Upload freeze-trained Qwen2.5-Coder for sentiment analysis

.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

added_tokens.json

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

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "float32",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.56.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.56.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b84c1776b96fdc04a9a648e55b2bde79293a23c671af877b9dbdcb945e1e93a0
+size 4115926608

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c41b737926bcae8264188fa0e65142c3e89866d4ab4226434d62b5752f01dc4
+size 4113939083

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c09a2378c9b2760c4be147a5b754dcc709d51c34ad1657c58d394fdb1e62c9cd
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de8fd08632edd3161dcf8212884a3eaa1f82041c675a3124a3e56be0cf052979
+size 1465

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,386 @@
+{
+  "best_global_step": 350,
+  "best_metric": 0.9981072077528771,
+  "best_model_checkpoint": "saves/qwen2_5-coder-1.5b/freeze/sft/checkpoint-200",
+  "epoch": 0.48470160557406844,
+  "eval_steps": 50,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012117540139351712,
+      "grad_norm": 1.1778391599655151,
+      "learning_rate": 1.0843373493975905e-06,
+      "loss": 0.0668,
+      "step": 10
+    },
+    {
+      "epoch": 0.024235080278703424,
+      "grad_norm": 0.807381808757782,
+      "learning_rate": 2.2891566265060243e-06,
+      "loss": 0.0256,
+      "step": 20
+    },
+    {
+      "epoch": 0.036352620418055134,
+      "grad_norm": 0.5498034954071045,
+      "learning_rate": 3.4939759036144583e-06,
+      "loss": 0.0519,
+      "step": 30
+    },
+    {
+      "epoch": 0.04847016055740685,
+      "grad_norm": 1.5650098323822021,
+      "learning_rate": 4.698795180722892e-06,
+      "loss": 0.0133,
+      "step": 40
+    },
+    {
+      "epoch": 0.060587700696758555,
+      "grad_norm": 2.43689227104187,
+      "learning_rate": 5.9036144578313255e-06,
+      "loss": 0.0147,
+      "step": 50
+    },
+    {
+      "epoch": 0.060587700696758555,
+      "eval_accuracy": 0.9958737129012719,
+      "eval_loss": 0.014296969398856163,
+      "eval_runtime": 528.9314,
+      "eval_samples_per_second": 3.121,
+      "eval_steps_per_second": 3.121,
+      "step": 50
+    },
+    {
+      "epoch": 0.07270524083611027,
+      "grad_norm": 0.7519652247428894,
+      "learning_rate": 7.1084337349397595e-06,
+      "loss": 0.0091,
+      "step": 60
+    },
+    {
+      "epoch": 0.08482278097546198,
+      "grad_norm": 0.13313020765781403,
+      "learning_rate": 8.313253012048194e-06,
+      "loss": 0.0072,
+      "step": 70
+    },
+    {
+      "epoch": 0.0969403211148137,
+      "grad_norm": 1.2990883588790894,
+      "learning_rate": 9.518072289156628e-06,
+      "loss": 0.0065,
+      "step": 80
+    },
+    {
+      "epoch": 0.1090578612541654,
+      "grad_norm": 3.4033000469207764,
+      "learning_rate": 1.0722891566265062e-05,
+      "loss": 0.0178,
+      "step": 90
+    },
+    {
+      "epoch": 0.12117540139351711,
+      "grad_norm": 1.2542734146118164,
+      "learning_rate": 1.1927710843373494e-05,
+      "loss": 0.0081,
+      "step": 100
+    },
+    {
+      "epoch": 0.12117540139351711,
+      "eval_accuracy": 0.996290127195639,
+      "eval_loss": 0.013640574179589748,
+      "eval_runtime": 528.0812,
+      "eval_samples_per_second": 3.126,
+      "eval_steps_per_second": 3.126,
+      "step": 100
+    },
+    {
+      "epoch": 0.13329294153286883,
+      "grad_norm": 0.1944456845521927,
+      "learning_rate": 1.3132530120481928e-05,
+      "loss": 0.0109,
+      "step": 110
+    },
+    {
+      "epoch": 0.14541048167222054,
+      "grad_norm": 0.07844550907611847,
+      "learning_rate": 1.4337349397590364e-05,
+      "loss": 0.0074,
+      "step": 120
+    },
+    {
+      "epoch": 0.15752802181157224,
+      "grad_norm": 1.4879134893417358,
+      "learning_rate": 1.5542168674698796e-05,
+      "loss": 0.0138,
+      "step": 130
+    },
+    {
+      "epoch": 0.16964556195092395,
+      "grad_norm": 0.02974073402583599,
+      "learning_rate": 1.6746987951807228e-05,
+      "loss": 0.0054,
+      "step": 140
+    },
+    {
+      "epoch": 0.18176310209027569,
+      "grad_norm": 1.4775711297988892,
+      "learning_rate": 1.7951807228915664e-05,
+      "loss": 0.0301,
+      "step": 150
+    },
+    {
+      "epoch": 0.18176310209027569,
+      "eval_accuracy": 0.9965172622652938,
+      "eval_loss": 0.012703897431492805,
+      "eval_runtime": 528.1973,
+      "eval_samples_per_second": 3.126,
+      "eval_steps_per_second": 3.126,
+      "step": 150
+    },
+    {
+      "epoch": 0.1938806422296274,
+      "grad_norm": 0.1594158411026001,
+      "learning_rate": 1.91566265060241e-05,
+      "loss": 0.0099,
+      "step": 160
+    },
+    {
+      "epoch": 0.2059981823689791,
+      "grad_norm": 0.12540395557880402,
+      "learning_rate": 1.9999798871699227e-05,
+      "loss": 0.0072,
+      "step": 170
+    },
+    {
+      "epoch": 0.2181157225083308,
+      "grad_norm": 0.7899434566497803,
+      "learning_rate": 1.9996223482528378e-05,
+      "loss": 0.0125,
+      "step": 180
+    },
+    {
+      "epoch": 0.2302332626476825,
+      "grad_norm": 6.3130903244018555,
+      "learning_rate": 1.9988180414914266e-05,
+      "loss": 0.0198,
+      "step": 190
+    },
+    {
+      "epoch": 0.24235080278703422,
+      "grad_norm": 0.9658088684082031,
+      "learning_rate": 1.997567326359842e-05,
+      "loss": 0.0106,
+      "step": 200
+    },
+    {
+      "epoch": 0.24235080278703422,
+      "eval_accuracy": 0.997198667474258,
+      "eval_loss": 0.013726573437452316,
+      "eval_runtime": 528.9048,
+      "eval_samples_per_second": 3.122,
+      "eval_steps_per_second": 3.122,
+      "step": 200
+    },
+    {
+      "epoch": 0.2544683429263859,
+      "grad_norm": 0.9940381646156311,
+      "learning_rate": 1.995870761848492e-05,
+      "loss": 0.0155,
+      "step": 210
+    },
+    {
+      "epoch": 0.26658588306573766,
+      "grad_norm": 0.3996841013431549,
+      "learning_rate": 1.993729106214203e-05,
+      "loss": 0.0041,
+      "step": 220
+    },
+    {
+      "epoch": 0.27870342320508934,
+      "grad_norm": 0.31791451573371887,
+      "learning_rate": 1.9911433166413277e-05,
+      "loss": 0.004,
+      "step": 230
+    },
+    {
+      "epoch": 0.2908209633444411,
+      "grad_norm": 0.010878289118409157,
+      "learning_rate": 1.988114548813946e-05,
+      "loss": 0.0044,
+      "step": 240
+    },
+    {
+      "epoch": 0.3029385034837928,
+      "grad_norm": 0.741184413433075,
+      "learning_rate": 1.9846441563993465e-05,
+      "loss": 0.0567,
+      "step": 250
+    },
+    {
+      "epoch": 0.3029385034837928,
+      "eval_accuracy": 0.9970472440944882,
+      "eval_loss": 0.010016725398600101,
+      "eval_runtime": 527.5691,
+      "eval_samples_per_second": 3.129,
+      "eval_steps_per_second": 3.129,
+      "step": 250
+    },
+    {
+      "epoch": 0.3150560436231445,
+      "grad_norm": 1.0590384006500244,
+      "learning_rate": 1.980733690443021e-05,
+      "loss": 0.0121,
+      "step": 260
+    },
+    {
+      "epoch": 0.3271735837624962,
+      "grad_norm": 0.07605874538421631,
+      "learning_rate": 1.9763848986754495e-05,
+      "loss": 0.0072,
+      "step": 270
+    },
+    {
+      "epoch": 0.3392911239018479,
+      "grad_norm": 1.010120153427124,
+      "learning_rate": 1.971599724730972e-05,
+      "loss": 0.0078,
+      "step": 280
+    },
+    {
+      "epoch": 0.35140866404119964,
+      "grad_norm": 0.3639002740383148,
+      "learning_rate": 1.966380307279109e-05,
+      "loss": 0.0169,
+      "step": 290
+    },
+    {
+      "epoch": 0.36352620418055137,
+      "grad_norm": 0.0576571561396122,
+      "learning_rate": 1.9607289790687104e-05,
+      "loss": 0.0062,
+      "step": 300
+    },
+    {
+      "epoch": 0.36352620418055137,
+      "eval_accuracy": 0.9971608116293156,
+      "eval_loss": 0.009564626030623913,
+      "eval_runtime": 528.2806,
+      "eval_samples_per_second": 3.125,
+      "eval_steps_per_second": 3.125,
+      "step": 300
+    },
+    {
+      "epoch": 0.37564374431990305,
+      "grad_norm": 0.06373932957649231,
+      "learning_rate": 1.954648265885366e-05,
+      "loss": 0.0176,
+      "step": 310
+    },
+    {
+      "epoch": 0.3877612844592548,
+      "grad_norm": 0.22646072506904602,
+      "learning_rate": 1.948140885422538e-05,
+      "loss": 0.0042,
+      "step": 320
+    },
+    {
+      "epoch": 0.39987882459860646,
+      "grad_norm": 0.009251746349036694,
+      "learning_rate": 1.9412097460669258e-05,
+      "loss": 0.002,
+      "step": 330
+    },
+    {
+      "epoch": 0.4119963647379582,
+      "grad_norm": 0.04042113944888115,
+      "learning_rate": 1.9338579455986e-05,
+      "loss": 0.0083,
+      "step": 340
+    },
+    {
+      "epoch": 0.42411390487730993,
+      "grad_norm": 0.2013320028781891,
+      "learning_rate": 1.9260887698064912e-05,
+      "loss": 0.0078,
+      "step": 350
+    },
+    {
+      "epoch": 0.42411390487730993,
+      "eval_accuracy": 0.9981072077528771,
+      "eval_loss": 0.006962946616113186,
+      "eval_runtime": 527.8415,
+      "eval_samples_per_second": 3.128,
+      "eval_steps_per_second": 3.128,
+      "step": 350
+    },
+    {
+      "epoch": 0.4362314450166616,
+      "grad_norm": 0.06966914236545563,
+      "learning_rate": 1.9179056910198515e-05,
+      "loss": 0.0072,
+      "step": 360
+    },
+    {
+      "epoch": 0.44834898515601335,
+      "grad_norm": 0.25409865379333496,
+      "learning_rate": 1.9093123665563434e-05,
+      "loss": 0.006,
+      "step": 370
+    },
+    {
+      "epoch": 0.460466525295365,
+      "grad_norm": 0.8325411081314087,
+      "learning_rate": 1.9003126370874493e-05,
+      "loss": 0.0105,
+      "step": 380
+    },
+    {
+      "epoch": 0.47258406543471676,
+      "grad_norm": 0.9408934116363525,
+      "learning_rate": 1.8909105249219345e-05,
+      "loss": 0.0096,
+      "step": 390
+    },
+    {
+      "epoch": 0.48470160557406844,
+      "grad_norm": 0.14342345297336578,
+      "learning_rate": 1.881110232208133e-05,
+      "loss": 0.0085,
+      "step": 400
+    },
+    {
+      "epoch": 0.48470160557406844,
+      "eval_accuracy": 0.9978800726832223,
+      "eval_loss": 0.006634953897446394,
+      "eval_runtime": 528.8373,
+      "eval_samples_per_second": 3.122,
+      "eval_steps_per_second": 3.122,
+      "step": 400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1652,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5031896623767552.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6d569d6eddc1d7b61818847db3afd10de061af8df1c3170513d8437d76a048e
+size 6161