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/Qwen3-4B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: concise_phase1_short_qwen3_4b_config1
+  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. -->
+
+# concise_phase1_short_qwen3_4b_config1
+
+This model is a fine-tuned version of [Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B) on the dpo_concise_phase1_short dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-06
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 64
+- 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: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.52.4
+- Pytorch 2.7.1
+- Datasets 3.6.0
+- Tokenizers 0.21.1

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 174251037229056.0,
+    "train_loss": 1.2841152152077095,
+    "train_runtime": 12715.4202,
+    "train_samples_per_second": 3.068,
+    "train_steps_per_second": 0.048
+}

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.52.4"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eef487b367663e0f617b0da82f57e7a565abe483f498b2ff2ddf08c3591b11b
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d16806ead3c08bef3516d2ba4222f8ef3611a2de0d56e7c64356fc035de93abc
+size 3077766632

model.safetensors.index.json

@@ -0,0 +1,405 @@
+{
+  "metadata": {
+    "total_size": 8044936192
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.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:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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": 2.0,
+    "total_flos": 174251037229056.0,
+    "train_loss": 1.2841152152077095,
+    "train_runtime": 12715.4202,
+    "train_samples_per_second": 3.068,
+    "train_steps_per_second": 0.048
+}

trainer_log.jsonl

@@ -0,0 +1,204 @@
+{"current_steps": 3, "total_steps": 610, "loss": 1.3164, "accuracy": 0.4895833432674408, "lr": 3.278688524590164e-08, "epoch": 0.009842116054951815, "percentage": 0.49, "elapsed_time": "0:01:10", "remaining_time": "3:57:56"}
+{"current_steps": 6, "total_steps": 610, "loss": 1.319, "accuracy": 0.515625, "lr": 8.196721311475409e-08, "epoch": 0.01968423210990363, "percentage": 0.98, "elapsed_time": "0:02:11", "remaining_time": "3:40:32"}
+{"current_steps": 9, "total_steps": 610, "loss": 1.3021, "accuracy": 0.5260416865348816, "lr": 1.3114754098360656e-07, "epoch": 0.029526348164855443, "percentage": 1.48, "elapsed_time": "0:03:17", "remaining_time": "3:39:52"}
+{"current_steps": 12, "total_steps": 610, "loss": 1.283, "accuracy": 0.5520833134651184, "lr": 1.80327868852459e-07, "epoch": 0.03936846421980726, "percentage": 1.97, "elapsed_time": "0:04:20", "remaining_time": "3:36:11"}
+{"current_steps": 15, "total_steps": 610, "loss": 1.3095, "accuracy": 0.484375, "lr": 2.2950819672131146e-07, "epoch": 0.04921058027475907, "percentage": 2.46, "elapsed_time": "0:05:21", "remaining_time": "3:32:15"}
+{"current_steps": 18, "total_steps": 610, "loss": 1.3161, "accuracy": 0.4791666865348816, "lr": 2.786885245901639e-07, "epoch": 0.059052696329710885, "percentage": 2.95, "elapsed_time": "0:06:21", "remaining_time": "3:29:17"}
+{"current_steps": 21, "total_steps": 610, "loss": 1.3035, "accuracy": 0.546875, "lr": 3.2786885245901637e-07, "epoch": 0.0688948123846627, "percentage": 3.44, "elapsed_time": "0:07:20", "remaining_time": "3:26:04"}
+{"current_steps": 24, "total_steps": 610, "loss": 1.3275, "accuracy": 0.463541716337204, "lr": 3.770491803278688e-07, "epoch": 0.07873692843961452, "percentage": 3.93, "elapsed_time": "0:08:25", "remaining_time": "3:25:39"}
+{"current_steps": 27, "total_steps": 610, "loss": 1.3084, "accuracy": 0.5104166865348816, "lr": 4.2622950819672127e-07, "epoch": 0.08857904449456633, "percentage": 4.43, "elapsed_time": "0:09:30", "remaining_time": "3:25:14"}
+{"current_steps": 30, "total_steps": 610, "loss": 1.3124, "accuracy": 0.5052083134651184, "lr": 4.754098360655737e-07, "epoch": 0.09842116054951815, "percentage": 4.92, "elapsed_time": "0:10:35", "remaining_time": "3:24:48"}
+{"current_steps": 33, "total_steps": 610, "loss": 1.3369, "accuracy": 0.453125, "lr": 5.245901639344262e-07, "epoch": 0.10826327660446997, "percentage": 5.41, "elapsed_time": "0:11:39", "remaining_time": "3:23:42"}
+{"current_steps": 36, "total_steps": 610, "loss": 1.3247, "accuracy": 0.4739583432674408, "lr": 5.737704918032786e-07, "epoch": 0.11810539265942177, "percentage": 5.9, "elapsed_time": "0:12:39", "remaining_time": "3:21:48"}
+{"current_steps": 39, "total_steps": 610, "loss": 1.3083, "accuracy": 0.5364583730697632, "lr": 6.229508196721311e-07, "epoch": 0.1279475087143736, "percentage": 6.39, "elapsed_time": "0:13:42", "remaining_time": "3:20:38"}
+{"current_steps": 42, "total_steps": 610, "loss": 1.3305, "accuracy": 0.4322916865348816, "lr": 6.721311475409835e-07, "epoch": 0.1377896247693254, "percentage": 6.89, "elapsed_time": "0:14:46", "remaining_time": "3:19:50"}
+{"current_steps": 45, "total_steps": 610, "loss": 1.3069, "accuracy": 0.5052083730697632, "lr": 7.21311475409836e-07, "epoch": 0.1476317408242772, "percentage": 7.38, "elapsed_time": "0:15:50", "remaining_time": "3:18:52"}
+{"current_steps": 48, "total_steps": 610, "loss": 1.3275, "accuracy": 0.4427083432674408, "lr": 7.704918032786884e-07, "epoch": 0.15747385687922905, "percentage": 7.87, "elapsed_time": "0:16:51", "remaining_time": "3:17:22"}
+{"current_steps": 51, "total_steps": 610, "loss": 1.3051, "accuracy": 0.5260416865348816, "lr": 8.196721311475409e-07, "epoch": 0.16731597293418085, "percentage": 8.36, "elapsed_time": "0:17:56", "remaining_time": "3:16:39"}
+{"current_steps": 54, "total_steps": 610, "loss": 1.3217, "accuracy": 0.4739583432674408, "lr": 8.688524590163933e-07, "epoch": 0.17715808898913266, "percentage": 8.85, "elapsed_time": "0:19:00", "remaining_time": "3:15:42"}
+{"current_steps": 57, "total_steps": 610, "loss": 1.3245, "accuracy": 0.4687500298023224, "lr": 9.180327868852458e-07, "epoch": 0.1870002050440845, "percentage": 9.34, "elapsed_time": "0:19:58", "remaining_time": "3:13:44"}
+{"current_steps": 60, "total_steps": 610, "loss": 1.3119, "accuracy": 0.5208333730697632, "lr": 9.672131147540984e-07, "epoch": 0.1968423210990363, "percentage": 9.84, "elapsed_time": "0:21:02", "remaining_time": "3:12:49"}
+{"current_steps": 63, "total_steps": 610, "loss": 1.3159, "accuracy": 0.4583333432674408, "lr": 9.981785063752275e-07, "epoch": 0.2066844371539881, "percentage": 10.33, "elapsed_time": "0:22:07", "remaining_time": "3:12:09"}
+{"current_steps": 66, "total_steps": 610, "loss": 1.3313, "accuracy": 0.4375, "lr": 9.927140255009107e-07, "epoch": 0.21652655320893993, "percentage": 10.82, "elapsed_time": "0:23:15", "remaining_time": "3:11:43"}
+{"current_steps": 69, "total_steps": 610, "loss": 1.318, "accuracy": 0.4739583730697632, "lr": 9.872495446265937e-07, "epoch": 0.22636866926389174, "percentage": 11.31, "elapsed_time": "0:24:20", "remaining_time": "3:10:49"}
+{"current_steps": 72, "total_steps": 610, "loss": 1.3179, "accuracy": 0.4843750298023224, "lr": 9.817850637522768e-07, "epoch": 0.23621078531884354, "percentage": 11.8, "elapsed_time": "0:25:24", "remaining_time": "3:09:52"}
+{"current_steps": 75, "total_steps": 610, "loss": 1.3131, "accuracy": 0.5520833730697632, "lr": 9.7632058287796e-07, "epoch": 0.24605290137379537, "percentage": 12.3, "elapsed_time": "0:26:27", "remaining_time": "3:08:44"}
+{"current_steps": 78, "total_steps": 610, "loss": 1.3005, "accuracy": 0.5625, "lr": 9.70856102003643e-07, "epoch": 0.2558950174287472, "percentage": 12.79, "elapsed_time": "0:27:30", "remaining_time": "3:07:39"}
+{"current_steps": 81, "total_steps": 610, "loss": 1.3001, "accuracy": 0.6041666865348816, "lr": 9.65391621129326e-07, "epoch": 0.265737133483699, "percentage": 13.28, "elapsed_time": "0:28:37", "remaining_time": "3:06:54"}
+{"current_steps": 84, "total_steps": 610, "loss": 1.3219, "accuracy": 0.484375, "lr": 9.599271402550091e-07, "epoch": 0.2755792495386508, "percentage": 13.77, "elapsed_time": "0:29:36", "remaining_time": "3:05:23"}
+{"current_steps": 87, "total_steps": 610, "loss": 1.3204, "accuracy": 0.4895833432674408, "lr": 9.54462659380692e-07, "epoch": 0.28542136559360265, "percentage": 14.26, "elapsed_time": "0:30:36", "remaining_time": "3:04:01"}
+{"current_steps": 90, "total_steps": 610, "loss": 1.3082, "accuracy": 0.5677083730697632, "lr": 9.489981785063752e-07, "epoch": 0.2952634816485544, "percentage": 14.75, "elapsed_time": "0:31:42", "remaining_time": "3:03:10"}
+{"current_steps": 93, "total_steps": 610, "loss": 1.3102, "accuracy": 0.5104166865348816, "lr": 9.435336976320582e-07, "epoch": 0.30510559770350626, "percentage": 15.25, "elapsed_time": "0:32:43", "remaining_time": "3:01:54"}
+{"current_steps": 96, "total_steps": 610, "loss": 1.3232, "accuracy": 0.4739583730697632, "lr": 9.380692167577413e-07, "epoch": 0.3149477137584581, "percentage": 15.74, "elapsed_time": "0:33:48", "remaining_time": "3:01:01"}
+{"current_steps": 99, "total_steps": 610, "loss": 1.3169, "accuracy": 0.4635416865348816, "lr": 9.326047358834243e-07, "epoch": 0.32478982981340987, "percentage": 16.23, "elapsed_time": "0:34:50", "remaining_time": "2:59:51"}
+{"current_steps": 102, "total_steps": 610, "loss": 1.3197, "accuracy": 0.4895833730697632, "lr": 9.271402550091074e-07, "epoch": 0.3346319458683617, "percentage": 16.72, "elapsed_time": "0:35:56", "remaining_time": "2:58:59"}
+{"current_steps": 105, "total_steps": 610, "loss": 1.3118, "accuracy": 0.484375, "lr": 9.216757741347905e-07, "epoch": 0.34447406192331353, "percentage": 17.21, "elapsed_time": "0:36:57", "remaining_time": "2:57:46"}
+{"current_steps": 108, "total_steps": 610, "loss": 1.3177, "accuracy": 0.479166716337204, "lr": 9.162112932604735e-07, "epoch": 0.3543161779782653, "percentage": 17.7, "elapsed_time": "0:37:59", "remaining_time": "2:56:35"}
+{"current_steps": 111, "total_steps": 610, "loss": 1.3121, "accuracy": 0.484375, "lr": 9.107468123861566e-07, "epoch": 0.36415829403321714, "percentage": 18.2, "elapsed_time": "0:39:00", "remaining_time": "2:55:20"}
+{"current_steps": 114, "total_steps": 610, "loss": 1.3162, "accuracy": 0.4791666865348816, "lr": 9.052823315118397e-07, "epoch": 0.374000410088169, "percentage": 18.69, "elapsed_time": "0:40:01", "remaining_time": "2:54:10"}
+{"current_steps": 117, "total_steps": 610, "loss": 1.3166, "accuracy": 0.515625, "lr": 8.998178506375227e-07, "epoch": 0.38384252614312075, "percentage": 19.18, "elapsed_time": "0:41:02", "remaining_time": "2:52:55"}
+{"current_steps": 120, "total_steps": 610, "loss": 1.316, "accuracy": 0.4531250298023224, "lr": 8.943533697632057e-07, "epoch": 0.3936846421980726, "percentage": 19.67, "elapsed_time": "0:42:04", "remaining_time": "2:51:49"}
+{"current_steps": 123, "total_steps": 610, "loss": 1.3047, "accuracy": 0.5416666865348816, "lr": 8.888888888888888e-07, "epoch": 0.4035267582530244, "percentage": 20.16, "elapsed_time": "0:43:05", "remaining_time": "2:50:37"}
+{"current_steps": 126, "total_steps": 610, "loss": 1.3127, "accuracy": 0.515625, "lr": 8.834244080145718e-07, "epoch": 0.4133688743079762, "percentage": 20.66, "elapsed_time": "0:44:06", "remaining_time": "2:49:25"}
+{"current_steps": 129, "total_steps": 610, "loss": 1.3048, "accuracy": 0.5572916865348816, "lr": 8.77959927140255e-07, "epoch": 0.42321099036292803, "percentage": 21.15, "elapsed_time": "0:45:12", "remaining_time": "2:48:34"}
+{"current_steps": 132, "total_steps": 610, "loss": 1.3144, "accuracy": 0.4479166865348816, "lr": 8.724954462659381e-07, "epoch": 0.43305310641787986, "percentage": 21.64, "elapsed_time": "0:46:15", "remaining_time": "2:47:29"}
+{"current_steps": 135, "total_steps": 610, "loss": 1.3219, "accuracy": 0.4843750298023224, "lr": 8.670309653916211e-07, "epoch": 0.44289522247283164, "percentage": 22.13, "elapsed_time": "0:47:16", "remaining_time": "2:46:20"}
+{"current_steps": 138, "total_steps": 610, "loss": 1.2998, "accuracy": 0.5625000596046448, "lr": 8.615664845173042e-07, "epoch": 0.4527373385277835, "percentage": 22.62, "elapsed_time": "0:48:15", "remaining_time": "2:45:03"}
+{"current_steps": 141, "total_steps": 610, "loss": 1.3155, "accuracy": 0.4947916865348816, "lr": 8.561020036429873e-07, "epoch": 0.4625794545827353, "percentage": 23.11, "elapsed_time": "0:49:16", "remaining_time": "2:43:55"}
+{"current_steps": 144, "total_steps": 610, "loss": 1.3097, "accuracy": 0.5104167461395264, "lr": 8.506375227686703e-07, "epoch": 0.4724215706376871, "percentage": 23.61, "elapsed_time": "0:50:22", "remaining_time": "2:43:00"}
+{"current_steps": 147, "total_steps": 610, "loss": 1.3163, "accuracy": 0.5208333730697632, "lr": 8.451730418943533e-07, "epoch": 0.4822636866926389, "percentage": 24.1, "elapsed_time": "0:51:23", "remaining_time": "2:41:53"}
+{"current_steps": 150, "total_steps": 610, "loss": 1.3146, "accuracy": 0.5260417461395264, "lr": 8.397085610200364e-07, "epoch": 0.49210580274759075, "percentage": 24.59, "elapsed_time": "0:52:24", "remaining_time": "2:40:43"}
+{"current_steps": 153, "total_steps": 610, "loss": 1.3112, "accuracy": 0.5833333730697632, "lr": 8.342440801457194e-07, "epoch": 0.5019479188025425, "percentage": 25.08, "elapsed_time": "0:53:28", "remaining_time": "2:39:44"}
+{"current_steps": 156, "total_steps": 610, "loss": 1.3027, "accuracy": 0.5364583730697632, "lr": 8.287795992714025e-07, "epoch": 0.5117900348574944, "percentage": 25.57, "elapsed_time": "0:54:33", "remaining_time": "2:38:46"}
+{"current_steps": 159, "total_steps": 610, "loss": 1.3047, "accuracy": 0.5208333730697632, "lr": 8.233151183970856e-07, "epoch": 0.5216321509124462, "percentage": 26.07, "elapsed_time": "0:55:32", "remaining_time": "2:37:33"}
+{"current_steps": 162, "total_steps": 610, "loss": 1.3113, "accuracy": 0.5104166865348816, "lr": 8.178506375227686e-07, "epoch": 0.531474266967398, "percentage": 26.56, "elapsed_time": "0:56:34", "remaining_time": "2:36:28"}
+{"current_steps": 165, "total_steps": 610, "loss": 1.3007, "accuracy": 0.5677083730697632, "lr": 8.123861566484517e-07, "epoch": 0.5413163830223499, "percentage": 27.05, "elapsed_time": "0:57:33", "remaining_time": "2:35:15"}
+{"current_steps": 168, "total_steps": 610, "loss": 1.318, "accuracy": 0.5104166865348816, "lr": 8.069216757741348e-07, "epoch": 0.5511584990773016, "percentage": 27.54, "elapsed_time": "0:58:34", "remaining_time": "2:34:07"}
+{"current_steps": 171, "total_steps": 610, "loss": 1.3094, "accuracy": 0.515625, "lr": 8.014571948998177e-07, "epoch": 0.5610006151322534, "percentage": 28.03, "elapsed_time": "0:59:40", "remaining_time": "2:33:13"}
+{"current_steps": 174, "total_steps": 610, "loss": 1.3143, "accuracy": 0.5052083730697632, "lr": 7.959927140255008e-07, "epoch": 0.5708427311872053, "percentage": 28.52, "elapsed_time": "1:00:44", "remaining_time": "2:32:11"}
+{"current_steps": 177, "total_steps": 610, "loss": 1.3182, "accuracy": 0.4687500298023224, "lr": 7.905282331511839e-07, "epoch": 0.5806848472421571, "percentage": 29.02, "elapsed_time": "1:01:45", "remaining_time": "2:31:05"}
+{"current_steps": 180, "total_steps": 610, "loss": 1.3251, "accuracy": 0.4739583730697632, "lr": 7.850637522768669e-07, "epoch": 0.5905269632971089, "percentage": 29.51, "elapsed_time": "1:02:45", "remaining_time": "2:29:54"}
+{"current_steps": 183, "total_steps": 610, "loss": 1.3181, "accuracy": 0.46875, "lr": 7.795992714025501e-07, "epoch": 0.6003690793520607, "percentage": 30.0, "elapsed_time": "1:03:45", "remaining_time": "2:28:47"}
+{"current_steps": 186, "total_steps": 610, "loss": 1.3177, "accuracy": 0.46875, "lr": 7.741347905282332e-07, "epoch": 0.6102111954070125, "percentage": 30.49, "elapsed_time": "1:04:49", "remaining_time": "2:27:46"}
+{"current_steps": 189, "total_steps": 610, "loss": 1.306, "accuracy": 0.4895833730697632, "lr": 7.686703096539162e-07, "epoch": 0.6200533114619643, "percentage": 30.98, "elapsed_time": "1:05:49", "remaining_time": "2:26:37"}
+{"current_steps": 192, "total_steps": 610, "loss": 1.3108, "accuracy": 0.4895833730697632, "lr": 7.632058287795993e-07, "epoch": 0.6298954275169162, "percentage": 31.48, "elapsed_time": "1:06:53", "remaining_time": "2:25:37"}
+{"current_steps": 195, "total_steps": 610, "loss": 1.3091, "accuracy": 0.5364583730697632, "lr": 7.577413479052824e-07, "epoch": 0.639737543571868, "percentage": 31.97, "elapsed_time": "1:07:53", "remaining_time": "2:24:29"}
+{"current_steps": 198, "total_steps": 610, "loss": 1.3132, "accuracy": 0.479166716337204, "lr": 7.522768670309653e-07, "epoch": 0.6495796596268197, "percentage": 32.46, "elapsed_time": "1:08:54", "remaining_time": "2:23:22"}
+{"current_steps": 201, "total_steps": 610, "loss": 1.3049, "accuracy": 0.5885416865348816, "lr": 7.468123861566484e-07, "epoch": 0.6594217756817716, "percentage": 32.95, "elapsed_time": "1:10:00", "remaining_time": "2:22:27"}
+{"current_steps": 204, "total_steps": 610, "loss": 1.3066, "accuracy": 0.53125, "lr": 7.413479052823315e-07, "epoch": 0.6692638917367234, "percentage": 33.44, "elapsed_time": "1:11:04", "remaining_time": "2:21:27"}
+{"current_steps": 207, "total_steps": 610, "loss": 1.3078, "accuracy": 0.5520833730697632, "lr": 7.358834244080145e-07, "epoch": 0.6791060077916752, "percentage": 33.93, "elapsed_time": "1:12:04", "remaining_time": "2:20:18"}
+{"current_steps": 210, "total_steps": 610, "loss": 1.3044, "accuracy": 0.5729166865348816, "lr": 7.304189435336976e-07, "epoch": 0.6889481238466271, "percentage": 34.43, "elapsed_time": "1:13:06", "remaining_time": "2:19:15"}
+{"current_steps": 213, "total_steps": 610, "loss": 1.3124, "accuracy": 0.494791716337204, "lr": 7.249544626593807e-07, "epoch": 0.6987902399015788, "percentage": 34.92, "elapsed_time": "1:14:11", "remaining_time": "2:18:16"}
+{"current_steps": 216, "total_steps": 610, "loss": 1.3127, "accuracy": 0.515625, "lr": 7.194899817850637e-07, "epoch": 0.7086323559565306, "percentage": 35.41, "elapsed_time": "1:15:13", "remaining_time": "2:17:12"}
+{"current_steps": 219, "total_steps": 610, "loss": 1.3229, "accuracy": 0.4687500298023224, "lr": 7.140255009107468e-07, "epoch": 0.7184744720114825, "percentage": 35.9, "elapsed_time": "1:16:14", "remaining_time": "2:16:06"}
+{"current_steps": 222, "total_steps": 610, "loss": 1.3099, "accuracy": 0.5104166865348816, "lr": 7.085610200364299e-07, "epoch": 0.7283165880664343, "percentage": 36.39, "elapsed_time": "1:17:15", "remaining_time": "2:15:01"}
+{"current_steps": 225, "total_steps": 610, "loss": 1.3218, "accuracy": 0.4739583432674408, "lr": 7.030965391621128e-07, "epoch": 0.7381587041213861, "percentage": 36.89, "elapsed_time": "1:18:15", "remaining_time": "2:13:54"}
+{"current_steps": 228, "total_steps": 610, "loss": 1.3053, "accuracy": 0.4635416865348816, "lr": 6.976320582877959e-07, "epoch": 0.748000820176338, "percentage": 37.38, "elapsed_time": "1:19:19", "remaining_time": "2:12:54"}
+{"current_steps": 231, "total_steps": 610, "loss": 1.3096, "accuracy": 0.5364583730697632, "lr": 6.92167577413479e-07, "epoch": 0.7578429362312897, "percentage": 37.87, "elapsed_time": "1:20:24", "remaining_time": "2:11:55"}
+{"current_steps": 234, "total_steps": 610, "loss": 1.3076, "accuracy": 0.53125, "lr": 6.86703096539162e-07, "epoch": 0.7676850522862415, "percentage": 38.36, "elapsed_time": "1:21:26", "remaining_time": "2:10:52"}
+{"current_steps": 237, "total_steps": 610, "loss": 1.3096, "accuracy": 0.515625, "lr": 6.812386156648452e-07, "epoch": 0.7775271683411934, "percentage": 38.85, "elapsed_time": "1:22:30", "remaining_time": "2:09:51"}
+{"current_steps": 240, "total_steps": 610, "loss": 1.3171, "accuracy": 0.5104166865348816, "lr": 6.757741347905283e-07, "epoch": 0.7873692843961452, "percentage": 39.34, "elapsed_time": "1:23:34", "remaining_time": "2:08:51"}
+{"current_steps": 243, "total_steps": 610, "loss": 1.3088, "accuracy": 0.5052083730697632, "lr": 6.703096539162113e-07, "epoch": 0.797211400451097, "percentage": 39.84, "elapsed_time": "1:24:37", "remaining_time": "2:07:48"}
+{"current_steps": 246, "total_steps": 610, "loss": 1.3161, "accuracy": 0.4739583730697632, "lr": 6.648451730418944e-07, "epoch": 0.8070535165060488, "percentage": 40.33, "elapsed_time": "1:25:39", "remaining_time": "2:06:44"}
+{"current_steps": 249, "total_steps": 610, "loss": 1.3097, "accuracy": 0.546875, "lr": 6.593806921675775e-07, "epoch": 0.8168956325610006, "percentage": 40.82, "elapsed_time": "1:26:37", "remaining_time": "2:05:34"}
+{"current_steps": 252, "total_steps": 610, "loss": 1.3094, "accuracy": 0.515625, "lr": 6.539162112932604e-07, "epoch": 0.8267377486159524, "percentage": 41.31, "elapsed_time": "1:28:07", "remaining_time": "2:05:11"}
+{"current_steps": 255, "total_steps": 610, "loss": 1.3122, "accuracy": 0.4895833730697632, "lr": 6.484517304189435e-07, "epoch": 0.8365798646709043, "percentage": 41.8, "elapsed_time": "1:29:13", "remaining_time": "2:04:12"}
+{"current_steps": 258, "total_steps": 610, "loss": 1.3209, "accuracy": 0.4843750298023224, "lr": 6.429872495446266e-07, "epoch": 0.8464219807258561, "percentage": 42.3, "elapsed_time": "1:30:18", "remaining_time": "2:03:12"}
+{"current_steps": 261, "total_steps": 610, "loss": 1.314, "accuracy": 0.515625, "lr": 6.375227686703096e-07, "epoch": 0.8562640967808078, "percentage": 42.79, "elapsed_time": "1:31:20", "remaining_time": "2:02:07"}
+{"current_steps": 264, "total_steps": 610, "loss": 1.3101, "accuracy": 0.53125, "lr": 6.320582877959927e-07, "epoch": 0.8661062128357597, "percentage": 43.28, "elapsed_time": "1:32:20", "remaining_time": "2:01:01"}
+{"current_steps": 267, "total_steps": 610, "loss": 1.3096, "accuracy": 0.5104166865348816, "lr": 6.265938069216758e-07, "epoch": 0.8759483288907115, "percentage": 43.77, "elapsed_time": "1:33:23", "remaining_time": "1:59:58"}
+{"current_steps": 270, "total_steps": 610, "loss": 1.299, "accuracy": 0.5729166865348816, "lr": 6.211293260473588e-07, "epoch": 0.8857904449456633, "percentage": 44.26, "elapsed_time": "1:34:26", "remaining_time": "1:58:55"}
+{"current_steps": 273, "total_steps": 610, "loss": 1.3066, "accuracy": 0.5364583730697632, "lr": 6.156648451730419e-07, "epoch": 0.8956325610006152, "percentage": 44.75, "elapsed_time": "1:35:30", "remaining_time": "1:57:54"}
+{"current_steps": 276, "total_steps": 610, "loss": 1.3091, "accuracy": 0.5052083730697632, "lr": 6.102003642987249e-07, "epoch": 0.905474677055567, "percentage": 45.25, "elapsed_time": "1:36:33", "remaining_time": "1:56:50"}
+{"current_steps": 279, "total_steps": 610, "loss": 1.306, "accuracy": 0.53125, "lr": 6.047358834244079e-07, "epoch": 0.9153167931105187, "percentage": 45.74, "elapsed_time": "1:37:36", "remaining_time": "1:55:48"}
+{"current_steps": 282, "total_steps": 610, "loss": 1.3107, "accuracy": 0.515625, "lr": 5.99271402550091e-07, "epoch": 0.9251589091654706, "percentage": 46.23, "elapsed_time": "1:38:43", "remaining_time": "1:54:49"}
+{"current_steps": 285, "total_steps": 610, "loss": 1.3106, "accuracy": 0.515625, "lr": 5.93806921675774e-07, "epoch": 0.9350010252204224, "percentage": 46.72, "elapsed_time": "1:39:43", "remaining_time": "1:53:43"}
+{"current_steps": 288, "total_steps": 610, "loss": 1.3077, "accuracy": 0.5625, "lr": 5.883424408014571e-07, "epoch": 0.9448431412753742, "percentage": 47.21, "elapsed_time": "1:40:44", "remaining_time": "1:52:38"}
+{"current_steps": 291, "total_steps": 610, "loss": 1.311, "accuracy": 0.5052083134651184, "lr": 5.828779599271403e-07, "epoch": 0.954685257330326, "percentage": 47.7, "elapsed_time": "1:41:42", "remaining_time": "1:51:30"}
+{"current_steps": 294, "total_steps": 610, "loss": 1.319, "accuracy": 0.4895833730697632, "lr": 5.774134790528234e-07, "epoch": 0.9645273733852778, "percentage": 48.2, "elapsed_time": "1:42:45", "remaining_time": "1:50:27"}
+{"current_steps": 297, "total_steps": 610, "loss": 1.3133, "accuracy": 0.5729166865348816, "lr": 5.719489981785064e-07, "epoch": 0.9743694894402296, "percentage": 48.69, "elapsed_time": "1:43:50", "remaining_time": "1:49:25"}
+{"current_steps": 300, "total_steps": 610, "loss": 1.3131, "accuracy": 0.4791666865348816, "lr": 5.664845173041895e-07, "epoch": 0.9842116054951815, "percentage": 49.18, "elapsed_time": "1:44:52", "remaining_time": "1:48:22"}
+{"current_steps": 303, "total_steps": 610, "loss": 1.3124, "accuracy": 0.5364583730697632, "lr": 5.610200364298725e-07, "epoch": 0.9940537215501333, "percentage": 49.67, "elapsed_time": "1:45:53", "remaining_time": "1:47:16"}
+{"current_steps": 306, "total_steps": 610, "loss": 1.21, "accuracy": 0.6166666746139526, "lr": 5.555555555555555e-07, "epoch": 1.0032807053516506, "percentage": 50.16, "elapsed_time": "1:46:49", "remaining_time": "1:46:08"}
+{"current_steps": 309, "total_steps": 610, "loss": 1.2742, "accuracy": 0.6822916865348816, "lr": 5.500910746812386e-07, "epoch": 1.0131228214066024, "percentage": 50.66, "elapsed_time": "1:47:52", "remaining_time": "1:45:05"}
+{"current_steps": 312, "total_steps": 610, "loss": 1.2852, "accuracy": 0.6197916865348816, "lr": 5.446265938069217e-07, "epoch": 1.0229649374615541, "percentage": 51.15, "elapsed_time": "1:48:56", "remaining_time": "1:44:03"}
+{"current_steps": 315, "total_steps": 610, "loss": 1.2851, "accuracy": 0.6614583730697632, "lr": 5.391621129326047e-07, "epoch": 1.0328070535165061, "percentage": 51.64, "elapsed_time": "1:50:01", "remaining_time": "1:43:01"}
+{"current_steps": 318, "total_steps": 610, "loss": 1.2793, "accuracy": 0.6510416865348816, "lr": 5.336976320582878e-07, "epoch": 1.042649169571458, "percentage": 52.13, "elapsed_time": "1:51:02", "remaining_time": "1:41:57"}
+{"current_steps": 321, "total_steps": 610, "loss": 1.2768, "accuracy": 0.6354166865348816, "lr": 5.282331511839709e-07, "epoch": 1.0524912856264097, "percentage": 52.62, "elapsed_time": "1:52:08", "remaining_time": "1:40:57"}
+{"current_steps": 324, "total_steps": 610, "loss": 1.2731, "accuracy": 0.6770833730697632, "lr": 5.227686703096539e-07, "epoch": 1.0623334016813615, "percentage": 53.11, "elapsed_time": "1:53:13", "remaining_time": "1:39:56"}
+{"current_steps": 327, "total_steps": 610, "loss": 1.2673, "accuracy": 0.6510417461395264, "lr": 5.17304189435337e-07, "epoch": 1.0721755177363133, "percentage": 53.61, "elapsed_time": "1:54:14", "remaining_time": "1:38:52"}
+{"current_steps": 330, "total_steps": 610, "loss": 1.2934, "accuracy": 0.5520833730697632, "lr": 5.118397085610199e-07, "epoch": 1.082017633791265, "percentage": 54.1, "elapsed_time": "1:55:16", "remaining_time": "1:37:48"}
+{"current_steps": 333, "total_steps": 610, "loss": 1.2794, "accuracy": 0.6041666865348816, "lr": 5.06375227686703e-07, "epoch": 1.091859749846217, "percentage": 54.59, "elapsed_time": "1:56:18", "remaining_time": "1:36:44"}
+{"current_steps": 336, "total_steps": 610, "loss": 1.2851, "accuracy": 0.5885416865348816, "lr": 5.009107468123861e-07, "epoch": 1.1017018659011688, "percentage": 55.08, "elapsed_time": "1:57:17", "remaining_time": "1:35:39"}
+{"current_steps": 339, "total_steps": 610, "loss": 1.2779, "accuracy": 0.5885416865348816, "lr": 4.954462659380693e-07, "epoch": 1.1115439819561206, "percentage": 55.57, "elapsed_time": "1:58:20", "remaining_time": "1:34:36"}
+{"current_steps": 342, "total_steps": 610, "loss": 1.2696, "accuracy": 0.6197917461395264, "lr": 4.899817850637522e-07, "epoch": 1.1213860980110724, "percentage": 56.07, "elapsed_time": "1:59:20", "remaining_time": "1:33:31"}
+{"current_steps": 345, "total_steps": 610, "loss": 1.2794, "accuracy": 0.5677083730697632, "lr": 4.845173041894353e-07, "epoch": 1.1312282140660241, "percentage": 56.56, "elapsed_time": "2:00:24", "remaining_time": "1:32:29"}
+{"current_steps": 348, "total_steps": 610, "loss": 1.2643, "accuracy": 0.6822916865348816, "lr": 4.790528233151183e-07, "epoch": 1.141070330120976, "percentage": 57.05, "elapsed_time": "2:01:24", "remaining_time": "1:31:24"}
+{"current_steps": 351, "total_steps": 610, "loss": 1.2661, "accuracy": 0.6510416865348816, "lr": 4.735883424408014e-07, "epoch": 1.150912446175928, "percentage": 57.54, "elapsed_time": "2:02:25", "remaining_time": "1:30:20"}
+{"current_steps": 354, "total_steps": 610, "loss": 1.2736, "accuracy": 0.6145833730697632, "lr": 4.681238615664845e-07, "epoch": 1.1607545622308797, "percentage": 58.03, "elapsed_time": "2:03:29", "remaining_time": "1:29:18"}
+{"current_steps": 357, "total_steps": 610, "loss": 1.2679, "accuracy": 0.609375, "lr": 4.6265938069216755e-07, "epoch": 1.1705966782858315, "percentage": 58.52, "elapsed_time": "2:04:31", "remaining_time": "1:28:15"}
+{"current_steps": 360, "total_steps": 610, "loss": 1.2573, "accuracy": 0.6354166865348816, "lr": 4.5719489981785067e-07, "epoch": 1.1804387943407832, "percentage": 59.02, "elapsed_time": "2:05:32", "remaining_time": "1:27:11"}
+{"current_steps": 363, "total_steps": 610, "loss": 1.2777, "accuracy": 0.59375, "lr": 4.517304189435337e-07, "epoch": 1.190280910395735, "percentage": 59.51, "elapsed_time": "2:06:32", "remaining_time": "1:26:06"}
+{"current_steps": 366, "total_steps": 610, "loss": 1.2644, "accuracy": 0.6354166865348816, "lr": 4.4626593806921675e-07, "epoch": 1.2001230264506868, "percentage": 60.0, "elapsed_time": "2:07:32", "remaining_time": "1:25:01"}
+{"current_steps": 369, "total_steps": 610, "loss": 1.2592, "accuracy": 0.65625, "lr": 4.408014571948998e-07, "epoch": 1.2099651425056388, "percentage": 60.49, "elapsed_time": "2:08:33", "remaining_time": "1:23:58"}
+{"current_steps": 372, "total_steps": 610, "loss": 1.2707, "accuracy": 0.6458333730697632, "lr": 4.353369763205829e-07, "epoch": 1.2198072585605906, "percentage": 60.98, "elapsed_time": "2:09:39", "remaining_time": "1:22:57"}
+{"current_steps": 375, "total_steps": 610, "loss": 1.2752, "accuracy": 0.6354166865348816, "lr": 4.298724954462659e-07, "epoch": 1.2296493746155424, "percentage": 61.48, "elapsed_time": "2:10:40", "remaining_time": "1:21:53"}
+{"current_steps": 378, "total_steps": 610, "loss": 1.2405, "accuracy": 0.6354166865348816, "lr": 4.2440801457194896e-07, "epoch": 1.2394914906704941, "percentage": 61.97, "elapsed_time": "2:11:40", "remaining_time": "1:20:48"}
+{"current_steps": 381, "total_steps": 610, "loss": 1.2673, "accuracy": 0.6458333730697632, "lr": 4.1894353369763203e-07, "epoch": 1.249333606725446, "percentage": 62.46, "elapsed_time": "2:12:41", "remaining_time": "1:19:45"}
+{"current_steps": 384, "total_steps": 610, "loss": 1.2646, "accuracy": 0.5989583730697632, "lr": 4.134790528233151e-07, "epoch": 1.2591757227803977, "percentage": 62.95, "elapsed_time": "2:13:41", "remaining_time": "1:18:41"}
+{"current_steps": 387, "total_steps": 610, "loss": 1.2519, "accuracy": 0.59375, "lr": 4.0801457194899816e-07, "epoch": 1.2690178388353495, "percentage": 63.44, "elapsed_time": "2:14:44", "remaining_time": "1:17:38"}
+{"current_steps": 390, "total_steps": 610, "loss": 1.2879, "accuracy": 0.6145833730697632, "lr": 4.0255009107468123e-07, "epoch": 1.2788599548903015, "percentage": 63.93, "elapsed_time": "2:15:46", "remaining_time": "1:16:35"}
+{"current_steps": 393, "total_steps": 610, "loss": 1.2674, "accuracy": 0.5729166865348816, "lr": 3.970856102003643e-07, "epoch": 1.2887020709452532, "percentage": 64.43, "elapsed_time": "2:16:47", "remaining_time": "1:15:31"}
+{"current_steps": 396, "total_steps": 610, "loss": 1.2736, "accuracy": 0.5885416865348816, "lr": 3.9162112932604736e-07, "epoch": 1.298544187000205, "percentage": 64.92, "elapsed_time": "2:17:44", "remaining_time": "1:14:25"}
+{"current_steps": 399, "total_steps": 610, "loss": 1.2666, "accuracy": 0.6302083730697632, "lr": 3.8615664845173043e-07, "epoch": 1.3083863030551568, "percentage": 65.41, "elapsed_time": "2:18:43", "remaining_time": "1:13:21"}
+{"current_steps": 402, "total_steps": 610, "loss": 1.289, "accuracy": 0.5208333730697632, "lr": 3.8069216757741344e-07, "epoch": 1.3182284191101088, "percentage": 65.9, "elapsed_time": "2:19:48", "remaining_time": "1:12:20"}
+{"current_steps": 405, "total_steps": 610, "loss": 1.2564, "accuracy": 0.6458333730697632, "lr": 3.752276867030965e-07, "epoch": 1.3280705351650606, "percentage": 66.39, "elapsed_time": "2:20:53", "remaining_time": "1:11:18"}
+{"current_steps": 408, "total_steps": 610, "loss": 1.2334, "accuracy": 0.6927083730697632, "lr": 3.697632058287796e-07, "epoch": 1.3379126512200123, "percentage": 66.89, "elapsed_time": "2:21:55", "remaining_time": "1:10:16"}
+{"current_steps": 411, "total_steps": 610, "loss": 1.2598, "accuracy": 0.5625, "lr": 3.6429872495446264e-07, "epoch": 1.3477547672749641, "percentage": 67.38, "elapsed_time": "2:22:55", "remaining_time": "1:09:12"}
+{"current_steps": 414, "total_steps": 610, "loss": 1.252, "accuracy": 0.6041666865348816, "lr": 3.5883424408014566e-07, "epoch": 1.357596883329916, "percentage": 67.87, "elapsed_time": "2:23:58", "remaining_time": "1:08:09"}
+{"current_steps": 417, "total_steps": 610, "loss": 1.2405, "accuracy": 0.59375, "lr": 3.533697632058288e-07, "epoch": 1.3674389993848677, "percentage": 68.36, "elapsed_time": "2:25:01", "remaining_time": "1:07:07"}
+{"current_steps": 420, "total_steps": 610, "loss": 1.2528, "accuracy": 0.625, "lr": 3.4790528233151184e-07, "epoch": 1.3772811154398195, "percentage": 68.85, "elapsed_time": "2:26:06", "remaining_time": "1:06:05"}
+{"current_steps": 423, "total_steps": 610, "loss": 1.2465, "accuracy": 0.6458333730697632, "lr": 3.424408014571949e-07, "epoch": 1.3871232314947715, "percentage": 69.34, "elapsed_time": "2:27:05", "remaining_time": "1:05:01"}
+{"current_steps": 426, "total_steps": 610, "loss": 1.234, "accuracy": 0.5885417461395264, "lr": 3.369763205828779e-07, "epoch": 1.3969653475497232, "percentage": 69.84, "elapsed_time": "2:28:03", "remaining_time": "1:03:56"}
+{"current_steps": 429, "total_steps": 610, "loss": 1.2604, "accuracy": 0.5625, "lr": 3.31511839708561e-07, "epoch": 1.406807463604675, "percentage": 70.33, "elapsed_time": "2:29:04", "remaining_time": "1:02:53"}
+{"current_steps": 432, "total_steps": 610, "loss": 1.2343, "accuracy": 0.6614583730697632, "lr": 3.2604735883424406e-07, "epoch": 1.4166495796596268, "percentage": 70.82, "elapsed_time": "2:30:04", "remaining_time": "1:01:50"}
+{"current_steps": 435, "total_steps": 610, "loss": 1.2755, "accuracy": 0.578125, "lr": 3.205828779599271e-07, "epoch": 1.4264916957145786, "percentage": 71.31, "elapsed_time": "2:31:10", "remaining_time": "1:00:48"}
+{"current_steps": 438, "total_steps": 610, "loss": 1.2495, "accuracy": 0.6145833730697632, "lr": 3.151183970856102e-07, "epoch": 1.4363338117695306, "percentage": 71.8, "elapsed_time": "2:32:14", "remaining_time": "0:59:47"}
+{"current_steps": 441, "total_steps": 610, "loss": 1.2574, "accuracy": 0.609375, "lr": 3.096539162112932e-07, "epoch": 1.4461759278244823, "percentage": 72.3, "elapsed_time": "2:33:17", "remaining_time": "0:58:44"}
+{"current_steps": 444, "total_steps": 610, "loss": 1.2465, "accuracy": 0.5833333730697632, "lr": 3.041894353369763e-07, "epoch": 1.4560180438794341, "percentage": 72.79, "elapsed_time": "2:34:20", "remaining_time": "0:57:42"}
+{"current_steps": 447, "total_steps": 610, "loss": 1.2547, "accuracy": 0.625, "lr": 2.987249544626594e-07, "epoch": 1.465860159934386, "percentage": 73.28, "elapsed_time": "2:35:20", "remaining_time": "0:56:38"}
+{"current_steps": 450, "total_steps": 610, "loss": 1.2274, "accuracy": 0.6770833730697632, "lr": 2.9326047358834246e-07, "epoch": 1.4757022759893377, "percentage": 73.77, "elapsed_time": "2:36:21", "remaining_time": "0:55:35"}
+{"current_steps": 453, "total_steps": 610, "loss": 1.2697, "accuracy": 0.6145833730697632, "lr": 2.8779599271402547e-07, "epoch": 1.4855443920442895, "percentage": 74.26, "elapsed_time": "2:37:24", "remaining_time": "0:54:33"}
+{"current_steps": 456, "total_steps": 610, "loss": 1.2448, "accuracy": 0.6354166865348816, "lr": 2.8233151183970854e-07, "epoch": 1.4953865080992412, "percentage": 74.75, "elapsed_time": "2:38:28", "remaining_time": "0:53:31"}
+{"current_steps": 459, "total_steps": 610, "loss": 1.2605, "accuracy": 0.59375, "lr": 2.768670309653916e-07, "epoch": 1.505228624154193, "percentage": 75.25, "elapsed_time": "2:39:30", "remaining_time": "0:52:28"}
+{"current_steps": 462, "total_steps": 610, "loss": 1.2382, "accuracy": 0.6458333730697632, "lr": 2.7140255009107467e-07, "epoch": 1.515070740209145, "percentage": 75.74, "elapsed_time": "2:40:30", "remaining_time": "0:51:25"}
+{"current_steps": 465, "total_steps": 610, "loss": 1.2622, "accuracy": 0.5885417461395264, "lr": 2.659380692167577e-07, "epoch": 1.5249128562640968, "percentage": 76.23, "elapsed_time": "2:41:35", "remaining_time": "0:50:23"}
+{"current_steps": 468, "total_steps": 610, "loss": 1.2494, "accuracy": 0.6197916865348816, "lr": 2.6047358834244075e-07, "epoch": 1.5347549723190486, "percentage": 76.72, "elapsed_time": "2:42:35", "remaining_time": "0:49:20"}
+{"current_steps": 471, "total_steps": 610, "loss": 1.2529, "accuracy": 0.6510416865348816, "lr": 2.5500910746812387e-07, "epoch": 1.5445970883740006, "percentage": 77.21, "elapsed_time": "2:43:35", "remaining_time": "0:48:16"}
+{"current_steps": 474, "total_steps": 610, "loss": 1.2651, "accuracy": 0.6041667461395264, "lr": 2.495446265938069e-07, "epoch": 1.5544392044289523, "percentage": 77.7, "elapsed_time": "2:44:37", "remaining_time": "0:47:14"}
+{"current_steps": 477, "total_steps": 610, "loss": 1.2272, "accuracy": 0.7135417461395264, "lr": 2.4408014571949e-07, "epoch": 1.5642813204839041, "percentage": 78.2, "elapsed_time": "2:45:39", "remaining_time": "0:46:11"}
+{"current_steps": 480, "total_steps": 610, "loss": 1.2564, "accuracy": 0.5833333730697632, "lr": 2.38615664845173e-07, "epoch": 1.574123436538856, "percentage": 78.69, "elapsed_time": "2:46:40", "remaining_time": "0:45:08"}
+{"current_steps": 483, "total_steps": 610, "loss": 1.2634, "accuracy": 0.609375, "lr": 2.3315118397085608e-07, "epoch": 1.5839655525938077, "percentage": 79.18, "elapsed_time": "2:47:41", "remaining_time": "0:44:05"}
+{"current_steps": 486, "total_steps": 610, "loss": 1.2617, "accuracy": 0.5572916865348816, "lr": 2.2768670309653915e-07, "epoch": 1.5938076686487594, "percentage": 79.67, "elapsed_time": "2:48:42", "remaining_time": "0:43:02"}
+{"current_steps": 489, "total_steps": 610, "loss": 1.2651, "accuracy": 0.6041666865348816, "lr": 2.222222222222222e-07, "epoch": 1.6036497847037112, "percentage": 80.16, "elapsed_time": "2:49:44", "remaining_time": "0:42:00"}
+{"current_steps": 492, "total_steps": 610, "loss": 1.2647, "accuracy": 0.5989583730697632, "lr": 2.1675774134790528e-07, "epoch": 1.613491900758663, "percentage": 80.66, "elapsed_time": "2:50:46", "remaining_time": "0:40:57"}
+{"current_steps": 495, "total_steps": 610, "loss": 1.256, "accuracy": 0.5520833730697632, "lr": 2.1129326047358833e-07, "epoch": 1.6233340168136148, "percentage": 81.15, "elapsed_time": "2:51:48", "remaining_time": "0:39:54"}
+{"current_steps": 498, "total_steps": 610, "loss": 1.251, "accuracy": 0.609375, "lr": 2.058287795992714e-07, "epoch": 1.6331761328685668, "percentage": 81.64, "elapsed_time": "2:52:53", "remaining_time": "0:38:52"}
+{"current_steps": 501, "total_steps": 610, "loss": 1.2428, "accuracy": 0.6406250596046448, "lr": 2.0036429872495443e-07, "epoch": 1.6430182489235186, "percentage": 82.13, "elapsed_time": "2:54:27", "remaining_time": "0:37:57"}
+{"current_steps": 504, "total_steps": 610, "loss": 1.251, "accuracy": 0.65625, "lr": 1.9489981785063753e-07, "epoch": 1.6528603649784703, "percentage": 82.62, "elapsed_time": "2:55:30", "remaining_time": "0:36:54"}
+{"current_steps": 507, "total_steps": 610, "loss": 1.2365, "accuracy": 0.65625, "lr": 1.894353369763206e-07, "epoch": 1.6627024810334223, "percentage": 83.11, "elapsed_time": "2:56:32", "remaining_time": "0:35:51"}
+{"current_steps": 510, "total_steps": 610, "loss": 1.2368, "accuracy": 0.6822916865348816, "lr": 1.8397085610200363e-07, "epoch": 1.672544597088374, "percentage": 83.61, "elapsed_time": "2:57:32", "remaining_time": "0:34:48"}
+{"current_steps": 513, "total_steps": 610, "loss": 1.2335, "accuracy": 0.6354166865348816, "lr": 1.785063752276867e-07, "epoch": 1.6823867131433259, "percentage": 84.1, "elapsed_time": "2:58:30", "remaining_time": "0:33:45"}
+{"current_steps": 516, "total_steps": 610, "loss": 1.2491, "accuracy": 0.6302083730697632, "lr": 1.7304189435336974e-07, "epoch": 1.6922288291982777, "percentage": 84.59, "elapsed_time": "2:59:30", "remaining_time": "0:32:42"}
+{"current_steps": 519, "total_steps": 610, "loss": 1.2456, "accuracy": 0.6302083730697632, "lr": 1.6757741347905283e-07, "epoch": 1.7020709452532294, "percentage": 85.08, "elapsed_time": "3:00:33", "remaining_time": "0:31:39"}
+{"current_steps": 522, "total_steps": 610, "loss": 1.2264, "accuracy": 0.6614583730697632, "lr": 1.6211293260473587e-07, "epoch": 1.7119130613081812, "percentage": 85.57, "elapsed_time": "3:01:36", "remaining_time": "0:30:36"}
+{"current_steps": 525, "total_steps": 610, "loss": 1.2491, "accuracy": 0.59375, "lr": 1.5664845173041894e-07, "epoch": 1.721755177363133, "percentage": 86.07, "elapsed_time": "3:02:40", "remaining_time": "0:29:34"}
+{"current_steps": 528, "total_steps": 610, "loss": 1.2527, "accuracy": 0.625, "lr": 1.5118397085610198e-07, "epoch": 1.7315972934180848, "percentage": 86.56, "elapsed_time": "3:03:40", "remaining_time": "0:28:31"}
+{"current_steps": 531, "total_steps": 610, "loss": 1.2394, "accuracy": 0.625, "lr": 1.4571948998178507e-07, "epoch": 1.7414394094730365, "percentage": 87.05, "elapsed_time": "3:04:40", "remaining_time": "0:27:28"}
+{"current_steps": 534, "total_steps": 610, "loss": 1.2462, "accuracy": 0.5833333730697632, "lr": 1.402550091074681e-07, "epoch": 1.7512815255279885, "percentage": 87.54, "elapsed_time": "3:05:41", "remaining_time": "0:26:25"}
+{"current_steps": 537, "total_steps": 610, "loss": 1.2462, "accuracy": 0.6041666865348816, "lr": 1.3479052823315118e-07, "epoch": 1.7611236415829403, "percentage": 88.03, "elapsed_time": "3:06:44", "remaining_time": "0:25:23"}
+{"current_steps": 540, "total_steps": 610, "loss": 1.2412, "accuracy": 0.6197916865348816, "lr": 1.2932604735883425e-07, "epoch": 1.770965757637892, "percentage": 88.52, "elapsed_time": "3:07:43", "remaining_time": "0:24:20"}
+{"current_steps": 543, "total_steps": 610, "loss": 1.2667, "accuracy": 0.5625000596046448, "lr": 1.238615664845173e-07, "epoch": 1.780807873692844, "percentage": 89.02, "elapsed_time": "3:08:41", "remaining_time": "0:23:16"}
+{"current_steps": 546, "total_steps": 610, "loss": 1.2437, "accuracy": 0.6614583730697632, "lr": 1.1839708561020035e-07, "epoch": 1.7906499897477959, "percentage": 89.51, "elapsed_time": "3:09:42", "remaining_time": "0:22:14"}
+{"current_steps": 549, "total_steps": 610, "loss": 1.2228, "accuracy": 0.6354166865348816, "lr": 1.1293260473588342e-07, "epoch": 1.8004921058027477, "percentage": 90.0, "elapsed_time": "3:10:47", "remaining_time": "0:21:11"}
+{"current_steps": 552, "total_steps": 610, "loss": 1.2546, "accuracy": 0.625, "lr": 1.0746812386156647e-07, "epoch": 1.8103342218576994, "percentage": 90.49, "elapsed_time": "3:11:48", "remaining_time": "0:20:09"}
+{"current_steps": 555, "total_steps": 610, "loss": 1.2515, "accuracy": 0.5833333730697632, "lr": 1.0200364298724954e-07, "epoch": 1.8201763379126512, "percentage": 90.98, "elapsed_time": "3:12:48", "remaining_time": "0:19:06"}
+{"current_steps": 558, "total_steps": 610, "loss": 1.2493, "accuracy": 0.625, "lr": 9.653916211293261e-08, "epoch": 1.830018453967603, "percentage": 91.48, "elapsed_time": "3:13:48", "remaining_time": "0:18:03"}
+{"current_steps": 561, "total_steps": 610, "loss": 1.2837, "accuracy": 0.5625, "lr": 9.107468123861566e-08, "epoch": 1.8398605700225548, "percentage": 91.97, "elapsed_time": "3:14:51", "remaining_time": "0:17:01"}
+{"current_steps": 564, "total_steps": 610, "loss": 1.2461, "accuracy": 0.59375, "lr": 8.561020036429873e-08, "epoch": 1.8497026860775065, "percentage": 92.46, "elapsed_time": "3:15:53", "remaining_time": "0:15:58"}
+{"current_steps": 567, "total_steps": 610, "loss": 1.2475, "accuracy": 0.6354166865348816, "lr": 8.014571948998178e-08, "epoch": 1.8595448021324583, "percentage": 92.95, "elapsed_time": "3:16:57", "remaining_time": "0:14:56"}
+{"current_steps": 570, "total_steps": 610, "loss": 1.2686, "accuracy": 0.5625, "lr": 7.468123861566485e-08, "epoch": 1.8693869181874103, "percentage": 93.44, "elapsed_time": "3:17:56", "remaining_time": "0:13:53"}
+{"current_steps": 573, "total_steps": 610, "loss": 1.2529, "accuracy": 0.6302083730697632, "lr": 6.92167577413479e-08, "epoch": 1.879229034242362, "percentage": 93.93, "elapsed_time": "3:18:57", "remaining_time": "0:12:50"}
+{"current_steps": 576, "total_steps": 610, "loss": 1.252, "accuracy": 0.640625, "lr": 6.375227686703097e-08, "epoch": 1.8890711502973139, "percentage": 94.43, "elapsed_time": "3:19:56", "remaining_time": "0:11:48"}
+{"current_steps": 579, "total_steps": 610, "loss": 1.2527, "accuracy": 0.6197916865348816, "lr": 5.828779599271402e-08, "epoch": 1.8989132663522659, "percentage": 94.92, "elapsed_time": "3:20:58", "remaining_time": "0:10:45"}
+{"current_steps": 582, "total_steps": 610, "loss": 1.2393, "accuracy": 0.6145833730697632, "lr": 5.282331511839708e-08, "epoch": 1.9087553824072176, "percentage": 95.41, "elapsed_time": "3:22:02", "remaining_time": "0:09:43"}
+{"current_steps": 585, "total_steps": 610, "loss": 1.255, "accuracy": 0.6197916865348816, "lr": 4.735883424408015e-08, "epoch": 1.9185974984621694, "percentage": 95.9, "elapsed_time": "3:23:03", "remaining_time": "0:08:40"}
+{"current_steps": 588, "total_steps": 610, "loss": 1.2431, "accuracy": 0.6197916865348816, "lr": 4.189435336976321e-08, "epoch": 1.9284396145171212, "percentage": 96.39, "elapsed_time": "3:24:05", "remaining_time": "0:07:38"}
+{"current_steps": 591, "total_steps": 610, "loss": 1.2665, "accuracy": 0.6093750596046448, "lr": 3.642987249544627e-08, "epoch": 1.938281730572073, "percentage": 96.89, "elapsed_time": "3:25:06", "remaining_time": "0:06:35"}
+{"current_steps": 594, "total_steps": 610, "loss": 1.2519, "accuracy": 0.640625, "lr": 3.096539162112933e-08, "epoch": 1.9481238466270248, "percentage": 97.38, "elapsed_time": "3:26:06", "remaining_time": "0:05:33"}
+{"current_steps": 597, "total_steps": 610, "loss": 1.2421, "accuracy": 0.5885416865348816, "lr": 2.5500910746812385e-08, "epoch": 1.9579659626819765, "percentage": 97.87, "elapsed_time": "3:27:07", "remaining_time": "0:04:30"}
+{"current_steps": 600, "total_steps": 610, "loss": 1.2421, "accuracy": 0.609375, "lr": 2.0036429872495445e-08, "epoch": 1.9678080787369283, "percentage": 98.36, "elapsed_time": "3:28:08", "remaining_time": "0:03:28"}
+{"current_steps": 603, "total_steps": 610, "loss": 1.2617, "accuracy": 0.5989583730697632, "lr": 1.4571948998178505e-08, "epoch": 1.97765019479188, "percentage": 98.85, "elapsed_time": "3:29:07", "remaining_time": "0:02:25"}
+{"current_steps": 606, "total_steps": 610, "loss": 1.2317, "accuracy": 0.6875, "lr": 9.107468123861567e-09, "epoch": 1.987492310846832, "percentage": 99.34, "elapsed_time": "3:30:09", "remaining_time": "0:01:23"}
+{"current_steps": 609, "total_steps": 610, "loss": 1.2608, "accuracy": 0.5989583730697632, "lr": 3.6429872495446263e-09, "epoch": 1.9973344269017839, "percentage": 99.84, "elapsed_time": "3:31:11", "remaining_time": "0:00:20"}
+{"current_steps": 610, "total_steps": 610, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "3:31:55", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a78a0cd678db97330ca9182786af94fd33fe4ae4e3ad956aab7c2f3f55a5041
+size 8145