Upload folder using huggingface_hub

.gitattributes

@@ -38,3 +38,4 @@ limo/full/checkpoint-1030/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 limo/full/checkpoint-1545/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 s1k/full/checkpoint-930/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 s1k/full/checkpoint-310/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+s1k/full/checkpoint-620/tokenizer.json filter=lfs diff=lfs merge=lfs -text

s1k/full/checkpoint-620/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
+}

s1k/full/checkpoint-620/config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/mnt/data/lh/models/Qwen2.5-0.5B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "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": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

s1k/full/checkpoint-620/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}

s1k/full/checkpoint-620/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:267262b0f64ae6e5925a74fd755ee056b626055fa2ead1a1dadfc9a441ec21d3
+size 1976163472

s1k/full/checkpoint-620/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9eed2b3d7dd2529f6fa2d7ba12a5cef455b09bef4e10bf23e5e15c94be5bccc
+size 3952505274

s1k/full/checkpoint-620/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb1165242405b17b3d6a8186ae61b13dcb1faa5a54320bebd74ef8d71b964bf7
+size 15984

s1k/full/checkpoint-620/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:562c262916c9997ec644c42fed9655ab28706b74fca20290ca921c4761d6a4b0
+size 15984

s1k/full/checkpoint-620/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8d40f8118f513299624ded0a9bcf09778b961635615090409394d4f96f928f6
+size 15984

s1k/full/checkpoint-620/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4391f924238a4cb855c4cbdc6d1a14954f785431c75997d05c7a4ee6615dae7
+size 15984

s1k/full/checkpoint-620/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be7b19bb9543a16bf9f4cd96466ac581436f63070f5815f3a7ba57980608994f
+size 15984

s1k/full/checkpoint-620/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97da4a1ede0a3e0f96411cacd5bfdf84d9355198f7aadc9bcb8be41122043f63
+size 15984

s1k/full/checkpoint-620/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:544cb6421b975bd5d2b2360a4e666003794e6197ae654d2ad963cd6572a86ede
+size 15984

s1k/full/checkpoint-620/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8d6eb32a23f3bef6262bbcb2eda724b2fd6f5e579969aa27c71a5971331722b
+size 15984

s1k/full/checkpoint-620/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e1e2c4df6a0e228e7402698c30d462b1c3f365fd9e3598d5f19b93128886dea
+size 1064

s1k/full/checkpoint-620/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
+  }
+}

s1k/full/checkpoint-620/tokenizer.json

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

s1k/full/checkpoint-620/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 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",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

s1k/full/checkpoint-620/trainer_state.json

@@ -0,0 +1,467 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.92,
+  "eval_steps": 500,
+  "global_step": 620,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.3802237510681152,
+      "learning_rate": 1.6129032258064516e-06,
+      "loss": 0.5835,
+      "step": 10
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.54867684841156,
+      "learning_rate": 3.225806451612903e-06,
+      "loss": 0.6041,
+      "step": 20
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.3039277791976929,
+      "learning_rate": 4.838709677419355e-06,
+      "loss": 0.6233,
+      "step": 30
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.1136252880096436,
+      "learning_rate": 6.451612903225806e-06,
+      "loss": 0.5368,
+      "step": 40
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.033889889717102,
+      "learning_rate": 8.064516129032258e-06,
+      "loss": 0.5403,
+      "step": 50
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.09119713306427,
+      "learning_rate": 9.67741935483871e-06,
+      "loss": 0.5382,
+      "step": 60
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 1.3345595598220825,
+      "learning_rate": 9.994929183335237e-06,
+      "loss": 0.5341,
+      "step": 70
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 1.0556639432907104,
+      "learning_rate": 9.974346616959476e-06,
+      "loss": 0.4711,
+      "step": 80
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 1.0054714679718018,
+      "learning_rate": 9.938000549906509e-06,
+      "loss": 0.4861,
+      "step": 90
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.0059211254119873,
+      "learning_rate": 9.88600616137407e-06,
+      "loss": 0.4707,
+      "step": 100
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 1.177834391593933,
+      "learning_rate": 9.818528219449705e-06,
+      "loss": 0.4569,
+      "step": 110
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 1.0392038822174072,
+      "learning_rate": 9.735780558967434e-06,
+      "loss": 0.4696,
+      "step": 120
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 1.1502702236175537,
+      "learning_rate": 9.638025403873939e-06,
+      "loss": 0.4897,
+      "step": 130
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 1.0028127431869507,
+      "learning_rate": 9.525572536251608e-06,
+      "loss": 0.4279,
+      "step": 140
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.186493992805481,
+      "learning_rate": 9.398778314631801e-06,
+      "loss": 0.437,
+      "step": 150
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 1.1572821140289307,
+      "learning_rate": 9.258044544709276e-06,
+      "loss": 0.4303,
+      "step": 160
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 1.133217692375183,
+      "learning_rate": 9.103817206036383e-06,
+      "loss": 0.4109,
+      "step": 170
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 1.0267817974090576,
+      "learning_rate": 8.936585038732143e-06,
+      "loss": 0.4125,
+      "step": 180
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 1.221564531326294,
+      "learning_rate": 8.756877994684818e-06,
+      "loss": 0.439,
+      "step": 190
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 1.1549971103668213,
+      "learning_rate": 8.565265558156101e-06,
+      "loss": 0.3815,
+      "step": 200
+    },
+    {
+      "epoch": 3.36,
+      "grad_norm": 1.1660393476486206,
+      "learning_rate": 8.362354941108803e-06,
+      "loss": 0.372,
+      "step": 210
+    },
+    {
+      "epoch": 3.52,
+      "grad_norm": 1.2219997644424438,
+      "learning_rate": 8.148789158977012e-06,
+      "loss": 0.3593,
+      "step": 220
+    },
+    {
+      "epoch": 3.68,
+      "grad_norm": 1.2729219198226929,
+      "learning_rate": 7.925244992976538e-06,
+      "loss": 0.3927,
+      "step": 230
+    },
+    {
+      "epoch": 3.84,
+      "grad_norm": 1.1232186555862427,
+      "learning_rate": 7.692430845412946e-06,
+      "loss": 0.3707,
+      "step": 240
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.6789491176605225,
+      "learning_rate": 7.451084494783668e-06,
+      "loss": 0.3969,
+      "step": 250
+    },
+    {
+      "epoch": 4.16,
+      "grad_norm": 1.1689192056655884,
+      "learning_rate": 7.201970757788172e-06,
+      "loss": 0.3291,
+      "step": 260
+    },
+    {
+      "epoch": 4.32,
+      "grad_norm": 1.2333303689956665,
+      "learning_rate": 6.945879065655164e-06,
+      "loss": 0.3389,
+      "step": 270
+    },
+    {
+      "epoch": 4.48,
+      "grad_norm": 1.1970478296279907,
+      "learning_rate": 6.6836209624673575e-06,
+      "loss": 0.3511,
+      "step": 280
+    },
+    {
+      "epoch": 4.64,
+      "grad_norm": 1.1437437534332275,
+      "learning_rate": 6.41602753341152e-06,
+      "loss": 0.3208,
+      "step": 290
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 1.1262255907058716,
+      "learning_rate": 6.143946771103561e-06,
+      "loss": 0.332,
+      "step": 300
+    },
+    {
+      "epoch": 4.96,
+      "grad_norm": 1.0892969369888306,
+      "learning_rate": 5.8682408883346535e-06,
+      "loss": 0.3187,
+      "step": 310
+    },
+    {
+      "epoch": 5.12,
+      "grad_norm": 1.5473947525024414,
+      "learning_rate": 5.5897835857542315e-06,
+      "loss": 0.328,
+      "step": 320
+    },
+    {
+      "epoch": 5.28,
+      "grad_norm": 1.2388378381729126,
+      "learning_rate": 5.30945728314841e-06,
+      "loss": 0.2748,
+      "step": 330
+    },
+    {
+      "epoch": 5.44,
+      "grad_norm": 1.0738927125930786,
+      "learning_rate": 5.0281503230878304e-06,
+      "loss": 0.2966,
+      "step": 340
+    },
+    {
+      "epoch": 5.6,
+      "grad_norm": 1.235426664352417,
+      "learning_rate": 4.746754155806437e-06,
+      "loss": 0.2998,
+      "step": 350
+    },
+    {
+      "epoch": 5.76,
+      "grad_norm": 1.2488200664520264,
+      "learning_rate": 4.466160514232206e-06,
+      "loss": 0.2816,
+      "step": 360
+    },
+    {
+      "epoch": 5.92,
+      "grad_norm": 1.2182546854019165,
+      "learning_rate": 4.187258588122019e-06,
+      "loss": 0.2899,
+      "step": 370
+    },
+    {
+      "epoch": 6.08,
+      "grad_norm": 1.138779640197754,
+      "learning_rate": 3.910932206255742e-06,
+      "loss": 0.2776,
+      "step": 380
+    },
+    {
+      "epoch": 6.24,
+      "grad_norm": 1.160627841949463,
+      "learning_rate": 3.6380570356190346e-06,
+      "loss": 0.2623,
+      "step": 390
+    },
+    {
+      "epoch": 6.4,
+      "grad_norm": 1.097216248512268,
+      "learning_rate": 3.3694978064505258e-06,
+      "loss": 0.2587,
+      "step": 400
+    },
+    {
+      "epoch": 6.5600000000000005,
+      "grad_norm": 1.0908410549163818,
+      "learning_rate": 3.10610557194712e-06,
+      "loss": 0.2432,
+      "step": 410
+    },
+    {
+      "epoch": 6.72,
+      "grad_norm": 1.1689103841781616,
+      "learning_rate": 2.848715011311271e-06,
+      "loss": 0.2868,
+      "step": 420
+    },
+    {
+      "epoch": 6.88,
+      "grad_norm": 1.136789083480835,
+      "learning_rate": 2.5981417846867753e-06,
+      "loss": 0.2445,
+      "step": 430
+    },
+    {
+      "epoch": 7.04,
+      "grad_norm": 1.1320103406906128,
+      "learning_rate": 2.3551799483651894e-06,
+      "loss": 0.2651,
+      "step": 440
+    },
+    {
+      "epoch": 7.2,
+      "grad_norm": 1.3189644813537598,
+      "learning_rate": 2.120599438453968e-06,
+      "loss": 0.2224,
+      "step": 450
+    },
+    {
+      "epoch": 7.36,
+      "grad_norm": 1.1489248275756836,
+      "learning_rate": 1.8951436309804766e-06,
+      "loss": 0.2367,
+      "step": 460
+    },
+    {
+      "epoch": 7.52,
+      "grad_norm": 1.264541745185852,
+      "learning_rate": 1.6795269861638041e-06,
+      "loss": 0.2348,
+      "step": 470
+    },
+    {
+      "epoch": 7.68,
+      "grad_norm": 1.1664469242095947,
+      "learning_rate": 1.4744327843196043e-06,
+      "loss": 0.2199,
+      "step": 480
+    },
+    {
+      "epoch": 7.84,
+      "grad_norm": 1.1112245321273804,
+      "learning_rate": 1.280510960572745e-06,
+      "loss": 0.2562,
+      "step": 490
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 2.1335887908935547,
+      "learning_rate": 1.0983760452395415e-06,
+      "loss": 0.2417,
+      "step": 500
+    },
+    {
+      "epoch": 8.16,
+      "grad_norm": 1.119673728942871,
+      "learning_rate": 9.286052164063369e-07,
+      "loss": 0.2167,
+      "step": 510
+    },
+    {
+      "epoch": 8.32,
+      "grad_norm": 1.1483794450759888,
+      "learning_rate": 7.717364708758024e-07,
+      "loss": 0.2182,
+      "step": 520
+    },
+    {
+      "epoch": 8.48,
+      "grad_norm": 1.0667556524276733,
+      "learning_rate": 6.282669192770896e-07,
+      "loss": 0.2219,
+      "step": 530
+    },
+    {
+      "epoch": 8.64,
+      "grad_norm": 1.1298916339874268,
+      "learning_rate": 4.986512107426283e-07,
+      "loss": 0.237,
+      "step": 540
+    },
+    {
+      "epoch": 8.8,
+      "grad_norm": 1.1533700227737427,
+      "learning_rate": 3.8330009214363197e-07,
+      "loss": 0.2216,
+      "step": 550
+    },
+    {
+      "epoch": 8.96,
+      "grad_norm": 1.3445242643356323,
+      "learning_rate": 2.8257910645009935e-07,
+      "loss": 0.2097,
+      "step": 560
+    },
+    {
+      "epoch": 9.12,
+      "grad_norm": 1.0335811376571655,
+      "learning_rate": 1.9680743434010385e-07,
+      "loss": 0.2119,
+      "step": 570
+    },
+    {
+      "epoch": 9.28,
+      "grad_norm": 1.0804325342178345,
+      "learning_rate": 1.2625688272930925e-07,
+      "loss": 0.2121,
+      "step": 580
+    },
+    {
+      "epoch": 9.44,
+      "grad_norm": 1.1088650226593018,
+      "learning_rate": 7.115102342598101e-08,
+      "loss": 0.2135,
+      "step": 590
+    },
+    {
+      "epoch": 9.6,
+      "grad_norm": 1.1131296157836914,
+      "learning_rate": 3.166448464108629e-08,
+      "loss": 0.2375,
+      "step": 600
+    },
+    {
+      "epoch": 9.76,
+      "grad_norm": 1.1123712062835693,
+      "learning_rate": 7.922397598642551e-09,
+      "loss": 0.2133,
+      "step": 610
+    },
+    {
+      "epoch": 9.92,
+      "grad_norm": 1.0262830257415771,
+      "learning_rate": 0.0,
+      "loss": 0.2119,
+      "step": 620
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 620,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 155,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.203946182892585e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

s1k/full/checkpoint-620/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13663f7d141b512d5af63c32d97059b8b97f1c56d4ffcecc3d69b78d0d7c97e8
+size 5560