Upload 8 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

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": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.987146529562982,
+    "total_flos": 2429732487168.0,
+    "train_loss": 1.380241756637891,
+    "train_runtime": 362.534,
+    "train_samples_per_second": 2.146,
+    "train_steps_per_second": 0.066
+}

trainer_log.jsonl

@@ -0,0 +1,25 @@
+{"current_steps": 1, "total_steps": 24, "loss": 1.9565, "lr": 0.0, "epoch": 0.04113110539845758, "percentage": 4.17, "elapsed_time": "0:00:15", "remaining_time": "0:06:02"}
+{"current_steps": 2, "total_steps": 24, "loss": 1.9718, "lr": 3.3333333333333333e-06, "epoch": 0.08226221079691516, "percentage": 8.33, "elapsed_time": "0:00:29", "remaining_time": "0:05:27"}
+{"current_steps": 3, "total_steps": 24, "loss": 1.9117, "lr": 6.666666666666667e-06, "epoch": 0.12339331619537275, "percentage": 12.5, "elapsed_time": "0:00:43", "remaining_time": "0:05:06"}
+{"current_steps": 4, "total_steps": 24, "loss": 1.6466, "lr": 1e-05, "epoch": 0.16452442159383032, "percentage": 16.67, "elapsed_time": "0:00:57", "remaining_time": "0:04:48"}
+{"current_steps": 5, "total_steps": 24, "loss": 1.592, "lr": 9.944154131125643e-06, "epoch": 0.20565552699228792, "percentage": 20.83, "elapsed_time": "0:01:11", "remaining_time": "0:04:32"}
+{"current_steps": 6, "total_steps": 24, "loss": 1.4903, "lr": 9.777864028930705e-06, "epoch": 0.2467866323907455, "percentage": 25.0, "elapsed_time": "0:01:25", "remaining_time": "0:04:17"}
+{"current_steps": 7, "total_steps": 24, "loss": 1.4336, "lr": 9.504844339512096e-06, "epoch": 0.2879177377892031, "percentage": 29.17, "elapsed_time": "0:01:39", "remaining_time": "0:04:02"}
+{"current_steps": 8, "total_steps": 24, "loss": 1.3946, "lr": 9.131193871579975e-06, "epoch": 0.32904884318766064, "percentage": 33.33, "elapsed_time": "0:01:53", "remaining_time": "0:03:47"}
+{"current_steps": 9, "total_steps": 24, "loss": 1.3505, "lr": 8.665259359149132e-06, "epoch": 0.37017994858611825, "percentage": 37.5, "elapsed_time": "0:02:07", "remaining_time": "0:03:32"}
+{"current_steps": 10, "total_steps": 24, "loss": 1.2975, "lr": 8.117449009293668e-06, "epoch": 0.41131105398457585, "percentage": 41.67, "elapsed_time": "0:02:21", "remaining_time": "0:03:18"}
+{"current_steps": 11, "total_steps": 24, "loss": 1.292, "lr": 7.500000000000001e-06, "epoch": 0.4524421593830334, "percentage": 45.83, "elapsed_time": "0:02:35", "remaining_time": "0:03:04"}
+{"current_steps": 12, "total_steps": 24, "loss": 1.2831, "lr": 6.8267051218319766e-06, "epoch": 0.493573264781491, "percentage": 50.0, "elapsed_time": "0:02:49", "remaining_time": "0:02:49"}
+{"current_steps": 13, "total_steps": 24, "loss": 1.2655, "lr": 6.112604669781572e-06, "epoch": 0.5347043701799485, "percentage": 54.17, "elapsed_time": "0:03:03", "remaining_time": "0:02:35"}
+{"current_steps": 14, "total_steps": 24, "loss": 1.2249, "lr": 5.373650467932122e-06, "epoch": 0.5758354755784062, "percentage": 58.33, "elapsed_time": "0:03:17", "remaining_time": "0:02:21"}
+{"current_steps": 15, "total_steps": 24, "loss": 1.216, "lr": 4.626349532067879e-06, "epoch": 0.6169665809768637, "percentage": 62.5, "elapsed_time": "0:03:31", "remaining_time": "0:02:07"}
+{"current_steps": 16, "total_steps": 24, "loss": 1.2203, "lr": 3.887395330218429e-06, "epoch": 0.6580976863753213, "percentage": 66.67, "elapsed_time": "0:03:45", "remaining_time": "0:01:52"}
+{"current_steps": 17, "total_steps": 24, "loss": 1.1852, "lr": 3.173294878168025e-06, "epoch": 0.699228791773779, "percentage": 70.83, "elapsed_time": "0:03:59", "remaining_time": "0:01:38"}
+{"current_steps": 18, "total_steps": 24, "loss": 1.2141, "lr": 2.5000000000000015e-06, "epoch": 0.7403598971722365, "percentage": 75.0, "elapsed_time": "0:04:13", "remaining_time": "0:01:24"}
+{"current_steps": 19, "total_steps": 24, "loss": 1.1936, "lr": 1.8825509907063328e-06, "epoch": 0.781491002570694, "percentage": 79.17, "elapsed_time": "0:04:27", "remaining_time": "0:01:10"}
+{"current_steps": 20, "total_steps": 24, "loss": 1.203, "lr": 1.3347406408508695e-06, "epoch": 0.8226221079691517, "percentage": 83.33, "elapsed_time": "0:04:41", "remaining_time": "0:00:56"}
+{"current_steps": 21, "total_steps": 24, "loss": 1.1874, "lr": 8.688061284200266e-07, "epoch": 0.8637532133676092, "percentage": 87.5, "elapsed_time": "0:04:55", "remaining_time": "0:00:42"}
+{"current_steps": 22, "total_steps": 24, "loss": 1.179, "lr": 4.951556604879049e-07, "epoch": 0.9048843187660668, "percentage": 91.67, "elapsed_time": "0:05:09", "remaining_time": "0:00:28"}
+{"current_steps": 23, "total_steps": 24, "loss": 1.2445, "lr": 2.2213597106929608e-07, "epoch": 0.9460154241645244, "percentage": 95.83, "elapsed_time": "0:05:23", "remaining_time": "0:00:14"}
+{"current_steps": 24, "total_steps": 24, "loss": 1.1723, "lr": 5.584586887435739e-08, "epoch": 0.987146529562982, "percentage": 100.0, "elapsed_time": "0:05:37", "remaining_time": "0:00:00"}
+{"current_steps": 24, "total_steps": 24, "epoch": 0.987146529562982, "percentage": 100.0, "elapsed_time": "0:06:02", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,211 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.987146529562982,
+  "eval_steps": 500,
+  "global_step": 24,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04113110539845758,
+      "grad_norm": 11.870390470134398,
+      "learning_rate": 0.0,
+      "loss": 1.9565,
+      "step": 1
+    },
+    {
+      "epoch": 0.08226221079691516,
+      "grad_norm": 12.009526817812961,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.9718,
+      "step": 2
+    },
+    {
+      "epoch": 0.12339331619537275,
+      "grad_norm": 10.36223708009221,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.9117,
+      "step": 3
+    },
+    {
+      "epoch": 0.16452442159383032,
+      "grad_norm": 6.001358940559066,
+      "learning_rate": 1e-05,
+      "loss": 1.6466,
+      "step": 4
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 5.288343588799703,
+      "learning_rate": 9.944154131125643e-06,
+      "loss": 1.592,
+      "step": 5
+    },
+    {
+      "epoch": 0.2467866323907455,
+      "grad_norm": 4.932448230700685,
+      "learning_rate": 9.777864028930705e-06,
+      "loss": 1.4903,
+      "step": 6
+    },
+    {
+      "epoch": 0.2879177377892031,
+      "grad_norm": 8.254123753090488,
+      "learning_rate": 9.504844339512096e-06,
+      "loss": 1.4336,
+      "step": 7
+    },
+    {
+      "epoch": 0.32904884318766064,
+      "grad_norm": 5.5899004421905865,
+      "learning_rate": 9.131193871579975e-06,
+      "loss": 1.3946,
+      "step": 8
+    },
+    {
+      "epoch": 0.37017994858611825,
+      "grad_norm": 4.385399717154605,
+      "learning_rate": 8.665259359149132e-06,
+      "loss": 1.3505,
+      "step": 9
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 3.4785474789966218,
+      "learning_rate": 8.117449009293668e-06,
+      "loss": 1.2975,
+      "step": 10
+    },
+    {
+      "epoch": 0.4524421593830334,
+      "grad_norm": 3.678459810428862,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.292,
+      "step": 11
+    },
+    {
+      "epoch": 0.493573264781491,
+      "grad_norm": 3.2622487154200623,
+      "learning_rate": 6.8267051218319766e-06,
+      "loss": 1.2831,
+      "step": 12
+    },
+    {
+      "epoch": 0.5347043701799485,
+      "grad_norm": 3.256780117492594,
+      "learning_rate": 6.112604669781572e-06,
+      "loss": 1.2655,
+      "step": 13
+    },
+    {
+      "epoch": 0.5758354755784062,
+      "grad_norm": 3.0556247184293808,
+      "learning_rate": 5.373650467932122e-06,
+      "loss": 1.2249,
+      "step": 14
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 2.565564759239293,
+      "learning_rate": 4.626349532067879e-06,
+      "loss": 1.216,
+      "step": 15
+    },
+    {
+      "epoch": 0.6580976863753213,
+      "grad_norm": 2.551619545114463,
+      "learning_rate": 3.887395330218429e-06,
+      "loss": 1.2203,
+      "step": 16
+    },
+    {
+      "epoch": 0.699228791773779,
+      "grad_norm": 2.1687201894188677,
+      "learning_rate": 3.173294878168025e-06,
+      "loss": 1.1852,
+      "step": 17
+    },
+    {
+      "epoch": 0.7403598971722365,
+      "grad_norm": 2.362660106641768,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 1.2141,
+      "step": 18
+    },
+    {
+      "epoch": 0.781491002570694,
+      "grad_norm": 2.4076108934592817,
+      "learning_rate": 1.8825509907063328e-06,
+      "loss": 1.1936,
+      "step": 19
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "grad_norm": 2.1775779534988646,
+      "learning_rate": 1.3347406408508695e-06,
+      "loss": 1.203,
+      "step": 20
+    },
+    {
+      "epoch": 0.8637532133676092,
+      "grad_norm": 2.33920988457465,
+      "learning_rate": 8.688061284200266e-07,
+      "loss": 1.1874,
+      "step": 21
+    },
+    {
+      "epoch": 0.9048843187660668,
+      "grad_norm": 2.276990062852866,
+      "learning_rate": 4.951556604879049e-07,
+      "loss": 1.179,
+      "step": 22
+    },
+    {
+      "epoch": 0.9460154241645244,
+      "grad_norm": 2.143656166201497,
+      "learning_rate": 2.2213597106929608e-07,
+      "loss": 1.2445,
+      "step": 23
+    },
+    {
+      "epoch": 0.987146529562982,
+      "grad_norm": 1.9960258314108954,
+      "learning_rate": 5.584586887435739e-08,
+      "loss": 1.1723,
+      "step": 24
+    },
+    {
+      "epoch": 0.987146529562982,
+      "step": 24,
+      "total_flos": 2429732487168.0,
+      "train_loss": 1.380241756637891,
+      "train_runtime": 362.534,
+      "train_samples_per_second": 2.146,
+      "train_steps_per_second": 0.066
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 24,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 2429732487168.0,
+  "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:a0ec64969346b040869149595c82497f947d4cfb31dc1d69b27d425358905a2a
+size 7608