Nivedita28/deepseekmedical

README.md

@@ -0,0 +1,57 @@
+---
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+library_name: peft
+license: mit
+tags:
+- trl
+- sft
+- finetuned
+- generated_from_trainer
+model-index:
+- name: outputs
+  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. -->
+
+# outputs
+
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) 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: 0.0001
+- train_batch_size: 5
+- eval_batch_size: 16
+- seed: 3407
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.44.2
+- Pytorch 2.4.0+cu121
+- Datasets 3.0.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2"
+  },
+  "base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
+  "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": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "down_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60d95b10b6e140a9626a7058d5038528f2ff80148dc4569b881db56052046509
+size 40

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.842821417926656e+16,
+    "train_loss": 0.37092622672207654,
+    "train_runtime": 190.7397,
+    "train_samples_per_second": 5.033,
+    "train_steps_per_second": 1.007
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151646,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.44.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8dd6742316c796595513bbdedee22b2939a3cd37c4f2fe068b0465af5d9a0d0
+size 3554214752

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "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": "<｜end▁of▁sentence｜>"
+}

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": 2048,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.842821417926656e+16,
+    "train_loss": 0.37092622672207654,
+    "train_runtime": 190.7397,
+    "train_samples_per_second": 5.033,
+    "train_steps_per_second": 1.007
+}

trainer_state.json

@@ -0,0 +1,203 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 192,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15625,
+      "grad_norm": 0.10847697407007217,
+      "learning_rate": 9.479166666666666e-05,
+      "loss": 5.5359,
+      "step": 10
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 0.0398186556994915,
+      "learning_rate": 8.958333333333335e-05,
+      "loss": 0.1263,
+      "step": 20
+    },
+    {
+      "epoch": 0.46875,
+      "grad_norm": 0.03957119584083557,
+      "learning_rate": 8.4375e-05,
+      "loss": 0.1074,
+      "step": 30
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.027517227455973625,
+      "learning_rate": 7.916666666666666e-05,
+      "loss": 0.0965,
+      "step": 40
+    },
+    {
+      "epoch": 0.78125,
+      "grad_norm": 0.02527707628905773,
+      "learning_rate": 7.395833333333335e-05,
+      "loss": 0.0884,
+      "step": 50
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 0.02493639849126339,
+      "learning_rate": 6.875e-05,
+      "loss": 0.0884,
+      "step": 60
+    },
+    {
+      "epoch": 1.0,
+      "eval_runtime": 6.6509,
+      "eval_samples_per_second": 12.028,
+      "eval_steps_per_second": 0.752,
+      "step": 64
+    },
+    {
+      "epoch": 1.09375,
+      "grad_norm": 0.02615288645029068,
+      "learning_rate": 6.354166666666666e-05,
+      "loss": 0.08,
+      "step": 70
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.027330700308084488,
+      "learning_rate": 5.833333333333334e-05,
+      "loss": 0.0891,
+      "step": 80
+    },
+    {
+      "epoch": 1.40625,
+      "grad_norm": 0.028688812628388405,
+      "learning_rate": 5.3125000000000004e-05,
+      "loss": 0.0947,
+      "step": 90
+    },
+    {
+      "epoch": 1.5625,
+      "grad_norm": 0.030911659821867943,
+      "learning_rate": 4.791666666666667e-05,
+      "loss": 0.0803,
+      "step": 100
+    },
+    {
+      "epoch": 1.71875,
+      "grad_norm": 0.028372356668114662,
+      "learning_rate": 4.270833333333333e-05,
+      "loss": 0.0791,
+      "step": 110
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 0.022600064054131508,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.078,
+      "step": 120
+    },
+    {
+      "epoch": 2.0,
+      "eval_runtime": 5.3296,
+      "eval_samples_per_second": 15.011,
+      "eval_steps_per_second": 0.938,
+      "step": 128
+    },
+    {
+      "epoch": 2.03125,
+      "grad_norm": 0.02555151842534542,
+      "learning_rate": 3.229166666666667e-05,
+      "loss": 0.0811,
+      "step": 130
+    },
+    {
+      "epoch": 2.1875,
+      "grad_norm": 0.028641177341341972,
+      "learning_rate": 2.7083333333333332e-05,
+      "loss": 0.0809,
+      "step": 140
+    },
+    {
+      "epoch": 2.34375,
+      "grad_norm": 0.023602696135640144,
+      "learning_rate": 2.1875e-05,
+      "loss": 0.0738,
+      "step": 150
+    },
+    {
+      "epoch": 2.34375,
+      "eval_runtime": 5.3233,
+      "eval_samples_per_second": 15.028,
+      "eval_steps_per_second": 0.939,
+      "step": 150
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.026037951931357384,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.0775,
+      "step": 160
+    },
+    {
+      "epoch": 2.65625,
+      "grad_norm": 0.027666736394166946,
+      "learning_rate": 1.1458333333333333e-05,
+      "loss": 0.0829,
+      "step": 170
+    },
+    {
+      "epoch": 2.8125,
+      "grad_norm": 0.025325452908873558,
+      "learning_rate": 6.25e-06,
+      "loss": 0.0802,
+      "step": 180
+    },
+    {
+      "epoch": 2.96875,
+      "grad_norm": 0.02601686492562294,
+      "learning_rate": 1.0416666666666667e-06,
+      "loss": 0.0858,
+      "step": 190
+    },
+    {
+      "epoch": 3.0,
+      "eval_runtime": 5.3306,
+      "eval_samples_per_second": 15.008,
+      "eval_steps_per_second": 0.938,
+      "step": 192
+    },
+    {
+      "epoch": 3.0,
+      "step": 192,
+      "total_flos": 1.842821417926656e+16,
+      "train_loss": 0.37092622672207654,
+      "train_runtime": 190.7397,
+      "train_samples_per_second": 5.033,
+      "train_steps_per_second": 1.007
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 192,
+  "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": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.842821417926656e+16,
+  "train_batch_size": 5,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d54ce947218fd70f81e3e7c2d88f7e082fcc501ccbe553663dabd3839b514bde
+size 5432