Upload checkpoint 100

Browse files

Files changed (15) hide show

.gitattributes +1 -0
README.md +47 -0
adapter_config.json +37 -0
adapter_model.safetensors +3 -0
added_tokens.json +24 -0
merges.txt +0 -0
optimizer.pt +3 -0
rng_state.pth +3 -0
scheduler.pt +3 -0
special_tokens_map.json +31 -0
tokenizer.json +3 -0
tokenizer_config.json +209 -0
trainer_state.json +734 -0
training_args.bin +3 -0
vocab.json +0 -0

.gitattributes CHANGED Viewed

@@ -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

 *.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 ADDED Viewed

	@@ -0,0 +1,47 @@

+---
+base_model: Qwen/Qwen2.5-3B-Instruct
+library_name: peft
+---
+# Gradience T1 3B (Step 100 Checkpoint)
+> [!NOTE]
+> Training in progress...
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <title>Progress Bar Example</title>
+    <style>
+        .progress-container {
+            width: 100%;
+            background-color: #e0e0e0;
+            border-radius: 25px;
+            overflow: hidden;
+            margin: 20px 0;
+        }
+        .progress-bar {
+            height: 30px;
+            width: 0;
+            background-color: #76c7c0;
+            text-align: center;
+            line-height: 30px;
+            color: white;
+            border-radius: 25px 0 0 25px;
+        }
+        .progress-text {
+            margin-top: 10px;
+            font-size: 16px;
+            font-family: Arial, sans-serif;
+        }
+    </style>
+</head>
+<body>
+<div style="width: 100%; background-color: #e0e0e0; border-radius: 25px; overflow: hidden; margin: 20px 0;">
+  <div style="height: 30px; width: 1.02%; background-color: #76c7c0; text-align: center; line-height: 30px; color: white; border-radius: 25px 0 0 25px;">
+    <!--  3.75% -->
+  </div>
+</div>
+<p style="font-family: Arial, sans-serif; font-size: 16px;">Progress: 100 out of 9838 steps</p>
+</body>
+</html>

adapter_config.json ADDED Viewed

	@@ -0,0 +1,37 @@

+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./Qwen-2.5-3B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:cbe0d5204ad703858d6dc2f9688b3bb2e4fbbcedaba0a3c27b72a5570b5acab2
+size 119801528

added_tokens.json ADDED Viewed

	@@ -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
+}

merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9f1ad7ad21247de632121e3e41ff8503ee5aeacd755cf1a5fdfad7f2169bdf3e
+size 61392180

rng_state.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:608fccb6c056ce88cdfd5355e6be2046f4d107a24a87c6b0d2c3b200ce6bb4ea
+size 14244

scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:7207e79ddf7718cfb8207e0ab325278ab33535994128d175a03a7d30940317c9
+size 1064

special_tokens_map.json ADDED Viewed

	@@ -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 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,209 @@

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

	@@ -0,0 +1,734 @@

+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.020329335230737954,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00020329335230737954,
+      "grad_norm": 0.36621615290641785,
+      "learning_rate": 0.0,
+      "loss": 1.5428,
+      "step": 1
+    },
+    {
+      "epoch": 0.0004065867046147591,
+      "grad_norm": 0.38205745816230774,
+      "learning_rate": 4e-05,
+      "loss": 1.3117,
+      "step": 2
+    },
+    {
+      "epoch": 0.0006098800569221387,
+      "grad_norm": 0.38206785917282104,
+      "learning_rate": 8e-05,
+      "loss": 1.5818,
+      "step": 3
+    },
+    {
+      "epoch": 0.0008131734092295182,
+      "grad_norm": 0.2856779396533966,
+      "learning_rate": 0.00012,
+      "loss": 1.4046,
+      "step": 4
+    },
+    {
+      "epoch": 0.0010164667615368977,
+      "grad_norm": 0.28240150213241577,
+      "learning_rate": 0.00016,
+      "loss": 1.1899,
+      "step": 5
+    },
+    {
+      "epoch": 0.0012197601138442774,
+      "grad_norm": 0.27537214756011963,
+      "learning_rate": 0.0002,
+      "loss": 1.3741,
+      "step": 6
+    },
+    {
+      "epoch": 0.0014230534661516568,
+      "grad_norm": 0.1832859218120575,
+      "learning_rate": 0.00019997966032746873,
+      "loss": 1.2432,
+      "step": 7
+    },
+    {
+      "epoch": 0.0016263468184590363,
+      "grad_norm": 0.1194186806678772,
+      "learning_rate": 0.00019995932065493746,
+      "loss": 1.1152,
+      "step": 8
+    },
+    {
+      "epoch": 0.001829640170766416,
+      "grad_norm": 0.287241131067276,
+      "learning_rate": 0.0001999389809824062,
+      "loss": 1.2556,
+      "step": 9
+    },
+    {
+      "epoch": 0.0020329335230737954,
+      "grad_norm": 0.2129606008529663,
+      "learning_rate": 0.00019991864130987493,
+      "loss": 1.2698,
+      "step": 10
+    },
+    {
+      "epoch": 0.002236226875381175,
+      "grad_norm": 0.16557097434997559,
+      "learning_rate": 0.00019989830163734363,
+      "loss": 1.2364,
+      "step": 11
+    },
+    {
+      "epoch": 0.002439520227688555,
+      "grad_norm": 0.15639722347259521,
+      "learning_rate": 0.00019987796196481236,
+      "loss": 1.2499,
+      "step": 12
+    },
+    {
+      "epoch": 0.002642813579995934,
+      "grad_norm": 0.11634412407875061,
+      "learning_rate": 0.0001998576222922811,
+      "loss": 1.148,
+      "step": 13
+    },
+    {
+      "epoch": 0.0028461069323033137,
+      "grad_norm": 0.13249927759170532,
+      "learning_rate": 0.00019983728261974983,
+      "loss": 1.267,
+      "step": 14
+    },
+    {
+      "epoch": 0.0030494002846106934,
+      "grad_norm": 0.12251798063516617,
+      "learning_rate": 0.00019981694294721856,
+      "loss": 1.1868,
+      "step": 15
+    },
+    {
+      "epoch": 0.0032526936369180726,
+      "grad_norm": 0.1279357224702835,
+      "learning_rate": 0.00019979660327468728,
+      "loss": 1.3611,
+      "step": 16
+    },
+    {
+      "epoch": 0.0034559869892254523,
+      "grad_norm": 0.10690166801214218,
+      "learning_rate": 0.00019977626360215603,
+      "loss": 1.2934,
+      "step": 17
+    },
+    {
+      "epoch": 0.003659280341532832,
+      "grad_norm": 0.09634354710578918,
+      "learning_rate": 0.00019975592392962476,
+      "loss": 1.1628,
+      "step": 18
+    },
+    {
+      "epoch": 0.0038625736938402116,
+      "grad_norm": 0.08993979543447495,
+      "learning_rate": 0.00019973558425709345,
+      "loss": 1.1328,
+      "step": 19
+    },
+    {
+      "epoch": 0.004065867046147591,
+      "grad_norm": 0.09834206104278564,
+      "learning_rate": 0.00019971524458456218,
+      "loss": 1.1424,
+      "step": 20
+    },
+    {
+      "epoch": 0.0042691603984549705,
+      "grad_norm": 0.10754235088825226,
+      "learning_rate": 0.00019969490491203093,
+      "loss": 1.0843,
+      "step": 21
+    },
+    {
+      "epoch": 0.00447245375076235,
+      "grad_norm": 0.09953349828720093,
+      "learning_rate": 0.00019967456523949966,
+      "loss": 1.1475,
+      "step": 22
+    },
+    {
+      "epoch": 0.00467574710306973,
+      "grad_norm": 0.09910175204277039,
+      "learning_rate": 0.00019965422556696838,
+      "loss": 1.1532,
+      "step": 23
+    },
+    {
+      "epoch": 0.00487904045537711,
+      "grad_norm": 0.10800202935934067,
+      "learning_rate": 0.0001996338858944371,
+      "loss": 1.2336,
+      "step": 24
+    },
+    {
+      "epoch": 0.005082333807684488,
+      "grad_norm": 0.10042817890644073,
+      "learning_rate": 0.00019961354622190586,
+      "loss": 1.1235,
+      "step": 25
+    },
+    {
+      "epoch": 0.005285627159991868,
+      "grad_norm": 0.10839787125587463,
+      "learning_rate": 0.00019959320654937458,
+      "loss": 1.3561,
+      "step": 26
+    },
+    {
+      "epoch": 0.005488920512299248,
+      "grad_norm": 0.10559111088514328,
+      "learning_rate": 0.00019957286687684328,
+      "loss": 1.3255,
+      "step": 27
+    },
+    {
+      "epoch": 0.005692213864606627,
+      "grad_norm": 0.12504474818706512,
+      "learning_rate": 0.000199552527204312,
+      "loss": 1.4834,
+      "step": 28
+    },
+    {
+      "epoch": 0.005895507216914007,
+      "grad_norm": 0.09099473804235458,
+      "learning_rate": 0.00019953218753178075,
+      "loss": 1.1404,
+      "step": 29
+    },
+    {
+      "epoch": 0.006098800569221387,
+      "grad_norm": 0.09648846834897995,
+      "learning_rate": 0.00019951184785924948,
+      "loss": 1.1302,
+      "step": 30
+    },
+    {
+      "epoch": 0.006302093921528766,
+      "grad_norm": 0.0992799773812294,
+      "learning_rate": 0.0001994915081867182,
+      "loss": 1.3508,
+      "step": 31
+    },
+    {
+      "epoch": 0.006505387273836145,
+      "grad_norm": 0.10332880914211273,
+      "learning_rate": 0.00019947116851418693,
+      "loss": 1.1819,
+      "step": 32
+    },
+    {
+      "epoch": 0.006708680626143525,
+      "grad_norm": 0.1172771006822586,
+      "learning_rate": 0.00019945082884165568,
+      "loss": 1.2512,
+      "step": 33
+    },
+    {
+      "epoch": 0.006911973978450905,
+      "grad_norm": 0.10649558156728745,
+      "learning_rate": 0.0001994304891691244,
+      "loss": 1.2394,
+      "step": 34
+    },
+    {
+      "epoch": 0.007115267330758284,
+      "grad_norm": 0.10849574208259583,
+      "learning_rate": 0.0001994101494965931,
+      "loss": 1.1847,
+      "step": 35
+    },
+    {
+      "epoch": 0.007318560683065664,
+      "grad_norm": 0.11581245064735413,
+      "learning_rate": 0.00019938980982406182,
+      "loss": 1.2788,
+      "step": 36
+    },
+    {
+      "epoch": 0.007521854035373044,
+      "grad_norm": 0.09857199341058731,
+      "learning_rate": 0.00019936947015153058,
+      "loss": 1.1072,
+      "step": 37
+    },
+    {
+      "epoch": 0.007725147387680423,
+      "grad_norm": 0.08895204216241837,
+      "learning_rate": 0.0001993491304789993,
+      "loss": 0.8741,
+      "step": 38
+    },
+    {
+      "epoch": 0.007928440739987802,
+      "grad_norm": 0.09715849161148071,
+      "learning_rate": 0.00019932879080646803,
+      "loss": 1.2999,
+      "step": 39
+    },
+    {
+      "epoch": 0.008131734092295182,
+      "grad_norm": 0.09145913273096085,
+      "learning_rate": 0.00019930845113393675,
+      "loss": 0.9852,
+      "step": 40
+    },
+    {
+      "epoch": 0.008335027444602561,
+      "grad_norm": 0.09298407286405563,
+      "learning_rate": 0.0001992881114614055,
+      "loss": 1.1033,
+      "step": 41
+    },
+    {
+      "epoch": 0.008538320796909941,
+      "grad_norm": 0.09957871586084366,
+      "learning_rate": 0.00019926777178887423,
+      "loss": 1.3203,
+      "step": 42
+    },
+    {
+      "epoch": 0.00874161414921732,
+      "grad_norm": 0.1212410032749176,
+      "learning_rate": 0.00019924743211634292,
+      "loss": 1.166,
+      "step": 43
+    },
+    {
+      "epoch": 0.0089449075015247,
+      "grad_norm": 0.10740375518798828,
+      "learning_rate": 0.00019922709244381165,
+      "loss": 1.1905,
+      "step": 44
+    },
+    {
+      "epoch": 0.00914820085383208,
+      "grad_norm": 0.10571859031915665,
+      "learning_rate": 0.0001992067527712804,
+      "loss": 1.07,
+      "step": 45
+    },
+    {
+      "epoch": 0.00935149420613946,
+      "grad_norm": 0.11196234077215195,
+      "learning_rate": 0.00019918641309874912,
+      "loss": 1.2516,
+      "step": 46
+    },
+    {
+      "epoch": 0.00955478755844684,
+      "grad_norm": 0.1025981530547142,
+      "learning_rate": 0.00019916607342621785,
+      "loss": 1.1118,
+      "step": 47
+    },
+    {
+      "epoch": 0.00975808091075422,
+      "grad_norm": 0.10584773868322372,
+      "learning_rate": 0.00019914573375368657,
+      "loss": 1.1551,
+      "step": 48
+    },
+    {
+      "epoch": 0.009961374263061597,
+      "grad_norm": 0.10157100111246109,
+      "learning_rate": 0.0001991253940811553,
+      "loss": 0.9638,
+      "step": 49
+    },
+    {
+      "epoch": 0.010164667615368977,
+      "grad_norm": 0.10194176435470581,
+      "learning_rate": 0.00019910505440862405,
+      "loss": 1.0024,
+      "step": 50
+    },
+    {
+      "epoch": 0.010367960967676356,
+      "grad_norm": 0.10047532618045807,
+      "learning_rate": 0.00019908471473609275,
+      "loss": 1.1767,
+      "step": 51
+    },
+    {
+      "epoch": 0.010571254319983736,
+      "grad_norm": 0.10448278486728668,
+      "learning_rate": 0.00019906437506356147,
+      "loss": 1.2346,
+      "step": 52
+    },
+    {
+      "epoch": 0.010774547672291116,
+      "grad_norm": 0.09438527375459671,
+      "learning_rate": 0.0001990440353910302,
+      "loss": 1.0517,
+      "step": 53
+    },
+    {
+      "epoch": 0.010977841024598495,
+      "grad_norm": 0.12310227751731873,
+      "learning_rate": 0.00019902369571849895,
+      "loss": 1.2809,
+      "step": 54
+    },
+    {
+      "epoch": 0.011181134376905875,
+      "grad_norm": 0.10811592638492584,
+      "learning_rate": 0.00019900335604596767,
+      "loss": 1.1171,
+      "step": 55
+    },
+    {
+      "epoch": 0.011384427729213255,
+      "grad_norm": 0.12063754349946976,
+      "learning_rate": 0.0001989830163734364,
+      "loss": 1.0719,
+      "step": 56
+    },
+    {
+      "epoch": 0.011587721081520634,
+      "grad_norm": 0.10147465020418167,
+      "learning_rate": 0.00019896267670090512,
+      "loss": 1.0643,
+      "step": 57
+    },
+    {
+      "epoch": 0.011791014433828014,
+      "grad_norm": 0.10184100270271301,
+      "learning_rate": 0.00019894233702837387,
+      "loss": 1.0148,
+      "step": 58
+    },
+    {
+      "epoch": 0.011994307786135394,
+      "grad_norm": 0.1090080663561821,
+      "learning_rate": 0.00019892199735584257,
+      "loss": 1.0762,
+      "step": 59
+    },
+    {
+      "epoch": 0.012197601138442773,
+      "grad_norm": 0.0960102528333664,
+      "learning_rate": 0.0001989016576833113,
+      "loss": 1.09,
+      "step": 60
+    },
+    {
+      "epoch": 0.012400894490750153,
+      "grad_norm": 0.1056618019938469,
+      "learning_rate": 0.00019888131801078002,
+      "loss": 1.0092,
+      "step": 61
+    },
+    {
+      "epoch": 0.012604187843057533,
+      "grad_norm": 0.10064820945262909,
+      "learning_rate": 0.00019886097833824877,
+      "loss": 1.0135,
+      "step": 62
+    },
+    {
+      "epoch": 0.01280748119536491,
+      "grad_norm": 0.11083406209945679,
+      "learning_rate": 0.0001988406386657175,
+      "loss": 1.2344,
+      "step": 63
+    },
+    {
+      "epoch": 0.01301077454767229,
+      "grad_norm": 0.10507647693157196,
+      "learning_rate": 0.00019882029899318622,
+      "loss": 1.1035,
+      "step": 64
+    },
+    {
+      "epoch": 0.01321406789997967,
+      "grad_norm": 0.10840694606304169,
+      "learning_rate": 0.00019879995932065494,
+      "loss": 1.1458,
+      "step": 65
+    },
+    {
+      "epoch": 0.01341736125228705,
+      "grad_norm": 0.1149667352437973,
+      "learning_rate": 0.0001987796196481237,
+      "loss": 1.0722,
+      "step": 66
+    },
+    {
+      "epoch": 0.01362065460459443,
+      "grad_norm": 0.1219320297241211,
+      "learning_rate": 0.00019875927997559242,
+      "loss": 1.1392,
+      "step": 67
+    },
+    {
+      "epoch": 0.01382394795690181,
+      "grad_norm": 0.1296710968017578,
+      "learning_rate": 0.00019873894030306112,
+      "loss": 1.1831,
+      "step": 68
+    },
+    {
+      "epoch": 0.014027241309209189,
+      "grad_norm": 0.11214271187782288,
+      "learning_rate": 0.00019871860063052984,
+      "loss": 1.0385,
+      "step": 69
+    },
+    {
+      "epoch": 0.014230534661516568,
+      "grad_norm": 0.12374462932348251,
+      "learning_rate": 0.0001986982609579986,
+      "loss": 1.2633,
+      "step": 70
+    },
+    {
+      "epoch": 0.014433828013823948,
+      "grad_norm": 0.09856373071670532,
+      "learning_rate": 0.00019867792128546732,
+      "loss": 1.0495,
+      "step": 71
+    },
+    {
+      "epoch": 0.014637121366131328,
+      "grad_norm": 0.1356707215309143,
+      "learning_rate": 0.00019865758161293604,
+      "loss": 1.2245,
+      "step": 72
+    },
+    {
+      "epoch": 0.014840414718438708,
+      "grad_norm": 0.10265105217695236,
+      "learning_rate": 0.00019863724194040477,
+      "loss": 1.0076,
+      "step": 73
+    },
+    {
+      "epoch": 0.015043708070746087,
+      "grad_norm": 0.1307467520236969,
+      "learning_rate": 0.00019861690226787352,
+      "loss": 1.3838,
+      "step": 74
+    },
+    {
+      "epoch": 0.015247001423053467,
+      "grad_norm": 0.12013835459947586,
+      "learning_rate": 0.00019859656259534224,
+      "loss": 1.1509,
+      "step": 75
+    },
+    {
+      "epoch": 0.015450294775360847,
+      "grad_norm": 0.10897748917341232,
+      "learning_rate": 0.00019857622292281094,
+      "loss": 1.025,
+      "step": 76
+    },
+    {
+      "epoch": 0.015653588127668226,
+      "grad_norm": 0.10924937576055527,
+      "learning_rate": 0.00019855588325027966,
+      "loss": 1.06,
+      "step": 77
+    },
+    {
+      "epoch": 0.015856881479975604,
+      "grad_norm": 0.10474475473165512,
+      "learning_rate": 0.00019853554357774841,
+      "loss": 0.9267,
+      "step": 78
+    },
+    {
+      "epoch": 0.016060174832282986,
+      "grad_norm": 0.12250765413045883,
+      "learning_rate": 0.00019851520390521714,
+      "loss": 1.1231,
+      "step": 79
+    },
+    {
+      "epoch": 0.016263468184590364,
+      "grad_norm": 0.12869718670845032,
+      "learning_rate": 0.00019849486423268586,
+      "loss": 1.1219,
+      "step": 80
+    },
+    {
+      "epoch": 0.016466761536897745,
+      "grad_norm": 0.11656077951192856,
+      "learning_rate": 0.0001984745245601546,
+      "loss": 1.1494,
+      "step": 81
+    },
+    {
+      "epoch": 0.016670054889205123,
+      "grad_norm": 0.12449704855680466,
+      "learning_rate": 0.00019845418488762334,
+      "loss": 1.3177,
+      "step": 82
+    },
+    {
+      "epoch": 0.016873348241512504,
+      "grad_norm": 0.10715439915657043,
+      "learning_rate": 0.00019843384521509206,
+      "loss": 1.0944,
+      "step": 83
+    },
+    {
+      "epoch": 0.017076641593819882,
+      "grad_norm": 0.11231628060340881,
+      "learning_rate": 0.00019841350554256076,
+      "loss": 1.0681,
+      "step": 84
+    },
+    {
+      "epoch": 0.01727993494612726,
+      "grad_norm": 0.1253119856119156,
+      "learning_rate": 0.00019839316587002949,
+      "loss": 1.104,
+      "step": 85
+    },
+    {
+      "epoch": 0.01748322829843464,
+      "grad_norm": 0.12725764513015747,
+      "learning_rate": 0.00019837282619749824,
+      "loss": 1.307,
+      "step": 86
+    },
+    {
+      "epoch": 0.01768652165074202,
+      "grad_norm": 0.11470405012369156,
+      "learning_rate": 0.00019835248652496696,
+      "loss": 1.0729,
+      "step": 87
+    },
+    {
+      "epoch": 0.0178898150030494,
+      "grad_norm": 0.12006914615631104,
+      "learning_rate": 0.0001983321468524357,
+      "loss": 1.1608,
+      "step": 88
+    },
+    {
+      "epoch": 0.01809310835535678,
+      "grad_norm": 0.11256147921085358,
+      "learning_rate": 0.0001983118071799044,
+      "loss": 1.0816,
+      "step": 89
+    },
+    {
+      "epoch": 0.01829640170766416,
+      "grad_norm": 0.12627887725830078,
+      "learning_rate": 0.00019829146750737314,
+      "loss": 1.2015,
+      "step": 90
+    },
+    {
+      "epoch": 0.018499695059971538,
+      "grad_norm": 0.12313251942396164,
+      "learning_rate": 0.0001982711278348419,
+      "loss": 1.0837,
+      "step": 91
+    },
+    {
+      "epoch": 0.01870298841227892,
+      "grad_norm": 0.1349901705980301,
+      "learning_rate": 0.00019825078816231058,
+      "loss": 1.2277,
+      "step": 92
+    },
+    {
+      "epoch": 0.018906281764586298,
+      "grad_norm": 0.11006023734807968,
+      "learning_rate": 0.0001982304484897793,
+      "loss": 1.0768,
+      "step": 93
+    },
+    {
+      "epoch": 0.01910957511689368,
+      "grad_norm": 0.1100686565041542,
+      "learning_rate": 0.00019821010881724803,
+      "loss": 1.1119,
+      "step": 94
+    },
+    {
+      "epoch": 0.019312868469201057,
+      "grad_norm": 0.1252383440732956,
+      "learning_rate": 0.00019818976914471678,
+      "loss": 1.1862,
+      "step": 95
+    },
+    {
+      "epoch": 0.01951616182150844,
+      "grad_norm": 0.1430596113204956,
+      "learning_rate": 0.0001981694294721855,
+      "loss": 1.1765,
+      "step": 96
+    },
+    {
+      "epoch": 0.019719455173815816,
+      "grad_norm": 0.130848690867424,
+      "learning_rate": 0.00019814908979965423,
+      "loss": 1.3255,
+      "step": 97
+    },
+    {
+      "epoch": 0.019922748526123194,
+      "grad_norm": 0.13019633293151855,
+      "learning_rate": 0.00019812875012712296,
+      "loss": 1.1853,
+      "step": 98
+    },
+    {
+      "epoch": 0.020126041878430576,
+      "grad_norm": 0.11539386957883835,
+      "learning_rate": 0.0001981084104545917,
+      "loss": 1.1897,
+      "step": 99
+    },
+    {
+      "epoch": 0.020329335230737954,
+      "grad_norm": 0.11749454587697983,
+      "learning_rate": 0.0001980880707820604,
+      "loss": 1.1189,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 9838,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.546683450019021e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:54123d12c6ee063bca8c706a4f849cf559a6a5bb17356534bcaf78b4e25f3df0
+size 5688

vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff