Model save

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,58 @@
+---
+library_name: transformers
+tags:
+- llama-factory
+- generated_from_trainer
+model-index:
+- name: subset_without_verbose_1.5b
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# subset_without_verbose_1.5b
+
+This model was trained from scratch on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 256
+- total_eval_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.50.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.4.1
+- Tokenizers 0.21.0

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 +1,28 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "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": "bfloat16",
+  "transformers_version": "4.50.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

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": "4.50.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dbf6eb899dd36180284d24a31c9070d63f45074e85dffac2008928742e397de
+size 3554214752

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 +1,209 @@
+{
+  "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_log.jsonl

@@ -0,0 +1,74 @@
+{"current_steps": 10, "total_steps": 732, "loss": 0.5098, "lr": 2.702702702702703e-06, "epoch": 0.027257240204429302, "percentage": 1.37, "elapsed_time": "0:04:23", "remaining_time": "5:16:57"}
+{"current_steps": 20, "total_steps": 732, "loss": 0.2853, "lr": 5.405405405405406e-06, "epoch": 0.054514480408858604, "percentage": 2.73, "elapsed_time": "0:08:47", "remaining_time": "5:13:08"}
+{"current_steps": 30, "total_steps": 732, "loss": 0.1413, "lr": 8.108108108108109e-06, "epoch": 0.0817717206132879, "percentage": 4.1, "elapsed_time": "0:13:24", "remaining_time": "5:13:35"}
+{"current_steps": 40, "total_steps": 732, "loss": 0.0924, "lr": 1.0810810810810812e-05, "epoch": 0.10902896081771721, "percentage": 5.46, "elapsed_time": "0:17:41", "remaining_time": "5:06:02"}
+{"current_steps": 50, "total_steps": 732, "loss": 0.0757, "lr": 1.3513513513513515e-05, "epoch": 0.1362862010221465, "percentage": 6.83, "elapsed_time": "0:22:04", "remaining_time": "5:01:09"}
+{"current_steps": 60, "total_steps": 732, "loss": 0.0662, "lr": 1.6216216216216218e-05, "epoch": 0.1635434412265758, "percentage": 8.2, "elapsed_time": "0:26:23", "remaining_time": "4:55:36"}
+{"current_steps": 70, "total_steps": 732, "loss": 0.0567, "lr": 1.891891891891892e-05, "epoch": 0.19080068143100512, "percentage": 9.56, "elapsed_time": "0:30:42", "remaining_time": "4:50:24"}
+{"current_steps": 80, "total_steps": 732, "loss": 0.0521, "lr": 1.9995897101594454e-05, "epoch": 0.21805792163543442, "percentage": 10.93, "elapsed_time": "0:35:06", "remaining_time": "4:46:05"}
+{"current_steps": 90, "total_steps": 732, "loss": 0.0466, "lr": 1.997083602488702e-05, "epoch": 0.2453151618398637, "percentage": 12.3, "elapsed_time": "0:39:32", "remaining_time": "4:42:02"}
+{"current_steps": 100, "total_steps": 732, "loss": 0.0447, "lr": 1.9923050307166655e-05, "epoch": 0.272572402044293, "percentage": 13.66, "elapsed_time": "0:43:51", "remaining_time": "4:37:13"}
+{"current_steps": 110, "total_steps": 732, "loss": 0.0432, "lr": 1.9852648857383224e-05, "epoch": 0.29982964224872233, "percentage": 15.03, "elapsed_time": "0:48:11", "remaining_time": "4:32:31"}
+{"current_steps": 120, "total_steps": 732, "loss": 0.041, "lr": 1.9759792128247922e-05, "epoch": 0.3270868824531516, "percentage": 16.39, "elapsed_time": "0:52:37", "remaining_time": "4:28:25"}
+{"current_steps": 130, "total_steps": 732, "loss": 0.0404, "lr": 1.964469175054377e-05, "epoch": 0.3543441226575809, "percentage": 17.76, "elapsed_time": "0:57:04", "remaining_time": "4:24:15"}
+{"current_steps": 140, "total_steps": 732, "loss": 0.0373, "lr": 1.950761005079556e-05, "epoch": 0.38160136286201024, "percentage": 19.13, "elapsed_time": "1:01:27", "remaining_time": "4:19:54"}
+{"current_steps": 150, "total_steps": 732, "loss": 0.0373, "lr": 1.934885945339865e-05, "epoch": 0.4088586030664395, "percentage": 20.49, "elapsed_time": "1:05:46", "remaining_time": "4:15:11"}
+{"current_steps": 160, "total_steps": 732, "loss": 0.0345, "lr": 1.916880176856909e-05, "epoch": 0.43611584327086883, "percentage": 21.86, "elapsed_time": "1:10:01", "remaining_time": "4:10:19"}
+{"current_steps": 170, "total_steps": 732, "loss": 0.0342, "lr": 1.896784736773805e-05, "epoch": 0.46337308347529815, "percentage": 23.22, "elapsed_time": "1:14:25", "remaining_time": "4:06:02"}
+{"current_steps": 180, "total_steps": 732, "loss": 0.034, "lr": 1.8746454248269777e-05, "epoch": 0.4906303236797274, "percentage": 24.59, "elapsed_time": "1:18:49", "remaining_time": "4:01:44"}
+{"current_steps": 190, "total_steps": 732, "loss": 0.0322, "lr": 1.850512698963485e-05, "epoch": 0.5178875638841567, "percentage": 25.96, "elapsed_time": "1:23:09", "remaining_time": "3:57:12"}
+{"current_steps": 200, "total_steps": 732, "loss": 0.0341, "lr": 1.8244415603417603e-05, "epoch": 0.545144804088586, "percentage": 27.32, "elapsed_time": "1:27:30", "remaining_time": "3:52:45"}
+{"current_steps": 210, "total_steps": 732, "loss": 0.0329, "lr": 1.7964914279778716e-05, "epoch": 0.5724020442930153, "percentage": 28.69, "elapsed_time": "1:31:53", "remaining_time": "3:48:25"}
+{"current_steps": 220, "total_steps": 732, "loss": 0.0308, "lr": 1.7667260033229953e-05, "epoch": 0.5996592844974447, "percentage": 30.05, "elapsed_time": "1:36:16", "remaining_time": "3:44:03"}
+{"current_steps": 230, "total_steps": 732, "loss": 0.0319, "lr": 1.7352131250807466e-05, "epoch": 0.626916524701874, "percentage": 31.42, "elapsed_time": "1:40:35", "remaining_time": "3:39:33"}
+{"current_steps": 240, "total_steps": 732, "loss": 0.03, "lr": 1.702024614595248e-05, "epoch": 0.6541737649063032, "percentage": 32.79, "elapsed_time": "1:44:57", "remaining_time": "3:35:10"}
+{"current_steps": 250, "total_steps": 732, "loss": 0.0291, "lr": 1.6672361121623238e-05, "epoch": 0.6814310051107325, "percentage": 34.15, "elapsed_time": "1:49:14", "remaining_time": "3:30:36"}
+{"current_steps": 260, "total_steps": 732, "loss": 0.0295, "lr": 1.6309269046368777e-05, "epoch": 0.7086882453151618, "percentage": 35.52, "elapsed_time": "1:53:32", "remaining_time": "3:26:07"}
+{"current_steps": 270, "total_steps": 732, "loss": 0.0297, "lr": 1.5931797447293553e-05, "epoch": 0.7359454855195912, "percentage": 36.89, "elapsed_time": "1:57:58", "remaining_time": "3:21:52"}
+{"current_steps": 280, "total_steps": 732, "loss": 0.0271, "lr": 1.554080662403144e-05, "epoch": 0.7632027257240205, "percentage": 38.25, "elapsed_time": "2:02:23", "remaining_time": "3:17:35"}
+{"current_steps": 290, "total_steps": 732, "loss": 0.0267, "lr": 1.5137187688027437e-05, "epoch": 0.7904599659284497, "percentage": 39.62, "elapsed_time": "2:06:48", "remaining_time": "3:13:15"}
+{"current_steps": 300, "total_steps": 732, "loss": 0.0275, "lr": 1.4721860531595868e-05, "epoch": 0.817717206132879, "percentage": 40.98, "elapsed_time": "2:11:07", "remaining_time": "3:08:49"}
+{"current_steps": 310, "total_steps": 732, "loss": 0.026, "lr": 1.4295771731383799e-05, "epoch": 0.8449744463373083, "percentage": 42.35, "elapsed_time": "2:15:30", "remaining_time": "3:04:28"}
+{"current_steps": 320, "total_steps": 732, "loss": 0.0262, "lr": 1.3859892391017867e-05, "epoch": 0.8722316865417377, "percentage": 43.72, "elapsed_time": "2:19:44", "remaining_time": "2:59:55"}
+{"current_steps": 330, "total_steps": 732, "loss": 0.0262, "lr": 1.341521592785145e-05, "epoch": 0.899488926746167, "percentage": 45.08, "elapsed_time": "2:24:08", "remaining_time": "2:55:35"}
+{"current_steps": 340, "total_steps": 732, "loss": 0.0264, "lr": 1.2962755808856341e-05, "epoch": 0.9267461669505963, "percentage": 46.45, "elapsed_time": "2:28:31", "remaining_time": "2:51:14"}
+{"current_steps": 350, "total_steps": 732, "loss": 0.0252, "lr": 1.2503543240819127e-05, "epoch": 0.9540034071550255, "percentage": 47.81, "elapsed_time": "2:32:44", "remaining_time": "2:46:42"}
+{"current_steps": 360, "total_steps": 732, "loss": 0.0257, "lr": 1.2038624820106572e-05, "epoch": 0.9812606473594548, "percentage": 49.18, "elapsed_time": "2:37:05", "remaining_time": "2:42:19"}
+{"current_steps": 370, "total_steps": 732, "loss": 0.0269, "lr": 1.1569060147356441e-05, "epoch": 1.0109028960817716, "percentage": 50.55, "elapsed_time": "2:41:24", "remaining_time": "2:37:54"}
+{"current_steps": 380, "total_steps": 732, "loss": 0.0251, "lr": 1.1095919412530136e-05, "epoch": 1.038160136286201, "percentage": 51.91, "elapsed_time": "2:45:43", "remaining_time": "2:33:31"}
+{"current_steps": 390, "total_steps": 732, "loss": 0.0212, "lr": 1.0620280955831088e-05, "epoch": 1.0654173764906303, "percentage": 53.28, "elapsed_time": "2:50:03", "remaining_time": "2:29:07"}
+{"current_steps": 400, "total_steps": 732, "loss": 0.0212, "lr": 1.0143228810047877e-05, "epoch": 1.0926746166950596, "percentage": 54.64, "elapsed_time": "2:54:25", "remaining_time": "2:24:46"}
+{"current_steps": 410, "total_steps": 732, "loss": 0.0228, "lr": 9.665850229923258e-06, "epoch": 1.119931856899489, "percentage": 56.01, "elapsed_time": "2:58:45", "remaining_time": "2:20:23"}
+{"current_steps": 420, "total_steps": 732, "loss": 0.0223, "lr": 9.189233214180057e-06, "epoch": 1.1471890971039183, "percentage": 57.38, "elapsed_time": "3:03:02", "remaining_time": "2:15:58"}
+{"current_steps": 430, "total_steps": 732, "loss": 0.0222, "lr": 8.714464025851428e-06, "epoch": 1.1744463373083476, "percentage": 58.74, "elapsed_time": "3:07:24", "remaining_time": "2:11:36"}
+{"current_steps": 440, "total_steps": 732, "loss": 0.0207, "lr": 8.242624716566928e-06, "epoch": 1.201703577512777, "percentage": 60.11, "elapsed_time": "3:11:36", "remaining_time": "2:07:09"}
+{"current_steps": 450, "total_steps": 732, "loss": 0.0216, "lr": 7.774790660436857e-06, "epoch": 1.2289608177172062, "percentage": 61.48, "elapsed_time": "3:16:01", "remaining_time": "2:02:50"}
+{"current_steps": 460, "total_steps": 732, "loss": 0.0211, "lr": 7.312028103155426e-06, "epoch": 1.2562180579216355, "percentage": 62.84, "elapsed_time": "3:20:16", "remaining_time": "1:58:25"}
+{"current_steps": 470, "total_steps": 732, "loss": 0.0218, "lr": 6.8553917319085676e-06, "epoch": 1.2834752981260649, "percentage": 64.21, "elapsed_time": "3:24:41", "remaining_time": "1:54:06"}
+{"current_steps": 480, "total_steps": 732, "loss": 0.0211, "lr": 6.405922271624874e-06, "epoch": 1.310732538330494, "percentage": 65.57, "elapsed_time": "3:29:03", "remaining_time": "1:49:45"}
+{"current_steps": 490, "total_steps": 732, "loss": 0.0209, "lr": 5.964644113048079e-06, "epoch": 1.3379897785349233, "percentage": 66.94, "elapsed_time": "3:33:31", "remaining_time": "1:45:27"}
+{"current_steps": 500, "total_steps": 732, "loss": 0.0225, "lr": 5.532562978036964e-06, "epoch": 1.3652470187393526, "percentage": 68.31, "elapsed_time": "3:37:58", "remaining_time": "1:41:08"}
+{"current_steps": 510, "total_steps": 732, "loss": 0.0206, "lr": 5.110663627413695e-06, "epoch": 1.392504258943782, "percentage": 69.67, "elapsed_time": "3:42:20", "remaining_time": "1:36:47"}
+{"current_steps": 520, "total_steps": 732, "loss": 0.0207, "lr": 4.6999076165847214e-06, "epoch": 1.4197614991482113, "percentage": 71.04, "elapsed_time": "3:46:48", "remaining_time": "1:32:28"}
+{"current_steps": 530, "total_steps": 732, "loss": 0.0204, "lr": 4.301231104049359e-06, "epoch": 1.4470187393526406, "percentage": 72.4, "elapsed_time": "3:50:58", "remaining_time": "1:28:01"}
+{"current_steps": 540, "total_steps": 732, "loss": 0.0216, "lr": 3.915542717790759e-06, "epoch": 1.47427597955707, "percentage": 73.77, "elapsed_time": "3:55:19", "remaining_time": "1:23:40"}
+{"current_steps": 550, "total_steps": 732, "loss": 0.02, "lr": 3.543721484411976e-06, "epoch": 1.501533219761499, "percentage": 75.14, "elapsed_time": "3:59:38", "remaining_time": "1:19:17"}
+{"current_steps": 560, "total_steps": 732, "loss": 0.0207, "lr": 3.1866148257368666e-06, "epoch": 1.5287904599659283, "percentage": 76.5, "elapsed_time": "4:03:54", "remaining_time": "1:14:54"}
+{"current_steps": 570, "total_steps": 732, "loss": 0.0189, "lr": 2.845036627441755e-06, "epoch": 1.5560477001703577, "percentage": 77.87, "elapsed_time": "4:08:13", "remaining_time": "1:10:32"}
+{"current_steps": 580, "total_steps": 732, "loss": 0.0194, "lr": 2.5197653841197546e-06, "epoch": 1.583304940374787, "percentage": 79.23, "elapsed_time": "4:12:24", "remaining_time": "1:06:08"}
+{"current_steps": 590, "total_steps": 732, "loss": 0.0203, "lr": 2.211542425005223e-06, "epoch": 1.6105621805792163, "percentage": 80.6, "elapsed_time": "4:16:42", "remaining_time": "1:01:46"}
+{"current_steps": 600, "total_steps": 732, "loss": 0.0194, "lr": 1.9210702244022616e-06, "epoch": 1.6378194207836456, "percentage": 81.97, "elapsed_time": "4:20:56", "remaining_time": "0:57:24"}
+{"current_steps": 610, "total_steps": 732, "loss": 0.022, "lr": 1.6490108006678495e-06, "epoch": 1.665076660988075, "percentage": 83.33, "elapsed_time": "4:25:16", "remaining_time": "0:53:03"}
+{"current_steps": 620, "total_steps": 732, "loss": 0.0196, "lr": 1.3959842073986085e-06, "epoch": 1.6923339011925043, "percentage": 84.7, "elapsed_time": "4:29:38", "remaining_time": "0:48:42"}
+{"current_steps": 630, "total_steps": 732, "loss": 0.0204, "lr": 1.1625671202598875e-06, "epoch": 1.7195911413969336, "percentage": 86.07, "elapsed_time": "4:33:58", "remaining_time": "0:44:21"}
+{"current_steps": 640, "total_steps": 732, "loss": 0.0209, "lr": 9.492915226779809e-07, "epoch": 1.746848381601363, "percentage": 87.43, "elapsed_time": "4:38:23", "remaining_time": "0:40:01"}
+{"current_steps": 650, "total_steps": 732, "loss": 0.0212, "lr": 7.566434933909006e-07, "epoch": 1.7741056218057922, "percentage": 88.8, "elapsed_time": "4:42:35", "remaining_time": "0:35:39"}
+{"current_steps": 660, "total_steps": 732, "loss": 0.0195, "lr": 5.850620986210198e-07, "epoch": 1.8013628620102216, "percentage": 90.16, "elapsed_time": "4:46:49", "remaining_time": "0:31:17"}
+{"current_steps": 670, "total_steps": 732, "loss": 0.0197, "lr": 4.3493839139447716e-07, "epoch": 1.8286201022146509, "percentage": 91.53, "elapsed_time": "4:51:01", "remaining_time": "0:26:55"}
+{"current_steps": 680, "total_steps": 732, "loss": 0.02, "lr": 3.0661452028795335e-07, "epoch": 1.8558773424190802, "percentage": 92.9, "elapsed_time": "4:55:20", "remaining_time": "0:22:35"}
+{"current_steps": 690, "total_steps": 732, "loss": 0.0198, "lr": 2.0038294963413251e-07, "epoch": 1.8831345826235095, "percentage": 94.26, "elapsed_time": "4:59:34", "remaining_time": "0:18:14"}
+{"current_steps": 700, "total_steps": 732, "loss": 0.0192, "lr": 1.1648579296304252e-07, "epoch": 1.9103918228279386, "percentage": 95.63, "elapsed_time": "5:03:57", "remaining_time": "0:13:53"}
+{"current_steps": 710, "total_steps": 732, "loss": 0.02, "lr": 5.51142611984834e-08, "epoch": 1.937649063032368, "percentage": 96.99, "elapsed_time": "5:08:21", "remaining_time": "0:09:33"}
+{"current_steps": 720, "total_steps": 732, "loss": 0.0204, "lr": 1.6408226867118404e-08, "epoch": 1.9649063032367973, "percentage": 98.36, "elapsed_time": "5:12:40", "remaining_time": "0:05:12"}
+{"current_steps": 730, "total_steps": 732, "loss": 0.0194, "lr": 4.5590531348227443e-10, "epoch": 1.9921635434412266, "percentage": 99.73, "elapsed_time": "5:16:56", "remaining_time": "0:00:52"}
+{"current_steps": 732, "total_steps": 732, "epoch": 1.9976149914821124, "percentage": 100.0, "elapsed_time": "5:17:59", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b22fb7b0cef2c149c81b22304bc355d85a6421250869665d1a45b6f853058a35
+size 7480