Trained adapter v1 (xLAM + synthetic, completion-only)

README.md

@@ -1,6 +1,13 @@
 ---
-library_name: transformers
-tags: []
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-14B-Instruct
+- lora
+- sft
+- transformers
+- trl
 ---
 
 # Model Card for Model ID
@@ -15,7 +22,7 @@ tags: []
 
 <!-- Provide a longer summary of what this model is. -->
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
 
 - **Developed by:** [More Information Needed]
 - **Funded by [optional]:** [More Information Needed]
@@ -196,4 +203,7 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 ## Model Card Contact
 
-[More Information Needed]
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.1

adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "up_proj",
+    "k_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c7c4239ee188cca5be79f702485a937eaa89a07f024232a5d04f39a24c8f3a7
+size 275341720

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
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a66633aa287f3cd50de2e3a4ab29c34ac32734d07da56ed4e4d4948622f34d37
+size 551070514

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5be56da870e9917819f54c6ab6f140d9006225f8b2adfc86c422f27f719bfd0
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d05c702376475f0ea0a1ccdece532557ebcba3c054194b40eda0060dbd7b3a56
+size 1064

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
-size 11421892
+oid sha256:913950e4971737031da511cdd1b410daae4566f62eb845b3975bca5a102323d8
+size 11421995

tokenizer_config.json

@@ -1,11 +1,185 @@
 {
+  "add_bos_token": false,
   "add_prefix_space": false,
-  "backend": "tokenizers",
-  "bos_token": null,
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "errors": "replace",
-  "extra_special_tokens": [
+  "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|>",
@@ -20,7 +194,11 @@
     "<|image_pad|>",
     "<|video_pad|>"
   ],
-  "is_local": false,
+  "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",
   "model_max_length": 32768,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,

trainer_state.json

@@ -0,0 +1,189 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3827751196172249,
+  "eval_steps": 200,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.019138755980861243,
+      "grad_norm": 0.6331622004508972,
+      "learning_rate": 6.25e-05,
+      "loss": 1.2934,
+      "step": 25
+    },
+    {
+      "epoch": 0.03827751196172249,
+      "grad_norm": 0.4265715181827545,
+      "learning_rate": 9.921011058451817e-05,
+      "loss": 0.646,
+      "step": 50
+    },
+    {
+      "epoch": 0.05741626794258373,
+      "grad_norm": 0.058480992913246155,
+      "learning_rate": 9.723538704581358e-05,
+      "loss": 0.526,
+      "step": 75
+    },
+    {
+      "epoch": 0.07655502392344497,
+      "grad_norm": 0.03429209440946579,
+      "learning_rate": 9.5260663507109e-05,
+      "loss": 0.5069,
+      "step": 100
+    },
+    {
+      "epoch": 0.09569377990430622,
+      "grad_norm": 0.11788608133792877,
+      "learning_rate": 9.328593996840442e-05,
+      "loss": 0.4748,
+      "step": 125
+    },
+    {
+      "epoch": 0.11483253588516747,
+      "grad_norm": 0.06252221018075943,
+      "learning_rate": 9.131121642969984e-05,
+      "loss": 0.4838,
+      "step": 150
+    },
+    {
+      "epoch": 0.1339712918660287,
+      "grad_norm": 0.020096125081181526,
+      "learning_rate": 8.933649289099526e-05,
+      "loss": 0.4918,
+      "step": 175
+    },
+    {
+      "epoch": 0.15311004784688995,
+      "grad_norm": 0.12325792759656906,
+      "learning_rate": 8.736176935229068e-05,
+      "loss": 0.5104,
+      "step": 200
+    },
+    {
+      "epoch": 0.15311004784688995,
+      "eval_loss": 0.49960193037986755,
+      "eval_runtime": 113.968,
+      "eval_samples_per_second": 4.826,
+      "eval_steps_per_second": 0.605,
+      "step": 200
+    },
+    {
+      "epoch": 0.1722488038277512,
+      "grad_norm": 0.10687647014856339,
+      "learning_rate": 8.53870458135861e-05,
+      "loss": 0.5015,
+      "step": 225
+    },
+    {
+      "epoch": 0.19138755980861244,
+      "grad_norm": 0.08051887899637222,
+      "learning_rate": 8.341232227488151e-05,
+      "loss": 0.4976,
+      "step": 250
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 0.03358834236860275,
+      "learning_rate": 8.143759873617693e-05,
+      "loss": 0.4916,
+      "step": 275
+    },
+    {
+      "epoch": 0.22966507177033493,
+      "grad_norm": 0.0065140132792294025,
+      "learning_rate": 7.946287519747235e-05,
+      "loss": 0.489,
+      "step": 300
+    },
+    {
+      "epoch": 0.24880382775119617,
+      "grad_norm": 0.06022901087999344,
+      "learning_rate": 7.748815165876777e-05,
+      "loss": 0.5067,
+      "step": 325
+    },
+    {
+      "epoch": 0.2679425837320574,
+      "grad_norm": 0.10035768896341324,
+      "learning_rate": 7.551342812006318e-05,
+      "loss": 0.4672,
+      "step": 350
+    },
+    {
+      "epoch": 0.28708133971291866,
+      "grad_norm": 0.12114957720041275,
+      "learning_rate": 7.35387045813586e-05,
+      "loss": 0.4941,
+      "step": 375
+    },
+    {
+      "epoch": 0.3062200956937799,
+      "grad_norm": 0.008501251228153706,
+      "learning_rate": 7.156398104265402e-05,
+      "loss": 0.5059,
+      "step": 400
+    },
+    {
+      "epoch": 0.3062200956937799,
+      "eval_loss": 0.49782803654670715,
+      "eval_runtime": 112.8287,
+      "eval_samples_per_second": 4.875,
+      "eval_steps_per_second": 0.612,
+      "step": 400
+    },
+    {
+      "epoch": 0.3253588516746411,
+      "grad_norm": 0.13349683582782745,
+      "learning_rate": 6.958925750394945e-05,
+      "loss": 0.4999,
+      "step": 425
+    },
+    {
+      "epoch": 0.3444976076555024,
+      "grad_norm": 0.07800962775945663,
+      "learning_rate": 6.761453396524487e-05,
+      "loss": 0.5059,
+      "step": 450
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 0.08217480778694153,
+      "learning_rate": 6.563981042654029e-05,
+      "loss": 0.5114,
+      "step": 475
+    },
+    {
+      "epoch": 0.3827751196172249,
+      "grad_norm": 0.07217281311750412,
+      "learning_rate": 6.36650868878357e-05,
+      "loss": 0.4855,
+      "step": 500
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1306,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 1.7646732515386368e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b760f4b0d3b9fc294ecfceb1ac7301982940828c666a4b2d2f92be2799525cb0
+size 5432