Upload 10 files

README.md

@@ -0,0 +1,9 @@
+---
+library_name: peft
+---
+## Training procedure
+
+### Framework versions
+
+
+- PEFT 0.4.0

adapter_config.json

@@ -0,0 +1,20 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "baichuan-inc/Baichuan-7B",
+  "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": [
+    "W_pack"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89ecbea566551453abb624441feb0a0e587636b975b586c9673c55cae3e277ca
+size 16799153

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.99,
+    "train_loss": 2.964561536835461,
+    "train_runtime": 1710.3688,
+    "train_samples_per_second": 5.771,
+    "train_steps_per_second": 0.36
+}

finetuning_args.json

@@ -0,0 +1,12 @@
+{
+  "finetuning_type": "lora",
+  "lora_alpha": 32.0,
+  "lora_dropout": 0.1,
+  "lora_rank": 8,
+  "lora_target": [
+    "W_pack"
+  ],
+  "name_module_trainable": "mlp",
+  "num_hidden_layers": 32,
+  "num_layer_trainable": 3
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.99,
+    "train_loss": 2.964561536835461,
+    "train_runtime": 1710.3688,
+    "train_samples_per_second": 5.771,
+    "train_steps_per_second": 0.36
+}

trainer_log.jsonl

@@ -0,0 +1,62 @@
+{"current_steps": 10, "total_steps": 615, "loss": 3.1898, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.996738892723075e-05, "epoch": 0.05, "percentage": 1.63, "elapsed_time": "0:00:28", "remaining_time": "0:28:38"}
+{"current_steps": 20, "total_steps": 615, "loss": 3.0387, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.986964078748837e-05, "epoch": 0.1, "percentage": 3.25, "elapsed_time": "0:00:56", "remaining_time": "0:27:48"}
+{"current_steps": 30, "total_steps": 615, "loss": 3.1413, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.970701059450872e-05, "epoch": 0.15, "percentage": 4.88, "elapsed_time": "0:01:22", "remaining_time": "0:26:51"}
+{"current_steps": 40, "total_steps": 615, "loss": 3.0543, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9479922631896405e-05, "epoch": 0.19, "percentage": 6.5, "elapsed_time": "0:01:51", "remaining_time": "0:26:40"}
+{"current_steps": 50, "total_steps": 615, "loss": 3.0544, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.918896934621734e-05, "epoch": 0.24, "percentage": 8.13, "elapsed_time": "0:02:19", "remaining_time": "0:26:13"}
+{"current_steps": 60, "total_steps": 615, "loss": 2.9954, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8834909801373264e-05, "epoch": 0.29, "percentage": 9.76, "elapsed_time": "0:02:45", "remaining_time": "0:25:34"}
+{"current_steps": 70, "total_steps": 615, "loss": 3.0829, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8418667698290696e-05, "epoch": 0.34, "percentage": 11.38, "elapsed_time": "0:03:14", "remaining_time": "0:25:13"}
+{"current_steps": 80, "total_steps": 615, "loss": 3.0368, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.79413289650907e-05, "epoch": 0.39, "percentage": 13.01, "elapsed_time": "0:03:43", "remaining_time": "0:24:55"}
+{"current_steps": 90, "total_steps": 615, "loss": 2.941, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.740413892402639e-05, "epoch": 0.44, "percentage": 14.63, "elapsed_time": "0:04:10", "remaining_time": "0:24:23"}
+{"current_steps": 100, "total_steps": 615, "loss": 2.9253, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.680849904257938e-05, "epoch": 0.49, "percentage": 16.26, "elapsed_time": "0:04:38", "remaining_time": "0:23:56"}
+{"current_steps": 110, "total_steps": 615, "loss": 2.9969, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.615596327719111e-05, "epoch": 0.53, "percentage": 17.89, "elapsed_time": "0:05:06", "remaining_time": "0:23:26"}
+{"current_steps": 120, "total_steps": 615, "loss": 2.9547, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.5448234019167945e-05, "epoch": 0.58, "percentage": 19.51, "elapsed_time": "0:05:33", "remaining_time": "0:22:55"}
+{"current_steps": 130, "total_steps": 615, "loss": 3.021, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.468715765333664e-05, "epoch": 0.63, "percentage": 21.14, "elapsed_time": "0:06:03", "remaining_time": "0:22:35"}
+{"current_steps": 140, "total_steps": 615, "loss": 2.96, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.387471974103713e-05, "epoch": 0.68, "percentage": 22.76, "elapsed_time": "0:06:30", "remaining_time": "0:22:05"}
+{"current_steps": 150, "total_steps": 615, "loss": 3.0919, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.301303984001967e-05, "epoch": 0.73, "percentage": 24.39, "elapsed_time": "0:06:57", "remaining_time": "0:21:34"}
+{"current_steps": 160, "total_steps": 615, "loss": 2.9032, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.210436597476076e-05, "epoch": 0.78, "percentage": 26.02, "elapsed_time": "0:07:23", "remaining_time": "0:21:02"}
+{"current_steps": 170, "total_steps": 615, "loss": 2.9535, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.1151068771623866e-05, "epoch": 0.83, "percentage": 27.64, "elapsed_time": "0:07:52", "remaining_time": "0:20:37"}
+{"current_steps": 180, "total_steps": 615, "loss": 2.9935, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.015563527416595e-05, "epoch": 0.87, "percentage": 29.27, "elapsed_time": "0:08:21", "remaining_time": "0:20:12"}
+{"current_steps": 190, "total_steps": 615, "loss": 3.0283, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.9120662454724836e-05, "epoch": 0.92, "percentage": 30.89, "elapsed_time": "0:08:48", "remaining_time": "0:19:42"}
+{"current_steps": 200, "total_steps": 615, "loss": 2.9129, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.8048850439214844e-05, "epoch": 0.97, "percentage": 32.52, "elapsed_time": "0:09:15", "remaining_time": "0:19:13"}
+{"current_steps": 210, "total_steps": 615, "loss": 2.9757, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.694299546280657e-05, "epoch": 1.02, "percentage": 34.15, "elapsed_time": "0:09:45", "remaining_time": "0:18:48"}
+{"current_steps": 220, "total_steps": 615, "loss": 2.9132, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.580598257486867e-05, "epoch": 1.07, "percentage": 35.77, "elapsed_time": "0:10:13", "remaining_time": "0:18:20"}
+{"current_steps": 230, "total_steps": 615, "loss": 2.8876, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.46407781122034e-05, "epoch": 1.12, "percentage": 37.4, "elapsed_time": "0:10:40", "remaining_time": "0:17:52"}
+{"current_steps": 240, "total_steps": 615, "loss": 2.9416, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.3450421960212566e-05, "epoch": 1.17, "percentage": 39.02, "elapsed_time": "0:11:08", "remaining_time": "0:17:24"}
+{"current_steps": 250, "total_steps": 615, "loss": 2.994, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.223801962218372e-05, "epoch": 1.22, "percentage": 40.65, "elapsed_time": "0:11:36", "remaining_time": "0:16:56"}
+{"current_steps": 260, "total_steps": 615, "loss": 2.9024, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.100673411738652e-05, "epoch": 1.26, "percentage": 42.28, "elapsed_time": "0:12:03", "remaining_time": "0:16:28"}
+{"current_steps": 270, "total_steps": 615, "loss": 2.9789, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.975977772911671e-05, "epoch": 1.31, "percentage": 43.9, "elapsed_time": "0:12:31", "remaining_time": "0:16:00"}
+{"current_steps": 280, "total_steps": 615, "loss": 2.9478, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8500403624215734e-05, "epoch": 1.36, "percentage": 45.53, "elapsed_time": "0:13:00", "remaining_time": "0:15:33"}
+{"current_steps": 290, "total_steps": 615, "loss": 2.8663, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.723189736592986e-05, "epoch": 1.41, "percentage": 47.15, "elapsed_time": "0:13:27", "remaining_time": "0:15:04"}
+{"current_steps": 300, "total_steps": 615, "loss": 3.0051, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.595756834225089e-05, "epoch": 1.46, "percentage": 48.78, "elapsed_time": "0:13:55", "remaining_time": "0:14:37"}
+{"current_steps": 310, "total_steps": 615, "loss": 2.8488, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.468074113210066e-05, "epoch": 1.51, "percentage": 50.41, "elapsed_time": "0:14:22", "remaining_time": "0:14:09"}
+{"current_steps": 320, "total_steps": 615, "loss": 2.9825, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.340474683188429e-05, "epoch": 1.56, "percentage": 52.03, "elapsed_time": "0:14:50", "remaining_time": "0:13:40"}
+{"current_steps": 330, "total_steps": 615, "loss": 3.0427, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2132914365039993e-05, "epoch": 1.6, "percentage": 53.66, "elapsed_time": "0:15:18", "remaining_time": "0:13:12"}
+{"current_steps": 340, "total_steps": 615, "loss": 3.0026, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0868561797257878e-05, "epoch": 1.65, "percentage": 55.28, "elapsed_time": "0:15:44", "remaining_time": "0:12:44"}
+{"current_steps": 350, "total_steps": 615, "loss": 2.984, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.961498768002547e-05, "epoch": 1.7, "percentage": 56.91, "elapsed_time": "0:16:11", "remaining_time": "0:12:15"}
+{"current_steps": 360, "total_steps": 615, "loss": 2.9845, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8375462445083464e-05, "epoch": 1.75, "percentage": 58.54, "elapsed_time": "0:16:42", "remaining_time": "0:11:49"}
+{"current_steps": 370, "total_steps": 615, "loss": 2.9139, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7153219872242727e-05, "epoch": 1.8, "percentage": 60.16, "elapsed_time": "0:17:09", "remaining_time": "0:11:21"}
+{"current_steps": 380, "total_steps": 615, "loss": 3.0234, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5951448652822047e-05, "epoch": 1.85, "percentage": 61.79, "elapsed_time": "0:17:35", "remaining_time": "0:10:52"}
+{"current_steps": 390, "total_steps": 615, "loss": 2.9504, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4773284070716503e-05, "epoch": 1.9, "percentage": 63.41, "elapsed_time": "0:18:03", "remaining_time": "0:10:25"}
+{"current_steps": 400, "total_steps": 615, "loss": 2.9035, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3621799822799788e-05, "epoch": 1.94, "percentage": 65.04, "elapsed_time": "0:18:32", "remaining_time": "0:09:58"}
+{"current_steps": 410, "total_steps": 615, "loss": 2.9339, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2500000000000006e-05, "epoch": 1.99, "percentage": 66.67, "elapsed_time": "0:19:00", "remaining_time": "0:09:30"}
+{"current_steps": 420, "total_steps": 615, "loss": 2.9613, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1410811249969475e-05, "epoch": 2.04, "percentage": 68.29, "elapsed_time": "0:19:27", "remaining_time": "0:09:02"}
+{"current_steps": 430, "total_steps": 615, "loss": 2.9762, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.035707514179513e-05, "epoch": 2.09, "percentage": 69.92, "elapsed_time": "0:19:54", "remaining_time": "0:08:34"}
+{"current_steps": 440, "total_steps": 615, "loss": 2.8895, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.341540752669235e-06, "epoch": 2.14, "percentage": 71.54, "elapsed_time": "0:20:22", "remaining_time": "0:08:06"}
+{"current_steps": 450, "total_steps": 615, "loss": 2.9219, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.36685749586087e-06, "epoch": 2.19, "percentage": 73.17, "elapsed_time": "0:20:50", "remaining_time": "0:07:38"}
+{"current_steps": 460, "total_steps": 615, "loss": 2.8863, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.435568208699203e-06, "epoch": 2.24, "percentage": 74.8, "elapsed_time": "0:21:18", "remaining_time": "0:07:10"}
+{"current_steps": 470, "total_steps": 615, "loss": 2.8696, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.55010251860127e-06, "epoch": 2.28, "percentage": 76.42, "elapsed_time": "0:21:48", "remaining_time": "0:06:43"}
+{"current_steps": 480, "total_steps": 615, "loss": 2.8808, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.712770504451426e-06, "epoch": 2.33, "percentage": 78.05, "elapsed_time": "0:22:16", "remaining_time": "0:06:15"}
+{"current_steps": 490, "total_steps": 615, "loss": 2.9685, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.925756669869314e-06, "epoch": 2.38, "percentage": 79.67, "elapsed_time": "0:22:44", "remaining_time": "0:05:48"}
+{"current_steps": 500, "total_steps": 615, "loss": 2.8873, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.19111424408932e-06, "epoch": 2.43, "percentage": 81.3, "elapsed_time": "0:23:10", "remaining_time": "0:05:19"}
+{"current_steps": 510, "total_steps": 615, "loss": 2.9854, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.5107598253199758e-06, "epoch": 2.48, "percentage": 82.93, "elapsed_time": "0:23:39", "remaining_time": "0:04:52"}
+{"current_steps": 520, "total_steps": 615, "loss": 2.9411, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8864683805580133e-06, "epoch": 2.53, "percentage": 84.55, "elapsed_time": "0:24:06", "remaining_time": "0:04:24"}
+{"current_steps": 530, "total_steps": 615, "loss": 2.9353, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3198686149022013e-06, "epoch": 2.58, "percentage": 86.18, "elapsed_time": "0:24:32", "remaining_time": "0:03:56"}
+{"current_steps": 540, "total_steps": 615, "loss": 2.9348, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8124387224476347e-06, "epoch": 2.62, "percentage": 87.8, "elapsed_time": "0:25:01", "remaining_time": "0:03:28"}
+{"current_steps": 550, "total_steps": 615, "loss": 2.8754, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.365502529846166e-06, "epoch": 2.67, "percentage": 89.43, "elapsed_time": "0:25:29", "remaining_time": "0:03:00"}
+{"current_steps": 560, "total_steps": 615, "loss": 2.925, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.802260425938099e-07, "epoch": 2.72, "percentage": 91.06, "elapsed_time": "0:25:57", "remaining_time": "0:02:32"}
+{"current_steps": 570, "total_steps": 615, "loss": 2.976, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.576144030555259e-07, "epoch": 2.77, "percentage": 92.68, "elapsed_time": "0:26:26", "remaining_time": "0:02:05"}
+{"current_steps": 580, "total_steps": 615, "loss": 2.913, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.9850926816357157e-07, "epoch": 2.82, "percentage": 94.31, "elapsed_time": "0:26:54", "remaining_time": "0:01:37"}
+{"current_steps": 590, "total_steps": 615, "loss": 2.9485, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0358661363065746e-07, "epoch": 2.87, "percentage": 95.93, "elapsed_time": "0:27:21", "remaining_time": "0:01:09"}
+{"current_steps": 600, "total_steps": 615, "loss": 2.946, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.335497040648898e-08, "epoch": 2.92, "percentage": 97.56, "elapsed_time": "0:27:48", "remaining_time": "0:00:41"}
+{"current_steps": 610, "total_steps": 615, "loss": 2.982, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.154097978591014e-09, "epoch": 2.96, "percentage": 99.19, "elapsed_time": "0:28:16", "remaining_time": "0:00:13"}
+{"current_steps": 615, "total_steps": 615, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.99, "percentage": 100.0, "elapsed_time": "0:28:30", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,391 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.98906439854192,
+  "global_step": 615,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.996738892723075e-05,
+      "loss": 3.1898,
+      "step": 10
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.986964078748837e-05,
+      "loss": 3.0387,
+      "step": 20
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.970701059450872e-05,
+      "loss": 3.1413,
+      "step": 30
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.9479922631896405e-05,
+      "loss": 3.0543,
+      "step": 40
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.918896934621734e-05,
+      "loss": 3.0544,
+      "step": 50
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.8834909801373264e-05,
+      "loss": 2.9954,
+      "step": 60
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.8418667698290696e-05,
+      "loss": 3.0829,
+      "step": 70
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.79413289650907e-05,
+      "loss": 3.0368,
+      "step": 80
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.740413892402639e-05,
+      "loss": 2.941,
+      "step": 90
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 4.680849904257938e-05,
+      "loss": 2.9253,
+      "step": 100
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.615596327719111e-05,
+      "loss": 2.9969,
+      "step": 110
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.5448234019167945e-05,
+      "loss": 2.9547,
+      "step": 120
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.468715765333664e-05,
+      "loss": 3.021,
+      "step": 130
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.387471974103713e-05,
+      "loss": 2.96,
+      "step": 140
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.301303984001967e-05,
+      "loss": 3.0919,
+      "step": 150
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 4.210436597476076e-05,
+      "loss": 2.9032,
+      "step": 160
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 4.1151068771623866e-05,
+      "loss": 2.9535,
+      "step": 170
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 4.015563527416595e-05,
+      "loss": 2.9935,
+      "step": 180
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.9120662454724836e-05,
+      "loss": 3.0283,
+      "step": 190
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.8048850439214844e-05,
+      "loss": 2.9129,
+      "step": 200
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 3.694299546280657e-05,
+      "loss": 2.9757,
+      "step": 210
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 3.580598257486867e-05,
+      "loss": 2.9132,
+      "step": 220
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 3.46407781122034e-05,
+      "loss": 2.8876,
+      "step": 230
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 3.3450421960212566e-05,
+      "loss": 2.9416,
+      "step": 240
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 3.223801962218372e-05,
+      "loss": 2.994,
+      "step": 250
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 3.100673411738652e-05,
+      "loss": 2.9024,
+      "step": 260
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 2.975977772911671e-05,
+      "loss": 2.9789,
+      "step": 270
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 2.8500403624215734e-05,
+      "loss": 2.9478,
+      "step": 280
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 2.723189736592986e-05,
+      "loss": 2.8663,
+      "step": 290
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 2.595756834225089e-05,
+      "loss": 3.0051,
+      "step": 300
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 2.468074113210066e-05,
+      "loss": 2.8488,
+      "step": 310
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 2.340474683188429e-05,
+      "loss": 2.9825,
+      "step": 320
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.2132914365039993e-05,
+      "loss": 3.0427,
+      "step": 330
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 2.0868561797257878e-05,
+      "loss": 3.0026,
+      "step": 340
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.961498768002547e-05,
+      "loss": 2.984,
+      "step": 350
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 1.8375462445083464e-05,
+      "loss": 2.9845,
+      "step": 360
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.7153219872242727e-05,
+      "loss": 2.9139,
+      "step": 370
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 1.5951448652822047e-05,
+      "loss": 3.0234,
+      "step": 380
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.4773284070716503e-05,
+      "loss": 2.9504,
+      "step": 390
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.3621799822799788e-05,
+      "loss": 2.9035,
+      "step": 400
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 2.9339,
+      "step": 410
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 1.1410811249969475e-05,
+      "loss": 2.9613,
+      "step": 420
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 1.035707514179513e-05,
+      "loss": 2.9762,
+      "step": 430
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 9.341540752669235e-06,
+      "loss": 2.8895,
+      "step": 440
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 8.36685749586087e-06,
+      "loss": 2.9219,
+      "step": 450
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 7.435568208699203e-06,
+      "loss": 2.8863,
+      "step": 460
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 6.55010251860127e-06,
+      "loss": 2.8696,
+      "step": 470
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 5.712770504451426e-06,
+      "loss": 2.8808,
+      "step": 480
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 4.925756669869314e-06,
+      "loss": 2.9685,
+      "step": 490
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 4.19111424408932e-06,
+      "loss": 2.8873,
+      "step": 500
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 3.5107598253199758e-06,
+      "loss": 2.9854,
+      "step": 510
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 2.8864683805580133e-06,
+      "loss": 2.9411,
+      "step": 520
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 2.3198686149022013e-06,
+      "loss": 2.9353,
+      "step": 530
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 1.8124387224476347e-06,
+      "loss": 2.9348,
+      "step": 540
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 1.365502529846166e-06,
+      "loss": 2.8754,
+      "step": 550
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 9.802260425938099e-07,
+      "loss": 2.925,
+      "step": 560
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 6.576144030555259e-07,
+      "loss": 2.976,
+      "step": 570
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 3.9850926816357157e-07,
+      "loss": 2.913,
+      "step": 580
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 2.0358661363065746e-07,
+      "loss": 2.9485,
+      "step": 590
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 7.335497040648898e-08,
+      "loss": 2.946,
+      "step": 600
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 8.154097978591014e-09,
+      "loss": 2.982,
+      "step": 610
+    },
+    {
+      "epoch": 2.99,
+      "step": 615,
+      "total_flos": 7.322328732745728e+16,
+      "train_loss": 2.964561536835461,
+      "train_runtime": 1710.3688,
+      "train_samples_per_second": 5.771,
+      "train_steps_per_second": 0.36
+    }
+  ],
+  "max_steps": 615,
+  "num_train_epochs": 3,
+  "total_flos": 7.322328732745728e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a6a7accf57470c06ec32db53579d7f0b36ea62a9b1f1250ab49aa0d99087bb3
+size 3325