Upload folder using huggingface_hub

README.md

@@ -0,0 +1,42 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: Deci/DeciLM-7B
+model-index:
+- name: decilm-7b-ocn-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. -->
+
+# decilm-7b-ocn-v1
+
+This model is a fine-tuned version of Deci/DeciLM-7B on the oncc_medqa_instruct 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: 10
+- num_epochs: 1.0
+- mixed_precision_training: Native AMP
+
+### 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": "Deci/DeciLM-7B",
+  "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 sha256:7a1ede054310744c023728b35074ba6312942b9a02de733a0d61ac7f6cc33857
+size 12874248

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.18545997113429855,
+    "train_runtime": 753.5433,
+    "train_samples_per_second": 4.317,
+    "train_steps_per_second": 0.269
+}

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 +1,45 @@
+{
+  "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>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '### User:\n' + message['content'] }}\n{% elif message['role'] == 'system' %}\n{{ '### System:\n' + message['content'] }}\n{% elif message['role'] == 'assistant' %}\n{{ '### Assistant:\n'  + message['content'] }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '### Assistant:' }}\n{% endif %}\n{% endfor %}",
+  "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": true
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.18545997113429855,
+    "train_runtime": 753.5433,
+    "train_samples_per_second": 4.317,
+    "train_steps_per_second": 0.269
+}

trainer_log.jsonl

@@ -0,0 +1,21 @@
+{"current_steps": 10, "total_steps": 203, "loss": 0.7395, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0005, "epoch": 0.05, "percentage": 4.93, "elapsed_time": "0:00:37", "remaining_time": "0:12:04"}
+{"current_steps": 20, "total_steps": 203, "loss": 0.1866, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004966952699028185, "epoch": 0.1, "percentage": 9.85, "elapsed_time": "0:01:13", "remaining_time": "0:11:11"}
+{"current_steps": 30, "total_steps": 203, "loss": 0.1742, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004868684495393958, "epoch": 0.15, "percentage": 14.78, "elapsed_time": "0:01:48", "remaining_time": "0:10:28"}
+{"current_steps": 40, "total_steps": 203, "loss": 0.166, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00047077933882184867, "epoch": 0.2, "percentage": 19.7, "elapsed_time": "0:02:26", "remaining_time": "0:09:56"}
+{"current_steps": 50, "total_steps": 203, "loss": 0.1629, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00044885329909757834, "epoch": 0.25, "percentage": 24.63, "elapsed_time": "0:03:02", "remaining_time": "0:09:19"}
+{"current_steps": 60, "total_steps": 203, "loss": 0.1655, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004216700075136953, "epoch": 0.29, "percentage": 29.56, "elapsed_time": "0:03:40", "remaining_time": "0:08:46"}
+{"current_steps": 70, "total_steps": 203, "loss": 0.1509, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00038994813160490117, "epoch": 0.34, "percentage": 34.48, "elapsed_time": "0:04:18", "remaining_time": "0:08:11"}
+{"current_steps": 80, "total_steps": 203, "loss": 0.1558, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003545263292756348, "epoch": 0.39, "percentage": 39.41, "elapsed_time": "0:04:55", "remaining_time": "0:07:34"}
+{"current_steps": 90, "total_steps": 203, "loss": 0.1634, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003163410764959277, "epoch": 0.44, "percentage": 44.33, "elapsed_time": "0:05:31", "remaining_time": "0:06:56"}
+{"current_steps": 100, "total_steps": 203, "loss": 0.1579, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002764019088988165, "epoch": 0.49, "percentage": 49.26, "elapsed_time": "0:06:06", "remaining_time": "0:06:17"}
+{"current_steps": 110, "total_steps": 203, "loss": 0.1534, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00023576473183801758, "epoch": 0.54, "percentage": 54.19, "elapsed_time": "0:06:43", "remaining_time": "0:05:41"}
+{"current_steps": 120, "total_steps": 203, "loss": 0.1488, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019550390453030946, "epoch": 0.59, "percentage": 59.11, "elapsed_time": "0:07:23", "remaining_time": "0:05:06"}
+{"current_steps": 130, "total_steps": 203, "loss": 0.1505, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001566838363176219, "epoch": 0.64, "percentage": 64.04, "elapsed_time": "0:08:00", "remaining_time": "0:04:29"}
+{"current_steps": 140, "total_steps": 203, "loss": 0.1601, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00012033084598233163, "epoch": 0.69, "percentage": 68.97, "elapsed_time": "0:08:38", "remaining_time": "0:03:53"}
+{"current_steps": 150, "total_steps": 203, "loss": 0.1611, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.051861465390624e-05, "epoch": 0.74, "percentage": 73.89, "elapsed_time": "0:09:15", "remaining_time": "0:03:16"}
+{"current_steps": 160, "total_steps": 203, "loss": 0.1447, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.412305518878342e-05, "epoch": 0.79, "percentage": 78.82, "elapsed_time": "0:09:53", "remaining_time": "0:02:39"}
+{"current_steps": 170, "total_steps": 203, "loss": 0.1454, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.948683851251877e-05, "epoch": 0.84, "percentage": 83.74, "elapsed_time": "0:10:31", "remaining_time": "0:02:02"}
+{"current_steps": 180, "total_steps": 203, "loss": 0.1548, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0416135281218216e-05, "epoch": 0.88, "percentage": 88.67, "elapsed_time": "0:11:08", "remaining_time": "0:01:25"}
+{"current_steps": 190, "total_steps": 203, "loss": 0.1504, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.415133710424793e-06, "epoch": 0.93, "percentage": 93.6, "elapsed_time": "0:11:44", "remaining_time": "0:00:48"}
+{"current_steps": 200, "total_steps": 203, "loss": 0.1288, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.275522096146404e-07, "epoch": 0.98, "percentage": 98.52, "elapsed_time": "0:12:21", "remaining_time": "0:00:11"}
+{"current_steps": 203, "total_steps": 203, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:12:33", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,150 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9975429975429976,
+  "eval_steps": 500,
+  "global_step": 203,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0005,
+      "loss": 0.7395,
+      "step": 10
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0004966952699028185,
+      "loss": 0.1866,
+      "step": 20
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0004868684495393958,
+      "loss": 0.1742,
+      "step": 30
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00047077933882184867,
+      "loss": 0.166,
+      "step": 40
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00044885329909757834,
+      "loss": 0.1629,
+      "step": 50
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0004216700075136953,
+      "loss": 0.1655,
+      "step": 60
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00038994813160490117,
+      "loss": 0.1509,
+      "step": 70
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003545263292756348,
+      "loss": 0.1558,
+      "step": 80
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003163410764959277,
+      "loss": 0.1634,
+      "step": 90
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0002764019088988165,
+      "loss": 0.1579,
+      "step": 100
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00023576473183801758,
+      "loss": 0.1534,
+      "step": 110
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00019550390453030946,
+      "loss": 0.1488,
+      "step": 120
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0001566838363176219,
+      "loss": 0.1505,
+      "step": 130
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00012033084598233163,
+      "loss": 0.1601,
+      "step": 140
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 9.051861465390624e-05,
+      "loss": 0.1611,
+      "step": 150
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 6.412305518878342e-05,
+      "loss": 0.1447,
+      "step": 160
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.948683851251877e-05,
+      "loss": 0.1454,
+      "step": 170
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2.0416135281218216e-05,
+      "loss": 0.1548,
+      "step": 180
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 7.415133710424793e-06,
+      "loss": 0.1504,
+      "step": 190
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 8.275522096146404e-07,
+      "loss": 0.1288,
+      "step": 200
+    },
+    {
+      "epoch": 1.0,
+      "step": 203,
+      "total_flos": 5.261592447850906e+16,
+      "train_loss": 0.18545997113429855,
+      "train_runtime": 753.5433,
+      "train_samples_per_second": 4.317,
+      "train_steps_per_second": 0.269
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 203,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 5.261592447850906e+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 sha256:97535dbc1a8e127fee91143dd81b58483e5692c1f7a10f650a0e02720739f8cf
+size 4856