Laurie commited on
Commit
0f5f3fe
1 Parent(s): 2f49801

Upload 11 files

Browse files
adapter_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "baichuan-inc/baichuan-7B",
3
+ "bias": "none",
4
+ "fan_in_fan_out": false,
5
+ "inference_mode": true,
6
+ "init_lora_weights": true,
7
+ "lora_alpha": 32.0,
8
+ "lora_dropout": 0.1,
9
+ "modules_to_save": null,
10
+ "peft_type": "LORA",
11
+ "r": 8,
12
+ "target_modules": [
13
+ "W_pack"
14
+ ],
15
+ "task_type": "CAUSAL_LM"
16
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a608b5ca80729ecaa032ad0bfe6b80b33f842f62f183aab7f47d56475108c113
3
+ size 16799153
all_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 1.3997734785079956,
4
+ "eval_runtime": 19.9371,
5
+ "eval_samples_per_second": 24.527,
6
+ "eval_steps_per_second": 6.169,
7
+ "train_loss": 1.4043121354732555,
8
+ "train_runtime": 20600.2987,
9
+ "train_samples_per_second": 7.038,
10
+ "train_steps_per_second": 0.22
11
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 1.3997734785079956,
4
+ "eval_runtime": 19.9371,
5
+ "eval_samples_per_second": 24.527,
6
+ "eval_steps_per_second": 6.169
7
+ }
finetuning_args.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "finetuning_type": "lora",
3
+ "lora_alpha": 32.0,
4
+ "lora_dropout": 0.1,
5
+ "lora_rank": 8,
6
+ "lora_target": [
7
+ "W_pack"
8
+ ],
9
+ "name_module_trainable": "mlp",
10
+ "num_layer_trainable": 3
11
+ }
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 1.4043121354732555,
4
+ "train_runtime": 20600.2987,
5
+ "train_samples_per_second": 7.038,
6
+ "train_steps_per_second": 0.22
7
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,453 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 4530, "loss": 1.6257, "reward": null, "learning_rate": 4.999939881018594e-05, "epoch": 0.01, "percentage": 0.22, "elapsed_time": "0:00:48", "remaining_time": "6:04:04"}
2
+ {"current_steps": 20, "total_steps": 4530, "loss": 1.6388, "reward": null, "learning_rate": 4.999759526965809e-05, "epoch": 0.01, "percentage": 0.44, "elapsed_time": "0:01:33", "remaining_time": "5:49:40"}
3
+ {"current_steps": 30, "total_steps": 4530, "loss": 1.5034, "reward": null, "learning_rate": 4.999458946515808e-05, "epoch": 0.02, "percentage": 0.66, "elapsed_time": "0:02:18", "remaining_time": "5:46:24"}
4
+ {"current_steps": 40, "total_steps": 4530, "loss": 1.5761, "reward": null, "learning_rate": 4.999038154125061e-05, "epoch": 0.03, "percentage": 0.88, "elapsed_time": "0:03:01", "remaining_time": "5:40:03"}
5
+ {"current_steps": 50, "total_steps": 4530, "loss": 1.5066, "reward": null, "learning_rate": 4.998497170031657e-05, "epoch": 0.03, "percentage": 1.1, "elapsed_time": "0:03:42", "remaining_time": "5:32:10"}
6
+ {"current_steps": 60, "total_steps": 4530, "loss": 1.5738, "reward": null, "learning_rate": 4.997836020254328e-05, "epoch": 0.04, "percentage": 1.32, "elapsed_time": "0:04:24", "remaining_time": "5:28:48"}
7
+ {"current_steps": 70, "total_steps": 4530, "loss": 1.4921, "reward": null, "learning_rate": 4.9970547365911925e-05, "epoch": 0.05, "percentage": 1.55, "elapsed_time": "0:05:10", "remaining_time": "5:29:44"}
8
+ {"current_steps": 80, "total_steps": 4530, "loss": 1.4508, "reward": null, "learning_rate": 4.996153356618233e-05, "epoch": 0.05, "percentage": 1.77, "elapsed_time": "0:05:55", "remaining_time": "5:29:27"}
9
+ {"current_steps": 90, "total_steps": 4530, "loss": 1.4714, "reward": null, "learning_rate": 4.995131923687488e-05, "epoch": 0.06, "percentage": 1.99, "elapsed_time": "0:06:39", "remaining_time": "5:28:16"}
10
+ {"current_steps": 100, "total_steps": 4530, "loss": 1.494, "reward": null, "learning_rate": 4.9939904869249616e-05, "epoch": 0.07, "percentage": 2.21, "elapsed_time": "0:07:23", "remaining_time": "5:27:38"}
11
+ {"current_steps": 110, "total_steps": 4530, "loss": 1.4934, "reward": null, "learning_rate": 4.992729101228267e-05, "epoch": 0.07, "percentage": 2.43, "elapsed_time": "0:08:27", "remaining_time": "5:39:45"}
12
+ {"current_steps": 120, "total_steps": 4530, "loss": 1.4789, "reward": null, "learning_rate": 4.991347827263982e-05, "epoch": 0.08, "percentage": 2.65, "elapsed_time": "0:09:09", "remaining_time": "5:36:30"}
13
+ {"current_steps": 130, "total_steps": 4530, "loss": 1.4511, "reward": null, "learning_rate": 4.9898467314647356e-05, "epoch": 0.09, "percentage": 2.87, "elapsed_time": "0:09:52", "remaining_time": "5:34:17"}
14
+ {"current_steps": 140, "total_steps": 4530, "loss": 1.4876, "reward": null, "learning_rate": 4.9882258860260065e-05, "epoch": 0.09, "percentage": 3.09, "elapsed_time": "0:10:35", "remaining_time": "5:32:00"}
15
+ {"current_steps": 150, "total_steps": 4530, "loss": 1.5124, "reward": null, "learning_rate": 4.9864853689026556e-05, "epoch": 0.1, "percentage": 3.31, "elapsed_time": "0:11:18", "remaining_time": "5:30:00"}
16
+ {"current_steps": 160, "total_steps": 4530, "loss": 1.4772, "reward": null, "learning_rate": 4.984625263805178e-05, "epoch": 0.11, "percentage": 3.53, "elapsed_time": "0:12:00", "remaining_time": "5:28:04"}
17
+ {"current_steps": 170, "total_steps": 4530, "loss": 1.436, "reward": null, "learning_rate": 4.982645660195671e-05, "epoch": 0.11, "percentage": 3.75, "elapsed_time": "0:12:44", "remaining_time": "5:26:50"}
18
+ {"current_steps": 180, "total_steps": 4530, "loss": 1.4377, "reward": null, "learning_rate": 4.9805466532835376e-05, "epoch": 0.12, "percentage": 3.97, "elapsed_time": "0:13:26", "remaining_time": "5:24:57"}
19
+ {"current_steps": 190, "total_steps": 4530, "loss": 1.438, "reward": null, "learning_rate": 4.978328344020904e-05, "epoch": 0.13, "percentage": 4.19, "elapsed_time": "0:14:10", "remaining_time": "5:23:46"}
20
+ {"current_steps": 200, "total_steps": 4530, "loss": 1.4448, "reward": null, "learning_rate": 4.975990839097764e-05, "epoch": 0.13, "percentage": 4.42, "elapsed_time": "0:14:52", "remaining_time": "5:22:08"}
21
+ {"current_steps": 210, "total_steps": 4530, "loss": 1.452, "reward": null, "learning_rate": 4.973534250936851e-05, "epoch": 0.14, "percentage": 4.64, "elapsed_time": "0:15:58", "remaining_time": "5:28:29"}
22
+ {"current_steps": 220, "total_steps": 4530, "loss": 1.4813, "reward": null, "learning_rate": 4.970958697688226e-05, "epoch": 0.15, "percentage": 4.86, "elapsed_time": "0:16:42", "remaining_time": "5:27:26"}
23
+ {"current_steps": 230, "total_steps": 4530, "loss": 1.41, "reward": null, "learning_rate": 4.9682643032235996e-05, "epoch": 0.15, "percentage": 5.08, "elapsed_time": "0:17:26", "remaining_time": "5:26:12"}
24
+ {"current_steps": 240, "total_steps": 4530, "loss": 1.428, "reward": null, "learning_rate": 4.965451197130373e-05, "epoch": 0.16, "percentage": 5.3, "elapsed_time": "0:18:12", "remaining_time": "5:25:21"}
25
+ {"current_steps": 250, "total_steps": 4530, "loss": 1.463, "reward": null, "learning_rate": 4.9625195147054034e-05, "epoch": 0.17, "percentage": 5.52, "elapsed_time": "0:18:56", "remaining_time": "5:24:16"}
26
+ {"current_steps": 260, "total_steps": 4530, "loss": 1.4821, "reward": null, "learning_rate": 4.9594693969485006e-05, "epoch": 0.17, "percentage": 5.74, "elapsed_time": "0:19:39", "remaining_time": "5:22:51"}
27
+ {"current_steps": 270, "total_steps": 4530, "loss": 1.4855, "reward": null, "learning_rate": 4.956300990555643e-05, "epoch": 0.18, "percentage": 5.96, "elapsed_time": "0:20:25", "remaining_time": "5:22:10"}
28
+ {"current_steps": 280, "total_steps": 4530, "loss": 1.4322, "reward": null, "learning_rate": 4.9530144479119215e-05, "epoch": 0.19, "percentage": 6.18, "elapsed_time": "0:21:09", "remaining_time": "5:21:15"}
29
+ {"current_steps": 290, "total_steps": 4530, "loss": 1.4397, "reward": null, "learning_rate": 4.9496099270842145e-05, "epoch": 0.19, "percentage": 6.4, "elapsed_time": "0:21:51", "remaining_time": "5:19:40"}
30
+ {"current_steps": 300, "total_steps": 4530, "loss": 1.4107, "reward": null, "learning_rate": 4.9460875918135804e-05, "epoch": 0.2, "percentage": 6.62, "elapsed_time": "0:22:35", "remaining_time": "5:18:27"}
31
+ {"current_steps": 310, "total_steps": 4530, "loss": 1.4722, "reward": null, "learning_rate": 4.942447611507386e-05, "epoch": 0.21, "percentage": 6.84, "elapsed_time": "0:23:37", "remaining_time": "5:21:34"}
32
+ {"current_steps": 320, "total_steps": 4530, "loss": 1.423, "reward": null, "learning_rate": 4.938690161231159e-05, "epoch": 0.21, "percentage": 7.06, "elapsed_time": "0:24:21", "remaining_time": "5:20:30"}
33
+ {"current_steps": 330, "total_steps": 4530, "loss": 1.4288, "reward": null, "learning_rate": 4.934815421700165e-05, "epoch": 0.22, "percentage": 7.28, "elapsed_time": "0:25:05", "remaining_time": "5:19:25"}
34
+ {"current_steps": 340, "total_steps": 4530, "loss": 1.4294, "reward": null, "learning_rate": 4.9308235792707194e-05, "epoch": 0.23, "percentage": 7.51, "elapsed_time": "0:25:51", "remaining_time": "5:18:43"}
35
+ {"current_steps": 350, "total_steps": 4530, "loss": 1.4233, "reward": null, "learning_rate": 4.9267148259312224e-05, "epoch": 0.23, "percentage": 7.73, "elapsed_time": "0:26:38", "remaining_time": "5:18:12"}
36
+ {"current_steps": 360, "total_steps": 4530, "loss": 1.4553, "reward": null, "learning_rate": 4.9224893592929275e-05, "epoch": 0.24, "percentage": 7.95, "elapsed_time": "0:27:19", "remaining_time": "5:16:36"}
37
+ {"current_steps": 370, "total_steps": 4530, "loss": 1.4206, "reward": null, "learning_rate": 4.9181473825804346e-05, "epoch": 0.24, "percentage": 8.17, "elapsed_time": "0:28:03", "remaining_time": "5:15:24"}
38
+ {"current_steps": 380, "total_steps": 4530, "loss": 1.442, "reward": null, "learning_rate": 4.913689104621917e-05, "epoch": 0.25, "percentage": 8.39, "elapsed_time": "0:28:48", "remaining_time": "5:14:32"}
39
+ {"current_steps": 390, "total_steps": 4530, "loss": 1.4668, "reward": null, "learning_rate": 4.909114739839079e-05, "epoch": 0.26, "percentage": 8.61, "elapsed_time": "0:29:33", "remaining_time": "5:13:43"}
40
+ {"current_steps": 400, "total_steps": 4530, "loss": 1.4439, "reward": null, "learning_rate": 4.9044245082368415e-05, "epoch": 0.26, "percentage": 8.83, "elapsed_time": "0:30:18", "remaining_time": "5:12:51"}
41
+ {"current_steps": 410, "total_steps": 4530, "loss": 1.4224, "reward": null, "learning_rate": 4.8996186353927606e-05, "epoch": 0.27, "percentage": 9.05, "elapsed_time": "0:31:21", "remaining_time": "5:15:01"}
42
+ {"current_steps": 420, "total_steps": 4530, "loss": 1.4084, "reward": null, "learning_rate": 4.894697352446182e-05, "epoch": 0.28, "percentage": 9.27, "elapsed_time": "0:32:11", "remaining_time": "5:14:58"}
43
+ {"current_steps": 430, "total_steps": 4530, "loss": 1.4398, "reward": null, "learning_rate": 4.889660896087119e-05, "epoch": 0.28, "percentage": 9.49, "elapsed_time": "0:32:54", "remaining_time": "5:13:50"}
44
+ {"current_steps": 440, "total_steps": 4530, "loss": 1.4268, "reward": null, "learning_rate": 4.884509508544874e-05, "epoch": 0.29, "percentage": 9.71, "elapsed_time": "0:33:38", "remaining_time": "5:12:44"}
45
+ {"current_steps": 450, "total_steps": 4530, "loss": 1.4522, "reward": null, "learning_rate": 4.879243437576383e-05, "epoch": 0.3, "percentage": 9.93, "elapsed_time": "0:34:20", "remaining_time": "5:11:24"}
46
+ {"current_steps": 460, "total_steps": 4530, "loss": 1.4222, "reward": null, "learning_rate": 4.8738629364543045e-05, "epoch": 0.3, "percentage": 10.15, "elapsed_time": "0:35:03", "remaining_time": "5:10:09"}
47
+ {"current_steps": 470, "total_steps": 4530, "loss": 1.4956, "reward": null, "learning_rate": 4.8683682639548365e-05, "epoch": 0.31, "percentage": 10.38, "elapsed_time": "0:35:45", "remaining_time": "5:08:51"}
48
+ {"current_steps": 480, "total_steps": 4530, "loss": 1.4538, "reward": null, "learning_rate": 4.862759684345269e-05, "epoch": 0.32, "percentage": 10.6, "elapsed_time": "0:36:28", "remaining_time": "5:07:48"}
49
+ {"current_steps": 490, "total_steps": 4530, "loss": 1.3748, "reward": null, "learning_rate": 4.857037467371278e-05, "epoch": 0.32, "percentage": 10.82, "elapsed_time": "0:37:11", "remaining_time": "5:06:38"}
50
+ {"current_steps": 500, "total_steps": 4530, "loss": 1.4127, "reward": null, "learning_rate": 4.8512018882439475e-05, "epoch": 0.33, "percentage": 11.04, "elapsed_time": "0:37:56", "remaining_time": "5:05:45"}
51
+ {"current_steps": 510, "total_steps": 4530, "loss": 1.3795, "reward": null, "learning_rate": 4.8452532276265364e-05, "epoch": 0.34, "percentage": 11.26, "elapsed_time": "0:39:03", "remaining_time": "5:07:49"}
52
+ {"current_steps": 520, "total_steps": 4530, "loss": 1.4414, "reward": null, "learning_rate": 4.8391917716209765e-05, "epoch": 0.34, "percentage": 11.48, "elapsed_time": "0:39:45", "remaining_time": "5:06:35"}
53
+ {"current_steps": 530, "total_steps": 4530, "loss": 1.4242, "reward": null, "learning_rate": 4.833017811754119e-05, "epoch": 0.35, "percentage": 11.7, "elapsed_time": "0:40:27", "remaining_time": "5:05:19"}
54
+ {"current_steps": 540, "total_steps": 4530, "loss": 1.4196, "reward": null, "learning_rate": 4.8267316449637054e-05, "epoch": 0.36, "percentage": 11.92, "elapsed_time": "0:41:09", "remaining_time": "5:04:08"}
55
+ {"current_steps": 550, "total_steps": 4530, "loss": 1.389, "reward": null, "learning_rate": 4.820333573584091e-05, "epoch": 0.36, "percentage": 12.14, "elapsed_time": "0:41:52", "remaining_time": "5:03:02"}
56
+ {"current_steps": 560, "total_steps": 4530, "loss": 1.4597, "reward": null, "learning_rate": 4.813823905331704e-05, "epoch": 0.37, "percentage": 12.36, "elapsed_time": "0:42:36", "remaining_time": "5:02:04"}
57
+ {"current_steps": 570, "total_steps": 4530, "loss": 1.4275, "reward": null, "learning_rate": 4.8072029532902426e-05, "epoch": 0.38, "percentage": 12.58, "elapsed_time": "0:43:22", "remaining_time": "5:01:23"}
58
+ {"current_steps": 580, "total_steps": 4530, "loss": 1.4364, "reward": null, "learning_rate": 4.800471035895624e-05, "epoch": 0.38, "percentage": 12.8, "elapsed_time": "0:44:08", "remaining_time": "5:00:38"}
59
+ {"current_steps": 590, "total_steps": 4530, "loss": 1.4366, "reward": null, "learning_rate": 4.7936284769206584e-05, "epoch": 0.39, "percentage": 13.02, "elapsed_time": "0:44:49", "remaining_time": "4:59:23"}
60
+ {"current_steps": 600, "total_steps": 4530, "loss": 1.5086, "reward": null, "learning_rate": 4.786675605459487e-05, "epoch": 0.4, "percentage": 13.25, "elapsed_time": "0:45:33", "remaining_time": "4:58:27"}
61
+ {"current_steps": 610, "total_steps": 4530, "loss": 1.4309, "reward": null, "learning_rate": 4.779612755911752e-05, "epoch": 0.4, "percentage": 13.47, "elapsed_time": "0:46:38", "remaining_time": "4:59:43"}
62
+ {"current_steps": 620, "total_steps": 4530, "loss": 1.4102, "reward": null, "learning_rate": 4.772440267966508e-05, "epoch": 0.41, "percentage": 13.69, "elapsed_time": "0:47:21", "remaining_time": "4:58:40"}
63
+ {"current_steps": 630, "total_steps": 4530, "loss": 1.4035, "reward": null, "learning_rate": 4.76515848658589e-05, "epoch": 0.42, "percentage": 13.91, "elapsed_time": "0:48:05", "remaining_time": "4:57:42"}
64
+ {"current_steps": 640, "total_steps": 4530, "loss": 1.4478, "reward": null, "learning_rate": 4.7577677619885234e-05, "epoch": 0.42, "percentage": 14.13, "elapsed_time": "0:48:45", "remaining_time": "4:56:24"}
65
+ {"current_steps": 650, "total_steps": 4530, "loss": 1.3999, "reward": null, "learning_rate": 4.7502684496326746e-05, "epoch": 0.43, "percentage": 14.35, "elapsed_time": "0:49:28", "remaining_time": "4:55:21"}
66
+ {"current_steps": 660, "total_steps": 4530, "loss": 1.4042, "reward": null, "learning_rate": 4.7426609101991605e-05, "epoch": 0.44, "percentage": 14.57, "elapsed_time": "0:50:13", "remaining_time": "4:54:30"}
67
+ {"current_steps": 670, "total_steps": 4530, "loss": 1.4216, "reward": null, "learning_rate": 4.734945509573997e-05, "epoch": 0.44, "percentage": 14.79, "elapsed_time": "0:50:55", "remaining_time": "4:53:21"}
68
+ {"current_steps": 680, "total_steps": 4530, "loss": 1.4786, "reward": null, "learning_rate": 4.727122618830808e-05, "epoch": 0.45, "percentage": 15.01, "elapsed_time": "0:51:41", "remaining_time": "4:52:40"}
69
+ {"current_steps": 690, "total_steps": 4530, "loss": 1.4414, "reward": null, "learning_rate": 4.719192614212969e-05, "epoch": 0.46, "percentage": 15.23, "elapsed_time": "0:52:24", "remaining_time": "4:51:40"}
70
+ {"current_steps": 700, "total_steps": 4530, "loss": 1.493, "reward": null, "learning_rate": 4.711155877115523e-05, "epoch": 0.46, "percentage": 15.45, "elapsed_time": "0:53:05", "remaining_time": "4:50:29"}
71
+ {"current_steps": 710, "total_steps": 4530, "loss": 1.4078, "reward": null, "learning_rate": 4.703012794066827e-05, "epoch": 0.47, "percentage": 15.67, "elapsed_time": "0:54:12", "remaining_time": "4:51:37"}
72
+ {"current_steps": 720, "total_steps": 4530, "loss": 1.4539, "reward": null, "learning_rate": 4.694763756709967e-05, "epoch": 0.48, "percentage": 15.89, "elapsed_time": "0:54:58", "remaining_time": "4:50:53"}
73
+ {"current_steps": 730, "total_steps": 4530, "loss": 1.4458, "reward": null, "learning_rate": 4.6864091617839235e-05, "epoch": 0.48, "percentage": 16.11, "elapsed_time": "0:55:42", "remaining_time": "4:49:59"}
74
+ {"current_steps": 740, "total_steps": 4530, "loss": 1.4001, "reward": null, "learning_rate": 4.677949411104485e-05, "epoch": 0.49, "percentage": 16.34, "elapsed_time": "0:56:25", "remaining_time": "4:49:01"}
75
+ {"current_steps": 750, "total_steps": 4530, "loss": 1.433, "reward": null, "learning_rate": 4.669384911544927e-05, "epoch": 0.5, "percentage": 16.56, "elapsed_time": "0:57:09", "remaining_time": "4:48:06"}
76
+ {"current_steps": 760, "total_steps": 4530, "loss": 1.4323, "reward": null, "learning_rate": 4.660716075016442e-05, "epoch": 0.5, "percentage": 16.78, "elapsed_time": "0:57:56", "remaining_time": "4:47:24"}
77
+ {"current_steps": 770, "total_steps": 4530, "loss": 1.4052, "reward": null, "learning_rate": 4.6519433184483245e-05, "epoch": 0.51, "percentage": 17.0, "elapsed_time": "0:58:42", "remaining_time": "4:46:39"}
78
+ {"current_steps": 780, "total_steps": 4530, "loss": 1.4021, "reward": null, "learning_rate": 4.6430670637679295e-05, "epoch": 0.52, "percentage": 17.22, "elapsed_time": "0:59:27", "remaining_time": "4:45:52"}
79
+ {"current_steps": 790, "total_steps": 4530, "loss": 1.4049, "reward": null, "learning_rate": 4.634087737880367e-05, "epoch": 0.52, "percentage": 17.44, "elapsed_time": "1:00:12", "remaining_time": "4:45:03"}
80
+ {"current_steps": 800, "total_steps": 4530, "loss": 1.3701, "reward": null, "learning_rate": 4.625005772647979e-05, "epoch": 0.53, "percentage": 17.66, "elapsed_time": "1:00:57", "remaining_time": "4:44:14"}
81
+ {"current_steps": 810, "total_steps": 4530, "loss": 1.4209, "reward": null, "learning_rate": 4.615821604869564e-05, "epoch": 0.54, "percentage": 17.88, "elapsed_time": "1:02:00", "remaining_time": "4:44:45"}
82
+ {"current_steps": 820, "total_steps": 4530, "loss": 1.4373, "reward": null, "learning_rate": 4.606535676259372e-05, "epoch": 0.54, "percentage": 18.1, "elapsed_time": "1:02:43", "remaining_time": "4:43:47"}
83
+ {"current_steps": 830, "total_steps": 4530, "loss": 1.4913, "reward": null, "learning_rate": 4.597148433425857e-05, "epoch": 0.55, "percentage": 18.32, "elapsed_time": "1:03:26", "remaining_time": "4:42:48"}
84
+ {"current_steps": 840, "total_steps": 4530, "loss": 1.434, "reward": null, "learning_rate": 4.587660327850203e-05, "epoch": 0.56, "percentage": 18.54, "elapsed_time": "1:04:13", "remaining_time": "4:42:06"}
85
+ {"current_steps": 850, "total_steps": 4530, "loss": 1.3932, "reward": null, "learning_rate": 4.578071815864602e-05, "epoch": 0.56, "percentage": 18.76, "elapsed_time": "1:04:58", "remaining_time": "4:41:18"}
86
+ {"current_steps": 860, "total_steps": 4530, "loss": 1.4232, "reward": null, "learning_rate": 4.5683833586303157e-05, "epoch": 0.57, "percentage": 18.98, "elapsed_time": "1:05:41", "remaining_time": "4:40:19"}
87
+ {"current_steps": 870, "total_steps": 4530, "loss": 1.3651, "reward": null, "learning_rate": 4.5585954221154856e-05, "epoch": 0.58, "percentage": 19.21, "elapsed_time": "1:06:24", "remaining_time": "4:39:23"}
88
+ {"current_steps": 880, "total_steps": 4530, "loss": 1.4009, "reward": null, "learning_rate": 4.548708477072733e-05, "epoch": 0.58, "percentage": 19.43, "elapsed_time": "1:07:10", "remaining_time": "4:38:38"}
89
+ {"current_steps": 890, "total_steps": 4530, "loss": 1.428, "reward": null, "learning_rate": 4.5387229990165073e-05, "epoch": 0.59, "percentage": 19.65, "elapsed_time": "1:07:55", "remaining_time": "4:37:49"}
90
+ {"current_steps": 900, "total_steps": 4530, "loss": 1.413, "reward": null, "learning_rate": 4.528639468200226e-05, "epoch": 0.6, "percentage": 19.87, "elapsed_time": "1:08:40", "remaining_time": "4:36:57"}
91
+ {"current_steps": 910, "total_steps": 4530, "loss": 1.4328, "reward": null, "learning_rate": 4.51845836959317e-05, "epoch": 0.6, "percentage": 20.09, "elapsed_time": "1:09:42", "remaining_time": "4:37:19"}
92
+ {"current_steps": 920, "total_steps": 4530, "loss": 1.4262, "reward": null, "learning_rate": 4.508180192857162e-05, "epoch": 0.61, "percentage": 20.31, "elapsed_time": "1:10:27", "remaining_time": "4:36:28"}
93
+ {"current_steps": 930, "total_steps": 4530, "loss": 1.3677, "reward": null, "learning_rate": 4.497805432323015e-05, "epoch": 0.62, "percentage": 20.53, "elapsed_time": "1:11:12", "remaining_time": "4:35:39"}
94
+ {"current_steps": 940, "total_steps": 4530, "loss": 1.4546, "reward": null, "learning_rate": 4.487334586966756e-05, "epoch": 0.62, "percentage": 20.75, "elapsed_time": "1:11:54", "remaining_time": "4:34:37"}
95
+ {"current_steps": 950, "total_steps": 4530, "loss": 1.4011, "reward": null, "learning_rate": 4.476768160385632e-05, "epoch": 0.63, "percentage": 20.97, "elapsed_time": "1:12:39", "remaining_time": "4:33:49"}
96
+ {"current_steps": 960, "total_steps": 4530, "loss": 1.441, "reward": null, "learning_rate": 4.466106660773885e-05, "epoch": 0.64, "percentage": 21.19, "elapsed_time": "1:13:22", "remaining_time": "4:32:50"}
97
+ {"current_steps": 970, "total_steps": 4530, "loss": 1.3946, "reward": null, "learning_rate": 4.4553506008983126e-05, "epoch": 0.64, "percentage": 21.41, "elapsed_time": "1:14:06", "remaining_time": "4:31:57"}
98
+ {"current_steps": 980, "total_steps": 4530, "loss": 1.4478, "reward": null, "learning_rate": 4.4445004980736064e-05, "epoch": 0.65, "percentage": 21.63, "elapsed_time": "1:14:47", "remaining_time": "4:30:55"}
99
+ {"current_steps": 990, "total_steps": 4530, "loss": 1.4093, "reward": null, "learning_rate": 4.43355687413747e-05, "epoch": 0.66, "percentage": 21.85, "elapsed_time": "1:15:30", "remaining_time": "4:29:58"}
100
+ {"current_steps": 1000, "total_steps": 4530, "loss": 1.4285, "reward": null, "learning_rate": 4.4225202554255227e-05, "epoch": 0.66, "percentage": 22.08, "elapsed_time": "1:16:14", "remaining_time": "4:29:06"}
101
+ {"current_steps": 1010, "total_steps": 4530, "loss": 1.3971, "reward": null, "learning_rate": 4.411391172745984e-05, "epoch": 0.67, "percentage": 22.3, "elapsed_time": "1:17:17", "remaining_time": "4:29:20"}
102
+ {"current_steps": 1020, "total_steps": 4530, "loss": 1.4024, "reward": null, "learning_rate": 4.4001701613541456e-05, "epoch": 0.68, "percentage": 22.52, "elapsed_time": "1:18:00", "remaining_time": "4:28:26"}
103
+ {"current_steps": 1030, "total_steps": 4530, "loss": 1.3623, "reward": null, "learning_rate": 4.388857760926629e-05, "epoch": 0.68, "percentage": 22.74, "elapsed_time": "1:18:45", "remaining_time": "4:27:37"}
104
+ {"current_steps": 1040, "total_steps": 4530, "loss": 1.3943, "reward": null, "learning_rate": 4.3774545155354254e-05, "epoch": 0.69, "percentage": 22.96, "elapsed_time": "1:19:31", "remaining_time": "4:26:53"}
105
+ {"current_steps": 1050, "total_steps": 4530, "loss": 1.4586, "reward": null, "learning_rate": 4.3659609736217344e-05, "epoch": 0.7, "percentage": 23.18, "elapsed_time": "1:20:18", "remaining_time": "4:26:09"}
106
+ {"current_steps": 1060, "total_steps": 4530, "loss": 1.4178, "reward": null, "learning_rate": 4.354377687969581e-05, "epoch": 0.7, "percentage": 23.4, "elapsed_time": "1:21:00", "remaining_time": "4:25:10"}
107
+ {"current_steps": 1070, "total_steps": 4530, "loss": 1.4454, "reward": null, "learning_rate": 4.342705215679232e-05, "epoch": 0.71, "percentage": 23.62, "elapsed_time": "1:21:44", "remaining_time": "4:24:18"}
108
+ {"current_steps": 1080, "total_steps": 4530, "loss": 1.3769, "reward": null, "learning_rate": 4.330944118140407e-05, "epoch": 0.72, "percentage": 23.84, "elapsed_time": "1:22:33", "remaining_time": "4:23:44"}
109
+ {"current_steps": 1090, "total_steps": 4530, "loss": 1.3912, "reward": null, "learning_rate": 4.3190949610052645e-05, "epoch": 0.72, "percentage": 24.06, "elapsed_time": "1:23:18", "remaining_time": "4:22:53"}
110
+ {"current_steps": 1100, "total_steps": 4530, "loss": 1.4116, "reward": null, "learning_rate": 4.3071583141612135e-05, "epoch": 0.73, "percentage": 24.28, "elapsed_time": "1:24:01", "remaining_time": "4:21:58"}
111
+ {"current_steps": 1110, "total_steps": 4530, "loss": 1.4019, "reward": null, "learning_rate": 4.295134751703493e-05, "epoch": 0.73, "percentage": 24.5, "elapsed_time": "1:25:01", "remaining_time": "4:21:59"}
112
+ {"current_steps": 1120, "total_steps": 4530, "loss": 1.378, "reward": null, "learning_rate": 4.283024851907565e-05, "epoch": 0.74, "percentage": 24.72, "elapsed_time": "1:25:46", "remaining_time": "4:21:09"}
113
+ {"current_steps": 1130, "total_steps": 4530, "loss": 1.432, "reward": null, "learning_rate": 4.2708291972013026e-05, "epoch": 0.75, "percentage": 24.94, "elapsed_time": "1:26:31", "remaining_time": "4:20:19"}
114
+ {"current_steps": 1140, "total_steps": 4530, "loss": 1.4531, "reward": null, "learning_rate": 4.2585483741369755e-05, "epoch": 0.75, "percentage": 25.17, "elapsed_time": "1:27:13", "remaining_time": "4:19:24"}
115
+ {"current_steps": 1150, "total_steps": 4530, "loss": 1.4455, "reward": null, "learning_rate": 4.2461829733630435e-05, "epoch": 0.76, "percentage": 25.39, "elapsed_time": "1:27:58", "remaining_time": "4:18:34"}
116
+ {"current_steps": 1160, "total_steps": 4530, "loss": 1.4081, "reward": null, "learning_rate": 4.233733589595746e-05, "epoch": 0.77, "percentage": 25.61, "elapsed_time": "1:28:40", "remaining_time": "4:17:38"}
117
+ {"current_steps": 1170, "total_steps": 4530, "loss": 1.4344, "reward": null, "learning_rate": 4.2212008215905e-05, "epoch": 0.77, "percentage": 25.83, "elapsed_time": "1:29:22", "remaining_time": "4:16:38"}
118
+ {"current_steps": 1180, "total_steps": 4530, "loss": 1.3935, "reward": null, "learning_rate": 4.208585272113102e-05, "epoch": 0.78, "percentage": 26.05, "elapsed_time": "1:30:04", "remaining_time": "4:15:43"}
119
+ {"current_steps": 1190, "total_steps": 4530, "loss": 1.4161, "reward": null, "learning_rate": 4.195887547910741e-05, "epoch": 0.79, "percentage": 26.27, "elapsed_time": "1:30:49", "remaining_time": "4:14:54"}
120
+ {"current_steps": 1200, "total_steps": 4530, "loss": 1.4185, "reward": null, "learning_rate": 4.1831082596828106e-05, "epoch": 0.79, "percentage": 26.49, "elapsed_time": "1:31:31", "remaining_time": "4:13:59"}
121
+ {"current_steps": 1210, "total_steps": 4530, "loss": 1.3714, "reward": null, "learning_rate": 4.1702480220515475e-05, "epoch": 0.8, "percentage": 26.71, "elapsed_time": "1:32:38", "remaining_time": "4:14:10"}
122
+ {"current_steps": 1220, "total_steps": 4530, "loss": 1.4062, "reward": null, "learning_rate": 4.157307453532457e-05, "epoch": 0.81, "percentage": 26.93, "elapsed_time": "1:33:23", "remaining_time": "4:13:23"}
123
+ {"current_steps": 1230, "total_steps": 4530, "loss": 1.4007, "reward": null, "learning_rate": 4.144287176504582e-05, "epoch": 0.81, "percentage": 27.15, "elapsed_time": "1:34:06", "remaining_time": "4:12:29"}
124
+ {"current_steps": 1240, "total_steps": 4530, "loss": 1.4153, "reward": null, "learning_rate": 4.131187817180554e-05, "epoch": 0.82, "percentage": 27.37, "elapsed_time": "1:34:51", "remaining_time": "4:11:41"}
125
+ {"current_steps": 1250, "total_steps": 4530, "loss": 1.3619, "reward": null, "learning_rate": 4.118010005576485e-05, "epoch": 0.83, "percentage": 27.59, "elapsed_time": "1:35:34", "remaining_time": "4:10:48"}
126
+ {"current_steps": 1260, "total_steps": 4530, "loss": 1.507, "reward": null, "learning_rate": 4.104754375481664e-05, "epoch": 0.83, "percentage": 27.81, "elapsed_time": "1:36:17", "remaining_time": "4:09:53"}
127
+ {"current_steps": 1270, "total_steps": 4530, "loss": 1.4487, "reward": null, "learning_rate": 4.0914215644280754e-05, "epoch": 0.84, "percentage": 28.04, "elapsed_time": "1:36:58", "remaining_time": "4:08:55"}
128
+ {"current_steps": 1280, "total_steps": 4530, "loss": 1.409, "reward": null, "learning_rate": 4.0780122136597323e-05, "epoch": 0.85, "percentage": 28.26, "elapsed_time": "1:37:42", "remaining_time": "4:08:04"}
129
+ {"current_steps": 1290, "total_steps": 4530, "loss": 1.3994, "reward": null, "learning_rate": 4.064526968101844e-05, "epoch": 0.85, "percentage": 28.48, "elapsed_time": "1:38:23", "remaining_time": "4:07:07"}
130
+ {"current_steps": 1300, "total_steps": 4530, "loss": 1.4285, "reward": null, "learning_rate": 4.050966476329793e-05, "epoch": 0.86, "percentage": 28.7, "elapsed_time": "1:39:06", "remaining_time": "4:06:14"}
131
+ {"current_steps": 1310, "total_steps": 4530, "loss": 1.4562, "reward": null, "learning_rate": 4.037331390537939e-05, "epoch": 0.87, "percentage": 28.92, "elapsed_time": "1:40:10", "remaining_time": "4:06:13"}
132
+ {"current_steps": 1320, "total_steps": 4530, "loss": 1.4202, "reward": null, "learning_rate": 4.023622366508261e-05, "epoch": 0.87, "percentage": 29.14, "elapsed_time": "1:40:53", "remaining_time": "4:05:22"}
133
+ {"current_steps": 1330, "total_steps": 4530, "loss": 1.381, "reward": null, "learning_rate": 4.0098400635788035e-05, "epoch": 0.88, "percentage": 29.36, "elapsed_time": "1:41:37", "remaining_time": "4:04:30"}
134
+ {"current_steps": 1340, "total_steps": 4530, "loss": 1.4656, "reward": null, "learning_rate": 3.99598514461198e-05, "epoch": 0.89, "percentage": 29.58, "elapsed_time": "1:42:16", "remaining_time": "4:03:27"}
135
+ {"current_steps": 1350, "total_steps": 4530, "loss": 1.4094, "reward": null, "learning_rate": 3.9820582759626825e-05, "epoch": 0.89, "percentage": 29.8, "elapsed_time": "1:43:03", "remaining_time": "4:02:45"}
136
+ {"current_steps": 1360, "total_steps": 4530, "loss": 1.4183, "reward": null, "learning_rate": 3.968060127446236e-05, "epoch": 0.9, "percentage": 30.02, "elapsed_time": "1:43:46", "remaining_time": "4:01:53"}
137
+ {"current_steps": 1370, "total_steps": 4530, "loss": 1.411, "reward": null, "learning_rate": 3.953991372306186e-05, "epoch": 0.91, "percentage": 30.24, "elapsed_time": "1:44:29", "remaining_time": "4:01:00"}
138
+ {"current_steps": 1380, "total_steps": 4530, "loss": 1.418, "reward": null, "learning_rate": 3.9398526871819154e-05, "epoch": 0.91, "percentage": 30.46, "elapsed_time": "1:45:13", "remaining_time": "4:00:10"}
139
+ {"current_steps": 1390, "total_steps": 4530, "loss": 1.4751, "reward": null, "learning_rate": 3.925644752076101e-05, "epoch": 0.92, "percentage": 30.68, "elapsed_time": "1:45:55", "remaining_time": "3:59:17"}
140
+ {"current_steps": 1400, "total_steps": 4530, "loss": 1.4246, "reward": null, "learning_rate": 3.911368250322014e-05, "epoch": 0.93, "percentage": 30.91, "elapsed_time": "1:46:39", "remaining_time": "3:58:27"}
141
+ {"current_steps": 1410, "total_steps": 4530, "loss": 1.4102, "reward": null, "learning_rate": 3.897023868550649e-05, "epoch": 0.93, "percentage": 31.13, "elapsed_time": "1:47:40", "remaining_time": "3:58:15"}
142
+ {"current_steps": 1420, "total_steps": 4530, "loss": 1.3871, "reward": null, "learning_rate": 3.882612296657701e-05, "epoch": 0.94, "percentage": 31.35, "elapsed_time": "1:48:23", "remaining_time": "3:57:24"}
143
+ {"current_steps": 1430, "total_steps": 4530, "loss": 1.4156, "reward": null, "learning_rate": 3.8681342277703906e-05, "epoch": 0.95, "percentage": 31.57, "elapsed_time": "1:49:06", "remaining_time": "3:56:32"}
144
+ {"current_steps": 1440, "total_steps": 4530, "loss": 1.433, "reward": null, "learning_rate": 3.853590358214119e-05, "epoch": 0.95, "percentage": 31.79, "elapsed_time": "1:49:49", "remaining_time": "3:55:40"}
145
+ {"current_steps": 1450, "total_steps": 4530, "loss": 1.4372, "reward": null, "learning_rate": 3.8389813874789856e-05, "epoch": 0.96, "percentage": 32.01, "elapsed_time": "1:50:31", "remaining_time": "3:54:46"}
146
+ {"current_steps": 1460, "total_steps": 4530, "loss": 1.3978, "reward": null, "learning_rate": 3.8243080181861435e-05, "epoch": 0.97, "percentage": 32.23, "elapsed_time": "1:51:13", "remaining_time": "3:53:52"}
147
+ {"current_steps": 1470, "total_steps": 4530, "loss": 1.3964, "reward": null, "learning_rate": 3.809570956054004e-05, "epoch": 0.97, "percentage": 32.45, "elapsed_time": "1:51:54", "remaining_time": "3:52:56"}
148
+ {"current_steps": 1480, "total_steps": 4530, "loss": 1.4332, "reward": null, "learning_rate": 3.794770909864298e-05, "epoch": 0.98, "percentage": 32.67, "elapsed_time": "1:52:35", "remaining_time": "3:52:02"}
149
+ {"current_steps": 1490, "total_steps": 4530, "loss": 1.4044, "reward": null, "learning_rate": 3.779908591427988e-05, "epoch": 0.99, "percentage": 32.89, "elapsed_time": "1:53:20", "remaining_time": "3:51:14"}
150
+ {"current_steps": 1500, "total_steps": 4530, "loss": 1.4301, "reward": null, "learning_rate": 3.764984715551032e-05, "epoch": 0.99, "percentage": 33.11, "elapsed_time": "1:54:00", "remaining_time": "3:50:18"}
151
+ {"current_steps": 1510, "total_steps": 4530, "loss": 1.4721, "reward": null, "learning_rate": 3.7500000000000003e-05, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "1:55:04", "remaining_time": "3:50:08"}
152
+ {"current_steps": 1520, "total_steps": 4530, "loss": 1.3905, "reward": null, "learning_rate": 3.734955165467563e-05, "epoch": 1.01, "percentage": 33.55, "elapsed_time": "1:55:47", "remaining_time": "3:49:17"}
153
+ {"current_steps": 1530, "total_steps": 4530, "loss": 1.423, "reward": null, "learning_rate": 3.719850935537821e-05, "epoch": 1.01, "percentage": 33.77, "elapsed_time": "1:56:29", "remaining_time": "3:48:24"}
154
+ {"current_steps": 1540, "total_steps": 4530, "loss": 1.404, "reward": null, "learning_rate": 3.70468803665151e-05, "epoch": 1.02, "percentage": 34.0, "elapsed_time": "1:57:10", "remaining_time": "3:47:30"}
155
+ {"current_steps": 1550, "total_steps": 4530, "loss": 1.4042, "reward": null, "learning_rate": 3.6894671980710574e-05, "epoch": 1.03, "percentage": 34.22, "elapsed_time": "1:57:54", "remaining_time": "3:46:42"}
156
+ {"current_steps": 1560, "total_steps": 4530, "loss": 1.4158, "reward": null, "learning_rate": 3.674189151845515e-05, "epoch": 1.03, "percentage": 34.44, "elapsed_time": "1:58:40", "remaining_time": "3:45:55"}
157
+ {"current_steps": 1570, "total_steps": 4530, "loss": 1.409, "reward": null, "learning_rate": 3.6588546327753425e-05, "epoch": 1.04, "percentage": 34.66, "elapsed_time": "1:59:21", "remaining_time": "3:45:01"}
158
+ {"current_steps": 1580, "total_steps": 4530, "loss": 1.3764, "reward": null, "learning_rate": 3.6434643783770736e-05, "epoch": 1.05, "percentage": 34.88, "elapsed_time": "2:00:04", "remaining_time": "3:44:11"}
159
+ {"current_steps": 1590, "total_steps": 4530, "loss": 1.4021, "reward": null, "learning_rate": 3.6280191288478436e-05, "epoch": 1.05, "percentage": 35.1, "elapsed_time": "2:00:47", "remaining_time": "3:43:20"}
160
+ {"current_steps": 1600, "total_steps": 4530, "loss": 1.3973, "reward": null, "learning_rate": 3.612519627029787e-05, "epoch": 1.06, "percentage": 35.32, "elapsed_time": "2:01:26", "remaining_time": "3:42:22"}
161
+ {"current_steps": 1610, "total_steps": 4530, "loss": 1.3985, "reward": null, "learning_rate": 3.596966618374313e-05, "epoch": 1.07, "percentage": 35.54, "elapsed_time": "2:02:32", "remaining_time": "3:42:14"}
162
+ {"current_steps": 1620, "total_steps": 4530, "loss": 1.3444, "reward": null, "learning_rate": 3.5813608509062526e-05, "epoch": 1.07, "percentage": 35.76, "elapsed_time": "2:03:19", "remaining_time": "3:41:31"}
163
+ {"current_steps": 1630, "total_steps": 4530, "loss": 1.4207, "reward": null, "learning_rate": 3.5657030751878814e-05, "epoch": 1.08, "percentage": 35.98, "elapsed_time": "2:04:00", "remaining_time": "3:40:38"}
164
+ {"current_steps": 1640, "total_steps": 4530, "loss": 1.4304, "reward": null, "learning_rate": 3.5499940442828206e-05, "epoch": 1.09, "percentage": 36.2, "elapsed_time": "2:04:42", "remaining_time": "3:39:46"}
165
+ {"current_steps": 1650, "total_steps": 4530, "loss": 1.3924, "reward": null, "learning_rate": 3.534234513719821e-05, "epoch": 1.09, "percentage": 36.42, "elapsed_time": "2:05:25", "remaining_time": "3:38:54"}
166
+ {"current_steps": 1660, "total_steps": 4530, "loss": 1.3686, "reward": null, "learning_rate": 3.51842524145642e-05, "epoch": 1.1, "percentage": 36.64, "elapsed_time": "2:06:11", "remaining_time": "3:38:09"}
167
+ {"current_steps": 1670, "total_steps": 4530, "loss": 1.4248, "reward": null, "learning_rate": 3.502566987842496e-05, "epoch": 1.11, "percentage": 36.87, "elapsed_time": "2:06:53", "remaining_time": "3:37:18"}
168
+ {"current_steps": 1680, "total_steps": 4530, "loss": 1.3906, "reward": null, "learning_rate": 3.4866605155836915e-05, "epoch": 1.11, "percentage": 37.09, "elapsed_time": "2:07:34", "remaining_time": "3:36:25"}
169
+ {"current_steps": 1690, "total_steps": 4530, "loss": 1.444, "reward": null, "learning_rate": 3.470706589704734e-05, "epoch": 1.12, "percentage": 37.31, "elapsed_time": "2:08:19", "remaining_time": "3:35:37"}
170
+ {"current_steps": 1700, "total_steps": 4530, "loss": 1.3589, "reward": null, "learning_rate": 3.4547059775126445e-05, "epoch": 1.13, "percentage": 37.53, "elapsed_time": "2:09:04", "remaining_time": "3:34:52"}
171
+ {"current_steps": 1710, "total_steps": 4530, "loss": 1.319, "reward": null, "learning_rate": 3.438659448559825e-05, "epoch": 1.13, "percentage": 37.75, "elapsed_time": "2:10:07", "remaining_time": "3:34:34"}
172
+ {"current_steps": 1720, "total_steps": 4530, "loss": 1.406, "reward": null, "learning_rate": 3.422567774607058e-05, "epoch": 1.14, "percentage": 37.97, "elapsed_time": "2:10:50", "remaining_time": "3:33:44"}
173
+ {"current_steps": 1730, "total_steps": 4530, "loss": 1.4114, "reward": null, "learning_rate": 3.406431729586382e-05, "epoch": 1.15, "percentage": 38.19, "elapsed_time": "2:11:33", "remaining_time": "3:32:55"}
174
+ {"current_steps": 1740, "total_steps": 4530, "loss": 1.3722, "reward": null, "learning_rate": 3.390252089563867e-05, "epoch": 1.15, "percentage": 38.41, "elapsed_time": "2:12:16", "remaining_time": "3:32:05"}
175
+ {"current_steps": 1750, "total_steps": 4530, "loss": 1.3528, "reward": null, "learning_rate": 3.3740296327022984e-05, "epoch": 1.16, "percentage": 38.63, "elapsed_time": "2:13:01", "remaining_time": "3:31:19"}
176
+ {"current_steps": 1760, "total_steps": 4530, "loss": 1.4274, "reward": null, "learning_rate": 3.35776513922374e-05, "epoch": 1.17, "percentage": 38.85, "elapsed_time": "2:13:45", "remaining_time": "3:30:31"}
177
+ {"current_steps": 1770, "total_steps": 4530, "loss": 1.4324, "reward": null, "learning_rate": 3.341459391372016e-05, "epoch": 1.17, "percentage": 39.07, "elapsed_time": "2:14:29", "remaining_time": "3:29:43"}
178
+ {"current_steps": 1780, "total_steps": 4530, "loss": 1.409, "reward": null, "learning_rate": 3.32511317337509e-05, "epoch": 1.18, "percentage": 39.29, "elapsed_time": "2:15:10", "remaining_time": "3:28:50"}
179
+ {"current_steps": 1790, "total_steps": 4530, "loss": 1.3464, "reward": null, "learning_rate": 3.30872727140734e-05, "epoch": 1.19, "percentage": 39.51, "elapsed_time": "2:15:55", "remaining_time": "3:28:04"}
180
+ {"current_steps": 1800, "total_steps": 4530, "loss": 1.4144, "reward": null, "learning_rate": 3.292302473551757e-05, "epoch": 1.19, "percentage": 39.74, "elapsed_time": "2:16:40", "remaining_time": "3:27:16"}
181
+ {"current_steps": 1810, "total_steps": 4530, "loss": 1.4139, "reward": null, "learning_rate": 3.2758395697620334e-05, "epoch": 1.2, "percentage": 39.96, "elapsed_time": "2:17:41", "remaining_time": "3:26:55"}
182
+ {"current_steps": 1820, "total_steps": 4530, "loss": 1.4247, "reward": null, "learning_rate": 3.259339351824575e-05, "epoch": 1.2, "percentage": 40.18, "elapsed_time": "2:18:25", "remaining_time": "3:26:06"}
183
+ {"current_steps": 1830, "total_steps": 4530, "loss": 1.4241, "reward": null, "learning_rate": 3.2428026133204184e-05, "epoch": 1.21, "percentage": 40.4, "elapsed_time": "2:19:09", "remaining_time": "3:25:18"}
184
+ {"current_steps": 1840, "total_steps": 4530, "loss": 1.3941, "reward": null, "learning_rate": 3.226230149587063e-05, "epoch": 1.22, "percentage": 40.62, "elapsed_time": "2:19:53", "remaining_time": "3:24:31"}
185
+ {"current_steps": 1850, "total_steps": 4530, "loss": 1.4238, "reward": null, "learning_rate": 3.20962275768022e-05, "epoch": 1.22, "percentage": 40.84, "elapsed_time": "2:20:36", "remaining_time": "3:23:41"}
186
+ {"current_steps": 1860, "total_steps": 4530, "loss": 1.382, "reward": null, "learning_rate": 3.1929812363354766e-05, "epoch": 1.23, "percentage": 41.06, "elapsed_time": "2:21:17", "remaining_time": "3:22:49"}
187
+ {"current_steps": 1870, "total_steps": 4530, "loss": 1.4124, "reward": null, "learning_rate": 3.1763063859298845e-05, "epoch": 1.24, "percentage": 41.28, "elapsed_time": "2:22:00", "remaining_time": "3:22:00"}
188
+ {"current_steps": 1880, "total_steps": 4530, "loss": 1.3963, "reward": null, "learning_rate": 3.159599008443459e-05, "epoch": 1.24, "percentage": 41.5, "elapsed_time": "2:22:44", "remaining_time": "3:21:12"}
189
+ {"current_steps": 1890, "total_steps": 4530, "loss": 1.3542, "reward": null, "learning_rate": 3.142859907420615e-05, "epoch": 1.25, "percentage": 41.72, "elapsed_time": "2:23:27", "remaining_time": "3:20:23"}
190
+ {"current_steps": 1900, "total_steps": 4530, "loss": 1.3852, "reward": null, "learning_rate": 3.126089887931515e-05, "epoch": 1.26, "percentage": 41.94, "elapsed_time": "2:24:09", "remaining_time": "3:19:32"}
191
+ {"current_steps": 1910, "total_steps": 4530, "loss": 1.3972, "reward": null, "learning_rate": 3.109289756533349e-05, "epoch": 1.26, "percentage": 42.16, "elapsed_time": "2:25:13", "remaining_time": "3:19:13"}
192
+ {"current_steps": 1920, "total_steps": 4530, "loss": 1.3783, "reward": null, "learning_rate": 3.092460321231547e-05, "epoch": 1.27, "percentage": 42.38, "elapsed_time": "2:25:55", "remaining_time": "3:18:21"}
193
+ {"current_steps": 1930, "total_steps": 4530, "loss": 1.4122, "reward": null, "learning_rate": 3.075602391440918e-05, "epoch": 1.28, "percentage": 42.6, "elapsed_time": "2:26:40", "remaining_time": "3:17:35"}
194
+ {"current_steps": 1940, "total_steps": 4530, "loss": 1.4105, "reward": null, "learning_rate": 3.058716777946713e-05, "epoch": 1.28, "percentage": 42.83, "elapsed_time": "2:27:26", "remaining_time": "3:16:50"}
195
+ {"current_steps": 1950, "total_steps": 4530, "loss": 1.4091, "reward": null, "learning_rate": 3.0418042928656414e-05, "epoch": 1.29, "percentage": 43.05, "elapsed_time": "2:28:10", "remaining_time": "3:16:03"}
196
+ {"current_steps": 1960, "total_steps": 4530, "loss": 1.4067, "reward": null, "learning_rate": 3.0248657496068027e-05, "epoch": 1.3, "percentage": 43.27, "elapsed_time": "2:28:55", "remaining_time": "3:15:16"}
197
+ {"current_steps": 1970, "total_steps": 4530, "loss": 1.4172, "reward": null, "learning_rate": 3.0079019628325706e-05, "epoch": 1.3, "percentage": 43.49, "elapsed_time": "2:29:36", "remaining_time": "3:14:24"}
198
+ {"current_steps": 1980, "total_steps": 4530, "loss": 1.3803, "reward": null, "learning_rate": 2.990913748419411e-05, "epoch": 1.31, "percentage": 43.71, "elapsed_time": "2:30:19", "remaining_time": "3:13:36"}
199
+ {"current_steps": 1990, "total_steps": 4530, "loss": 1.4096, "reward": null, "learning_rate": 2.97390192341864e-05, "epoch": 1.32, "percentage": 43.93, "elapsed_time": "2:31:03", "remaining_time": "3:12:48"}
200
+ {"current_steps": 2000, "total_steps": 4530, "loss": 1.3774, "reward": null, "learning_rate": 2.9568673060171326e-05, "epoch": 1.32, "percentage": 44.15, "elapsed_time": "2:31:46", "remaining_time": "3:11:59"}
201
+ {"current_steps": 2010, "total_steps": 4530, "loss": 1.3729, "reward": null, "learning_rate": 2.9398107154979638e-05, "epoch": 1.33, "percentage": 44.37, "elapsed_time": "2:32:51", "remaining_time": "3:11:38"}
202
+ {"current_steps": 2020, "total_steps": 4530, "loss": 1.3687, "reward": null, "learning_rate": 2.922732972201014e-05, "epoch": 1.34, "percentage": 44.59, "elapsed_time": "2:33:33", "remaining_time": "3:10:49"}
203
+ {"current_steps": 2030, "total_steps": 4530, "loss": 1.3946, "reward": null, "learning_rate": 2.9056348974835067e-05, "epoch": 1.34, "percentage": 44.81, "elapsed_time": "2:34:17", "remaining_time": "3:10:01"}
204
+ {"current_steps": 2040, "total_steps": 4530, "loss": 1.3922, "reward": null, "learning_rate": 2.8885173136805127e-05, "epoch": 1.35, "percentage": 45.03, "elapsed_time": "2:35:01", "remaining_time": "3:09:12"}
205
+ {"current_steps": 2050, "total_steps": 4530, "loss": 1.3631, "reward": null, "learning_rate": 2.8713810440653926e-05, "epoch": 1.36, "percentage": 45.25, "elapsed_time": "2:35:45", "remaining_time": "3:08:25"}
206
+ {"current_steps": 2060, "total_steps": 4530, "loss": 1.4193, "reward": null, "learning_rate": 2.8542269128102063e-05, "epoch": 1.36, "percentage": 45.47, "elapsed_time": "2:36:29", "remaining_time": "3:07:37"}
207
+ {"current_steps": 2070, "total_steps": 4530, "loss": 1.3776, "reward": null, "learning_rate": 2.837055744946072e-05, "epoch": 1.37, "percentage": 45.7, "elapsed_time": "2:37:14", "remaining_time": "3:06:51"}
208
+ {"current_steps": 2080, "total_steps": 4530, "loss": 1.4099, "reward": null, "learning_rate": 2.819868366323488e-05, "epoch": 1.38, "percentage": 45.92, "elapsed_time": "2:37:56", "remaining_time": "3:06:02"}
209
+ {"current_steps": 2090, "total_steps": 4530, "loss": 1.41, "reward": null, "learning_rate": 2.8026656035726095e-05, "epoch": 1.38, "percentage": 46.14, "elapsed_time": "2:38:40", "remaining_time": "3:05:14"}
210
+ {"current_steps": 2100, "total_steps": 4530, "loss": 1.4604, "reward": null, "learning_rate": 2.7854482840634965e-05, "epoch": 1.39, "percentage": 46.36, "elapsed_time": "2:39:21", "remaining_time": "3:04:24"}
211
+ {"current_steps": 2110, "total_steps": 4530, "loss": 1.4485, "reward": null, "learning_rate": 2.7682172358663173e-05, "epoch": 1.4, "percentage": 46.58, "elapsed_time": "2:40:23", "remaining_time": "3:03:57"}
212
+ {"current_steps": 2120, "total_steps": 4530, "loss": 1.4445, "reward": null, "learning_rate": 2.7509732877115257e-05, "epoch": 1.4, "percentage": 46.8, "elapsed_time": "2:41:06", "remaining_time": "3:03:08"}
213
+ {"current_steps": 2130, "total_steps": 4530, "loss": 1.3889, "reward": null, "learning_rate": 2.73371726895e-05, "epoch": 1.41, "percentage": 47.02, "elapsed_time": "2:41:49", "remaining_time": "3:02:20"}
214
+ {"current_steps": 2140, "total_steps": 4530, "loss": 1.4167, "reward": null, "learning_rate": 2.716450009513158e-05, "epoch": 1.42, "percentage": 47.24, "elapsed_time": "2:42:32", "remaining_time": "3:01:31"}
215
+ {"current_steps": 2150, "total_steps": 4530, "loss": 1.3388, "reward": null, "learning_rate": 2.6991723398730383e-05, "epoch": 1.42, "percentage": 47.46, "elapsed_time": "2:43:16", "remaining_time": "3:00:44"}
216
+ {"current_steps": 2160, "total_steps": 4530, "loss": 1.4379, "reward": null, "learning_rate": 2.68188509100236e-05, "epoch": 1.43, "percentage": 47.68, "elapsed_time": "2:44:01", "remaining_time": "2:59:57"}
217
+ {"current_steps": 2170, "total_steps": 4530, "loss": 1.4119, "reward": null, "learning_rate": 2.6645890943345585e-05, "epoch": 1.44, "percentage": 47.9, "elapsed_time": "2:44:44", "remaining_time": "2:59:09"}
218
+ {"current_steps": 2180, "total_steps": 4530, "loss": 1.3961, "reward": null, "learning_rate": 2.6472851817237948e-05, "epoch": 1.44, "percentage": 48.12, "elapsed_time": "2:45:29", "remaining_time": "2:58:23"}
219
+ {"current_steps": 2190, "total_steps": 4530, "loss": 1.3999, "reward": null, "learning_rate": 2.6299741854049508e-05, "epoch": 1.45, "percentage": 48.34, "elapsed_time": "2:46:10", "remaining_time": "2:57:33"}
220
+ {"current_steps": 2200, "total_steps": 4530, "loss": 1.3739, "reward": null, "learning_rate": 2.6126569379535985e-05, "epoch": 1.46, "percentage": 48.57, "elapsed_time": "2:46:53", "remaining_time": "2:56:45"}
221
+ {"current_steps": 2210, "total_steps": 4530, "loss": 1.4256, "reward": null, "learning_rate": 2.5953342722459594e-05, "epoch": 1.46, "percentage": 48.79, "elapsed_time": "2:47:53", "remaining_time": "2:56:14"}
222
+ {"current_steps": 2220, "total_steps": 4530, "loss": 1.4615, "reward": null, "learning_rate": 2.5780070214188478e-05, "epoch": 1.47, "percentage": 49.01, "elapsed_time": "2:48:38", "remaining_time": "2:55:28"}
223
+ {"current_steps": 2230, "total_steps": 4530, "loss": 1.3877, "reward": null, "learning_rate": 2.5606760188296004e-05, "epoch": 1.48, "percentage": 49.23, "elapsed_time": "2:49:20", "remaining_time": "2:54:38"}
224
+ {"current_steps": 2240, "total_steps": 4530, "loss": 1.3752, "reward": null, "learning_rate": 2.5433420980159944e-05, "epoch": 1.48, "percentage": 49.45, "elapsed_time": "2:50:03", "remaining_time": "2:53:50"}
225
+ {"current_steps": 2250, "total_steps": 4530, "loss": 1.4084, "reward": null, "learning_rate": 2.526006092656161e-05, "epoch": 1.49, "percentage": 49.67, "elapsed_time": "2:50:45", "remaining_time": "2:53:01"}
226
+ {"current_steps": 2260, "total_steps": 4530, "loss": 1.3921, "reward": null, "learning_rate": 2.508668836528486e-05, "epoch": 1.5, "percentage": 49.89, "elapsed_time": "2:51:29", "remaining_time": "2:52:14"}
227
+ {"current_steps": 2270, "total_steps": 4530, "loss": 1.4104, "reward": null, "learning_rate": 2.491331163471514e-05, "epoch": 1.5, "percentage": 50.11, "elapsed_time": "2:52:13", "remaining_time": "2:51:28"}
228
+ {"current_steps": 2280, "total_steps": 4530, "loss": 1.4053, "reward": null, "learning_rate": 2.4739939073438397e-05, "epoch": 1.51, "percentage": 50.33, "elapsed_time": "2:52:59", "remaining_time": "2:50:42"}
229
+ {"current_steps": 2290, "total_steps": 4530, "loss": 1.381, "reward": null, "learning_rate": 2.456657901984006e-05, "epoch": 1.52, "percentage": 50.55, "elapsed_time": "2:53:45", "remaining_time": "2:49:57"}
230
+ {"current_steps": 2300, "total_steps": 4530, "loss": 1.3752, "reward": null, "learning_rate": 2.4393239811704e-05, "epoch": 1.52, "percentage": 50.77, "elapsed_time": "2:54:29", "remaining_time": "2:49:10"}
231
+ {"current_steps": 2310, "total_steps": 4530, "loss": 1.4023, "reward": null, "learning_rate": 2.4219929785811518e-05, "epoch": 1.53, "percentage": 50.99, "elapsed_time": "2:55:31", "remaining_time": "2:48:41"}
232
+ {"current_steps": 2320, "total_steps": 4530, "loss": 1.3642, "reward": null, "learning_rate": 2.4046657277540412e-05, "epoch": 1.54, "percentage": 51.21, "elapsed_time": "2:56:16", "remaining_time": "2:47:55"}
233
+ {"current_steps": 2330, "total_steps": 4530, "loss": 1.3977, "reward": null, "learning_rate": 2.3873430620464024e-05, "epoch": 1.54, "percentage": 51.43, "elapsed_time": "2:57:01", "remaining_time": "2:47:09"}
234
+ {"current_steps": 2340, "total_steps": 4530, "loss": 1.3905, "reward": null, "learning_rate": 2.3700258145950495e-05, "epoch": 1.55, "percentage": 51.66, "elapsed_time": "2:57:45", "remaining_time": "2:46:22"}
235
+ {"current_steps": 2350, "total_steps": 4530, "loss": 1.4022, "reward": null, "learning_rate": 2.3527148182762054e-05, "epoch": 1.56, "percentage": 51.88, "elapsed_time": "2:58:29", "remaining_time": "2:45:34"}
236
+ {"current_steps": 2360, "total_steps": 4530, "loss": 1.4162, "reward": null, "learning_rate": 2.335410905665442e-05, "epoch": 1.56, "percentage": 52.1, "elapsed_time": "2:59:10", "remaining_time": "2:44:45"}
237
+ {"current_steps": 2370, "total_steps": 4530, "loss": 1.3877, "reward": null, "learning_rate": 2.3181149089976405e-05, "epoch": 1.57, "percentage": 52.32, "elapsed_time": "2:59:55", "remaining_time": "2:43:58"}
238
+ {"current_steps": 2380, "total_steps": 4530, "loss": 1.3704, "reward": null, "learning_rate": 2.3008276601269623e-05, "epoch": 1.58, "percentage": 52.54, "elapsed_time": "3:00:41", "remaining_time": "2:43:14"}
239
+ {"current_steps": 2390, "total_steps": 4530, "loss": 1.3725, "reward": null, "learning_rate": 2.283549990486842e-05, "epoch": 1.58, "percentage": 52.76, "elapsed_time": "3:01:26", "remaining_time": "2:42:28"}
240
+ {"current_steps": 2400, "total_steps": 4530, "loss": 1.4232, "reward": null, "learning_rate": 2.2662827310499995e-05, "epoch": 1.59, "percentage": 52.98, "elapsed_time": "3:02:10", "remaining_time": "2:41:41"}
241
+ {"current_steps": 2410, "total_steps": 4530, "loss": 1.3916, "reward": null, "learning_rate": 2.249026712288474e-05, "epoch": 1.6, "percentage": 53.2, "elapsed_time": "3:03:15", "remaining_time": "2:41:12"}
242
+ {"current_steps": 2420, "total_steps": 4530, "loss": 1.384, "reward": null, "learning_rate": 2.2317827641336833e-05, "epoch": 1.6, "percentage": 53.42, "elapsed_time": "3:03:59", "remaining_time": "2:40:25"}
243
+ {"current_steps": 2430, "total_steps": 4530, "loss": 1.3969, "reward": null, "learning_rate": 2.2145517159365044e-05, "epoch": 1.61, "percentage": 53.64, "elapsed_time": "3:04:44", "remaining_time": "2:39:39"}
244
+ {"current_steps": 2440, "total_steps": 4530, "loss": 1.3742, "reward": null, "learning_rate": 2.197334396427391e-05, "epoch": 1.62, "percentage": 53.86, "elapsed_time": "3:05:26", "remaining_time": "2:38:50"}
245
+ {"current_steps": 2450, "total_steps": 4530, "loss": 1.3901, "reward": null, "learning_rate": 2.1801316336765126e-05, "epoch": 1.62, "percentage": 54.08, "elapsed_time": "3:06:08", "remaining_time": "2:38:02"}
246
+ {"current_steps": 2460, "total_steps": 4530, "loss": 1.3853, "reward": null, "learning_rate": 2.162944255053928e-05, "epoch": 1.63, "percentage": 54.3, "elapsed_time": "3:06:52", "remaining_time": "2:37:14"}
247
+ {"current_steps": 2470, "total_steps": 4530, "loss": 1.3709, "reward": null, "learning_rate": 2.145773087189794e-05, "epoch": 1.64, "percentage": 54.53, "elapsed_time": "3:07:36", "remaining_time": "2:36:27"}
248
+ {"current_steps": 2480, "total_steps": 4530, "loss": 1.3758, "reward": null, "learning_rate": 2.128618955934608e-05, "epoch": 1.64, "percentage": 54.75, "elapsed_time": "3:08:19", "remaining_time": "2:35:40"}
249
+ {"current_steps": 2490, "total_steps": 4530, "loss": 1.3561, "reward": null, "learning_rate": 2.1114826863194882e-05, "epoch": 1.65, "percentage": 54.97, "elapsed_time": "3:09:04", "remaining_time": "2:34:54"}
250
+ {"current_steps": 2500, "total_steps": 4530, "loss": 1.3774, "reward": null, "learning_rate": 2.0943651025164932e-05, "epoch": 1.66, "percentage": 55.19, "elapsed_time": "3:09:48", "remaining_time": "2:34:07"}
251
+ {"current_steps": 2510, "total_steps": 4530, "loss": 1.3961, "reward": null, "learning_rate": 2.0772670277989864e-05, "epoch": 1.66, "percentage": 55.41, "elapsed_time": "3:10:52", "remaining_time": "2:33:36"}
252
+ {"current_steps": 2520, "total_steps": 4530, "loss": 1.3794, "reward": null, "learning_rate": 2.060189284502037e-05, "epoch": 1.67, "percentage": 55.63, "elapsed_time": "3:11:35", "remaining_time": "2:32:49"}
253
+ {"current_steps": 2530, "total_steps": 4530, "loss": 1.4147, "reward": null, "learning_rate": 2.0431326939828686e-05, "epoch": 1.68, "percentage": 55.85, "elapsed_time": "3:12:17", "remaining_time": "2:32:00"}
254
+ {"current_steps": 2540, "total_steps": 4530, "loss": 1.4336, "reward": null, "learning_rate": 2.0260980765813604e-05, "epoch": 1.68, "percentage": 56.07, "elapsed_time": "3:13:00", "remaining_time": "2:31:13"}
255
+ {"current_steps": 2550, "total_steps": 4530, "loss": 1.4228, "reward": null, "learning_rate": 2.0090862515805898e-05, "epoch": 1.69, "percentage": 56.29, "elapsed_time": "3:13:45", "remaining_time": "2:30:26"}
256
+ {"current_steps": 2560, "total_steps": 4530, "loss": 1.4188, "reward": null, "learning_rate": 1.99209803716743e-05, "epoch": 1.69, "percentage": 56.51, "elapsed_time": "3:14:26", "remaining_time": "2:29:37"}
257
+ {"current_steps": 2570, "total_steps": 4530, "loss": 1.4492, "reward": null, "learning_rate": 1.975134250393198e-05, "epoch": 1.7, "percentage": 56.73, "elapsed_time": "3:15:10", "remaining_time": "2:28:50"}
258
+ {"current_steps": 2580, "total_steps": 4530, "loss": 1.4492, "reward": null, "learning_rate": 1.9581957071343592e-05, "epoch": 1.71, "percentage": 56.95, "elapsed_time": "3:15:51", "remaining_time": "2:28:02"}
259
+ {"current_steps": 2590, "total_steps": 4530, "loss": 1.4261, "reward": null, "learning_rate": 1.9412832220532867e-05, "epoch": 1.71, "percentage": 57.17, "elapsed_time": "3:16:32", "remaining_time": "2:27:13"}
260
+ {"current_steps": 2600, "total_steps": 4530, "loss": 1.412, "reward": null, "learning_rate": 1.9243976085590824e-05, "epoch": 1.72, "percentage": 57.4, "elapsed_time": "3:17:14", "remaining_time": "2:26:25"}
261
+ {"current_steps": 2610, "total_steps": 4530, "loss": 1.3858, "reward": null, "learning_rate": 1.9075396787684533e-05, "epoch": 1.73, "percentage": 57.62, "elapsed_time": "3:18:17", "remaining_time": "2:25:51"}
262
+ {"current_steps": 2620, "total_steps": 4530, "loss": 1.3648, "reward": null, "learning_rate": 1.8907102434666523e-05, "epoch": 1.73, "percentage": 57.84, "elapsed_time": "3:19:00", "remaining_time": "2:25:04"}
263
+ {"current_steps": 2630, "total_steps": 4530, "loss": 1.4267, "reward": null, "learning_rate": 1.8739101120684866e-05, "epoch": 1.74, "percentage": 58.06, "elapsed_time": "3:19:40", "remaining_time": "2:24:15"}
264
+ {"current_steps": 2640, "total_steps": 4530, "loss": 1.4115, "reward": null, "learning_rate": 1.8571400925793855e-05, "epoch": 1.75, "percentage": 58.28, "elapsed_time": "3:20:23", "remaining_time": "2:23:27"}
265
+ {"current_steps": 2650, "total_steps": 4530, "loss": 1.3767, "reward": null, "learning_rate": 1.840400991556541e-05, "epoch": 1.75, "percentage": 58.5, "elapsed_time": "3:21:07", "remaining_time": "2:22:41"}
266
+ {"current_steps": 2660, "total_steps": 4530, "loss": 1.3934, "reward": null, "learning_rate": 1.8236936140701165e-05, "epoch": 1.76, "percentage": 58.72, "elapsed_time": "3:21:53", "remaining_time": "2:21:56"}
267
+ {"current_steps": 2670, "total_steps": 4530, "loss": 1.368, "reward": null, "learning_rate": 1.807018763664524e-05, "epoch": 1.77, "percentage": 58.94, "elapsed_time": "3:22:39", "remaining_time": "2:21:10"}
268
+ {"current_steps": 2680, "total_steps": 4530, "loss": 1.3925, "reward": null, "learning_rate": 1.7903772423197806e-05, "epoch": 1.77, "percentage": 59.16, "elapsed_time": "3:23:20", "remaining_time": "2:20:22"}
269
+ {"current_steps": 2690, "total_steps": 4530, "loss": 1.3786, "reward": null, "learning_rate": 1.773769850412937e-05, "epoch": 1.78, "percentage": 59.38, "elapsed_time": "3:24:04", "remaining_time": "2:19:35"}
270
+ {"current_steps": 2700, "total_steps": 4530, "loss": 1.4204, "reward": null, "learning_rate": 1.7571973866795815e-05, "epoch": 1.79, "percentage": 59.6, "elapsed_time": "3:24:46", "remaining_time": "2:18:47"}
271
+ {"current_steps": 2710, "total_steps": 4530, "loss": 1.3907, "reward": null, "learning_rate": 1.7406606481754258e-05, "epoch": 1.79, "percentage": 59.82, "elapsed_time": "3:25:52", "remaining_time": "2:18:15"}
272
+ {"current_steps": 2720, "total_steps": 4530, "loss": 1.3598, "reward": null, "learning_rate": 1.724160430237967e-05, "epoch": 1.8, "percentage": 60.04, "elapsed_time": "3:26:39", "remaining_time": "2:17:31"}
273
+ {"current_steps": 2730, "total_steps": 4530, "loss": 1.4157, "reward": null, "learning_rate": 1.7076975264482434e-05, "epoch": 1.81, "percentage": 60.26, "elapsed_time": "3:27:20", "remaining_time": "2:16:42"}
274
+ {"current_steps": 2740, "total_steps": 4530, "loss": 1.3922, "reward": null, "learning_rate": 1.6912727285926605e-05, "epoch": 1.81, "percentage": 60.49, "elapsed_time": "3:28:04", "remaining_time": "2:15:55"}
275
+ {"current_steps": 2750, "total_steps": 4530, "loss": 1.4413, "reward": null, "learning_rate": 1.6748868266249114e-05, "epoch": 1.82, "percentage": 60.71, "elapsed_time": "3:28:47", "remaining_time": "2:15:08"}
276
+ {"current_steps": 2760, "total_steps": 4530, "loss": 1.4219, "reward": null, "learning_rate": 1.658540608627985e-05, "epoch": 1.83, "percentage": 60.93, "elapsed_time": "3:29:30", "remaining_time": "2:14:21"}
277
+ {"current_steps": 2770, "total_steps": 4530, "loss": 1.3447, "reward": null, "learning_rate": 1.642234860776261e-05, "epoch": 1.83, "percentage": 61.15, "elapsed_time": "3:30:13", "remaining_time": "2:13:34"}
278
+ {"current_steps": 2780, "total_steps": 4530, "loss": 1.4383, "reward": null, "learning_rate": 1.6259703672977022e-05, "epoch": 1.84, "percentage": 61.37, "elapsed_time": "3:30:55", "remaining_time": "2:12:46"}
279
+ {"current_steps": 2790, "total_steps": 4530, "loss": 1.3562, "reward": null, "learning_rate": 1.6097479104361326e-05, "epoch": 1.85, "percentage": 61.59, "elapsed_time": "3:31:39", "remaining_time": "2:12:00"}
280
+ {"current_steps": 2800, "total_steps": 4530, "loss": 1.3865, "reward": null, "learning_rate": 1.5935682704136183e-05, "epoch": 1.85, "percentage": 61.81, "elapsed_time": "3:32:23", "remaining_time": "2:11:13"}
281
+ {"current_steps": 2810, "total_steps": 4530, "loss": 1.3875, "reward": null, "learning_rate": 1.5774322253929425e-05, "epoch": 1.86, "percentage": 62.03, "elapsed_time": "3:33:27", "remaining_time": "2:10:39"}
282
+ {"current_steps": 2820, "total_steps": 4530, "loss": 1.4282, "reward": null, "learning_rate": 1.561340551440176e-05, "epoch": 1.87, "percentage": 62.25, "elapsed_time": "3:34:09", "remaining_time": "2:09:51"}
283
+ {"current_steps": 2830, "total_steps": 4530, "loss": 1.401, "reward": null, "learning_rate": 1.5452940224873568e-05, "epoch": 1.87, "percentage": 62.47, "elapsed_time": "3:34:51", "remaining_time": "2:09:04"}
284
+ {"current_steps": 2840, "total_steps": 4530, "loss": 1.3645, "reward": null, "learning_rate": 1.529293410295266e-05, "epoch": 1.88, "percentage": 62.69, "elapsed_time": "3:35:37", "remaining_time": "2:08:18"}
285
+ {"current_steps": 2850, "total_steps": 4530, "loss": 1.3877, "reward": null, "learning_rate": 1.5133394844163093e-05, "epoch": 1.89, "percentage": 62.91, "elapsed_time": "3:36:19", "remaining_time": "2:07:30"}
286
+ {"current_steps": 2860, "total_steps": 4530, "loss": 1.4026, "reward": null, "learning_rate": 1.4974330121575048e-05, "epoch": 1.89, "percentage": 63.13, "elapsed_time": "3:37:03", "remaining_time": "2:06:44"}
287
+ {"current_steps": 2870, "total_steps": 4530, "loss": 1.4235, "reward": null, "learning_rate": 1.4815747585435801e-05, "epoch": 1.9, "percentage": 63.36, "elapsed_time": "3:37:42", "remaining_time": "2:05:55"}
288
+ {"current_steps": 2880, "total_steps": 4530, "loss": 1.3623, "reward": null, "learning_rate": 1.4657654862801798e-05, "epoch": 1.91, "percentage": 63.58, "elapsed_time": "3:38:23", "remaining_time": "2:05:07"}
289
+ {"current_steps": 2890, "total_steps": 4530, "loss": 1.3823, "reward": null, "learning_rate": 1.4500059557171791e-05, "epoch": 1.91, "percentage": 63.8, "elapsed_time": "3:39:07", "remaining_time": "2:04:20"}
290
+ {"current_steps": 2900, "total_steps": 4530, "loss": 1.3717, "reward": null, "learning_rate": 1.4342969248121185e-05, "epoch": 1.92, "percentage": 64.02, "elapsed_time": "3:39:51", "remaining_time": "2:03:34"}
291
+ {"current_steps": 2910, "total_steps": 4530, "loss": 1.434, "reward": null, "learning_rate": 1.4186391490937481e-05, "epoch": 1.93, "percentage": 64.24, "elapsed_time": "3:40:52", "remaining_time": "2:02:57"}
292
+ {"current_steps": 2920, "total_steps": 4530, "loss": 1.3688, "reward": null, "learning_rate": 1.403033381625688e-05, "epoch": 1.93, "percentage": 64.46, "elapsed_time": "3:41:34", "remaining_time": "2:02:10"}
293
+ {"current_steps": 2930, "total_steps": 4530, "loss": 1.3404, "reward": null, "learning_rate": 1.3874803729702141e-05, "epoch": 1.94, "percentage": 64.68, "elapsed_time": "3:42:21", "remaining_time": "2:01:25"}
294
+ {"current_steps": 2940, "total_steps": 4530, "loss": 1.3956, "reward": null, "learning_rate": 1.3719808711521573e-05, "epoch": 1.95, "percentage": 64.9, "elapsed_time": "3:43:04", "remaining_time": "2:00:38"}
295
+ {"current_steps": 2950, "total_steps": 4530, "loss": 1.366, "reward": null, "learning_rate": 1.3565356216229268e-05, "epoch": 1.95, "percentage": 65.12, "elapsed_time": "3:43:50", "remaining_time": "1:59:53"}
296
+ {"current_steps": 2960, "total_steps": 4530, "loss": 1.4425, "reward": null, "learning_rate": 1.341145367224657e-05, "epoch": 1.96, "percentage": 65.34, "elapsed_time": "3:44:32", "remaining_time": "1:59:06"}
297
+ {"current_steps": 2970, "total_steps": 4530, "loss": 1.3728, "reward": null, "learning_rate": 1.3258108481544849e-05, "epoch": 1.97, "percentage": 65.56, "elapsed_time": "3:45:17", "remaining_time": "1:58:20"}
298
+ {"current_steps": 2980, "total_steps": 4530, "loss": 1.4581, "reward": null, "learning_rate": 1.310532801928942e-05, "epoch": 1.97, "percentage": 65.78, "elapsed_time": "3:45:59", "remaining_time": "1:57:32"}
299
+ {"current_steps": 2990, "total_steps": 4530, "loss": 1.3678, "reward": null, "learning_rate": 1.2953119633484903e-05, "epoch": 1.98, "percentage": 66.0, "elapsed_time": "3:46:42", "remaining_time": "1:56:46"}
300
+ {"current_steps": 3000, "total_steps": 4530, "loss": 1.4091, "reward": null, "learning_rate": 1.2801490644621789e-05, "epoch": 1.99, "percentage": 66.23, "elapsed_time": "3:47:26", "remaining_time": "1:55:59"}
301
+ {"current_steps": 3010, "total_steps": 4530, "loss": 1.3642, "reward": null, "learning_rate": 1.2650448345324384e-05, "epoch": 1.99, "percentage": 66.45, "elapsed_time": "3:48:27", "remaining_time": "1:55:21"}
302
+ {"current_steps": 3020, "total_steps": 4530, "loss": 1.3949, "reward": null, "learning_rate": 1.2500000000000006e-05, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "3:49:12", "remaining_time": "1:54:36"}
303
+ {"current_steps": 3030, "total_steps": 4530, "loss": 1.3507, "reward": null, "learning_rate": 1.235015284448969e-05, "epoch": 2.01, "percentage": 66.89, "elapsed_time": "3:49:55", "remaining_time": "1:53:49"}
304
+ {"current_steps": 3040, "total_steps": 4530, "loss": 1.3553, "reward": null, "learning_rate": 1.2200914085720119e-05, "epoch": 2.01, "percentage": 67.11, "elapsed_time": "3:50:39", "remaining_time": "1:53:03"}
305
+ {"current_steps": 3050, "total_steps": 4530, "loss": 1.4108, "reward": null, "learning_rate": 1.2052290901357025e-05, "epoch": 2.02, "percentage": 67.33, "elapsed_time": "3:51:21", "remaining_time": "1:52:16"}
306
+ {"current_steps": 3060, "total_steps": 4530, "loss": 1.3549, "reward": null, "learning_rate": 1.1904290439459973e-05, "epoch": 2.03, "percentage": 67.55, "elapsed_time": "3:52:05", "remaining_time": "1:51:29"}
307
+ {"current_steps": 3070, "total_steps": 4530, "loss": 1.3371, "reward": null, "learning_rate": 1.175691981813858e-05, "epoch": 2.03, "percentage": 67.77, "elapsed_time": "3:52:51", "remaining_time": "1:50:44"}
308
+ {"current_steps": 3080, "total_steps": 4530, "loss": 1.3775, "reward": null, "learning_rate": 1.1610186125210151e-05, "epoch": 2.04, "percentage": 67.99, "elapsed_time": "3:53:33", "remaining_time": "1:49:57"}
309
+ {"current_steps": 3090, "total_steps": 4530, "loss": 1.3884, "reward": null, "learning_rate": 1.1464096417858822e-05, "epoch": 2.05, "percentage": 68.21, "elapsed_time": "3:54:18", "remaining_time": "1:49:11"}
310
+ {"current_steps": 3100, "total_steps": 4530, "loss": 1.3516, "reward": null, "learning_rate": 1.1318657722296097e-05, "epoch": 2.05, "percentage": 68.43, "elapsed_time": "3:54:59", "remaining_time": "1:48:24"}
311
+ {"current_steps": 3110, "total_steps": 4530, "loss": 1.405, "reward": null, "learning_rate": 1.1173877033422994e-05, "epoch": 2.06, "percentage": 68.65, "elapsed_time": "3:56:02", "remaining_time": "1:47:46"}
312
+ {"current_steps": 3120, "total_steps": 4530, "loss": 1.3909, "reward": null, "learning_rate": 1.102976131449352e-05, "epoch": 2.07, "percentage": 68.87, "elapsed_time": "3:56:44", "remaining_time": "1:46:59"}
313
+ {"current_steps": 3130, "total_steps": 4530, "loss": 1.4057, "reward": null, "learning_rate": 1.0886317496779863e-05, "epoch": 2.07, "percentage": 69.09, "elapsed_time": "3:57:27", "remaining_time": "1:46:12"}
314
+ {"current_steps": 3140, "total_steps": 4530, "loss": 1.3807, "reward": null, "learning_rate": 1.0743552479238994e-05, "epoch": 2.08, "percentage": 69.32, "elapsed_time": "3:58:11", "remaining_time": "1:45:26"}
315
+ {"current_steps": 3150, "total_steps": 4530, "loss": 1.3804, "reward": null, "learning_rate": 1.0601473128180855e-05, "epoch": 2.09, "percentage": 69.54, "elapsed_time": "3:58:55", "remaining_time": "1:44:40"}
316
+ {"current_steps": 3160, "total_steps": 4530, "loss": 1.3368, "reward": null, "learning_rate": 1.0460086276938144e-05, "epoch": 2.09, "percentage": 69.76, "elapsed_time": "3:59:38", "remaining_time": "1:43:53"}
317
+ {"current_steps": 3170, "total_steps": 4530, "loss": 1.3465, "reward": null, "learning_rate": 1.0319398725537644e-05, "epoch": 2.1, "percentage": 69.98, "elapsed_time": "4:00:22", "remaining_time": "1:43:07"}
318
+ {"current_steps": 3180, "total_steps": 4530, "loss": 1.3716, "reward": null, "learning_rate": 1.0179417240373183e-05, "epoch": 2.11, "percentage": 70.2, "elapsed_time": "4:01:04", "remaining_time": "1:42:20"}
319
+ {"current_steps": 3190, "total_steps": 4530, "loss": 1.3833, "reward": null, "learning_rate": 1.0040148553880205e-05, "epoch": 2.11, "percentage": 70.42, "elapsed_time": "4:01:47", "remaining_time": "1:41:33"}
320
+ {"current_steps": 3200, "total_steps": 4530, "loss": 1.3893, "reward": null, "learning_rate": 9.90159936421197e-06, "epoch": 2.12, "percentage": 70.64, "elapsed_time": "4:02:29", "remaining_time": "1:40:47"}
321
+ {"current_steps": 3210, "total_steps": 4530, "loss": 1.4088, "reward": null, "learning_rate": 9.763776334917399e-06, "epoch": 2.13, "percentage": 70.86, "elapsed_time": "4:03:32", "remaining_time": "1:40:08"}
322
+ {"current_steps": 3220, "total_steps": 4530, "loss": 1.402, "reward": null, "learning_rate": 9.626686094620608e-06, "epoch": 2.13, "percentage": 71.08, "elapsed_time": "4:04:14", "remaining_time": "1:39:21"}
323
+ {"current_steps": 3230, "total_steps": 4530, "loss": 1.3151, "reward": null, "learning_rate": 9.490335236702075e-06, "epoch": 2.14, "percentage": 71.3, "elapsed_time": "4:04:57", "remaining_time": "1:38:35"}
324
+ {"current_steps": 3240, "total_steps": 4530, "loss": 1.4126, "reward": null, "learning_rate": 9.354730318981562e-06, "epoch": 2.15, "percentage": 71.52, "elapsed_time": "4:05:40", "remaining_time": "1:37:48"}
325
+ {"current_steps": 3250, "total_steps": 4530, "loss": 1.431, "reward": null, "learning_rate": 9.219877863402682e-06, "epoch": 2.15, "percentage": 71.74, "elapsed_time": "4:06:23", "remaining_time": "1:37:02"}
326
+ {"current_steps": 3260, "total_steps": 4530, "loss": 1.3843, "reward": null, "learning_rate": 9.085784355719257e-06, "epoch": 2.16, "percentage": 71.96, "elapsed_time": "4:07:06", "remaining_time": "1:36:15"}
327
+ {"current_steps": 3270, "total_steps": 4530, "loss": 1.3513, "reward": null, "learning_rate": 8.95245624518336e-06, "epoch": 2.17, "percentage": 72.19, "elapsed_time": "4:07:51", "remaining_time": "1:35:30"}
328
+ {"current_steps": 3280, "total_steps": 4530, "loss": 1.362, "reward": null, "learning_rate": 8.819899944235152e-06, "epoch": 2.17, "percentage": 72.41, "elapsed_time": "4:08:35", "remaining_time": "1:34:44"}
329
+ {"current_steps": 3290, "total_steps": 4530, "loss": 1.3979, "reward": null, "learning_rate": 8.688121828194462e-06, "epoch": 2.18, "percentage": 72.63, "elapsed_time": "4:09:17", "remaining_time": "1:33:57"}
330
+ {"current_steps": 3300, "total_steps": 4530, "loss": 1.3949, "reward": null, "learning_rate": 8.55712823495419e-06, "epoch": 2.18, "percentage": 72.85, "elapsed_time": "4:10:01", "remaining_time": "1:33:11"}
331
+ {"current_steps": 3310, "total_steps": 4530, "loss": 1.3912, "reward": null, "learning_rate": 8.426925464675433e-06, "epoch": 2.19, "percentage": 73.07, "elapsed_time": "4:11:04", "remaining_time": "1:32:32"}
332
+ {"current_steps": 3320, "total_steps": 4530, "loss": 1.35, "reward": null, "learning_rate": 8.297519779484541e-06, "epoch": 2.2, "percentage": 73.29, "elapsed_time": "4:11:47", "remaining_time": "1:31:45"}
333
+ {"current_steps": 3330, "total_steps": 4530, "loss": 1.3528, "reward": null, "learning_rate": 8.168917403171891e-06, "epoch": 2.2, "percentage": 73.51, "elapsed_time": "4:12:33", "remaining_time": "1:31:00"}
334
+ {"current_steps": 3340, "total_steps": 4530, "loss": 1.3743, "reward": null, "learning_rate": 8.041124520892598e-06, "epoch": 2.21, "percentage": 73.73, "elapsed_time": "4:13:19", "remaining_time": "1:30:15"}
335
+ {"current_steps": 3350, "total_steps": 4530, "loss": 1.3708, "reward": null, "learning_rate": 7.91414727886898e-06, "epoch": 2.22, "percentage": 73.95, "elapsed_time": "4:14:05", "remaining_time": "1:29:30"}
336
+ {"current_steps": 3360, "total_steps": 4530, "loss": 1.4525, "reward": null, "learning_rate": 7.787991784095e-06, "epoch": 2.22, "percentage": 74.17, "elapsed_time": "4:14:46", "remaining_time": "1:28:43"}
337
+ {"current_steps": 3370, "total_steps": 4530, "loss": 1.3708, "reward": null, "learning_rate": 7.662664104042538e-06, "epoch": 2.23, "percentage": 74.39, "elapsed_time": "4:15:29", "remaining_time": "1:27:56"}
338
+ {"current_steps": 3380, "total_steps": 4530, "loss": 1.3871, "reward": null, "learning_rate": 7.538170266369563e-06, "epoch": 2.24, "percentage": 74.61, "elapsed_time": "4:16:13", "remaining_time": "1:27:10"}
339
+ {"current_steps": 3390, "total_steps": 4530, "loss": 1.3853, "reward": null, "learning_rate": 7.414516258630244e-06, "epoch": 2.24, "percentage": 74.83, "elapsed_time": "4:16:55", "remaining_time": "1:26:24"}
340
+ {"current_steps": 3400, "total_steps": 4530, "loss": 1.3861, "reward": null, "learning_rate": 7.291708027986988e-06, "epoch": 2.25, "percentage": 75.06, "elapsed_time": "4:17:38", "remaining_time": "1:25:37"}
341
+ {"current_steps": 3410, "total_steps": 4530, "loss": 1.3738, "reward": null, "learning_rate": 7.169751480924361e-06, "epoch": 2.26, "percentage": 75.28, "elapsed_time": "4:18:41", "remaining_time": "1:24:58"}
342
+ {"current_steps": 3420, "total_steps": 4530, "loss": 1.3908, "reward": null, "learning_rate": 7.048652482965079e-06, "epoch": 2.26, "percentage": 75.5, "elapsed_time": "4:19:23", "remaining_time": "1:24:11"}
343
+ {"current_steps": 3430, "total_steps": 4530, "loss": 1.3652, "reward": null, "learning_rate": 6.928416858387874e-06, "epoch": 2.27, "percentage": 75.72, "elapsed_time": "4:20:09", "remaining_time": "1:23:26"}
344
+ {"current_steps": 3440, "total_steps": 4530, "loss": 1.3673, "reward": null, "learning_rate": 6.809050389947363e-06, "epoch": 2.28, "percentage": 75.94, "elapsed_time": "4:20:54", "remaining_time": "1:22:40"}
345
+ {"current_steps": 3450, "total_steps": 4530, "loss": 1.395, "reward": null, "learning_rate": 6.690558818595943e-06, "epoch": 2.28, "percentage": 76.16, "elapsed_time": "4:21:39", "remaining_time": "1:21:54"}
346
+ {"current_steps": 3460, "total_steps": 4530, "loss": 1.3734, "reward": null, "learning_rate": 6.5729478432076775e-06, "epoch": 2.29, "percentage": 76.38, "elapsed_time": "4:22:23", "remaining_time": "1:21:08"}
347
+ {"current_steps": 3470, "total_steps": 4530, "loss": 1.4366, "reward": null, "learning_rate": 6.456223120304192e-06, "epoch": 2.3, "percentage": 76.6, "elapsed_time": "4:23:02", "remaining_time": "1:20:21"}
348
+ {"current_steps": 3480, "total_steps": 4530, "loss": 1.4222, "reward": null, "learning_rate": 6.340390263782655e-06, "epoch": 2.3, "percentage": 76.82, "elapsed_time": "4:23:43", "remaining_time": "1:19:34"}
349
+ {"current_steps": 3490, "total_steps": 4530, "loss": 1.3545, "reward": null, "learning_rate": 6.22545484464574e-06, "epoch": 2.31, "percentage": 77.04, "elapsed_time": "4:24:29", "remaining_time": "1:18:49"}
350
+ {"current_steps": 3500, "total_steps": 4530, "loss": 1.3581, "reward": null, "learning_rate": 6.111422390733715e-06, "epoch": 2.32, "percentage": 77.26, "elapsed_time": "4:25:13", "remaining_time": "1:18:02"}
351
+ {"current_steps": 3510, "total_steps": 4530, "loss": 1.4052, "reward": null, "learning_rate": 5.998298386458545e-06, "epoch": 2.32, "percentage": 77.48, "elapsed_time": "4:26:17", "remaining_time": "1:17:23"}
352
+ {"current_steps": 3520, "total_steps": 4530, "loss": 1.3886, "reward": null, "learning_rate": 5.8860882725401665e-06, "epoch": 2.33, "percentage": 77.7, "elapsed_time": "4:27:02", "remaining_time": "1:16:37"}
353
+ {"current_steps": 3530, "total_steps": 4530, "loss": 1.3818, "reward": null, "learning_rate": 5.774797445744781e-06, "epoch": 2.34, "percentage": 77.92, "elapsed_time": "4:27:45", "remaining_time": "1:15:51"}
354
+ {"current_steps": 3540, "total_steps": 4530, "loss": 1.3817, "reward": null, "learning_rate": 5.664431258625305e-06, "epoch": 2.34, "percentage": 78.15, "elapsed_time": "4:28:25", "remaining_time": "1:15:04"}
355
+ {"current_steps": 3550, "total_steps": 4530, "loss": 1.3617, "reward": null, "learning_rate": 5.55499501926394e-06, "epoch": 2.35, "percentage": 78.37, "elapsed_time": "4:29:09", "remaining_time": "1:14:18"}
356
+ {"current_steps": 3560, "total_steps": 4530, "loss": 1.3768, "reward": null, "learning_rate": 5.446493991016879e-06, "epoch": 2.36, "percentage": 78.59, "elapsed_time": "4:29:50", "remaining_time": "1:13:31"}
357
+ {"current_steps": 3570, "total_steps": 4530, "loss": 1.3755, "reward": null, "learning_rate": 5.338933392261159e-06, "epoch": 2.36, "percentage": 78.81, "elapsed_time": "4:30:35", "remaining_time": "1:12:45"}
358
+ {"current_steps": 3580, "total_steps": 4530, "loss": 1.3823, "reward": null, "learning_rate": 5.23231839614369e-06, "epoch": 2.37, "percentage": 79.03, "elapsed_time": "4:31:20", "remaining_time": "1:12:00"}
359
+ {"current_steps": 3590, "total_steps": 4530, "loss": 1.3883, "reward": null, "learning_rate": 5.126654130332451e-06, "epoch": 2.38, "percentage": 79.25, "elapsed_time": "4:32:02", "remaining_time": "1:11:13"}
360
+ {"current_steps": 3600, "total_steps": 4530, "loss": 1.3988, "reward": null, "learning_rate": 5.02194567676986e-06, "epoch": 2.38, "percentage": 79.47, "elapsed_time": "4:32:44", "remaining_time": "1:10:27"}
361
+ {"current_steps": 3610, "total_steps": 4530, "loss": 1.3838, "reward": null, "learning_rate": 4.918198071428382e-06, "epoch": 2.39, "percentage": 79.69, "elapsed_time": "4:33:48", "remaining_time": "1:09:46"}
362
+ {"current_steps": 3620, "total_steps": 4530, "loss": 1.4422, "reward": null, "learning_rate": 4.815416304068298e-06, "epoch": 2.4, "percentage": 79.91, "elapsed_time": "4:34:36", "remaining_time": "1:09:01"}
363
+ {"current_steps": 3630, "total_steps": 4530, "loss": 1.3834, "reward": null, "learning_rate": 4.713605317997741e-06, "epoch": 2.4, "percentage": 80.13, "elapsed_time": "4:35:20", "remaining_time": "1:08:15"}
364
+ {"current_steps": 3640, "total_steps": 4530, "loss": 1.3743, "reward": null, "learning_rate": 4.61277000983493e-06, "epoch": 2.41, "percentage": 80.35, "elapsed_time": "4:36:00", "remaining_time": "1:07:29"}
365
+ {"current_steps": 3650, "total_steps": 4530, "loss": 1.451, "reward": null, "learning_rate": 4.51291522927268e-06, "epoch": 2.42, "percentage": 80.57, "elapsed_time": "4:36:40", "remaining_time": "1:06:42"}
366
+ {"current_steps": 3660, "total_steps": 4530, "loss": 1.3644, "reward": null, "learning_rate": 4.414045778845144e-06, "epoch": 2.42, "percentage": 80.79, "elapsed_time": "4:37:22", "remaining_time": "1:05:56"}
367
+ {"current_steps": 3670, "total_steps": 4530, "loss": 1.3944, "reward": null, "learning_rate": 4.316166413696851e-06, "epoch": 2.43, "percentage": 81.02, "elapsed_time": "4:38:05", "remaining_time": "1:05:09"}
368
+ {"current_steps": 3680, "total_steps": 4530, "loss": 1.3514, "reward": null, "learning_rate": 4.219281841353981e-06, "epoch": 2.44, "percentage": 81.24, "elapsed_time": "4:38:47", "remaining_time": "1:04:23"}
369
+ {"current_steps": 3690, "total_steps": 4530, "loss": 1.3389, "reward": null, "learning_rate": 4.123396721497977e-06, "epoch": 2.44, "percentage": 81.46, "elapsed_time": "4:39:30", "remaining_time": "1:03:37"}
370
+ {"current_steps": 3700, "total_steps": 4530, "loss": 1.3792, "reward": null, "learning_rate": 4.028515665741439e-06, "epoch": 2.45, "percentage": 81.68, "elapsed_time": "4:40:13", "remaining_time": "1:02:51"}
371
+ {"current_steps": 3710, "total_steps": 4530, "loss": 1.3686, "reward": null, "learning_rate": 3.934643237406291e-06, "epoch": 2.46, "percentage": 81.9, "elapsed_time": "4:41:18", "remaining_time": "1:02:10"}
372
+ {"current_steps": 3720, "total_steps": 4530, "loss": 1.3424, "reward": null, "learning_rate": 3.8417839513043645e-06, "epoch": 2.46, "percentage": 82.12, "elapsed_time": "4:42:03", "remaining_time": "1:01:25"}
373
+ {"current_steps": 3730, "total_steps": 4530, "loss": 1.3684, "reward": null, "learning_rate": 3.7499422735202127e-06, "epoch": 2.47, "percentage": 82.34, "elapsed_time": "4:42:45", "remaining_time": "1:00:38"}
374
+ {"current_steps": 3740, "total_steps": 4530, "loss": 1.3868, "reward": null, "learning_rate": 3.6591226211963287e-06, "epoch": 2.48, "percentage": 82.56, "elapsed_time": "4:43:28", "remaining_time": "0:59:52"}
375
+ {"current_steps": 3750, "total_steps": 4530, "loss": 1.368, "reward": null, "learning_rate": 3.5693293623207086e-06, "epoch": 2.48, "percentage": 82.78, "elapsed_time": "4:44:12", "remaining_time": "0:59:06"}
376
+ {"current_steps": 3760, "total_steps": 4530, "loss": 1.3027, "reward": null, "learning_rate": 3.480566815516756e-06, "epoch": 2.49, "percentage": 83.0, "elapsed_time": "4:44:59", "remaining_time": "0:58:21"}
377
+ {"current_steps": 3770, "total_steps": 4530, "loss": 1.4223, "reward": null, "learning_rate": 3.3928392498355916e-06, "epoch": 2.5, "percentage": 83.22, "elapsed_time": "4:45:40", "remaining_time": "0:57:35"}
378
+ {"current_steps": 3780, "total_steps": 4530, "loss": 1.3674, "reward": null, "learning_rate": 3.3061508845507323e-06, "epoch": 2.5, "percentage": 83.44, "elapsed_time": "4:46:26", "remaining_time": "0:56:49"}
379
+ {"current_steps": 3790, "total_steps": 4530, "loss": 1.3848, "reward": null, "learning_rate": 3.22050588895515e-06, "epoch": 2.51, "percentage": 83.66, "elapsed_time": "4:47:11", "remaining_time": "0:56:04"}
380
+ {"current_steps": 3800, "total_steps": 4530, "loss": 1.4191, "reward": null, "learning_rate": 3.135908382160771e-06, "epoch": 2.52, "percentage": 83.89, "elapsed_time": "4:47:54", "remaining_time": "0:55:18"}
381
+ {"current_steps": 3810, "total_steps": 4530, "loss": 1.3796, "reward": null, "learning_rate": 3.0523624329003324e-06, "epoch": 2.52, "percentage": 84.11, "elapsed_time": "4:49:00", "remaining_time": "0:54:37"}
382
+ {"current_steps": 3820, "total_steps": 4530, "loss": 1.4101, "reward": null, "learning_rate": 2.969872059331738e-06, "epoch": 2.53, "percentage": 84.33, "elapsed_time": "4:49:44", "remaining_time": "0:53:51"}
383
+ {"current_steps": 3830, "total_steps": 4530, "loss": 1.379, "reward": null, "learning_rate": 2.8884412288447737e-06, "epoch": 2.54, "percentage": 84.55, "elapsed_time": "4:50:27", "remaining_time": "0:53:05"}
384
+ {"current_steps": 3840, "total_steps": 4530, "loss": 1.3881, "reward": null, "learning_rate": 2.8080738578703054e-06, "epoch": 2.54, "percentage": 84.77, "elapsed_time": "4:51:09", "remaining_time": "0:52:19"}
385
+ {"current_steps": 3850, "total_steps": 4530, "loss": 1.3464, "reward": null, "learning_rate": 2.728773811691923e-06, "epoch": 2.55, "percentage": 84.99, "elapsed_time": "4:51:54", "remaining_time": "0:51:33"}
386
+ {"current_steps": 3860, "total_steps": 4530, "loss": 1.367, "reward": null, "learning_rate": 2.6505449042600244e-06, "epoch": 2.56, "percentage": 85.21, "elapsed_time": "4:52:39", "remaining_time": "0:50:47"}
387
+ {"current_steps": 3870, "total_steps": 4530, "loss": 1.3498, "reward": null, "learning_rate": 2.5733908980083988e-06, "epoch": 2.56, "percentage": 85.43, "elapsed_time": "4:53:24", "remaining_time": "0:50:02"}
388
+ {"current_steps": 3880, "total_steps": 4530, "loss": 1.3895, "reward": null, "learning_rate": 2.4973155036732534e-06, "epoch": 2.57, "percentage": 85.65, "elapsed_time": "4:54:06", "remaining_time": "0:49:16"}
389
+ {"current_steps": 3890, "total_steps": 4530, "loss": 1.4072, "reward": null, "learning_rate": 2.422322380114772e-06, "epoch": 2.58, "percentage": 85.87, "elapsed_time": "4:54:47", "remaining_time": "0:48:30"}
390
+ {"current_steps": 3900, "total_steps": 4530, "loss": 1.347, "reward": null, "learning_rate": 2.348415134141102e-06, "epoch": 2.58, "percentage": 86.09, "elapsed_time": "4:55:33", "remaining_time": "0:47:44"}
391
+ {"current_steps": 3910, "total_steps": 4530, "loss": 1.3605, "reward": null, "learning_rate": 2.2755973203349294e-06, "epoch": 2.59, "percentage": 86.31, "elapsed_time": "4:56:36", "remaining_time": "0:47:02"}
392
+ {"current_steps": 3920, "total_steps": 4530, "loss": 1.3105, "reward": null, "learning_rate": 2.2038724408824844e-06, "epoch": 2.6, "percentage": 86.53, "elapsed_time": "4:57:21", "remaining_time": "0:46:16"}
393
+ {"current_steps": 3930, "total_steps": 4530, "loss": 1.3718, "reward": null, "learning_rate": 2.133243945405128e-06, "epoch": 2.6, "percentage": 86.75, "elapsed_time": "4:58:06", "remaining_time": "0:45:30"}
394
+ {"current_steps": 3940, "total_steps": 4530, "loss": 1.3293, "reward": null, "learning_rate": 2.0637152307934228e-06, "epoch": 2.61, "percentage": 86.98, "elapsed_time": "4:58:53", "remaining_time": "0:44:45"}
395
+ {"current_steps": 3950, "total_steps": 4530, "loss": 1.3677, "reward": null, "learning_rate": 1.995289641043768e-06, "epoch": 2.62, "percentage": 87.2, "elapsed_time": "4:59:35", "remaining_time": "0:43:59"}
396
+ {"current_steps": 3960, "total_steps": 4530, "loss": 1.409, "reward": null, "learning_rate": 1.927970467097573e-06, "epoch": 2.62, "percentage": 87.42, "elapsed_time": "5:00:16", "remaining_time": "0:43:13"}
397
+ {"current_steps": 3970, "total_steps": 4530, "loss": 1.3973, "reward": null, "learning_rate": 1.8617609466829666e-06, "epoch": 2.63, "percentage": 87.64, "elapsed_time": "5:01:01", "remaining_time": "0:42:27"}
398
+ {"current_steps": 3980, "total_steps": 4530, "loss": 1.3991, "reward": null, "learning_rate": 1.7966642641590925e-06, "epoch": 2.64, "percentage": 87.86, "elapsed_time": "5:01:43", "remaining_time": "0:41:41"}
399
+ {"current_steps": 3990, "total_steps": 4530, "loss": 1.3662, "reward": null, "learning_rate": 1.732683550362954e-06, "epoch": 2.64, "percentage": 88.08, "elapsed_time": "5:02:25", "remaining_time": "0:40:55"}
400
+ {"current_steps": 4000, "total_steps": 4530, "loss": 1.3871, "reward": null, "learning_rate": 1.6698218824588164e-06, "epoch": 2.65, "percentage": 88.3, "elapsed_time": "5:03:09", "remaining_time": "0:40:10"}
401
+ {"current_steps": 4010, "total_steps": 4530, "loss": 1.4072, "reward": null, "learning_rate": 1.6080822837902382e-06, "epoch": 2.65, "percentage": 88.52, "elapsed_time": "5:04:12", "remaining_time": "0:39:26"}
402
+ {"current_steps": 4020, "total_steps": 4530, "loss": 1.3841, "reward": null, "learning_rate": 1.5474677237346468e-06, "epoch": 2.66, "percentage": 88.74, "elapsed_time": "5:04:57", "remaining_time": "0:38:41"}
403
+ {"current_steps": 4030, "total_steps": 4530, "loss": 1.3729, "reward": null, "learning_rate": 1.4879811175605302e-06, "epoch": 2.67, "percentage": 88.96, "elapsed_time": "5:05:42", "remaining_time": "0:37:55"}
404
+ {"current_steps": 4040, "total_steps": 4530, "loss": 1.3648, "reward": null, "learning_rate": 1.4296253262872234e-06, "epoch": 2.67, "percentage": 89.18, "elapsed_time": "5:06:24", "remaining_time": "0:37:09"}
405
+ {"current_steps": 4050, "total_steps": 4530, "loss": 1.4043, "reward": null, "learning_rate": 1.3724031565473112e-06, "epoch": 2.68, "percentage": 89.4, "elapsed_time": "5:07:06", "remaining_time": "0:36:23"}
406
+ {"current_steps": 4060, "total_steps": 4530, "loss": 1.4135, "reward": null, "learning_rate": 1.316317360451641e-06, "epoch": 2.69, "percentage": 89.62, "elapsed_time": "5:07:50", "remaining_time": "0:35:38"}
407
+ {"current_steps": 4070, "total_steps": 4530, "loss": 1.399, "reward": null, "learning_rate": 1.2613706354569571e-06, "epoch": 2.69, "percentage": 89.85, "elapsed_time": "5:08:34", "remaining_time": "0:34:52"}
408
+ {"current_steps": 4080, "total_steps": 4530, "loss": 1.4024, "reward": null, "learning_rate": 1.2075656242361732e-06, "epoch": 2.7, "percentage": 90.07, "elapsed_time": "5:09:18", "remaining_time": "0:34:06"}
409
+ {"current_steps": 4090, "total_steps": 4530, "loss": 1.3668, "reward": null, "learning_rate": 1.1549049145512636e-06, "epoch": 2.71, "percentage": 90.29, "elapsed_time": "5:10:02", "remaining_time": "0:33:21"}
410
+ {"current_steps": 4100, "total_steps": 4530, "loss": 1.3692, "reward": null, "learning_rate": 1.1033910391288065e-06, "epoch": 2.71, "percentage": 90.51, "elapsed_time": "5:10:48", "remaining_time": "0:32:35"}
411
+ {"current_steps": 4110, "total_steps": 4530, "loss": 1.3908, "reward": null, "learning_rate": 1.0530264755381824e-06, "epoch": 2.72, "percentage": 90.73, "elapsed_time": "5:11:50", "remaining_time": "0:31:52"}
412
+ {"current_steps": 4120, "total_steps": 4530, "loss": 1.3999, "reward": null, "learning_rate": 1.0038136460723963e-06, "epoch": 2.73, "percentage": 90.95, "elapsed_time": "5:12:34", "remaining_time": "0:31:06"}
413
+ {"current_steps": 4130, "total_steps": 4530, "loss": 1.4098, "reward": null, "learning_rate": 9.557549176315934e-07, "epoch": 2.73, "percentage": 91.17, "elapsed_time": "5:13:16", "remaining_time": "0:30:20"}
414
+ {"current_steps": 4140, "total_steps": 4530, "loss": 1.3973, "reward": null, "learning_rate": 9.088526016092142e-07, "epoch": 2.74, "percentage": 91.39, "elapsed_time": "5:13:59", "remaining_time": "0:29:34"}
415
+ {"current_steps": 4150, "total_steps": 4530, "loss": 1.3758, "reward": null, "learning_rate": 8.631089537808307e-07, "epoch": 2.75, "percentage": 91.61, "elapsed_time": "5:14:41", "remaining_time": "0:28:48"}
416
+ {"current_steps": 4160, "total_steps": 4530, "loss": 1.3197, "reward": null, "learning_rate": 8.185261741956551e-07, "epoch": 2.75, "percentage": 91.83, "elapsed_time": "5:15:24", "remaining_time": "0:28:03"}
417
+ {"current_steps": 4170, "total_steps": 4530, "loss": 1.3794, "reward": null, "learning_rate": 7.751064070707248e-07, "epoch": 2.76, "percentage": 92.05, "elapsed_time": "5:16:10", "remaining_time": "0:27:17"}
418
+ {"current_steps": 4180, "total_steps": 4530, "loss": 1.3764, "reward": null, "learning_rate": 7.328517406877761e-07, "epoch": 2.77, "percentage": 92.27, "elapsed_time": "5:16:57", "remaining_time": "0:26:32"}
419
+ {"current_steps": 4190, "total_steps": 4530, "loss": 1.4063, "reward": null, "learning_rate": 6.917642072928137e-07, "epoch": 2.77, "percentage": 92.49, "elapsed_time": "5:17:38", "remaining_time": "0:25:46"}
420
+ {"current_steps": 4200, "total_steps": 4530, "loss": 1.3959, "reward": null, "learning_rate": 6.51845782998356e-07, "epoch": 2.78, "percentage": 92.72, "elapsed_time": "5:18:19", "remaining_time": "0:25:00"}
421
+ {"current_steps": 4210, "total_steps": 4530, "loss": 1.3767, "reward": null, "learning_rate": 6.130983876884155e-07, "epoch": 2.79, "percentage": 92.94, "elapsed_time": "5:19:24", "remaining_time": "0:24:16"}
422
+ {"current_steps": 4220, "total_steps": 4530, "loss": 1.3619, "reward": null, "learning_rate": 5.755238849261407e-07, "epoch": 2.79, "percentage": 93.16, "elapsed_time": "5:20:07", "remaining_time": "0:23:30"}
423
+ {"current_steps": 4230, "total_steps": 4530, "loss": 1.3723, "reward": null, "learning_rate": 5.391240818642007e-07, "epoch": 2.8, "percentage": 93.38, "elapsed_time": "5:20:48", "remaining_time": "0:22:45"}
424
+ {"current_steps": 4240, "total_steps": 4530, "loss": 1.4262, "reward": null, "learning_rate": 5.039007291578579e-07, "epoch": 2.81, "percentage": 93.6, "elapsed_time": "5:21:33", "remaining_time": "0:21:59"}
425
+ {"current_steps": 4250, "total_steps": 4530, "loss": 1.3775, "reward": null, "learning_rate": 4.698555208807853e-07, "epoch": 2.81, "percentage": 93.82, "elapsed_time": "5:22:16", "remaining_time": "0:21:13"}
426
+ {"current_steps": 4260, "total_steps": 4530, "loss": 1.4159, "reward": null, "learning_rate": 4.3699009444357344e-07, "epoch": 2.82, "percentage": 94.04, "elapsed_time": "5:22:58", "remaining_time": "0:20:28"}
427
+ {"current_steps": 4270, "total_steps": 4530, "loss": 1.4007, "reward": null, "learning_rate": 4.0530603051499584e-07, "epoch": 2.83, "percentage": 94.26, "elapsed_time": "5:23:38", "remaining_time": "0:19:42"}
428
+ {"current_steps": 4280, "total_steps": 4530, "loss": 1.3898, "reward": null, "learning_rate": 3.7480485294596747e-07, "epoch": 2.83, "percentage": 94.48, "elapsed_time": "5:24:23", "remaining_time": "0:18:56"}
429
+ {"current_steps": 4290, "total_steps": 4530, "loss": 1.4173, "reward": null, "learning_rate": 3.454880286962781e-07, "epoch": 2.84, "percentage": 94.7, "elapsed_time": "5:25:05", "remaining_time": "0:18:11"}
430
+ {"current_steps": 4300, "total_steps": 4530, "loss": 1.3539, "reward": null, "learning_rate": 3.1735696776400703e-07, "epoch": 2.85, "percentage": 94.92, "elapsed_time": "5:25:51", "remaining_time": "0:17:25"}
431
+ {"current_steps": 4310, "total_steps": 4530, "loss": 1.3803, "reward": null, "learning_rate": 2.9041302311774433e-07, "epoch": 2.85, "percentage": 95.14, "elapsed_time": "5:26:52", "remaining_time": "0:16:41"}
432
+ {"current_steps": 4320, "total_steps": 4530, "loss": 1.4141, "reward": null, "learning_rate": 2.646574906314925e-07, "epoch": 2.86, "percentage": 95.36, "elapsed_time": "5:27:35", "remaining_time": "0:15:55"}
433
+ {"current_steps": 4330, "total_steps": 4530, "loss": 1.3444, "reward": null, "learning_rate": 2.4009160902235816e-07, "epoch": 2.87, "percentage": 95.58, "elapsed_time": "5:28:18", "remaining_time": "0:15:09"}
434
+ {"current_steps": 4340, "total_steps": 4530, "loss": 1.3669, "reward": null, "learning_rate": 2.1671655979096094e-07, "epoch": 2.87, "percentage": 95.81, "elapsed_time": "5:29:03", "remaining_time": "0:14:24"}
435
+ {"current_steps": 4350, "total_steps": 4530, "loss": 1.3776, "reward": null, "learning_rate": 1.9453346716462317e-07, "epoch": 2.88, "percentage": 96.03, "elapsed_time": "5:29:46", "remaining_time": "0:13:38"}
436
+ {"current_steps": 4360, "total_steps": 4530, "loss": 1.4048, "reward": null, "learning_rate": 1.73543398043291e-07, "epoch": 2.89, "percentage": 96.25, "elapsed_time": "5:30:28", "remaining_time": "0:12:53"}
437
+ {"current_steps": 4370, "total_steps": 4530, "loss": 1.3623, "reward": null, "learning_rate": 1.537473619482227e-07, "epoch": 2.89, "percentage": 96.47, "elapsed_time": "5:31:09", "remaining_time": "0:12:07"}
438
+ {"current_steps": 4380, "total_steps": 4530, "loss": 1.3861, "reward": null, "learning_rate": 1.351463109734441e-07, "epoch": 2.9, "percentage": 96.69, "elapsed_time": "5:31:48", "remaining_time": "0:11:21"}
439
+ {"current_steps": 4390, "total_steps": 4530, "loss": 1.3323, "reward": null, "learning_rate": 1.1774113973994083e-07, "epoch": 2.91, "percentage": 96.91, "elapsed_time": "5:32:32", "remaining_time": "0:10:36"}
440
+ {"current_steps": 4400, "total_steps": 4530, "loss": 1.3646, "reward": null, "learning_rate": 1.0153268535264827e-07, "epoch": 2.91, "percentage": 97.13, "elapsed_time": "5:33:15", "remaining_time": "0:09:50"}
441
+ {"current_steps": 4410, "total_steps": 4530, "loss": 1.3963, "reward": null, "learning_rate": 8.652172736017816e-08, "epoch": 2.92, "percentage": 97.35, "elapsed_time": "5:34:18", "remaining_time": "0:09:05"}
442
+ {"current_steps": 4420, "total_steps": 4530, "loss": 1.3812, "reward": null, "learning_rate": 7.270898771733481e-08, "epoch": 2.93, "percentage": 97.57, "elapsed_time": "5:35:04", "remaining_time": "0:08:20"}
443
+ {"current_steps": 4430, "total_steps": 4530, "loss": 1.375, "reward": null, "learning_rate": 6.00951307503872e-08, "epoch": 2.93, "percentage": 97.79, "elapsed_time": "5:35:47", "remaining_time": "0:07:34"}
444
+ {"current_steps": 4440, "total_steps": 4530, "loss": 1.4015, "reward": null, "learning_rate": 4.868076312512515e-08, "epoch": 2.94, "percentage": 98.01, "elapsed_time": "5:36:30", "remaining_time": "0:06:49"}
445
+ {"current_steps": 4450, "total_steps": 4530, "loss": 1.3795, "reward": null, "learning_rate": 3.846643381766879e-08, "epoch": 2.95, "percentage": 98.23, "elapsed_time": "5:37:12", "remaining_time": "0:06:03"}
446
+ {"current_steps": 4460, "total_steps": 4530, "loss": 1.4244, "reward": null, "learning_rate": 2.94526340880813e-08, "epoch": 2.95, "percentage": 98.45, "elapsed_time": "5:37:53", "remaining_time": "0:05:18"}
447
+ {"current_steps": 4470, "total_steps": 4530, "loss": 1.3731, "reward": null, "learning_rate": 2.1639797456723952e-08, "epoch": 2.96, "percentage": 98.68, "elapsed_time": "5:38:37", "remaining_time": "0:04:32"}
448
+ {"current_steps": 4480, "total_steps": 4530, "loss": 1.4061, "reward": null, "learning_rate": 1.5028299683425562e-08, "epoch": 2.97, "percentage": 98.9, "elapsed_time": "5:39:21", "remaining_time": "0:03:47"}
449
+ {"current_steps": 4490, "total_steps": 4530, "loss": 1.3842, "reward": null, "learning_rate": 9.618458749391379e-09, "epoch": 2.97, "percentage": 99.12, "elapsed_time": "5:40:04", "remaining_time": "0:03:01"}
450
+ {"current_steps": 4500, "total_steps": 4530, "loss": 1.3693, "reward": null, "learning_rate": 5.41053484192644e-09, "epoch": 2.98, "percentage": 99.34, "elapsed_time": "5:40:45", "remaining_time": "0:02:16"}
451
+ {"current_steps": 4510, "total_steps": 4530, "loss": 1.3439, "reward": null, "learning_rate": 2.4047303419094667e-09, "epoch": 2.99, "percentage": 99.56, "elapsed_time": "5:41:51", "remaining_time": "0:01:30"}
452
+ {"current_steps": 4520, "total_steps": 4530, "loss": 1.3848, "reward": null, "learning_rate": 6.011898140617645e-10, "epoch": 2.99, "percentage": 99.78, "elapsed_time": "5:42:37", "remaining_time": "0:00:45"}
453
+ {"current_steps": 4530, "total_steps": 4530, "loss": 1.3852, "reward": null, "learning_rate": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "5:43:21", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,3103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.3997734785079956,
3
+ "best_model_checkpoint": "alpaca_baichuan/checkpoint-4400",
4
+ "epoch": 2.9992551518662585,
5
+ "global_step": 4530,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 4.999939881018594e-05,
13
+ "loss": 1.6257,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.01,
18
+ "learning_rate": 4.999759526965809e-05,
19
+ "loss": 1.6388,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.02,
24
+ "learning_rate": 4.999458946515808e-05,
25
+ "loss": 1.5034,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.03,
30
+ "learning_rate": 4.999038154125061e-05,
31
+ "loss": 1.5761,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.03,
36
+ "learning_rate": 4.998497170031657e-05,
37
+ "loss": 1.5066,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.04,
42
+ "learning_rate": 4.997836020254328e-05,
43
+ "loss": 1.5738,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.05,
48
+ "learning_rate": 4.9970547365911925e-05,
49
+ "loss": 1.4921,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.05,
54
+ "learning_rate": 4.996153356618233e-05,
55
+ "loss": 1.4508,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.06,
60
+ "learning_rate": 4.995131923687488e-05,
61
+ "loss": 1.4714,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.07,
66
+ "learning_rate": 4.9939904869249616e-05,
67
+ "loss": 1.494,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.07,
72
+ "eval_loss": 1.4796885251998901,
73
+ "eval_runtime": 20.1174,
74
+ "eval_samples_per_second": 24.307,
75
+ "eval_steps_per_second": 6.114,
76
+ "step": 100
77
+ },
78
+ {
79
+ "epoch": 0.07,
80
+ "learning_rate": 4.992729101228267e-05,
81
+ "loss": 1.4934,
82
+ "step": 110
83
+ },
84
+ {
85
+ "epoch": 0.08,
86
+ "learning_rate": 4.991347827263982e-05,
87
+ "loss": 1.4789,
88
+ "step": 120
89
+ },
90
+ {
91
+ "epoch": 0.09,
92
+ "learning_rate": 4.9898467314647356e-05,
93
+ "loss": 1.4511,
94
+ "step": 130
95
+ },
96
+ {
97
+ "epoch": 0.09,
98
+ "learning_rate": 4.9882258860260065e-05,
99
+ "loss": 1.4876,
100
+ "step": 140
101
+ },
102
+ {
103
+ "epoch": 0.1,
104
+ "learning_rate": 4.9864853689026556e-05,
105
+ "loss": 1.5124,
106
+ "step": 150
107
+ },
108
+ {
109
+ "epoch": 0.11,
110
+ "learning_rate": 4.984625263805178e-05,
111
+ "loss": 1.4772,
112
+ "step": 160
113
+ },
114
+ {
115
+ "epoch": 0.11,
116
+ "learning_rate": 4.982645660195671e-05,
117
+ "loss": 1.436,
118
+ "step": 170
119
+ },
120
+ {
121
+ "epoch": 0.12,
122
+ "learning_rate": 4.9805466532835376e-05,
123
+ "loss": 1.4377,
124
+ "step": 180
125
+ },
126
+ {
127
+ "epoch": 0.13,
128
+ "learning_rate": 4.978328344020904e-05,
129
+ "loss": 1.438,
130
+ "step": 190
131
+ },
132
+ {
133
+ "epoch": 0.13,
134
+ "learning_rate": 4.975990839097764e-05,
135
+ "loss": 1.4448,
136
+ "step": 200
137
+ },
138
+ {
139
+ "epoch": 0.13,
140
+ "eval_loss": 1.45673668384552,
141
+ "eval_runtime": 20.2667,
142
+ "eval_samples_per_second": 24.128,
143
+ "eval_steps_per_second": 6.069,
144
+ "step": 200
145
+ },
146
+ {
147
+ "epoch": 0.14,
148
+ "learning_rate": 4.973534250936851e-05,
149
+ "loss": 1.452,
150
+ "step": 210
151
+ },
152
+ {
153
+ "epoch": 0.15,
154
+ "learning_rate": 4.970958697688226e-05,
155
+ "loss": 1.4813,
156
+ "step": 220
157
+ },
158
+ {
159
+ "epoch": 0.15,
160
+ "learning_rate": 4.9682643032235996e-05,
161
+ "loss": 1.41,
162
+ "step": 230
163
+ },
164
+ {
165
+ "epoch": 0.16,
166
+ "learning_rate": 4.965451197130373e-05,
167
+ "loss": 1.428,
168
+ "step": 240
169
+ },
170
+ {
171
+ "epoch": 0.17,
172
+ "learning_rate": 4.9625195147054034e-05,
173
+ "loss": 1.463,
174
+ "step": 250
175
+ },
176
+ {
177
+ "epoch": 0.17,
178
+ "learning_rate": 4.9594693969485006e-05,
179
+ "loss": 1.4821,
180
+ "step": 260
181
+ },
182
+ {
183
+ "epoch": 0.18,
184
+ "learning_rate": 4.956300990555643e-05,
185
+ "loss": 1.4855,
186
+ "step": 270
187
+ },
188
+ {
189
+ "epoch": 0.19,
190
+ "learning_rate": 4.9530144479119215e-05,
191
+ "loss": 1.4322,
192
+ "step": 280
193
+ },
194
+ {
195
+ "epoch": 0.19,
196
+ "learning_rate": 4.9496099270842145e-05,
197
+ "loss": 1.4397,
198
+ "step": 290
199
+ },
200
+ {
201
+ "epoch": 0.2,
202
+ "learning_rate": 4.9460875918135804e-05,
203
+ "loss": 1.4107,
204
+ "step": 300
205
+ },
206
+ {
207
+ "epoch": 0.2,
208
+ "eval_loss": 1.4451508522033691,
209
+ "eval_runtime": 19.869,
210
+ "eval_samples_per_second": 24.611,
211
+ "eval_steps_per_second": 6.191,
212
+ "step": 300
213
+ },
214
+ {
215
+ "epoch": 0.21,
216
+ "learning_rate": 4.942447611507386e-05,
217
+ "loss": 1.4722,
218
+ "step": 310
219
+ },
220
+ {
221
+ "epoch": 0.21,
222
+ "learning_rate": 4.938690161231159e-05,
223
+ "loss": 1.423,
224
+ "step": 320
225
+ },
226
+ {
227
+ "epoch": 0.22,
228
+ "learning_rate": 4.934815421700165e-05,
229
+ "loss": 1.4288,
230
+ "step": 330
231
+ },
232
+ {
233
+ "epoch": 0.23,
234
+ "learning_rate": 4.9308235792707194e-05,
235
+ "loss": 1.4294,
236
+ "step": 340
237
+ },
238
+ {
239
+ "epoch": 0.23,
240
+ "learning_rate": 4.9267148259312224e-05,
241
+ "loss": 1.4233,
242
+ "step": 350
243
+ },
244
+ {
245
+ "epoch": 0.24,
246
+ "learning_rate": 4.9224893592929275e-05,
247
+ "loss": 1.4553,
248
+ "step": 360
249
+ },
250
+ {
251
+ "epoch": 0.24,
252
+ "learning_rate": 4.9181473825804346e-05,
253
+ "loss": 1.4206,
254
+ "step": 370
255
+ },
256
+ {
257
+ "epoch": 0.25,
258
+ "learning_rate": 4.913689104621917e-05,
259
+ "loss": 1.442,
260
+ "step": 380
261
+ },
262
+ {
263
+ "epoch": 0.26,
264
+ "learning_rate": 4.909114739839079e-05,
265
+ "loss": 1.4668,
266
+ "step": 390
267
+ },
268
+ {
269
+ "epoch": 0.26,
270
+ "learning_rate": 4.9044245082368415e-05,
271
+ "loss": 1.4439,
272
+ "step": 400
273
+ },
274
+ {
275
+ "epoch": 0.26,
276
+ "eval_loss": 1.4394803047180176,
277
+ "eval_runtime": 19.9302,
278
+ "eval_samples_per_second": 24.536,
279
+ "eval_steps_per_second": 6.172,
280
+ "step": 400
281
+ },
282
+ {
283
+ "epoch": 0.27,
284
+ "learning_rate": 4.8996186353927606e-05,
285
+ "loss": 1.4224,
286
+ "step": 410
287
+ },
288
+ {
289
+ "epoch": 0.28,
290
+ "learning_rate": 4.894697352446182e-05,
291
+ "loss": 1.4084,
292
+ "step": 420
293
+ },
294
+ {
295
+ "epoch": 0.28,
296
+ "learning_rate": 4.889660896087119e-05,
297
+ "loss": 1.4398,
298
+ "step": 430
299
+ },
300
+ {
301
+ "epoch": 0.29,
302
+ "learning_rate": 4.884509508544874e-05,
303
+ "loss": 1.4268,
304
+ "step": 440
305
+ },
306
+ {
307
+ "epoch": 0.3,
308
+ "learning_rate": 4.879243437576383e-05,
309
+ "loss": 1.4522,
310
+ "step": 450
311
+ },
312
+ {
313
+ "epoch": 0.3,
314
+ "learning_rate": 4.8738629364543045e-05,
315
+ "loss": 1.4222,
316
+ "step": 460
317
+ },
318
+ {
319
+ "epoch": 0.31,
320
+ "learning_rate": 4.8683682639548365e-05,
321
+ "loss": 1.4956,
322
+ "step": 470
323
+ },
324
+ {
325
+ "epoch": 0.32,
326
+ "learning_rate": 4.862759684345269e-05,
327
+ "loss": 1.4538,
328
+ "step": 480
329
+ },
330
+ {
331
+ "epoch": 0.32,
332
+ "learning_rate": 4.857037467371278e-05,
333
+ "loss": 1.3748,
334
+ "step": 490
335
+ },
336
+ {
337
+ "epoch": 0.33,
338
+ "learning_rate": 4.8512018882439475e-05,
339
+ "loss": 1.4127,
340
+ "step": 500
341
+ },
342
+ {
343
+ "epoch": 0.33,
344
+ "eval_loss": 1.435186505317688,
345
+ "eval_runtime": 19.8689,
346
+ "eval_samples_per_second": 24.611,
347
+ "eval_steps_per_second": 6.191,
348
+ "step": 500
349
+ },
350
+ {
351
+ "epoch": 0.34,
352
+ "learning_rate": 4.8452532276265364e-05,
353
+ "loss": 1.3795,
354
+ "step": 510
355
+ },
356
+ {
357
+ "epoch": 0.34,
358
+ "learning_rate": 4.8391917716209765e-05,
359
+ "loss": 1.4414,
360
+ "step": 520
361
+ },
362
+ {
363
+ "epoch": 0.35,
364
+ "learning_rate": 4.833017811754119e-05,
365
+ "loss": 1.4242,
366
+ "step": 530
367
+ },
368
+ {
369
+ "epoch": 0.36,
370
+ "learning_rate": 4.8267316449637054e-05,
371
+ "loss": 1.4196,
372
+ "step": 540
373
+ },
374
+ {
375
+ "epoch": 0.36,
376
+ "learning_rate": 4.820333573584091e-05,
377
+ "loss": 1.389,
378
+ "step": 550
379
+ },
380
+ {
381
+ "epoch": 0.37,
382
+ "learning_rate": 4.813823905331704e-05,
383
+ "loss": 1.4597,
384
+ "step": 560
385
+ },
386
+ {
387
+ "epoch": 0.38,
388
+ "learning_rate": 4.8072029532902426e-05,
389
+ "loss": 1.4275,
390
+ "step": 570
391
+ },
392
+ {
393
+ "epoch": 0.38,
394
+ "learning_rate": 4.800471035895624e-05,
395
+ "loss": 1.4364,
396
+ "step": 580
397
+ },
398
+ {
399
+ "epoch": 0.39,
400
+ "learning_rate": 4.7936284769206584e-05,
401
+ "loss": 1.4366,
402
+ "step": 590
403
+ },
404
+ {
405
+ "epoch": 0.4,
406
+ "learning_rate": 4.786675605459487e-05,
407
+ "loss": 1.5086,
408
+ "step": 600
409
+ },
410
+ {
411
+ "epoch": 0.4,
412
+ "eval_loss": 1.4307918548583984,
413
+ "eval_runtime": 20.0563,
414
+ "eval_samples_per_second": 24.381,
415
+ "eval_steps_per_second": 6.133,
416
+ "step": 600
417
+ },
418
+ {
419
+ "epoch": 0.4,
420
+ "learning_rate": 4.779612755911752e-05,
421
+ "loss": 1.4309,
422
+ "step": 610
423
+ },
424
+ {
425
+ "epoch": 0.41,
426
+ "learning_rate": 4.772440267966508e-05,
427
+ "loss": 1.4102,
428
+ "step": 620
429
+ },
430
+ {
431
+ "epoch": 0.42,
432
+ "learning_rate": 4.76515848658589e-05,
433
+ "loss": 1.4035,
434
+ "step": 630
435
+ },
436
+ {
437
+ "epoch": 0.42,
438
+ "learning_rate": 4.7577677619885234e-05,
439
+ "loss": 1.4478,
440
+ "step": 640
441
+ },
442
+ {
443
+ "epoch": 0.43,
444
+ "learning_rate": 4.7502684496326746e-05,
445
+ "loss": 1.3999,
446
+ "step": 650
447
+ },
448
+ {
449
+ "epoch": 0.44,
450
+ "learning_rate": 4.7426609101991605e-05,
451
+ "loss": 1.4042,
452
+ "step": 660
453
+ },
454
+ {
455
+ "epoch": 0.44,
456
+ "learning_rate": 4.734945509573997e-05,
457
+ "loss": 1.4216,
458
+ "step": 670
459
+ },
460
+ {
461
+ "epoch": 0.45,
462
+ "learning_rate": 4.727122618830808e-05,
463
+ "loss": 1.4786,
464
+ "step": 680
465
+ },
466
+ {
467
+ "epoch": 0.46,
468
+ "learning_rate": 4.719192614212969e-05,
469
+ "loss": 1.4414,
470
+ "step": 690
471
+ },
472
+ {
473
+ "epoch": 0.46,
474
+ "learning_rate": 4.711155877115523e-05,
475
+ "loss": 1.493,
476
+ "step": 700
477
+ },
478
+ {
479
+ "epoch": 0.46,
480
+ "eval_loss": 1.427127480506897,
481
+ "eval_runtime": 20.5172,
482
+ "eval_samples_per_second": 23.834,
483
+ "eval_steps_per_second": 5.995,
484
+ "step": 700
485
+ },
486
+ {
487
+ "epoch": 0.47,
488
+ "learning_rate": 4.703012794066827e-05,
489
+ "loss": 1.4078,
490
+ "step": 710
491
+ },
492
+ {
493
+ "epoch": 0.48,
494
+ "learning_rate": 4.694763756709967e-05,
495
+ "loss": 1.4539,
496
+ "step": 720
497
+ },
498
+ {
499
+ "epoch": 0.48,
500
+ "learning_rate": 4.6864091617839235e-05,
501
+ "loss": 1.4458,
502
+ "step": 730
503
+ },
504
+ {
505
+ "epoch": 0.49,
506
+ "learning_rate": 4.677949411104485e-05,
507
+ "loss": 1.4001,
508
+ "step": 740
509
+ },
510
+ {
511
+ "epoch": 0.5,
512
+ "learning_rate": 4.669384911544927e-05,
513
+ "loss": 1.433,
514
+ "step": 750
515
+ },
516
+ {
517
+ "epoch": 0.5,
518
+ "learning_rate": 4.660716075016442e-05,
519
+ "loss": 1.4323,
520
+ "step": 760
521
+ },
522
+ {
523
+ "epoch": 0.51,
524
+ "learning_rate": 4.6519433184483245e-05,
525
+ "loss": 1.4052,
526
+ "step": 770
527
+ },
528
+ {
529
+ "epoch": 0.52,
530
+ "learning_rate": 4.6430670637679295e-05,
531
+ "loss": 1.4021,
532
+ "step": 780
533
+ },
534
+ {
535
+ "epoch": 0.52,
536
+ "learning_rate": 4.634087737880367e-05,
537
+ "loss": 1.4049,
538
+ "step": 790
539
+ },
540
+ {
541
+ "epoch": 0.53,
542
+ "learning_rate": 4.625005772647979e-05,
543
+ "loss": 1.3701,
544
+ "step": 800
545
+ },
546
+ {
547
+ "epoch": 0.53,
548
+ "eval_loss": 1.4250208139419556,
549
+ "eval_runtime": 20.0939,
550
+ "eval_samples_per_second": 24.336,
551
+ "eval_steps_per_second": 6.121,
552
+ "step": 800
553
+ },
554
+ {
555
+ "epoch": 0.54,
556
+ "learning_rate": 4.615821604869564e-05,
557
+ "loss": 1.4209,
558
+ "step": 810
559
+ },
560
+ {
561
+ "epoch": 0.54,
562
+ "learning_rate": 4.606535676259372e-05,
563
+ "loss": 1.4373,
564
+ "step": 820
565
+ },
566
+ {
567
+ "epoch": 0.55,
568
+ "learning_rate": 4.597148433425857e-05,
569
+ "loss": 1.4913,
570
+ "step": 830
571
+ },
572
+ {
573
+ "epoch": 0.56,
574
+ "learning_rate": 4.587660327850203e-05,
575
+ "loss": 1.434,
576
+ "step": 840
577
+ },
578
+ {
579
+ "epoch": 0.56,
580
+ "learning_rate": 4.578071815864602e-05,
581
+ "loss": 1.3932,
582
+ "step": 850
583
+ },
584
+ {
585
+ "epoch": 0.57,
586
+ "learning_rate": 4.5683833586303157e-05,
587
+ "loss": 1.4232,
588
+ "step": 860
589
+ },
590
+ {
591
+ "epoch": 0.58,
592
+ "learning_rate": 4.5585954221154856e-05,
593
+ "loss": 1.3651,
594
+ "step": 870
595
+ },
596
+ {
597
+ "epoch": 0.58,
598
+ "learning_rate": 4.548708477072733e-05,
599
+ "loss": 1.4009,
600
+ "step": 880
601
+ },
602
+ {
603
+ "epoch": 0.59,
604
+ "learning_rate": 4.5387229990165073e-05,
605
+ "loss": 1.428,
606
+ "step": 890
607
+ },
608
+ {
609
+ "epoch": 0.6,
610
+ "learning_rate": 4.528639468200226e-05,
611
+ "loss": 1.413,
612
+ "step": 900
613
+ },
614
+ {
615
+ "epoch": 0.6,
616
+ "eval_loss": 1.4226006269454956,
617
+ "eval_runtime": 20.161,
618
+ "eval_samples_per_second": 24.255,
619
+ "eval_steps_per_second": 6.101,
620
+ "step": 900
621
+ },
622
+ {
623
+ "epoch": 0.6,
624
+ "learning_rate": 4.51845836959317e-05,
625
+ "loss": 1.4328,
626
+ "step": 910
627
+ },
628
+ {
629
+ "epoch": 0.61,
630
+ "learning_rate": 4.508180192857162e-05,
631
+ "loss": 1.4262,
632
+ "step": 920
633
+ },
634
+ {
635
+ "epoch": 0.62,
636
+ "learning_rate": 4.497805432323015e-05,
637
+ "loss": 1.3677,
638
+ "step": 930
639
+ },
640
+ {
641
+ "epoch": 0.62,
642
+ "learning_rate": 4.487334586966756e-05,
643
+ "loss": 1.4546,
644
+ "step": 940
645
+ },
646
+ {
647
+ "epoch": 0.63,
648
+ "learning_rate": 4.476768160385632e-05,
649
+ "loss": 1.4011,
650
+ "step": 950
651
+ },
652
+ {
653
+ "epoch": 0.64,
654
+ "learning_rate": 4.466106660773885e-05,
655
+ "loss": 1.441,
656
+ "step": 960
657
+ },
658
+ {
659
+ "epoch": 0.64,
660
+ "learning_rate": 4.4553506008983126e-05,
661
+ "loss": 1.3946,
662
+ "step": 970
663
+ },
664
+ {
665
+ "epoch": 0.65,
666
+ "learning_rate": 4.4445004980736064e-05,
667
+ "loss": 1.4478,
668
+ "step": 980
669
+ },
670
+ {
671
+ "epoch": 0.66,
672
+ "learning_rate": 4.43355687413747e-05,
673
+ "loss": 1.4093,
674
+ "step": 990
675
+ },
676
+ {
677
+ "epoch": 0.66,
678
+ "learning_rate": 4.4225202554255227e-05,
679
+ "loss": 1.4285,
680
+ "step": 1000
681
+ },
682
+ {
683
+ "epoch": 0.66,
684
+ "eval_loss": 1.4204448461532593,
685
+ "eval_runtime": 19.9265,
686
+ "eval_samples_per_second": 24.54,
687
+ "eval_steps_per_second": 6.173,
688
+ "step": 1000
689
+ },
690
+ {
691
+ "epoch": 0.67,
692
+ "learning_rate": 4.411391172745984e-05,
693
+ "loss": 1.3971,
694
+ "step": 1010
695
+ },
696
+ {
697
+ "epoch": 0.68,
698
+ "learning_rate": 4.4001701613541456e-05,
699
+ "loss": 1.4024,
700
+ "step": 1020
701
+ },
702
+ {
703
+ "epoch": 0.68,
704
+ "learning_rate": 4.388857760926629e-05,
705
+ "loss": 1.3623,
706
+ "step": 1030
707
+ },
708
+ {
709
+ "epoch": 0.69,
710
+ "learning_rate": 4.3774545155354254e-05,
711
+ "loss": 1.3943,
712
+ "step": 1040
713
+ },
714
+ {
715
+ "epoch": 0.7,
716
+ "learning_rate": 4.3659609736217344e-05,
717
+ "loss": 1.4586,
718
+ "step": 1050
719
+ },
720
+ {
721
+ "epoch": 0.7,
722
+ "learning_rate": 4.354377687969581e-05,
723
+ "loss": 1.4178,
724
+ "step": 1060
725
+ },
726
+ {
727
+ "epoch": 0.71,
728
+ "learning_rate": 4.342705215679232e-05,
729
+ "loss": 1.4454,
730
+ "step": 1070
731
+ },
732
+ {
733
+ "epoch": 0.72,
734
+ "learning_rate": 4.330944118140407e-05,
735
+ "loss": 1.3769,
736
+ "step": 1080
737
+ },
738
+ {
739
+ "epoch": 0.72,
740
+ "learning_rate": 4.3190949610052645e-05,
741
+ "loss": 1.3912,
742
+ "step": 1090
743
+ },
744
+ {
745
+ "epoch": 0.73,
746
+ "learning_rate": 4.3071583141612135e-05,
747
+ "loss": 1.4116,
748
+ "step": 1100
749
+ },
750
+ {
751
+ "epoch": 0.73,
752
+ "eval_loss": 1.4190473556518555,
753
+ "eval_runtime": 19.9596,
754
+ "eval_samples_per_second": 24.499,
755
+ "eval_steps_per_second": 6.162,
756
+ "step": 1100
757
+ },
758
+ {
759
+ "epoch": 0.73,
760
+ "learning_rate": 4.295134751703493e-05,
761
+ "loss": 1.4019,
762
+ "step": 1110
763
+ },
764
+ {
765
+ "epoch": 0.74,
766
+ "learning_rate": 4.283024851907565e-05,
767
+ "loss": 1.378,
768
+ "step": 1120
769
+ },
770
+ {
771
+ "epoch": 0.75,
772
+ "learning_rate": 4.2708291972013026e-05,
773
+ "loss": 1.432,
774
+ "step": 1130
775
+ },
776
+ {
777
+ "epoch": 0.75,
778
+ "learning_rate": 4.2585483741369755e-05,
779
+ "loss": 1.4531,
780
+ "step": 1140
781
+ },
782
+ {
783
+ "epoch": 0.76,
784
+ "learning_rate": 4.2461829733630435e-05,
785
+ "loss": 1.4455,
786
+ "step": 1150
787
+ },
788
+ {
789
+ "epoch": 0.77,
790
+ "learning_rate": 4.233733589595746e-05,
791
+ "loss": 1.4081,
792
+ "step": 1160
793
+ },
794
+ {
795
+ "epoch": 0.77,
796
+ "learning_rate": 4.2212008215905e-05,
797
+ "loss": 1.4344,
798
+ "step": 1170
799
+ },
800
+ {
801
+ "epoch": 0.78,
802
+ "learning_rate": 4.208585272113102e-05,
803
+ "loss": 1.3935,
804
+ "step": 1180
805
+ },
806
+ {
807
+ "epoch": 0.79,
808
+ "learning_rate": 4.195887547910741e-05,
809
+ "loss": 1.4161,
810
+ "step": 1190
811
+ },
812
+ {
813
+ "epoch": 0.79,
814
+ "learning_rate": 4.1831082596828106e-05,
815
+ "loss": 1.4185,
816
+ "step": 1200
817
+ },
818
+ {
819
+ "epoch": 0.79,
820
+ "eval_loss": 1.4168447256088257,
821
+ "eval_runtime": 19.9431,
822
+ "eval_samples_per_second": 24.52,
823
+ "eval_steps_per_second": 6.168,
824
+ "step": 1200
825
+ },
826
+ {
827
+ "epoch": 0.8,
828
+ "learning_rate": 4.1702480220515475e-05,
829
+ "loss": 1.3714,
830
+ "step": 1210
831
+ },
832
+ {
833
+ "epoch": 0.81,
834
+ "learning_rate": 4.157307453532457e-05,
835
+ "loss": 1.4062,
836
+ "step": 1220
837
+ },
838
+ {
839
+ "epoch": 0.81,
840
+ "learning_rate": 4.144287176504582e-05,
841
+ "loss": 1.4007,
842
+ "step": 1230
843
+ },
844
+ {
845
+ "epoch": 0.82,
846
+ "learning_rate": 4.131187817180554e-05,
847
+ "loss": 1.4153,
848
+ "step": 1240
849
+ },
850
+ {
851
+ "epoch": 0.83,
852
+ "learning_rate": 4.118010005576485e-05,
853
+ "loss": 1.3619,
854
+ "step": 1250
855
+ },
856
+ {
857
+ "epoch": 0.83,
858
+ "learning_rate": 4.104754375481664e-05,
859
+ "loss": 1.507,
860
+ "step": 1260
861
+ },
862
+ {
863
+ "epoch": 0.84,
864
+ "learning_rate": 4.0914215644280754e-05,
865
+ "loss": 1.4487,
866
+ "step": 1270
867
+ },
868
+ {
869
+ "epoch": 0.85,
870
+ "learning_rate": 4.0780122136597323e-05,
871
+ "loss": 1.409,
872
+ "step": 1280
873
+ },
874
+ {
875
+ "epoch": 0.85,
876
+ "learning_rate": 4.064526968101844e-05,
877
+ "loss": 1.3994,
878
+ "step": 1290
879
+ },
880
+ {
881
+ "epoch": 0.86,
882
+ "learning_rate": 4.050966476329793e-05,
883
+ "loss": 1.4285,
884
+ "step": 1300
885
+ },
886
+ {
887
+ "epoch": 0.86,
888
+ "eval_loss": 1.4150002002716064,
889
+ "eval_runtime": 19.9449,
890
+ "eval_samples_per_second": 24.518,
891
+ "eval_steps_per_second": 6.167,
892
+ "step": 1300
893
+ },
894
+ {
895
+ "epoch": 0.87,
896
+ "learning_rate": 4.037331390537939e-05,
897
+ "loss": 1.4562,
898
+ "step": 1310
899
+ },
900
+ {
901
+ "epoch": 0.87,
902
+ "learning_rate": 4.023622366508261e-05,
903
+ "loss": 1.4202,
904
+ "step": 1320
905
+ },
906
+ {
907
+ "epoch": 0.88,
908
+ "learning_rate": 4.0098400635788035e-05,
909
+ "loss": 1.381,
910
+ "step": 1330
911
+ },
912
+ {
913
+ "epoch": 0.89,
914
+ "learning_rate": 3.99598514461198e-05,
915
+ "loss": 1.4656,
916
+ "step": 1340
917
+ },
918
+ {
919
+ "epoch": 0.89,
920
+ "learning_rate": 3.9820582759626825e-05,
921
+ "loss": 1.4094,
922
+ "step": 1350
923
+ },
924
+ {
925
+ "epoch": 0.9,
926
+ "learning_rate": 3.968060127446236e-05,
927
+ "loss": 1.4183,
928
+ "step": 1360
929
+ },
930
+ {
931
+ "epoch": 0.91,
932
+ "learning_rate": 3.953991372306186e-05,
933
+ "loss": 1.411,
934
+ "step": 1370
935
+ },
936
+ {
937
+ "epoch": 0.91,
938
+ "learning_rate": 3.9398526871819154e-05,
939
+ "loss": 1.418,
940
+ "step": 1380
941
+ },
942
+ {
943
+ "epoch": 0.92,
944
+ "learning_rate": 3.925644752076101e-05,
945
+ "loss": 1.4751,
946
+ "step": 1390
947
+ },
948
+ {
949
+ "epoch": 0.93,
950
+ "learning_rate": 3.911368250322014e-05,
951
+ "loss": 1.4246,
952
+ "step": 1400
953
+ },
954
+ {
955
+ "epoch": 0.93,
956
+ "eval_loss": 1.4129770994186401,
957
+ "eval_runtime": 19.9327,
958
+ "eval_samples_per_second": 24.533,
959
+ "eval_steps_per_second": 6.171,
960
+ "step": 1400
961
+ },
962
+ {
963
+ "epoch": 0.93,
964
+ "learning_rate": 3.897023868550649e-05,
965
+ "loss": 1.4102,
966
+ "step": 1410
967
+ },
968
+ {
969
+ "epoch": 0.94,
970
+ "learning_rate": 3.882612296657701e-05,
971
+ "loss": 1.3871,
972
+ "step": 1420
973
+ },
974
+ {
975
+ "epoch": 0.95,
976
+ "learning_rate": 3.8681342277703906e-05,
977
+ "loss": 1.4156,
978
+ "step": 1430
979
+ },
980
+ {
981
+ "epoch": 0.95,
982
+ "learning_rate": 3.853590358214119e-05,
983
+ "loss": 1.433,
984
+ "step": 1440
985
+ },
986
+ {
987
+ "epoch": 0.96,
988
+ "learning_rate": 3.8389813874789856e-05,
989
+ "loss": 1.4372,
990
+ "step": 1450
991
+ },
992
+ {
993
+ "epoch": 0.97,
994
+ "learning_rate": 3.8243080181861435e-05,
995
+ "loss": 1.3978,
996
+ "step": 1460
997
+ },
998
+ {
999
+ "epoch": 0.97,
1000
+ "learning_rate": 3.809570956054004e-05,
1001
+ "loss": 1.3964,
1002
+ "step": 1470
1003
+ },
1004
+ {
1005
+ "epoch": 0.98,
1006
+ "learning_rate": 3.794770909864298e-05,
1007
+ "loss": 1.4332,
1008
+ "step": 1480
1009
+ },
1010
+ {
1011
+ "epoch": 0.99,
1012
+ "learning_rate": 3.779908591427988e-05,
1013
+ "loss": 1.4044,
1014
+ "step": 1490
1015
+ },
1016
+ {
1017
+ "epoch": 0.99,
1018
+ "learning_rate": 3.764984715551032e-05,
1019
+ "loss": 1.4301,
1020
+ "step": 1500
1021
+ },
1022
+ {
1023
+ "epoch": 0.99,
1024
+ "eval_loss": 1.412743330001831,
1025
+ "eval_runtime": 19.9577,
1026
+ "eval_samples_per_second": 24.502,
1027
+ "eval_steps_per_second": 6.163,
1028
+ "step": 1500
1029
+ },
1030
+ {
1031
+ "epoch": 1.0,
1032
+ "learning_rate": 3.7500000000000003e-05,
1033
+ "loss": 1.4721,
1034
+ "step": 1510
1035
+ },
1036
+ {
1037
+ "epoch": 1.01,
1038
+ "learning_rate": 3.734955165467563e-05,
1039
+ "loss": 1.3905,
1040
+ "step": 1520
1041
+ },
1042
+ {
1043
+ "epoch": 1.01,
1044
+ "learning_rate": 3.719850935537821e-05,
1045
+ "loss": 1.423,
1046
+ "step": 1530
1047
+ },
1048
+ {
1049
+ "epoch": 1.02,
1050
+ "learning_rate": 3.70468803665151e-05,
1051
+ "loss": 1.404,
1052
+ "step": 1540
1053
+ },
1054
+ {
1055
+ "epoch": 1.03,
1056
+ "learning_rate": 3.6894671980710574e-05,
1057
+ "loss": 1.4042,
1058
+ "step": 1550
1059
+ },
1060
+ {
1061
+ "epoch": 1.03,
1062
+ "learning_rate": 3.674189151845515e-05,
1063
+ "loss": 1.4158,
1064
+ "step": 1560
1065
+ },
1066
+ {
1067
+ "epoch": 1.04,
1068
+ "learning_rate": 3.6588546327753425e-05,
1069
+ "loss": 1.409,
1070
+ "step": 1570
1071
+ },
1072
+ {
1073
+ "epoch": 1.05,
1074
+ "learning_rate": 3.6434643783770736e-05,
1075
+ "loss": 1.3764,
1076
+ "step": 1580
1077
+ },
1078
+ {
1079
+ "epoch": 1.05,
1080
+ "learning_rate": 3.6280191288478436e-05,
1081
+ "loss": 1.4021,
1082
+ "step": 1590
1083
+ },
1084
+ {
1085
+ "epoch": 1.06,
1086
+ "learning_rate": 3.612519627029787e-05,
1087
+ "loss": 1.3973,
1088
+ "step": 1600
1089
+ },
1090
+ {
1091
+ "epoch": 1.06,
1092
+ "eval_loss": 1.411142349243164,
1093
+ "eval_runtime": 19.9375,
1094
+ "eval_samples_per_second": 24.527,
1095
+ "eval_steps_per_second": 6.169,
1096
+ "step": 1600
1097
+ },
1098
+ {
1099
+ "epoch": 1.07,
1100
+ "learning_rate": 3.596966618374313e-05,
1101
+ "loss": 1.3985,
1102
+ "step": 1610
1103
+ },
1104
+ {
1105
+ "epoch": 1.07,
1106
+ "learning_rate": 3.5813608509062526e-05,
1107
+ "loss": 1.3444,
1108
+ "step": 1620
1109
+ },
1110
+ {
1111
+ "epoch": 1.08,
1112
+ "learning_rate": 3.5657030751878814e-05,
1113
+ "loss": 1.4207,
1114
+ "step": 1630
1115
+ },
1116
+ {
1117
+ "epoch": 1.09,
1118
+ "learning_rate": 3.5499940442828206e-05,
1119
+ "loss": 1.4304,
1120
+ "step": 1640
1121
+ },
1122
+ {
1123
+ "epoch": 1.09,
1124
+ "learning_rate": 3.534234513719821e-05,
1125
+ "loss": 1.3924,
1126
+ "step": 1650
1127
+ },
1128
+ {
1129
+ "epoch": 1.1,
1130
+ "learning_rate": 3.51842524145642e-05,
1131
+ "loss": 1.3686,
1132
+ "step": 1660
1133
+ },
1134
+ {
1135
+ "epoch": 1.11,
1136
+ "learning_rate": 3.502566987842496e-05,
1137
+ "loss": 1.4248,
1138
+ "step": 1670
1139
+ },
1140
+ {
1141
+ "epoch": 1.11,
1142
+ "learning_rate": 3.4866605155836915e-05,
1143
+ "loss": 1.3906,
1144
+ "step": 1680
1145
+ },
1146
+ {
1147
+ "epoch": 1.12,
1148
+ "learning_rate": 3.470706589704734e-05,
1149
+ "loss": 1.444,
1150
+ "step": 1690
1151
+ },
1152
+ {
1153
+ "epoch": 1.13,
1154
+ "learning_rate": 3.4547059775126445e-05,
1155
+ "loss": 1.3589,
1156
+ "step": 1700
1157
+ },
1158
+ {
1159
+ "epoch": 1.13,
1160
+ "eval_loss": 1.4102592468261719,
1161
+ "eval_runtime": 19.9452,
1162
+ "eval_samples_per_second": 24.517,
1163
+ "eval_steps_per_second": 6.167,
1164
+ "step": 1700
1165
+ },
1166
+ {
1167
+ "epoch": 1.13,
1168
+ "learning_rate": 3.438659448559825e-05,
1169
+ "loss": 1.319,
1170
+ "step": 1710
1171
+ },
1172
+ {
1173
+ "epoch": 1.14,
1174
+ "learning_rate": 3.422567774607058e-05,
1175
+ "loss": 1.406,
1176
+ "step": 1720
1177
+ },
1178
+ {
1179
+ "epoch": 1.15,
1180
+ "learning_rate": 3.406431729586382e-05,
1181
+ "loss": 1.4114,
1182
+ "step": 1730
1183
+ },
1184
+ {
1185
+ "epoch": 1.15,
1186
+ "learning_rate": 3.390252089563867e-05,
1187
+ "loss": 1.3722,
1188
+ "step": 1740
1189
+ },
1190
+ {
1191
+ "epoch": 1.16,
1192
+ "learning_rate": 3.3740296327022984e-05,
1193
+ "loss": 1.3528,
1194
+ "step": 1750
1195
+ },
1196
+ {
1197
+ "epoch": 1.17,
1198
+ "learning_rate": 3.35776513922374e-05,
1199
+ "loss": 1.4274,
1200
+ "step": 1760
1201
+ },
1202
+ {
1203
+ "epoch": 1.17,
1204
+ "learning_rate": 3.341459391372016e-05,
1205
+ "loss": 1.4324,
1206
+ "step": 1770
1207
+ },
1208
+ {
1209
+ "epoch": 1.18,
1210
+ "learning_rate": 3.32511317337509e-05,
1211
+ "loss": 1.409,
1212
+ "step": 1780
1213
+ },
1214
+ {
1215
+ "epoch": 1.19,
1216
+ "learning_rate": 3.30872727140734e-05,
1217
+ "loss": 1.3464,
1218
+ "step": 1790
1219
+ },
1220
+ {
1221
+ "epoch": 1.19,
1222
+ "learning_rate": 3.292302473551757e-05,
1223
+ "loss": 1.4144,
1224
+ "step": 1800
1225
+ },
1226
+ {
1227
+ "epoch": 1.19,
1228
+ "eval_loss": 1.4091637134552002,
1229
+ "eval_runtime": 19.9455,
1230
+ "eval_samples_per_second": 24.517,
1231
+ "eval_steps_per_second": 6.167,
1232
+ "step": 1800
1233
+ },
1234
+ {
1235
+ "epoch": 1.2,
1236
+ "learning_rate": 3.2758395697620334e-05,
1237
+ "loss": 1.4139,
1238
+ "step": 1810
1239
+ },
1240
+ {
1241
+ "epoch": 1.2,
1242
+ "learning_rate": 3.259339351824575e-05,
1243
+ "loss": 1.4247,
1244
+ "step": 1820
1245
+ },
1246
+ {
1247
+ "epoch": 1.21,
1248
+ "learning_rate": 3.2428026133204184e-05,
1249
+ "loss": 1.4241,
1250
+ "step": 1830
1251
+ },
1252
+ {
1253
+ "epoch": 1.22,
1254
+ "learning_rate": 3.226230149587063e-05,
1255
+ "loss": 1.3941,
1256
+ "step": 1840
1257
+ },
1258
+ {
1259
+ "epoch": 1.22,
1260
+ "learning_rate": 3.20962275768022e-05,
1261
+ "loss": 1.4238,
1262
+ "step": 1850
1263
+ },
1264
+ {
1265
+ "epoch": 1.23,
1266
+ "learning_rate": 3.1929812363354766e-05,
1267
+ "loss": 1.382,
1268
+ "step": 1860
1269
+ },
1270
+ {
1271
+ "epoch": 1.24,
1272
+ "learning_rate": 3.1763063859298845e-05,
1273
+ "loss": 1.4124,
1274
+ "step": 1870
1275
+ },
1276
+ {
1277
+ "epoch": 1.24,
1278
+ "learning_rate": 3.159599008443459e-05,
1279
+ "loss": 1.3963,
1280
+ "step": 1880
1281
+ },
1282
+ {
1283
+ "epoch": 1.25,
1284
+ "learning_rate": 3.142859907420615e-05,
1285
+ "loss": 1.3542,
1286
+ "step": 1890
1287
+ },
1288
+ {
1289
+ "epoch": 1.26,
1290
+ "learning_rate": 3.126089887931515e-05,
1291
+ "loss": 1.3852,
1292
+ "step": 1900
1293
+ },
1294
+ {
1295
+ "epoch": 1.26,
1296
+ "eval_loss": 1.4086569547653198,
1297
+ "eval_runtime": 19.948,
1298
+ "eval_samples_per_second": 24.514,
1299
+ "eval_steps_per_second": 6.166,
1300
+ "step": 1900
1301
+ },
1302
+ {
1303
+ "epoch": 1.26,
1304
+ "learning_rate": 3.109289756533349e-05,
1305
+ "loss": 1.3972,
1306
+ "step": 1910
1307
+ },
1308
+ {
1309
+ "epoch": 1.27,
1310
+ "learning_rate": 3.092460321231547e-05,
1311
+ "loss": 1.3783,
1312
+ "step": 1920
1313
+ },
1314
+ {
1315
+ "epoch": 1.28,
1316
+ "learning_rate": 3.075602391440918e-05,
1317
+ "loss": 1.4122,
1318
+ "step": 1930
1319
+ },
1320
+ {
1321
+ "epoch": 1.28,
1322
+ "learning_rate": 3.058716777946713e-05,
1323
+ "loss": 1.4105,
1324
+ "step": 1940
1325
+ },
1326
+ {
1327
+ "epoch": 1.29,
1328
+ "learning_rate": 3.0418042928656414e-05,
1329
+ "loss": 1.4091,
1330
+ "step": 1950
1331
+ },
1332
+ {
1333
+ "epoch": 1.3,
1334
+ "learning_rate": 3.0248657496068027e-05,
1335
+ "loss": 1.4067,
1336
+ "step": 1960
1337
+ },
1338
+ {
1339
+ "epoch": 1.3,
1340
+ "learning_rate": 3.0079019628325706e-05,
1341
+ "loss": 1.4172,
1342
+ "step": 1970
1343
+ },
1344
+ {
1345
+ "epoch": 1.31,
1346
+ "learning_rate": 2.990913748419411e-05,
1347
+ "loss": 1.3803,
1348
+ "step": 1980
1349
+ },
1350
+ {
1351
+ "epoch": 1.32,
1352
+ "learning_rate": 2.97390192341864e-05,
1353
+ "loss": 1.4096,
1354
+ "step": 1990
1355
+ },
1356
+ {
1357
+ "epoch": 1.32,
1358
+ "learning_rate": 2.9568673060171326e-05,
1359
+ "loss": 1.3774,
1360
+ "step": 2000
1361
+ },
1362
+ {
1363
+ "epoch": 1.32,
1364
+ "eval_loss": 1.407130479812622,
1365
+ "eval_runtime": 19.928,
1366
+ "eval_samples_per_second": 24.538,
1367
+ "eval_steps_per_second": 6.172,
1368
+ "step": 2000
1369
+ },
1370
+ {
1371
+ "epoch": 1.33,
1372
+ "learning_rate": 2.9398107154979638e-05,
1373
+ "loss": 1.3729,
1374
+ "step": 2010
1375
+ },
1376
+ {
1377
+ "epoch": 1.34,
1378
+ "learning_rate": 2.922732972201014e-05,
1379
+ "loss": 1.3687,
1380
+ "step": 2020
1381
+ },
1382
+ {
1383
+ "epoch": 1.34,
1384
+ "learning_rate": 2.9056348974835067e-05,
1385
+ "loss": 1.3946,
1386
+ "step": 2030
1387
+ },
1388
+ {
1389
+ "epoch": 1.35,
1390
+ "learning_rate": 2.8885173136805127e-05,
1391
+ "loss": 1.3922,
1392
+ "step": 2040
1393
+ },
1394
+ {
1395
+ "epoch": 1.36,
1396
+ "learning_rate": 2.8713810440653926e-05,
1397
+ "loss": 1.3631,
1398
+ "step": 2050
1399
+ },
1400
+ {
1401
+ "epoch": 1.36,
1402
+ "learning_rate": 2.8542269128102063e-05,
1403
+ "loss": 1.4193,
1404
+ "step": 2060
1405
+ },
1406
+ {
1407
+ "epoch": 1.37,
1408
+ "learning_rate": 2.837055744946072e-05,
1409
+ "loss": 1.3776,
1410
+ "step": 2070
1411
+ },
1412
+ {
1413
+ "epoch": 1.38,
1414
+ "learning_rate": 2.819868366323488e-05,
1415
+ "loss": 1.4099,
1416
+ "step": 2080
1417
+ },
1418
+ {
1419
+ "epoch": 1.38,
1420
+ "learning_rate": 2.8026656035726095e-05,
1421
+ "loss": 1.41,
1422
+ "step": 2090
1423
+ },
1424
+ {
1425
+ "epoch": 1.39,
1426
+ "learning_rate": 2.7854482840634965e-05,
1427
+ "loss": 1.4604,
1428
+ "step": 2100
1429
+ },
1430
+ {
1431
+ "epoch": 1.39,
1432
+ "eval_loss": 1.406220555305481,
1433
+ "eval_runtime": 19.947,
1434
+ "eval_samples_per_second": 24.515,
1435
+ "eval_steps_per_second": 6.166,
1436
+ "step": 2100
1437
+ },
1438
+ {
1439
+ "epoch": 1.4,
1440
+ "learning_rate": 2.7682172358663173e-05,
1441
+ "loss": 1.4485,
1442
+ "step": 2110
1443
+ },
1444
+ {
1445
+ "epoch": 1.4,
1446
+ "learning_rate": 2.7509732877115257e-05,
1447
+ "loss": 1.4445,
1448
+ "step": 2120
1449
+ },
1450
+ {
1451
+ "epoch": 1.41,
1452
+ "learning_rate": 2.73371726895e-05,
1453
+ "loss": 1.3889,
1454
+ "step": 2130
1455
+ },
1456
+ {
1457
+ "epoch": 1.42,
1458
+ "learning_rate": 2.716450009513158e-05,
1459
+ "loss": 1.4167,
1460
+ "step": 2140
1461
+ },
1462
+ {
1463
+ "epoch": 1.42,
1464
+ "learning_rate": 2.6991723398730383e-05,
1465
+ "loss": 1.3388,
1466
+ "step": 2150
1467
+ },
1468
+ {
1469
+ "epoch": 1.43,
1470
+ "learning_rate": 2.68188509100236e-05,
1471
+ "loss": 1.4379,
1472
+ "step": 2160
1473
+ },
1474
+ {
1475
+ "epoch": 1.44,
1476
+ "learning_rate": 2.6645890943345585e-05,
1477
+ "loss": 1.4119,
1478
+ "step": 2170
1479
+ },
1480
+ {
1481
+ "epoch": 1.44,
1482
+ "learning_rate": 2.6472851817237948e-05,
1483
+ "loss": 1.3961,
1484
+ "step": 2180
1485
+ },
1486
+ {
1487
+ "epoch": 1.45,
1488
+ "learning_rate": 2.6299741854049508e-05,
1489
+ "loss": 1.3999,
1490
+ "step": 2190
1491
+ },
1492
+ {
1493
+ "epoch": 1.46,
1494
+ "learning_rate": 2.6126569379535985e-05,
1495
+ "loss": 1.3739,
1496
+ "step": 2200
1497
+ },
1498
+ {
1499
+ "epoch": 1.46,
1500
+ "eval_loss": 1.4052706956863403,
1501
+ "eval_runtime": 19.9293,
1502
+ "eval_samples_per_second": 24.537,
1503
+ "eval_steps_per_second": 6.172,
1504
+ "step": 2200
1505
+ },
1506
+ {
1507
+ "epoch": 1.46,
1508
+ "learning_rate": 2.5953342722459594e-05,
1509
+ "loss": 1.4256,
1510
+ "step": 2210
1511
+ },
1512
+ {
1513
+ "epoch": 1.47,
1514
+ "learning_rate": 2.5780070214188478e-05,
1515
+ "loss": 1.4615,
1516
+ "step": 2220
1517
+ },
1518
+ {
1519
+ "epoch": 1.48,
1520
+ "learning_rate": 2.5606760188296004e-05,
1521
+ "loss": 1.3877,
1522
+ "step": 2230
1523
+ },
1524
+ {
1525
+ "epoch": 1.48,
1526
+ "learning_rate": 2.5433420980159944e-05,
1527
+ "loss": 1.3752,
1528
+ "step": 2240
1529
+ },
1530
+ {
1531
+ "epoch": 1.49,
1532
+ "learning_rate": 2.526006092656161e-05,
1533
+ "loss": 1.4084,
1534
+ "step": 2250
1535
+ },
1536
+ {
1537
+ "epoch": 1.5,
1538
+ "learning_rate": 2.508668836528486e-05,
1539
+ "loss": 1.3921,
1540
+ "step": 2260
1541
+ },
1542
+ {
1543
+ "epoch": 1.5,
1544
+ "learning_rate": 2.491331163471514e-05,
1545
+ "loss": 1.4104,
1546
+ "step": 2270
1547
+ },
1548
+ {
1549
+ "epoch": 1.51,
1550
+ "learning_rate": 2.4739939073438397e-05,
1551
+ "loss": 1.4053,
1552
+ "step": 2280
1553
+ },
1554
+ {
1555
+ "epoch": 1.52,
1556
+ "learning_rate": 2.456657901984006e-05,
1557
+ "loss": 1.381,
1558
+ "step": 2290
1559
+ },
1560
+ {
1561
+ "epoch": 1.52,
1562
+ "learning_rate": 2.4393239811704e-05,
1563
+ "loss": 1.3752,
1564
+ "step": 2300
1565
+ },
1566
+ {
1567
+ "epoch": 1.52,
1568
+ "eval_loss": 1.4050989151000977,
1569
+ "eval_runtime": 19.9544,
1570
+ "eval_samples_per_second": 24.506,
1571
+ "eval_steps_per_second": 6.164,
1572
+ "step": 2300
1573
+ },
1574
+ {
1575
+ "epoch": 1.53,
1576
+ "learning_rate": 2.4219929785811518e-05,
1577
+ "loss": 1.4023,
1578
+ "step": 2310
1579
+ },
1580
+ {
1581
+ "epoch": 1.54,
1582
+ "learning_rate": 2.4046657277540412e-05,
1583
+ "loss": 1.3642,
1584
+ "step": 2320
1585
+ },
1586
+ {
1587
+ "epoch": 1.54,
1588
+ "learning_rate": 2.3873430620464024e-05,
1589
+ "loss": 1.3977,
1590
+ "step": 2330
1591
+ },
1592
+ {
1593
+ "epoch": 1.55,
1594
+ "learning_rate": 2.3700258145950495e-05,
1595
+ "loss": 1.3905,
1596
+ "step": 2340
1597
+ },
1598
+ {
1599
+ "epoch": 1.56,
1600
+ "learning_rate": 2.3527148182762054e-05,
1601
+ "loss": 1.4022,
1602
+ "step": 2350
1603
+ },
1604
+ {
1605
+ "epoch": 1.56,
1606
+ "learning_rate": 2.335410905665442e-05,
1607
+ "loss": 1.4162,
1608
+ "step": 2360
1609
+ },
1610
+ {
1611
+ "epoch": 1.57,
1612
+ "learning_rate": 2.3181149089976405e-05,
1613
+ "loss": 1.3877,
1614
+ "step": 2370
1615
+ },
1616
+ {
1617
+ "epoch": 1.58,
1618
+ "learning_rate": 2.3008276601269623e-05,
1619
+ "loss": 1.3704,
1620
+ "step": 2380
1621
+ },
1622
+ {
1623
+ "epoch": 1.58,
1624
+ "learning_rate": 2.283549990486842e-05,
1625
+ "loss": 1.3725,
1626
+ "step": 2390
1627
+ },
1628
+ {
1629
+ "epoch": 1.59,
1630
+ "learning_rate": 2.2662827310499995e-05,
1631
+ "loss": 1.4232,
1632
+ "step": 2400
1633
+ },
1634
+ {
1635
+ "epoch": 1.59,
1636
+ "eval_loss": 1.4044643640518188,
1637
+ "eval_runtime": 19.9565,
1638
+ "eval_samples_per_second": 24.503,
1639
+ "eval_steps_per_second": 6.163,
1640
+ "step": 2400
1641
+ },
1642
+ {
1643
+ "epoch": 1.6,
1644
+ "learning_rate": 2.249026712288474e-05,
1645
+ "loss": 1.3916,
1646
+ "step": 2410
1647
+ },
1648
+ {
1649
+ "epoch": 1.6,
1650
+ "learning_rate": 2.2317827641336833e-05,
1651
+ "loss": 1.384,
1652
+ "step": 2420
1653
+ },
1654
+ {
1655
+ "epoch": 1.61,
1656
+ "learning_rate": 2.2145517159365044e-05,
1657
+ "loss": 1.3969,
1658
+ "step": 2430
1659
+ },
1660
+ {
1661
+ "epoch": 1.62,
1662
+ "learning_rate": 2.197334396427391e-05,
1663
+ "loss": 1.3742,
1664
+ "step": 2440
1665
+ },
1666
+ {
1667
+ "epoch": 1.62,
1668
+ "learning_rate": 2.1801316336765126e-05,
1669
+ "loss": 1.3901,
1670
+ "step": 2450
1671
+ },
1672
+ {
1673
+ "epoch": 1.63,
1674
+ "learning_rate": 2.162944255053928e-05,
1675
+ "loss": 1.3853,
1676
+ "step": 2460
1677
+ },
1678
+ {
1679
+ "epoch": 1.64,
1680
+ "learning_rate": 2.145773087189794e-05,
1681
+ "loss": 1.3709,
1682
+ "step": 2470
1683
+ },
1684
+ {
1685
+ "epoch": 1.64,
1686
+ "learning_rate": 2.128618955934608e-05,
1687
+ "loss": 1.3758,
1688
+ "step": 2480
1689
+ },
1690
+ {
1691
+ "epoch": 1.65,
1692
+ "learning_rate": 2.1114826863194882e-05,
1693
+ "loss": 1.3561,
1694
+ "step": 2490
1695
+ },
1696
+ {
1697
+ "epoch": 1.66,
1698
+ "learning_rate": 2.0943651025164932e-05,
1699
+ "loss": 1.3774,
1700
+ "step": 2500
1701
+ },
1702
+ {
1703
+ "epoch": 1.66,
1704
+ "eval_loss": 1.4048223495483398,
1705
+ "eval_runtime": 19.9312,
1706
+ "eval_samples_per_second": 24.534,
1707
+ "eval_steps_per_second": 6.171,
1708
+ "step": 2500
1709
+ },
1710
+ {
1711
+ "epoch": 1.66,
1712
+ "learning_rate": 2.0772670277989864e-05,
1713
+ "loss": 1.3961,
1714
+ "step": 2510
1715
+ },
1716
+ {
1717
+ "epoch": 1.67,
1718
+ "learning_rate": 2.060189284502037e-05,
1719
+ "loss": 1.3794,
1720
+ "step": 2520
1721
+ },
1722
+ {
1723
+ "epoch": 1.68,
1724
+ "learning_rate": 2.0431326939828686e-05,
1725
+ "loss": 1.4147,
1726
+ "step": 2530
1727
+ },
1728
+ {
1729
+ "epoch": 1.68,
1730
+ "learning_rate": 2.0260980765813604e-05,
1731
+ "loss": 1.4336,
1732
+ "step": 2540
1733
+ },
1734
+ {
1735
+ "epoch": 1.69,
1736
+ "learning_rate": 2.0090862515805898e-05,
1737
+ "loss": 1.4228,
1738
+ "step": 2550
1739
+ },
1740
+ {
1741
+ "epoch": 1.69,
1742
+ "learning_rate": 1.99209803716743e-05,
1743
+ "loss": 1.4188,
1744
+ "step": 2560
1745
+ },
1746
+ {
1747
+ "epoch": 1.7,
1748
+ "learning_rate": 1.975134250393198e-05,
1749
+ "loss": 1.4492,
1750
+ "step": 2570
1751
+ },
1752
+ {
1753
+ "epoch": 1.71,
1754
+ "learning_rate": 1.9581957071343592e-05,
1755
+ "loss": 1.4492,
1756
+ "step": 2580
1757
+ },
1758
+ {
1759
+ "epoch": 1.71,
1760
+ "learning_rate": 1.9412832220532867e-05,
1761
+ "loss": 1.4261,
1762
+ "step": 2590
1763
+ },
1764
+ {
1765
+ "epoch": 1.72,
1766
+ "learning_rate": 1.9243976085590824e-05,
1767
+ "loss": 1.412,
1768
+ "step": 2600
1769
+ },
1770
+ {
1771
+ "epoch": 1.72,
1772
+ "eval_loss": 1.4038400650024414,
1773
+ "eval_runtime": 19.9456,
1774
+ "eval_samples_per_second": 24.517,
1775
+ "eval_steps_per_second": 6.167,
1776
+ "step": 2600
1777
+ },
1778
+ {
1779
+ "epoch": 1.73,
1780
+ "learning_rate": 1.9075396787684533e-05,
1781
+ "loss": 1.3858,
1782
+ "step": 2610
1783
+ },
1784
+ {
1785
+ "epoch": 1.73,
1786
+ "learning_rate": 1.8907102434666523e-05,
1787
+ "loss": 1.3648,
1788
+ "step": 2620
1789
+ },
1790
+ {
1791
+ "epoch": 1.74,
1792
+ "learning_rate": 1.8739101120684866e-05,
1793
+ "loss": 1.4267,
1794
+ "step": 2630
1795
+ },
1796
+ {
1797
+ "epoch": 1.75,
1798
+ "learning_rate": 1.8571400925793855e-05,
1799
+ "loss": 1.4115,
1800
+ "step": 2640
1801
+ },
1802
+ {
1803
+ "epoch": 1.75,
1804
+ "learning_rate": 1.840400991556541e-05,
1805
+ "loss": 1.3767,
1806
+ "step": 2650
1807
+ },
1808
+ {
1809
+ "epoch": 1.76,
1810
+ "learning_rate": 1.8236936140701165e-05,
1811
+ "loss": 1.3934,
1812
+ "step": 2660
1813
+ },
1814
+ {
1815
+ "epoch": 1.77,
1816
+ "learning_rate": 1.807018763664524e-05,
1817
+ "loss": 1.368,
1818
+ "step": 2670
1819
+ },
1820
+ {
1821
+ "epoch": 1.77,
1822
+ "learning_rate": 1.7903772423197806e-05,
1823
+ "loss": 1.3925,
1824
+ "step": 2680
1825
+ },
1826
+ {
1827
+ "epoch": 1.78,
1828
+ "learning_rate": 1.773769850412937e-05,
1829
+ "loss": 1.3786,
1830
+ "step": 2690
1831
+ },
1832
+ {
1833
+ "epoch": 1.79,
1834
+ "learning_rate": 1.7571973866795815e-05,
1835
+ "loss": 1.4204,
1836
+ "step": 2700
1837
+ },
1838
+ {
1839
+ "epoch": 1.79,
1840
+ "eval_loss": 1.4035720825195312,
1841
+ "eval_runtime": 19.9322,
1842
+ "eval_samples_per_second": 24.533,
1843
+ "eval_steps_per_second": 6.171,
1844
+ "step": 2700
1845
+ },
1846
+ {
1847
+ "epoch": 1.79,
1848
+ "learning_rate": 1.7406606481754258e-05,
1849
+ "loss": 1.3907,
1850
+ "step": 2710
1851
+ },
1852
+ {
1853
+ "epoch": 1.8,
1854
+ "learning_rate": 1.724160430237967e-05,
1855
+ "loss": 1.3598,
1856
+ "step": 2720
1857
+ },
1858
+ {
1859
+ "epoch": 1.81,
1860
+ "learning_rate": 1.7076975264482434e-05,
1861
+ "loss": 1.4157,
1862
+ "step": 2730
1863
+ },
1864
+ {
1865
+ "epoch": 1.81,
1866
+ "learning_rate": 1.6912727285926605e-05,
1867
+ "loss": 1.3922,
1868
+ "step": 2740
1869
+ },
1870
+ {
1871
+ "epoch": 1.82,
1872
+ "learning_rate": 1.6748868266249114e-05,
1873
+ "loss": 1.4413,
1874
+ "step": 2750
1875
+ },
1876
+ {
1877
+ "epoch": 1.83,
1878
+ "learning_rate": 1.658540608627985e-05,
1879
+ "loss": 1.4219,
1880
+ "step": 2760
1881
+ },
1882
+ {
1883
+ "epoch": 1.83,
1884
+ "learning_rate": 1.642234860776261e-05,
1885
+ "loss": 1.3447,
1886
+ "step": 2770
1887
+ },
1888
+ {
1889
+ "epoch": 1.84,
1890
+ "learning_rate": 1.6259703672977022e-05,
1891
+ "loss": 1.4383,
1892
+ "step": 2780
1893
+ },
1894
+ {
1895
+ "epoch": 1.85,
1896
+ "learning_rate": 1.6097479104361326e-05,
1897
+ "loss": 1.3562,
1898
+ "step": 2790
1899
+ },
1900
+ {
1901
+ "epoch": 1.85,
1902
+ "learning_rate": 1.5935682704136183e-05,
1903
+ "loss": 1.3865,
1904
+ "step": 2800
1905
+ },
1906
+ {
1907
+ "epoch": 1.85,
1908
+ "eval_loss": 1.40265691280365,
1909
+ "eval_runtime": 19.9442,
1910
+ "eval_samples_per_second": 24.518,
1911
+ "eval_steps_per_second": 6.167,
1912
+ "step": 2800
1913
+ },
1914
+ {
1915
+ "epoch": 1.86,
1916
+ "learning_rate": 1.5774322253929425e-05,
1917
+ "loss": 1.3875,
1918
+ "step": 2810
1919
+ },
1920
+ {
1921
+ "epoch": 1.87,
1922
+ "learning_rate": 1.561340551440176e-05,
1923
+ "loss": 1.4282,
1924
+ "step": 2820
1925
+ },
1926
+ {
1927
+ "epoch": 1.87,
1928
+ "learning_rate": 1.5452940224873568e-05,
1929
+ "loss": 1.401,
1930
+ "step": 2830
1931
+ },
1932
+ {
1933
+ "epoch": 1.88,
1934
+ "learning_rate": 1.529293410295266e-05,
1935
+ "loss": 1.3645,
1936
+ "step": 2840
1937
+ },
1938
+ {
1939
+ "epoch": 1.89,
1940
+ "learning_rate": 1.5133394844163093e-05,
1941
+ "loss": 1.3877,
1942
+ "step": 2850
1943
+ },
1944
+ {
1945
+ "epoch": 1.89,
1946
+ "learning_rate": 1.4974330121575048e-05,
1947
+ "loss": 1.4026,
1948
+ "step": 2860
1949
+ },
1950
+ {
1951
+ "epoch": 1.9,
1952
+ "learning_rate": 1.4815747585435801e-05,
1953
+ "loss": 1.4235,
1954
+ "step": 2870
1955
+ },
1956
+ {
1957
+ "epoch": 1.91,
1958
+ "learning_rate": 1.4657654862801798e-05,
1959
+ "loss": 1.3623,
1960
+ "step": 2880
1961
+ },
1962
+ {
1963
+ "epoch": 1.91,
1964
+ "learning_rate": 1.4500059557171791e-05,
1965
+ "loss": 1.3823,
1966
+ "step": 2890
1967
+ },
1968
+ {
1969
+ "epoch": 1.92,
1970
+ "learning_rate": 1.4342969248121185e-05,
1971
+ "loss": 1.3717,
1972
+ "step": 2900
1973
+ },
1974
+ {
1975
+ "epoch": 1.92,
1976
+ "eval_loss": 1.4025269746780396,
1977
+ "eval_runtime": 19.9411,
1978
+ "eval_samples_per_second": 24.522,
1979
+ "eval_steps_per_second": 6.168,
1980
+ "step": 2900
1981
+ },
1982
+ {
1983
+ "epoch": 1.93,
1984
+ "learning_rate": 1.4186391490937481e-05,
1985
+ "loss": 1.434,
1986
+ "step": 2910
1987
+ },
1988
+ {
1989
+ "epoch": 1.93,
1990
+ "learning_rate": 1.403033381625688e-05,
1991
+ "loss": 1.3688,
1992
+ "step": 2920
1993
+ },
1994
+ {
1995
+ "epoch": 1.94,
1996
+ "learning_rate": 1.3874803729702141e-05,
1997
+ "loss": 1.3404,
1998
+ "step": 2930
1999
+ },
2000
+ {
2001
+ "epoch": 1.95,
2002
+ "learning_rate": 1.3719808711521573e-05,
2003
+ "loss": 1.3956,
2004
+ "step": 2940
2005
+ },
2006
+ {
2007
+ "epoch": 1.95,
2008
+ "learning_rate": 1.3565356216229268e-05,
2009
+ "loss": 1.366,
2010
+ "step": 2950
2011
+ },
2012
+ {
2013
+ "epoch": 1.96,
2014
+ "learning_rate": 1.341145367224657e-05,
2015
+ "loss": 1.4425,
2016
+ "step": 2960
2017
+ },
2018
+ {
2019
+ "epoch": 1.97,
2020
+ "learning_rate": 1.3258108481544849e-05,
2021
+ "loss": 1.3728,
2022
+ "step": 2970
2023
+ },
2024
+ {
2025
+ "epoch": 1.97,
2026
+ "learning_rate": 1.310532801928942e-05,
2027
+ "loss": 1.4581,
2028
+ "step": 2980
2029
+ },
2030
+ {
2031
+ "epoch": 1.98,
2032
+ "learning_rate": 1.2953119633484903e-05,
2033
+ "loss": 1.3678,
2034
+ "step": 2990
2035
+ },
2036
+ {
2037
+ "epoch": 1.99,
2038
+ "learning_rate": 1.2801490644621789e-05,
2039
+ "loss": 1.4091,
2040
+ "step": 3000
2041
+ },
2042
+ {
2043
+ "epoch": 1.99,
2044
+ "eval_loss": 1.4022454023361206,
2045
+ "eval_runtime": 19.9582,
2046
+ "eval_samples_per_second": 24.501,
2047
+ "eval_steps_per_second": 6.163,
2048
+ "step": 3000
2049
+ },
2050
+ {
2051
+ "epoch": 1.99,
2052
+ "learning_rate": 1.2650448345324384e-05,
2053
+ "loss": 1.3642,
2054
+ "step": 3010
2055
+ },
2056
+ {
2057
+ "epoch": 2.0,
2058
+ "learning_rate": 1.2500000000000006e-05,
2059
+ "loss": 1.3949,
2060
+ "step": 3020
2061
+ },
2062
+ {
2063
+ "epoch": 2.01,
2064
+ "learning_rate": 1.235015284448969e-05,
2065
+ "loss": 1.3507,
2066
+ "step": 3030
2067
+ },
2068
+ {
2069
+ "epoch": 2.01,
2070
+ "learning_rate": 1.2200914085720119e-05,
2071
+ "loss": 1.3553,
2072
+ "step": 3040
2073
+ },
2074
+ {
2075
+ "epoch": 2.02,
2076
+ "learning_rate": 1.2052290901357025e-05,
2077
+ "loss": 1.4108,
2078
+ "step": 3050
2079
+ },
2080
+ {
2081
+ "epoch": 2.03,
2082
+ "learning_rate": 1.1904290439459973e-05,
2083
+ "loss": 1.3549,
2084
+ "step": 3060
2085
+ },
2086
+ {
2087
+ "epoch": 2.03,
2088
+ "learning_rate": 1.175691981813858e-05,
2089
+ "loss": 1.3371,
2090
+ "step": 3070
2091
+ },
2092
+ {
2093
+ "epoch": 2.04,
2094
+ "learning_rate": 1.1610186125210151e-05,
2095
+ "loss": 1.3775,
2096
+ "step": 3080
2097
+ },
2098
+ {
2099
+ "epoch": 2.05,
2100
+ "learning_rate": 1.1464096417858822e-05,
2101
+ "loss": 1.3884,
2102
+ "step": 3090
2103
+ },
2104
+ {
2105
+ "epoch": 2.05,
2106
+ "learning_rate": 1.1318657722296097e-05,
2107
+ "loss": 1.3516,
2108
+ "step": 3100
2109
+ },
2110
+ {
2111
+ "epoch": 2.05,
2112
+ "eval_loss": 1.4020849466323853,
2113
+ "eval_runtime": 19.9491,
2114
+ "eval_samples_per_second": 24.512,
2115
+ "eval_steps_per_second": 6.166,
2116
+ "step": 3100
2117
+ },
2118
+ {
2119
+ "epoch": 2.06,
2120
+ "learning_rate": 1.1173877033422994e-05,
2121
+ "loss": 1.405,
2122
+ "step": 3110
2123
+ },
2124
+ {
2125
+ "epoch": 2.07,
2126
+ "learning_rate": 1.102976131449352e-05,
2127
+ "loss": 1.3909,
2128
+ "step": 3120
2129
+ },
2130
+ {
2131
+ "epoch": 2.07,
2132
+ "learning_rate": 1.0886317496779863e-05,
2133
+ "loss": 1.4057,
2134
+ "step": 3130
2135
+ },
2136
+ {
2137
+ "epoch": 2.08,
2138
+ "learning_rate": 1.0743552479238994e-05,
2139
+ "loss": 1.3807,
2140
+ "step": 3140
2141
+ },
2142
+ {
2143
+ "epoch": 2.09,
2144
+ "learning_rate": 1.0601473128180855e-05,
2145
+ "loss": 1.3804,
2146
+ "step": 3150
2147
+ },
2148
+ {
2149
+ "epoch": 2.09,
2150
+ "learning_rate": 1.0460086276938144e-05,
2151
+ "loss": 1.3368,
2152
+ "step": 3160
2153
+ },
2154
+ {
2155
+ "epoch": 2.1,
2156
+ "learning_rate": 1.0319398725537644e-05,
2157
+ "loss": 1.3465,
2158
+ "step": 3170
2159
+ },
2160
+ {
2161
+ "epoch": 2.11,
2162
+ "learning_rate": 1.0179417240373183e-05,
2163
+ "loss": 1.3716,
2164
+ "step": 3180
2165
+ },
2166
+ {
2167
+ "epoch": 2.11,
2168
+ "learning_rate": 1.0040148553880205e-05,
2169
+ "loss": 1.3833,
2170
+ "step": 3190
2171
+ },
2172
+ {
2173
+ "epoch": 2.12,
2174
+ "learning_rate": 9.90159936421197e-06,
2175
+ "loss": 1.3893,
2176
+ "step": 3200
2177
+ },
2178
+ {
2179
+ "epoch": 2.12,
2180
+ "eval_loss": 1.4016104936599731,
2181
+ "eval_runtime": 19.9587,
2182
+ "eval_samples_per_second": 24.501,
2183
+ "eval_steps_per_second": 6.163,
2184
+ "step": 3200
2185
+ },
2186
+ {
2187
+ "epoch": 2.13,
2188
+ "learning_rate": 9.763776334917399e-06,
2189
+ "loss": 1.4088,
2190
+ "step": 3210
2191
+ },
2192
+ {
2193
+ "epoch": 2.13,
2194
+ "learning_rate": 9.626686094620608e-06,
2195
+ "loss": 1.402,
2196
+ "step": 3220
2197
+ },
2198
+ {
2199
+ "epoch": 2.14,
2200
+ "learning_rate": 9.490335236702075e-06,
2201
+ "loss": 1.3151,
2202
+ "step": 3230
2203
+ },
2204
+ {
2205
+ "epoch": 2.15,
2206
+ "learning_rate": 9.354730318981562e-06,
2207
+ "loss": 1.4126,
2208
+ "step": 3240
2209
+ },
2210
+ {
2211
+ "epoch": 2.15,
2212
+ "learning_rate": 9.219877863402682e-06,
2213
+ "loss": 1.431,
2214
+ "step": 3250
2215
+ },
2216
+ {
2217
+ "epoch": 2.16,
2218
+ "learning_rate": 9.085784355719257e-06,
2219
+ "loss": 1.3843,
2220
+ "step": 3260
2221
+ },
2222
+ {
2223
+ "epoch": 2.17,
2224
+ "learning_rate": 8.95245624518336e-06,
2225
+ "loss": 1.3513,
2226
+ "step": 3270
2227
+ },
2228
+ {
2229
+ "epoch": 2.17,
2230
+ "learning_rate": 8.819899944235152e-06,
2231
+ "loss": 1.362,
2232
+ "step": 3280
2233
+ },
2234
+ {
2235
+ "epoch": 2.18,
2236
+ "learning_rate": 8.688121828194462e-06,
2237
+ "loss": 1.3979,
2238
+ "step": 3290
2239
+ },
2240
+ {
2241
+ "epoch": 2.18,
2242
+ "learning_rate": 8.55712823495419e-06,
2243
+ "loss": 1.3949,
2244
+ "step": 3300
2245
+ },
2246
+ {
2247
+ "epoch": 2.18,
2248
+ "eval_loss": 1.4013094902038574,
2249
+ "eval_runtime": 19.9488,
2250
+ "eval_samples_per_second": 24.513,
2251
+ "eval_steps_per_second": 6.166,
2252
+ "step": 3300
2253
+ },
2254
+ {
2255
+ "epoch": 2.19,
2256
+ "learning_rate": 8.426925464675433e-06,
2257
+ "loss": 1.3912,
2258
+ "step": 3310
2259
+ },
2260
+ {
2261
+ "epoch": 2.2,
2262
+ "learning_rate": 8.297519779484541e-06,
2263
+ "loss": 1.35,
2264
+ "step": 3320
2265
+ },
2266
+ {
2267
+ "epoch": 2.2,
2268
+ "learning_rate": 8.168917403171891e-06,
2269
+ "loss": 1.3528,
2270
+ "step": 3330
2271
+ },
2272
+ {
2273
+ "epoch": 2.21,
2274
+ "learning_rate": 8.041124520892598e-06,
2275
+ "loss": 1.3743,
2276
+ "step": 3340
2277
+ },
2278
+ {
2279
+ "epoch": 2.22,
2280
+ "learning_rate": 7.91414727886898e-06,
2281
+ "loss": 1.3708,
2282
+ "step": 3350
2283
+ },
2284
+ {
2285
+ "epoch": 2.22,
2286
+ "learning_rate": 7.787991784095e-06,
2287
+ "loss": 1.4525,
2288
+ "step": 3360
2289
+ },
2290
+ {
2291
+ "epoch": 2.23,
2292
+ "learning_rate": 7.662664104042538e-06,
2293
+ "loss": 1.3708,
2294
+ "step": 3370
2295
+ },
2296
+ {
2297
+ "epoch": 2.24,
2298
+ "learning_rate": 7.538170266369563e-06,
2299
+ "loss": 1.3871,
2300
+ "step": 3380
2301
+ },
2302
+ {
2303
+ "epoch": 2.24,
2304
+ "learning_rate": 7.414516258630244e-06,
2305
+ "loss": 1.3853,
2306
+ "step": 3390
2307
+ },
2308
+ {
2309
+ "epoch": 2.25,
2310
+ "learning_rate": 7.291708027986988e-06,
2311
+ "loss": 1.3861,
2312
+ "step": 3400
2313
+ },
2314
+ {
2315
+ "epoch": 2.25,
2316
+ "eval_loss": 1.4008599519729614,
2317
+ "eval_runtime": 19.9567,
2318
+ "eval_samples_per_second": 24.503,
2319
+ "eval_steps_per_second": 6.163,
2320
+ "step": 3400
2321
+ },
2322
+ {
2323
+ "epoch": 2.26,
2324
+ "learning_rate": 7.169751480924361e-06,
2325
+ "loss": 1.3738,
2326
+ "step": 3410
2327
+ },
2328
+ {
2329
+ "epoch": 2.26,
2330
+ "learning_rate": 7.048652482965079e-06,
2331
+ "loss": 1.3908,
2332
+ "step": 3420
2333
+ },
2334
+ {
2335
+ "epoch": 2.27,
2336
+ "learning_rate": 6.928416858387874e-06,
2337
+ "loss": 1.3652,
2338
+ "step": 3430
2339
+ },
2340
+ {
2341
+ "epoch": 2.28,
2342
+ "learning_rate": 6.809050389947363e-06,
2343
+ "loss": 1.3673,
2344
+ "step": 3440
2345
+ },
2346
+ {
2347
+ "epoch": 2.28,
2348
+ "learning_rate": 6.690558818595943e-06,
2349
+ "loss": 1.395,
2350
+ "step": 3450
2351
+ },
2352
+ {
2353
+ "epoch": 2.29,
2354
+ "learning_rate": 6.5729478432076775e-06,
2355
+ "loss": 1.3734,
2356
+ "step": 3460
2357
+ },
2358
+ {
2359
+ "epoch": 2.3,
2360
+ "learning_rate": 6.456223120304192e-06,
2361
+ "loss": 1.4366,
2362
+ "step": 3470
2363
+ },
2364
+ {
2365
+ "epoch": 2.3,
2366
+ "learning_rate": 6.340390263782655e-06,
2367
+ "loss": 1.4222,
2368
+ "step": 3480
2369
+ },
2370
+ {
2371
+ "epoch": 2.31,
2372
+ "learning_rate": 6.22545484464574e-06,
2373
+ "loss": 1.3545,
2374
+ "step": 3490
2375
+ },
2376
+ {
2377
+ "epoch": 2.32,
2378
+ "learning_rate": 6.111422390733715e-06,
2379
+ "loss": 1.3581,
2380
+ "step": 3500
2381
+ },
2382
+ {
2383
+ "epoch": 2.32,
2384
+ "eval_loss": 1.4005074501037598,
2385
+ "eval_runtime": 19.9485,
2386
+ "eval_samples_per_second": 24.513,
2387
+ "eval_steps_per_second": 6.166,
2388
+ "step": 3500
2389
+ },
2390
+ {
2391
+ "epoch": 2.32,
2392
+ "learning_rate": 5.998298386458545e-06,
2393
+ "loss": 1.4052,
2394
+ "step": 3510
2395
+ },
2396
+ {
2397
+ "epoch": 2.33,
2398
+ "learning_rate": 5.8860882725401665e-06,
2399
+ "loss": 1.3886,
2400
+ "step": 3520
2401
+ },
2402
+ {
2403
+ "epoch": 2.34,
2404
+ "learning_rate": 5.774797445744781e-06,
2405
+ "loss": 1.3818,
2406
+ "step": 3530
2407
+ },
2408
+ {
2409
+ "epoch": 2.34,
2410
+ "learning_rate": 5.664431258625305e-06,
2411
+ "loss": 1.3817,
2412
+ "step": 3540
2413
+ },
2414
+ {
2415
+ "epoch": 2.35,
2416
+ "learning_rate": 5.55499501926394e-06,
2417
+ "loss": 1.3617,
2418
+ "step": 3550
2419
+ },
2420
+ {
2421
+ "epoch": 2.36,
2422
+ "learning_rate": 5.446493991016879e-06,
2423
+ "loss": 1.3768,
2424
+ "step": 3560
2425
+ },
2426
+ {
2427
+ "epoch": 2.36,
2428
+ "learning_rate": 5.338933392261159e-06,
2429
+ "loss": 1.3755,
2430
+ "step": 3570
2431
+ },
2432
+ {
2433
+ "epoch": 2.37,
2434
+ "learning_rate": 5.23231839614369e-06,
2435
+ "loss": 1.3823,
2436
+ "step": 3580
2437
+ },
2438
+ {
2439
+ "epoch": 2.38,
2440
+ "learning_rate": 5.126654130332451e-06,
2441
+ "loss": 1.3883,
2442
+ "step": 3590
2443
+ },
2444
+ {
2445
+ "epoch": 2.38,
2446
+ "learning_rate": 5.02194567676986e-06,
2447
+ "loss": 1.3988,
2448
+ "step": 3600
2449
+ },
2450
+ {
2451
+ "epoch": 2.38,
2452
+ "eval_loss": 1.4005191326141357,
2453
+ "eval_runtime": 19.9633,
2454
+ "eval_samples_per_second": 24.495,
2455
+ "eval_steps_per_second": 6.161,
2456
+ "step": 3600
2457
+ },
2458
+ {
2459
+ "epoch": 2.39,
2460
+ "learning_rate": 4.918198071428382e-06,
2461
+ "loss": 1.3838,
2462
+ "step": 3610
2463
+ },
2464
+ {
2465
+ "epoch": 2.4,
2466
+ "learning_rate": 4.815416304068298e-06,
2467
+ "loss": 1.4422,
2468
+ "step": 3620
2469
+ },
2470
+ {
2471
+ "epoch": 2.4,
2472
+ "learning_rate": 4.713605317997741e-06,
2473
+ "loss": 1.3834,
2474
+ "step": 3630
2475
+ },
2476
+ {
2477
+ "epoch": 2.41,
2478
+ "learning_rate": 4.61277000983493e-06,
2479
+ "loss": 1.3743,
2480
+ "step": 3640
2481
+ },
2482
+ {
2483
+ "epoch": 2.42,
2484
+ "learning_rate": 4.51291522927268e-06,
2485
+ "loss": 1.451,
2486
+ "step": 3650
2487
+ },
2488
+ {
2489
+ "epoch": 2.42,
2490
+ "learning_rate": 4.414045778845144e-06,
2491
+ "loss": 1.3644,
2492
+ "step": 3660
2493
+ },
2494
+ {
2495
+ "epoch": 2.43,
2496
+ "learning_rate": 4.316166413696851e-06,
2497
+ "loss": 1.3944,
2498
+ "step": 3670
2499
+ },
2500
+ {
2501
+ "epoch": 2.44,
2502
+ "learning_rate": 4.219281841353981e-06,
2503
+ "loss": 1.3514,
2504
+ "step": 3680
2505
+ },
2506
+ {
2507
+ "epoch": 2.44,
2508
+ "learning_rate": 4.123396721497977e-06,
2509
+ "loss": 1.3389,
2510
+ "step": 3690
2511
+ },
2512
+ {
2513
+ "epoch": 2.45,
2514
+ "learning_rate": 4.028515665741439e-06,
2515
+ "loss": 1.3792,
2516
+ "step": 3700
2517
+ },
2518
+ {
2519
+ "epoch": 2.45,
2520
+ "eval_loss": 1.400659203529358,
2521
+ "eval_runtime": 19.9466,
2522
+ "eval_samples_per_second": 24.515,
2523
+ "eval_steps_per_second": 6.166,
2524
+ "step": 3700
2525
+ },
2526
+ {
2527
+ "epoch": 2.46,
2528
+ "learning_rate": 3.934643237406291e-06,
2529
+ "loss": 1.3686,
2530
+ "step": 3710
2531
+ },
2532
+ {
2533
+ "epoch": 2.46,
2534
+ "learning_rate": 3.8417839513043645e-06,
2535
+ "loss": 1.3424,
2536
+ "step": 3720
2537
+ },
2538
+ {
2539
+ "epoch": 2.47,
2540
+ "learning_rate": 3.7499422735202127e-06,
2541
+ "loss": 1.3684,
2542
+ "step": 3730
2543
+ },
2544
+ {
2545
+ "epoch": 2.48,
2546
+ "learning_rate": 3.6591226211963287e-06,
2547
+ "loss": 1.3868,
2548
+ "step": 3740
2549
+ },
2550
+ {
2551
+ "epoch": 2.48,
2552
+ "learning_rate": 3.5693293623207086e-06,
2553
+ "loss": 1.368,
2554
+ "step": 3750
2555
+ },
2556
+ {
2557
+ "epoch": 2.49,
2558
+ "learning_rate": 3.480566815516756e-06,
2559
+ "loss": 1.3027,
2560
+ "step": 3760
2561
+ },
2562
+ {
2563
+ "epoch": 2.5,
2564
+ "learning_rate": 3.3928392498355916e-06,
2565
+ "loss": 1.4223,
2566
+ "step": 3770
2567
+ },
2568
+ {
2569
+ "epoch": 2.5,
2570
+ "learning_rate": 3.3061508845507323e-06,
2571
+ "loss": 1.3674,
2572
+ "step": 3780
2573
+ },
2574
+ {
2575
+ "epoch": 2.51,
2576
+ "learning_rate": 3.22050588895515e-06,
2577
+ "loss": 1.3848,
2578
+ "step": 3790
2579
+ },
2580
+ {
2581
+ "epoch": 2.52,
2582
+ "learning_rate": 3.135908382160771e-06,
2583
+ "loss": 1.4191,
2584
+ "step": 3800
2585
+ },
2586
+ {
2587
+ "epoch": 2.52,
2588
+ "eval_loss": 1.4003913402557373,
2589
+ "eval_runtime": 19.9553,
2590
+ "eval_samples_per_second": 24.505,
2591
+ "eval_steps_per_second": 6.164,
2592
+ "step": 3800
2593
+ },
2594
+ {
2595
+ "epoch": 2.52,
2596
+ "learning_rate": 3.0523624329003324e-06,
2597
+ "loss": 1.3796,
2598
+ "step": 3810
2599
+ },
2600
+ {
2601
+ "epoch": 2.53,
2602
+ "learning_rate": 2.969872059331738e-06,
2603
+ "loss": 1.4101,
2604
+ "step": 3820
2605
+ },
2606
+ {
2607
+ "epoch": 2.54,
2608
+ "learning_rate": 2.8884412288447737e-06,
2609
+ "loss": 1.379,
2610
+ "step": 3830
2611
+ },
2612
+ {
2613
+ "epoch": 2.54,
2614
+ "learning_rate": 2.8080738578703054e-06,
2615
+ "loss": 1.3881,
2616
+ "step": 3840
2617
+ },
2618
+ {
2619
+ "epoch": 2.55,
2620
+ "learning_rate": 2.728773811691923e-06,
2621
+ "loss": 1.3464,
2622
+ "step": 3850
2623
+ },
2624
+ {
2625
+ "epoch": 2.56,
2626
+ "learning_rate": 2.6505449042600244e-06,
2627
+ "loss": 1.367,
2628
+ "step": 3860
2629
+ },
2630
+ {
2631
+ "epoch": 2.56,
2632
+ "learning_rate": 2.5733908980083988e-06,
2633
+ "loss": 1.3498,
2634
+ "step": 3870
2635
+ },
2636
+ {
2637
+ "epoch": 2.57,
2638
+ "learning_rate": 2.4973155036732534e-06,
2639
+ "loss": 1.3895,
2640
+ "step": 3880
2641
+ },
2642
+ {
2643
+ "epoch": 2.58,
2644
+ "learning_rate": 2.422322380114772e-06,
2645
+ "loss": 1.4072,
2646
+ "step": 3890
2647
+ },
2648
+ {
2649
+ "epoch": 2.58,
2650
+ "learning_rate": 2.348415134141102e-06,
2651
+ "loss": 1.347,
2652
+ "step": 3900
2653
+ },
2654
+ {
2655
+ "epoch": 2.58,
2656
+ "eval_loss": 1.400329351425171,
2657
+ "eval_runtime": 19.9385,
2658
+ "eval_samples_per_second": 24.525,
2659
+ "eval_steps_per_second": 6.169,
2660
+ "step": 3900
2661
+ },
2662
+ {
2663
+ "epoch": 2.59,
2664
+ "learning_rate": 2.2755973203349294e-06,
2665
+ "loss": 1.3605,
2666
+ "step": 3910
2667
+ },
2668
+ {
2669
+ "epoch": 2.6,
2670
+ "learning_rate": 2.2038724408824844e-06,
2671
+ "loss": 1.3105,
2672
+ "step": 3920
2673
+ },
2674
+ {
2675
+ "epoch": 2.6,
2676
+ "learning_rate": 2.133243945405128e-06,
2677
+ "loss": 1.3718,
2678
+ "step": 3930
2679
+ },
2680
+ {
2681
+ "epoch": 2.61,
2682
+ "learning_rate": 2.0637152307934228e-06,
2683
+ "loss": 1.3293,
2684
+ "step": 3940
2685
+ },
2686
+ {
2687
+ "epoch": 2.62,
2688
+ "learning_rate": 1.995289641043768e-06,
2689
+ "loss": 1.3677,
2690
+ "step": 3950
2691
+ },
2692
+ {
2693
+ "epoch": 2.62,
2694
+ "learning_rate": 1.927970467097573e-06,
2695
+ "loss": 1.409,
2696
+ "step": 3960
2697
+ },
2698
+ {
2699
+ "epoch": 2.63,
2700
+ "learning_rate": 1.8617609466829666e-06,
2701
+ "loss": 1.3973,
2702
+ "step": 3970
2703
+ },
2704
+ {
2705
+ "epoch": 2.64,
2706
+ "learning_rate": 1.7966642641590925e-06,
2707
+ "loss": 1.3991,
2708
+ "step": 3980
2709
+ },
2710
+ {
2711
+ "epoch": 2.64,
2712
+ "learning_rate": 1.732683550362954e-06,
2713
+ "loss": 1.3662,
2714
+ "step": 3990
2715
+ },
2716
+ {
2717
+ "epoch": 2.65,
2718
+ "learning_rate": 1.6698218824588164e-06,
2719
+ "loss": 1.3871,
2720
+ "step": 4000
2721
+ },
2722
+ {
2723
+ "epoch": 2.65,
2724
+ "eval_loss": 1.4001953601837158,
2725
+ "eval_runtime": 19.9558,
2726
+ "eval_samples_per_second": 24.504,
2727
+ "eval_steps_per_second": 6.164,
2728
+ "step": 4000
2729
+ },
2730
+ {
2731
+ "epoch": 2.65,
2732
+ "learning_rate": 1.6080822837902382e-06,
2733
+ "loss": 1.4072,
2734
+ "step": 4010
2735
+ },
2736
+ {
2737
+ "epoch": 2.66,
2738
+ "learning_rate": 1.5474677237346468e-06,
2739
+ "loss": 1.3841,
2740
+ "step": 4020
2741
+ },
2742
+ {
2743
+ "epoch": 2.67,
2744
+ "learning_rate": 1.4879811175605302e-06,
2745
+ "loss": 1.3729,
2746
+ "step": 4030
2747
+ },
2748
+ {
2749
+ "epoch": 2.67,
2750
+ "learning_rate": 1.4296253262872234e-06,
2751
+ "loss": 1.3648,
2752
+ "step": 4040
2753
+ },
2754
+ {
2755
+ "epoch": 2.68,
2756
+ "learning_rate": 1.3724031565473112e-06,
2757
+ "loss": 1.4043,
2758
+ "step": 4050
2759
+ },
2760
+ {
2761
+ "epoch": 2.69,
2762
+ "learning_rate": 1.316317360451641e-06,
2763
+ "loss": 1.4135,
2764
+ "step": 4060
2765
+ },
2766
+ {
2767
+ "epoch": 2.69,
2768
+ "learning_rate": 1.2613706354569571e-06,
2769
+ "loss": 1.399,
2770
+ "step": 4070
2771
+ },
2772
+ {
2773
+ "epoch": 2.7,
2774
+ "learning_rate": 1.2075656242361732e-06,
2775
+ "loss": 1.4024,
2776
+ "step": 4080
2777
+ },
2778
+ {
2779
+ "epoch": 2.71,
2780
+ "learning_rate": 1.1549049145512636e-06,
2781
+ "loss": 1.3668,
2782
+ "step": 4090
2783
+ },
2784
+ {
2785
+ "epoch": 2.71,
2786
+ "learning_rate": 1.1033910391288065e-06,
2787
+ "loss": 1.3692,
2788
+ "step": 4100
2789
+ },
2790
+ {
2791
+ "epoch": 2.71,
2792
+ "eval_loss": 1.399943232536316,
2793
+ "eval_runtime": 19.9364,
2794
+ "eval_samples_per_second": 24.528,
2795
+ "eval_steps_per_second": 6.17,
2796
+ "step": 4100
2797
+ },
2798
+ {
2799
+ "epoch": 2.72,
2800
+ "learning_rate": 1.0530264755381824e-06,
2801
+ "loss": 1.3908,
2802
+ "step": 4110
2803
+ },
2804
+ {
2805
+ "epoch": 2.73,
2806
+ "learning_rate": 1.0038136460723963e-06,
2807
+ "loss": 1.3999,
2808
+ "step": 4120
2809
+ },
2810
+ {
2811
+ "epoch": 2.73,
2812
+ "learning_rate": 9.557549176315934e-07,
2813
+ "loss": 1.4098,
2814
+ "step": 4130
2815
+ },
2816
+ {
2817
+ "epoch": 2.74,
2818
+ "learning_rate": 9.088526016092142e-07,
2819
+ "loss": 1.3973,
2820
+ "step": 4140
2821
+ },
2822
+ {
2823
+ "epoch": 2.75,
2824
+ "learning_rate": 8.631089537808307e-07,
2825
+ "loss": 1.3758,
2826
+ "step": 4150
2827
+ },
2828
+ {
2829
+ "epoch": 2.75,
2830
+ "learning_rate": 8.185261741956551e-07,
2831
+ "loss": 1.3197,
2832
+ "step": 4160
2833
+ },
2834
+ {
2835
+ "epoch": 2.76,
2836
+ "learning_rate": 7.751064070707248e-07,
2837
+ "loss": 1.3794,
2838
+ "step": 4170
2839
+ },
2840
+ {
2841
+ "epoch": 2.77,
2842
+ "learning_rate": 7.328517406877761e-07,
2843
+ "loss": 1.3764,
2844
+ "step": 4180
2845
+ },
2846
+ {
2847
+ "epoch": 2.77,
2848
+ "learning_rate": 6.917642072928137e-07,
2849
+ "loss": 1.4063,
2850
+ "step": 4190
2851
+ },
2852
+ {
2853
+ "epoch": 2.78,
2854
+ "learning_rate": 6.51845782998356e-07,
2855
+ "loss": 1.3959,
2856
+ "step": 4200
2857
+ },
2858
+ {
2859
+ "epoch": 2.78,
2860
+ "eval_loss": 1.3998632431030273,
2861
+ "eval_runtime": 19.9527,
2862
+ "eval_samples_per_second": 24.508,
2863
+ "eval_steps_per_second": 6.165,
2864
+ "step": 4200
2865
+ },
2866
+ {
2867
+ "epoch": 2.79,
2868
+ "learning_rate": 6.130983876884155e-07,
2869
+ "loss": 1.3767,
2870
+ "step": 4210
2871
+ },
2872
+ {
2873
+ "epoch": 2.79,
2874
+ "learning_rate": 5.755238849261407e-07,
2875
+ "loss": 1.3619,
2876
+ "step": 4220
2877
+ },
2878
+ {
2879
+ "epoch": 2.8,
2880
+ "learning_rate": 5.391240818642007e-07,
2881
+ "loss": 1.3723,
2882
+ "step": 4230
2883
+ },
2884
+ {
2885
+ "epoch": 2.81,
2886
+ "learning_rate": 5.039007291578579e-07,
2887
+ "loss": 1.4262,
2888
+ "step": 4240
2889
+ },
2890
+ {
2891
+ "epoch": 2.81,
2892
+ "learning_rate": 4.698555208807853e-07,
2893
+ "loss": 1.3775,
2894
+ "step": 4250
2895
+ },
2896
+ {
2897
+ "epoch": 2.82,
2898
+ "learning_rate": 4.3699009444357344e-07,
2899
+ "loss": 1.4159,
2900
+ "step": 4260
2901
+ },
2902
+ {
2903
+ "epoch": 2.83,
2904
+ "learning_rate": 4.0530603051499584e-07,
2905
+ "loss": 1.4007,
2906
+ "step": 4270
2907
+ },
2908
+ {
2909
+ "epoch": 2.83,
2910
+ "learning_rate": 3.7480485294596747e-07,
2911
+ "loss": 1.3898,
2912
+ "step": 4280
2913
+ },
2914
+ {
2915
+ "epoch": 2.84,
2916
+ "learning_rate": 3.454880286962781e-07,
2917
+ "loss": 1.4173,
2918
+ "step": 4290
2919
+ },
2920
+ {
2921
+ "epoch": 2.85,
2922
+ "learning_rate": 3.1735696776400703e-07,
2923
+ "loss": 1.3539,
2924
+ "step": 4300
2925
+ },
2926
+ {
2927
+ "epoch": 2.85,
2928
+ "eval_loss": 1.3998057842254639,
2929
+ "eval_runtime": 19.9318,
2930
+ "eval_samples_per_second": 24.534,
2931
+ "eval_steps_per_second": 6.171,
2932
+ "step": 4300
2933
+ },
2934
+ {
2935
+ "epoch": 2.85,
2936
+ "learning_rate": 2.9041302311774433e-07,
2937
+ "loss": 1.3803,
2938
+ "step": 4310
2939
+ },
2940
+ {
2941
+ "epoch": 2.86,
2942
+ "learning_rate": 2.646574906314925e-07,
2943
+ "loss": 1.4141,
2944
+ "step": 4320
2945
+ },
2946
+ {
2947
+ "epoch": 2.87,
2948
+ "learning_rate": 2.4009160902235816e-07,
2949
+ "loss": 1.3444,
2950
+ "step": 4330
2951
+ },
2952
+ {
2953
+ "epoch": 2.87,
2954
+ "learning_rate": 2.1671655979096094e-07,
2955
+ "loss": 1.3669,
2956
+ "step": 4340
2957
+ },
2958
+ {
2959
+ "epoch": 2.88,
2960
+ "learning_rate": 1.9453346716462317e-07,
2961
+ "loss": 1.3776,
2962
+ "step": 4350
2963
+ },
2964
+ {
2965
+ "epoch": 2.89,
2966
+ "learning_rate": 1.73543398043291e-07,
2967
+ "loss": 1.4048,
2968
+ "step": 4360
2969
+ },
2970
+ {
2971
+ "epoch": 2.89,
2972
+ "learning_rate": 1.537473619482227e-07,
2973
+ "loss": 1.3623,
2974
+ "step": 4370
2975
+ },
2976
+ {
2977
+ "epoch": 2.9,
2978
+ "learning_rate": 1.351463109734441e-07,
2979
+ "loss": 1.3861,
2980
+ "step": 4380
2981
+ },
2982
+ {
2983
+ "epoch": 2.91,
2984
+ "learning_rate": 1.1774113973994083e-07,
2985
+ "loss": 1.3323,
2986
+ "step": 4390
2987
+ },
2988
+ {
2989
+ "epoch": 2.91,
2990
+ "learning_rate": 1.0153268535264827e-07,
2991
+ "loss": 1.3646,
2992
+ "step": 4400
2993
+ },
2994
+ {
2995
+ "epoch": 2.91,
2996
+ "eval_loss": 1.3997734785079956,
2997
+ "eval_runtime": 19.9549,
2998
+ "eval_samples_per_second": 24.505,
2999
+ "eval_steps_per_second": 6.164,
3000
+ "step": 4400
3001
+ },
3002
+ {
3003
+ "epoch": 2.92,
3004
+ "learning_rate": 8.652172736017816e-08,
3005
+ "loss": 1.3963,
3006
+ "step": 4410
3007
+ },
3008
+ {
3009
+ "epoch": 2.93,
3010
+ "learning_rate": 7.270898771733481e-08,
3011
+ "loss": 1.3812,
3012
+ "step": 4420
3013
+ },
3014
+ {
3015
+ "epoch": 2.93,
3016
+ "learning_rate": 6.00951307503872e-08,
3017
+ "loss": 1.375,
3018
+ "step": 4430
3019
+ },
3020
+ {
3021
+ "epoch": 2.94,
3022
+ "learning_rate": 4.868076312512515e-08,
3023
+ "loss": 1.4015,
3024
+ "step": 4440
3025
+ },
3026
+ {
3027
+ "epoch": 2.95,
3028
+ "learning_rate": 3.846643381766879e-08,
3029
+ "loss": 1.3795,
3030
+ "step": 4450
3031
+ },
3032
+ {
3033
+ "epoch": 2.95,
3034
+ "learning_rate": 2.94526340880813e-08,
3035
+ "loss": 1.4244,
3036
+ "step": 4460
3037
+ },
3038
+ {
3039
+ "epoch": 2.96,
3040
+ "learning_rate": 2.1639797456723952e-08,
3041
+ "loss": 1.3731,
3042
+ "step": 4470
3043
+ },
3044
+ {
3045
+ "epoch": 2.97,
3046
+ "learning_rate": 1.5028299683425562e-08,
3047
+ "loss": 1.4061,
3048
+ "step": 4480
3049
+ },
3050
+ {
3051
+ "epoch": 2.97,
3052
+ "learning_rate": 9.618458749391379e-09,
3053
+ "loss": 1.3842,
3054
+ "step": 4490
3055
+ },
3056
+ {
3057
+ "epoch": 2.98,
3058
+ "learning_rate": 5.41053484192644e-09,
3059
+ "loss": 1.3693,
3060
+ "step": 4500
3061
+ },
3062
+ {
3063
+ "epoch": 2.98,
3064
+ "eval_loss": 1.3998451232910156,
3065
+ "eval_runtime": 19.9451,
3066
+ "eval_samples_per_second": 24.517,
3067
+ "eval_steps_per_second": 6.167,
3068
+ "step": 4500
3069
+ },
3070
+ {
3071
+ "epoch": 2.99,
3072
+ "learning_rate": 2.4047303419094667e-09,
3073
+ "loss": 1.3439,
3074
+ "step": 4510
3075
+ },
3076
+ {
3077
+ "epoch": 2.99,
3078
+ "learning_rate": 6.011898140617645e-10,
3079
+ "loss": 1.3848,
3080
+ "step": 4520
3081
+ },
3082
+ {
3083
+ "epoch": 3.0,
3084
+ "learning_rate": 0.0,
3085
+ "loss": 1.3852,
3086
+ "step": 4530
3087
+ },
3088
+ {
3089
+ "epoch": 3.0,
3090
+ "step": 4530,
3091
+ "total_flos": 1.828885230092206e+18,
3092
+ "train_loss": 1.4043121354732555,
3093
+ "train_runtime": 20600.2987,
3094
+ "train_samples_per_second": 7.038,
3095
+ "train_steps_per_second": 0.22
3096
+ }
3097
+ ],
3098
+ "max_steps": 4530,
3099
+ "num_train_epochs": 3,
3100
+ "total_flos": 1.828885230092206e+18,
3101
+ "trial_name": null,
3102
+ "trial_params": null
3103
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:600e570fde3f2384ebc2a5bebb380c9dafeb644821c59a35d0ce55abb93dd55d
3
+ size 3274
training_eval_loss.png ADDED
training_loss.png ADDED