Training in progress, step 100

.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 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "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",
+    "up_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77d2d874882233bee99e2389e5509d0d83e4d9e1574b7074521c9003d05668f5
+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 +1,32 @@
+{"current_steps": 10, "total_steps": 610, "loss": 0.3745, "lr": 1.6393442622950818e-05, "epoch": 0.01639344262295082, "percentage": 1.64, "elapsed_time": "0:01:34", "remaining_time": "1:34:08"}
+{"current_steps": 20, "total_steps": 610, "loss": 0.2514, "lr": 3.2786885245901635e-05, "epoch": 0.03278688524590164, "percentage": 3.28, "elapsed_time": "0:03:06", "remaining_time": "1:31:44"}
+{"current_steps": 30, "total_steps": 610, "loss": 0.1555, "lr": 4.918032786885246e-05, "epoch": 0.04918032786885246, "percentage": 4.92, "elapsed_time": "0:05:00", "remaining_time": "1:36:44"}
+{"current_steps": 40, "total_steps": 610, "loss": 0.1932, "lr": 6.557377049180327e-05, "epoch": 0.06557377049180328, "percentage": 6.56, "elapsed_time": "0:06:38", "remaining_time": "1:34:35"}
+{"current_steps": 50, "total_steps": 610, "loss": 0.1536, "lr": 8.19672131147541e-05, "epoch": 0.08196721311475409, "percentage": 8.2, "elapsed_time": "0:08:35", "remaining_time": "1:36:11"}
+{"current_steps": 60, "total_steps": 610, "loss": 0.1524, "lr": 9.836065573770493e-05, "epoch": 0.09836065573770492, "percentage": 9.84, "elapsed_time": "0:10:34", "remaining_time": "1:36:55"}
+{"current_steps": 70, "total_steps": 610, "loss": 0.1391, "lr": 9.993370449424153e-05, "epoch": 0.11475409836065574, "percentage": 11.48, "elapsed_time": "0:12:34", "remaining_time": "1:37:02"}
+{"current_steps": 80, "total_steps": 610, "loss": 0.1274, "lr": 9.970476054107763e-05, "epoch": 0.13114754098360656, "percentage": 13.11, "elapsed_time": "0:14:37", "remaining_time": "1:36:54"}
+{"current_steps": 90, "total_steps": 610, "loss": 0.1283, "lr": 9.931309898856423e-05, "epoch": 0.14754098360655737, "percentage": 14.75, "elapsed_time": "0:16:37", "remaining_time": "1:36:04"}
+{"current_steps": 100, "total_steps": 610, "loss": 0.1317, "lr": 9.876000201222912e-05, "epoch": 0.16393442622950818, "percentage": 16.39, "elapsed_time": "0:18:35", "remaining_time": "1:34:48"}
+{"current_steps": 100, "total_steps": 610, "eval_loss": 0.16001197695732117, "epoch": 0.16393442622950818, "percentage": 16.39, "elapsed_time": "0:19:36", "remaining_time": "1:40:02"}
+{"current_steps": 110, "total_steps": 610, "loss": 0.1882, "lr": 9.804728027590449e-05, "epoch": 0.18032786885245902, "percentage": 18.03, "elapsed_time": "0:21:17", "remaining_time": "1:36:44"}
+{"current_steps": 120, "total_steps": 610, "loss": 0.1557, "lr": 9.717726700418842e-05, "epoch": 0.19672131147540983, "percentage": 19.67, "elapsed_time": "0:23:09", "remaining_time": "1:34:33"}
+{"current_steps": 130, "total_steps": 610, "loss": 0.161, "lr": 9.61528103442088e-05, "epoch": 0.21311475409836064, "percentage": 21.31, "elapsed_time": "0:24:53", "remaining_time": "1:31:55"}
+{"current_steps": 140, "total_steps": 610, "loss": 0.1615, "lr": 9.497726404169412e-05, "epoch": 0.22950819672131148, "percentage": 22.95, "elapsed_time": "0:26:35", "remaining_time": "1:29:15"}
+{"current_steps": 150, "total_steps": 610, "loss": 0.1473, "lr": 9.365447646187509e-05, "epoch": 0.2459016393442623, "percentage": 24.59, "elapsed_time": "0:28:18", "remaining_time": "1:26:48"}
+{"current_steps": 160, "total_steps": 610, "loss": 0.125, "lr": 9.218877799115928e-05, "epoch": 0.26229508196721313, "percentage": 26.23, "elapsed_time": "0:30:16", "remaining_time": "1:25:08"}
+{"current_steps": 170, "total_steps": 610, "loss": 0.1401, "lr": 9.058496686082132e-05, "epoch": 0.2786885245901639, "percentage": 27.87, "elapsed_time": "0:31:55", "remaining_time": "1:22:38"}
+{"current_steps": 180, "total_steps": 610, "loss": 0.145, "lr": 8.884829343911762e-05, "epoch": 0.29508196721311475, "percentage": 29.51, "elapsed_time": "0:33:43", "remaining_time": "1:20:34"}
+{"current_steps": 190, "total_steps": 610, "loss": 0.1411, "lr": 8.698444304324835e-05, "epoch": 0.3114754098360656, "percentage": 31.15, "elapsed_time": "0:35:43", "remaining_time": "1:18:57"}
+{"current_steps": 200, "total_steps": 610, "loss": 0.1605, "lr": 8.499951732743457e-05, "epoch": 0.32786885245901637, "percentage": 32.79, "elapsed_time": "0:37:24", "remaining_time": "1:16:41"}
+{"current_steps": 10, "total_steps": 610, "loss": 0.3745, "lr": 1.6393442622950818e-05, "epoch": 0.01639344262295082, "percentage": 1.64, "elapsed_time": "0:01:41", "remaining_time": "1:41:48"}
+{"current_steps": 20, "total_steps": 610, "loss": 0.2514, "lr": 3.2786885245901635e-05, "epoch": 0.03278688524590164, "percentage": 3.28, "elapsed_time": "0:03:18", "remaining_time": "1:37:42"}
+{"current_steps": 30, "total_steps": 610, "loss": 0.1555, "lr": 4.918032786885246e-05, "epoch": 0.04918032786885246, "percentage": 4.92, "elapsed_time": "0:05:13", "remaining_time": "1:41:07"}
+{"current_steps": 40, "total_steps": 610, "loss": 0.1932, "lr": 6.557377049180327e-05, "epoch": 0.06557377049180328, "percentage": 6.56, "elapsed_time": "0:06:53", "remaining_time": "1:38:10"}
+{"current_steps": 50, "total_steps": 610, "loss": 0.1536, "lr": 8.19672131147541e-05, "epoch": 0.08196721311475409, "percentage": 8.2, "elapsed_time": "0:08:52", "remaining_time": "1:39:18"}
+{"current_steps": 60, "total_steps": 610, "loss": 0.1524, "lr": 9.836065573770493e-05, "epoch": 0.09836065573770492, "percentage": 9.84, "elapsed_time": "0:10:52", "remaining_time": "1:39:42"}
+{"current_steps": 70, "total_steps": 610, "loss": 0.1391, "lr": 9.993370449424153e-05, "epoch": 0.11475409836065574, "percentage": 11.48, "elapsed_time": "0:12:54", "remaining_time": "1:39:36"}
+{"current_steps": 80, "total_steps": 610, "loss": 0.1274, "lr": 9.970476054107763e-05, "epoch": 0.13114754098360656, "percentage": 13.11, "elapsed_time": "0:14:59", "remaining_time": "1:39:19"}
+{"current_steps": 90, "total_steps": 610, "loss": 0.1283, "lr": 9.931309898856423e-05, "epoch": 0.14754098360655737, "percentage": 14.75, "elapsed_time": "0:17:01", "remaining_time": "1:38:21"}
+{"current_steps": 100, "total_steps": 610, "loss": 0.1317, "lr": 9.876000201222912e-05, "epoch": 0.16393442622950818, "percentage": 16.39, "elapsed_time": "0:19:00", "remaining_time": "1:36:55"}
+{"current_steps": 100, "total_steps": 610, "eval_loss": 0.16001197695732117, "epoch": 0.16393442622950818, "percentage": 16.39, "elapsed_time": "0:20:02", "remaining_time": "1:42:13"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d7d02bc3f5de32fb95efed0802063e827b466700f663c456dda4212036f5682
+size 5816