Upload task output 0ace46bc-8f88-4e70-95b9-9502b5a4d1dc

config.json

@@ -4,11 +4,38 @@
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 151643,
+  "dtype": "bfloat16",
   "eos_token_id": 151643,
   "hidden_act": "silu",
   "hidden_size": 896,
   "initializer_range": 0.02,
   "intermediate_size": 4864,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
   "max_position_embeddings": 32768,
   "max_window_layers": 24,
   "model_type": "qwen2",
@@ -16,9 +43,13 @@
   "num_hidden_layers": 24,
   "num_key_value_heads": 2,
   "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
   "rope_scaling": null,
-  "rope_theta": 1000000.0,
-  "sliding_window": 32768,
+  "rope_theta": 10000.0,
+  "sliding_window": null,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.51.3",

loss.txt

@@ -0,0 +1 @@
+200,1.234911322593689

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0d813fdcbbe23f03f94a462d9e34860c669bba2b2c2b035d0a4b6e425f7d2ec
+oid sha256:5b55eeba4a93cecf11ad953d8b45fdeb11144b309b6e9f9f4f119bf54a5c016b
 size 988097824

special_tokens_map.json

@@ -1,19 +1,17 @@
 {
-  "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|>"
-  ],
+  "<|box_end|>": "<|box_end|>",
+  "<|box_start|>": "<|box_start|>",
+  "<|im_end|>": "<|im_end|>",
+  "<|im_start|>": "<|im_start|>",
+  "<|image_pad|>": "<|image_pad|>",
+  "<|object_ref_end|>": "<|object_ref_end|>",
+  "<|object_ref_start|>": "<|object_ref_start|>",
+  "<|quad_end|>": "<|quad_end|>",
+  "<|quad_start|>": "<|quad_start|>",
+  "<|video_pad|>": "<|video_pad|>",
+  "<|vision_end|>": "<|vision_end|>",
+  "<|vision_pad|>": "<|vision_pad|>",
+  "<|vision_start|>": "<|vision_start|>",
   "eos_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
-size 11421896
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

tokenizer_config.json

@@ -1,5 +1,17 @@
 {
-  "add_bos_token": false,
+  "<|box_end|>": "<|box_end|>",
+  "<|box_start|>": "<|box_start|>",
+  "<|im_end|>": "<|im_end|>",
+  "<|im_start|>": "<|im_start|>",
+  "<|image_pad|>": "<|image_pad|>",
+  "<|object_ref_end|>": "<|object_ref_end|>",
+  "<|object_ref_start|>": "<|object_ref_start|>",
+  "<|quad_end|>": "<|quad_end|>",
+  "<|quad_start|>": "<|quad_start|>",
+  "<|video_pad|>": "<|video_pad|>",
+  "<|vision_end|>": "<|vision_end|>",
+  "<|vision_pad|>": "<|vision_pad|>",
+  "<|vision_start|>": "<|vision_start|>",
   "add_prefix_space": false,
   "added_tokens_decoder": {
     "151643": {
@@ -179,27 +191,29 @@
       "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|>"
-  ],
+  "backend": "tokenizers",
   "bos_token": null,
   "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "errors": "replace",
-  "extra_special_tokens": {},
+  "extra_special_tokens": {
+    "<|box_end|>": "<|box_end|>",
+    "<|box_start|>": "<|box_start|>",
+    "<|im_end|>": "<|im_end|>",
+    "<|im_start|>": "<|im_start|>",
+    "<|image_pad|>": "<|image_pad|>",
+    "<|object_ref_end|>": "<|object_ref_end|>",
+    "<|object_ref_start|>": "<|object_ref_start|>",
+    "<|quad_end|>": "<|quad_end|>",
+    "<|quad_start|>": "<|quad_start|>",
+    "<|video_pad|>": "<|video_pad|>",
+    "<|vision_end|>": "<|vision_end|>",
+    "<|vision_pad|>": "<|vision_pad|>",
+    "<|vision_start|>": "<|vision_start|>"
+  },
+  "is_local": false,
+  "local_files_only": false,
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,

trainer_state.json

@@ -0,0 +1,322 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.025,
+      "grad_norm": 40.75,
+      "learning_rate": 1.2215565714285715e-05,
+      "loss": 3.6599,
+      "step": 5
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 15.9375,
+      "learning_rate": 2.7485022857142857e-05,
+      "loss": 2.5999,
+      "step": 10
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 13.6875,
+      "learning_rate": 4.2754480000000004e-05,
+      "loss": 1.9074,
+      "step": 15
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 8.1875,
+      "learning_rate": 5.802393714285714e-05,
+      "loss": 1.72,
+      "step": 20
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 7.53125,
+      "learning_rate": 7.329339428571428e-05,
+      "loss": 1.6114,
+      "step": 25
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 7.59375,
+      "learning_rate": 8.856285142857144e-05,
+      "loss": 1.6335,
+      "step": 30
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 6.78125,
+      "learning_rate": 0.00010383230857142857,
+      "loss": 1.5292,
+      "step": 35
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 7.3125,
+      "learning_rate": 0.00010688538037339344,
+      "loss": 1.5352,
+      "step": 40
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 6.25,
+      "learning_rate": 0.0001068820506977537,
+      "loss": 1.5399,
+      "step": 45
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 6.25,
+      "learning_rate": 0.00010687615995902611,
+      "loss": 1.5242,
+      "step": 50
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 5.71875,
+      "learning_rate": 0.00010686770853363879,
+      "loss": 1.5208,
+      "step": 55
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 6.09375,
+      "learning_rate": 0.00010685669696165211,
+      "loss": 1.5109,
+      "step": 60
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 5.8125,
+      "learning_rate": 0.0001068431259467241,
+      "loss": 1.4876,
+      "step": 65
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 6.125,
+      "learning_rate": 0.00010682699635606553,
+      "loss": 1.4368,
+      "step": 70
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 5.34375,
+      "learning_rate": 0.0001068083092203845,
+      "loss": 1.4979,
+      "step": 75
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 5.5625,
+      "learning_rate": 0.00010678706573382047,
+      "loss": 1.4688,
+      "step": 80
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 5.71875,
+      "learning_rate": 0.00010676326725386813,
+      "loss": 1.4732,
+      "step": 85
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 5.65625,
+      "learning_rate": 0.00010673691530129053,
+      "loss": 1.4505,
+      "step": 90
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 6.34375,
+      "learning_rate": 0.00010670801156002194,
+      "loss": 1.4747,
+      "step": 95
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 5.3125,
+      "learning_rate": 0.00010667655787706019,
+      "loss": 1.4145,
+      "step": 100
+    },
+    {
+      "epoch": 0.525,
+      "grad_norm": 5.0,
+      "learning_rate": 0.00010664255626234872,
+      "loss": 1.4288,
+      "step": 105
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 5.03125,
+      "learning_rate": 0.00010660600888864813,
+      "loss": 1.431,
+      "step": 110
+    },
+    {
+      "epoch": 0.575,
+      "grad_norm": 5.0,
+      "learning_rate": 0.00010656691809139731,
+      "loss": 1.406,
+      "step": 115
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 4.71875,
+      "learning_rate": 0.00010652528636856418,
+      "loss": 1.4174,
+      "step": 120
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 5.375,
+      "learning_rate": 0.00010648111638048613,
+      "loss": 1.3684,
+      "step": 125
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 4.9375,
+      "learning_rate": 0.00010643441094969993,
+      "loss": 1.4044,
+      "step": 130
+    },
+    {
+      "epoch": 0.675,
+      "grad_norm": 5.1875,
+      "learning_rate": 0.0001063851730607615,
+      "loss": 1.3708,
+      "step": 135
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 4.75,
+      "learning_rate": 0.00010633340586005505,
+      "loss": 1.3198,
+      "step": 140
+    },
+    {
+      "epoch": 0.725,
+      "grad_norm": 5.375,
+      "learning_rate": 0.00010627911265559208,
+      "loss": 1.4137,
+      "step": 145
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 5.15625,
+      "learning_rate": 0.00010622229691680005,
+      "loss": 1.3347,
+      "step": 150
+    },
+    {
+      "epoch": 0.775,
+      "grad_norm": 4.6875,
+      "learning_rate": 0.00010616296227430056,
+      "loss": 1.338,
+      "step": 155
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 5.0625,
+      "learning_rate": 0.00010610111251967746,
+      "loss": 1.3591,
+      "step": 160
+    },
+    {
+      "epoch": 0.825,
+      "grad_norm": 5.0,
+      "learning_rate": 0.00010603675160523444,
+      "loss": 1.3449,
+      "step": 165
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 5.15625,
+      "learning_rate": 0.00010596988364374265,
+      "loss": 1.3247,
+      "step": 170
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 6.0,
+      "learning_rate": 0.00010590051290817767,
+      "loss": 1.3147,
+      "step": 175
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 4.5625,
+      "learning_rate": 0.00010582864383144663,
+      "loss": 1.3264,
+      "step": 180
+    },
+    {
+      "epoch": 0.925,
+      "grad_norm": 4.71875,
+      "learning_rate": 0.00010575428100610488,
+      "loss": 1.2702,
+      "step": 185
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 4.46875,
+      "learning_rate": 0.00010567742918406246,
+      "loss": 1.3076,
+      "step": 190
+    },
+    {
+      "epoch": 0.975,
+      "grad_norm": 4.46875,
+      "learning_rate": 0.0001055980932762806,
+      "loss": 1.2769,
+      "step": 195
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.59375,
+      "learning_rate": 0.00010551627835245768,
+      "loss": 1.2735,
+      "step": 200
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.234911322593689,
+      "eval_runtime": 0.3775,
+      "eval_samples_per_second": 7.948,
+      "eval_steps_per_second": 7.948,
+      "step": 200
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 2000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.46279712014336e+17,
+  "train_batch_size": 140,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9335070a47dedbb24e52c226990e18916ebe5bfee099d3faddf68095a47d9160
+size 5688