Upload 9 files

README.md

@@ -1,3 +1,10 @@
 ---
-license: bigscience-openrail-m
+library_name: peft
 ---
+## Training procedure
+
+### Framework versions
+
+- PEFT 0.4.0
+
+- PEFT 0.4.0

adapter_config.json

@@ -0,0 +1,20 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "/HOME/jack/model/chatglm-6b/",
+  "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": [
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:676b20b731081c69a9deae3f0111c5fa0ecb2ba49b132d34c223b7dd607c8ebf
+size 14700057

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.29589878051511703,
+    "train_runtime": 277.1475,
+    "train_samples_per_second": 2.219,
+    "train_steps_per_second": 0.559
+}

finetuning_args.json

@@ -0,0 +1,13 @@
+{
+  "finetuning_type": "lora",
+  "lora_alpha": 32.0,
+  "lora_dropout": 0.1,
+  "lora_rank": 8,
+  "lora_target": [
+    "query_key_value"
+  ],
+  "name_module_trainable": "mlp",
+  "num_layer_trainable": 3,
+  "pre_seq_len": 64,
+  "prefix_projection": false
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.29589878051511703,
+    "train_runtime": 277.1475,
+    "train_samples_per_second": 2.219,
+    "train_steps_per_second": 0.559
+}

trainer_log.jsonl

@@ -0,0 +1,16 @@
+{"current_steps": 10, "total_steps": 155, "loss": 0.7217, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009897649706262473, "epoch": 0.32, "percentage": 6.45, "elapsed_time": "0:00:35", "remaining_time": "0:08:28"}
+{"current_steps": 20, "total_steps": 155, "loss": 0.4332, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009594789058101153, "epoch": 0.65, "percentage": 12.9, "elapsed_time": "0:01:05", "remaining_time": "0:07:24"}
+{"current_steps": 30, "total_steps": 155, "loss": 0.41, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009103817206036382, "epoch": 0.97, "percentage": 19.35, "elapsed_time": "0:01:28", "remaining_time": "0:06:10"}
+{"current_steps": 40, "total_steps": 155, "loss": 0.4098, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0008444834595378434, "epoch": 1.29, "percentage": 25.81, "elapsed_time": "0:01:43", "remaining_time": "0:04:58"}
+{"current_steps": 50, "total_steps": 155, "loss": 0.308, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0007644820051634812, "epoch": 1.61, "percentage": 32.26, "elapsed_time": "0:01:58", "remaining_time": "0:04:08"}
+{"current_steps": 60, "total_steps": 155, "loss": 0.3254, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0006736526264224101, "epoch": 1.94, "percentage": 38.71, "elapsed_time": "0:02:13", "remaining_time": "0:03:31"}
+{"current_steps": 70, "total_steps": 155, "loss": 0.1859, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0005757138887522884, "epoch": 2.26, "percentage": 45.16, "elapsed_time": "0:02:27", "remaining_time": "0:02:59"}
+{"current_steps": 80, "total_steps": 155, "loss": 0.2975, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004746754155806437, "epoch": 2.58, "percentage": 51.61, "elapsed_time": "0:02:42", "remaining_time": "0:02:32"}
+{"current_steps": 90, "total_steps": 155, "loss": 0.2897, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00037467373387063967, "epoch": 2.9, "percentage": 58.06, "elapsed_time": "0:02:58", "remaining_time": "0:02:09"}
+{"current_steps": 100, "total_steps": 155, "loss": 0.1815, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002798029242211828, "epoch": 3.23, "percentage": 64.52, "elapsed_time": "0:03:13", "remaining_time": "0:01:46"}
+{"current_steps": 110, "total_steps": 155, "loss": 0.2632, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019394700872616856, "epoch": 3.55, "percentage": 70.97, "elapsed_time": "0:03:29", "remaining_time": "0:01:25"}
+{"current_steps": 120, "total_steps": 155, "loss": 0.109, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00012062093865360457, "epoch": 3.87, "percentage": 77.42, "elapsed_time": "0:03:44", "remaining_time": "0:01:05"}
+{"current_steps": 130, "total_steps": 155, "loss": 0.2943, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.282669192770896e-05, "epoch": 4.19, "percentage": 83.87, "elapsed_time": "0:03:59", "remaining_time": "0:00:46"}
+{"current_steps": 140, "total_steps": 155, "loss": 0.0821, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2930371799975592e-05, "epoch": 4.52, "percentage": 90.32, "elapsed_time": "0:04:14", "remaining_time": "0:00:27"}
+{"current_steps": 150, "total_steps": 155, "loss": 0.1791, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5653383040524227e-06, "epoch": 4.84, "percentage": 96.77, "elapsed_time": "0:04:29", "remaining_time": "0:00:08"}
+{"current_steps": 155, "total_steps": 155, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "0:04:37", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 155,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0009897649706262473,
+      "loss": 0.7217,
+      "step": 10
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0009594789058101153,
+      "loss": 0.4332,
+      "step": 20
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0009103817206036382,
+      "loss": 0.41,
+      "step": 30
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.0008444834595378434,
+      "loss": 0.4098,
+      "step": 40
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.0007644820051634812,
+      "loss": 0.308,
+      "step": 50
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 0.0006736526264224101,
+      "loss": 0.3254,
+      "step": 60
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 0.0005757138887522884,
+      "loss": 0.1859,
+      "step": 70
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 0.0004746754155806437,
+      "loss": 0.2975,
+      "step": 80
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 0.00037467373387063967,
+      "loss": 0.2897,
+      "step": 90
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 0.0002798029242211828,
+      "loss": 0.1815,
+      "step": 100
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 0.00019394700872616856,
+      "loss": 0.2632,
+      "step": 110
+    },
+    {
+      "epoch": 3.87,
+      "learning_rate": 0.00012062093865360457,
+      "loss": 0.109,
+      "step": 120
+    },
+    {
+      "epoch": 4.19,
+      "learning_rate": 6.282669192770896e-05,
+      "loss": 0.2943,
+      "step": 130
+    },
+    {
+      "epoch": 4.52,
+      "learning_rate": 2.2930371799975592e-05,
+      "loss": 0.0821,
+      "step": 140
+    },
+    {
+      "epoch": 4.84,
+      "learning_rate": 2.5653383040524227e-06,
+      "loss": 0.1791,
+      "step": 150
+    },
+    {
+      "epoch": 5.0,
+      "step": 155,
+      "total_flos": 1.7897091891019776e+16,
+      "train_loss": 0.29589878051511703,
+      "train_runtime": 277.1475,
+      "train_samples_per_second": 2.219,
+      "train_steps_per_second": 0.559
+    }
+  ],
+  "max_steps": 155,
+  "num_train_epochs": 5,
+  "total_flos": 1.7897091891019776e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e31fb62b9330340d05178325de3b580880975dceb0d71e8057bea364092e24e
+size 3326