Upload 10 files

README.md

@@ -0,0 +1,10 @@
+---
+library_name: peft
+---
+## Training procedure
+
+### Framework versions
+
+- PEFT 0.4.0
+
+- PEFT 0.4.0

adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "medicalcode-prefinetune-v3",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32.0,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5377190cdd0804d563e21a7f087a002fade3f0ffc7b20a2918345a2186e8b797
+size 16821197

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 14.63,
+    "train_loss": 7.812765197753906,
+    "train_runtime": 716.3495,
+    "train_samples_per_second": 3.413,
+    "train_steps_per_second": 0.209
+}

finetuning_args.json

@@ -0,0 +1,16 @@
+{
+  "dpo_beta": 0.1,
+  "finetuning_type": "lora",
+  "lora_alpha": 32.0,
+  "lora_dropout": 0.1,
+  "lora_rank": 8,
+  "lora_target": [
+    "q_proj",
+    "v_proj"
+  ],
+  "name_module_trainable": "mlp",
+  "num_hidden_layers": 32,
+  "num_layer_trainable": 3,
+  "ppo_score_norm": false,
+  "resume_lora_training": true
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 14.63,
+    "train_loss": 7.812765197753906,
+    "train_runtime": 716.3495,
+    "train_samples_per_second": 3.413,
+    "train_steps_per_second": 0.209
+}

trainer_log.jsonl

@@ -0,0 +1,16 @@
+{"current_steps": 10, "total_steps": 150, "loss": 2.7294, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9863047384206835e-05, "epoch": 0.98, "percentage": 6.67, "elapsed_time": "0:00:47", "remaining_time": "0:11:02"}
+{"current_steps": 20, "total_steps": 150, "loss": 3.5475, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9453690018345144e-05, "epoch": 1.95, "percentage": 13.33, "elapsed_time": "0:01:34", "remaining_time": "0:10:13"}
+{"current_steps": 30, "total_steps": 150, "loss": 5.3042, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9453690018345144e-05, "epoch": 2.93, "percentage": 20.0, "elapsed_time": "0:02:23", "remaining_time": "0:09:33"}
+{"current_steps": 40, "total_steps": 150, "loss": 6.5608, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9214579028215776e-05, "epoch": 3.9, "percentage": 26.67, "elapsed_time": "0:03:12", "remaining_time": "0:08:49"}
+{"current_steps": 50, "total_steps": 150, "loss": 12.436, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9214579028215776e-05, "epoch": 4.88, "percentage": 33.33, "elapsed_time": "0:04:00", "remaining_time": "0:08:00"}
+{"current_steps": 60, "total_steps": 150, "loss": 8.1905, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9214579028215776e-05, "epoch": 5.85, "percentage": 40.0, "elapsed_time": "0:04:46", "remaining_time": "0:07:09"}
+{"current_steps": 70, "total_steps": 150, "loss": 5.0973, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9214579028215776e-05, "epoch": 6.83, "percentage": 46.67, "elapsed_time": "0:05:36", "remaining_time": "0:06:24"}
+{"current_steps": 80, "total_steps": 150, "loss": 3.3543, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9214579028215776e-05, "epoch": 7.8, "percentage": 53.33, "elapsed_time": "0:06:22", "remaining_time": "0:05:34"}
+{"current_steps": 90, "total_steps": 150, "loss": 9.9021, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.893298743830168e-05, "epoch": 8.78, "percentage": 60.0, "elapsed_time": "0:07:10", "remaining_time": "0:04:47"}
+{"current_steps": 100, "total_steps": 150, "loss": 16.1257, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.893298743830168e-05, "epoch": 9.76, "percentage": 66.67, "elapsed_time": "0:07:57", "remaining_time": "0:03:58"}
+{"current_steps": 110, "total_steps": 150, "loss": 15.988, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.893298743830168e-05, "epoch": 10.73, "percentage": 73.33, "elapsed_time": "0:08:46", "remaining_time": "0:03:11"}
+{"current_steps": 120, "total_steps": 150, "loss": 5.743, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.877641290737884e-05, "epoch": 11.71, "percentage": 80.0, "elapsed_time": "0:09:34", "remaining_time": "0:02:23"}
+{"current_steps": 130, "total_steps": 150, "loss": 4.5123, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.860940925593703e-05, "epoch": 12.68, "percentage": 86.67, "elapsed_time": "0:10:21", "remaining_time": "0:01:35"}
+{"current_steps": 140, "total_steps": 150, "loss": 8.7191, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.860940925593703e-05, "epoch": 13.66, "percentage": 93.33, "elapsed_time": "0:11:10", "remaining_time": "0:00:47"}
+{"current_steps": 150, "total_steps": 150, "loss": 8.9813, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.860940925593703e-05, "epoch": 14.63, "percentage": 100.0, "elapsed_time": "0:11:56", "remaining_time": "0:00:00"}
+{"current_steps": 150, "total_steps": 150, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 14.63, "percentage": 100.0, "elapsed_time": "0:11:56", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,118 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 14.634146341463415,
+  "eval_steps": 500,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.98,
+      "learning_rate": 4.9863047384206835e-05,
+      "loss": 2.7294,
+      "step": 10
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 4.9453690018345144e-05,
+      "loss": 3.5475,
+      "step": 20
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 4.9453690018345144e-05,
+      "loss": 5.3042,
+      "step": 30
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 4.9214579028215776e-05,
+      "loss": 6.5608,
+      "step": 40
+    },
+    {
+      "epoch": 4.88,
+      "learning_rate": 4.9214579028215776e-05,
+      "loss": 12.436,
+      "step": 50
+    },
+    {
+      "epoch": 5.85,
+      "learning_rate": 4.9214579028215776e-05,
+      "loss": 8.1905,
+      "step": 60
+    },
+    {
+      "epoch": 6.83,
+      "learning_rate": 4.9214579028215776e-05,
+      "loss": 5.0973,
+      "step": 70
+    },
+    {
+      "epoch": 7.8,
+      "learning_rate": 4.9214579028215776e-05,
+      "loss": 3.3543,
+      "step": 80
+    },
+    {
+      "epoch": 8.78,
+      "learning_rate": 4.893298743830168e-05,
+      "loss": 9.9021,
+      "step": 90
+    },
+    {
+      "epoch": 9.76,
+      "learning_rate": 4.893298743830168e-05,
+      "loss": 16.1257,
+      "step": 100
+    },
+    {
+      "epoch": 10.73,
+      "learning_rate": 4.893298743830168e-05,
+      "loss": 15.988,
+      "step": 110
+    },
+    {
+      "epoch": 11.71,
+      "learning_rate": 4.877641290737884e-05,
+      "loss": 5.743,
+      "step": 120
+    },
+    {
+      "epoch": 12.68,
+      "learning_rate": 4.860940925593703e-05,
+      "loss": 4.5123,
+      "step": 130
+    },
+    {
+      "epoch": 13.66,
+      "learning_rate": 4.860940925593703e-05,
+      "loss": 8.7191,
+      "step": 140
+    },
+    {
+      "epoch": 14.63,
+      "learning_rate": 4.860940925593703e-05,
+      "loss": 8.9813,
+      "step": 150
+    },
+    {
+      "epoch": 14.63,
+      "step": 150,
+      "total_flos": 3.550292723048448e+16,
+      "train_loss": 7.812765197753906,
+      "train_runtime": 716.3495,
+      "train_samples_per_second": 3.413,
+      "train_steps_per_second": 0.209
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 150,
+  "num_train_epochs": 15,
+  "save_steps": 1000,
+  "total_flos": 3.550292723048448e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc013c5547caf1b5273f81ad4bb2a7b11fe90ffb5a49162a426421bed537e7ff
+size 3330