Upload folder using huggingface_hub

README.md

@@ -0,0 +1,46 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-v0.1
+model-index:
+- name: mistral-7b-medqa-v1
+  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. -->
+
+# mistral-7b-medqa-v1
+
+This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the medical_meadow_medqa dataset.
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0005
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 20
+- num_epochs: 1.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.37.2
+- Pytorch 2.1.1+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

adapter_config.json

@@ -0,0 +1,27 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.2,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9eed2c63b22828645550f6ee74d632e57d3e84cd2decc2b1d1fd9c2868ac901d
+size 13648432

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.16286772943268985,
+    "train_runtime": 1280.7232,
+    "train_samples_per_second": 3.904,
+    "train_steps_per_second": 0.244
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.16286772943268985,
+    "train_runtime": 1280.7232,
+    "train_samples_per_second": 3.904,
+    "train_steps_per_second": 0.244
+}

trainer_log.jsonl

@@ -0,0 +1,32 @@
+{"current_steps": 10, "total_steps": 312, "loss": 0.7923, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00025, "epoch": 0.03, "percentage": 3.21, "elapsed_time": "0:00:44", "remaining_time": "0:22:15"}
+{"current_steps": 20, "total_steps": 312, "loss": 0.1889, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0005, "epoch": 0.06, "percentage": 6.41, "elapsed_time": "0:01:24", "remaining_time": "0:20:33"}
+{"current_steps": 30, "total_steps": 312, "loss": 0.1673, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000498554476723488, "epoch": 0.1, "percentage": 9.62, "elapsed_time": "0:02:05", "remaining_time": "0:19:39"}
+{"current_steps": 40, "total_steps": 312, "loss": 0.1507, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004942346231942955, "epoch": 0.13, "percentage": 12.82, "elapsed_time": "0:02:46", "remaining_time": "0:18:49"}
+{"current_steps": 50, "total_steps": 312, "loss": 0.1385, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004870903950030429, "epoch": 0.16, "percentage": 16.03, "elapsed_time": "0:03:27", "remaining_time": "0:18:09"}
+{"current_steps": 60, "total_steps": 312, "loss": 0.1593, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00047720440933487574, "epoch": 0.19, "percentage": 19.23, "elapsed_time": "0:04:10", "remaining_time": "0:17:30"}
+{"current_steps": 70, "total_steps": 312, "loss": 0.1549, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004646909895689508, "epoch": 0.22, "percentage": 22.44, "elapsed_time": "0:04:50", "remaining_time": "0:16:43"}
+{"current_steps": 80, "total_steps": 312, "loss": 0.159, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004496948432215913, "epoch": 0.26, "percentage": 25.64, "elapsed_time": "0:05:30", "remaining_time": "0:15:59"}
+{"current_steps": 90, "total_steps": 312, "loss": 0.1562, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004323893885216219, "epoch": 0.29, "percentage": 28.85, "elapsed_time": "0:06:10", "remaining_time": "0:15:13"}
+{"current_steps": 100, "total_steps": 312, "loss": 0.1352, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00041297474896967814, "epoch": 0.32, "percentage": 32.05, "elapsed_time": "0:06:53", "remaining_time": "0:14:36"}
+{"current_steps": 110, "total_steps": 312, "loss": 0.1588, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003916754390727794, "epoch": 0.35, "percentage": 35.26, "elapsed_time": "0:07:33", "remaining_time": "0:13:52"}
+{"current_steps": 120, "total_steps": 312, "loss": 0.1523, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003687377680167626, "epoch": 0.38, "percentage": 38.46, "elapsed_time": "0:08:15", "remaining_time": "0:13:12"}
+{"current_steps": 130, "total_steps": 312, "loss": 0.1418, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003444269913009912, "epoch": 0.42, "percentage": 41.67, "elapsed_time": "0:08:55", "remaining_time": "0:12:29"}
+{"current_steps": 140, "total_steps": 312, "loss": 0.1428, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003190242432743673, "epoch": 0.45, "percentage": 44.87, "elapsed_time": "0:09:38", "remaining_time": "0:11:50"}
+{"current_steps": 150, "total_steps": 312, "loss": 0.1471, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002928232860453694, "epoch": 0.48, "percentage": 48.08, "elapsed_time": "0:10:18", "remaining_time": "0:11:08"}
+{"current_steps": 160, "total_steps": 312, "loss": 0.1427, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00026612711236232914, "epoch": 0.51, "percentage": 51.28, "elapsed_time": "0:10:59", "remaining_time": "0:10:26"}
+{"current_steps": 170, "total_steps": 312, "loss": 0.1366, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00023924444174886733, "epoch": 0.54, "percentage": 54.49, "elapsed_time": "0:11:40", "remaining_time": "0:09:44"}
+{"current_steps": 180, "total_steps": 312, "loss": 0.1463, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00021248615041383683, "epoch": 0.58, "percentage": 57.69, "elapsed_time": "0:12:21", "remaining_time": "0:09:03"}
+{"current_steps": 190, "total_steps": 312, "loss": 0.1328, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00018616167622095327, "epoch": 0.61, "percentage": 60.9, "elapsed_time": "0:13:03", "remaining_time": "0:08:22"}
+{"current_steps": 200, "total_steps": 312, "loss": 0.134, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001605754402917186, "epoch": 0.64, "percentage": 64.1, "elapsed_time": "0:13:42", "remaining_time": "0:07:40"}
+{"current_steps": 210, "total_steps": 312, "loss": 0.1417, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00013602332662288535, "epoch": 0.67, "percentage": 67.31, "elapsed_time": "0:14:22", "remaining_time": "0:06:59"}
+{"current_steps": 220, "total_steps": 312, "loss": 0.1194, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00011278926042882027, "epoch": 0.7, "percentage": 70.51, "elapsed_time": "0:15:03", "remaining_time": "0:06:18"}
+{"current_steps": 230, "total_steps": 312, "loss": 0.1359, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.114192477745568e-05, "epoch": 0.74, "percentage": 73.72, "elapsed_time": "0:15:44", "remaining_time": "0:05:36"}
+{"current_steps": 240, "total_steps": 312, "loss": 0.1244, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.133165348925977e-05, "epoch": 0.77, "percentage": 76.92, "elapsed_time": "0:16:22", "remaining_time": "0:04:54"}
+{"current_steps": 250, "total_steps": 312, "loss": 0.1367, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.3587536230321364e-05, "epoch": 0.8, "percentage": 80.13, "elapsed_time": "0:17:05", "remaining_time": "0:04:14"}
+{"current_steps": 260, "total_steps": 312, "loss": 0.1256, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.811476927679228e-05, "epoch": 0.83, "percentage": 83.33, "elapsed_time": "0:17:47", "remaining_time": "0:03:33"}
+{"current_steps": 270, "total_steps": 312, "loss": 0.1312, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5092282586939186e-05, "epoch": 0.86, "percentage": 86.54, "elapsed_time": "0:18:27", "remaining_time": "0:02:52"}
+{"current_steps": 280, "total_steps": 312, "loss": 0.1272, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.467067062178823e-05, "epoch": 0.9, "percentage": 89.74, "elapsed_time": "0:19:06", "remaining_time": "0:02:11"}
+{"current_steps": 290, "total_steps": 312, "loss": 0.1241, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.970450842734649e-06, "epoch": 0.93, "percentage": 92.95, "elapsed_time": "0:19:49", "remaining_time": "0:01:30"}
+{"current_steps": 300, "total_steps": 312, "loss": 0.1234, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0806700251775058e-06, "epoch": 0.96, "percentage": 96.15, "elapsed_time": "0:20:32", "remaining_time": "0:00:49"}
+{"current_steps": 310, "total_steps": 312, "loss": 0.1305, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.7874505027283307e-08, "epoch": 0.99, "percentage": 99.36, "elapsed_time": "0:21:12", "remaining_time": "0:00:08"}
+{"current_steps": 312, "total_steps": 312, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:21:20", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,216 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9984,
+  "eval_steps": 500,
+  "global_step": 312,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00025,
+      "loss": 0.7923,
+      "step": 10
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0005,
+      "loss": 0.1889,
+      "step": 20
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.000498554476723488,
+      "loss": 0.1673,
+      "step": 30
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0004942346231942955,
+      "loss": 0.1507,
+      "step": 40
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0004870903950030429,
+      "loss": 0.1385,
+      "step": 50
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00047720440933487574,
+      "loss": 0.1593,
+      "step": 60
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0004646909895689508,
+      "loss": 0.1549,
+      "step": 70
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0004496948432215913,
+      "loss": 0.159,
+      "step": 80
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0004323893885216219,
+      "loss": 0.1562,
+      "step": 90
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00041297474896967814,
+      "loss": 0.1352,
+      "step": 100
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003916754390727794,
+      "loss": 0.1588,
+      "step": 110
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003687377680167626,
+      "loss": 0.1523,
+      "step": 120
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003444269913009912,
+      "loss": 0.1418,
+      "step": 130
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003190242432743673,
+      "loss": 0.1428,
+      "step": 140
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0002928232860453694,
+      "loss": 0.1471,
+      "step": 150
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00026612711236232914,
+      "loss": 0.1427,
+      "step": 160
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00023924444174886733,
+      "loss": 0.1366,
+      "step": 170
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00021248615041383683,
+      "loss": 0.1463,
+      "step": 180
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00018616167622095327,
+      "loss": 0.1328,
+      "step": 190
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0001605754402917186,
+      "loss": 0.134,
+      "step": 200
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00013602332662288535,
+      "loss": 0.1417,
+      "step": 210
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00011278926042882027,
+      "loss": 0.1194,
+      "step": 220
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 9.114192477745568e-05,
+      "loss": 0.1359,
+      "step": 230
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 7.133165348925977e-05,
+      "loss": 0.1244,
+      "step": 240
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 5.3587536230321364e-05,
+      "loss": 0.1367,
+      "step": 250
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.811476927679228e-05,
+      "loss": 0.1256,
+      "step": 260
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.5092282586939186e-05,
+      "loss": 0.1312,
+      "step": 270
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.467067062178823e-05,
+      "loss": 0.1272,
+      "step": 280
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 6.970450842734649e-06,
+      "loss": 0.1241,
+      "step": 290
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.0806700251775058e-06,
+      "loss": 0.1234,
+      "step": 300
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 5.7874505027283307e-08,
+      "loss": 0.1305,
+      "step": 310
+    },
+    {
+      "epoch": 1.0,
+      "step": 312,
+      "total_flos": 8.46080087312302e+16,
+      "train_loss": 0.16286772943268985,
+      "train_runtime": 1280.7232,
+      "train_samples_per_second": 3.904,
+      "train_steps_per_second": 0.244
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 312,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 8.46080087312302e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c16dec8e3498a9cca28ece05614b36ebe1dc05c1d57240fdb006563e36eac2f
+size 4920