Training in progress, step 200

.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 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33fb3aa08eb4c4949e4934fe5b5dd6d500b7d122eeb830debb25d08774a9ae68
+size 295488936

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": "<|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
+}

trainer_log.jsonl

@@ -0,0 +1,22 @@
+{"current_steps": 10, "total_steps": 1455, "loss": 0.3919, "lr": 6.1643835616438354e-06, "epoch": 0.020607934054611025, "percentage": 0.69, "elapsed_time": "0:05:34", "remaining_time": "13:26:01"}
+{"current_steps": 20, "total_steps": 1455, "loss": 0.3437, "lr": 1.3013698630136986e-05, "epoch": 0.04121586810922205, "percentage": 1.37, "elapsed_time": "0:11:06", "remaining_time": "13:16:30"}
+{"current_steps": 30, "total_steps": 1455, "loss": 0.3129, "lr": 1.9863013698630137e-05, "epoch": 0.061823802163833076, "percentage": 2.06, "elapsed_time": "0:16:58", "remaining_time": "13:26:11"}
+{"current_steps": 40, "total_steps": 1455, "loss": 0.2943, "lr": 2.671232876712329e-05, "epoch": 0.0824317362184441, "percentage": 2.75, "elapsed_time": "0:22:47", "remaining_time": "13:26:29"}
+{"current_steps": 50, "total_steps": 1455, "loss": 0.2838, "lr": 3.356164383561644e-05, "epoch": 0.10303967027305512, "percentage": 3.44, "elapsed_time": "0:28:49", "remaining_time": "13:30:05"}
+{"current_steps": 60, "total_steps": 1455, "loss": 0.2776, "lr": 4.041095890410959e-05, "epoch": 0.12364760432766615, "percentage": 4.12, "elapsed_time": "0:35:01", "remaining_time": "13:34:21"}
+{"current_steps": 70, "total_steps": 1455, "loss": 0.2653, "lr": 4.726027397260274e-05, "epoch": 0.14425553838227717, "percentage": 4.81, "elapsed_time": "0:40:49", "remaining_time": "13:27:44"}
+{"current_steps": 80, "total_steps": 1455, "loss": 0.2705, "lr": 5.4109589041095895e-05, "epoch": 0.1648634724368882, "percentage": 5.5, "elapsed_time": "0:46:03", "remaining_time": "13:11:41"}
+{"current_steps": 90, "total_steps": 1455, "loss": 0.2418, "lr": 6.095890410958904e-05, "epoch": 0.18547140649149924, "percentage": 6.19, "elapsed_time": "0:51:50", "remaining_time": "13:06:17"}
+{"current_steps": 100, "total_steps": 1455, "loss": 0.2435, "lr": 6.78082191780822e-05, "epoch": 0.20607934054611024, "percentage": 6.87, "elapsed_time": "0:56:54", "remaining_time": "12:51:09"}
+{"current_steps": 100, "total_steps": 1455, "eval_loss": 0.23216360807418823, "epoch": 0.20607934054611024, "percentage": 6.87, "elapsed_time": "0:59:28", "remaining_time": "13:25:51"}
+{"current_steps": 110, "total_steps": 1455, "loss": 0.2408, "lr": 7.465753424657535e-05, "epoch": 0.22668727460072127, "percentage": 7.56, "elapsed_time": "1:04:47", "remaining_time": "13:12:07"}
+{"current_steps": 120, "total_steps": 1455, "loss": 0.2336, "lr": 8.15068493150685e-05, "epoch": 0.2472952086553323, "percentage": 8.25, "elapsed_time": "1:09:52", "remaining_time": "12:57:23"}
+{"current_steps": 130, "total_steps": 1455, "loss": 0.2388, "lr": 8.835616438356165e-05, "epoch": 0.2679031427099433, "percentage": 8.93, "elapsed_time": "1:15:40", "remaining_time": "12:51:21"}
+{"current_steps": 140, "total_steps": 1455, "loss": 0.2218, "lr": 9.520547945205481e-05, "epoch": 0.28851107676455434, "percentage": 9.62, "elapsed_time": "1:20:58", "remaining_time": "12:40:39"}
+{"current_steps": 150, "total_steps": 1455, "loss": 0.2356, "lr": 9.999870401165987e-05, "epoch": 0.3091190108191654, "percentage": 10.31, "elapsed_time": "1:26:21", "remaining_time": "12:31:18"}
+{"current_steps": 160, "total_steps": 1455, "loss": 0.2323, "lr": 9.99756660878697e-05, "epoch": 0.3297269448737764, "percentage": 11.0, "elapsed_time": "1:31:39", "remaining_time": "12:21:53"}
+{"current_steps": 170, "total_steps": 1455, "loss": 0.2362, "lr": 9.992384369672854e-05, "epoch": 0.35033487892838744, "percentage": 11.68, "elapsed_time": "1:37:48", "remaining_time": "12:19:19"}
+{"current_steps": 180, "total_steps": 1455, "loss": 0.2277, "lr": 9.984326668636131e-05, "epoch": 0.37094281298299847, "percentage": 12.37, "elapsed_time": "1:43:29", "remaining_time": "12:13:03"}
+{"current_steps": 190, "total_steps": 1455, "loss": 0.2348, "lr": 9.973398146668118e-05, "epoch": 0.3915507470376095, "percentage": 13.06, "elapsed_time": "1:49:00", "remaining_time": "12:05:46"}
+{"current_steps": 200, "total_steps": 1455, "loss": 0.2341, "lr": 9.959605098265886e-05, "epoch": 0.4121586810922205, "percentage": 13.75, "elapsed_time": "1:54:06", "remaining_time": "11:56:03"}
+{"current_steps": 200, "total_steps": 1455, "eval_loss": 0.21873560547828674, "epoch": 0.4121586810922205, "percentage": 13.75, "elapsed_time": "1:56:40", "remaining_time": "12:12:08"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45d3b60c6cfeb2594183cbb1041a6b81ad0bf3b4f10261892a7b472c3a0d744d
+size 5752