Upload 9 files

README.md

@@ -1,3 +1,9 @@
 ---
-license: bigscience-openrail-m
+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": "/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 sha256:300597c54f0972fe96bbc2f1b3fd9ecb320930708a2ac7582ac458b29ff9806b
+size 14700057

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 20.0,
+    "train_loss": 0.09885127827404969,
+    "train_runtime": 1180.114,
+    "train_samples_per_second": 2.085,
+    "train_steps_per_second": 0.525
+}

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": 20.0,
+    "train_loss": 0.09885127827404969,
+    "train_runtime": 1180.114,
+    "train_samples_per_second": 2.085,
+    "train_steps_per_second": 0.525
+}

trainer_log.jsonl

@@ -0,0 +1,63 @@
+{"current_steps": 10, "total_steps": 620, "loss": 0.7008, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009993582535855264, "epoch": 0.32, "percentage": 1.61, "elapsed_time": "0:00:17", "remaining_time": "0:17:19"}
+{"current_steps": 20, "total_steps": 620, "loss": 0.4261, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009974346616959476, "epoch": 0.65, "percentage": 3.23, "elapsed_time": "0:00:31", "remaining_time": "0:15:51"}
+{"current_steps": 30, "total_steps": 620, "loss": 0.3999, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009942341621640557, "epoch": 0.97, "percentage": 4.84, "elapsed_time": "0:00:46", "remaining_time": "0:15:23"}
+{"current_steps": 40, "total_steps": 620, "loss": 0.403, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009897649706262473, "epoch": 1.29, "percentage": 6.45, "elapsed_time": "0:01:02", "remaining_time": "0:15:02"}
+{"current_steps": 50, "total_steps": 620, "loss": 0.3025, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000984038559433102, "epoch": 1.61, "percentage": 8.06, "elapsed_time": "0:01:16", "remaining_time": "0:14:35"}
+{"current_steps": 60, "total_steps": 620, "loss": 0.3243, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009770696282000244, "epoch": 1.94, "percentage": 9.68, "elapsed_time": "0:01:32", "remaining_time": "0:14:19"}
+{"current_steps": 70, "total_steps": 620, "loss": 0.1971, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009688760660735403, "epoch": 2.26, "percentage": 11.29, "elapsed_time": "0:01:46", "remaining_time": "0:13:57"}
+{"current_steps": 80, "total_steps": 620, "loss": 0.3054, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009594789058101153, "epoch": 2.58, "percentage": 12.9, "elapsed_time": "0:02:01", "remaining_time": "0:13:40"}
+{"current_steps": 90, "total_steps": 620, "loss": 0.3146, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009489022697853709, "epoch": 2.9, "percentage": 14.52, "elapsed_time": "0:02:17", "remaining_time": "0:13:28"}
+{"current_steps": 100, "total_steps": 620, "loss": 0.1914, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009371733080722911, "epoch": 3.23, "percentage": 16.13, "elapsed_time": "0:02:31", "remaining_time": "0:13:09"}
+{"current_steps": 110, "total_steps": 620, "loss": 0.2848, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009243221287473755, "epoch": 3.55, "percentage": 17.74, "elapsed_time": "0:02:48", "remaining_time": "0:13:02"}
+{"current_steps": 120, "total_steps": 620, "loss": 0.1316, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009103817206036382, "epoch": 3.87, "percentage": 19.35, "elapsed_time": "0:03:04", "remaining_time": "0:12:47"}
+{"current_steps": 130, "total_steps": 620, "loss": 0.3139, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0008953878684688492, "epoch": 4.19, "percentage": 20.97, "elapsed_time": "0:03:20", "remaining_time": "0:12:37"}
+{"current_steps": 140, "total_steps": 620, "loss": 0.1033, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0008793790613463954, "epoch": 4.52, "percentage": 22.58, "elapsed_time": "0:03:40", "remaining_time": "0:12:36"}
+{"current_steps": 150, "total_steps": 620, "loss": 0.1794, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00086239639361456, "epoch": 4.84, "percentage": 24.19, "elapsed_time": "0:03:58", "remaining_time": "0:12:28"}
+{"current_steps": 160, "total_steps": 620, "loss": 0.1794, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0008444834595378434, "epoch": 5.16, "percentage": 25.81, "elapsed_time": "0:04:14", "remaining_time": "0:12:10"}
+{"current_steps": 170, "total_steps": 620, "loss": 0.1136, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0008256862413611113, "epoch": 5.48, "percentage": 27.42, "elapsed_time": "0:04:29", "remaining_time": "0:11:52"}
+{"current_steps": 180, "total_steps": 620, "loss": 0.1584, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0008060529912738315, "epoch": 5.81, "percentage": 29.03, "elapsed_time": "0:04:44", "remaining_time": "0:11:34"}
+{"current_steps": 190, "total_steps": 620, "loss": 0.1127, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0007856341075473961, "epoch": 6.13, "percentage": 30.65, "elapsed_time": "0:05:01", "remaining_time": "0:11:23"}
+{"current_steps": 200, "total_steps": 620, "loss": 0.1422, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0007644820051634812, "epoch": 6.45, "percentage": 32.26, "elapsed_time": "0:05:22", "remaining_time": "0:11:16"}
+{"current_steps": 210, "total_steps": 620, "loss": 0.1001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0007426509812655407, "epoch": 6.77, "percentage": 33.87, "elapsed_time": "0:05:44", "remaining_time": "0:11:12"}
+{"current_steps": 220, "total_steps": 620, "loss": 0.0521, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0007201970757788173, "epoch": 7.1, "percentage": 35.48, "elapsed_time": "0:06:04", "remaining_time": "0:11:02"}
+{"current_steps": 230, "total_steps": 620, "loss": 0.0499, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0006971779275566593, "epoch": 7.42, "percentage": 37.1, "elapsed_time": "0:06:23", "remaining_time": "0:10:51"}
+{"current_steps": 240, "total_steps": 620, "loss": 0.1083, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0006736526264224101, "epoch": 7.74, "percentage": 38.71, "elapsed_time": "0:06:44", "remaining_time": "0:10:39"}
+{"current_steps": 250, "total_steps": 620, "loss": 0.0762, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0006496815614866791, "epoch": 8.06, "percentage": 40.32, "elapsed_time": "0:07:04", "remaining_time": "0:10:27"}
+{"current_steps": 260, "total_steps": 620, "loss": 0.0363, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0006253262661293602, "epoch": 8.39, "percentage": 41.94, "elapsed_time": "0:07:24", "remaining_time": "0:10:15"}
+{"current_steps": 270, "total_steps": 620, "loss": 0.0455, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0006006492600443301, "epoch": 8.71, "percentage": 43.55, "elapsed_time": "0:07:45", "remaining_time": "0:10:02"}
+{"current_steps": 280, "total_steps": 620, "loss": 0.0614, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0005757138887522884, "epoch": 9.03, "percentage": 45.16, "elapsed_time": "0:08:04", "remaining_time": "0:09:48"}
+{"current_steps": 290, "total_steps": 620, "loss": 0.0279, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0005505841609937161, "epoch": 9.35, "percentage": 46.77, "elapsed_time": "0:08:24", "remaining_time": "0:09:34"}
+{"current_steps": 300, "total_steps": 620, "loss": 0.0383, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0005253245844193564, "epoch": 9.68, "percentage": 48.39, "elapsed_time": "0:08:45", "remaining_time": "0:09:20"}
+{"current_steps": 310, "total_steps": 620, "loss": 0.0219, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0005, "epoch": 10.0, "percentage": 50.0, "elapsed_time": "0:09:06", "remaining_time": "0:09:06"}
+{"current_steps": 320, "total_steps": 620, "loss": 0.0069, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004746754155806437, "epoch": 10.32, "percentage": 51.61, "elapsed_time": "0:09:27", "remaining_time": "0:08:51"}
+{"current_steps": 330, "total_steps": 620, "loss": 0.0399, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000449415839006284, "epoch": 10.65, "percentage": 53.23, "elapsed_time": "0:09:48", "remaining_time": "0:08:37"}
+{"current_steps": 340, "total_steps": 620, "loss": 0.0208, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00042428611124771184, "epoch": 10.97, "percentage": 54.84, "elapsed_time": "0:10:08", "remaining_time": "0:08:21"}
+{"current_steps": 350, "total_steps": 620, "loss": 0.0109, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003993507399556699, "epoch": 11.29, "percentage": 56.45, "elapsed_time": "0:10:28", "remaining_time": "0:08:04"}
+{"current_steps": 360, "total_steps": 620, "loss": 0.0249, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00037467373387063967, "epoch": 11.61, "percentage": 58.06, "elapsed_time": "0:10:49", "remaining_time": "0:07:49"}
+{"current_steps": 370, "total_steps": 620, "loss": 0.0041, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000350318438513321, "epoch": 11.94, "percentage": 59.68, "elapsed_time": "0:11:09", "remaining_time": "0:07:32"}
+{"current_steps": 380, "total_steps": 620, "loss": 0.009, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003263473735775899, "epoch": 12.26, "percentage": 61.29, "elapsed_time": "0:11:28", "remaining_time": "0:07:15"}
+{"current_steps": 390, "total_steps": 620, "loss": 0.007, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00030282207244334083, "epoch": 12.58, "percentage": 62.9, "elapsed_time": "0:11:49", "remaining_time": "0:06:58"}
+{"current_steps": 400, "total_steps": 620, "loss": 0.0089, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002798029242211828, "epoch": 12.9, "percentage": 64.52, "elapsed_time": "0:12:09", "remaining_time": "0:06:41"}
+{"current_steps": 410, "total_steps": 620, "loss": 0.0103, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002573490187344596, "epoch": 13.23, "percentage": 66.13, "elapsed_time": "0:12:31", "remaining_time": "0:06:24"}
+{"current_steps": 420, "total_steps": 620, "loss": 0.0054, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002355179948365189, "epoch": 13.55, "percentage": 67.74, "elapsed_time": "0:12:52", "remaining_time": "0:06:07"}
+{"current_steps": 430, "total_steps": 620, "loss": 0.0037, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00021436589245260373, "epoch": 13.87, "percentage": 69.35, "elapsed_time": "0:13:12", "remaining_time": "0:05:49"}
+{"current_steps": 440, "total_steps": 620, "loss": 0.0047, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019394700872616856, "epoch": 14.19, "percentage": 70.97, "elapsed_time": "0:13:31", "remaining_time": "0:05:31"}
+{"current_steps": 450, "total_steps": 620, "loss": 0.0061, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00017431375863888898, "epoch": 14.52, "percentage": 72.58, "elapsed_time": "0:13:52", "remaining_time": "0:05:14"}
+{"current_steps": 460, "total_steps": 620, "loss": 0.0043, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00015551654046215668, "epoch": 14.84, "percentage": 74.19, "elapsed_time": "0:14:12", "remaining_time": "0:04:56"}
+{"current_steps": 470, "total_steps": 620, "loss": 0.0058, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00013760360638544013, "epoch": 15.16, "percentage": 75.81, "elapsed_time": "0:14:33", "remaining_time": "0:04:38"}
+{"current_steps": 480, "total_steps": 620, "loss": 0.0029, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00012062093865360457, "epoch": 15.48, "percentage": 77.42, "elapsed_time": "0:14:53", "remaining_time": "0:04:20"}
+{"current_steps": 490, "total_steps": 620, "loss": 0.0037, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00010461213153115079, "epoch": 15.81, "percentage": 79.03, "elapsed_time": "0:15:14", "remaining_time": "0:04:02"}
+{"current_steps": 500, "total_steps": 620, "loss": 0.004, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.961827939636197e-05, "epoch": 16.13, "percentage": 80.65, "elapsed_time": "0:15:35", "remaining_time": "0:03:44"}
+{"current_steps": 510, "total_steps": 620, "loss": 0.0048, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.567787125262449e-05, "epoch": 16.45, "percentage": 82.26, "elapsed_time": "0:15:57", "remaining_time": "0:03:26"}
+{"current_steps": 520, "total_steps": 620, "loss": 0.0036, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.282669192770896e-05, "epoch": 16.77, "percentage": 83.87, "elapsed_time": "0:16:17", "remaining_time": "0:03:07"}
+{"current_steps": 530, "total_steps": 620, "loss": 0.0018, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.109773021462921e-05, "epoch": 17.1, "percentage": 85.48, "elapsed_time": "0:16:36", "remaining_time": "0:02:49"}
+{"current_steps": 540, "total_steps": 620, "loss": 0.0039, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.05210941898847e-05, "epoch": 17.42, "percentage": 87.1, "elapsed_time": "0:16:56", "remaining_time": "0:02:30"}
+{"current_steps": 550, "total_steps": 620, "loss": 0.004, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.112393392645985e-05, "epoch": 17.74, "percentage": 88.71, "elapsed_time": "0:17:17", "remaining_time": "0:02:12"}
+{"current_steps": 560, "total_steps": 620, "loss": 0.0038, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2930371799975592e-05, "epoch": 18.06, "percentage": 90.32, "elapsed_time": "0:17:37", "remaining_time": "0:01:53"}
+{"current_steps": 570, "total_steps": 620, "loss": 0.0027, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.596144056689791e-05, "epoch": 18.39, "percentage": 91.94, "elapsed_time": "0:17:57", "remaining_time": "0:01:34"}
+{"current_steps": 580, "total_steps": 620, "loss": 0.0043, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0235029373752758e-05, "epoch": 18.71, "percentage": 93.55, "elapsed_time": "0:18:17", "remaining_time": "0:01:15"}
+{"current_steps": 590, "total_steps": 620, "loss": 0.0034, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.76583783594431e-06, "epoch": 19.03, "percentage": 95.16, "elapsed_time": "0:18:37", "remaining_time": "0:00:56"}
+{"current_steps": 600, "total_steps": 620, "loss": 0.0034, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5653383040524227e-06, "epoch": 19.35, "percentage": 96.77, "elapsed_time": "0:18:58", "remaining_time": "0:00:37"}
+{"current_steps": 610, "total_steps": 620, "loss": 0.0037, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.417464144736207e-07, "epoch": 19.68, "percentage": 98.39, "elapsed_time": "0:19:20", "remaining_time": "0:00:19"}
+{"current_steps": 620, "total_steps": 620, "loss": 0.0038, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:19:40", "remaining_time": "0:00:00"}
+{"current_steps": 620, "total_steps": 620, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:19:40", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,397 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 20.0,
+  "global_step": 620,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0009993582535855264,
+      "loss": 0.7008,
+      "step": 10
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0009974346616959476,
+      "loss": 0.4261,
+      "step": 20
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0009942341621640557,
+      "loss": 0.3999,
+      "step": 30
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.0009897649706262473,
+      "loss": 0.403,
+      "step": 40
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.000984038559433102,
+      "loss": 0.3025,
+      "step": 50
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 0.0009770696282000244,
+      "loss": 0.3243,
+      "step": 60
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 0.0009688760660735403,
+      "loss": 0.1971,
+      "step": 70
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 0.0009594789058101153,
+      "loss": 0.3054,
+      "step": 80
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 0.0009489022697853709,
+      "loss": 0.3146,
+      "step": 90
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 0.0009371733080722911,
+      "loss": 0.1914,
+      "step": 100
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 0.0009243221287473755,
+      "loss": 0.2848,
+      "step": 110
+    },
+    {
+      "epoch": 3.87,
+      "learning_rate": 0.0009103817206036382,
+      "loss": 0.1316,
+      "step": 120
+    },
+    {
+      "epoch": 4.19,
+      "learning_rate": 0.0008953878684688492,
+      "loss": 0.3139,
+      "step": 130
+    },
+    {
+      "epoch": 4.52,
+      "learning_rate": 0.0008793790613463954,
+      "loss": 0.1033,
+      "step": 140
+    },
+    {
+      "epoch": 4.84,
+      "learning_rate": 0.00086239639361456,
+      "loss": 0.1794,
+      "step": 150
+    },
+    {
+      "epoch": 5.16,
+      "learning_rate": 0.0008444834595378434,
+      "loss": 0.1794,
+      "step": 160
+    },
+    {
+      "epoch": 5.48,
+      "learning_rate": 0.0008256862413611113,
+      "loss": 0.1136,
+      "step": 170
+    },
+    {
+      "epoch": 5.81,
+      "learning_rate": 0.0008060529912738315,
+      "loss": 0.1584,
+      "step": 180
+    },
+    {
+      "epoch": 6.13,
+      "learning_rate": 0.0007856341075473961,
+      "loss": 0.1127,
+      "step": 190
+    },
+    {
+      "epoch": 6.45,
+      "learning_rate": 0.0007644820051634812,
+      "loss": 0.1422,
+      "step": 200
+    },
+    {
+      "epoch": 6.77,
+      "learning_rate": 0.0007426509812655407,
+      "loss": 0.1001,
+      "step": 210
+    },
+    {
+      "epoch": 7.1,
+      "learning_rate": 0.0007201970757788173,
+      "loss": 0.0521,
+      "step": 220
+    },
+    {
+      "epoch": 7.42,
+      "learning_rate": 0.0006971779275566593,
+      "loss": 0.0499,
+      "step": 230
+    },
+    {
+      "epoch": 7.74,
+      "learning_rate": 0.0006736526264224101,
+      "loss": 0.1083,
+      "step": 240
+    },
+    {
+      "epoch": 8.06,
+      "learning_rate": 0.0006496815614866791,
+      "loss": 0.0762,
+      "step": 250
+    },
+    {
+      "epoch": 8.39,
+      "learning_rate": 0.0006253262661293602,
+      "loss": 0.0363,
+      "step": 260
+    },
+    {
+      "epoch": 8.71,
+      "learning_rate": 0.0006006492600443301,
+      "loss": 0.0455,
+      "step": 270
+    },
+    {
+      "epoch": 9.03,
+      "learning_rate": 0.0005757138887522884,
+      "loss": 0.0614,
+      "step": 280
+    },
+    {
+      "epoch": 9.35,
+      "learning_rate": 0.0005505841609937161,
+      "loss": 0.0279,
+      "step": 290
+    },
+    {
+      "epoch": 9.68,
+      "learning_rate": 0.0005253245844193564,
+      "loss": 0.0383,
+      "step": 300
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0005,
+      "loss": 0.0219,
+      "step": 310
+    },
+    {
+      "epoch": 10.32,
+      "learning_rate": 0.0004746754155806437,
+      "loss": 0.0069,
+      "step": 320
+    },
+    {
+      "epoch": 10.65,
+      "learning_rate": 0.000449415839006284,
+      "loss": 0.0399,
+      "step": 330
+    },
+    {
+      "epoch": 10.97,
+      "learning_rate": 0.00042428611124771184,
+      "loss": 0.0208,
+      "step": 340
+    },
+    {
+      "epoch": 11.29,
+      "learning_rate": 0.0003993507399556699,
+      "loss": 0.0109,
+      "step": 350
+    },
+    {
+      "epoch": 11.61,
+      "learning_rate": 0.00037467373387063967,
+      "loss": 0.0249,
+      "step": 360
+    },
+    {
+      "epoch": 11.94,
+      "learning_rate": 0.000350318438513321,
+      "loss": 0.0041,
+      "step": 370
+    },
+    {
+      "epoch": 12.26,
+      "learning_rate": 0.0003263473735775899,
+      "loss": 0.009,
+      "step": 380
+    },
+    {
+      "epoch": 12.58,
+      "learning_rate": 0.00030282207244334083,
+      "loss": 0.007,
+      "step": 390
+    },
+    {
+      "epoch": 12.9,
+      "learning_rate": 0.0002798029242211828,
+      "loss": 0.0089,
+      "step": 400
+    },
+    {
+      "epoch": 13.23,
+      "learning_rate": 0.0002573490187344596,
+      "loss": 0.0103,
+      "step": 410
+    },
+    {
+      "epoch": 13.55,
+      "learning_rate": 0.0002355179948365189,
+      "loss": 0.0054,
+      "step": 420
+    },
+    {
+      "epoch": 13.87,
+      "learning_rate": 0.00021436589245260373,
+      "loss": 0.0037,
+      "step": 430
+    },
+    {
+      "epoch": 14.19,
+      "learning_rate": 0.00019394700872616856,
+      "loss": 0.0047,
+      "step": 440
+    },
+    {
+      "epoch": 14.52,
+      "learning_rate": 0.00017431375863888898,
+      "loss": 0.0061,
+      "step": 450
+    },
+    {
+      "epoch": 14.84,
+      "learning_rate": 0.00015551654046215668,
+      "loss": 0.0043,
+      "step": 460
+    },
+    {
+      "epoch": 15.16,
+      "learning_rate": 0.00013760360638544013,
+      "loss": 0.0058,
+      "step": 470
+    },
+    {
+      "epoch": 15.48,
+      "learning_rate": 0.00012062093865360457,
+      "loss": 0.0029,
+      "step": 480
+    },
+    {
+      "epoch": 15.81,
+      "learning_rate": 0.00010461213153115079,
+      "loss": 0.0037,
+      "step": 490
+    },
+    {
+      "epoch": 16.13,
+      "learning_rate": 8.961827939636197e-05,
+      "loss": 0.004,
+      "step": 500
+    },
+    {
+      "epoch": 16.45,
+      "learning_rate": 7.567787125262449e-05,
+      "loss": 0.0048,
+      "step": 510
+    },
+    {
+      "epoch": 16.77,
+      "learning_rate": 6.282669192770896e-05,
+      "loss": 0.0036,
+      "step": 520
+    },
+    {
+      "epoch": 17.1,
+      "learning_rate": 5.109773021462921e-05,
+      "loss": 0.0018,
+      "step": 530
+    },
+    {
+      "epoch": 17.42,
+      "learning_rate": 4.05210941898847e-05,
+      "loss": 0.0039,
+      "step": 540
+    },
+    {
+      "epoch": 17.74,
+      "learning_rate": 3.112393392645985e-05,
+      "loss": 0.004,
+      "step": 550
+    },
+    {
+      "epoch": 18.06,
+      "learning_rate": 2.2930371799975592e-05,
+      "loss": 0.0038,
+      "step": 560
+    },
+    {
+      "epoch": 18.39,
+      "learning_rate": 1.596144056689791e-05,
+      "loss": 0.0027,
+      "step": 570
+    },
+    {
+      "epoch": 18.71,
+      "learning_rate": 1.0235029373752758e-05,
+      "loss": 0.0043,
+      "step": 580
+    },
+    {
+      "epoch": 19.03,
+      "learning_rate": 5.76583783594431e-06,
+      "loss": 0.0034,
+      "step": 590
+    },
+    {
+      "epoch": 19.35,
+      "learning_rate": 2.5653383040524227e-06,
+      "loss": 0.0034,
+      "step": 600
+    },
+    {
+      "epoch": 19.68,
+      "learning_rate": 6.417464144736207e-07,
+      "loss": 0.0037,
+      "step": 610
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 0.0,
+      "loss": 0.0038,
+      "step": 620
+    },
+    {
+      "epoch": 20.0,
+      "step": 620,
+      "total_flos": 7.220647174835405e+16,
+      "train_loss": 0.09885127827404969,
+      "train_runtime": 1180.114,
+      "train_samples_per_second": 2.085,
+      "train_steps_per_second": 0.525
+    }
+  ],
+  "max_steps": 620,
+  "num_train_epochs": 20,
+  "total_flos": 7.220647174835405e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15f05a4433b99018d2be90230f60ffc93c2f5d7a1922a6be224ea552f1db2848
+size 3327