Model save

.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

README.md

@@ -0,0 +1,61 @@
+---
+library_name: peft
+license: mit
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: models-feb18-block-mask-step7
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# models-feb18-block-mask-step7
+
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 8e-05
+- train_batch_size: 2
+- eval_batch_size: 1
+- seed: 158176
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 16
+- total_eval_batch_size: 8
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.47.0.dev0
+- Pytorch 2.4.0+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
+  "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": [
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "up_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 sha256:39c998bafd7d4d1f30e12c4328c23a3cc865a7886b1e2b085d37d743035a23ea
+size 2147607752

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c11a6ac886e89a098471690b6ced3af1fbd2cdfd12722f5d9b47d3d1327018d
+size 11422878

tokenizer_config.json

@@ -0,0 +1,194 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "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
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin��>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,315 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 39,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07692307692307693,
+      "grad_norm": 0.01335646424877593,
+      "learning_rate": 2e-05,
+      "loss": 0.2098,
+      "step": 1
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 0.013496294572671225,
+      "learning_rate": 4e-05,
+      "loss": 0.2296,
+      "step": 2
+    },
+    {
+      "epoch": 0.23076923076923078,
+      "grad_norm": 0.013573079062097768,
+      "learning_rate": 6.000000000000001e-05,
+      "loss": 0.2085,
+      "step": 3
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 0.015160308475595475,
+      "learning_rate": 8e-05,
+      "loss": 0.2064,
+      "step": 4
+    },
+    {
+      "epoch": 0.38461538461538464,
+      "grad_norm": 0.017640160839030004,
+      "learning_rate": 7.983897175980957e-05,
+      "loss": 0.2148,
+      "step": 5
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 0.019886262511162607,
+      "learning_rate": 7.93571835439452e-05,
+      "loss": 0.2057,
+      "step": 6
+    },
+    {
+      "epoch": 0.5384615384615384,
+      "grad_norm": 0.018769991473644332,
+      "learning_rate": 7.855851442783414e-05,
+      "loss": 0.2047,
+      "step": 7
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 0.013726476079369812,
+      "learning_rate": 7.74493948255895e-05,
+      "loss": 0.1958,
+      "step": 8
+    },
+    {
+      "epoch": 0.6923076923076923,
+      "grad_norm": 0.014758031209037372,
+      "learning_rate": 7.603875471609677e-05,
+      "loss": 0.2037,
+      "step": 9
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 0.01661942322375908,
+      "learning_rate": 7.433795174407465e-05,
+      "loss": 0.2186,
+      "step": 10
+    },
+    {
+      "epoch": 0.8461538461538461,
+      "grad_norm": 0.018861223287726433,
+      "learning_rate": 7.236067977499791e-05,
+      "loss": 0.1756,
+      "step": 11
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.02217985452594929,
+      "learning_rate": 7.012285864014445e-05,
+      "loss": 0.201,
+      "step": 12
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.022247173923258347,
+      "learning_rate": 6.76425059594746e-05,
+      "loss": 0.1587,
+      "step": 13
+    },
+    {
+      "epoch": 1.0769230769230769,
+      "grad_norm": 0.018185997662387956,
+      "learning_rate": 6.493959207434934e-05,
+      "loss": 0.1878,
+      "step": 14
+    },
+    {
+      "epoch": 1.1538461538461537,
+      "grad_norm": 0.012635955883730596,
+      "learning_rate": 6.20358792580841e-05,
+      "loss": 0.1496,
+      "step": 15
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 0.007961045255962347,
+      "learning_rate": 5.895474649891995e-05,
+      "loss": 0.1671,
+      "step": 16
+    },
+    {
+      "epoch": 1.3076923076923077,
+      "grad_norm": 0.009054115166385043,
+      "learning_rate": 5.572100126615695e-05,
+      "loss": 0.1656,
+      "step": 17
+    },
+    {
+      "epoch": 1.3846153846153846,
+      "grad_norm": 0.008216814060178514,
+      "learning_rate": 5.23606797749979e-05,
+      "loss": 0.2004,
+      "step": 18
+    },
+    {
+      "epoch": 1.4615384615384617,
+      "grad_norm": 0.010898885972727207,
+      "learning_rate": 4.890083735825258e-05,
+      "loss": 0.1592,
+      "step": 19
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 0.010694981841141952,
+      "learning_rate": 4.5369330632706223e-05,
+      "loss": 0.1503,
+      "step": 20
+    },
+    {
+      "epoch": 1.6153846153846154,
+      "grad_norm": 0.010613783437549805,
+      "learning_rate": 4.17945932140206e-05,
+      "loss": 0.1926,
+      "step": 21
+    },
+    {
+      "epoch": 1.6923076923076923,
+      "grad_norm": 0.009739342113653163,
+      "learning_rate": 3.820540678597942e-05,
+      "loss": 0.174,
+      "step": 22
+    },
+    {
+      "epoch": 1.7692307692307692,
+      "grad_norm": 0.010286306709408949,
+      "learning_rate": 3.4630669367293797e-05,
+      "loss": 0.1568,
+      "step": 23
+    },
+    {
+      "epoch": 1.8461538461538463,
+      "grad_norm": 0.010301808604637058,
+      "learning_rate": 3.109916264174743e-05,
+      "loss": 0.1517,
+      "step": 24
+    },
+    {
+      "epoch": 1.9230769230769231,
+      "grad_norm": 0.011157938401911613,
+      "learning_rate": 2.7639320225002108e-05,
+      "loss": 0.176,
+      "step": 25
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.008789995536671761,
+      "learning_rate": 2.427899873384306e-05,
+      "loss": 0.1296,
+      "step": 26
+    },
+    {
+      "epoch": 2.076923076923077,
+      "grad_norm": 0.008951507111483502,
+      "learning_rate": 2.1045253501080058e-05,
+      "loss": 0.1486,
+      "step": 27
+    },
+    {
+      "epoch": 2.1538461538461537,
+      "grad_norm": 0.008954329943955836,
+      "learning_rate": 1.7964120741915905e-05,
+      "loss": 0.1419,
+      "step": 28
+    },
+    {
+      "epoch": 2.230769230769231,
+      "grad_norm": 0.008925051326339568,
+      "learning_rate": 1.5060407925650662e-05,
+      "loss": 0.1201,
+      "step": 29
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 0.007634536377541851,
+      "learning_rate": 1.2357494040525416e-05,
+      "loss": 0.1426,
+      "step": 30
+    },
+    {
+      "epoch": 2.3846153846153846,
+      "grad_norm": 0.007979228123081128,
+      "learning_rate": 9.877141359855567e-06,
+      "loss": 0.1397,
+      "step": 31
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": 0.008720002025150176,
+      "learning_rate": 7.639320225002106e-06,
+      "loss": 0.1685,
+      "step": 32
+    },
+    {
+      "epoch": 2.5384615384615383,
+      "grad_norm": 0.007510053650263451,
+      "learning_rate": 5.662048255925357e-06,
+      "loss": 0.1632,
+      "step": 33
+    },
+    {
+      "epoch": 2.6153846153846154,
+      "grad_norm": 0.007542709941422978,
+      "learning_rate": 3.961245283903239e-06,
+      "loss": 0.1253,
+      "step": 34
+    },
+    {
+      "epoch": 2.6923076923076925,
+      "grad_norm": 0.008007863027970272,
+      "learning_rate": 2.550605174410512e-06,
+      "loss": 0.142,
+      "step": 35
+    },
+    {
+      "epoch": 2.769230769230769,
+      "grad_norm": 0.007419092794139719,
+      "learning_rate": 1.4414855721658705e-06,
+      "loss": 0.1437,
+      "step": 36
+    },
+    {
+      "epoch": 2.8461538461538463,
+      "grad_norm": 0.007716443781153161,
+      "learning_rate": 6.428164560548134e-07,
+      "loss": 0.1554,
+      "step": 37
+    },
+    {
+      "epoch": 2.9230769230769234,
+      "grad_norm": 0.006982688635770704,
+      "learning_rate": 1.6102824019043728e-07,
+      "loss": 0.1847,
+      "step": 38
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.007222173592213081,
+      "learning_rate": 0.0,
+      "loss": 0.1558,
+      "step": 39
+    },
+    {
+      "epoch": 3.0,
+      "step": 39,
+      "total_flos": 84978881789952.0,
+      "train_loss": 0.17243788907161126,
+      "train_runtime": 1112.3035,
+      "train_samples_per_second": 0.539,
+      "train_steps_per_second": 0.035
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 39,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 84978881789952.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3806c4c4834386705b2d10284fd77a18406e2fb056a99ff68c917c08aceb5c8b
+size 7224