Training in progress, step 500, checkpoint

.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
+last-checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text

last-checkpoint/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

last-checkpoint/config.json

@@ -15,7 +15,7 @@
   "pad_token_id": 0,
   "rms_norm_eps": 1e-06,
   "rope_theta": 1000000.0,
-  "transformers_version": "5.15.0",
+  "transformers_version": "5.15.1",
   "use_cache": false,
   "vocab_size": 151936
 }

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81de9b280c9780cf3feaf944ed951aca1ee11fa1f451d8fe3983a73cd5acf1ff
+oid sha256:61bffa07b45ea172ed2e6316fca83698825d827432b4eaa5d1e39c152b7de39b
 size 1235573136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af4dab1bd40e26061d7373627d7696e6ebcd35c8a058d709a83490dc1881eb7c
+oid sha256:8514b4945a797b24abc9ae3ec07458e72f84f4934fbd92b37d3888f233f8e67b
 size 2471218763

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74d64db17f5541ae52946e5b4e988b9c8496b896a7fd08f53e3196d74b6433cb
+oid sha256:68b03f74e10591ff22477365642275703166a34b306471da2a9df3e87497356f
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be625e9e3b7c2d0674d4d1ce1044104bf1d523b3db3eb682bb066436988eb458
+oid sha256:0471ce3745a36e49a3e0d19eac020ddc42dff8b92447d06fa38e6a682e228b19
 size 1465

last-checkpoint/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e2b7649a086fbb9771cd78ec5b7ffa7069e16a82424a382950fedfa1e057861
+size 11421991

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008,
+  "epoch": 0.01,
   "eval_steps": 500,
-  "global_step": 400,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -288,6 +288,76 @@
       "learning_rate": 0.0002982024048096192,
       "loss": 7.4337646484375,
       "step": 400
+    },
+    {
+      "epoch": 0.0082,
+      "grad_norm": 28.452800750732422,
+      "learning_rate": 0.00029814228456913827,
+      "loss": 102.99000244140625,
+      "step": 410
+    },
+    {
+      "epoch": 0.0084,
+      "grad_norm": 12.671554565429688,
+      "learning_rate": 0.00029808216432865726,
+      "loss": 83.27249755859376,
+      "step": 420
+    },
+    {
+      "epoch": 0.0086,
+      "grad_norm": 7.306222438812256,
+      "learning_rate": 0.0002980220440881763,
+      "loss": 73.54000854492188,
+      "step": 430
+    },
+    {
+      "epoch": 0.0088,
+      "grad_norm": 11.418675422668457,
+      "learning_rate": 0.00029796192384769535,
+      "loss": 77.23857421875,
+      "step": 440
+    },
+    {
+      "epoch": 0.009,
+      "grad_norm": 8.655750274658203,
+      "learning_rate": 0.0002979018036072144,
+      "loss": 77.81395263671875,
+      "step": 450
+    },
+    {
+      "epoch": 0.0092,
+      "grad_norm": 11.155708312988281,
+      "learning_rate": 0.00029784168336673345,
+      "loss": 78.6078125,
+      "step": 460
+    },
+    {
+      "epoch": 0.0094,
+      "grad_norm": 9.934618949890137,
+      "learning_rate": 0.0002977815631262525,
+      "loss": 71.70912475585938,
+      "step": 470
+    },
+    {
+      "epoch": 0.0096,
+      "grad_norm": 7.762029647827148,
+      "learning_rate": 0.00029772144288577155,
+      "loss": 73.4228515625,
+      "step": 480
+    },
+    {
+      "epoch": 0.0098,
+      "grad_norm": 9.61263370513916,
+      "learning_rate": 0.00029766132264529054,
+      "loss": 75.76692504882813,
+      "step": 490
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 11.183115005493164,
+      "learning_rate": 0.0002976012024048096,
+      "loss": 78.96190795898437,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -307,7 +377,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7557749932032000.0,
+  "total_flos": 8161860202859520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edcf268bd411db3d29ef48993a8be91c48e0928ee9333782a1c880f5f6a50c85
+oid sha256:3ead25e90961f39a7cf235a53c52302322d446327bb423dad890f04c47276211
 size 5201