Upload 10 files
Browse files- adapter_config.json +28 -0
- adapter_model.safetensors +3 -0
- all_results.json +11 -0
- eval_results.json +7 -0
- train_results.json +7 -0
- trainer_log.jsonl +51 -0
- trainer_state.json +1447 -0
- training_args.bin +3 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "baichuan-inc/Baichuan2-7B-Chat",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 512,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 256,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"W_pack"
|
| 24 |
+
],
|
| 25 |
+
"task_type": "CAUSAL_LM",
|
| 26 |
+
"use_dora": false,
|
| 27 |
+
"use_rslora": false
|
| 28 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f5c1e1ee625ef1ed02b92e803cb8b3e8870ca71fbaed94ce5aaf1d5786d3ca0
|
| 3 |
+
size 536879768
|
all_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.24519601464271545,
|
| 4 |
+
"eval_runtime": 16.144,
|
| 5 |
+
"eval_samples_per_second": 0.681,
|
| 6 |
+
"eval_steps_per_second": 0.681,
|
| 7 |
+
"train_loss": 0.32009275511924523,
|
| 8 |
+
"train_runtime": 49821.5539,
|
| 9 |
+
"train_samples_per_second": 6.399,
|
| 10 |
+
"train_steps_per_second": 0.04
|
| 11 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.24519601464271545,
|
| 4 |
+
"eval_runtime": 16.144,
|
| 5 |
+
"eval_samples_per_second": 0.681,
|
| 6 |
+
"eval_steps_per_second": 0.681
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.32009275511924523,
|
| 4 |
+
"train_runtime": 49821.5539,
|
| 5 |
+
"train_samples_per_second": 6.399,
|
| 6 |
+
"train_steps_per_second": 0.04
|
| 7 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 10, "total_steps": 1992, "loss": 0.6539, "learning_rate": 9.999384369486675e-05, "epoch": 0.02, "percentage": 0.5, "elapsed_time": "0:04:10", "remaining_time": "13:45:52"}
|
| 2 |
+
{"current_steps": 20, "total_steps": 1992, "loss": 0.4242, "learning_rate": 9.997525241303441e-05, "epoch": 0.03, "percentage": 1.0, "elapsed_time": "0:08:23", "remaining_time": "13:47:34"}
|
| 3 |
+
{"current_steps": 30, "total_steps": 1992, "loss": 0.4085, "learning_rate": 9.994423062331178e-05, "epoch": 0.05, "percentage": 1.51, "elapsed_time": "0:12:34", "remaining_time": "13:41:53"}
|
| 4 |
+
{"current_steps": 40, "total_steps": 1992, "loss": 0.3843, "learning_rate": 9.990078604185e-05, "epoch": 0.06, "percentage": 2.01, "elapsed_time": "0:16:47", "remaining_time": "13:39:45"}
|
| 5 |
+
{"current_steps": 50, "total_steps": 1992, "loss": 0.3814, "learning_rate": 9.984492947476183e-05, "epoch": 0.08, "percentage": 2.51, "elapsed_time": "0:20:59", "remaining_time": "13:35:01"}
|
| 6 |
+
{"current_steps": 60, "total_steps": 1992, "loss": 0.3806, "learning_rate": 9.977667481543383e-05, "epoch": 0.09, "percentage": 3.01, "elapsed_time": "0:25:12", "remaining_time": "13:31:46"}
|
| 7 |
+
{"current_steps": 70, "total_steps": 1992, "loss": 0.3823, "learning_rate": 9.969603904107045e-05, "epoch": 0.11, "percentage": 3.51, "elapsed_time": "0:29:23", "remaining_time": "13:26:56"}
|
| 8 |
+
{"current_steps": 80, "total_steps": 1992, "loss": 0.3717, "learning_rate": 9.960304220847147e-05, "epoch": 0.12, "percentage": 4.02, "elapsed_time": "0:33:44", "remaining_time": "13:26:31"}
|
| 9 |
+
{"current_steps": 90, "total_steps": 1992, "loss": 0.3761, "learning_rate": 9.949770744904306e-05, "epoch": 0.14, "percentage": 4.52, "elapsed_time": "0:37:47", "remaining_time": "13:18:44"}
|
| 10 |
+
{"current_steps": 100, "total_steps": 1992, "loss": 0.3766, "learning_rate": 9.938006096304422e-05, "epoch": 0.15, "percentage": 5.02, "elapsed_time": "0:42:02", "remaining_time": "13:15:27"}
|
| 11 |
+
{"current_steps": 110, "total_steps": 1992, "loss": 0.3815, "learning_rate": 9.925013201306999e-05, "epoch": 0.17, "percentage": 5.52, "elapsed_time": "0:46:16", "remaining_time": "13:11:50"}
|
| 12 |
+
{"current_steps": 120, "total_steps": 1992, "loss": 0.3793, "learning_rate": 9.910795291677279e-05, "epoch": 0.18, "percentage": 6.02, "elapsed_time": "0:50:31", "remaining_time": "13:08:16"}
|
| 13 |
+
{"current_steps": 130, "total_steps": 1992, "loss": 0.3746, "learning_rate": 9.8953559038824e-05, "epoch": 0.2, "percentage": 6.53, "elapsed_time": "0:54:25", "remaining_time": "12:59:27"}
|
| 14 |
+
{"current_steps": 140, "total_steps": 1992, "loss": 0.3627, "learning_rate": 9.878698878211756e-05, "epoch": 0.21, "percentage": 7.03, "elapsed_time": "0:58:35", "remaining_time": "12:55:02"}
|
| 15 |
+
{"current_steps": 150, "total_steps": 1992, "loss": 0.3585, "learning_rate": 9.86082835782179e-05, "epoch": 0.23, "percentage": 7.53, "elapsed_time": "1:02:30", "remaining_time": "12:47:40"}
|
| 16 |
+
{"current_steps": 160, "total_steps": 1992, "loss": 0.3648, "learning_rate": 9.841748787705453e-05, "epoch": 0.24, "percentage": 8.03, "elapsed_time": "1:06:36", "remaining_time": "12:42:39"}
|
| 17 |
+
{"current_steps": 170, "total_steps": 1992, "loss": 0.3714, "learning_rate": 9.821464913586586e-05, "epoch": 0.26, "percentage": 8.53, "elapsed_time": "1:10:43", "remaining_time": "12:38:04"}
|
| 18 |
+
{"current_steps": 180, "total_steps": 1992, "loss": 0.3691, "learning_rate": 9.799981780739504e-05, "epoch": 0.27, "percentage": 9.04, "elapsed_time": "1:14:50", "remaining_time": "12:33:22"}
|
| 19 |
+
{"current_steps": 190, "total_steps": 1992, "loss": 0.3621, "learning_rate": 9.777304732734063e-05, "epoch": 0.29, "percentage": 9.54, "elapsed_time": "1:19:07", "remaining_time": "12:30:27"}
|
| 20 |
+
{"current_steps": 200, "total_steps": 1992, "loss": 0.3627, "learning_rate": 9.753439410106537e-05, "epoch": 0.3, "percentage": 10.04, "elapsed_time": "1:23:15", "remaining_time": "12:25:57"}
|
| 21 |
+
{"current_steps": 210, "total_steps": 1992, "loss": 0.358, "learning_rate": 9.728391748956637e-05, "epoch": 0.32, "percentage": 10.54, "elapsed_time": "1:27:26", "remaining_time": "12:22:00"}
|
| 22 |
+
{"current_steps": 220, "total_steps": 1992, "loss": 0.3587, "learning_rate": 9.702167979470994e-05, "epoch": 0.33, "percentage": 11.04, "elapsed_time": "1:31:18", "remaining_time": "12:15:28"}
|
| 23 |
+
{"current_steps": 230, "total_steps": 1992, "loss": 0.3593, "learning_rate": 9.67477462437351e-05, "epoch": 0.35, "percentage": 11.55, "elapsed_time": "1:35:42", "remaining_time": "12:13:11"}
|
| 24 |
+
{"current_steps": 240, "total_steps": 1992, "loss": 0.3619, "learning_rate": 9.646218497302945e-05, "epoch": 0.36, "percentage": 12.05, "elapsed_time": "1:39:45", "remaining_time": "12:08:12"}
|
| 25 |
+
{"current_steps": 250, "total_steps": 1992, "loss": 0.3592, "learning_rate": 9.616506701118124e-05, "epoch": 0.38, "percentage": 12.55, "elapsed_time": "1:43:50", "remaining_time": "12:03:31"}
|
| 26 |
+
{"current_steps": 260, "total_steps": 1992, "loss": 0.3572, "learning_rate": 9.585646626131237e-05, "epoch": 0.39, "percentage": 13.05, "elapsed_time": "1:48:01", "remaining_time": "11:59:35"}
|
| 27 |
+
{"current_steps": 270, "total_steps": 1992, "loss": 0.3584, "learning_rate": 9.553645948269607e-05, "epoch": 0.41, "percentage": 13.55, "elapsed_time": "1:52:11", "remaining_time": "11:55:31"}
|
| 28 |
+
{"current_steps": 280, "total_steps": 1992, "loss": 0.3569, "learning_rate": 9.520512627166445e-05, "epoch": 0.42, "percentage": 14.06, "elapsed_time": "1:56:19", "remaining_time": "11:51:13"}
|
| 29 |
+
{"current_steps": 290, "total_steps": 1992, "loss": 0.353, "learning_rate": 9.48625490418101e-05, "epoch": 0.44, "percentage": 14.56, "elapsed_time": "2:00:34", "remaining_time": "11:47:38"}
|
| 30 |
+
{"current_steps": 300, "total_steps": 1992, "loss": 0.3492, "learning_rate": 9.450881300348724e-05, "epoch": 0.45, "percentage": 15.06, "elapsed_time": "2:04:44", "remaining_time": "11:43:32"}
|
| 31 |
+
{"current_steps": 310, "total_steps": 1992, "loss": 0.3618, "learning_rate": 9.414400614261693e-05, "epoch": 0.47, "percentage": 15.56, "elapsed_time": "2:08:54", "remaining_time": "11:39:23"}
|
| 32 |
+
{"current_steps": 320, "total_steps": 1992, "loss": 0.3668, "learning_rate": 9.376821919880219e-05, "epoch": 0.48, "percentage": 16.06, "elapsed_time": "2:12:56", "remaining_time": "11:34:36"}
|
| 33 |
+
{"current_steps": 330, "total_steps": 1992, "loss": 0.3445, "learning_rate": 9.338154564275788e-05, "epoch": 0.5, "percentage": 16.57, "elapsed_time": "2:17:08", "remaining_time": "11:30:42"}
|
| 34 |
+
{"current_steps": 340, "total_steps": 1992, "loss": 0.3459, "learning_rate": 9.298408165306157e-05, "epoch": 0.51, "percentage": 17.07, "elapsed_time": "2:21:16", "remaining_time": "11:26:24"}
|
| 35 |
+
{"current_steps": 350, "total_steps": 1992, "loss": 0.3532, "learning_rate": 9.257592609223059e-05, "epoch": 0.53, "percentage": 17.57, "elapsed_time": "2:25:26", "remaining_time": "11:22:18"}
|
| 36 |
+
{"current_steps": 360, "total_steps": 1992, "loss": 0.3542, "learning_rate": 9.21571804821318e-05, "epoch": 0.54, "percentage": 18.07, "elapsed_time": "2:29:41", "remaining_time": "11:18:33"}
|
| 37 |
+
{"current_steps": 370, "total_steps": 1992, "loss": 0.3424, "learning_rate": 9.172794897872957e-05, "epoch": 0.56, "percentage": 18.57, "elapsed_time": "2:33:52", "remaining_time": "11:14:33"}
|
| 38 |
+
{"current_steps": 380, "total_steps": 1992, "loss": 0.35, "learning_rate": 9.128833834617876e-05, "epoch": 0.57, "percentage": 19.08, "elapsed_time": "2:38:04", "remaining_time": "11:10:35"}
|
| 39 |
+
{"current_steps": 390, "total_steps": 1992, "loss": 0.3461, "learning_rate": 9.083845793026905e-05, "epoch": 0.59, "percentage": 19.58, "elapsed_time": "2:42:14", "remaining_time": "11:06:25"}
|
| 40 |
+
{"current_steps": 400, "total_steps": 1992, "loss": 0.3367, "learning_rate": 9.037841963122682e-05, "epoch": 0.6, "percentage": 20.08, "elapsed_time": "2:46:19", "remaining_time": "11:01:57"}
|
| 41 |
+
{"current_steps": 410, "total_steps": 1992, "loss": 0.3504, "learning_rate": 8.990833787588194e-05, "epoch": 0.62, "percentage": 20.58, "elapsed_time": "2:50:42", "remaining_time": "10:58:42"}
|
| 42 |
+
{"current_steps": 420, "total_steps": 1992, "loss": 0.3496, "learning_rate": 8.942832958920602e-05, "epoch": 0.63, "percentage": 21.08, "elapsed_time": "2:55:02", "remaining_time": "10:55:11"}
|
| 43 |
+
{"current_steps": 430, "total_steps": 1992, "loss": 0.3513, "learning_rate": 8.893851416522925e-05, "epoch": 0.65, "percentage": 21.59, "elapsed_time": "2:59:27", "remaining_time": "10:51:54"}
|
| 44 |
+
{"current_steps": 440, "total_steps": 1992, "loss": 0.3409, "learning_rate": 8.843901343734309e-05, "epoch": 0.66, "percentage": 22.09, "elapsed_time": "3:03:43", "remaining_time": "10:48:01"}
|
| 45 |
+
{"current_steps": 450, "total_steps": 1992, "loss": 0.3446, "learning_rate": 8.792995164799637e-05, "epoch": 0.68, "percentage": 22.59, "elapsed_time": "3:08:05", "remaining_time": "10:44:30"}
|
| 46 |
+
{"current_steps": 460, "total_steps": 1992, "loss": 0.3442, "learning_rate": 8.741145541779199e-05, "epoch": 0.69, "percentage": 23.09, "elapsed_time": "3:12:05", "remaining_time": "10:39:44"}
|
| 47 |
+
{"current_steps": 470, "total_steps": 1992, "loss": 0.3444, "learning_rate": 8.688365371399208e-05, "epoch": 0.71, "percentage": 23.59, "elapsed_time": "3:16:16", "remaining_time": "10:35:36"}
|
| 48 |
+
{"current_steps": 480, "total_steps": 1992, "loss": 0.3402, "learning_rate": 8.63466778184397e-05, "epoch": 0.72, "percentage": 24.1, "elapsed_time": "3:20:26", "remaining_time": "10:31:23"}
|
| 49 |
+
{"current_steps": 490, "total_steps": 1992, "loss": 0.3424, "learning_rate": 8.580066129490462e-05, "epoch": 0.74, "percentage": 24.6, "elapsed_time": "3:24:38", "remaining_time": "10:27:18"}
|
| 50 |
+
{"current_steps": 500, "total_steps": 1992, "loss": 0.358, "learning_rate": 8.524573995586153e-05, "epoch": 0.75, "percentage": 25.1, "elapsed_time": "3:29:03", "remaining_time": "10:23:48"}
|
| 51 |
+
{"current_steps": 500, "total_steps": 1992, "eval_loss": 0.26840201020240784, "epoch": 0.75, "percentage": 25.1, "elapsed_time": "3:29:24", "remaining_time": "10:24:51"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1447 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.998870907038013,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1992,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02,
|
| 13 |
+
"grad_norm": 0.2066432386636734,
|
| 14 |
+
"learning_rate": 9.999384369486675e-05,
|
| 15 |
+
"loss": 0.6539,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03,
|
| 20 |
+
"grad_norm": 0.1350802630186081,
|
| 21 |
+
"learning_rate": 9.997525241303441e-05,
|
| 22 |
+
"loss": 0.4242,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.05,
|
| 27 |
+
"grad_norm": 0.12290512770414352,
|
| 28 |
+
"learning_rate": 9.994423062331178e-05,
|
| 29 |
+
"loss": 0.4085,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.06,
|
| 34 |
+
"grad_norm": 0.10319065302610397,
|
| 35 |
+
"learning_rate": 9.990078604185e-05,
|
| 36 |
+
"loss": 0.3843,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.08,
|
| 41 |
+
"grad_norm": 0.1067107692360878,
|
| 42 |
+
"learning_rate": 9.984492947476183e-05,
|
| 43 |
+
"loss": 0.3814,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.09,
|
| 48 |
+
"grad_norm": 0.10464764386415482,
|
| 49 |
+
"learning_rate": 9.977667481543383e-05,
|
| 50 |
+
"loss": 0.3806,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.11,
|
| 55 |
+
"grad_norm": 0.10096515715122223,
|
| 56 |
+
"learning_rate": 9.969603904107045e-05,
|
| 57 |
+
"loss": 0.3823,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.12,
|
| 62 |
+
"grad_norm": 0.10181506723165512,
|
| 63 |
+
"learning_rate": 9.960304220847147e-05,
|
| 64 |
+
"loss": 0.3717,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.14,
|
| 69 |
+
"grad_norm": 0.10328900068998337,
|
| 70 |
+
"learning_rate": 9.949770744904306e-05,
|
| 71 |
+
"loss": 0.3761,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.15,
|
| 76 |
+
"grad_norm": 0.10094640403985977,
|
| 77 |
+
"learning_rate": 9.938006096304422e-05,
|
| 78 |
+
"loss": 0.3766,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.17,
|
| 83 |
+
"grad_norm": 0.10436520725488663,
|
| 84 |
+
"learning_rate": 9.925013201306999e-05,
|
| 85 |
+
"loss": 0.3815,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.18,
|
| 90 |
+
"grad_norm": 0.09791135042905807,
|
| 91 |
+
"learning_rate": 9.910795291677279e-05,
|
| 92 |
+
"loss": 0.3793,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.2,
|
| 97 |
+
"grad_norm": 0.10530658811330795,
|
| 98 |
+
"learning_rate": 9.8953559038824e-05,
|
| 99 |
+
"loss": 0.3746,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.21,
|
| 104 |
+
"grad_norm": 0.10106656700372696,
|
| 105 |
+
"learning_rate": 9.878698878211756e-05,
|
| 106 |
+
"loss": 0.3627,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.23,
|
| 111 |
+
"grad_norm": 0.10589198768138885,
|
| 112 |
+
"learning_rate": 9.86082835782179e-05,
|
| 113 |
+
"loss": 0.3585,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.24,
|
| 118 |
+
"grad_norm": 0.09950920939445496,
|
| 119 |
+
"learning_rate": 9.841748787705453e-05,
|
| 120 |
+
"loss": 0.3648,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.26,
|
| 125 |
+
"grad_norm": 0.09534649550914764,
|
| 126 |
+
"learning_rate": 9.821464913586586e-05,
|
| 127 |
+
"loss": 0.3714,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.27,
|
| 132 |
+
"grad_norm": 0.1069357767701149,
|
| 133 |
+
"learning_rate": 9.799981780739504e-05,
|
| 134 |
+
"loss": 0.3691,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.29,
|
| 139 |
+
"grad_norm": 0.0956304594874382,
|
| 140 |
+
"learning_rate": 9.777304732734063e-05,
|
| 141 |
+
"loss": 0.3621,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.3,
|
| 146 |
+
"grad_norm": 0.1080741360783577,
|
| 147 |
+
"learning_rate": 9.753439410106537e-05,
|
| 148 |
+
"loss": 0.3627,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.32,
|
| 153 |
+
"grad_norm": 0.11919151246547699,
|
| 154 |
+
"learning_rate": 9.728391748956637e-05,
|
| 155 |
+
"loss": 0.358,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.33,
|
| 160 |
+
"grad_norm": 0.09667570888996124,
|
| 161 |
+
"learning_rate": 9.702167979470994e-05,
|
| 162 |
+
"loss": 0.3587,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.35,
|
| 167 |
+
"grad_norm": 0.09914813190698624,
|
| 168 |
+
"learning_rate": 9.67477462437351e-05,
|
| 169 |
+
"loss": 0.3593,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.36,
|
| 174 |
+
"grad_norm": 0.09963402152061462,
|
| 175 |
+
"learning_rate": 9.646218497302945e-05,
|
| 176 |
+
"loss": 0.3619,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.38,
|
| 181 |
+
"grad_norm": 0.0956585481762886,
|
| 182 |
+
"learning_rate": 9.616506701118124e-05,
|
| 183 |
+
"loss": 0.3592,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.39,
|
| 188 |
+
"grad_norm": 0.08918160200119019,
|
| 189 |
+
"learning_rate": 9.585646626131237e-05,
|
| 190 |
+
"loss": 0.3572,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.41,
|
| 195 |
+
"grad_norm": 0.10680545121431351,
|
| 196 |
+
"learning_rate": 9.553645948269607e-05,
|
| 197 |
+
"loss": 0.3584,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.42,
|
| 202 |
+
"grad_norm": 0.09338073432445526,
|
| 203 |
+
"learning_rate": 9.520512627166445e-05,
|
| 204 |
+
"loss": 0.3569,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.44,
|
| 209 |
+
"grad_norm": 0.09849222749471664,
|
| 210 |
+
"learning_rate": 9.48625490418101e-05,
|
| 211 |
+
"loss": 0.353,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.45,
|
| 216 |
+
"grad_norm": 0.09319322556257248,
|
| 217 |
+
"learning_rate": 9.450881300348724e-05,
|
| 218 |
+
"loss": 0.3492,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.47,
|
| 223 |
+
"grad_norm": 0.09313003718852997,
|
| 224 |
+
"learning_rate": 9.414400614261693e-05,
|
| 225 |
+
"loss": 0.3618,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.48,
|
| 230 |
+
"grad_norm": 0.09641731530427933,
|
| 231 |
+
"learning_rate": 9.376821919880219e-05,
|
| 232 |
+
"loss": 0.3668,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.5,
|
| 237 |
+
"grad_norm": 0.10052476078271866,
|
| 238 |
+
"learning_rate": 9.338154564275788e-05,
|
| 239 |
+
"loss": 0.3445,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.51,
|
| 244 |
+
"grad_norm": 0.09882521629333496,
|
| 245 |
+
"learning_rate": 9.298408165306157e-05,
|
| 246 |
+
"loss": 0.3459,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.53,
|
| 251 |
+
"grad_norm": 0.0998958945274353,
|
| 252 |
+
"learning_rate": 9.257592609223059e-05,
|
| 253 |
+
"loss": 0.3532,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.54,
|
| 258 |
+
"grad_norm": 0.0996759906411171,
|
| 259 |
+
"learning_rate": 9.21571804821318e-05,
|
| 260 |
+
"loss": 0.3542,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.56,
|
| 265 |
+
"grad_norm": 0.09207039326429367,
|
| 266 |
+
"learning_rate": 9.172794897872957e-05,
|
| 267 |
+
"loss": 0.3424,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.57,
|
| 272 |
+
"grad_norm": 0.09934650361537933,
|
| 273 |
+
"learning_rate": 9.128833834617876e-05,
|
| 274 |
+
"loss": 0.35,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.59,
|
| 279 |
+
"grad_norm": 0.09678385406732559,
|
| 280 |
+
"learning_rate": 9.083845793026905e-05,
|
| 281 |
+
"loss": 0.3461,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.6,
|
| 286 |
+
"grad_norm": 0.09645042568445206,
|
| 287 |
+
"learning_rate": 9.037841963122682e-05,
|
| 288 |
+
"loss": 0.3367,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.62,
|
| 293 |
+
"grad_norm": 0.09238140285015106,
|
| 294 |
+
"learning_rate": 8.990833787588194e-05,
|
| 295 |
+
"loss": 0.3504,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.63,
|
| 300 |
+
"grad_norm": 0.09661918878555298,
|
| 301 |
+
"learning_rate": 8.942832958920602e-05,
|
| 302 |
+
"loss": 0.3496,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.65,
|
| 307 |
+
"grad_norm": 0.09576547890901566,
|
| 308 |
+
"learning_rate": 8.893851416522925e-05,
|
| 309 |
+
"loss": 0.3513,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.66,
|
| 314 |
+
"grad_norm": 0.091176837682724,
|
| 315 |
+
"learning_rate": 8.843901343734309e-05,
|
| 316 |
+
"loss": 0.3409,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.68,
|
| 321 |
+
"grad_norm": 0.09654372185468674,
|
| 322 |
+
"learning_rate": 8.792995164799637e-05,
|
| 323 |
+
"loss": 0.3446,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.69,
|
| 328 |
+
"grad_norm": 0.08725057542324066,
|
| 329 |
+
"learning_rate": 8.741145541779199e-05,
|
| 330 |
+
"loss": 0.3442,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.71,
|
| 335 |
+
"grad_norm": 0.09062401205301285,
|
| 336 |
+
"learning_rate": 8.688365371399208e-05,
|
| 337 |
+
"loss": 0.3444,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.72,
|
| 342 |
+
"grad_norm": 0.09887181222438812,
|
| 343 |
+
"learning_rate": 8.63466778184397e-05,
|
| 344 |
+
"loss": 0.3402,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.74,
|
| 349 |
+
"grad_norm": 0.09595289826393127,
|
| 350 |
+
"learning_rate": 8.580066129490462e-05,
|
| 351 |
+
"loss": 0.3424,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.75,
|
| 356 |
+
"grad_norm": 0.0977388396859169,
|
| 357 |
+
"learning_rate": 8.524573995586153e-05,
|
| 358 |
+
"loss": 0.358,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.75,
|
| 363 |
+
"eval_loss": 0.26840201020240784,
|
| 364 |
+
"eval_runtime": 20.7882,
|
| 365 |
+
"eval_samples_per_second": 0.529,
|
| 366 |
+
"eval_steps_per_second": 0.529,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.77,
|
| 371 |
+
"grad_norm": 0.08854895085096359,
|
| 372 |
+
"learning_rate": 8.468205182870901e-05,
|
| 373 |
+
"loss": 0.3328,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.78,
|
| 378 |
+
"grad_norm": 0.09385243058204651,
|
| 379 |
+
"learning_rate": 8.410973712143747e-05,
|
| 380 |
+
"loss": 0.3441,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.8,
|
| 385 |
+
"grad_norm": 0.09778619557619095,
|
| 386 |
+
"learning_rate": 8.352893818775484e-05,
|
| 387 |
+
"loss": 0.3451,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.81,
|
| 392 |
+
"grad_norm": 0.09615397453308105,
|
| 393 |
+
"learning_rate": 8.293979949167839e-05,
|
| 394 |
+
"loss": 0.3441,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.83,
|
| 399 |
+
"grad_norm": 0.10019069164991379,
|
| 400 |
+
"learning_rate": 8.234246757160174e-05,
|
| 401 |
+
"loss": 0.3309,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.84,
|
| 406 |
+
"grad_norm": 0.09099920839071274,
|
| 407 |
+
"learning_rate": 8.17370910038459e-05,
|
| 408 |
+
"loss": 0.3319,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.86,
|
| 413 |
+
"grad_norm": 0.10040932148694992,
|
| 414 |
+
"learning_rate": 8.112382036570344e-05,
|
| 415 |
+
"loss": 0.342,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.87,
|
| 420 |
+
"grad_norm": 0.09268151968717575,
|
| 421 |
+
"learning_rate": 8.050280819798481e-05,
|
| 422 |
+
"loss": 0.334,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.89,
|
| 427 |
+
"grad_norm": 0.09127725660800934,
|
| 428 |
+
"learning_rate": 7.987420896707645e-05,
|
| 429 |
+
"loss": 0.3476,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.9,
|
| 434 |
+
"grad_norm": 0.09117837995290756,
|
| 435 |
+
"learning_rate": 7.923817902651978e-05,
|
| 436 |
+
"loss": 0.3351,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.92,
|
| 441 |
+
"grad_norm": 0.09493087977170944,
|
| 442 |
+
"learning_rate": 7.859487657812095e-05,
|
| 443 |
+
"loss": 0.3408,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.93,
|
| 448 |
+
"grad_norm": 0.09857796877622604,
|
| 449 |
+
"learning_rate": 7.794446163260077e-05,
|
| 450 |
+
"loss": 0.3416,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.95,
|
| 455 |
+
"grad_norm": 0.09530830383300781,
|
| 456 |
+
"learning_rate": 7.728709596979471e-05,
|
| 457 |
+
"loss": 0.3403,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.96,
|
| 462 |
+
"grad_norm": 0.10255115479230881,
|
| 463 |
+
"learning_rate": 7.662294309841283e-05,
|
| 464 |
+
"loss": 0.3349,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.98,
|
| 469 |
+
"grad_norm": 0.09442761540412903,
|
| 470 |
+
"learning_rate": 7.595216821536981e-05,
|
| 471 |
+
"loss": 0.3469,
|
| 472 |
+
"step": 650
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.99,
|
| 476 |
+
"grad_norm": 0.09131593257188797,
|
| 477 |
+
"learning_rate": 7.527493816469492e-05,
|
| 478 |
+
"loss": 0.3232,
|
| 479 |
+
"step": 660
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.01,
|
| 483 |
+
"grad_norm": 0.10782450437545776,
|
| 484 |
+
"learning_rate": 7.459142139603236e-05,
|
| 485 |
+
"loss": 0.3275,
|
| 486 |
+
"step": 670
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.02,
|
| 490 |
+
"grad_norm": 0.10051246732473373,
|
| 491 |
+
"learning_rate": 7.390178792274227e-05,
|
| 492 |
+
"loss": 0.3168,
|
| 493 |
+
"step": 680
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.04,
|
| 497 |
+
"grad_norm": 0.09489897638559341,
|
| 498 |
+
"learning_rate": 7.32062092796127e-05,
|
| 499 |
+
"loss": 0.3205,
|
| 500 |
+
"step": 690
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.05,
|
| 504 |
+
"grad_norm": 0.10021229833364487,
|
| 505 |
+
"learning_rate": 7.250485848019326e-05,
|
| 506 |
+
"loss": 0.314,
|
| 507 |
+
"step": 700
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.07,
|
| 511 |
+
"grad_norm": 0.09837724268436432,
|
| 512 |
+
"learning_rate": 7.179790997376083e-05,
|
| 513 |
+
"loss": 0.3131,
|
| 514 |
+
"step": 710
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.08,
|
| 518 |
+
"grad_norm": 0.11071084439754486,
|
| 519 |
+
"learning_rate": 7.108553960192827e-05,
|
| 520 |
+
"loss": 0.3141,
|
| 521 |
+
"step": 720
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.1,
|
| 525 |
+
"grad_norm": 0.09489303082227707,
|
| 526 |
+
"learning_rate": 7.036792455490675e-05,
|
| 527 |
+
"loss": 0.3124,
|
| 528 |
+
"step": 730
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.11,
|
| 532 |
+
"grad_norm": 0.10039713978767395,
|
| 533 |
+
"learning_rate": 6.964524332743263e-05,
|
| 534 |
+
"loss": 0.3258,
|
| 535 |
+
"step": 740
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.13,
|
| 539 |
+
"grad_norm": 0.09435191005468369,
|
| 540 |
+
"learning_rate": 6.891767567436988e-05,
|
| 541 |
+
"loss": 0.318,
|
| 542 |
+
"step": 750
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.14,
|
| 546 |
+
"grad_norm": 0.10240574926137924,
|
| 547 |
+
"learning_rate": 6.818540256599913e-05,
|
| 548 |
+
"loss": 0.3286,
|
| 549 |
+
"step": 760
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.16,
|
| 553 |
+
"grad_norm": 0.10050353407859802,
|
| 554 |
+
"learning_rate": 6.744860614300426e-05,
|
| 555 |
+
"loss": 0.3096,
|
| 556 |
+
"step": 770
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.17,
|
| 560 |
+
"grad_norm": 0.09765986353158951,
|
| 561 |
+
"learning_rate": 6.670746967116793e-05,
|
| 562 |
+
"loss": 0.318,
|
| 563 |
+
"step": 780
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.19,
|
| 567 |
+
"grad_norm": 0.10131178051233292,
|
| 568 |
+
"learning_rate": 6.596217749578743e-05,
|
| 569 |
+
"loss": 0.3199,
|
| 570 |
+
"step": 790
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.2,
|
| 574 |
+
"grad_norm": 0.0985412448644638,
|
| 575 |
+
"learning_rate": 6.521291499582172e-05,
|
| 576 |
+
"loss": 0.3173,
|
| 577 |
+
"step": 800
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.22,
|
| 581 |
+
"grad_norm": 0.10045495629310608,
|
| 582 |
+
"learning_rate": 6.445986853778156e-05,
|
| 583 |
+
"loss": 0.304,
|
| 584 |
+
"step": 810
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.23,
|
| 588 |
+
"grad_norm": 0.10255653411149979,
|
| 589 |
+
"learning_rate": 6.370322542937403e-05,
|
| 590 |
+
"loss": 0.3215,
|
| 591 |
+
"step": 820
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.25,
|
| 595 |
+
"grad_norm": 0.10014262050390244,
|
| 596 |
+
"learning_rate": 6.294317387291276e-05,
|
| 597 |
+
"loss": 0.3185,
|
| 598 |
+
"step": 830
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.26,
|
| 602 |
+
"grad_norm": 0.10973095148801804,
|
| 603 |
+
"learning_rate": 6.217990291850581e-05,
|
| 604 |
+
"loss": 0.3128,
|
| 605 |
+
"step": 840
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.28,
|
| 609 |
+
"grad_norm": 0.1075139194726944,
|
| 610 |
+
"learning_rate": 6.141360241703264e-05,
|
| 611 |
+
"loss": 0.3117,
|
| 612 |
+
"step": 850
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.29,
|
| 616 |
+
"grad_norm": 0.10679470747709274,
|
| 617 |
+
"learning_rate": 6.0644462972921845e-05,
|
| 618 |
+
"loss": 0.314,
|
| 619 |
+
"step": 860
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.31,
|
| 623 |
+
"grad_norm": 0.10646017640829086,
|
| 624 |
+
"learning_rate": 5.98726758967415e-05,
|
| 625 |
+
"loss": 0.3166,
|
| 626 |
+
"step": 870
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.32,
|
| 630 |
+
"grad_norm": 0.10854795575141907,
|
| 631 |
+
"learning_rate": 5.909843315761385e-05,
|
| 632 |
+
"loss": 0.3104,
|
| 633 |
+
"step": 880
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.34,
|
| 637 |
+
"grad_norm": 0.09923075139522552,
|
| 638 |
+
"learning_rate": 5.832192733546621e-05,
|
| 639 |
+
"loss": 0.3085,
|
| 640 |
+
"step": 890
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.35,
|
| 644 |
+
"grad_norm": 0.10540423542261124,
|
| 645 |
+
"learning_rate": 5.7543351573129964e-05,
|
| 646 |
+
"loss": 0.3035,
|
| 647 |
+
"step": 900
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.37,
|
| 651 |
+
"grad_norm": 0.10513672232627869,
|
| 652 |
+
"learning_rate": 5.676289952829945e-05,
|
| 653 |
+
"loss": 0.3069,
|
| 654 |
+
"step": 910
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.39,
|
| 658 |
+
"grad_norm": 0.10602447390556335,
|
| 659 |
+
"learning_rate": 5.598076532536291e-05,
|
| 660 |
+
"loss": 0.3126,
|
| 661 |
+
"step": 920
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.4,
|
| 665 |
+
"grad_norm": 0.10258585214614868,
|
| 666 |
+
"learning_rate": 5.5197143507117234e-05,
|
| 667 |
+
"loss": 0.3148,
|
| 668 |
+
"step": 930
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.42,
|
| 672 |
+
"grad_norm": 0.10304014384746552,
|
| 673 |
+
"learning_rate": 5.441222898637877e-05,
|
| 674 |
+
"loss": 0.3138,
|
| 675 |
+
"step": 940
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.43,
|
| 679 |
+
"grad_norm": 0.10201530903577805,
|
| 680 |
+
"learning_rate": 5.362621699750196e-05,
|
| 681 |
+
"loss": 0.3104,
|
| 682 |
+
"step": 950
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.45,
|
| 686 |
+
"grad_norm": 0.10214639455080032,
|
| 687 |
+
"learning_rate": 5.28393030478181e-05,
|
| 688 |
+
"loss": 0.3081,
|
| 689 |
+
"step": 960
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.46,
|
| 693 |
+
"grad_norm": 0.09911152720451355,
|
| 694 |
+
"learning_rate": 5.2051682869006126e-05,
|
| 695 |
+
"loss": 0.3081,
|
| 696 |
+
"step": 970
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.48,
|
| 700 |
+
"grad_norm": 0.10031607747077942,
|
| 701 |
+
"learning_rate": 5.126355236840764e-05,
|
| 702 |
+
"loss": 0.3134,
|
| 703 |
+
"step": 980
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.49,
|
| 707 |
+
"grad_norm": 0.1077575534582138,
|
| 708 |
+
"learning_rate": 5.047510758029832e-05,
|
| 709 |
+
"loss": 0.3272,
|
| 710 |
+
"step": 990
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.51,
|
| 714 |
+
"grad_norm": 0.11312615871429443,
|
| 715 |
+
"learning_rate": 4.968654461712753e-05,
|
| 716 |
+
"loss": 0.3167,
|
| 717 |
+
"step": 1000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.51,
|
| 721 |
+
"eval_loss": 0.2502507269382477,
|
| 722 |
+
"eval_runtime": 14.5906,
|
| 723 |
+
"eval_samples_per_second": 0.754,
|
| 724 |
+
"eval_steps_per_second": 0.754,
|
| 725 |
+
"step": 1000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 1.52,
|
| 729 |
+
"grad_norm": 0.10545619577169418,
|
| 730 |
+
"learning_rate": 4.889805962073874e-05,
|
| 731 |
+
"loss": 0.3142,
|
| 732 |
+
"step": 1010
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 1.54,
|
| 736 |
+
"grad_norm": 0.11502473056316376,
|
| 737 |
+
"learning_rate": 4.8109848713582475e-05,
|
| 738 |
+
"loss": 0.3164,
|
| 739 |
+
"step": 1020
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 1.55,
|
| 743 |
+
"grad_norm": 0.11116404086351395,
|
| 744 |
+
"learning_rate": 4.7322107949934146e-05,
|
| 745 |
+
"loss": 0.3191,
|
| 746 |
+
"step": 1030
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 1.57,
|
| 750 |
+
"grad_norm": 0.11101904511451721,
|
| 751 |
+
"learning_rate": 4.653503326712886e-05,
|
| 752 |
+
"loss": 0.3223,
|
| 753 |
+
"step": 1040
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 1.58,
|
| 757 |
+
"grad_norm": 0.10275658220052719,
|
| 758 |
+
"learning_rate": 4.5748820436825204e-05,
|
| 759 |
+
"loss": 0.3127,
|
| 760 |
+
"step": 1050
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 1.6,
|
| 764 |
+
"grad_norm": 0.10536840558052063,
|
| 765 |
+
"learning_rate": 4.496366501631043e-05,
|
| 766 |
+
"loss": 0.3104,
|
| 767 |
+
"step": 1060
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 1.61,
|
| 771 |
+
"grad_norm": 0.11228681355714798,
|
| 772 |
+
"learning_rate": 4.417976229985876e-05,
|
| 773 |
+
"loss": 0.3181,
|
| 774 |
+
"step": 1070
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 1.63,
|
| 778 |
+
"grad_norm": 0.10409337282180786,
|
| 779 |
+
"learning_rate": 4.339730727015527e-05,
|
| 780 |
+
"loss": 0.3085,
|
| 781 |
+
"step": 1080
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 1.64,
|
| 785 |
+
"grad_norm": 0.11756953597068787,
|
| 786 |
+
"learning_rate": 4.261649454979714e-05,
|
| 787 |
+
"loss": 0.3105,
|
| 788 |
+
"step": 1090
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 1.66,
|
| 792 |
+
"grad_norm": 0.10340123623609543,
|
| 793 |
+
"learning_rate": 4.183751835288463e-05,
|
| 794 |
+
"loss": 0.3168,
|
| 795 |
+
"step": 1100
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 1.67,
|
| 799 |
+
"grad_norm": 0.11595764011144638,
|
| 800 |
+
"learning_rate": 4.10605724367135e-05,
|
| 801 |
+
"loss": 0.3172,
|
| 802 |
+
"step": 1110
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 1.69,
|
| 806 |
+
"grad_norm": 0.1063317060470581,
|
| 807 |
+
"learning_rate": 4.0285850053581105e-05,
|
| 808 |
+
"loss": 0.319,
|
| 809 |
+
"step": 1120
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 1.7,
|
| 813 |
+
"grad_norm": 0.10760544240474701,
|
| 814 |
+
"learning_rate": 3.9513543902718206e-05,
|
| 815 |
+
"loss": 0.3096,
|
| 816 |
+
"step": 1130
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 1.72,
|
| 820 |
+
"grad_norm": 0.11430344730615616,
|
| 821 |
+
"learning_rate": 3.87438460823582e-05,
|
| 822 |
+
"loss": 0.3119,
|
| 823 |
+
"step": 1140
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 1.73,
|
| 827 |
+
"grad_norm": 0.10582321882247925,
|
| 828 |
+
"learning_rate": 3.7976948041955904e-05,
|
| 829 |
+
"loss": 0.3179,
|
| 830 |
+
"step": 1150
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 1.75,
|
| 834 |
+
"grad_norm": 0.11124568432569504,
|
| 835 |
+
"learning_rate": 3.7213040534567725e-05,
|
| 836 |
+
"loss": 0.3099,
|
| 837 |
+
"step": 1160
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 1.76,
|
| 841 |
+
"grad_norm": 0.10317942500114441,
|
| 842 |
+
"learning_rate": 3.645231356940501e-05,
|
| 843 |
+
"loss": 0.3081,
|
| 844 |
+
"step": 1170
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 1.78,
|
| 848 |
+
"grad_norm": 0.10943736135959625,
|
| 849 |
+
"learning_rate": 3.569495636457244e-05,
|
| 850 |
+
"loss": 0.3103,
|
| 851 |
+
"step": 1180
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 1.79,
|
| 855 |
+
"grad_norm": 0.10795300453901291,
|
| 856 |
+
"learning_rate": 3.494115730000321e-05,
|
| 857 |
+
"loss": 0.3123,
|
| 858 |
+
"step": 1190
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 1.81,
|
| 862 |
+
"grad_norm": 0.1120479553937912,
|
| 863 |
+
"learning_rate": 3.4191103870602656e-05,
|
| 864 |
+
"loss": 0.3072,
|
| 865 |
+
"step": 1200
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 1.82,
|
| 869 |
+
"grad_norm": 0.10475881397724152,
|
| 870 |
+
"learning_rate": 3.344498263961201e-05,
|
| 871 |
+
"loss": 0.3107,
|
| 872 |
+
"step": 1210
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 1.84,
|
| 876 |
+
"grad_norm": 0.10638121515512466,
|
| 877 |
+
"learning_rate": 3.270297919220395e-05,
|
| 878 |
+
"loss": 0.3101,
|
| 879 |
+
"step": 1220
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 1.85,
|
| 883 |
+
"grad_norm": 0.10646604746580124,
|
| 884 |
+
"learning_rate": 3.1965278089321396e-05,
|
| 885 |
+
"loss": 0.3201,
|
| 886 |
+
"step": 1230
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 1.87,
|
| 890 |
+
"grad_norm": 0.10810079425573349,
|
| 891 |
+
"learning_rate": 3.123206282177105e-05,
|
| 892 |
+
"loss": 0.3129,
|
| 893 |
+
"step": 1240
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 1.88,
|
| 897 |
+
"grad_norm": 0.10837584733963013,
|
| 898 |
+
"learning_rate": 3.05035157645831e-05,
|
| 899 |
+
"loss": 0.3138,
|
| 900 |
+
"step": 1250
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 1.9,
|
| 904 |
+
"grad_norm": 0.11282283812761307,
|
| 905 |
+
"learning_rate": 2.9779818131648563e-05,
|
| 906 |
+
"loss": 0.3048,
|
| 907 |
+
"step": 1260
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 1.91,
|
| 911 |
+
"grad_norm": 0.10869032144546509,
|
| 912 |
+
"learning_rate": 2.9061149930645243e-05,
|
| 913 |
+
"loss": 0.3163,
|
| 914 |
+
"step": 1270
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 1.93,
|
| 918 |
+
"grad_norm": 0.11098149418830872,
|
| 919 |
+
"learning_rate": 2.8347689918263976e-05,
|
| 920 |
+
"loss": 0.3083,
|
| 921 |
+
"step": 1280
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 1.94,
|
| 925 |
+
"grad_norm": 0.10902676731348038,
|
| 926 |
+
"learning_rate": 2.763961555574575e-05,
|
| 927 |
+
"loss": 0.3008,
|
| 928 |
+
"step": 1290
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 1.96,
|
| 932 |
+
"grad_norm": 0.10680384933948517,
|
| 933 |
+
"learning_rate": 2.69371029647413e-05,
|
| 934 |
+
"loss": 0.3022,
|
| 935 |
+
"step": 1300
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 1.97,
|
| 939 |
+
"grad_norm": 0.10289633274078369,
|
| 940 |
+
"learning_rate": 2.624032688350374e-05,
|
| 941 |
+
"loss": 0.3045,
|
| 942 |
+
"step": 1310
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 1.99,
|
| 946 |
+
"grad_norm": 0.11078934371471405,
|
| 947 |
+
"learning_rate": 2.5549460623425354e-05,
|
| 948 |
+
"loss": 0.3065,
|
| 949 |
+
"step": 1320
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 2.0,
|
| 953 |
+
"grad_norm": 0.10170484334230423,
|
| 954 |
+
"learning_rate": 2.486467602592929e-05,
|
| 955 |
+
"loss": 0.2956,
|
| 956 |
+
"step": 1330
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 2.02,
|
| 960 |
+
"grad_norm": 0.1094578206539154,
|
| 961 |
+
"learning_rate": 2.4186143419726885e-05,
|
| 962 |
+
"loss": 0.2938,
|
| 963 |
+
"step": 1340
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 2.03,
|
| 967 |
+
"grad_norm": 0.10822325944900513,
|
| 968 |
+
"learning_rate": 2.351403157845125e-05,
|
| 969 |
+
"loss": 0.2863,
|
| 970 |
+
"step": 1350
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 2.05,
|
| 974 |
+
"grad_norm": 0.11142423003911972,
|
| 975 |
+
"learning_rate": 2.2848507678677633e-05,
|
| 976 |
+
"loss": 0.2846,
|
| 977 |
+
"step": 1360
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 2.06,
|
| 981 |
+
"grad_norm": 0.11497773230075836,
|
| 982 |
+
"learning_rate": 2.218973725834109e-05,
|
| 983 |
+
"loss": 0.2936,
|
| 984 |
+
"step": 1370
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 2.08,
|
| 988 |
+
"grad_norm": 0.10550795495510101,
|
| 989 |
+
"learning_rate": 2.153788417556164e-05,
|
| 990 |
+
"loss": 0.2888,
|
| 991 |
+
"step": 1380
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 2.09,
|
| 995 |
+
"grad_norm": 0.10813359171152115,
|
| 996 |
+
"learning_rate": 2.089311056788731e-05,
|
| 997 |
+
"loss": 0.2889,
|
| 998 |
+
"step": 1390
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 2.11,
|
| 1002 |
+
"grad_norm": 0.10650567710399628,
|
| 1003 |
+
"learning_rate": 2.0255576811965154e-05,
|
| 1004 |
+
"loss": 0.2925,
|
| 1005 |
+
"step": 1400
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 2.12,
|
| 1009 |
+
"grad_norm": 0.11273263394832611,
|
| 1010 |
+
"learning_rate": 1.9625441483650235e-05,
|
| 1011 |
+
"loss": 0.2856,
|
| 1012 |
+
"step": 1410
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 2.14,
|
| 1016 |
+
"grad_norm": 0.11437318474054337,
|
| 1017 |
+
"learning_rate": 1.9002861318562536e-05,
|
| 1018 |
+
"loss": 0.2845,
|
| 1019 |
+
"step": 1420
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 2.15,
|
| 1023 |
+
"grad_norm": 0.11178340762853622,
|
| 1024 |
+
"learning_rate": 1.8387991173101587e-05,
|
| 1025 |
+
"loss": 0.2904,
|
| 1026 |
+
"step": 1430
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 2.17,
|
| 1030 |
+
"grad_norm": 0.11630496382713318,
|
| 1031 |
+
"learning_rate": 1.7780983985928534e-05,
|
| 1032 |
+
"loss": 0.2851,
|
| 1033 |
+
"step": 1440
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 2.18,
|
| 1037 |
+
"grad_norm": 0.11532077938318253,
|
| 1038 |
+
"learning_rate": 1.7181990739925213e-05,
|
| 1039 |
+
"loss": 0.2797,
|
| 1040 |
+
"step": 1450
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 2.2,
|
| 1044 |
+
"grad_norm": 0.11311406642198563,
|
| 1045 |
+
"learning_rate": 1.6591160424639675e-05,
|
| 1046 |
+
"loss": 0.288,
|
| 1047 |
+
"step": 1460
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 2.21,
|
| 1051 |
+
"grad_norm": 0.11721379309892654,
|
| 1052 |
+
"learning_rate": 1.6008639999227527e-05,
|
| 1053 |
+
"loss": 0.2926,
|
| 1054 |
+
"step": 1470
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 2.23,
|
| 1058 |
+
"grad_norm": 0.11629457771778107,
|
| 1059 |
+
"learning_rate": 1.5434574355898306e-05,
|
| 1060 |
+
"loss": 0.2883,
|
| 1061 |
+
"step": 1480
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 2.24,
|
| 1065 |
+
"grad_norm": 0.11253120750188828,
|
| 1066 |
+
"learning_rate": 1.4869106283875972e-05,
|
| 1067 |
+
"loss": 0.2878,
|
| 1068 |
+
"step": 1490
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 2.26,
|
| 1072 |
+
"grad_norm": 0.1093481034040451,
|
| 1073 |
+
"learning_rate": 1.4312376433882457e-05,
|
| 1074 |
+
"loss": 0.2893,
|
| 1075 |
+
"step": 1500
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 2.26,
|
| 1079 |
+
"eval_loss": 0.24623431265354156,
|
| 1080 |
+
"eval_runtime": 15.3708,
|
| 1081 |
+
"eval_samples_per_second": 0.716,
|
| 1082 |
+
"eval_steps_per_second": 0.716,
|
| 1083 |
+
"step": 1500
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 2.27,
|
| 1087 |
+
"grad_norm": 0.114622101187706,
|
| 1088 |
+
"learning_rate": 1.376452328315318e-05,
|
| 1089 |
+
"loss": 0.2905,
|
| 1090 |
+
"step": 1510
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 2.29,
|
| 1094 |
+
"grad_norm": 0.11465822905302048,
|
| 1095 |
+
"learning_rate": 1.3225683100993113e-05,
|
| 1096 |
+
"loss": 0.2886,
|
| 1097 |
+
"step": 1520
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 2.3,
|
| 1101 |
+
"grad_norm": 0.11255551874637604,
|
| 1102 |
+
"learning_rate": 1.2695989914882128e-05,
|
| 1103 |
+
"loss": 0.2873,
|
| 1104 |
+
"step": 1530
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 2.32,
|
| 1108 |
+
"grad_norm": 0.11598910391330719,
|
| 1109 |
+
"learning_rate": 1.2175575477137824e-05,
|
| 1110 |
+
"loss": 0.2853,
|
| 1111 |
+
"step": 1540
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 2.33,
|
| 1115 |
+
"grad_norm": 0.11426587402820587,
|
| 1116 |
+
"learning_rate": 1.1664569232144445e-05,
|
| 1117 |
+
"loss": 0.2934,
|
| 1118 |
+
"step": 1550
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 2.35,
|
| 1122 |
+
"grad_norm": 0.11229728907346725,
|
| 1123 |
+
"learning_rate": 1.1163098284155665e-05,
|
| 1124 |
+
"loss": 0.2878,
|
| 1125 |
+
"step": 1560
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 2.36,
|
| 1129 |
+
"grad_norm": 0.10811661183834076,
|
| 1130 |
+
"learning_rate": 1.0671287365679567e-05,
|
| 1131 |
+
"loss": 0.2818,
|
| 1132 |
+
"step": 1570
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 2.38,
|
| 1136 |
+
"grad_norm": 0.109583280980587,
|
| 1137 |
+
"learning_rate": 1.018925880645351e-05,
|
| 1138 |
+
"loss": 0.2915,
|
| 1139 |
+
"step": 1580
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 2.39,
|
| 1143 |
+
"grad_norm": 0.1194503903388977,
|
| 1144 |
+
"learning_rate": 9.717132503016685e-06,
|
| 1145 |
+
"loss": 0.2922,
|
| 1146 |
+
"step": 1590
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 2.41,
|
| 1150 |
+
"grad_norm": 0.11107660830020905,
|
| 1151 |
+
"learning_rate": 9.255025888887814e-06,
|
| 1152 |
+
"loss": 0.2843,
|
| 1153 |
+
"step": 1600
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 2.42,
|
| 1157 |
+
"grad_norm": 0.12213042378425598,
|
| 1158 |
+
"learning_rate": 8.80305390535554e-06,
|
| 1159 |
+
"loss": 0.2867,
|
| 1160 |
+
"step": 1610
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 2.44,
|
| 1164 |
+
"grad_norm": 0.11774149537086487,
|
| 1165 |
+
"learning_rate": 8.361328972888732e-06,
|
| 1166 |
+
"loss": 0.2838,
|
| 1167 |
+
"step": 1620
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 2.45,
|
| 1171 |
+
"grad_norm": 0.11726924777030945,
|
| 1172 |
+
"learning_rate": 7.929960963173727e-06,
|
| 1173 |
+
"loss": 0.288,
|
| 1174 |
+
"step": 1630
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 2.47,
|
| 1178 |
+
"grad_norm": 0.12220928817987442,
|
| 1179 |
+
"learning_rate": 7.509057171785639e-06,
|
| 1180 |
+
"loss": 0.2844,
|
| 1181 |
+
"step": 1640
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 2.48,
|
| 1185 |
+
"grad_norm": 0.11534737050533295,
|
| 1186 |
+
"learning_rate": 7.098722291500331e-06,
|
| 1187 |
+
"loss": 0.2842,
|
| 1188 |
+
"step": 1650
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 2.5,
|
| 1192 |
+
"grad_norm": 0.11947780847549438,
|
| 1193 |
+
"learning_rate": 6.699058386253865e-06,
|
| 1194 |
+
"loss": 0.2827,
|
| 1195 |
+
"step": 1660
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 2.51,
|
| 1199 |
+
"grad_norm": 0.1192295104265213,
|
| 1200 |
+
"learning_rate": 6.310164865755808e-06,
|
| 1201 |
+
"loss": 0.2907,
|
| 1202 |
+
"step": 1670
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 2.53,
|
| 1206 |
+
"grad_norm": 0.11454175412654877,
|
| 1207 |
+
"learning_rate": 5.93213846076271e-06,
|
| 1208 |
+
"loss": 0.2833,
|
| 1209 |
+
"step": 1680
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 2.54,
|
| 1213 |
+
"grad_norm": 0.11072956025600433,
|
| 1214 |
+
"learning_rate": 5.5650731990179674e-06,
|
| 1215 |
+
"loss": 0.2869,
|
| 1216 |
+
"step": 1690
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 2.56,
|
| 1220 |
+
"grad_norm": 0.10620978474617004,
|
| 1221 |
+
"learning_rate": 5.20906038186399e-06,
|
| 1222 |
+
"loss": 0.2775,
|
| 1223 |
+
"step": 1700
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 2.57,
|
| 1227 |
+
"grad_norm": 0.1189485564827919,
|
| 1228 |
+
"learning_rate": 4.864188561532507e-06,
|
| 1229 |
+
"loss": 0.2842,
|
| 1230 |
+
"step": 1710
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 2.59,
|
| 1234 |
+
"grad_norm": 0.1264795958995819,
|
| 1235 |
+
"learning_rate": 4.530543519118702e-06,
|
| 1236 |
+
"loss": 0.2944,
|
| 1237 |
+
"step": 1720
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 2.6,
|
| 1241 |
+
"grad_norm": 0.10882660746574402,
|
| 1242 |
+
"learning_rate": 4.208208243244577e-06,
|
| 1243 |
+
"loss": 0.2903,
|
| 1244 |
+
"step": 1730
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 2.62,
|
| 1248 |
+
"grad_norm": 0.1184026375412941,
|
| 1249 |
+
"learning_rate": 3.8972629094169485e-06,
|
| 1250 |
+
"loss": 0.2934,
|
| 1251 |
+
"step": 1740
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 2.63,
|
| 1255 |
+
"grad_norm": 0.115041583776474,
|
| 1256 |
+
"learning_rate": 3.5977848600851016e-06,
|
| 1257 |
+
"loss": 0.2831,
|
| 1258 |
+
"step": 1750
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 2.65,
|
| 1262 |
+
"grad_norm": 0.1151689738035202,
|
| 1263 |
+
"learning_rate": 3.309848585403169e-06,
|
| 1264 |
+
"loss": 0.2828,
|
| 1265 |
+
"step": 1760
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 2.66,
|
| 1269 |
+
"grad_norm": 0.11265784502029419,
|
| 1270 |
+
"learning_rate": 3.033525704701956e-06,
|
| 1271 |
+
"loss": 0.2868,
|
| 1272 |
+
"step": 1770
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 2.68,
|
| 1276 |
+
"grad_norm": 0.10989955067634583,
|
| 1277 |
+
"learning_rate": 2.768884948674816e-06,
|
| 1278 |
+
"loss": 0.2798,
|
| 1279 |
+
"step": 1780
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 2.69,
|
| 1283 |
+
"grad_norm": 0.12034480273723602,
|
| 1284 |
+
"learning_rate": 2.515992142282042e-06,
|
| 1285 |
+
"loss": 0.2932,
|
| 1286 |
+
"step": 1790
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 2.71,
|
| 1290 |
+
"grad_norm": 0.11389750242233276,
|
| 1291 |
+
"learning_rate": 2.2749101883780157e-06,
|
| 1292 |
+
"loss": 0.2877,
|
| 1293 |
+
"step": 1800
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 2.72,
|
| 1297 |
+
"grad_norm": 0.12224046885967255,
|
| 1298 |
+
"learning_rate": 2.0456990520651696e-06,
|
| 1299 |
+
"loss": 0.29,
|
| 1300 |
+
"step": 1810
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 2.74,
|
| 1304 |
+
"grad_norm": 0.11018862575292587,
|
| 1305 |
+
"learning_rate": 1.8284157457786833e-06,
|
| 1306 |
+
"loss": 0.2903,
|
| 1307 |
+
"step": 1820
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 2.75,
|
| 1311 |
+
"grad_norm": 0.11373750865459442,
|
| 1312 |
+
"learning_rate": 1.6231143151055838e-06,
|
| 1313 |
+
"loss": 0.2823,
|
| 1314 |
+
"step": 1830
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 2.77,
|
| 1318 |
+
"grad_norm": 0.11346758902072906,
|
| 1319 |
+
"learning_rate": 1.4298458253417968e-06,
|
| 1320 |
+
"loss": 0.2918,
|
| 1321 |
+
"step": 1840
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 2.79,
|
| 1325 |
+
"grad_norm": 0.12030266970396042,
|
| 1326 |
+
"learning_rate": 1.2486583487905324e-06,
|
| 1327 |
+
"loss": 0.2793,
|
| 1328 |
+
"step": 1850
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 2.8,
|
| 1332 |
+
"grad_norm": 0.11971867829561234,
|
| 1333 |
+
"learning_rate": 1.079596952805101e-06,
|
| 1334 |
+
"loss": 0.2835,
|
| 1335 |
+
"step": 1860
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 2.82,
|
| 1339 |
+
"grad_norm": 0.11345378309488297,
|
| 1340 |
+
"learning_rate": 9.227036885791352e-07,
|
| 1341 |
+
"loss": 0.287,
|
| 1342 |
+
"step": 1870
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 2.83,
|
| 1346 |
+
"grad_norm": 0.12087972462177277,
|
| 1347 |
+
"learning_rate": 7.78017580687107e-07,
|
| 1348 |
+
"loss": 0.2834,
|
| 1349 |
+
"step": 1880
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 2.85,
|
| 1353 |
+
"grad_norm": 0.11702313274145126,
|
| 1354 |
+
"learning_rate": 6.455746173775701e-07,
|
| 1355 |
+
"loss": 0.2828,
|
| 1356 |
+
"step": 1890
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 2.86,
|
| 1360 |
+
"grad_norm": 0.11680703610181808,
|
| 1361 |
+
"learning_rate": 5.25407741621714e-07,
|
| 1362 |
+
"loss": 0.2821,
|
| 1363 |
+
"step": 1900
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 2.88,
|
| 1367 |
+
"grad_norm": 0.11461573839187622,
|
| 1368 |
+
"learning_rate": 4.1754684291934744e-07,
|
| 1369 |
+
"loss": 0.2784,
|
| 1370 |
+
"step": 1910
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 2.89,
|
| 1374 |
+
"grad_norm": 0.12143554538488388,
|
| 1375 |
+
"learning_rate": 3.2201874986437784e-07,
|
| 1376 |
+
"loss": 0.278,
|
| 1377 |
+
"step": 1920
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 2.91,
|
| 1381 |
+
"grad_norm": 0.11503802239894867,
|
| 1382 |
+
"learning_rate": 2.3884722347164434e-07,
|
| 1383 |
+
"loss": 0.2881,
|
| 1384 |
+
"step": 1930
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 2.92,
|
| 1388 |
+
"grad_norm": 0.11443481594324112,
|
| 1389 |
+
"learning_rate": 1.6805295126677833e-07,
|
| 1390 |
+
"loss": 0.2952,
|
| 1391 |
+
"step": 1940
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 2.94,
|
| 1395 |
+
"grad_norm": 0.1119546890258789,
|
| 1396 |
+
"learning_rate": 1.0965354214051982e-07,
|
| 1397 |
+
"loss": 0.2833,
|
| 1398 |
+
"step": 1950
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 2.95,
|
| 1402 |
+
"grad_norm": 0.11658598482608795,
|
| 1403 |
+
"learning_rate": 6.366352196878756e-08,
|
| 1404 |
+
"loss": 0.2954,
|
| 1405 |
+
"step": 1960
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 2.97,
|
| 1409 |
+
"grad_norm": 0.11841295659542084,
|
| 1410 |
+
"learning_rate": 3.0094329999635906e-08,
|
| 1411 |
+
"loss": 0.2792,
|
| 1412 |
+
"step": 1970
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 2.98,
|
| 1416 |
+
"grad_norm": 0.11211774498224258,
|
| 1417 |
+
"learning_rate": 8.954316007908636e-09,
|
| 1418 |
+
"loss": 0.2914,
|
| 1419 |
+
"step": 1980
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 3.0,
|
| 1423 |
+
"grad_norm": 0.12004334479570389,
|
| 1424 |
+
"learning_rate": 2.4873821838911073e-10,
|
| 1425 |
+
"loss": 0.2895,
|
| 1426 |
+
"step": 1990
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 3.0,
|
| 1430 |
+
"step": 1992,
|
| 1431 |
+
"total_flos": 7.377073297607885e+18,
|
| 1432 |
+
"train_loss": 0.32009275511924523,
|
| 1433 |
+
"train_runtime": 49821.5539,
|
| 1434 |
+
"train_samples_per_second": 6.399,
|
| 1435 |
+
"train_steps_per_second": 0.04
|
| 1436 |
+
}
|
| 1437 |
+
],
|
| 1438 |
+
"logging_steps": 10,
|
| 1439 |
+
"max_steps": 1992,
|
| 1440 |
+
"num_input_tokens_seen": 0,
|
| 1441 |
+
"num_train_epochs": 3,
|
| 1442 |
+
"save_steps": 250,
|
| 1443 |
+
"total_flos": 7.377073297607885e+18,
|
| 1444 |
+
"train_batch_size": 20,
|
| 1445 |
+
"trial_name": null,
|
| 1446 |
+
"trial_params": null
|
| 1447 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85f10b5751a98b3548e4b442f055cd1873b10a4262d8c0879383d6791fb9e828
|
| 3 |
+
size 5112
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|