 2.866248679611846e-05,
+      "loss": 0.3824,
+      "step": 25
+    },
+    {
+      "epoch": 2.1706666666666665,
+      "grad_norm": 0.6868897117855765,
+      "learning_rate": 2.774742754244764e-05,
+      "loss": 0.34,
+      "step": 26
+    },
+    {
+      "epoch": 2.2560000000000002,
+      "grad_norm": 0.6329547253401125,
+      "learning_rate": 2.681551009352598e-05,
+      "loss": 0.3577,
+      "step": 27
+    },
+    {
+      "epoch": 2.3413333333333335,
+      "grad_norm": 0.7087428490324059,
+      "learning_rate": 2.586946792379844e-05,
+      "loss": 0.3519,
+      "step": 28
+    },
+    {
+      "epoch": 2.4266666666666667,
+      "grad_norm": 0.6266353632340126,
+      "learning_rate": 2.491207593794977e-05,
+      "loss": 0.3251,
+      "step": 29
+    },
+    {
+      "epoch": 2.512,
+      "grad_norm": 0.5822120409569,
+      "learning_rate": 2.3946142331630955e-05,
+      "loss": 0.3098,
+      "step": 30
+    },
+    {
+      "epoch": 2.5973333333333333,
+      "grad_norm": 0.602806966101651,
+      "learning_rate": 2.297450035453752e-05,
+      "loss": 0.3443,
+      "step": 31
+    },
+    {
+      "epoch": 2.6826666666666665,
+      "grad_norm": 0.5376510071707957,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 0.3295,
+      "step": 32
+    },
+    {
+      "epoch": 2.768,
+      "grad_norm": 0.5705130453549662,
+      "learning_rate": 2.1025499645462485e-05,
+      "loss": 0.3137,
+      "step": 33
+    },
+    {
+      "epoch": 2.8533333333333335,
+      "grad_norm": 0.5043286363745183,
+      "learning_rate": 2.0053857668369054e-05,
+      "loss": 0.3115,
+      "step": 34
+    },
+    {
+      "epoch": 2.9386666666666668,
+      "grad_norm": 0.41142089674196747,
+      "learning_rate": 1.9087924062050235e-05,
+      "loss": 0.2944,
+      "step": 35
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.5645739901906839,
+      "learning_rate": 1.8130532076201567e-05,
+      "loss": 0.2286,
+      "step": 36
+    },
+    {
+      "epoch": 3.0853333333333333,
+      "grad_norm": 0.43084927397789824,
+      "learning_rate": 1.7184489906474028e-05,
+      "loss": 0.2556,
+      "step": 37
+    },
+    {
+      "epoch": 3.1706666666666665,
+      "grad_norm": 0.4785715148027804,
+      "learning_rate": 1.6252572457552366e-05,
+      "loss": 0.2486,
+      "step": 38
+    },
+    {
+      "epoch": 3.2560000000000002,
+      "grad_norm": 0.48284181173314744,
+      "learning_rate": 1.533751320388154e-05,
+      "loss": 0.248,
+      "step": 39
+    },
+    {
+      "epoch": 3.3413333333333335,
+      "grad_norm": 0.4486695709595867,
+      "learning_rate": 1.4441996171915241e-05,
+      "loss": 0.2427,
+      "step": 40
+    },
+    {
+      "epoch": 3.4266666666666667,
+      "grad_norm": 0.45515108810384375,
+      "learning_rate": 1.356864806740378e-05,
+      "loss": 0.2313,
+      "step": 41
+    },
+    {
+      "epoch": 3.512,
+      "grad_norm": 0.4768420671943082,
+      "learning_rate": 1.2720030570813608e-05,
+      "loss": 0.2651,
+      "step": 42
+    },
+    {
+      "epoch": 3.5973333333333333,
+      "grad_norm": 0.44608004702049003,
+      "learning_rate": 1.1898632823477121e-05,
+      "loss": 0.2382,
+      "step": 43
+    },
+    {
+      "epoch": 3.6826666666666665,
+      "grad_norm": 0.4780060358370541,
+      "learning_rate": 1.1106864126512233e-05,
+      "loss": 0.2628,
+      "step": 44
+    },
+    {
+      "epoch": 3.768,
+      "grad_norm": 0.41039041344773,
+      "learning_rate": 1.0347046873927104e-05,
+      "loss": 0.2228,
+      "step": 45
+    },
+    {
+      "epoch": 3.8533333333333335,
+      "grad_norm": 0.35875405696476276,
+      "learning_rate": 9.62140974063838e-06,
+      "loss": 0.2264,
+      "step": 46
+    },
+    {
+      "epoch": 3.9386666666666668,
+      "grad_norm": 0.4345913144288298,
+      "learning_rate": 8.93208114538365e-06,
+      "loss": 0.2317,
+      "step": 47
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.4345913144288298,
+      "learning_rate": 8.281083007702546e-06,
+      "loss": 0.1773,
+      "step": 48
+    },
+    {
+      "epoch": 4.085333333333334,
+      "grad_norm": 0.3679685887922565,
+      "learning_rate": 7.670324817298414e-06,
+      "loss": 0.218,
+      "step": 49
+    },
+    {
+      "epoch": 4.1706666666666665,
+      "grad_norm": 0.3677298278123729,
+      "learning_rate": 7.101598033175973e-06,
+      "loss": 0.1968,
+      "step": 50
+    },
+    {
+      "epoch": 4.256,
+      "grad_norm": 0.32479113103959867,
+      "learning_rate": 6.576570828983397e-06,
+      "loss": 0.2085,
+      "step": 51
+    },
+    {
+      "epoch": 4.341333333333333,
+      "grad_norm": 0.3139710188610545,
+      "learning_rate": 6.0967831999715895e-06,
+      "loss": 0.1927,
+      "step": 52
+    },
+    {
+      "epoch": 4.426666666666667,
+      "grad_norm": 0.3545890466978573,
+      "learning_rate": 5.663642445922777e-06,
+      "loss": 0.1836,
+      "step": 53
+    },
+    {
+      "epoch": 4.5120000000000005,
+      "grad_norm": 0.32966873074012826,
+      "learning_rate": 5.278419043297756e-06,
+      "loss": 0.187,
+      "step": 54
+    },
+    {
+      "epoch": 4.597333333333333,
+      "grad_norm": 0.32158898287910775,
+      "learning_rate": 4.9422429187095586e-06,
+      "loss": 0.1733,
+      "step": 55
+    },
+    {
+      "epoch": 4.682666666666667,
+      "grad_norm": 0.3261200364116069,
+      "learning_rate": 4.656100134653988e-06,
+      "loss": 0.1885,
+      "step": 56
+    },
+    {
+      "epoch": 4.768,
+      "grad_norm": 0.30401427961662475,
+      "learning_rate": 4.420829997218441e-06,
+      "loss": 0.1717,
+      "step": 57
+    },
+    {
+      "epoch": 4.8533333333333335,
+      "grad_norm": 0.2826937087587518,
+      "learning_rate": 4.23712259425253e-06,
+      "loss": 0.1904,
+      "step": 58
+    },
+    {
+      "epoch": 4.938666666666666,
+      "grad_norm": 0.2810378347062423,
+      "learning_rate": 4.105516771221528e-06,
+      "loss": 0.1567,
+      "step": 59
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.2854110729980929,
+      "learning_rate": 4.026398550679772e-06,
+      "loss": 0.151,
+      "step": 60
+    },
+    {
+      "epoch": 5.0,
+      "step": 60,
+      "total_flos": 1.3964481498657587e+17,
+      "train_loss": 0.3644733558098475,
+      "train_runtime": 19998.7035,
+      "train_samples_per_second": 0.375,
+      "train_steps_per_second": 0.003
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 60,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 1.3964481498657587e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:758e1d9b4e3594fc2a2000ffd4ce24d6c959aff201a02ba97230419925bdce0b
+size 7736