Upload 16 files

.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
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-0.5B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.49.0"
+}

main.py

@@ -0,0 +1,24 @@
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+model_path = "./Path-to-llm-folder"
+
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForCausalLM.from_pretrained(model_path)
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model.to(device)
+
+def generate_text(prompt, max_length=2000):
+    inputs = tokenizer(prompt, return_tensors="pt").to(device)  
+    output = model.generate(
+        **inputs, 
+        do_sample=True, 
+        temperature=0.7
+    )
+    return tokenizer.decode(output[0], skip_special_tokens=True)
+
+prompt = "Write a code in react for calling api to server at https://example.com/test"
+generated_text = generate_text(prompt)
+
+print(generated_text)

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac65ca279281cf744fb4668c6c824ee5aa85a4c0f5e102fb03eb9ae801ccd727
+size 1976163472

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce3891f5630d76ca40928cc31f3aecab9dfb868b998f2acda96f7bff9078cf30
+size 3952505274

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95b6047bd8cc6f4cdf7c46dea47edb8e542435510070c6cd1e0a7d9ccf5fd7da
+size 14244

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9710f568b59aba2846ca4ef568d997abfab62e884f5f4524a6561eb514a981e
+size 988

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61effe5a5a556d42bd8f2f6a98f8f6bc989ee943d8307697de4a78bae8f1175e
+size 1064

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

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

trainer_state.json

@@ -0,0 +1,565 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 7662,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07830853563038372,
+      "grad_norm": 9.886259078979492,
+      "learning_rate": 9.874706342991386e-05,
+      "loss": 2.2961,
+      "step": 100
+    },
+    {
+      "epoch": 0.15661707126076743,
+      "grad_norm": 9.754347801208496,
+      "learning_rate": 9.744192116940747e-05,
+      "loss": 2.1652,
+      "step": 200
+    },
+    {
+      "epoch": 0.23492560689115113,
+      "grad_norm": 10.011685371398926,
+      "learning_rate": 9.613677890890107e-05,
+      "loss": 2.2701,
+      "step": 300
+    },
+    {
+      "epoch": 0.31323414252153486,
+      "grad_norm": 10.389019966125488,
+      "learning_rate": 9.483163664839469e-05,
+      "loss": 2.1357,
+      "step": 400
+    },
+    {
+      "epoch": 0.39154267815191857,
+      "grad_norm": 8.717257499694824,
+      "learning_rate": 9.352649438788829e-05,
+      "loss": 2.0979,
+      "step": 500
+    },
+    {
+      "epoch": 0.46985121378230227,
+      "grad_norm": 10.2243070602417,
+      "learning_rate": 9.222135212738188e-05,
+      "loss": 2.0926,
+      "step": 600
+    },
+    {
+      "epoch": 0.548159749412686,
+      "grad_norm": 9.24715518951416,
+      "learning_rate": 9.091620986687549e-05,
+      "loss": 2.0199,
+      "step": 700
+    },
+    {
+      "epoch": 0.6264682850430697,
+      "grad_norm": 8.67659854888916,
+      "learning_rate": 8.96110676063691e-05,
+      "loss": 2.071,
+      "step": 800
+    },
+    {
+      "epoch": 0.7047768206734534,
+      "grad_norm": 6.2473015785217285,
+      "learning_rate": 8.830592534586271e-05,
+      "loss": 2.0342,
+      "step": 900
+    },
+    {
+      "epoch": 0.7830853563038371,
+      "grad_norm": 9.428214073181152,
+      "learning_rate": 8.700078308535631e-05,
+      "loss": 1.9497,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8613938919342208,
+      "grad_norm": 7.909013271331787,
+      "learning_rate": 8.569564082484992e-05,
+      "loss": 2.006,
+      "step": 1100
+    },
+    {
+      "epoch": 0.9397024275646045,
+      "grad_norm": 7.305349826812744,
+      "learning_rate": 8.43904985643435e-05,
+      "loss": 1.9751,
+      "step": 1200
+    },
+    {
+      "epoch": 1.0180109631949883,
+      "grad_norm": 6.404293060302734,
+      "learning_rate": 8.308535630383712e-05,
+      "loss": 1.7841,
+      "step": 1300
+    },
+    {
+      "epoch": 1.096319498825372,
+      "grad_norm": 6.121842384338379,
+      "learning_rate": 8.178021404333073e-05,
+      "loss": 1.2646,
+      "step": 1400
+    },
+    {
+      "epoch": 1.1746280344557556,
+      "grad_norm": 5.871735572814941,
+      "learning_rate": 8.047507178282433e-05,
+      "loss": 1.2666,
+      "step": 1500
+    },
+    {
+      "epoch": 1.2529365700861395,
+      "grad_norm": 6.930913925170898,
+      "learning_rate": 7.916992952231794e-05,
+      "loss": 1.295,
+      "step": 1600
+    },
+    {
+      "epoch": 1.331245105716523,
+      "grad_norm": 5.334323406219482,
+      "learning_rate": 7.786478726181154e-05,
+      "loss": 1.3333,
+      "step": 1700
+    },
+    {
+      "epoch": 1.4095536413469067,
+      "grad_norm": 7.161041259765625,
+      "learning_rate": 7.655964500130514e-05,
+      "loss": 1.3355,
+      "step": 1800
+    },
+    {
+      "epoch": 1.4878621769772904,
+      "grad_norm": 7.43231725692749,
+      "learning_rate": 7.525450274079875e-05,
+      "loss": 1.284,
+      "step": 1900
+    },
+    {
+      "epoch": 1.5661707126076743,
+      "grad_norm": 6.2656354904174805,
+      "learning_rate": 7.394936048029235e-05,
+      "loss": 1.287,
+      "step": 2000
+    },
+    {
+      "epoch": 1.644479248238058,
+      "grad_norm": 5.97381067276001,
+      "learning_rate": 7.264421821978597e-05,
+      "loss": 1.3196,
+      "step": 2100
+    },
+    {
+      "epoch": 1.7227877838684416,
+      "grad_norm": 7.828345775604248,
+      "learning_rate": 7.133907595927957e-05,
+      "loss": 1.2884,
+      "step": 2200
+    },
+    {
+      "epoch": 1.8010963194988254,
+      "grad_norm": 7.866464614868164,
+      "learning_rate": 7.003393369877316e-05,
+      "loss": 1.3136,
+      "step": 2300
+    },
+    {
+      "epoch": 1.879404855129209,
+      "grad_norm": 5.8095598220825195,
+      "learning_rate": 6.872879143826677e-05,
+      "loss": 1.2181,
+      "step": 2400
+    },
+    {
+      "epoch": 1.9577133907595927,
+      "grad_norm": 6.666238784790039,
+      "learning_rate": 6.742364917776038e-05,
+      "loss": 1.2461,
+      "step": 2500
+    },
+    {
+      "epoch": 2.0360219263899766,
+      "grad_norm": 7.129757881164551,
+      "learning_rate": 6.611850691725399e-05,
+      "loss": 0.9798,
+      "step": 2600
+    },
+    {
+      "epoch": 2.11433046202036,
+      "grad_norm": 6.111073017120361,
+      "learning_rate": 6.481336465674759e-05,
+      "loss": 0.6804,
+      "step": 2700
+    },
+    {
+      "epoch": 2.192638997650744,
+      "grad_norm": 5.344665050506592,
+      "learning_rate": 6.35082223962412e-05,
+      "loss": 0.6946,
+      "step": 2800
+    },
+    {
+      "epoch": 2.2709475332811278,
+      "grad_norm": 5.611790657043457,
+      "learning_rate": 6.220308013573479e-05,
+      "loss": 0.6516,
+      "step": 2900
+    },
+    {
+      "epoch": 2.349256068911511,
+      "grad_norm": 7.892216682434082,
+      "learning_rate": 6.0897937875228404e-05,
+      "loss": 0.6718,
+      "step": 3000
+    },
+    {
+      "epoch": 2.427564604541895,
+      "grad_norm": 8.479430198669434,
+      "learning_rate": 5.959279561472201e-05,
+      "loss": 0.6601,
+      "step": 3100
+    },
+    {
+      "epoch": 2.505873140172279,
+      "grad_norm": 6.140246391296387,
+      "learning_rate": 5.828765335421561e-05,
+      "loss": 0.6619,
+      "step": 3200
+    },
+    {
+      "epoch": 2.5841816758026623,
+      "grad_norm": 6.076893329620361,
+      "learning_rate": 5.6982511093709215e-05,
+      "loss": 0.69,
+      "step": 3300
+    },
+    {
+      "epoch": 2.662490211433046,
+      "grad_norm": 6.6155900955200195,
+      "learning_rate": 5.5677368833202826e-05,
+      "loss": 0.6866,
+      "step": 3400
+    },
+    {
+      "epoch": 2.74079874706343,
+      "grad_norm": 6.685502052307129,
+      "learning_rate": 5.437222657269643e-05,
+      "loss": 0.6615,
+      "step": 3500
+    },
+    {
+      "epoch": 2.8191072826938135,
+      "grad_norm": 8.586551666259766,
+      "learning_rate": 5.306708431219003e-05,
+      "loss": 0.7118,
+      "step": 3600
+    },
+    {
+      "epoch": 2.8974158183241974,
+      "grad_norm": 5.001748085021973,
+      "learning_rate": 5.176194205168363e-05,
+      "loss": 0.7117,
+      "step": 3700
+    },
+    {
+      "epoch": 2.975724353954581,
+      "grad_norm": 5.666826248168945,
+      "learning_rate": 5.045679979117724e-05,
+      "loss": 0.6868,
+      "step": 3800
+    },
+    {
+      "epoch": 3.0540328895849647,
+      "grad_norm": 5.463041305541992,
+      "learning_rate": 4.9151657530670846e-05,
+      "loss": 0.4208,
+      "step": 3900
+    },
+    {
+      "epoch": 3.1323414252153485,
+      "grad_norm": 6.563859939575195,
+      "learning_rate": 4.784651527016445e-05,
+      "loss": 0.2744,
+      "step": 4000
+    },
+    {
+      "epoch": 3.210649960845732,
+      "grad_norm": 5.918147087097168,
+      "learning_rate": 4.654137300965806e-05,
+      "loss": 0.309,
+      "step": 4100
+    },
+    {
+      "epoch": 3.288958496476116,
+      "grad_norm": 4.2588958740234375,
+      "learning_rate": 4.523623074915166e-05,
+      "loss": 0.3063,
+      "step": 4200
+    },
+    {
+      "epoch": 3.3672670321064997,
+      "grad_norm": 5.194436073303223,
+      "learning_rate": 4.393108848864527e-05,
+      "loss": 0.3002,
+      "step": 4300
+    },
+    {
+      "epoch": 3.445575567736883,
+      "grad_norm": 4.340348720550537,
+      "learning_rate": 4.262594622813887e-05,
+      "loss": 0.2957,
+      "step": 4400
+    },
+    {
+      "epoch": 3.523884103367267,
+      "grad_norm": 3.6878747940063477,
+      "learning_rate": 4.1320803967632476e-05,
+      "loss": 0.2968,
+      "step": 4500
+    },
+    {
+      "epoch": 3.602192638997651,
+      "grad_norm": 4.565743923187256,
+      "learning_rate": 4.001566170712608e-05,
+      "loss": 0.2921,
+      "step": 4600
+    },
+    {
+      "epoch": 3.6805011746280343,
+      "grad_norm": 4.834578514099121,
+      "learning_rate": 3.8710519446619684e-05,
+      "loss": 0.2937,
+      "step": 4700
+    },
+    {
+      "epoch": 3.758809710258418,
+      "grad_norm": 4.321404933929443,
+      "learning_rate": 3.740537718611329e-05,
+      "loss": 0.2927,
+      "step": 4800
+    },
+    {
+      "epoch": 3.837118245888802,
+      "grad_norm": 5.987460136413574,
+      "learning_rate": 3.610023492560689e-05,
+      "loss": 0.2813,
+      "step": 4900
+    },
+    {
+      "epoch": 3.9154267815191854,
+      "grad_norm": 4.690079689025879,
+      "learning_rate": 3.4795092665100495e-05,
+      "loss": 0.2848,
+      "step": 5000
+    },
+    {
+      "epoch": 3.9937353171495693,
+      "grad_norm": 4.9851298332214355,
+      "learning_rate": 3.34899504045941e-05,
+      "loss": 0.2776,
+      "step": 5100
+    },
+    {
+      "epoch": 4.072043852779953,
+      "grad_norm": 4.890774726867676,
+      "learning_rate": 3.218480814408771e-05,
+      "loss": 0.1309,
+      "step": 5200
+    },
+    {
+      "epoch": 4.150352388410337,
+      "grad_norm": 3.3844189643859863,
+      "learning_rate": 3.087966588358131e-05,
+      "loss": 0.1197,
+      "step": 5300
+    },
+    {
+      "epoch": 4.22866092404072,
+      "grad_norm": 3.3200528621673584,
+      "learning_rate": 2.9574523623074918e-05,
+      "loss": 0.1252,
+      "step": 5400
+    },
+    {
+      "epoch": 4.306969459671104,
+      "grad_norm": 2.3074514865875244,
+      "learning_rate": 2.826938136256852e-05,
+      "loss": 0.1181,
+      "step": 5500
+    },
+    {
+      "epoch": 4.385277995301488,
+      "grad_norm": 4.1699724197387695,
+      "learning_rate": 2.696423910206213e-05,
+      "loss": 0.1234,
+      "step": 5600
+    },
+    {
+      "epoch": 4.463586530931871,
+      "grad_norm": 3.833683729171753,
+      "learning_rate": 2.565909684155573e-05,
+      "loss": 0.1161,
+      "step": 5700
+    },
+    {
+      "epoch": 4.5418950665622555,
+      "grad_norm": 2.7541275024414062,
+      "learning_rate": 2.4353954581049333e-05,
+      "loss": 0.1101,
+      "step": 5800
+    },
+    {
+      "epoch": 4.620203602192639,
+      "grad_norm": 4.193445205688477,
+      "learning_rate": 2.304881232054294e-05,
+      "loss": 0.1118,
+      "step": 5900
+    },
+    {
+      "epoch": 4.698512137823022,
+      "grad_norm": 3.851712465286255,
+      "learning_rate": 2.1743670060036544e-05,
+      "loss": 0.1144,
+      "step": 6000
+    },
+    {
+      "epoch": 4.776820673453407,
+      "grad_norm": 3.333712100982666,
+      "learning_rate": 2.043852779953015e-05,
+      "loss": 0.1117,
+      "step": 6100
+    },
+    {
+      "epoch": 4.85512920908379,
+      "grad_norm": 3.7569446563720703,
+      "learning_rate": 1.9133385539023756e-05,
+      "loss": 0.1049,
+      "step": 6200
+    },
+    {
+      "epoch": 4.9334377447141735,
+      "grad_norm": 3.2152910232543945,
+      "learning_rate": 1.782824327851736e-05,
+      "loss": 0.1064,
+      "step": 6300
+    },
+    {
+      "epoch": 5.011746280344558,
+      "grad_norm": 1.593434453010559,
+      "learning_rate": 1.6523101018010963e-05,
+      "loss": 0.0936,
+      "step": 6400
+    },
+    {
+      "epoch": 5.090054815974941,
+      "grad_norm": 1.8612021207809448,
+      "learning_rate": 1.5217958757504569e-05,
+      "loss": 0.047,
+      "step": 6500
+    },
+    {
+      "epoch": 5.168363351605325,
+      "grad_norm": 2.482856035232544,
+      "learning_rate": 1.3912816496998175e-05,
+      "loss": 0.0448,
+      "step": 6600
+    },
+    {
+      "epoch": 5.246671887235709,
+      "grad_norm": 1.4229090213775635,
+      "learning_rate": 1.2607674236491779e-05,
+      "loss": 0.044,
+      "step": 6700
+    },
+    {
+      "epoch": 5.324980422866092,
+      "grad_norm": 1.7034039497375488,
+      "learning_rate": 1.1302531975985382e-05,
+      "loss": 0.0459,
+      "step": 6800
+    },
+    {
+      "epoch": 5.403288958496476,
+      "grad_norm": 2.2560577392578125,
+      "learning_rate": 9.997389715478986e-06,
+      "loss": 0.0453,
+      "step": 6900
+    },
+    {
+      "epoch": 5.48159749412686,
+      "grad_norm": 2.826206922531128,
+      "learning_rate": 8.692247454972592e-06,
+      "loss": 0.0439,
+      "step": 7000
+    },
+    {
+      "epoch": 5.559906029757244,
+      "grad_norm": 1.7038235664367676,
+      "learning_rate": 7.387105194466197e-06,
+      "loss": 0.0421,
+      "step": 7100
+    },
+    {
+      "epoch": 5.638214565387627,
+      "grad_norm": 2.713496685028076,
+      "learning_rate": 6.081962933959802e-06,
+      "loss": 0.0417,
+      "step": 7200
+    },
+    {
+      "epoch": 5.716523101018011,
+      "grad_norm": 0.9614657163619995,
+      "learning_rate": 4.776820673453407e-06,
+      "loss": 0.0403,
+      "step": 7300
+    },
+    {
+      "epoch": 5.794831636648395,
+      "grad_norm": 1.6873942613601685,
+      "learning_rate": 3.471678412947011e-06,
+      "loss": 0.0407,
+      "step": 7400
+    },
+    {
+      "epoch": 5.873140172278778,
+      "grad_norm": 2.548095464706421,
+      "learning_rate": 2.166536152440616e-06,
+      "loss": 0.0397,
+      "step": 7500
+    },
+    {
+      "epoch": 5.9514487079091625,
+      "grad_norm": 1.1459206342697144,
+      "learning_rate": 8.613938919342209e-07,
+      "loss": 0.0366,
+      "step": 7600
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 7662,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8424085506490368.0,
+  "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 sha256:4664b8c7a0f79707f74e0aadf4dd8746c525027955e7321ade9815f3f41f1407
+size 5304