Training in progress, step 500

.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

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "gate_proj",
+    "k_proj",
+    "down_proj",
+    "up_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": true
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fed271f1467dfe2955d0a83d772e7bc039e67576a4a78e40af30f04d40064dc9
+size 645976488

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
+}

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": "<|endoftext|>",
+    "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 +1,208 @@
+{
+  "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 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",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_log.jsonl

@@ -0,0 +1,50 @@
+{"current_steps": 10, "total_steps": 3573, "loss": 1.7981, "lr": 1.3966480446927373e-06, "epoch": 0.008396305625524769, "percentage": 0.28, "elapsed_time": "0:00:30", "remaining_time": "2:59:09"}
+{"current_steps": 20, "total_steps": 3573, "loss": 1.7816, "lr": 2.7932960893854746e-06, "epoch": 0.016792611251049538, "percentage": 0.56, "elapsed_time": "0:00:42", "remaining_time": "2:05:34"}
+{"current_steps": 30, "total_steps": 3573, "loss": 1.6797, "lr": 4.189944134078212e-06, "epoch": 0.02518891687657431, "percentage": 0.84, "elapsed_time": "0:00:54", "remaining_time": "1:47:34"}
+{"current_steps": 40, "total_steps": 3573, "loss": 1.5657, "lr": 5.586592178770949e-06, "epoch": 0.033585222502099076, "percentage": 1.12, "elapsed_time": "0:01:06", "remaining_time": "1:38:30"}
+{"current_steps": 50, "total_steps": 3573, "loss": 1.4759, "lr": 6.983240223463687e-06, "epoch": 0.041981528127623846, "percentage": 1.4, "elapsed_time": "0:01:19", "remaining_time": "1:32:58"}
+{"current_steps": 60, "total_steps": 3573, "loss": 1.4312, "lr": 8.379888268156424e-06, "epoch": 0.05037783375314862, "percentage": 1.68, "elapsed_time": "0:01:31", "remaining_time": "1:29:12"}
+{"current_steps": 70, "total_steps": 3573, "loss": 1.4082, "lr": 9.776536312849161e-06, "epoch": 0.05877413937867338, "percentage": 1.96, "elapsed_time": "0:01:43", "remaining_time": "1:26:26"}
+{"current_steps": 80, "total_steps": 3573, "loss": 1.4263, "lr": 1.1173184357541899e-05, "epoch": 0.06717044500419815, "percentage": 2.24, "elapsed_time": "0:01:55", "remaining_time": "1:24:19"}
+{"current_steps": 90, "total_steps": 3573, "loss": 1.4216, "lr": 1.2569832402234637e-05, "epoch": 0.07556675062972293, "percentage": 2.52, "elapsed_time": "0:02:08", "remaining_time": "1:22:42"}
+{"current_steps": 100, "total_steps": 3573, "loss": 1.4207, "lr": 1.3966480446927374e-05, "epoch": 0.08396305625524769, "percentage": 2.8, "elapsed_time": "0:02:20", "remaining_time": "1:21:18"}
+{"current_steps": 110, "total_steps": 3573, "loss": 1.399, "lr": 1.5363128491620113e-05, "epoch": 0.09235936188077246, "percentage": 3.08, "elapsed_time": "0:02:32", "remaining_time": "1:20:06"}
+{"current_steps": 120, "total_steps": 3573, "loss": 1.404, "lr": 1.675977653631285e-05, "epoch": 0.10075566750629723, "percentage": 3.36, "elapsed_time": "0:02:44", "remaining_time": "1:19:05"}
+{"current_steps": 130, "total_steps": 3573, "loss": 1.4057, "lr": 1.8156424581005588e-05, "epoch": 0.109151973131822, "percentage": 3.64, "elapsed_time": "0:02:57", "remaining_time": "1:18:10"}
+{"current_steps": 140, "total_steps": 3573, "loss": 1.3956, "lr": 1.9553072625698323e-05, "epoch": 0.11754827875734676, "percentage": 3.92, "elapsed_time": "0:03:09", "remaining_time": "1:17:22"}
+{"current_steps": 150, "total_steps": 3573, "loss": 1.4179, "lr": 2.0949720670391062e-05, "epoch": 0.12594458438287154, "percentage": 4.2, "elapsed_time": "0:03:21", "remaining_time": "1:16:39"}
+{"current_steps": 160, "total_steps": 3573, "loss": 1.412, "lr": 2.2346368715083797e-05, "epoch": 0.1343408900083963, "percentage": 4.48, "elapsed_time": "0:03:33", "remaining_time": "1:16:00"}
+{"current_steps": 170, "total_steps": 3573, "loss": 1.39, "lr": 2.3743016759776536e-05, "epoch": 0.14273719563392107, "percentage": 4.76, "elapsed_time": "0:03:46", "remaining_time": "1:15:24"}
+{"current_steps": 180, "total_steps": 3573, "loss": 1.4004, "lr": 2.5139664804469275e-05, "epoch": 0.15113350125944586, "percentage": 5.04, "elapsed_time": "0:03:58", "remaining_time": "1:14:50"}
+{"current_steps": 190, "total_steps": 3573, "loss": 1.386, "lr": 2.6536312849162014e-05, "epoch": 0.15952980688497062, "percentage": 5.32, "elapsed_time": "0:04:10", "remaining_time": "1:14:18"}
+{"current_steps": 200, "total_steps": 3573, "loss": 1.4012, "lr": 2.793296089385475e-05, "epoch": 0.16792611251049538, "percentage": 5.6, "elapsed_time": "0:04:22", "remaining_time": "1:13:50"}
+{"current_steps": 210, "total_steps": 3573, "loss": 1.3707, "lr": 2.9329608938547488e-05, "epoch": 0.17632241813602015, "percentage": 5.88, "elapsed_time": "0:04:34", "remaining_time": "1:13:23"}
+{"current_steps": 220, "total_steps": 3573, "loss": 1.4125, "lr": 3.0726256983240227e-05, "epoch": 0.1847187237615449, "percentage": 6.16, "elapsed_time": "0:04:47", "remaining_time": "1:12:57"}
+{"current_steps": 230, "total_steps": 3573, "loss": 1.3699, "lr": 3.212290502793296e-05, "epoch": 0.19311502938706968, "percentage": 6.44, "elapsed_time": "0:04:59", "remaining_time": "1:12:31"}
+{"current_steps": 240, "total_steps": 3573, "loss": 1.374, "lr": 3.35195530726257e-05, "epoch": 0.20151133501259447, "percentage": 6.72, "elapsed_time": "0:05:11", "remaining_time": "1:12:06"}
+{"current_steps": 250, "total_steps": 3573, "loss": 1.3788, "lr": 3.491620111731844e-05, "epoch": 0.20990764063811923, "percentage": 7.0, "elapsed_time": "0:05:23", "remaining_time": "1:11:42"}
+{"current_steps": 260, "total_steps": 3573, "loss": 1.3565, "lr": 3.6312849162011175e-05, "epoch": 0.218303946263644, "percentage": 7.28, "elapsed_time": "0:05:35", "remaining_time": "1:11:20"}
+{"current_steps": 270, "total_steps": 3573, "loss": 1.3521, "lr": 3.770949720670392e-05, "epoch": 0.22670025188916876, "percentage": 7.56, "elapsed_time": "0:05:48", "remaining_time": "1:10:58"}
+{"current_steps": 280, "total_steps": 3573, "loss": 1.3613, "lr": 3.9106145251396646e-05, "epoch": 0.23509655751469352, "percentage": 7.84, "elapsed_time": "0:06:00", "remaining_time": "1:10:37"}
+{"current_steps": 290, "total_steps": 3573, "loss": 1.36, "lr": 4.050279329608939e-05, "epoch": 0.2434928631402183, "percentage": 8.12, "elapsed_time": "0:06:12", "remaining_time": "1:10:17"}
+{"current_steps": 300, "total_steps": 3573, "loss": 1.3799, "lr": 4.1899441340782123e-05, "epoch": 0.2518891687657431, "percentage": 8.4, "elapsed_time": "0:06:24", "remaining_time": "1:09:58"}
+{"current_steps": 310, "total_steps": 3573, "loss": 1.3797, "lr": 4.3296089385474866e-05, "epoch": 0.26028547439126787, "percentage": 8.68, "elapsed_time": "0:06:37", "remaining_time": "1:09:39"}
+{"current_steps": 320, "total_steps": 3573, "loss": 1.3675, "lr": 4.4692737430167594e-05, "epoch": 0.2686817800167926, "percentage": 8.96, "elapsed_time": "0:06:49", "remaining_time": "1:09:21"}
+{"current_steps": 330, "total_steps": 3573, "loss": 1.3888, "lr": 4.6089385474860336e-05, "epoch": 0.2770780856423174, "percentage": 9.24, "elapsed_time": "0:07:01", "remaining_time": "1:09:02"}
+{"current_steps": 340, "total_steps": 3573, "loss": 1.3626, "lr": 4.748603351955307e-05, "epoch": 0.28547439126784213, "percentage": 9.52, "elapsed_time": "0:07:13", "remaining_time": "1:08:45"}
+{"current_steps": 350, "total_steps": 3573, "loss": 1.3598, "lr": 4.8882681564245814e-05, "epoch": 0.2938706968933669, "percentage": 9.8, "elapsed_time": "0:07:26", "remaining_time": "1:08:27"}
+{"current_steps": 360, "total_steps": 3573, "loss": 1.3933, "lr": 4.9999952257225154e-05, "epoch": 0.3022670025188917, "percentage": 10.08, "elapsed_time": "0:07:38", "remaining_time": "1:08:10"}
+{"current_steps": 370, "total_steps": 3573, "loss": 1.3723, "lr": 4.9998281279252004e-05, "epoch": 0.31066330814441645, "percentage": 10.36, "elapsed_time": "0:07:50", "remaining_time": "1:07:53"}
+{"current_steps": 380, "total_steps": 3573, "loss": 1.3889, "lr": 4.9994223344882976e-05, "epoch": 0.31905961376994124, "percentage": 10.64, "elapsed_time": "0:08:02", "remaining_time": "1:07:36"}
+{"current_steps": 390, "total_steps": 3573, "loss": 1.3757, "lr": 4.9987778841589184e-05, "epoch": 0.327455919395466, "percentage": 10.92, "elapsed_time": "0:08:15", "remaining_time": "1:07:20"}
+{"current_steps": 400, "total_steps": 3573, "loss": 1.3602, "lr": 4.997894838472288e-05, "epoch": 0.33585222502099077, "percentage": 11.2, "elapsed_time": "0:08:27", "remaining_time": "1:07:04"}
+{"current_steps": 410, "total_steps": 3573, "loss": 1.3483, "lr": 4.996773281745864e-05, "epoch": 0.34424853064651556, "percentage": 11.47, "elapsed_time": "0:08:39", "remaining_time": "1:06:48"}
+{"current_steps": 420, "total_steps": 3573, "loss": 1.3773, "lr": 4.9954133210712904e-05, "epoch": 0.3526448362720403, "percentage": 11.75, "elapsed_time": "0:08:51", "remaining_time": "1:06:32"}
+{"current_steps": 430, "total_steps": 3573, "loss": 1.3817, "lr": 4.9938150863041666e-05, "epoch": 0.3610411418975651, "percentage": 12.03, "elapsed_time": "0:09:03", "remaining_time": "1:06:15"}
+{"current_steps": 440, "total_steps": 3573, "loss": 1.3436, "lr": 4.991978730051653e-05, "epoch": 0.3694374475230898, "percentage": 12.31, "elapsed_time": "0:09:16", "remaining_time": "1:05:59"}
+{"current_steps": 450, "total_steps": 3573, "loss": 1.376, "lr": 4.9899044276578956e-05, "epoch": 0.3778337531486146, "percentage": 12.59, "elapsed_time": "0:09:28", "remaining_time": "1:05:42"}
+{"current_steps": 460, "total_steps": 3573, "loss": 1.3699, "lr": 4.987592377187286e-05, "epoch": 0.38623005877413935, "percentage": 12.87, "elapsed_time": "0:09:40", "remaining_time": "1:05:27"}
+{"current_steps": 470, "total_steps": 3573, "loss": 1.3831, "lr": 4.985042799405547e-05, "epoch": 0.39462636439966414, "percentage": 13.15, "elapsed_time": "0:09:52", "remaining_time": "1:05:11"}
+{"current_steps": 480, "total_steps": 3573, "loss": 1.3579, "lr": 4.982255937758657e-05, "epoch": 0.40302267002518893, "percentage": 13.43, "elapsed_time": "0:10:04", "remaining_time": "1:04:56"}
+{"current_steps": 490, "total_steps": 3573, "loss": 1.348, "lr": 4.9792320583495975e-05, "epoch": 0.41141897565071367, "percentage": 13.71, "elapsed_time": "0:10:16", "remaining_time": "1:04:41"}
+{"current_steps": 500, "total_steps": 3573, "loss": 1.3474, "lr": 4.975971449912952e-05, "epoch": 0.41981528127623846, "percentage": 13.99, "elapsed_time": "0:10:29", "remaining_time": "1:04:26"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40daf5eb189a8ece98e0109b19819bcb42aaa6f0ea4951bf50c6c55d73ab199b
+size 7224