aylinakkus commited on
Commit
f4c4a91
·
verified ·
1 Parent(s): f4e072c

Model save

Browse files
README.md ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: ByteDance-Seed/UI-TARS-1.5-7B
5
+ tags:
6
+ - llama-factory
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: ui-tars-1.5-7b-idm-full-sft-8-frames
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # ui-tars-1.5-7b-idm-full-sft-8-frames
17
+
18
+ This model is a fine-tuned version of [ByteDance-Seed/UI-TARS-1.5-7B](https://huggingface.co/ByteDance-Seed/UI-TARS-1.5-7B) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.0213
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 1e-05
40
+ - train_batch_size: 2
41
+ - eval_batch_size: 1
42
+ - seed: 42
43
+ - distributed_type: multi-GPU
44
+ - num_devices: 8
45
+ - total_train_batch_size: 16
46
+ - total_eval_batch_size: 8
47
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: cosine
49
+ - lr_scheduler_warmup_ratio: 0.05
50
+ - num_epochs: 3.0
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss |
55
+ |:-------------:|:-----:|:----:|:---------------:|
56
+ | 0.0779 | 1.0 | 512 | 0.0556 |
57
+ | 0.0275 | 2.0 | 1024 | 0.0226 |
58
+ | 0.0274 | 3.0 | 1536 | 0.0213 |
59
+
60
+
61
+ ### Framework versions
62
+
63
+ - Transformers 4.51.3
64
+ - Pytorch 2.6.0+cu124
65
+ - Datasets 3.0.2
66
+ - Tokenizers 0.21.1
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b720cf224107471b5d6d218a56cc75172f36325db26b0569e7733453da35ef41
3
  size 4968243304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58eb1a98e485bada607dff0c8b731c9336c6efe01bc9981479cd2ca0f969e850
3
  size 4968243304
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f8638276adb99a8cb384b10f54ff9d38e74427697bf5777e2be47256d2d936f
3
  size 4991495816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f4bea07d39d8829aca1e6d3a4b6c8680d584725ded8d49dfaf4989c72949ca3
3
  size 4991495816
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f375dc8cbd12ae4ee7356880f9ed203766609c8088d2aab7ce24dd98905506a
3
  size 4932751040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3f151652160ebd1ed20b1db686bb6890491cd401c2088fbc2f1c6f138b0c2d8
3
  size 4932751040
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85d5e1f462048b2b49bfa9fca72b950bd9f602bae204d51a8ed580a92a0d14b0
3
  size 1691924384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa0730ede60ce918be5bb78076ecbfc40469dcbfff9d1b617042fcbb9e3bf2df
3
  size 1691924384
trainer_log.jsonl ADDED
@@ -0,0 +1,288 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1251, "total_steps": 1536, "loss": 0.0121, "lr": 9.185276172577284e-07, "epoch": 2.443359375, "percentage": 81.45, "elapsed_time": "0:00:37", "remaining_time": "0:00:08"}
2
+ {"current_steps": 1252, "total_steps": 1536, "loss": 0.0209, "lr": 9.123181087305316e-07, "epoch": 2.4453125, "percentage": 81.51, "elapsed_time": "0:01:05", "remaining_time": "0:00:14"}
3
+ {"current_steps": 1253, "total_steps": 1536, "loss": 0.0177, "lr": 9.061275526849883e-07, "epoch": 2.447265625, "percentage": 81.58, "elapsed_time": "0:01:33", "remaining_time": "0:00:21"}
4
+ {"current_steps": 1254, "total_steps": 1536, "loss": 0.0194, "lr": 8.999559778235268e-07, "epoch": 2.44921875, "percentage": 81.64, "elapsed_time": "0:02:01", "remaining_time": "0:00:27"}
5
+ {"current_steps": 1255, "total_steps": 1536, "loss": 0.0173, "lr": 8.938034127605688e-07, "epoch": 2.451171875, "percentage": 81.71, "elapsed_time": "0:02:29", "remaining_time": "0:00:33"}
6
+ {"current_steps": 1256, "total_steps": 1536, "loss": 0.0218, "lr": 8.876698860224015e-07, "epoch": 2.453125, "percentage": 81.77, "elapsed_time": "0:02:57", "remaining_time": "0:00:39"}
7
+ {"current_steps": 1257, "total_steps": 1536, "loss": 0.0148, "lr": 8.815554260470366e-07, "epoch": 2.455078125, "percentage": 81.84, "elapsed_time": "0:03:25", "remaining_time": "0:00:45"}
8
+ {"current_steps": 1258, "total_steps": 1536, "loss": 0.025, "lr": 8.754600611840841e-07, "epoch": 2.45703125, "percentage": 81.9, "elapsed_time": "0:03:52", "remaining_time": "0:00:51"}
9
+ {"current_steps": 1259, "total_steps": 1536, "loss": 0.0136, "lr": 8.693838196946236e-07, "epoch": 2.458984375, "percentage": 81.97, "elapsed_time": "0:04:20", "remaining_time": "0:00:57"}
10
+ {"current_steps": 1260, "total_steps": 1536, "loss": 0.013, "lr": 8.633267297510639e-07, "epoch": 2.4609375, "percentage": 82.03, "elapsed_time": "0:04:48", "remaining_time": "0:01:03"}
11
+ {"current_steps": 1261, "total_steps": 1536, "loss": 0.014, "lr": 8.572888194370194e-07, "epoch": 2.462890625, "percentage": 82.1, "elapsed_time": "0:05:16", "remaining_time": "0:01:08"}
12
+ {"current_steps": 1262, "total_steps": 1536, "loss": 0.0153, "lr": 8.512701167471826e-07, "epoch": 2.46484375, "percentage": 82.16, "elapsed_time": "0:05:44", "remaining_time": "0:01:14"}
13
+ {"current_steps": 1263, "total_steps": 1536, "loss": 0.0135, "lr": 8.452706495871837e-07, "epoch": 2.466796875, "percentage": 82.23, "elapsed_time": "0:06:12", "remaining_time": "0:01:20"}
14
+ {"current_steps": 1264, "total_steps": 1536, "loss": 0.0172, "lr": 8.392904457734741e-07, "epoch": 2.46875, "percentage": 82.29, "elapsed_time": "0:06:39", "remaining_time": "0:01:26"}
15
+ {"current_steps": 1265, "total_steps": 1536, "loss": 0.0188, "lr": 8.333295330331842e-07, "epoch": 2.470703125, "percentage": 82.36, "elapsed_time": "0:07:07", "remaining_time": "0:01:31"}
16
+ {"current_steps": 1266, "total_steps": 1536, "loss": 0.0235, "lr": 8.273879390040079e-07, "epoch": 2.47265625, "percentage": 82.42, "elapsed_time": "0:07:35", "remaining_time": "0:01:37"}
17
+ {"current_steps": 1267, "total_steps": 1536, "loss": 0.0167, "lr": 8.214656912340646e-07, "epoch": 2.474609375, "percentage": 82.49, "elapsed_time": "0:08:03", "remaining_time": "0:01:42"}
18
+ {"current_steps": 1268, "total_steps": 1536, "loss": 0.026, "lr": 8.155628171817742e-07, "epoch": 2.4765625, "percentage": 82.55, "elapsed_time": "0:08:31", "remaining_time": "0:01:48"}
19
+ {"current_steps": 1269, "total_steps": 1536, "loss": 0.0215, "lr": 8.096793442157347e-07, "epoch": 2.478515625, "percentage": 82.62, "elapsed_time": "0:08:59", "remaining_time": "0:01:53"}
20
+ {"current_steps": 1270, "total_steps": 1536, "loss": 0.0127, "lr": 8.03815299614587e-07, "epoch": 2.48046875, "percentage": 82.68, "elapsed_time": "0:09:27", "remaining_time": "0:01:58"}
21
+ {"current_steps": 1271, "total_steps": 1536, "loss": 0.023, "lr": 7.979707105668938e-07, "epoch": 2.482421875, "percentage": 82.75, "elapsed_time": "0:09:55", "remaining_time": "0:02:04"}
22
+ {"current_steps": 1272, "total_steps": 1536, "loss": 0.0086, "lr": 7.921456041710152e-07, "epoch": 2.484375, "percentage": 82.81, "elapsed_time": "0:10:23", "remaining_time": "0:02:09"}
23
+ {"current_steps": 1273, "total_steps": 1536, "loss": 0.0176, "lr": 7.863400074349764e-07, "epoch": 2.486328125, "percentage": 82.88, "elapsed_time": "0:10:50", "remaining_time": "0:02:14"}
24
+ {"current_steps": 1274, "total_steps": 1536, "loss": 0.0253, "lr": 7.805539472763474e-07, "epoch": 2.48828125, "percentage": 82.94, "elapsed_time": "0:11:18", "remaining_time": "0:02:19"}
25
+ {"current_steps": 1275, "total_steps": 1536, "loss": 0.0163, "lr": 7.747874505221198e-07, "epoch": 2.490234375, "percentage": 83.01, "elapsed_time": "0:11:46", "remaining_time": "0:02:24"}
26
+ {"current_steps": 1276, "total_steps": 1536, "loss": 0.0185, "lr": 7.690405439085758e-07, "epoch": 2.4921875, "percentage": 83.07, "elapsed_time": "0:12:14", "remaining_time": "0:02:29"}
27
+ {"current_steps": 1277, "total_steps": 1536, "loss": 0.0152, "lr": 7.6331325408117e-07, "epoch": 2.494140625, "percentage": 83.14, "elapsed_time": "0:12:42", "remaining_time": "0:02:34"}
28
+ {"current_steps": 1278, "total_steps": 1536, "loss": 0.019, "lr": 7.576056075944039e-07, "epoch": 2.49609375, "percentage": 83.2, "elapsed_time": "0:13:10", "remaining_time": "0:02:39"}
29
+ {"current_steps": 1279, "total_steps": 1536, "loss": 0.0185, "lr": 7.519176309117065e-07, "epoch": 2.498046875, "percentage": 83.27, "elapsed_time": "0:13:38", "remaining_time": "0:02:44"}
30
+ {"current_steps": 1280, "total_steps": 1536, "loss": 0.0149, "lr": 7.462493504052986e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "0:14:05", "remaining_time": "0:02:49"}
31
+ {"current_steps": 1281, "total_steps": 1536, "loss": 0.0183, "lr": 7.406007923560899e-07, "epoch": 2.501953125, "percentage": 83.4, "elapsed_time": "0:14:33", "remaining_time": "0:02:53"}
32
+ {"current_steps": 1282, "total_steps": 1536, "loss": 0.0149, "lr": 7.349719829535429e-07, "epoch": 2.50390625, "percentage": 83.46, "elapsed_time": "0:15:01", "remaining_time": "0:02:58"}
33
+ {"current_steps": 1283, "total_steps": 1536, "loss": 0.0231, "lr": 7.293629482955555e-07, "epoch": 2.505859375, "percentage": 83.53, "elapsed_time": "0:15:29", "remaining_time": "0:03:03"}
34
+ {"current_steps": 1284, "total_steps": 1536, "loss": 0.0211, "lr": 7.237737143883399e-07, "epoch": 2.5078125, "percentage": 83.59, "elapsed_time": "0:15:56", "remaining_time": "0:03:07"}
35
+ {"current_steps": 1285, "total_steps": 1536, "loss": 0.0185, "lr": 7.182043071463046e-07, "epoch": 2.509765625, "percentage": 83.66, "elapsed_time": "0:16:24", "remaining_time": "0:03:12"}
36
+ {"current_steps": 1286, "total_steps": 1536, "loss": 0.0119, "lr": 7.126547523919309e-07, "epoch": 2.51171875, "percentage": 83.72, "elapsed_time": "0:16:52", "remaining_time": "0:03:16"}
37
+ {"current_steps": 1287, "total_steps": 1536, "loss": 0.018, "lr": 7.071250758556524e-07, "epoch": 2.513671875, "percentage": 83.79, "elapsed_time": "0:17:20", "remaining_time": "0:03:21"}
38
+ {"current_steps": 1288, "total_steps": 1536, "loss": 0.0212, "lr": 7.016153031757417e-07, "epoch": 2.515625, "percentage": 83.85, "elapsed_time": "0:17:48", "remaining_time": "0:03:25"}
39
+ {"current_steps": 1289, "total_steps": 1536, "loss": 0.0163, "lr": 6.961254598981837e-07, "epoch": 2.517578125, "percentage": 83.92, "elapsed_time": "0:18:16", "remaining_time": "0:03:30"}
40
+ {"current_steps": 1290, "total_steps": 1536, "loss": 0.0158, "lr": 6.906555714765617e-07, "epoch": 2.51953125, "percentage": 83.98, "elapsed_time": "0:18:44", "remaining_time": "0:03:34"}
41
+ {"current_steps": 1291, "total_steps": 1536, "loss": 0.0134, "lr": 6.852056632719411e-07, "epoch": 2.521484375, "percentage": 84.05, "elapsed_time": "0:19:11", "remaining_time": "0:03:38"}
42
+ {"current_steps": 1292, "total_steps": 1536, "loss": 0.0173, "lr": 6.797757605527461e-07, "epoch": 2.5234375, "percentage": 84.11, "elapsed_time": "0:19:39", "remaining_time": "0:03:42"}
43
+ {"current_steps": 1293, "total_steps": 1536, "loss": 0.0111, "lr": 6.743658884946464e-07, "epoch": 2.525390625, "percentage": 84.18, "elapsed_time": "0:20:07", "remaining_time": "0:03:46"}
44
+ {"current_steps": 1294, "total_steps": 1536, "loss": 0.0139, "lr": 6.689760721804411e-07, "epoch": 2.52734375, "percentage": 84.24, "elapsed_time": "0:20:35", "remaining_time": "0:03:51"}
45
+ {"current_steps": 1295, "total_steps": 1536, "loss": 0.0144, "lr": 6.636063365999428e-07, "epoch": 2.529296875, "percentage": 84.31, "elapsed_time": "0:21:03", "remaining_time": "0:03:55"}
46
+ {"current_steps": 1296, "total_steps": 1536, "loss": 0.017, "lr": 6.58256706649853e-07, "epoch": 2.53125, "percentage": 84.38, "elapsed_time": "0:21:30", "remaining_time": "0:03:59"}
47
+ {"current_steps": 1297, "total_steps": 1536, "loss": 0.0113, "lr": 6.529272071336617e-07, "epoch": 2.533203125, "percentage": 84.44, "elapsed_time": "0:21:58", "remaining_time": "0:04:03"}
48
+ {"current_steps": 1298, "total_steps": 1536, "loss": 0.0245, "lr": 6.476178627615221e-07, "epoch": 2.53515625, "percentage": 84.51, "elapsed_time": "0:22:26", "remaining_time": "0:04:06"}
49
+ {"current_steps": 1299, "total_steps": 1536, "loss": 0.0208, "lr": 6.423286981501331e-07, "epoch": 2.537109375, "percentage": 84.57, "elapsed_time": "0:22:54", "remaining_time": "0:04:10"}
50
+ {"current_steps": 1300, "total_steps": 1536, "loss": 0.0161, "lr": 6.370597378226378e-07, "epoch": 2.5390625, "percentage": 84.64, "elapsed_time": "0:23:22", "remaining_time": "0:04:14"}
51
+ {"current_steps": 1301, "total_steps": 1536, "loss": 0.0112, "lr": 6.318110062085004e-07, "epoch": 2.541015625, "percentage": 84.7, "elapsed_time": "0:23:49", "remaining_time": "0:04:18"}
52
+ {"current_steps": 1302, "total_steps": 1536, "loss": 0.0129, "lr": 6.265825276433901e-07, "epoch": 2.54296875, "percentage": 84.77, "elapsed_time": "0:24:17", "remaining_time": "0:04:21"}
53
+ {"current_steps": 1303, "total_steps": 1536, "loss": 0.0144, "lr": 6.213743263690791e-07, "epoch": 2.544921875, "percentage": 84.83, "elapsed_time": "0:24:45", "remaining_time": "0:04:25"}
54
+ {"current_steps": 1304, "total_steps": 1536, "loss": 0.0225, "lr": 6.161864265333229e-07, "epoch": 2.546875, "percentage": 84.9, "elapsed_time": "0:25:13", "remaining_time": "0:04:29"}
55
+ {"current_steps": 1305, "total_steps": 1536, "loss": 0.016, "lr": 6.110188521897475e-07, "epoch": 2.548828125, "percentage": 84.96, "elapsed_time": "0:25:41", "remaining_time": "0:04:32"}
56
+ {"current_steps": 1306, "total_steps": 1536, "loss": 0.0183, "lr": 6.058716272977405e-07, "epoch": 2.55078125, "percentage": 85.03, "elapsed_time": "0:26:09", "remaining_time": "0:04:36"}
57
+ {"current_steps": 1307, "total_steps": 1536, "loss": 0.0139, "lr": 6.007447757223422e-07, "epoch": 2.552734375, "percentage": 85.09, "elapsed_time": "0:26:37", "remaining_time": "0:04:39"}
58
+ {"current_steps": 1308, "total_steps": 1536, "loss": 0.0168, "lr": 5.956383212341294e-07, "epoch": 2.5546875, "percentage": 85.16, "elapsed_time": "0:27:05", "remaining_time": "0:04:43"}
59
+ {"current_steps": 1309, "total_steps": 1536, "loss": 0.0087, "lr": 5.90552287509108e-07, "epoch": 2.556640625, "percentage": 85.22, "elapsed_time": "0:27:33", "remaining_time": "0:04:46"}
60
+ {"current_steps": 1310, "total_steps": 1536, "loss": 0.0135, "lr": 5.854866981286061e-07, "epoch": 2.55859375, "percentage": 85.29, "elapsed_time": "0:28:00", "remaining_time": "0:04:49"}
61
+ {"current_steps": 1311, "total_steps": 1536, "loss": 0.013, "lr": 5.804415765791599e-07, "epoch": 2.560546875, "percentage": 85.35, "elapsed_time": "0:28:28", "remaining_time": "0:04:53"}
62
+ {"current_steps": 1312, "total_steps": 1536, "loss": 0.0134, "lr": 5.754169462524056e-07, "epoch": 2.5625, "percentage": 85.42, "elapsed_time": "0:28:56", "remaining_time": "0:04:56"}
63
+ {"current_steps": 1313, "total_steps": 1536, "loss": 0.0256, "lr": 5.704128304449758e-07, "epoch": 2.564453125, "percentage": 85.48, "elapsed_time": "0:29:24", "remaining_time": "0:04:59"}
64
+ {"current_steps": 1314, "total_steps": 1536, "loss": 0.0147, "lr": 5.654292523583843e-07, "epoch": 2.56640625, "percentage": 85.55, "elapsed_time": "0:29:52", "remaining_time": "0:05:02"}
65
+ {"current_steps": 1315, "total_steps": 1536, "loss": 0.0161, "lr": 5.604662350989226e-07, "epoch": 2.568359375, "percentage": 85.61, "elapsed_time": "0:30:19", "remaining_time": "0:05:05"}
66
+ {"current_steps": 1316, "total_steps": 1536, "loss": 0.0248, "lr": 5.555238016775538e-07, "epoch": 2.5703125, "percentage": 85.68, "elapsed_time": "0:30:47", "remaining_time": "0:05:08"}
67
+ {"current_steps": 1317, "total_steps": 1536, "loss": 0.0169, "lr": 5.50601975009804e-07, "epoch": 2.572265625, "percentage": 85.74, "elapsed_time": "0:31:15", "remaining_time": "0:05:11"}
68
+ {"current_steps": 1318, "total_steps": 1536, "loss": 0.0115, "lr": 5.457007779156553e-07, "epoch": 2.57421875, "percentage": 85.81, "elapsed_time": "0:31:43", "remaining_time": "0:05:14"}
69
+ {"current_steps": 1319, "total_steps": 1536, "loss": 0.0218, "lr": 5.408202331194406e-07, "epoch": 2.576171875, "percentage": 85.87, "elapsed_time": "0:32:10", "remaining_time": "0:05:17"}
70
+ {"current_steps": 1320, "total_steps": 1536, "loss": 0.0243, "lr": 5.359603632497412e-07, "epoch": 2.578125, "percentage": 85.94, "elapsed_time": "0:32:38", "remaining_time": "0:05:20"}
71
+ {"current_steps": 1321, "total_steps": 1536, "loss": 0.0179, "lr": 5.311211908392772e-07, "epoch": 2.580078125, "percentage": 86.0, "elapsed_time": "0:33:06", "remaining_time": "0:05:23"}
72
+ {"current_steps": 1322, "total_steps": 1536, "loss": 0.0136, "lr": 5.263027383248049e-07, "epoch": 2.58203125, "percentage": 86.07, "elapsed_time": "0:33:34", "remaining_time": "0:05:26"}
73
+ {"current_steps": 1323, "total_steps": 1536, "loss": 0.0091, "lr": 5.215050280470163e-07, "epoch": 2.583984375, "percentage": 86.13, "elapsed_time": "0:34:02", "remaining_time": "0:05:28"}
74
+ {"current_steps": 1324, "total_steps": 1536, "loss": 0.0175, "lr": 5.167280822504278e-07, "epoch": 2.5859375, "percentage": 86.2, "elapsed_time": "0:34:30", "remaining_time": "0:05:31"}
75
+ {"current_steps": 1325, "total_steps": 1536, "loss": 0.0141, "lr": 5.119719230832842e-07, "epoch": 2.587890625, "percentage": 86.26, "elapsed_time": "0:34:58", "remaining_time": "0:05:34"}
76
+ {"current_steps": 1326, "total_steps": 1536, "loss": 0.0152, "lr": 5.072365725974543e-07, "epoch": 2.58984375, "percentage": 86.33, "elapsed_time": "0:35:25", "remaining_time": "0:05:36"}
77
+ {"current_steps": 1327, "total_steps": 1536, "loss": 0.0213, "lr": 5.02522052748326e-07, "epoch": 2.591796875, "percentage": 86.39, "elapsed_time": "0:35:53", "remaining_time": "0:05:39"}
78
+ {"current_steps": 1328, "total_steps": 1536, "loss": 0.0115, "lr": 4.978283853947047e-07, "epoch": 2.59375, "percentage": 86.46, "elapsed_time": "0:36:21", "remaining_time": "0:05:41"}
79
+ {"current_steps": 1329, "total_steps": 1536, "loss": 0.0213, "lr": 4.93155592298718e-07, "epoch": 2.595703125, "percentage": 86.52, "elapsed_time": "0:36:49", "remaining_time": "0:05:44"}
80
+ {"current_steps": 1330, "total_steps": 1536, "loss": 0.0198, "lr": 4.885036951257055e-07, "epoch": 2.59765625, "percentage": 86.59, "elapsed_time": "0:37:17", "remaining_time": "0:05:46"}
81
+ {"current_steps": 1331, "total_steps": 1536, "loss": 0.0191, "lr": 4.83872715444128e-07, "epoch": 2.599609375, "percentage": 86.65, "elapsed_time": "0:37:44", "remaining_time": "0:05:48"}
82
+ {"current_steps": 1332, "total_steps": 1536, "loss": 0.0164, "lr": 4.79262674725458e-07, "epoch": 2.6015625, "percentage": 86.72, "elapsed_time": "0:38:12", "remaining_time": "0:05:51"}
83
+ {"current_steps": 1333, "total_steps": 1536, "loss": 0.0165, "lr": 4.7467359434408613e-07, "epoch": 2.603515625, "percentage": 86.78, "elapsed_time": "0:38:40", "remaining_time": "0:05:53"}
84
+ {"current_steps": 1334, "total_steps": 1536, "loss": 0.0189, "lr": 4.7010549557722387e-07, "epoch": 2.60546875, "percentage": 86.85, "elapsed_time": "0:39:08", "remaining_time": "0:05:55"}
85
+ {"current_steps": 1335, "total_steps": 1536, "loss": 0.0221, "lr": 4.655583996047969e-07, "epoch": 2.607421875, "percentage": 86.91, "elapsed_time": "0:39:36", "remaining_time": "0:05:57"}
86
+ {"current_steps": 1336, "total_steps": 1536, "loss": 0.0086, "lr": 4.6103232750935534e-07, "epoch": 2.609375, "percentage": 86.98, "elapsed_time": "0:40:04", "remaining_time": "0:05:59"}
87
+ {"current_steps": 1337, "total_steps": 1536, "loss": 0.0145, "lr": 4.5652730027597125e-07, "epoch": 2.611328125, "percentage": 87.04, "elapsed_time": "0:40:31", "remaining_time": "0:06:01"}
88
+ {"current_steps": 1338, "total_steps": 1536, "loss": 0.0119, "lr": 4.5204333879214024e-07, "epoch": 2.61328125, "percentage": 87.11, "elapsed_time": "0:40:59", "remaining_time": "0:06:04"}
89
+ {"current_steps": 1339, "total_steps": 1536, "loss": 0.0209, "lr": 4.475804638476916e-07, "epoch": 2.615234375, "percentage": 87.17, "elapsed_time": "0:41:27", "remaining_time": "0:06:05"}
90
+ {"current_steps": 1340, "total_steps": 1536, "loss": 0.0149, "lr": 4.431386961346834e-07, "epoch": 2.6171875, "percentage": 87.24, "elapsed_time": "0:41:55", "remaining_time": "0:06:07"}
91
+ {"current_steps": 1341, "total_steps": 1536, "loss": 0.0093, "lr": 4.387180562473103e-07, "epoch": 2.619140625, "percentage": 87.3, "elapsed_time": "0:42:22", "remaining_time": "0:06:09"}
92
+ {"current_steps": 1342, "total_steps": 1536, "loss": 0.0106, "lr": 4.34318564681811e-07, "epoch": 2.62109375, "percentage": 87.37, "elapsed_time": "0:42:50", "remaining_time": "0:06:11"}
93
+ {"current_steps": 1343, "total_steps": 1536, "loss": 0.0243, "lr": 4.299402418363663e-07, "epoch": 2.623046875, "percentage": 87.43, "elapsed_time": "0:43:18", "remaining_time": "0:06:13"}
94
+ {"current_steps": 1344, "total_steps": 1536, "loss": 0.0161, "lr": 4.255831080110134e-07, "epoch": 2.625, "percentage": 87.5, "elapsed_time": "0:43:46", "remaining_time": "0:06:15"}
95
+ {"current_steps": 1345, "total_steps": 1536, "loss": 0.0121, "lr": 4.212471834075432e-07, "epoch": 2.626953125, "percentage": 87.57, "elapsed_time": "0:44:14", "remaining_time": "0:06:16"}
96
+ {"current_steps": 1346, "total_steps": 1536, "loss": 0.02, "lr": 4.169324881294096e-07, "epoch": 2.62890625, "percentage": 87.63, "elapsed_time": "0:44:42", "remaining_time": "0:06:18"}
97
+ {"current_steps": 1347, "total_steps": 1536, "loss": 0.0211, "lr": 4.1263904218164064e-07, "epoch": 2.630859375, "percentage": 87.7, "elapsed_time": "0:45:10", "remaining_time": "0:06:20"}
98
+ {"current_steps": 1348, "total_steps": 1536, "loss": 0.021, "lr": 4.083668654707401e-07, "epoch": 2.6328125, "percentage": 87.76, "elapsed_time": "0:45:38", "remaining_time": "0:06:21"}
99
+ {"current_steps": 1349, "total_steps": 1536, "loss": 0.0124, "lr": 4.041159778045961e-07, "epoch": 2.634765625, "percentage": 87.83, "elapsed_time": "0:46:05", "remaining_time": "0:06:23"}
100
+ {"current_steps": 1350, "total_steps": 1536, "loss": 0.0111, "lr": 3.9988639889239344e-07, "epoch": 2.63671875, "percentage": 87.89, "elapsed_time": "0:46:33", "remaining_time": "0:06:24"}
101
+ {"current_steps": 1351, "total_steps": 1536, "loss": 0.0162, "lr": 3.956781483445166e-07, "epoch": 2.638671875, "percentage": 87.96, "elapsed_time": "0:47:01", "remaining_time": "0:06:26"}
102
+ {"current_steps": 1352, "total_steps": 1536, "loss": 0.0114, "lr": 3.9149124567246066e-07, "epoch": 2.640625, "percentage": 88.02, "elapsed_time": "0:47:29", "remaining_time": "0:06:27"}
103
+ {"current_steps": 1353, "total_steps": 1536, "loss": 0.0233, "lr": 3.8732571028874566e-07, "epoch": 2.642578125, "percentage": 88.09, "elapsed_time": "0:47:57", "remaining_time": "0:06:29"}
104
+ {"current_steps": 1354, "total_steps": 1536, "loss": 0.0213, "lr": 3.8318156150681853e-07, "epoch": 2.64453125, "percentage": 88.15, "elapsed_time": "0:48:25", "remaining_time": "0:06:30"}
105
+ {"current_steps": 1355, "total_steps": 1536, "loss": 0.0228, "lr": 3.7905881854096824e-07, "epoch": 2.646484375, "percentage": 88.22, "elapsed_time": "0:48:53", "remaining_time": "0:06:31"}
106
+ {"current_steps": 1356, "total_steps": 1536, "loss": 0.0132, "lr": 3.7495750050623724e-07, "epoch": 2.6484375, "percentage": 88.28, "elapsed_time": "0:49:21", "remaining_time": "0:06:33"}
107
+ {"current_steps": 1357, "total_steps": 1536, "loss": 0.0115, "lr": 3.708776264183322e-07, "epoch": 2.650390625, "percentage": 88.35, "elapsed_time": "0:49:49", "remaining_time": "0:06:34"}
108
+ {"current_steps": 1358, "total_steps": 1536, "loss": 0.0151, "lr": 3.668192151935335e-07, "epoch": 2.65234375, "percentage": 88.41, "elapsed_time": "0:50:17", "remaining_time": "0:06:35"}
109
+ {"current_steps": 1359, "total_steps": 1536, "loss": 0.0121, "lr": 3.627822856486074e-07, "epoch": 2.654296875, "percentage": 88.48, "elapsed_time": "0:50:44", "remaining_time": "0:06:36"}
110
+ {"current_steps": 1360, "total_steps": 1536, "loss": 0.0127, "lr": 3.587668565007263e-07, "epoch": 2.65625, "percentage": 88.54, "elapsed_time": "0:51:12", "remaining_time": "0:06:37"}
111
+ {"current_steps": 1361, "total_steps": 1536, "loss": 0.0161, "lr": 3.5477294636737157e-07, "epoch": 2.658203125, "percentage": 88.61, "elapsed_time": "0:51:40", "remaining_time": "0:06:38"}
112
+ {"current_steps": 1362, "total_steps": 1536, "loss": 0.0104, "lr": 3.508005737662523e-07, "epoch": 2.66015625, "percentage": 88.67, "elapsed_time": "0:52:08", "remaining_time": "0:06:39"}
113
+ {"current_steps": 1363, "total_steps": 1536, "loss": 0.0167, "lr": 3.468497571152218e-07, "epoch": 2.662109375, "percentage": 88.74, "elapsed_time": "0:52:36", "remaining_time": "0:06:40"}
114
+ {"current_steps": 1364, "total_steps": 1536, "loss": 0.0133, "lr": 3.429205147321879e-07, "epoch": 2.6640625, "percentage": 88.8, "elapsed_time": "0:53:04", "remaining_time": "0:06:41"}
115
+ {"current_steps": 1365, "total_steps": 1536, "loss": 0.0125, "lr": 3.390128648350277e-07, "epoch": 2.666015625, "percentage": 88.87, "elapsed_time": "0:53:32", "remaining_time": "0:06:42"}
116
+ {"current_steps": 1366, "total_steps": 1536, "loss": 0.011, "lr": 3.3512682554150857e-07, "epoch": 2.66796875, "percentage": 88.93, "elapsed_time": "0:53:59", "remaining_time": "0:06:43"}
117
+ {"current_steps": 1367, "total_steps": 1536, "loss": 0.0119, "lr": 3.312624148692001e-07, "epoch": 2.669921875, "percentage": 89.0, "elapsed_time": "0:54:27", "remaining_time": "0:06:44"}
118
+ {"current_steps": 1368, "total_steps": 1536, "loss": 0.0222, "lr": 3.274196507353866e-07, "epoch": 2.671875, "percentage": 89.06, "elapsed_time": "0:54:55", "remaining_time": "0:06:44"}
119
+ {"current_steps": 1369, "total_steps": 1536, "loss": 0.0219, "lr": 3.2359855095699444e-07, "epoch": 2.673828125, "percentage": 89.13, "elapsed_time": "0:55:23", "remaining_time": "0:06:45"}
120
+ {"current_steps": 1370, "total_steps": 1536, "loss": 0.0156, "lr": 3.197991332505018e-07, "epoch": 2.67578125, "percentage": 89.19, "elapsed_time": "0:55:51", "remaining_time": "0:06:46"}
121
+ {"current_steps": 1371, "total_steps": 1536, "loss": 0.0135, "lr": 3.1602141523185414e-07, "epoch": 2.677734375, "percentage": 89.26, "elapsed_time": "0:56:19", "remaining_time": "0:06:46"}
122
+ {"current_steps": 1372, "total_steps": 1536, "loss": 0.0174, "lr": 3.1226541441639114e-07, "epoch": 2.6796875, "percentage": 89.32, "elapsed_time": "0:56:47", "remaining_time": "0:06:47"}
123
+ {"current_steps": 1373, "total_steps": 1536, "loss": 0.018, "lr": 3.0853114821876193e-07, "epoch": 2.681640625, "percentage": 89.39, "elapsed_time": "0:57:15", "remaining_time": "0:06:47"}
124
+ {"current_steps": 1374, "total_steps": 1536, "loss": 0.0114, "lr": 3.0481863395283807e-07, "epoch": 2.68359375, "percentage": 89.45, "elapsed_time": "0:57:42", "remaining_time": "0:06:48"}
125
+ {"current_steps": 1375, "total_steps": 1536, "loss": 0.0112, "lr": 3.011278888316421e-07, "epoch": 2.685546875, "percentage": 89.52, "elapsed_time": "0:58:10", "remaining_time": "0:06:48"}
126
+ {"current_steps": 1376, "total_steps": 1536, "loss": 0.0179, "lr": 2.9745892996726535e-07, "epoch": 2.6875, "percentage": 89.58, "elapsed_time": "0:58:38", "remaining_time": "0:06:49"}
127
+ {"current_steps": 1377, "total_steps": 1536, "loss": 0.0128, "lr": 2.938117743707847e-07, "epoch": 2.689453125, "percentage": 89.65, "elapsed_time": "0:59:06", "remaining_time": "0:06:49"}
128
+ {"current_steps": 1378, "total_steps": 1536, "loss": 0.0111, "lr": 2.901864389521869e-07, "epoch": 2.69140625, "percentage": 89.71, "elapsed_time": "0:59:34", "remaining_time": "0:06:49"}
129
+ {"current_steps": 1379, "total_steps": 1536, "loss": 0.0183, "lr": 2.8658294052029246e-07, "epoch": 2.693359375, "percentage": 89.78, "elapsed_time": "1:00:02", "remaining_time": "0:06:50"}
130
+ {"current_steps": 1380, "total_steps": 1536, "loss": 0.0153, "lr": 2.8300129578267164e-07, "epoch": 2.6953125, "percentage": 89.84, "elapsed_time": "1:00:30", "remaining_time": "0:06:50"}
131
+ {"current_steps": 1381, "total_steps": 1536, "loss": 0.011, "lr": 2.794415213455709e-07, "epoch": 2.697265625, "percentage": 89.91, "elapsed_time": "1:00:58", "remaining_time": "0:06:50"}
132
+ {"current_steps": 1382, "total_steps": 1536, "loss": 0.0117, "lr": 2.759036337138382e-07, "epoch": 2.69921875, "percentage": 89.97, "elapsed_time": "1:01:26", "remaining_time": "0:06:50"}
133
+ {"current_steps": 1383, "total_steps": 1536, "loss": 0.0187, "lr": 2.723876492908406e-07, "epoch": 2.701171875, "percentage": 90.04, "elapsed_time": "1:01:54", "remaining_time": "0:06:50"}
134
+ {"current_steps": 1384, "total_steps": 1536, "loss": 0.0103, "lr": 2.6889358437839074e-07, "epoch": 2.703125, "percentage": 90.1, "elapsed_time": "1:02:22", "remaining_time": "0:06:51"}
135
+ {"current_steps": 1385, "total_steps": 1536, "loss": 0.0224, "lr": 2.654214551766759e-07, "epoch": 2.705078125, "percentage": 90.17, "elapsed_time": "1:02:50", "remaining_time": "0:06:51"}
136
+ {"current_steps": 1386, "total_steps": 1536, "loss": 0.0266, "lr": 2.619712777841743e-07, "epoch": 2.70703125, "percentage": 90.23, "elapsed_time": "1:03:17", "remaining_time": "0:06:51"}
137
+ {"current_steps": 1387, "total_steps": 1536, "loss": 0.0147, "lr": 2.5854306819758647e-07, "epoch": 2.708984375, "percentage": 90.3, "elapsed_time": "1:03:45", "remaining_time": "0:06:51"}
138
+ {"current_steps": 1388, "total_steps": 1536, "loss": 0.024, "lr": 2.551368423117601e-07, "epoch": 2.7109375, "percentage": 90.36, "elapsed_time": "1:04:13", "remaining_time": "0:06:50"}
139
+ {"current_steps": 1389, "total_steps": 1536, "loss": 0.0191, "lr": 2.517526159196171e-07, "epoch": 2.712890625, "percentage": 90.43, "elapsed_time": "1:04:41", "remaining_time": "0:06:50"}
140
+ {"current_steps": 1390, "total_steps": 1536, "loss": 0.0098, "lr": 2.4839040471207386e-07, "epoch": 2.71484375, "percentage": 90.49, "elapsed_time": "1:05:09", "remaining_time": "0:06:50"}
141
+ {"current_steps": 1391, "total_steps": 1536, "loss": 0.0168, "lr": 2.4505022427797843e-07, "epoch": 2.716796875, "percentage": 90.56, "elapsed_time": "1:05:37", "remaining_time": "0:06:50"}
142
+ {"current_steps": 1392, "total_steps": 1536, "loss": 0.0116, "lr": 2.4173209010403374e-07, "epoch": 2.71875, "percentage": 90.62, "elapsed_time": "1:06:05", "remaining_time": "0:06:50"}
143
+ {"current_steps": 1393, "total_steps": 1536, "loss": 0.0186, "lr": 2.3843601757472193e-07, "epoch": 2.720703125, "percentage": 90.69, "elapsed_time": "1:06:32", "remaining_time": "0:06:49"}
144
+ {"current_steps": 1394, "total_steps": 1536, "loss": 0.0101, "lr": 2.3516202197223892e-07, "epoch": 2.72265625, "percentage": 90.76, "elapsed_time": "1:07:00", "remaining_time": "0:06:49"}
145
+ {"current_steps": 1395, "total_steps": 1536, "loss": 0.0121, "lr": 2.319101184764222e-07, "epoch": 2.724609375, "percentage": 90.82, "elapsed_time": "1:07:28", "remaining_time": "0:06:49"}
146
+ {"current_steps": 1396, "total_steps": 1536, "loss": 0.0178, "lr": 2.286803221646766e-07, "epoch": 2.7265625, "percentage": 90.89, "elapsed_time": "1:07:56", "remaining_time": "0:06:48"}
147
+ {"current_steps": 1397, "total_steps": 1536, "loss": 0.0133, "lr": 2.2547264801190904e-07, "epoch": 2.728515625, "percentage": 90.95, "elapsed_time": "1:08:24", "remaining_time": "0:06:48"}
148
+ {"current_steps": 1398, "total_steps": 1536, "loss": 0.0147, "lr": 2.222871108904584e-07, "epoch": 2.73046875, "percentage": 91.02, "elapsed_time": "1:08:52", "remaining_time": "0:06:47"}
149
+ {"current_steps": 1399, "total_steps": 1536, "loss": 0.0172, "lr": 2.1912372557002404e-07, "epoch": 2.732421875, "percentage": 91.08, "elapsed_time": "1:09:20", "remaining_time": "0:06:47"}
150
+ {"current_steps": 1400, "total_steps": 1536, "loss": 0.0142, "lr": 2.1598250671759802e-07, "epoch": 2.734375, "percentage": 91.15, "elapsed_time": "1:09:47", "remaining_time": "0:06:46"}
151
+ {"current_steps": 1401, "total_steps": 1536, "loss": 0.019, "lr": 2.128634688973996e-07, "epoch": 2.736328125, "percentage": 91.21, "elapsed_time": "1:10:15", "remaining_time": "0:06:46"}
152
+ {"current_steps": 1402, "total_steps": 1536, "loss": 0.019, "lr": 2.0976662657080594e-07, "epoch": 2.73828125, "percentage": 91.28, "elapsed_time": "1:10:43", "remaining_time": "0:06:45"}
153
+ {"current_steps": 1403, "total_steps": 1536, "loss": 0.0218, "lr": 2.066919940962836e-07, "epoch": 2.740234375, "percentage": 91.34, "elapsed_time": "1:11:11", "remaining_time": "0:06:44"}
154
+ {"current_steps": 1404, "total_steps": 1536, "loss": 0.0107, "lr": 2.0363958572932495e-07, "epoch": 2.7421875, "percentage": 91.41, "elapsed_time": "1:11:39", "remaining_time": "0:06:44"}
155
+ {"current_steps": 1405, "total_steps": 1536, "loss": 0.0156, "lr": 2.0060941562237923e-07, "epoch": 2.744140625, "percentage": 91.47, "elapsed_time": "1:12:07", "remaining_time": "0:06:43"}
156
+ {"current_steps": 1406, "total_steps": 1536, "loss": 0.0158, "lr": 1.9760149782478976e-07, "epoch": 2.74609375, "percentage": 91.54, "elapsed_time": "1:12:35", "remaining_time": "0:06:42"}
157
+ {"current_steps": 1407, "total_steps": 1536, "loss": 0.0131, "lr": 1.9461584628272633e-07, "epoch": 2.748046875, "percentage": 91.6, "elapsed_time": "1:13:02", "remaining_time": "0:06:41"}
158
+ {"current_steps": 1408, "total_steps": 1536, "loss": 0.0125, "lr": 1.9165247483912243e-07, "epoch": 2.75, "percentage": 91.67, "elapsed_time": "1:13:30", "remaining_time": "0:06:40"}
159
+ {"current_steps": 1409, "total_steps": 1536, "loss": 0.0155, "lr": 1.887113972336091e-07, "epoch": 2.751953125, "percentage": 91.73, "elapsed_time": "1:13:58", "remaining_time": "0:06:40"}
160
+ {"current_steps": 1410, "total_steps": 1536, "loss": 0.0139, "lr": 1.8579262710245184e-07, "epoch": 2.75390625, "percentage": 91.8, "elapsed_time": "1:14:26", "remaining_time": "0:06:39"}
161
+ {"current_steps": 1411, "total_steps": 1536, "loss": 0.02, "lr": 1.8289617797849045e-07, "epoch": 2.755859375, "percentage": 91.86, "elapsed_time": "1:14:54", "remaining_time": "0:06:38"}
162
+ {"current_steps": 1412, "total_steps": 1536, "loss": 0.023, "lr": 1.8002206329107097e-07, "epoch": 2.7578125, "percentage": 91.93, "elapsed_time": "1:15:22", "remaining_time": "0:06:37"}
163
+ {"current_steps": 1413, "total_steps": 1536, "loss": 0.0216, "lr": 1.7717029636598714e-07, "epoch": 2.759765625, "percentage": 91.99, "elapsed_time": "1:15:50", "remaining_time": "0:06:36"}
164
+ {"current_steps": 1414, "total_steps": 1536, "loss": 0.0162, "lr": 1.7434089042541791e-07, "epoch": 2.76171875, "percentage": 92.06, "elapsed_time": "1:16:17", "remaining_time": "0:06:34"}
165
+ {"current_steps": 1415, "total_steps": 1536, "loss": 0.0161, "lr": 1.715338585878662e-07, "epoch": 2.763671875, "percentage": 92.12, "elapsed_time": "1:16:45", "remaining_time": "0:06:33"}
166
+ {"current_steps": 1416, "total_steps": 1536, "loss": 0.0166, "lr": 1.6874921386809572e-07, "epoch": 2.765625, "percentage": 92.19, "elapsed_time": "1:17:13", "remaining_time": "0:06:32"}
167
+ {"current_steps": 1417, "total_steps": 1536, "loss": 0.0135, "lr": 1.6598696917707492e-07, "epoch": 2.767578125, "percentage": 92.25, "elapsed_time": "1:17:41", "remaining_time": "0:06:31"}
168
+ {"current_steps": 1418, "total_steps": 1536, "loss": 0.013, "lr": 1.63247137321913e-07, "epoch": 2.76953125, "percentage": 92.32, "elapsed_time": "1:18:08", "remaining_time": "0:06:30"}
169
+ {"current_steps": 1419, "total_steps": 1536, "loss": 0.0176, "lr": 1.605297310058046e-07, "epoch": 2.771484375, "percentage": 92.38, "elapsed_time": "1:18:36", "remaining_time": "0:06:28"}
170
+ {"current_steps": 1420, "total_steps": 1536, "loss": 0.0089, "lr": 1.578347628279664e-07, "epoch": 2.7734375, "percentage": 92.45, "elapsed_time": "1:19:04", "remaining_time": "0:06:27"}
171
+ {"current_steps": 1421, "total_steps": 1536, "loss": 0.0126, "lr": 1.5516224528358103e-07, "epoch": 2.775390625, "percentage": 92.51, "elapsed_time": "1:19:32", "remaining_time": "0:06:26"}
172
+ {"current_steps": 1422, "total_steps": 1536, "loss": 0.0201, "lr": 1.5251219076374114e-07, "epoch": 2.77734375, "percentage": 92.58, "elapsed_time": "1:20:00", "remaining_time": "0:06:24"}
173
+ {"current_steps": 1423, "total_steps": 1536, "loss": 0.0155, "lr": 1.4988461155538813e-07, "epoch": 2.779296875, "percentage": 92.64, "elapsed_time": "1:20:28", "remaining_time": "0:06:23"}
174
+ {"current_steps": 1424, "total_steps": 1536, "loss": 0.0173, "lr": 1.4727951984125688e-07, "epoch": 2.78125, "percentage": 92.71, "elapsed_time": "1:20:56", "remaining_time": "0:06:21"}
175
+ {"current_steps": 1425, "total_steps": 1536, "loss": 0.0145, "lr": 1.4469692769982057e-07, "epoch": 2.783203125, "percentage": 92.77, "elapsed_time": "1:21:24", "remaining_time": "0:06:20"}
176
+ {"current_steps": 1426, "total_steps": 1536, "loss": 0.0231, "lr": 1.4213684710523257e-07, "epoch": 2.78515625, "percentage": 92.84, "elapsed_time": "1:21:52", "remaining_time": "0:06:18"}
177
+ {"current_steps": 1427, "total_steps": 1536, "loss": 0.0168, "lr": 1.3959928992727078e-07, "epoch": 2.787109375, "percentage": 92.9, "elapsed_time": "1:22:20", "remaining_time": "0:06:17"}
178
+ {"current_steps": 1428, "total_steps": 1536, "loss": 0.0129, "lr": 1.3708426793128615e-07, "epoch": 2.7890625, "percentage": 92.97, "elapsed_time": "1:22:48", "remaining_time": "0:06:15"}
179
+ {"current_steps": 1429, "total_steps": 1536, "loss": 0.019, "lr": 1.345917927781426e-07, "epoch": 2.791015625, "percentage": 93.03, "elapsed_time": "1:23:15", "remaining_time": "0:06:14"}
180
+ {"current_steps": 1430, "total_steps": 1536, "loss": 0.0219, "lr": 1.321218760241688e-07, "epoch": 2.79296875, "percentage": 93.1, "elapsed_time": "1:23:43", "remaining_time": "0:06:12"}
181
+ {"current_steps": 1431, "total_steps": 1536, "loss": 0.0154, "lr": 1.2967452912109878e-07, "epoch": 2.794921875, "percentage": 93.16, "elapsed_time": "1:24:11", "remaining_time": "0:06:10"}
182
+ {"current_steps": 1432, "total_steps": 1536, "loss": 0.0149, "lr": 1.272497634160247e-07, "epoch": 2.796875, "percentage": 93.23, "elapsed_time": "1:24:39", "remaining_time": "0:06:08"}
183
+ {"current_steps": 1433, "total_steps": 1536, "loss": 0.0104, "lr": 1.2484759015133906e-07, "epoch": 2.798828125, "percentage": 93.29, "elapsed_time": "1:25:07", "remaining_time": "0:06:07"}
184
+ {"current_steps": 1434, "total_steps": 1536, "loss": 0.0149, "lr": 1.2246802046468553e-07, "epoch": 2.80078125, "percentage": 93.36, "elapsed_time": "1:25:35", "remaining_time": "0:06:05"}
185
+ {"current_steps": 1435, "total_steps": 1536, "loss": 0.0193, "lr": 1.201110653889076e-07, "epoch": 2.802734375, "percentage": 93.42, "elapsed_time": "1:26:03", "remaining_time": "0:06:03"}
186
+ {"current_steps": 1436, "total_steps": 1536, "loss": 0.0177, "lr": 1.1777673585199434e-07, "epoch": 2.8046875, "percentage": 93.49, "elapsed_time": "1:26:31", "remaining_time": "0:06:01"}
187
+ {"current_steps": 1437, "total_steps": 1536, "loss": 0.0131, "lr": 1.1546504267703373e-07, "epoch": 2.806640625, "percentage": 93.55, "elapsed_time": "1:26:59", "remaining_time": "0:05:59"}
188
+ {"current_steps": 1438, "total_steps": 1536, "loss": 0.0149, "lr": 1.1317599658215938e-07, "epoch": 2.80859375, "percentage": 93.62, "elapsed_time": "1:27:27", "remaining_time": "0:05:57"}
189
+ {"current_steps": 1439, "total_steps": 1536, "loss": 0.0159, "lr": 1.1090960818050334e-07, "epoch": 2.810546875, "percentage": 93.68, "elapsed_time": "1:27:55", "remaining_time": "0:05:55"}
190
+ {"current_steps": 1440, "total_steps": 1536, "loss": 0.0191, "lr": 1.0866588798014277e-07, "epoch": 2.8125, "percentage": 93.75, "elapsed_time": "1:28:23", "remaining_time": "0:05:53"}
191
+ {"current_steps": 1441, "total_steps": 1536, "loss": 0.0216, "lr": 1.0644484638405839e-07, "epoch": 2.814453125, "percentage": 93.82, "elapsed_time": "1:28:51", "remaining_time": "0:05:51"}
192
+ {"current_steps": 1442, "total_steps": 1536, "loss": 0.0159, "lr": 1.0424649369007778e-07, "epoch": 2.81640625, "percentage": 93.88, "elapsed_time": "1:29:18", "remaining_time": "0:05:49"}
193
+ {"current_steps": 1443, "total_steps": 1536, "loss": 0.0136, "lr": 1.0207084009083379e-07, "epoch": 2.818359375, "percentage": 93.95, "elapsed_time": "1:29:46", "remaining_time": "0:05:47"}
194
+ {"current_steps": 1444, "total_steps": 1536, "loss": 0.0169, "lr": 9.991789567371513e-08, "epoch": 2.8203125, "percentage": 94.01, "elapsed_time": "1:30:14", "remaining_time": "0:05:44"}
195
+ {"current_steps": 1445, "total_steps": 1536, "loss": 0.0176, "lr": 9.778767042081972e-08, "epoch": 2.822265625, "percentage": 94.08, "elapsed_time": "1:30:42", "remaining_time": "0:05:42"}
196
+ {"current_steps": 1446, "total_steps": 1536, "loss": 0.0163, "lr": 9.568017420890697e-08, "epoch": 2.82421875, "percentage": 94.14, "elapsed_time": "1:31:10", "remaining_time": "0:05:40"}
197
+ {"current_steps": 1447, "total_steps": 1536, "loss": 0.0174, "lr": 9.359541680935447e-08, "epoch": 2.826171875, "percentage": 94.21, "elapsed_time": "1:31:38", "remaining_time": "0:05:38"}
198
+ {"current_steps": 1448, "total_steps": 1536, "loss": 0.0137, "lr": 9.15334078881136e-08, "epoch": 2.828125, "percentage": 94.27, "elapsed_time": "1:32:06", "remaining_time": "0:05:35"}
199
+ {"current_steps": 1449, "total_steps": 1536, "loss": 0.0123, "lr": 8.949415700565844e-08, "epoch": 2.830078125, "percentage": 94.34, "elapsed_time": "1:32:34", "remaining_time": "0:05:33"}
200
+ {"current_steps": 1450, "total_steps": 1536, "loss": 0.0189, "lr": 8.747767361694859e-08, "epoch": 2.83203125, "percentage": 94.4, "elapsed_time": "1:33:01", "remaining_time": "0:05:31"}
201
+ {"current_steps": 1451, "total_steps": 1536, "loss": 0.0182, "lr": 8.548396707138307e-08, "epoch": 2.833984375, "percentage": 94.47, "elapsed_time": "1:33:29", "remaining_time": "0:05:28"}
202
+ {"current_steps": 1452, "total_steps": 1536, "loss": 0.0124, "lr": 8.351304661275428e-08, "epoch": 2.8359375, "percentage": 94.53, "elapsed_time": "1:33:57", "remaining_time": "0:05:26"}
203
+ {"current_steps": 1453, "total_steps": 1536, "loss": 0.013, "lr": 8.156492137920857e-08, "epoch": 2.837890625, "percentage": 94.6, "elapsed_time": "1:34:25", "remaining_time": "0:05:23"}
204
+ {"current_steps": 1454, "total_steps": 1536, "loss": 0.0131, "lr": 7.963960040320184e-08, "epoch": 2.83984375, "percentage": 94.66, "elapsed_time": "1:34:53", "remaining_time": "0:05:21"}
205
+ {"current_steps": 1455, "total_steps": 1536, "loss": 0.0133, "lr": 7.773709261145901e-08, "epoch": 2.841796875, "percentage": 94.73, "elapsed_time": "1:35:20", "remaining_time": "0:05:18"}
206
+ {"current_steps": 1456, "total_steps": 1536, "loss": 0.0236, "lr": 7.58574068249307e-08, "epoch": 2.84375, "percentage": 94.79, "elapsed_time": "1:35:48", "remaining_time": "0:05:15"}
207
+ {"current_steps": 1457, "total_steps": 1536, "loss": 0.0213, "lr": 7.400055175875609e-08, "epoch": 2.845703125, "percentage": 94.86, "elapsed_time": "1:36:16", "remaining_time": "0:05:13"}
208
+ {"current_steps": 1458, "total_steps": 1536, "loss": 0.0182, "lr": 7.21665360222179e-08, "epoch": 2.84765625, "percentage": 94.92, "elapsed_time": "1:36:44", "remaining_time": "0:05:10"}
209
+ {"current_steps": 1459, "total_steps": 1536, "loss": 0.0147, "lr": 7.035536811870469e-08, "epoch": 2.849609375, "percentage": 94.99, "elapsed_time": "1:37:12", "remaining_time": "0:05:07"}
210
+ {"current_steps": 1460, "total_steps": 1536, "loss": 0.0151, "lr": 6.856705644567197e-08, "epoch": 2.8515625, "percentage": 95.05, "elapsed_time": "1:37:39", "remaining_time": "0:05:05"}
211
+ {"current_steps": 1461, "total_steps": 1536, "loss": 0.0152, "lr": 6.680160929460389e-08, "epoch": 2.853515625, "percentage": 95.12, "elapsed_time": "1:38:07", "remaining_time": "0:05:02"}
212
+ {"current_steps": 1462, "total_steps": 1536, "loss": 0.0143, "lr": 6.505903485097054e-08, "epoch": 2.85546875, "percentage": 95.18, "elapsed_time": "1:38:35", "remaining_time": "0:04:59"}
213
+ {"current_steps": 1463, "total_steps": 1536, "loss": 0.0126, "lr": 6.333934119419516e-08, "epoch": 2.857421875, "percentage": 95.25, "elapsed_time": "1:39:03", "remaining_time": "0:04:56"}
214
+ {"current_steps": 1464, "total_steps": 1536, "loss": 0.0263, "lr": 6.16425362976153e-08, "epoch": 2.859375, "percentage": 95.31, "elapsed_time": "1:39:31", "remaining_time": "0:04:53"}
215
+ {"current_steps": 1465, "total_steps": 1536, "loss": 0.0171, "lr": 5.996862802844172e-08, "epoch": 2.861328125, "percentage": 95.38, "elapsed_time": "1:39:59", "remaining_time": "0:04:50"}
216
+ {"current_steps": 1466, "total_steps": 1536, "loss": 0.0131, "lr": 5.831762414772901e-08, "epoch": 2.86328125, "percentage": 95.44, "elapsed_time": "1:40:26", "remaining_time": "0:04:47"}
217
+ {"current_steps": 1467, "total_steps": 1536, "loss": 0.0199, "lr": 5.6689532310333916e-08, "epoch": 2.865234375, "percentage": 95.51, "elapsed_time": "1:40:54", "remaining_time": "0:04:44"}
218
+ {"current_steps": 1468, "total_steps": 1536, "loss": 0.0138, "lr": 5.508436006488205e-08, "epoch": 2.8671875, "percentage": 95.57, "elapsed_time": "1:41:22", "remaining_time": "0:04:41"}
219
+ {"current_steps": 1469, "total_steps": 1536, "loss": 0.0136, "lr": 5.35021148537318e-08, "epoch": 2.869140625, "percentage": 95.64, "elapsed_time": "1:41:50", "remaining_time": "0:04:38"}
220
+ {"current_steps": 1470, "total_steps": 1536, "loss": 0.0161, "lr": 5.194280401294383e-08, "epoch": 2.87109375, "percentage": 95.7, "elapsed_time": "1:42:18", "remaining_time": "0:04:35"}
221
+ {"current_steps": 1471, "total_steps": 1536, "loss": 0.0135, "lr": 5.0406434772239946e-08, "epoch": 2.873046875, "percentage": 95.77, "elapsed_time": "1:42:46", "remaining_time": "0:04:32"}
222
+ {"current_steps": 1472, "total_steps": 1536, "loss": 0.0075, "lr": 4.889301425497539e-08, "epoch": 2.875, "percentage": 95.83, "elapsed_time": "1:43:13", "remaining_time": "0:04:29"}
223
+ {"current_steps": 1473, "total_steps": 1536, "loss": 0.0129, "lr": 4.740254947810441e-08, "epoch": 2.876953125, "percentage": 95.9, "elapsed_time": "1:43:42", "remaining_time": "0:04:26"}
224
+ {"current_steps": 1474, "total_steps": 1536, "loss": 0.0185, "lr": 4.593504735214693e-08, "epoch": 2.87890625, "percentage": 95.96, "elapsed_time": "1:44:09", "remaining_time": "0:04:22"}
225
+ {"current_steps": 1475, "total_steps": 1536, "loss": 0.0258, "lr": 4.4490514681156396e-08, "epoch": 2.880859375, "percentage": 96.03, "elapsed_time": "1:44:37", "remaining_time": "0:04:19"}
226
+ {"current_steps": 1476, "total_steps": 1536, "loss": 0.0116, "lr": 4.306895816268863e-08, "epoch": 2.8828125, "percentage": 96.09, "elapsed_time": "1:45:05", "remaining_time": "0:04:16"}
227
+ {"current_steps": 1477, "total_steps": 1536, "loss": 0.0149, "lr": 4.167038438777138e-08, "epoch": 2.884765625, "percentage": 96.16, "elapsed_time": "1:45:32", "remaining_time": "0:04:12"}
228
+ {"current_steps": 1478, "total_steps": 1536, "loss": 0.014, "lr": 4.029479984087259e-08, "epoch": 2.88671875, "percentage": 96.22, "elapsed_time": "1:46:00", "remaining_time": "0:04:09"}
229
+ {"current_steps": 1479, "total_steps": 1536, "loss": 0.013, "lr": 3.894221089987216e-08, "epoch": 2.888671875, "percentage": 96.29, "elapsed_time": "1:46:28", "remaining_time": "0:04:06"}
230
+ {"current_steps": 1480, "total_steps": 1536, "loss": 0.018, "lr": 3.761262383603026e-08, "epoch": 2.890625, "percentage": 96.35, "elapsed_time": "1:46:56", "remaining_time": "0:04:02"}
231
+ {"current_steps": 1481, "total_steps": 1536, "loss": 0.0141, "lr": 3.6306044813958496e-08, "epoch": 2.892578125, "percentage": 96.42, "elapsed_time": "1:47:24", "remaining_time": "0:03:59"}
232
+ {"current_steps": 1482, "total_steps": 1536, "loss": 0.0118, "lr": 3.5022479891593244e-08, "epoch": 2.89453125, "percentage": 96.48, "elapsed_time": "1:47:51", "remaining_time": "0:03:55"}
233
+ {"current_steps": 1483, "total_steps": 1536, "loss": 0.0179, "lr": 3.3761935020166224e-08, "epoch": 2.896484375, "percentage": 96.55, "elapsed_time": "1:48:19", "remaining_time": "0:03:52"}
234
+ {"current_steps": 1484, "total_steps": 1536, "loss": 0.0121, "lr": 3.2524416044176223e-08, "epoch": 2.8984375, "percentage": 96.61, "elapsed_time": "1:48:47", "remaining_time": "0:03:48"}
235
+ {"current_steps": 1485, "total_steps": 1536, "loss": 0.0204, "lr": 3.130992870136296e-08, "epoch": 2.900390625, "percentage": 96.68, "elapsed_time": "1:49:15", "remaining_time": "0:03:45"}
236
+ {"current_steps": 1486, "total_steps": 1536, "loss": 0.0181, "lr": 3.011847862268158e-08, "epoch": 2.90234375, "percentage": 96.74, "elapsed_time": "1:49:43", "remaining_time": "0:03:41"}
237
+ {"current_steps": 1487, "total_steps": 1536, "loss": 0.0103, "lr": 2.895007133227268e-08, "epoch": 2.904296875, "percentage": 96.81, "elapsed_time": "1:50:11", "remaining_time": "0:03:37"}
238
+ {"current_steps": 1488, "total_steps": 1536, "loss": 0.0135, "lr": 2.7804712247441744e-08, "epoch": 2.90625, "percentage": 96.88, "elapsed_time": "1:50:38", "remaining_time": "0:03:34"}
239
+ {"current_steps": 1489, "total_steps": 1536, "loss": 0.0149, "lr": 2.6682406678630867e-08, "epoch": 2.908203125, "percentage": 96.94, "elapsed_time": "1:51:06", "remaining_time": "0:03:30"}
240
+ {"current_steps": 1490, "total_steps": 1536, "loss": 0.0202, "lr": 2.55831598293943e-08, "epoch": 2.91015625, "percentage": 97.01, "elapsed_time": "1:51:34", "remaining_time": "0:03:26"}
241
+ {"current_steps": 1491, "total_steps": 1536, "loss": 0.013, "lr": 2.4506976796374595e-08, "epoch": 2.912109375, "percentage": 97.07, "elapsed_time": "1:52:02", "remaining_time": "0:03:22"}
242
+ {"current_steps": 1492, "total_steps": 1536, "loss": 0.0311, "lr": 2.3453862569280393e-08, "epoch": 2.9140625, "percentage": 97.14, "elapsed_time": "1:52:30", "remaining_time": "0:03:19"}
243
+ {"current_steps": 1493, "total_steps": 1536, "loss": 0.0154, "lr": 2.2423822030861462e-08, "epoch": 2.916015625, "percentage": 97.2, "elapsed_time": "1:52:58", "remaining_time": "0:03:15"}
244
+ {"current_steps": 1494, "total_steps": 1536, "loss": 0.0128, "lr": 2.1416859956887026e-08, "epoch": 2.91796875, "percentage": 97.27, "elapsed_time": "1:53:26", "remaining_time": "0:03:11"}
245
+ {"current_steps": 1495, "total_steps": 1536, "loss": 0.0149, "lr": 2.0432981016122454e-08, "epoch": 2.919921875, "percentage": 97.33, "elapsed_time": "1:53:54", "remaining_time": "0:03:07"}
246
+ {"current_steps": 1496, "total_steps": 1536, "loss": 0.0176, "lr": 1.9472189770309846e-08, "epoch": 2.921875, "percentage": 97.4, "elapsed_time": "1:54:21", "remaining_time": "0:03:03"}
247
+ {"current_steps": 1497, "total_steps": 1536, "loss": 0.0096, "lr": 1.8534490674144146e-08, "epoch": 2.923828125, "percentage": 97.46, "elapsed_time": "1:54:49", "remaining_time": "0:02:59"}
248
+ {"current_steps": 1498, "total_steps": 1536, "loss": 0.0161, "lr": 1.7619888075254833e-08, "epoch": 2.92578125, "percentage": 97.53, "elapsed_time": "1:55:17", "remaining_time": "0:02:55"}
249
+ {"current_steps": 1499, "total_steps": 1536, "loss": 0.0167, "lr": 1.6728386214184268e-08, "epoch": 2.927734375, "percentage": 97.59, "elapsed_time": "1:55:45", "remaining_time": "0:02:51"}
250
+ {"current_steps": 1500, "total_steps": 1536, "loss": 0.0116, "lr": 1.585998922436882e-08, "epoch": 2.9296875, "percentage": 97.66, "elapsed_time": "1:56:13", "remaining_time": "0:02:47"}
251
+ {"current_steps": 1501, "total_steps": 1536, "loss": 0.0219, "lr": 1.5014701132118892e-08, "epoch": 2.931640625, "percentage": 97.72, "elapsed_time": "1:57:20", "remaining_time": "0:02:44"}
252
+ {"current_steps": 1502, "total_steps": 1536, "loss": 0.017, "lr": 1.4192525856602247e-08, "epoch": 2.93359375, "percentage": 97.79, "elapsed_time": "1:57:48", "remaining_time": "0:02:40"}
253
+ {"current_steps": 1503, "total_steps": 1536, "loss": 0.0128, "lr": 1.339346720982293e-08, "epoch": 2.935546875, "percentage": 97.85, "elapsed_time": "1:58:16", "remaining_time": "0:02:35"}
254
+ {"current_steps": 1504, "total_steps": 1536, "loss": 0.013, "lr": 1.2617528896605724e-08, "epoch": 2.9375, "percentage": 97.92, "elapsed_time": "1:58:44", "remaining_time": "0:02:31"}
255
+ {"current_steps": 1505, "total_steps": 1536, "loss": 0.0122, "lr": 1.1864714514577269e-08, "epoch": 2.939453125, "percentage": 97.98, "elapsed_time": "1:59:12", "remaining_time": "0:02:27"}
256
+ {"current_steps": 1506, "total_steps": 1536, "loss": 0.0131, "lr": 1.1135027554152188e-08, "epoch": 2.94140625, "percentage": 98.05, "elapsed_time": "1:59:40", "remaining_time": "0:02:23"}
257
+ {"current_steps": 1507, "total_steps": 1536, "loss": 0.0192, "lr": 1.0428471398513663e-08, "epoch": 2.943359375, "percentage": 98.11, "elapsed_time": "2:00:08", "remaining_time": "0:02:18"}
258
+ {"current_steps": 1508, "total_steps": 1536, "loss": 0.0184, "lr": 9.745049323600098e-09, "epoch": 2.9453125, "percentage": 98.18, "elapsed_time": "2:00:36", "remaining_time": "0:02:14"}
259
+ {"current_steps": 1509, "total_steps": 1536, "loss": 0.0126, "lr": 9.084764498087928e-09, "epoch": 2.947265625, "percentage": 98.24, "elapsed_time": "2:01:04", "remaining_time": "0:02:09"}
260
+ {"current_steps": 1510, "total_steps": 1536, "loss": 0.0123, "lr": 8.447619983379952e-09, "epoch": 2.94921875, "percentage": 98.31, "elapsed_time": "2:01:31", "remaining_time": "0:02:05"}
261
+ {"current_steps": 1511, "total_steps": 1536, "loss": 0.0247, "lr": 7.833618733587012e-09, "epoch": 2.951171875, "percentage": 98.37, "elapsed_time": "2:01:59", "remaining_time": "0:02:01"}
262
+ {"current_steps": 1512, "total_steps": 1536, "loss": 0.0123, "lr": 7.24276359551801e-09, "epoch": 2.953125, "percentage": 98.44, "elapsed_time": "2:02:27", "remaining_time": "0:01:56"}
263
+ {"current_steps": 1513, "total_steps": 1536, "loss": 0.0123, "lr": 6.6750573086649116e-09, "epoch": 2.955078125, "percentage": 98.5, "elapsed_time": "2:02:55", "remaining_time": "0:01:52"}
264
+ {"current_steps": 1514, "total_steps": 1536, "loss": 0.0189, "lr": 6.130502505190538e-09, "epoch": 2.95703125, "percentage": 98.57, "elapsed_time": "2:03:23", "remaining_time": "0:01:47"}
265
+ {"current_steps": 1515, "total_steps": 1536, "loss": 0.018, "lr": 5.609101709914688e-09, "epoch": 2.958984375, "percentage": 98.63, "elapsed_time": "2:03:51", "remaining_time": "0:01:43"}
266
+ {"current_steps": 1516, "total_steps": 1536, "loss": 0.0136, "lr": 5.110857340305808e-09, "epoch": 2.9609375, "percentage": 98.7, "elapsed_time": "2:04:19", "remaining_time": "0:01:38"}
267
+ {"current_steps": 1517, "total_steps": 1536, "loss": 0.0065, "lr": 4.635771706467673e-09, "epoch": 2.962890625, "percentage": 98.76, "elapsed_time": "2:04:47", "remaining_time": "0:01:33"}
268
+ {"current_steps": 1518, "total_steps": 1536, "loss": 0.0172, "lr": 4.183847011127174e-09, "epoch": 2.96484375, "percentage": 98.83, "elapsed_time": "2:05:15", "remaining_time": "0:01:29"}
269
+ {"current_steps": 1519, "total_steps": 1536, "loss": 0.0175, "lr": 3.7550853496282066e-09, "epoch": 2.966796875, "percentage": 98.89, "elapsed_time": "2:05:43", "remaining_time": "0:01:24"}
270
+ {"current_steps": 1520, "total_steps": 1536, "loss": 0.0183, "lr": 3.349488709917803e-09, "epoch": 2.96875, "percentage": 98.96, "elapsed_time": "2:06:11", "remaining_time": "0:01:19"}
271
+ {"current_steps": 1521, "total_steps": 1536, "loss": 0.0174, "lr": 2.9670589725389052e-09, "epoch": 2.970703125, "percentage": 99.02, "elapsed_time": "2:06:38", "remaining_time": "0:01:14"}
272
+ {"current_steps": 1522, "total_steps": 1536, "loss": 0.0172, "lr": 2.6077979106226003e-09, "epoch": 2.97265625, "percentage": 99.09, "elapsed_time": "2:07:06", "remaining_time": "0:01:10"}
273
+ {"current_steps": 1523, "total_steps": 1536, "loss": 0.0128, "lr": 2.27170718987757e-09, "epoch": 2.974609375, "percentage": 99.15, "elapsed_time": "2:07:35", "remaining_time": "0:01:05"}
274
+ {"current_steps": 1524, "total_steps": 1536, "loss": 0.0115, "lr": 1.958788368583986e-09, "epoch": 2.9765625, "percentage": 99.22, "elapsed_time": "2:08:02", "remaining_time": "0:01:00"}
275
+ {"current_steps": 1525, "total_steps": 1536, "loss": 0.0195, "lr": 1.6690428975857375e-09, "epoch": 2.978515625, "percentage": 99.28, "elapsed_time": "2:08:30", "remaining_time": "0:00:55"}
276
+ {"current_steps": 1526, "total_steps": 1536, "loss": 0.0223, "lr": 1.4024721202832158e-09, "epoch": 2.98046875, "percentage": 99.35, "elapsed_time": "2:08:58", "remaining_time": "0:00:50"}
277
+ {"current_steps": 1527, "total_steps": 1536, "loss": 0.0186, "lr": 1.1590772726294274e-09, "epoch": 2.982421875, "percentage": 99.41, "elapsed_time": "2:09:26", "remaining_time": "0:00:45"}
278
+ {"current_steps": 1528, "total_steps": 1536, "loss": 0.0174, "lr": 9.388594831200026e-10, "epoch": 2.984375, "percentage": 99.48, "elapsed_time": "2:09:54", "remaining_time": "0:00:40"}
279
+ {"current_steps": 1529, "total_steps": 1536, "loss": 0.0233, "lr": 7.41819772792085e-10, "epoch": 2.986328125, "percentage": 99.54, "elapsed_time": "2:10:22", "remaining_time": "0:00:35"}
280
+ {"current_steps": 1530, "total_steps": 1536, "loss": 0.0187, "lr": 5.679590552182257e-10, "epoch": 2.98828125, "percentage": 99.61, "elapsed_time": "2:10:50", "remaining_time": "0:00:30"}
281
+ {"current_steps": 1531, "total_steps": 1536, "loss": 0.0145, "lr": 4.172781365008316e-10, "epoch": 2.990234375, "percentage": 99.67, "elapsed_time": "2:11:18", "remaining_time": "0:00:25"}
282
+ {"current_steps": 1532, "total_steps": 1536, "loss": 0.0141, "lr": 2.897777152699455e-10, "epoch": 2.9921875, "percentage": 99.74, "elapsed_time": "2:11:45", "remaining_time": "0:00:20"}
283
+ {"current_steps": 1533, "total_steps": 1536, "loss": 0.0185, "lr": 1.854583826793599e-10, "epoch": 2.994140625, "percentage": 99.8, "elapsed_time": "2:12:13", "remaining_time": "0:00:15"}
284
+ {"current_steps": 1534, "total_steps": 1536, "loss": 0.0087, "lr": 1.0432062240439688e-10, "epoch": 2.99609375, "percentage": 99.87, "elapsed_time": "2:12:41", "remaining_time": "0:00:10"}
285
+ {"current_steps": 1535, "total_steps": 1536, "loss": 0.0231, "lr": 4.636481063913234e-11, "epoch": 2.998046875, "percentage": 99.93, "elapsed_time": "2:13:09", "remaining_time": "0:00:05"}
286
+ {"current_steps": 1536, "total_steps": 1536, "loss": 0.0274, "lr": 1.1591216095285796e-11, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:13:36", "remaining_time": "0:00:00"}
287
+ {"current_steps": 1536, "total_steps": 1536, "eval_loss": 0.021319197490811348, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:15:31", "remaining_time": "0:00:00"}
288
+ {"current_steps": 1536, "total_steps": 1536, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:15:31", "remaining_time": "0:00:00"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6585eb14e08431e1e6a8aa4927ed212e81bc74de0b8b847119bfbf98a5d77612
3
  size 7800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c3e58fd9bd0ba8303ccae9171c8c03aef070a5d86db3d799c800a9b619cb77f
3
  size 7800