kahou1234 commited on
Commit
a3ee8c3
1 Parent(s): a3db2d0

Upload 11 files

Browse files
README.md CHANGED
@@ -44,7 +44,7 @@ The following hyperparameters were used during training:
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: cosine
46
  - lr_scheduler_warmup_ratio: 0.1
47
- - num_epochs: 45.0
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
@@ -55,6 +55,6 @@ The following hyperparameters were used during training:
55
 
56
  - PEFT 0.11.1
57
  - Transformers 4.41.2
58
- - Pytorch 2.3.1+cu121
59
  - Datasets 2.20.0
60
  - Tokenizers 0.19.1
 
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: cosine
46
  - lr_scheduler_warmup_ratio: 0.1
47
+ - num_epochs: 50.0
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
 
55
 
56
  - PEFT 0.11.1
57
  - Transformers 4.41.2
58
+ - Pytorch 2.2.1+cu121
59
  - Datasets 2.20.0
60
  - Tokenizers 0.19.1
adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "o_proj",
 
24
  "k_proj",
25
  "down_proj",
26
- "up_proj",
27
  "v_proj",
28
- "q_proj",
29
- "gate_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "up_proj",
24
  "o_proj",
25
+ "gate_proj",
26
  "k_proj",
27
  "down_proj",
 
28
  "v_proj",
29
+ "q_proj"
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd3e43b4e1c586304d1ab5aa130372b341b6ab5cd9f3b07c123c9202b8d59fe0
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f4b7393e56e2f0346f390598222852eb21d40dabdca7cd2a40f958dfb77a4dc
3
  size 83945296
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 45.0,
3
- "total_flos": 1851009220214784.0,
4
- "train_loss": 0.7845717103155847,
5
- "train_runtime": 154.7444,
6
- "train_samples_per_second": 2.326,
7
- "train_steps_per_second": 0.291
8
  }
 
1
  {
2
+ "epoch": 49.6,
3
+ "total_flos": 1.7939255986343117e+17,
4
+ "train_loss": 0.172668604437382,
5
+ "train_runtime": 11274.7291,
6
+ "train_samples_per_second": 2.217,
7
+ "train_steps_per_second": 0.275
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 45.0,
3
- "total_flos": 1851009220214784.0,
4
- "train_loss": 0.7845717103155847,
5
- "train_runtime": 154.7444,
6
- "train_samples_per_second": 2.326,
7
- "train_steps_per_second": 0.291
8
  }
 
1
  {
2
+ "epoch": 49.6,
3
+ "total_flos": 1.7939255986343117e+17,
4
+ "train_loss": 0.172668604437382,
5
+ "train_runtime": 11274.7291,
6
+ "train_samples_per_second": 2.217,
7
+ "train_steps_per_second": 0.275
8
  }
trainer_log.jsonl CHANGED
@@ -1,5 +1,156 @@
1
- {"current_steps": 10, "total_steps": 45, "loss": 3.453, "learning_rate": 4.9309248009941914e-05, "epoch": 10.0, "percentage": 22.22, "elapsed_time": "0:00:34", "remaining_time": "0:02:01", "throughput": "0.00", "total_tokens": 0}
2
- {"current_steps": 20, "total_steps": 45, "loss": 0.077, "learning_rate": 3.8062464117898724e-05, "epoch": 20.0, "percentage": 44.44, "elapsed_time": "0:01:10", "remaining_time": "0:01:27", "throughput": "0.00", "total_tokens": 0}
3
- {"current_steps": 30, "total_steps": 45, "loss": 0.0004, "learning_rate": 1.9163865903602374e-05, "epoch": 30.0, "percentage": 66.67, "elapsed_time": "0:01:43", "remaining_time": "0:00:51", "throughput": "0.00", "total_tokens": 0}
4
- {"current_steps": 40, "total_steps": 45, "loss": 0.0001, "learning_rate": 3.6839958911476957e-06, "epoch": 40.0, "percentage": 88.89, "elapsed_time": "0:02:17", "remaining_time": "0:00:17", "throughput": "0.00", "total_tokens": 0}
5
- {"current_steps": 45, "total_steps": 45, "epoch": 45.0, "percentage": 100.0, "elapsed_time": "0:02:34", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 20, "total_steps": 3100, "loss": 2.8022, "learning_rate": 3.064516129032258e-06, "epoch": 0.32, "percentage": 0.65, "elapsed_time": "0:01:15", "remaining_time": "3:13:27", "throughput": "0.00", "total_tokens": 0}
2
+ {"current_steps": 40, "total_steps": 3100, "loss": 2.6463, "learning_rate": 6.290322580645161e-06, "epoch": 0.64, "percentage": 1.29, "elapsed_time": "0:02:28", "remaining_time": "3:09:21", "throughput": "0.00", "total_tokens": 0}
3
+ {"current_steps": 60, "total_steps": 3100, "loss": 2.4026, "learning_rate": 9.516129032258064e-06, "epoch": 0.96, "percentage": 1.94, "elapsed_time": "0:03:42", "remaining_time": "3:07:38", "throughput": "0.00", "total_tokens": 0}
4
+ {"current_steps": 80, "total_steps": 3100, "loss": 1.9639, "learning_rate": 1.2741935483870968e-05, "epoch": 1.28, "percentage": 2.58, "elapsed_time": "0:04:54", "remaining_time": "3:05:17", "throughput": "0.00", "total_tokens": 0}
5
+ {"current_steps": 100, "total_steps": 3100, "loss": 1.7115, "learning_rate": 1.596774193548387e-05, "epoch": 1.6, "percentage": 3.23, "elapsed_time": "0:06:08", "remaining_time": "3:04:08", "throughput": "0.00", "total_tokens": 0}
6
+ {"current_steps": 120, "total_steps": 3100, "loss": 1.7534, "learning_rate": 1.9193548387096774e-05, "epoch": 1.92, "percentage": 3.87, "elapsed_time": "0:07:23", "remaining_time": "3:03:30", "throughput": "0.00", "total_tokens": 0}
7
+ {"current_steps": 140, "total_steps": 3100, "loss": 1.3422, "learning_rate": 2.2419354838709678e-05, "epoch": 2.24, "percentage": 4.52, "elapsed_time": "0:08:37", "remaining_time": "3:02:14", "throughput": "0.00", "total_tokens": 0}
8
+ {"current_steps": 160, "total_steps": 3100, "loss": 1.1582, "learning_rate": 2.5645161290322582e-05, "epoch": 2.56, "percentage": 5.16, "elapsed_time": "0:09:48", "remaining_time": "3:00:17", "throughput": "0.00", "total_tokens": 0}
9
+ {"current_steps": 180, "total_steps": 3100, "loss": 1.1084, "learning_rate": 2.8870967741935483e-05, "epoch": 2.88, "percentage": 5.81, "elapsed_time": "0:10:59", "remaining_time": "2:58:23", "throughput": "0.00", "total_tokens": 0}
10
+ {"current_steps": 200, "total_steps": 3100, "loss": 0.844, "learning_rate": 3.2096774193548393e-05, "epoch": 3.2, "percentage": 6.45, "elapsed_time": "0:12:12", "remaining_time": "2:56:57", "throughput": "0.00", "total_tokens": 0}
11
+ {"current_steps": 220, "total_steps": 3100, "loss": 0.6051, "learning_rate": 3.532258064516129e-05, "epoch": 3.52, "percentage": 7.1, "elapsed_time": "0:13:22", "remaining_time": "2:55:04", "throughput": "0.00", "total_tokens": 0}
12
+ {"current_steps": 240, "total_steps": 3100, "loss": 0.7587, "learning_rate": 3.8548387096774195e-05, "epoch": 3.84, "percentage": 7.74, "elapsed_time": "0:14:34", "remaining_time": "2:53:47", "throughput": "0.00", "total_tokens": 0}
13
+ {"current_steps": 260, "total_steps": 3100, "loss": 0.537, "learning_rate": 4.17741935483871e-05, "epoch": 4.16, "percentage": 8.39, "elapsed_time": "0:15:46", "remaining_time": "2:52:23", "throughput": "0.00", "total_tokens": 0}
14
+ {"current_steps": 280, "total_steps": 3100, "loss": 0.4063, "learning_rate": 4.5e-05, "epoch": 4.48, "percentage": 9.03, "elapsed_time": "0:16:59", "remaining_time": "2:51:12", "throughput": "0.00", "total_tokens": 0}
15
+ {"current_steps": 300, "total_steps": 3100, "loss": 0.4817, "learning_rate": 4.822580645161291e-05, "epoch": 4.8, "percentage": 9.68, "elapsed_time": "0:18:11", "remaining_time": "2:49:50", "throughput": "0.00", "total_tokens": 0}
16
+ {"current_steps": 320, "total_steps": 3100, "loss": 0.3556, "learning_rate": 4.9998716243505096e-05, "epoch": 5.12, "percentage": 10.32, "elapsed_time": "0:19:23", "remaining_time": "2:48:28", "throughput": "0.00", "total_tokens": 0}
17
+ {"current_steps": 340, "total_steps": 3100, "loss": 0.2663, "learning_rate": 4.9986672191133314e-05, "epoch": 5.44, "percentage": 10.97, "elapsed_time": "0:20:35", "remaining_time": "2:47:11", "throughput": "0.00", "total_tokens": 0}
18
+ {"current_steps": 360, "total_steps": 3100, "loss": 0.3273, "learning_rate": 4.9961956248762694e-05, "epoch": 5.76, "percentage": 11.61, "elapsed_time": "0:21:46", "remaining_time": "2:45:41", "throughput": "0.00", "total_tokens": 0}
19
+ {"current_steps": 380, "total_steps": 3100, "loss": 0.2174, "learning_rate": 4.992458095098368e-05, "epoch": 6.08, "percentage": 12.26, "elapsed_time": "0:22:57", "remaining_time": "2:44:20", "throughput": "0.00", "total_tokens": 0}
20
+ {"current_steps": 400, "total_steps": 3100, "loss": 0.1886, "learning_rate": 4.9874565252527765e-05, "epoch": 6.4, "percentage": 12.9, "elapsed_time": "0:24:11", "remaining_time": "2:43:20", "throughput": "0.00", "total_tokens": 0}
21
+ {"current_steps": 420, "total_steps": 3100, "loss": 0.2278, "learning_rate": 4.981193451865465e-05, "epoch": 6.72, "percentage": 13.55, "elapsed_time": "0:25:24", "remaining_time": "2:42:05", "throughput": "0.00", "total_tokens": 0}
22
+ {"current_steps": 440, "total_steps": 3100, "loss": 0.168, "learning_rate": 4.9736720512288334e-05, "epoch": 7.04, "percentage": 14.19, "elapsed_time": "0:26:37", "remaining_time": "2:40:54", "throughput": "0.00", "total_tokens": 0}
23
+ {"current_steps": 460, "total_steps": 3100, "loss": 0.1227, "learning_rate": 4.964896137790873e-05, "epoch": 7.36, "percentage": 14.84, "elapsed_time": "0:27:47", "remaining_time": "2:39:31", "throughput": "0.00", "total_tokens": 0}
24
+ {"current_steps": 480, "total_steps": 3100, "loss": 0.1261, "learning_rate": 4.954870162220679e-05, "epoch": 7.68, "percentage": 15.48, "elapsed_time": "0:28:59", "remaining_time": "2:38:15", "throughput": "0.00", "total_tokens": 0}
25
+ {"current_steps": 500, "total_steps": 3100, "loss": 0.1167, "learning_rate": 4.943599209151314e-05, "epoch": 8.0, "percentage": 16.13, "elapsed_time": "0:30:11", "remaining_time": "2:36:58", "throughput": "0.00", "total_tokens": 0}
26
+ {"current_steps": 520, "total_steps": 3100, "loss": 0.1049, "learning_rate": 4.931088994601157e-05, "epoch": 8.32, "percentage": 16.77, "elapsed_time": "0:31:20", "remaining_time": "2:35:32", "throughput": "0.00", "total_tokens": 0}
27
+ {"current_steps": 540, "total_steps": 3100, "loss": 0.1016, "learning_rate": 4.917345863075048e-05, "epoch": 8.64, "percentage": 17.42, "elapsed_time": "0:32:32", "remaining_time": "2:34:14", "throughput": "0.00", "total_tokens": 0}
28
+ {"current_steps": 560, "total_steps": 3100, "loss": 0.1157, "learning_rate": 4.902376784346697e-05, "epoch": 8.96, "percentage": 18.06, "elapsed_time": "0:33:48", "remaining_time": "2:33:19", "throughput": "0.00", "total_tokens": 0}
29
+ {"current_steps": 580, "total_steps": 3100, "loss": 0.073, "learning_rate": 4.886189349923992e-05, "epoch": 9.28, "percentage": 18.71, "elapsed_time": "0:35:01", "remaining_time": "2:32:11", "throughput": "0.00", "total_tokens": 0}
30
+ {"current_steps": 600, "total_steps": 3100, "loss": 0.0908, "learning_rate": 4.868791769198995e-05, "epoch": 9.6, "percentage": 19.35, "elapsed_time": "0:36:13", "remaining_time": "2:30:56", "throughput": "0.00", "total_tokens": 0}
31
+ {"current_steps": 620, "total_steps": 3100, "loss": 0.0557, "learning_rate": 4.8501928652845854e-05, "epoch": 9.92, "percentage": 20.0, "elapsed_time": "0:37:22", "remaining_time": "2:29:31", "throughput": "0.00", "total_tokens": 0}
32
+ {"current_steps": 640, "total_steps": 3100, "loss": 0.0779, "learning_rate": 4.83040207053985e-05, "epoch": 10.24, "percentage": 20.65, "elapsed_time": "0:38:33", "remaining_time": "2:28:12", "throughput": "0.00", "total_tokens": 0}
33
+ {"current_steps": 660, "total_steps": 3100, "loss": 0.048, "learning_rate": 4.809429421786502e-05, "epoch": 10.56, "percentage": 21.29, "elapsed_time": "0:39:43", "remaining_time": "2:26:52", "throughput": "0.00", "total_tokens": 0}
34
+ {"current_steps": 680, "total_steps": 3100, "loss": 0.0747, "learning_rate": 4.787285555218748e-05, "epoch": 10.88, "percentage": 21.94, "elapsed_time": "0:40:54", "remaining_time": "2:25:35", "throughput": "0.00", "total_tokens": 0}
35
+ {"current_steps": 700, "total_steps": 3100, "loss": 0.0629, "learning_rate": 4.763981701009184e-05, "epoch": 11.2, "percentage": 22.58, "elapsed_time": "0:42:06", "remaining_time": "2:24:20", "throughput": "0.00", "total_tokens": 0}
36
+ {"current_steps": 720, "total_steps": 3100, "loss": 0.051, "learning_rate": 4.739529677613456e-05, "epoch": 11.52, "percentage": 23.23, "elapsed_time": "0:43:21", "remaining_time": "2:23:18", "throughput": "0.00", "total_tokens": 0}
37
+ {"current_steps": 740, "total_steps": 3100, "loss": 0.0699, "learning_rate": 4.713941885776586e-05, "epoch": 11.84, "percentage": 23.87, "elapsed_time": "0:44:34", "remaining_time": "2:22:10", "throughput": "0.00", "total_tokens": 0}
38
+ {"current_steps": 760, "total_steps": 3100, "loss": 0.0526, "learning_rate": 4.687231302243975e-05, "epoch": 12.16, "percentage": 24.52, "elapsed_time": "0:45:46", "remaining_time": "2:20:54", "throughput": "0.00", "total_tokens": 0}
39
+ {"current_steps": 780, "total_steps": 3100, "loss": 0.0412, "learning_rate": 4.659411473180304e-05, "epoch": 12.48, "percentage": 25.16, "elapsed_time": "0:46:59", "remaining_time": "2:19:45", "throughput": "0.00", "total_tokens": 0}
40
+ {"current_steps": 800, "total_steps": 3100, "loss": 0.0495, "learning_rate": 4.6304965072996495e-05, "epoch": 12.8, "percentage": 25.81, "elapsed_time": "0:48:10", "remaining_time": "2:18:29", "throughput": "0.00", "total_tokens": 0}
41
+ {"current_steps": 820, "total_steps": 3100, "loss": 0.063, "learning_rate": 4.6005010687103076e-05, "epoch": 13.12, "percentage": 26.45, "elapsed_time": "0:49:22", "remaining_time": "2:17:17", "throughput": "0.00", "total_tokens": 0}
42
+ {"current_steps": 840, "total_steps": 3100, "loss": 0.0425, "learning_rate": 4.569440369477951e-05, "epoch": 13.44, "percentage": 27.1, "elapsed_time": "0:50:34", "remaining_time": "2:16:05", "throughput": "0.00", "total_tokens": 0}
43
+ {"current_steps": 860, "total_steps": 3100, "loss": 0.0451, "learning_rate": 4.5373301619108854e-05, "epoch": 13.76, "percentage": 27.74, "elapsed_time": "0:51:47", "remaining_time": "2:14:54", "throughput": "0.00", "total_tokens": 0}
44
+ {"current_steps": 880, "total_steps": 3100, "loss": 0.0445, "learning_rate": 4.5041867305713384e-05, "epoch": 14.08, "percentage": 28.39, "elapsed_time": "0:53:00", "remaining_time": "2:13:44", "throughput": "0.00", "total_tokens": 0}
45
+ {"current_steps": 900, "total_steps": 3100, "loss": 0.0214, "learning_rate": 4.4700268840168045e-05, "epoch": 14.4, "percentage": 29.03, "elapsed_time": "0:54:14", "remaining_time": "2:12:36", "throughput": "0.00", "total_tokens": 0}
46
+ {"current_steps": 920, "total_steps": 3100, "loss": 0.0552, "learning_rate": 4.4348679462756556e-05, "epoch": 14.72, "percentage": 29.68, "elapsed_time": "0:55:29", "remaining_time": "2:11:28", "throughput": "0.00", "total_tokens": 0}
47
+ {"current_steps": 940, "total_steps": 3100, "loss": 0.0524, "learning_rate": 4.398727748061324e-05, "epoch": 15.04, "percentage": 30.32, "elapsed_time": "0:56:42", "remaining_time": "2:10:19", "throughput": "0.00", "total_tokens": 0}
48
+ {"current_steps": 960, "total_steps": 3100, "loss": 0.0318, "learning_rate": 4.361624617729536e-05, "epoch": 15.36, "percentage": 30.97, "elapsed_time": "0:57:55", "remaining_time": "2:09:07", "throughput": "0.00", "total_tokens": 0}
49
+ {"current_steps": 980, "total_steps": 3100, "loss": 0.0347, "learning_rate": 4.323577371983155e-05, "epoch": 15.68, "percentage": 31.61, "elapsed_time": "0:59:10", "remaining_time": "2:08:01", "throughput": "0.00", "total_tokens": 0}
50
+ {"current_steps": 1000, "total_steps": 3100, "loss": 0.0541, "learning_rate": 4.28460530632937e-05, "epoch": 16.0, "percentage": 32.26, "elapsed_time": "1:00:25", "remaining_time": "2:06:53", "throughput": "0.00", "total_tokens": 0}
51
+ {"current_steps": 1020, "total_steps": 3100, "loss": 0.0327, "learning_rate": 4.2447281852940525e-05, "epoch": 16.32, "percentage": 32.9, "elapsed_time": "1:01:40", "remaining_time": "2:05:45", "throughput": "0.00", "total_tokens": 0}
52
+ {"current_steps": 1040, "total_steps": 3100, "loss": 0.0251, "learning_rate": 4.203966232398261e-05, "epoch": 16.64, "percentage": 33.55, "elapsed_time": "1:02:52", "remaining_time": "2:04:33", "throughput": "0.00", "total_tokens": 0}
53
+ {"current_steps": 1060, "total_steps": 3100, "loss": 0.0451, "learning_rate": 4.162340119901961e-05, "epoch": 16.96, "percentage": 34.19, "elapsed_time": "1:04:05", "remaining_time": "2:03:20", "throughput": "0.00", "total_tokens": 0}
54
+ {"current_steps": 1080, "total_steps": 3100, "loss": 0.0272, "learning_rate": 4.1198709583201754e-05, "epoch": 17.28, "percentage": 34.84, "elapsed_time": "1:05:16", "remaining_time": "2:02:05", "throughput": "0.00", "total_tokens": 0}
55
+ {"current_steps": 1100, "total_steps": 3100, "loss": 0.0517, "learning_rate": 4.0765802857168687e-05, "epoch": 17.6, "percentage": 35.48, "elapsed_time": "1:06:29", "remaining_time": "2:00:54", "throughput": "0.00", "total_tokens": 0}
56
+ {"current_steps": 1120, "total_steps": 3100, "loss": 0.0286, "learning_rate": 4.0324900567820046e-05, "epoch": 17.92, "percentage": 36.13, "elapsed_time": "1:07:45", "remaining_time": "1:59:46", "throughput": "0.00", "total_tokens": 0}
57
+ {"current_steps": 1140, "total_steps": 3100, "loss": 0.0258, "learning_rate": 3.987622631697316e-05, "epoch": 18.24, "percentage": 36.77, "elapsed_time": "1:08:59", "remaining_time": "1:58:37", "throughput": "0.00", "total_tokens": 0}
58
+ {"current_steps": 1160, "total_steps": 3100, "loss": 0.0289, "learning_rate": 3.942000764796427e-05, "epoch": 18.56, "percentage": 37.42, "elapsed_time": "1:10:14", "remaining_time": "1:57:29", "throughput": "0.00", "total_tokens": 0}
59
+ {"current_steps": 1180, "total_steps": 3100, "loss": 0.0457, "learning_rate": 3.895647593025088e-05, "epoch": 18.88, "percentage": 38.06, "elapsed_time": "1:11:29", "remaining_time": "1:56:19", "throughput": "0.00", "total_tokens": 0}
60
+ {"current_steps": 1200, "total_steps": 3100, "loss": 0.0316, "learning_rate": 3.8485866242073584e-05, "epoch": 19.2, "percentage": 38.71, "elapsed_time": "1:12:42", "remaining_time": "1:55:07", "throughput": "0.00", "total_tokens": 0}
61
+ {"current_steps": 1220, "total_steps": 3100, "loss": 0.0326, "learning_rate": 3.80084172512372e-05, "epoch": 19.52, "percentage": 39.35, "elapsed_time": "1:13:55", "remaining_time": "1:53:55", "throughput": "0.00", "total_tokens": 0}
62
+ {"current_steps": 1240, "total_steps": 3100, "loss": 0.0238, "learning_rate": 3.7524371094071266e-05, "epoch": 19.84, "percentage": 40.0, "elapsed_time": "1:15:07", "remaining_time": "1:52:41", "throughput": "0.00", "total_tokens": 0}
63
+ {"current_steps": 1260, "total_steps": 3100, "loss": 0.0286, "learning_rate": 3.703397325263162e-05, "epoch": 20.16, "percentage": 40.65, "elapsed_time": "1:16:19", "remaining_time": "1:51:27", "throughput": "0.00", "total_tokens": 0}
64
+ {"current_steps": 1280, "total_steps": 3100, "loss": 0.0294, "learning_rate": 3.653747243020515e-05, "epoch": 20.48, "percentage": 41.29, "elapsed_time": "1:17:32", "remaining_time": "1:50:15", "throughput": "0.00", "total_tokens": 0}
65
+ {"current_steps": 1300, "total_steps": 3100, "loss": 0.0364, "learning_rate": 3.603512042518093e-05, "epoch": 20.8, "percentage": 41.94, "elapsed_time": "1:18:45", "remaining_time": "1:49:02", "throughput": "0.00", "total_tokens": 0}
66
+ {"current_steps": 1320, "total_steps": 3100, "loss": 0.0265, "learning_rate": 3.552717200335171e-05, "epoch": 21.12, "percentage": 42.58, "elapsed_time": "1:19:57", "remaining_time": "1:47:49", "throughput": "0.00", "total_tokens": 0}
67
+ {"current_steps": 1340, "total_steps": 3100, "loss": 0.0319, "learning_rate": 3.501388476871039e-05, "epoch": 21.44, "percentage": 43.23, "elapsed_time": "1:21:08", "remaining_time": "1:46:34", "throughput": "0.00", "total_tokens": 0}
68
+ {"current_steps": 1360, "total_steps": 3100, "loss": 0.0137, "learning_rate": 3.449551903280729e-05, "epoch": 21.76, "percentage": 43.87, "elapsed_time": "1:22:19", "remaining_time": "1:45:19", "throughput": "0.00", "total_tokens": 0}
69
+ {"current_steps": 1380, "total_steps": 3100, "loss": 0.0416, "learning_rate": 3.397233768273415e-05, "epoch": 22.08, "percentage": 44.52, "elapsed_time": "1:23:30", "remaining_time": "1:44:05", "throughput": "0.00", "total_tokens": 0}
70
+ {"current_steps": 1400, "total_steps": 3100, "loss": 0.0179, "learning_rate": 3.344460604780202e-05, "epoch": 22.4, "percentage": 45.16, "elapsed_time": "1:24:42", "remaining_time": "1:42:51", "throughput": "0.00", "total_tokens": 0}
71
+ {"current_steps": 1420, "total_steps": 3100, "loss": 0.0276, "learning_rate": 3.291259176498052e-05, "epoch": 22.72, "percentage": 45.81, "elapsed_time": "1:25:52", "remaining_time": "1:41:35", "throughput": "0.00", "total_tokens": 0}
72
+ {"current_steps": 1440, "total_steps": 3100, "loss": 0.0352, "learning_rate": 3.237656464316693e-05, "epoch": 23.04, "percentage": 46.45, "elapsed_time": "1:27:01", "remaining_time": "1:40:19", "throughput": "0.00", "total_tokens": 0}
73
+ {"current_steps": 1460, "total_steps": 3100, "loss": 0.0212, "learning_rate": 3.183679652635357e-05, "epoch": 23.36, "percentage": 47.1, "elapsed_time": "1:28:11", "remaining_time": "1:39:04", "throughput": "0.00", "total_tokens": 0}
74
+ {"current_steps": 1480, "total_steps": 3100, "loss": 0.0338, "learning_rate": 3.129356115576332e-05, "epoch": 23.68, "percentage": 47.74, "elapsed_time": "1:29:24", "remaining_time": "1:37:51", "throughput": "0.00", "total_tokens": 0}
75
+ {"current_steps": 1500, "total_steps": 3100, "loss": 0.0295, "learning_rate": 3.074713403102284e-05, "epoch": 24.0, "percentage": 48.39, "elapsed_time": "1:30:35", "remaining_time": "1:36:38", "throughput": "0.00", "total_tokens": 0}
76
+ {"current_steps": 1520, "total_steps": 3100, "loss": 0.0185, "learning_rate": 3.0197792270443982e-05, "epoch": 24.32, "percentage": 49.03, "elapsed_time": "1:31:46", "remaining_time": "1:35:24", "throughput": "0.00", "total_tokens": 0}
77
+ {"current_steps": 1540, "total_steps": 3100, "loss": 0.0328, "learning_rate": 2.9645814470484452e-05, "epoch": 24.64, "percentage": 49.68, "elapsed_time": "1:32:59", "remaining_time": "1:34:11", "throughput": "0.00", "total_tokens": 0}
78
+ {"current_steps": 1560, "total_steps": 3100, "loss": 0.025, "learning_rate": 2.9091480564458666e-05, "epoch": 24.96, "percentage": 50.32, "elapsed_time": "1:34:12", "remaining_time": "1:32:59", "throughput": "0.00", "total_tokens": 0}
79
+ {"current_steps": 1580, "total_steps": 3100, "loss": 0.0294, "learning_rate": 2.8535071680570734e-05, "epoch": 25.28, "percentage": 50.97, "elapsed_time": "1:35:23", "remaining_time": "1:31:45", "throughput": "0.00", "total_tokens": 0}
80
+ {"current_steps": 1600, "total_steps": 3100, "loss": 0.0282, "learning_rate": 2.7976869999341426e-05, "epoch": 25.6, "percentage": 51.61, "elapsed_time": "1:36:38", "remaining_time": "1:30:35", "throughput": "0.00", "total_tokens": 0}
81
+ {"current_steps": 1620, "total_steps": 3100, "loss": 0.0294, "learning_rate": 2.741715861050143e-05, "epoch": 25.92, "percentage": 52.26, "elapsed_time": "1:37:51", "remaining_time": "1:29:23", "throughput": "0.00", "total_tokens": 0}
82
+ {"current_steps": 1640, "total_steps": 3100, "loss": 0.0354, "learning_rate": 2.685622136942359e-05, "epoch": 26.24, "percentage": 52.9, "elapsed_time": "1:39:04", "remaining_time": "1:28:11", "throughput": "0.00", "total_tokens": 0}
83
+ {"current_steps": 1660, "total_steps": 3100, "loss": 0.0162, "learning_rate": 2.629434275316673e-05, "epoch": 26.56, "percentage": 53.55, "elapsed_time": "1:40:19", "remaining_time": "1:27:01", "throughput": "0.00", "total_tokens": 0}
84
+ {"current_steps": 1680, "total_steps": 3100, "loss": 0.0205, "learning_rate": 2.573180771620432e-05, "epoch": 26.88, "percentage": 54.19, "elapsed_time": "1:41:32", "remaining_time": "1:25:49", "throughput": "0.00", "total_tokens": 0}
85
+ {"current_steps": 1700, "total_steps": 3100, "loss": 0.0129, "learning_rate": 2.516890154591095e-05, "epoch": 27.2, "percentage": 54.84, "elapsed_time": "1:42:47", "remaining_time": "1:24:39", "throughput": "0.00", "total_tokens": 0}
86
+ {"current_steps": 1720, "total_steps": 3100, "loss": 0.0333, "learning_rate": 2.4605909717879964e-05, "epoch": 27.52, "percentage": 55.48, "elapsed_time": "1:44:01", "remaining_time": "1:23:27", "throughput": "0.00", "total_tokens": 0}
87
+ {"current_steps": 1740, "total_steps": 3100, "loss": 0.0261, "learning_rate": 2.4043117751145694e-05, "epoch": 27.84, "percentage": 56.13, "elapsed_time": "1:45:14", "remaining_time": "1:22:15", "throughput": "0.00", "total_tokens": 0}
88
+ {"current_steps": 1760, "total_steps": 3100, "loss": 0.0418, "learning_rate": 2.34808110633836e-05, "epoch": 28.16, "percentage": 56.77, "elapsed_time": "1:46:27", "remaining_time": "1:21:03", "throughput": "0.00", "total_tokens": 0}
89
+ {"current_steps": 1780, "total_steps": 3100, "loss": 0.0111, "learning_rate": 2.291927482616191e-05, "epoch": 28.48, "percentage": 57.42, "elapsed_time": "1:47:39", "remaining_time": "1:19:50", "throughput": "0.00", "total_tokens": 0}
90
+ {"current_steps": 1800, "total_steps": 3100, "loss": 0.0263, "learning_rate": 2.235879382031794e-05, "epoch": 28.8, "percentage": 58.06, "elapsed_time": "1:48:52", "remaining_time": "1:18:38", "throughput": "0.00", "total_tokens": 0}
91
+ {"current_steps": 1820, "total_steps": 3100, "loss": 0.0299, "learning_rate": 2.179965229153265e-05, "epoch": 29.12, "percentage": 58.71, "elapsed_time": "1:50:05", "remaining_time": "1:17:25", "throughput": "0.00", "total_tokens": 0}
92
+ {"current_steps": 1840, "total_steps": 3100, "loss": 0.0267, "learning_rate": 2.1242133806176667e-05, "epoch": 29.44, "percentage": 59.35, "elapsed_time": "1:51:16", "remaining_time": "1:16:12", "throughput": "0.00", "total_tokens": 0}
93
+ {"current_steps": 1860, "total_steps": 3100, "loss": 0.0204, "learning_rate": 2.0686521107500638e-05, "epoch": 29.76, "percentage": 60.0, "elapsed_time": "1:52:29", "remaining_time": "1:14:59", "throughput": "0.00", "total_tokens": 0}
94
+ {"current_steps": 1880, "total_steps": 3100, "loss": 0.0308, "learning_rate": 2.0133095972243233e-05, "epoch": 30.08, "percentage": 60.65, "elapsed_time": "1:53:42", "remaining_time": "1:13:47", "throughput": "0.00", "total_tokens": 0}
95
+ {"current_steps": 1900, "total_steps": 3100, "loss": 0.024, "learning_rate": 1.9582139067729117e-05, "epoch": 30.4, "percentage": 61.29, "elapsed_time": "1:54:52", "remaining_time": "1:12:33", "throughput": "0.00", "total_tokens": 0}
96
+ {"current_steps": 1920, "total_steps": 3100, "loss": 0.0113, "learning_rate": 1.90339298095297e-05, "epoch": 30.72, "percentage": 61.94, "elapsed_time": "1:56:03", "remaining_time": "1:11:19", "throughput": "0.00", "total_tokens": 0}
97
+ {"current_steps": 1940, "total_steps": 3100, "loss": 0.0301, "learning_rate": 1.8488746219758674e-05, "epoch": 31.04, "percentage": 62.58, "elapsed_time": "1:57:14", "remaining_time": "1:10:06", "throughput": "0.00", "total_tokens": 0}
98
+ {"current_steps": 1960, "total_steps": 3100, "loss": 0.0293, "learning_rate": 1.7946864786074165e-05, "epoch": 31.36, "percentage": 63.23, "elapsed_time": "1:58:26", "remaining_time": "1:08:53", "throughput": "0.00", "total_tokens": 0}
99
+ {"current_steps": 1980, "total_steps": 3100, "loss": 0.0242, "learning_rate": 1.740856032145917e-05, "epoch": 31.68, "percentage": 63.87, "elapsed_time": "1:59:35", "remaining_time": "1:07:39", "throughput": "0.00", "total_tokens": 0}
100
+ {"current_steps": 2000, "total_steps": 3100, "loss": 0.022, "learning_rate": 1.6874105824851267e-05, "epoch": 32.0, "percentage": 64.52, "elapsed_time": "2:00:48", "remaining_time": "1:06:26", "throughput": "0.00", "total_tokens": 0}
101
+ {"current_steps": 2020, "total_steps": 3100, "loss": 0.0264, "learning_rate": 1.634377234269226e-05, "epoch": 32.32, "percentage": 65.16, "elapsed_time": "2:02:02", "remaining_time": "1:05:15", "throughput": "0.00", "total_tokens": 0}
102
+ {"current_steps": 2040, "total_steps": 3100, "loss": 0.0155, "learning_rate": 1.5817828831468144e-05, "epoch": 32.64, "percentage": 65.81, "elapsed_time": "2:03:17", "remaining_time": "1:04:03", "throughput": "0.00", "total_tokens": 0}
103
+ {"current_steps": 2060, "total_steps": 3100, "loss": 0.0208, "learning_rate": 1.5296542021308825e-05, "epoch": 32.96, "percentage": 66.45, "elapsed_time": "2:04:32", "remaining_time": "1:02:52", "throughput": "0.00", "total_tokens": 0}
104
+ {"current_steps": 2080, "total_steps": 3100, "loss": 0.0264, "learning_rate": 1.478017628071706e-05, "epoch": 33.28, "percentage": 67.1, "elapsed_time": "2:05:48", "remaining_time": "1:01:41", "throughput": "0.00", "total_tokens": 0}
105
+ {"current_steps": 2100, "total_steps": 3100, "loss": 0.0174, "learning_rate": 1.4268993482495055e-05, "epoch": 33.6, "percentage": 67.74, "elapsed_time": "2:07:02", "remaining_time": "1:00:29", "throughput": "0.00", "total_tokens": 0}
106
+ {"current_steps": 2120, "total_steps": 3100, "loss": 0.0214, "learning_rate": 1.3763252870936649e-05, "epoch": 33.92, "percentage": 68.39, "elapsed_time": "2:08:20", "remaining_time": "0:59:19", "throughput": "0.00", "total_tokens": 0}
107
+ {"current_steps": 2140, "total_steps": 3100, "loss": 0.0306, "learning_rate": 1.3263210930352737e-05, "epoch": 34.24, "percentage": 69.03, "elapsed_time": "2:09:32", "remaining_time": "0:58:06", "throughput": "0.00", "total_tokens": 0}
108
+ {"current_steps": 2160, "total_steps": 3100, "loss": 0.0146, "learning_rate": 1.2769121254996159e-05, "epoch": 34.56, "percentage": 69.68, "elapsed_time": "2:10:44", "remaining_time": "0:56:54", "throughput": "0.00", "total_tokens": 0}
109
+ {"current_steps": 2180, "total_steps": 3100, "loss": 0.0254, "learning_rate": 1.228123442045249e-05, "epoch": 34.88, "percentage": 70.32, "elapsed_time": "2:12:00", "remaining_time": "0:55:42", "throughput": "0.00", "total_tokens": 0}
110
+ {"current_steps": 2200, "total_steps": 3100, "loss": 0.0176, "learning_rate": 1.1799797856561606e-05, "epoch": 35.2, "percentage": 70.97, "elapsed_time": "2:13:13", "remaining_time": "0:54:30", "throughput": "0.00", "total_tokens": 0}
111
+ {"current_steps": 2220, "total_steps": 3100, "loss": 0.0205, "learning_rate": 1.1325055721934637e-05, "epoch": 35.52, "percentage": 71.61, "elapsed_time": "2:14:27", "remaining_time": "0:53:17", "throughput": "0.00", "total_tokens": 0}
112
+ {"current_steps": 2240, "total_steps": 3100, "loss": 0.0153, "learning_rate": 1.0857248780129928e-05, "epoch": 35.84, "percentage": 72.26, "elapsed_time": "2:15:41", "remaining_time": "0:52:05", "throughput": "0.00", "total_tokens": 0}
113
+ {"current_steps": 2260, "total_steps": 3100, "loss": 0.0251, "learning_rate": 1.0396614277550752e-05, "epoch": 36.16, "percentage": 72.9, "elapsed_time": "2:16:56", "remaining_time": "0:50:53", "throughput": "0.00", "total_tokens": 0}
114
+ {"current_steps": 2280, "total_steps": 3100, "loss": 0.0224, "learning_rate": 9.943385823126775e-06, "epoch": 36.48, "percentage": 73.55, "elapsed_time": "2:18:09", "remaining_time": "0:49:41", "throughput": "0.00", "total_tokens": 0}
115
+ {"current_steps": 2300, "total_steps": 3100, "loss": 0.0219, "learning_rate": 9.497793269840211e-06, "epoch": 36.8, "percentage": 74.19, "elapsed_time": "2:19:24", "remaining_time": "0:48:29", "throughput": "0.00", "total_tokens": 0}
116
+ {"current_steps": 2320, "total_steps": 3100, "loss": 0.021, "learning_rate": 9.06006259815683e-06, "epoch": 37.12, "percentage": 74.84, "elapsed_time": "2:20:38", "remaining_time": "0:47:17", "throughput": "0.00", "total_tokens": 0}
117
+ {"current_steps": 2340, "total_steps": 3100, "loss": 0.0236, "learning_rate": 8.630415801420835e-06, "epoch": 37.44, "percentage": 75.48, "elapsed_time": "2:21:52", "remaining_time": "0:46:04", "throughput": "0.00", "total_tokens": 0}
118
+ {"current_steps": 2360, "total_steps": 3100, "loss": 0.0216, "learning_rate": 8.209070773271894e-06, "epoch": 37.76, "percentage": 76.13, "elapsed_time": "2:23:05", "remaining_time": "0:44:52", "throughput": "0.00", "total_tokens": 0}
119
+ {"current_steps": 2380, "total_steps": 3100, "loss": 0.0268, "learning_rate": 7.79624119714121e-06, "epoch": 38.08, "percentage": 76.77, "elapsed_time": "2:24:15", "remaining_time": "0:43:38", "throughput": "0.00", "total_tokens": 0}
120
+ {"current_steps": 2400, "total_steps": 3100, "loss": 0.0306, "learning_rate": 7.392136437882855e-06, "epoch": 38.4, "percentage": 77.42, "elapsed_time": "2:25:28", "remaining_time": "0:42:25", "throughput": "0.00", "total_tokens": 0}
121
+ {"current_steps": 2420, "total_steps": 3100, "loss": 0.0224, "learning_rate": 6.996961435595223e-06, "epoch": 38.72, "percentage": 78.06, "elapsed_time": "2:26:44", "remaining_time": "0:41:13", "throughput": "0.00", "total_tokens": 0}
122
+ {"current_steps": 2440, "total_steps": 3100, "loss": 0.0138, "learning_rate": 6.610916601686481e-06, "epoch": 39.04, "percentage": 78.71, "elapsed_time": "2:27:57", "remaining_time": "0:40:01", "throughput": "0.00", "total_tokens": 0}
123
+ {"current_steps": 2460, "total_steps": 3100, "loss": 0.0234, "learning_rate": 6.234197717236742e-06, "epoch": 39.36, "percentage": 79.35, "elapsed_time": "2:29:10", "remaining_time": "0:38:48", "throughput": "0.00", "total_tokens": 0}
124
+ {"current_steps": 2480, "total_steps": 3100, "loss": 0.0164, "learning_rate": 5.866995833708464e-06, "epoch": 39.68, "percentage": 80.0, "elapsed_time": "2:30:25", "remaining_time": "0:37:36", "throughput": "0.00", "total_tokens": 0}
125
+ {"current_steps": 2500, "total_steps": 3100, "loss": 0.0169, "learning_rate": 5.509497176055492e-06, "epoch": 40.0, "percentage": 80.65, "elapsed_time": "2:31:36", "remaining_time": "0:36:23", "throughput": "0.00", "total_tokens": 0}
126
+ {"current_steps": 2520, "total_steps": 3100, "loss": 0.0116, "learning_rate": 5.161883048279817e-06, "epoch": 40.32, "percentage": 81.29, "elapsed_time": "2:32:48", "remaining_time": "0:35:10", "throughput": "0.00", "total_tokens": 0}
127
+ {"current_steps": 2540, "total_steps": 3100, "loss": 0.0219, "learning_rate": 4.824329741483949e-06, "epoch": 40.64, "percentage": 81.94, "elapsed_time": "2:33:57", "remaining_time": "0:33:56", "throughput": "0.00", "total_tokens": 0}
128
+ {"current_steps": 2560, "total_steps": 3100, "loss": 0.0366, "learning_rate": 4.497008444465681e-06, "epoch": 40.96, "percentage": 82.58, "elapsed_time": "2:35:09", "remaining_time": "0:32:43", "throughput": "0.00", "total_tokens": 0}
129
+ {"current_steps": 2580, "total_steps": 3100, "loss": 0.0228, "learning_rate": 4.180085156900274e-06, "epoch": 41.28, "percentage": 83.23, "elapsed_time": "2:36:21", "remaining_time": "0:31:30", "throughput": "0.00", "total_tokens": 0}
130
+ {"current_steps": 2600, "total_steps": 3100, "loss": 0.0135, "learning_rate": 3.873720605154468e-06, "epoch": 41.6, "percentage": 83.87, "elapsed_time": "2:37:34", "remaining_time": "0:30:18", "throughput": "0.00", "total_tokens": 0}
131
+ {"current_steps": 2620, "total_steps": 3100, "loss": 0.0267, "learning_rate": 3.578070160774724e-06, "epoch": 41.92, "percentage": 84.52, "elapsed_time": "2:38:46", "remaining_time": "0:29:05", "throughput": "0.00", "total_tokens": 0}
132
+ {"current_steps": 2640, "total_steps": 3100, "loss": 0.0218, "learning_rate": 3.293283761691182e-06, "epoch": 42.24, "percentage": 85.16, "elapsed_time": "2:40:00", "remaining_time": "0:27:52", "throughput": "0.00", "total_tokens": 0}
133
+ {"current_steps": 2660, "total_steps": 3100, "loss": 0.0315, "learning_rate": 3.0195058361772277e-06, "epoch": 42.56, "percentage": 85.81, "elapsed_time": "2:41:16", "remaining_time": "0:26:40", "throughput": "0.00", "total_tokens": 0}
134
+ {"current_steps": 2680, "total_steps": 3100, "loss": 0.022, "learning_rate": 2.756875229603295e-06, "epoch": 42.88, "percentage": 86.45, "elapsed_time": "2:42:28", "remaining_time": "0:25:27", "throughput": "0.00", "total_tokens": 0}
135
+ {"current_steps": 2700, "total_steps": 3100, "loss": 0.016, "learning_rate": 2.5055251340219855e-06, "epoch": 43.2, "percentage": 87.1, "elapsed_time": "2:43:40", "remaining_time": "0:24:14", "throughput": "0.00", "total_tokens": 0}
136
+ {"current_steps": 2720, "total_steps": 3100, "loss": 0.0267, "learning_rate": 2.2655830206202655e-06, "epoch": 43.52, "percentage": 87.74, "elapsed_time": "2:44:52", "remaining_time": "0:23:01", "throughput": "0.00", "total_tokens": 0}
137
+ {"current_steps": 2740, "total_steps": 3100, "loss": 0.0167, "learning_rate": 2.037170575072944e-06, "epoch": 43.84, "percentage": 88.39, "elapsed_time": "2:46:03", "remaining_time": "0:21:49", "throughput": "0.00", "total_tokens": 0}
138
+ {"current_steps": 2760, "total_steps": 3100, "loss": 0.0492, "learning_rate": 1.8204036358303173e-06, "epoch": 44.16, "percentage": 89.03, "elapsed_time": "2:47:16", "remaining_time": "0:20:36", "throughput": "0.00", "total_tokens": 0}
139
+ {"current_steps": 2780, "total_steps": 3100, "loss": 0.0254, "learning_rate": 1.615392135371116e-06, "epoch": 44.48, "percentage": 89.68, "elapsed_time": "2:48:27", "remaining_time": "0:19:23", "throughput": "0.00", "total_tokens": 0}
140
+ {"current_steps": 2800, "total_steps": 3100, "loss": 0.0136, "learning_rate": 1.4222400444507318e-06, "epoch": 44.8, "percentage": 90.32, "elapsed_time": "2:49:38", "remaining_time": "0:18:10", "throughput": "0.00", "total_tokens": 0}
141
+ {"current_steps": 2820, "total_steps": 3100, "loss": 0.0116, "learning_rate": 1.2410453193728493e-06, "epoch": 45.12, "percentage": 90.97, "elapsed_time": "2:50:51", "remaining_time": "0:16:57", "throughput": "0.00", "total_tokens": 0}
142
+ {"current_steps": 2840, "total_steps": 3100, "loss": 0.0311, "learning_rate": 1.0718998523113004e-06, "epoch": 45.44, "percentage": 91.61, "elapsed_time": "2:52:02", "remaining_time": "0:15:45", "throughput": "0.00", "total_tokens": 0}
143
+ {"current_steps": 2860, "total_steps": 3100, "loss": 0.0283, "learning_rate": 9.148894247073298e-07, "epoch": 45.76, "percentage": 92.26, "elapsed_time": "2:53:15", "remaining_time": "0:14:32", "throughput": "0.00", "total_tokens": 0}
144
+ {"current_steps": 2880, "total_steps": 3100, "loss": 0.0186, "learning_rate": 7.700936637658779e-07, "epoch": 46.08, "percentage": 92.9, "elapsed_time": "2:54:29", "remaining_time": "0:13:19", "throughput": "0.00", "total_tokens": 0}
145
+ {"current_steps": 2900, "total_steps": 3100, "loss": 0.0229, "learning_rate": 6.375860020729541e-07, "epoch": 46.4, "percentage": 93.55, "elapsed_time": "2:55:42", "remaining_time": "0:12:07", "throughput": "0.00", "total_tokens": 0}
146
+ {"current_steps": 2920, "total_steps": 3100, "loss": 0.0268, "learning_rate": 5.174336403546226e-07, "epoch": 46.72, "percentage": 94.19, "elapsed_time": "2:56:56", "remaining_time": "0:10:54", "throughput": "0.00", "total_tokens": 0}
147
+ {"current_steps": 2940, "total_steps": 3100, "loss": 0.0161, "learning_rate": 4.096975133963954e-07, "epoch": 47.04, "percentage": 94.84, "elapsed_time": "2:58:07", "remaining_time": "0:09:41", "throughput": "0.00", "total_tokens": 0}
148
+ {"current_steps": 2960, "total_steps": 3100, "loss": 0.0113, "learning_rate": 3.144322591404292e-07, "epoch": 47.36, "percentage": 95.48, "elapsed_time": "2:59:19", "remaining_time": "0:08:28", "throughput": "0.00", "total_tokens": 0}
149
+ {"current_steps": 2980, "total_steps": 3100, "loss": 0.0222, "learning_rate": 2.316861909760909e-07, "epoch": 47.68, "percentage": 96.13, "elapsed_time": "3:00:30", "remaining_time": "0:07:16", "throughput": "0.00", "total_tokens": 0}
150
+ {"current_steps": 3000, "total_steps": 3100, "loss": 0.028, "learning_rate": 1.6150127323803222e-07, "epoch": 48.0, "percentage": 96.77, "elapsed_time": "3:01:48", "remaining_time": "0:06:03", "throughput": "0.00", "total_tokens": 0}
151
+ {"current_steps": 3020, "total_steps": 3100, "loss": 0.0217, "learning_rate": 1.0391309992413833e-07, "epoch": 48.32, "percentage": 97.42, "elapsed_time": "3:03:02", "remaining_time": "0:04:50", "throughput": "0.00", "total_tokens": 0}
152
+ {"current_steps": 3040, "total_steps": 3100, "loss": 0.0191, "learning_rate": 5.895087664417876e-08, "epoch": 48.64, "percentage": 98.06, "elapsed_time": "3:04:13", "remaining_time": "0:03:38", "throughput": "0.00", "total_tokens": 0}
153
+ {"current_steps": 3060, "total_steps": 3100, "loss": 0.0162, "learning_rate": 2.6637405808302428e-08, "epoch": 48.96, "percentage": 98.71, "elapsed_time": "3:05:27", "remaining_time": "0:02:25", "throughput": "0.00", "total_tokens": 0}
154
+ {"current_steps": 3080, "total_steps": 3100, "loss": 0.0146, "learning_rate": 6.989075062879824e-09, "epoch": 49.28, "percentage": 99.35, "elapsed_time": "3:06:41", "remaining_time": "0:01:12", "throughput": "0.00", "total_tokens": 0}
155
+ {"current_steps": 3100, "total_steps": 3100, "loss": 0.0217, "learning_rate": 1.584897958428755e-11, "epoch": 49.6, "percentage": 100.0, "elapsed_time": "3:07:54", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}
156
+ {"current_steps": 3100, "total_steps": 3100, "epoch": 49.6, "percentage": 100.0, "elapsed_time": "3:07:54", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}
trainer_state.json CHANGED
@@ -1,55 +1,1112 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 45.0,
5
  "eval_steps": 500,
6
- "global_step": 45,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 10.0,
13
- "grad_norm": 1.8389599323272705,
14
- "learning_rate": 4.9309248009941914e-05,
15
- "loss": 3.453,
16
- "step": 10
17
  },
18
  {
19
- "epoch": 20.0,
20
- "grad_norm": 0.037354476749897,
21
- "learning_rate": 3.8062464117898724e-05,
22
- "loss": 0.077,
23
- "step": 20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
24
  },
25
  {
26
- "epoch": 30.0,
27
- "grad_norm": 0.00799699779599905,
28
- "learning_rate": 1.9163865903602374e-05,
29
- "loss": 0.0004,
30
- "step": 30
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31
  },
32
  {
33
  "epoch": 40.0,
34
- "grad_norm": 0.003759935265406966,
35
- "learning_rate": 3.6839958911476957e-06,
36
- "loss": 0.0001,
37
- "step": 40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
38
  },
39
  {
40
- "epoch": 45.0,
41
- "step": 45,
42
- "total_flos": 1851009220214784.0,
43
- "train_loss": 0.7845717103155847,
44
- "train_runtime": 154.7444,
45
- "train_samples_per_second": 2.326,
46
- "train_steps_per_second": 0.291
47
  }
48
  ],
49
- "logging_steps": 10,
50
- "max_steps": 45,
51
  "num_input_tokens_seen": 0,
52
- "num_train_epochs": 45,
53
  "save_steps": 1000,
54
  "stateful_callbacks": {
55
  "TrainerControl": {
@@ -57,13 +1114,13 @@
57
  "should_epoch_stop": false,
58
  "should_evaluate": false,
59
  "should_log": false,
60
- "should_save": false,
61
  "should_training_stop": false
62
  },
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 1851009220214784.0,
67
  "train_batch_size": 2,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 49.6,
5
  "eval_steps": 500,
6
+ "global_step": 3100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.32,
13
+ "grad_norm": 2.214611053466797,
14
+ "learning_rate": 3.064516129032258e-06,
15
+ "loss": 2.8022,
16
+ "step": 20
17
  },
18
  {
19
+ "epoch": 0.64,
20
+ "grad_norm": 0.9293187260627747,
21
+ "learning_rate": 6.290322580645161e-06,
22
+ "loss": 2.6463,
23
+ "step": 40
24
+ },
25
+ {
26
+ "epoch": 0.96,
27
+ "grad_norm": 2.630194902420044,
28
+ "learning_rate": 9.516129032258064e-06,
29
+ "loss": 2.4026,
30
+ "step": 60
31
+ },
32
+ {
33
+ "epoch": 1.28,
34
+ "grad_norm": 1.7517138719558716,
35
+ "learning_rate": 1.2741935483870968e-05,
36
+ "loss": 1.9639,
37
+ "step": 80
38
+ },
39
+ {
40
+ "epoch": 1.6,
41
+ "grad_norm": 1.6100302934646606,
42
+ "learning_rate": 1.596774193548387e-05,
43
+ "loss": 1.7115,
44
+ "step": 100
45
+ },
46
+ {
47
+ "epoch": 1.92,
48
+ "grad_norm": 3.468630790710449,
49
+ "learning_rate": 1.9193548387096774e-05,
50
+ "loss": 1.7534,
51
+ "step": 120
52
+ },
53
+ {
54
+ "epoch": 2.24,
55
+ "grad_norm": 2.6692144870758057,
56
+ "learning_rate": 2.2419354838709678e-05,
57
+ "loss": 1.3422,
58
+ "step": 140
59
+ },
60
+ {
61
+ "epoch": 2.56,
62
+ "grad_norm": 1.5186293125152588,
63
+ "learning_rate": 2.5645161290322582e-05,
64
+ "loss": 1.1582,
65
+ "step": 160
66
+ },
67
+ {
68
+ "epoch": 2.88,
69
+ "grad_norm": 4.727887153625488,
70
+ "learning_rate": 2.8870967741935483e-05,
71
+ "loss": 1.1084,
72
+ "step": 180
73
+ },
74
+ {
75
+ "epoch": 3.2,
76
+ "grad_norm": 2.800290107727051,
77
+ "learning_rate": 3.2096774193548393e-05,
78
+ "loss": 0.844,
79
+ "step": 200
80
+ },
81
+ {
82
+ "epoch": 3.52,
83
+ "grad_norm": 1.1538563966751099,
84
+ "learning_rate": 3.532258064516129e-05,
85
+ "loss": 0.6051,
86
+ "step": 220
87
+ },
88
+ {
89
+ "epoch": 3.84,
90
+ "grad_norm": 3.282315492630005,
91
+ "learning_rate": 3.8548387096774195e-05,
92
+ "loss": 0.7587,
93
+ "step": 240
94
+ },
95
+ {
96
+ "epoch": 4.16,
97
+ "grad_norm": 0.9393389821052551,
98
+ "learning_rate": 4.17741935483871e-05,
99
+ "loss": 0.537,
100
+ "step": 260
101
+ },
102
+ {
103
+ "epoch": 4.48,
104
+ "grad_norm": 1.5951660871505737,
105
+ "learning_rate": 4.5e-05,
106
+ "loss": 0.4063,
107
+ "step": 280
108
+ },
109
+ {
110
+ "epoch": 4.8,
111
+ "grad_norm": 2.4143407344818115,
112
+ "learning_rate": 4.822580645161291e-05,
113
+ "loss": 0.4817,
114
+ "step": 300
115
+ },
116
+ {
117
+ "epoch": 5.12,
118
+ "grad_norm": 1.1503572463989258,
119
+ "learning_rate": 4.9998716243505096e-05,
120
+ "loss": 0.3556,
121
+ "step": 320
122
+ },
123
+ {
124
+ "epoch": 5.44,
125
+ "grad_norm": 1.5514352321624756,
126
+ "learning_rate": 4.9986672191133314e-05,
127
+ "loss": 0.2663,
128
+ "step": 340
129
+ },
130
+ {
131
+ "epoch": 5.76,
132
+ "grad_norm": 2.0045723915100098,
133
+ "learning_rate": 4.9961956248762694e-05,
134
+ "loss": 0.3273,
135
+ "step": 360
136
+ },
137
+ {
138
+ "epoch": 6.08,
139
+ "grad_norm": 0.716200053691864,
140
+ "learning_rate": 4.992458095098368e-05,
141
+ "loss": 0.2174,
142
+ "step": 380
143
+ },
144
+ {
145
+ "epoch": 6.4,
146
+ "grad_norm": 3.2870705127716064,
147
+ "learning_rate": 4.9874565252527765e-05,
148
+ "loss": 0.1886,
149
+ "step": 400
150
+ },
151
+ {
152
+ "epoch": 6.72,
153
+ "grad_norm": 2.3181071281433105,
154
+ "learning_rate": 4.981193451865465e-05,
155
+ "loss": 0.2278,
156
+ "step": 420
157
+ },
158
+ {
159
+ "epoch": 7.04,
160
+ "grad_norm": 1.6296441555023193,
161
+ "learning_rate": 4.9736720512288334e-05,
162
+ "loss": 0.168,
163
+ "step": 440
164
+ },
165
+ {
166
+ "epoch": 7.36,
167
+ "grad_norm": 1.757379174232483,
168
+ "learning_rate": 4.964896137790873e-05,
169
+ "loss": 0.1227,
170
+ "step": 460
171
+ },
172
+ {
173
+ "epoch": 7.68,
174
+ "grad_norm": 1.2622524499893188,
175
+ "learning_rate": 4.954870162220679e-05,
176
+ "loss": 0.1261,
177
+ "step": 480
178
+ },
179
+ {
180
+ "epoch": 8.0,
181
+ "grad_norm": 1.1865277290344238,
182
+ "learning_rate": 4.943599209151314e-05,
183
+ "loss": 0.1167,
184
+ "step": 500
185
+ },
186
+ {
187
+ "epoch": 8.32,
188
+ "grad_norm": 1.244333028793335,
189
+ "learning_rate": 4.931088994601157e-05,
190
+ "loss": 0.1049,
191
+ "step": 520
192
+ },
193
+ {
194
+ "epoch": 8.64,
195
+ "grad_norm": 2.6851558685302734,
196
+ "learning_rate": 4.917345863075048e-05,
197
+ "loss": 0.1016,
198
+ "step": 540
199
+ },
200
+ {
201
+ "epoch": 8.96,
202
+ "grad_norm": 1.0457267761230469,
203
+ "learning_rate": 4.902376784346697e-05,
204
+ "loss": 0.1157,
205
+ "step": 560
206
+ },
207
+ {
208
+ "epoch": 9.28,
209
+ "grad_norm": 0.2963043749332428,
210
+ "learning_rate": 4.886189349923992e-05,
211
+ "loss": 0.073,
212
+ "step": 580
213
+ },
214
+ {
215
+ "epoch": 9.6,
216
+ "grad_norm": 0.45336633920669556,
217
+ "learning_rate": 4.868791769198995e-05,
218
+ "loss": 0.0908,
219
+ "step": 600
220
+ },
221
+ {
222
+ "epoch": 9.92,
223
+ "grad_norm": 1.0918829441070557,
224
+ "learning_rate": 4.8501928652845854e-05,
225
+ "loss": 0.0557,
226
+ "step": 620
227
+ },
228
+ {
229
+ "epoch": 10.24,
230
+ "grad_norm": 2.7920358180999756,
231
+ "learning_rate": 4.83040207053985e-05,
232
+ "loss": 0.0779,
233
+ "step": 640
234
+ },
235
+ {
236
+ "epoch": 10.56,
237
+ "grad_norm": 0.8492644429206848,
238
+ "learning_rate": 4.809429421786502e-05,
239
+ "loss": 0.048,
240
+ "step": 660
241
+ },
242
+ {
243
+ "epoch": 10.88,
244
+ "grad_norm": 0.6128495335578918,
245
+ "learning_rate": 4.787285555218748e-05,
246
+ "loss": 0.0747,
247
+ "step": 680
248
+ },
249
+ {
250
+ "epoch": 11.2,
251
+ "grad_norm": 0.5186921954154968,
252
+ "learning_rate": 4.763981701009184e-05,
253
+ "loss": 0.0629,
254
+ "step": 700
255
+ },
256
+ {
257
+ "epoch": 11.52,
258
+ "grad_norm": 1.6753857135772705,
259
+ "learning_rate": 4.739529677613456e-05,
260
+ "loss": 0.051,
261
+ "step": 720
262
+ },
263
+ {
264
+ "epoch": 11.84,
265
+ "grad_norm": 0.18876530230045319,
266
+ "learning_rate": 4.713941885776586e-05,
267
+ "loss": 0.0699,
268
+ "step": 740
269
+ },
270
+ {
271
+ "epoch": 12.16,
272
+ "grad_norm": 0.4428744912147522,
273
+ "learning_rate": 4.687231302243975e-05,
274
+ "loss": 0.0526,
275
+ "step": 760
276
+ },
277
+ {
278
+ "epoch": 12.48,
279
+ "grad_norm": 0.4765178859233856,
280
+ "learning_rate": 4.659411473180304e-05,
281
+ "loss": 0.0412,
282
+ "step": 780
283
+ },
284
+ {
285
+ "epoch": 12.8,
286
+ "grad_norm": 1.4559166431427002,
287
+ "learning_rate": 4.6304965072996495e-05,
288
+ "loss": 0.0495,
289
+ "step": 800
290
+ },
291
+ {
292
+ "epoch": 13.12,
293
+ "grad_norm": 1.1842377185821533,
294
+ "learning_rate": 4.6005010687103076e-05,
295
+ "loss": 0.063,
296
+ "step": 820
297
+ },
298
+ {
299
+ "epoch": 13.44,
300
+ "grad_norm": 0.5502442717552185,
301
+ "learning_rate": 4.569440369477951e-05,
302
+ "loss": 0.0425,
303
+ "step": 840
304
+ },
305
+ {
306
+ "epoch": 13.76,
307
+ "grad_norm": 1.819698452949524,
308
+ "learning_rate": 4.5373301619108854e-05,
309
+ "loss": 0.0451,
310
+ "step": 860
311
+ },
312
+ {
313
+ "epoch": 14.08,
314
+ "grad_norm": 0.045023053884506226,
315
+ "learning_rate": 4.5041867305713384e-05,
316
+ "loss": 0.0445,
317
+ "step": 880
318
+ },
319
+ {
320
+ "epoch": 14.4,
321
+ "grad_norm": 0.10354474931955338,
322
+ "learning_rate": 4.4700268840168045e-05,
323
+ "loss": 0.0214,
324
+ "step": 900
325
+ },
326
+ {
327
+ "epoch": 14.72,
328
+ "grad_norm": 0.23762211203575134,
329
+ "learning_rate": 4.4348679462756556e-05,
330
+ "loss": 0.0552,
331
+ "step": 920
332
+ },
333
+ {
334
+ "epoch": 15.04,
335
+ "grad_norm": 0.845052182674408,
336
+ "learning_rate": 4.398727748061324e-05,
337
+ "loss": 0.0524,
338
+ "step": 940
339
+ },
340
+ {
341
+ "epoch": 15.36,
342
+ "grad_norm": 0.29455024003982544,
343
+ "learning_rate": 4.361624617729536e-05,
344
+ "loss": 0.0318,
345
+ "step": 960
346
+ },
347
+ {
348
+ "epoch": 15.68,
349
+ "grad_norm": 0.05131356045603752,
350
+ "learning_rate": 4.323577371983155e-05,
351
+ "loss": 0.0347,
352
+ "step": 980
353
+ },
354
+ {
355
+ "epoch": 16.0,
356
+ "grad_norm": 0.2307986468076706,
357
+ "learning_rate": 4.28460530632937e-05,
358
+ "loss": 0.0541,
359
+ "step": 1000
360
+ },
361
+ {
362
+ "epoch": 16.32,
363
+ "grad_norm": 0.9982470870018005,
364
+ "learning_rate": 4.2447281852940525e-05,
365
+ "loss": 0.0327,
366
+ "step": 1020
367
+ },
368
+ {
369
+ "epoch": 16.64,
370
+ "grad_norm": 2.9247119426727295,
371
+ "learning_rate": 4.203966232398261e-05,
372
+ "loss": 0.0251,
373
+ "step": 1040
374
+ },
375
+ {
376
+ "epoch": 16.96,
377
+ "grad_norm": 0.5199835896492004,
378
+ "learning_rate": 4.162340119901961e-05,
379
+ "loss": 0.0451,
380
+ "step": 1060
381
+ },
382
+ {
383
+ "epoch": 17.28,
384
+ "grad_norm": 0.6802399754524231,
385
+ "learning_rate": 4.1198709583201754e-05,
386
+ "loss": 0.0272,
387
+ "step": 1080
388
+ },
389
+ {
390
+ "epoch": 17.6,
391
+ "grad_norm": 0.9806874394416809,
392
+ "learning_rate": 4.0765802857168687e-05,
393
+ "loss": 0.0517,
394
+ "step": 1100
395
+ },
396
+ {
397
+ "epoch": 17.92,
398
+ "grad_norm": 0.12717130780220032,
399
+ "learning_rate": 4.0324900567820046e-05,
400
+ "loss": 0.0286,
401
+ "step": 1120
402
+ },
403
+ {
404
+ "epoch": 18.24,
405
+ "grad_norm": 0.4048568308353424,
406
+ "learning_rate": 3.987622631697316e-05,
407
+ "loss": 0.0258,
408
+ "step": 1140
409
+ },
410
+ {
411
+ "epoch": 18.56,
412
+ "grad_norm": 1.2760275602340698,
413
+ "learning_rate": 3.942000764796427e-05,
414
+ "loss": 0.0289,
415
+ "step": 1160
416
+ },
417
+ {
418
+ "epoch": 18.88,
419
+ "grad_norm": 0.30493712425231934,
420
+ "learning_rate": 3.895647593025088e-05,
421
+ "loss": 0.0457,
422
+ "step": 1180
423
+ },
424
+ {
425
+ "epoch": 19.2,
426
+ "grad_norm": 0.6177706122398376,
427
+ "learning_rate": 3.8485866242073584e-05,
428
+ "loss": 0.0316,
429
+ "step": 1200
430
+ },
431
+ {
432
+ "epoch": 19.52,
433
+ "grad_norm": 0.10721703618764877,
434
+ "learning_rate": 3.80084172512372e-05,
435
+ "loss": 0.0326,
436
+ "step": 1220
437
+ },
438
+ {
439
+ "epoch": 19.84,
440
+ "grad_norm": 0.06823062896728516,
441
+ "learning_rate": 3.7524371094071266e-05,
442
+ "loss": 0.0238,
443
+ "step": 1240
444
+ },
445
+ {
446
+ "epoch": 20.16,
447
+ "grad_norm": 0.9792996644973755,
448
+ "learning_rate": 3.703397325263162e-05,
449
+ "loss": 0.0286,
450
+ "step": 1260
451
+ },
452
+ {
453
+ "epoch": 20.48,
454
+ "grad_norm": 0.20131415128707886,
455
+ "learning_rate": 3.653747243020515e-05,
456
+ "loss": 0.0294,
457
+ "step": 1280
458
+ },
459
+ {
460
+ "epoch": 20.8,
461
+ "grad_norm": 0.530823826789856,
462
+ "learning_rate": 3.603512042518093e-05,
463
+ "loss": 0.0364,
464
+ "step": 1300
465
+ },
466
+ {
467
+ "epoch": 21.12,
468
+ "grad_norm": 0.006112121045589447,
469
+ "learning_rate": 3.552717200335171e-05,
470
+ "loss": 0.0265,
471
+ "step": 1320
472
+ },
473
+ {
474
+ "epoch": 21.44,
475
+ "grad_norm": 0.005943021737039089,
476
+ "learning_rate": 3.501388476871039e-05,
477
+ "loss": 0.0319,
478
+ "step": 1340
479
+ },
480
+ {
481
+ "epoch": 21.76,
482
+ "grad_norm": 0.07666248083114624,
483
+ "learning_rate": 3.449551903280729e-05,
484
+ "loss": 0.0137,
485
+ "step": 1360
486
+ },
487
+ {
488
+ "epoch": 22.08,
489
+ "grad_norm": 0.6763716340065002,
490
+ "learning_rate": 3.397233768273415e-05,
491
+ "loss": 0.0416,
492
+ "step": 1380
493
+ },
494
+ {
495
+ "epoch": 22.4,
496
+ "grad_norm": 0.07458912581205368,
497
+ "learning_rate": 3.344460604780202e-05,
498
+ "loss": 0.0179,
499
+ "step": 1400
500
+ },
501
+ {
502
+ "epoch": 22.72,
503
+ "grad_norm": 0.25514400005340576,
504
+ "learning_rate": 3.291259176498052e-05,
505
+ "loss": 0.0276,
506
+ "step": 1420
507
+ },
508
+ {
509
+ "epoch": 23.04,
510
+ "grad_norm": 0.006252670660614967,
511
+ "learning_rate": 3.237656464316693e-05,
512
+ "loss": 0.0352,
513
+ "step": 1440
514
+ },
515
+ {
516
+ "epoch": 23.36,
517
+ "grad_norm": 0.36337536573410034,
518
+ "learning_rate": 3.183679652635357e-05,
519
+ "loss": 0.0212,
520
+ "step": 1460
521
+ },
522
+ {
523
+ "epoch": 23.68,
524
+ "grad_norm": 0.28176209330558777,
525
+ "learning_rate": 3.129356115576332e-05,
526
+ "loss": 0.0338,
527
+ "step": 1480
528
+ },
529
+ {
530
+ "epoch": 24.0,
531
+ "grad_norm": 0.012418941594660282,
532
+ "learning_rate": 3.074713403102284e-05,
533
+ "loss": 0.0295,
534
+ "step": 1500
535
+ },
536
+ {
537
+ "epoch": 24.32,
538
+ "grad_norm": 0.16376622021198273,
539
+ "learning_rate": 3.0197792270443982e-05,
540
+ "loss": 0.0185,
541
+ "step": 1520
542
+ },
543
+ {
544
+ "epoch": 24.64,
545
+ "grad_norm": 0.45608577132225037,
546
+ "learning_rate": 2.9645814470484452e-05,
547
+ "loss": 0.0328,
548
+ "step": 1540
549
  },
550
  {
551
+ "epoch": 24.96,
552
+ "grad_norm": 0.1006656065583229,
553
+ "learning_rate": 2.9091480564458666e-05,
554
+ "loss": 0.025,
555
+ "step": 1560
556
+ },
557
+ {
558
+ "epoch": 25.28,
559
+ "grad_norm": 0.3901682496070862,
560
+ "learning_rate": 2.8535071680570734e-05,
561
+ "loss": 0.0294,
562
+ "step": 1580
563
+ },
564
+ {
565
+ "epoch": 25.6,
566
+ "grad_norm": 0.12243347615003586,
567
+ "learning_rate": 2.7976869999341426e-05,
568
+ "loss": 0.0282,
569
+ "step": 1600
570
+ },
571
+ {
572
+ "epoch": 25.92,
573
+ "grad_norm": 0.0033943182788789272,
574
+ "learning_rate": 2.741715861050143e-05,
575
+ "loss": 0.0294,
576
+ "step": 1620
577
+ },
578
+ {
579
+ "epoch": 26.24,
580
+ "grad_norm": 0.0014275741996243596,
581
+ "learning_rate": 2.685622136942359e-05,
582
+ "loss": 0.0354,
583
+ "step": 1640
584
+ },
585
+ {
586
+ "epoch": 26.56,
587
+ "grad_norm": 0.018641650676727295,
588
+ "learning_rate": 2.629434275316673e-05,
589
+ "loss": 0.0162,
590
+ "step": 1660
591
+ },
592
+ {
593
+ "epoch": 26.88,
594
+ "grad_norm": 0.13316482305526733,
595
+ "learning_rate": 2.573180771620432e-05,
596
+ "loss": 0.0205,
597
+ "step": 1680
598
+ },
599
+ {
600
+ "epoch": 27.2,
601
+ "grad_norm": 0.003175324061885476,
602
+ "learning_rate": 2.516890154591095e-05,
603
+ "loss": 0.0129,
604
+ "step": 1700
605
+ },
606
+ {
607
+ "epoch": 27.52,
608
+ "grad_norm": 0.28820428252220154,
609
+ "learning_rate": 2.4605909717879964e-05,
610
+ "loss": 0.0333,
611
+ "step": 1720
612
+ },
613
+ {
614
+ "epoch": 27.84,
615
+ "grad_norm": 0.08302447199821472,
616
+ "learning_rate": 2.4043117751145694e-05,
617
+ "loss": 0.0261,
618
+ "step": 1740
619
+ },
620
+ {
621
+ "epoch": 28.16,
622
+ "grad_norm": 0.37718892097473145,
623
+ "learning_rate": 2.34808110633836e-05,
624
+ "loss": 0.0418,
625
+ "step": 1760
626
+ },
627
+ {
628
+ "epoch": 28.48,
629
+ "grad_norm": 0.16185913980007172,
630
+ "learning_rate": 2.291927482616191e-05,
631
+ "loss": 0.0111,
632
+ "step": 1780
633
+ },
634
+ {
635
+ "epoch": 28.8,
636
+ "grad_norm": 0.33071696758270264,
637
+ "learning_rate": 2.235879382031794e-05,
638
+ "loss": 0.0263,
639
+ "step": 1800
640
+ },
641
+ {
642
+ "epoch": 29.12,
643
+ "grad_norm": 0.002949915360659361,
644
+ "learning_rate": 2.179965229153265e-05,
645
+ "loss": 0.0299,
646
+ "step": 1820
647
+ },
648
+ {
649
+ "epoch": 29.44,
650
+ "grad_norm": 0.0035819699987769127,
651
+ "learning_rate": 2.1242133806176667e-05,
652
+ "loss": 0.0267,
653
+ "step": 1840
654
+ },
655
+ {
656
+ "epoch": 29.76,
657
+ "grad_norm": 0.0039703804068267345,
658
+ "learning_rate": 2.0686521107500638e-05,
659
+ "loss": 0.0204,
660
+ "step": 1860
661
+ },
662
+ {
663
+ "epoch": 30.08,
664
+ "grad_norm": 0.004021900240331888,
665
+ "learning_rate": 2.0133095972243233e-05,
666
+ "loss": 0.0308,
667
+ "step": 1880
668
+ },
669
+ {
670
+ "epoch": 30.4,
671
+ "grad_norm": 0.2821226418018341,
672
+ "learning_rate": 1.9582139067729117e-05,
673
+ "loss": 0.024,
674
+ "step": 1900
675
+ },
676
+ {
677
+ "epoch": 30.72,
678
+ "grad_norm": 0.5529562830924988,
679
+ "learning_rate": 1.90339298095297e-05,
680
+ "loss": 0.0113,
681
+ "step": 1920
682
+ },
683
+ {
684
+ "epoch": 31.04,
685
+ "grad_norm": 0.1492016613483429,
686
+ "learning_rate": 1.8488746219758674e-05,
687
+ "loss": 0.0301,
688
+ "step": 1940
689
+ },
690
+ {
691
+ "epoch": 31.36,
692
+ "grad_norm": 0.19194553792476654,
693
+ "learning_rate": 1.7946864786074165e-05,
694
+ "loss": 0.0293,
695
+ "step": 1960
696
+ },
697
+ {
698
+ "epoch": 31.68,
699
+ "grad_norm": 0.1448647677898407,
700
+ "learning_rate": 1.740856032145917e-05,
701
+ "loss": 0.0242,
702
+ "step": 1980
703
+ },
704
+ {
705
+ "epoch": 32.0,
706
+ "grad_norm": 0.06869282573461533,
707
+ "learning_rate": 1.6874105824851267e-05,
708
+ "loss": 0.022,
709
+ "step": 2000
710
+ },
711
+ {
712
+ "epoch": 32.32,
713
+ "grad_norm": 0.002635813085362315,
714
+ "learning_rate": 1.634377234269226e-05,
715
+ "loss": 0.0264,
716
+ "step": 2020
717
+ },
718
+ {
719
+ "epoch": 32.64,
720
+ "grad_norm": 0.0027471587527543306,
721
+ "learning_rate": 1.5817828831468144e-05,
722
+ "loss": 0.0155,
723
+ "step": 2040
724
+ },
725
+ {
726
+ "epoch": 32.96,
727
+ "grad_norm": 0.28300318121910095,
728
+ "learning_rate": 1.5296542021308825e-05,
729
+ "loss": 0.0208,
730
+ "step": 2060
731
+ },
732
+ {
733
+ "epoch": 33.28,
734
+ "grad_norm": 0.0016769981011748314,
735
+ "learning_rate": 1.478017628071706e-05,
736
+ "loss": 0.0264,
737
+ "step": 2080
738
+ },
739
+ {
740
+ "epoch": 33.6,
741
+ "grad_norm": 0.0014146752655506134,
742
+ "learning_rate": 1.4268993482495055e-05,
743
+ "loss": 0.0174,
744
+ "step": 2100
745
+ },
746
+ {
747
+ "epoch": 33.92,
748
+ "grad_norm": 0.05964767187833786,
749
+ "learning_rate": 1.3763252870936649e-05,
750
+ "loss": 0.0214,
751
+ "step": 2120
752
+ },
753
+ {
754
+ "epoch": 34.24,
755
+ "grad_norm": 0.0016291196225211024,
756
+ "learning_rate": 1.3263210930352737e-05,
757
+ "loss": 0.0306,
758
+ "step": 2140
759
+ },
760
+ {
761
+ "epoch": 34.56,
762
+ "grad_norm": 0.034806057810783386,
763
+ "learning_rate": 1.2769121254996159e-05,
764
+ "loss": 0.0146,
765
+ "step": 2160
766
+ },
767
+ {
768
+ "epoch": 34.88,
769
+ "grad_norm": 0.315729558467865,
770
+ "learning_rate": 1.228123442045249e-05,
771
+ "loss": 0.0254,
772
+ "step": 2180
773
+ },
774
+ {
775
+ "epoch": 35.2,
776
+ "grad_norm": 0.5809018015861511,
777
+ "learning_rate": 1.1799797856561606e-05,
778
+ "loss": 0.0176,
779
+ "step": 2200
780
+ },
781
+ {
782
+ "epoch": 35.52,
783
+ "grad_norm": 0.18777510523796082,
784
+ "learning_rate": 1.1325055721934637e-05,
785
+ "loss": 0.0205,
786
+ "step": 2220
787
+ },
788
+ {
789
+ "epoch": 35.84,
790
+ "grad_norm": 0.11027589440345764,
791
+ "learning_rate": 1.0857248780129928e-05,
792
+ "loss": 0.0153,
793
+ "step": 2240
794
+ },
795
+ {
796
+ "epoch": 36.16,
797
+ "grad_norm": 0.18985402584075928,
798
+ "learning_rate": 1.0396614277550752e-05,
799
+ "loss": 0.0251,
800
+ "step": 2260
801
+ },
802
+ {
803
+ "epoch": 36.48,
804
+ "grad_norm": 0.011078303679823875,
805
+ "learning_rate": 9.943385823126775e-06,
806
+ "loss": 0.0224,
807
+ "step": 2280
808
+ },
809
+ {
810
+ "epoch": 36.8,
811
+ "grad_norm": 0.15364831686019897,
812
+ "learning_rate": 9.497793269840211e-06,
813
+ "loss": 0.0219,
814
+ "step": 2300
815
+ },
816
+ {
817
+ "epoch": 37.12,
818
+ "grad_norm": 0.16373781859874725,
819
+ "learning_rate": 9.06006259815683e-06,
820
+ "loss": 0.021,
821
+ "step": 2320
822
+ },
823
+ {
824
+ "epoch": 37.44,
825
+ "grad_norm": 0.41937291622161865,
826
+ "learning_rate": 8.630415801420835e-06,
827
+ "loss": 0.0236,
828
+ "step": 2340
829
+ },
830
+ {
831
+ "epoch": 37.76,
832
+ "grad_norm": 0.4237123727798462,
833
+ "learning_rate": 8.209070773271894e-06,
834
+ "loss": 0.0216,
835
+ "step": 2360
836
+ },
837
+ {
838
+ "epoch": 38.08,
839
+ "grad_norm": 0.08532612025737762,
840
+ "learning_rate": 7.79624119714121e-06,
841
+ "loss": 0.0268,
842
+ "step": 2380
843
+ },
844
+ {
845
+ "epoch": 38.4,
846
+ "grad_norm": 0.2872686982154846,
847
+ "learning_rate": 7.392136437882855e-06,
848
+ "loss": 0.0306,
849
+ "step": 2400
850
+ },
851
+ {
852
+ "epoch": 38.72,
853
+ "grad_norm": 0.2834513485431671,
854
+ "learning_rate": 6.996961435595223e-06,
855
+ "loss": 0.0224,
856
+ "step": 2420
857
+ },
858
+ {
859
+ "epoch": 39.04,
860
+ "grad_norm": 0.0006759735988453031,
861
+ "learning_rate": 6.610916601686481e-06,
862
+ "loss": 0.0138,
863
+ "step": 2440
864
+ },
865
+ {
866
+ "epoch": 39.36,
867
+ "grad_norm": 0.24796371161937714,
868
+ "learning_rate": 6.234197717236742e-06,
869
+ "loss": 0.0234,
870
+ "step": 2460
871
+ },
872
+ {
873
+ "epoch": 39.68,
874
+ "grad_norm": 0.2657662332057953,
875
+ "learning_rate": 5.866995833708464e-06,
876
+ "loss": 0.0164,
877
+ "step": 2480
878
  },
879
  {
880
  "epoch": 40.0,
881
+ "grad_norm": 0.0017559522530063987,
882
+ "learning_rate": 5.509497176055492e-06,
883
+ "loss": 0.0169,
884
+ "step": 2500
885
+ },
886
+ {
887
+ "epoch": 40.32,
888
+ "grad_norm": 0.18896016478538513,
889
+ "learning_rate": 5.161883048279817e-06,
890
+ "loss": 0.0116,
891
+ "step": 2520
892
+ },
893
+ {
894
+ "epoch": 40.64,
895
+ "grad_norm": 0.2336779683828354,
896
+ "learning_rate": 4.824329741483949e-06,
897
+ "loss": 0.0219,
898
+ "step": 2540
899
+ },
900
+ {
901
+ "epoch": 40.96,
902
+ "grad_norm": 0.16521525382995605,
903
+ "learning_rate": 4.497008444465681e-06,
904
+ "loss": 0.0366,
905
+ "step": 2560
906
+ },
907
+ {
908
+ "epoch": 41.28,
909
+ "grad_norm": 0.0013411182444542646,
910
+ "learning_rate": 4.180085156900274e-06,
911
+ "loss": 0.0228,
912
+ "step": 2580
913
+ },
914
+ {
915
+ "epoch": 41.6,
916
+ "grad_norm": 0.0015802403213456273,
917
+ "learning_rate": 3.873720605154468e-06,
918
+ "loss": 0.0135,
919
+ "step": 2600
920
+ },
921
+ {
922
+ "epoch": 41.92,
923
+ "grad_norm": 0.002210975391790271,
924
+ "learning_rate": 3.578070160774724e-06,
925
+ "loss": 0.0267,
926
+ "step": 2620
927
+ },
928
+ {
929
+ "epoch": 42.24,
930
+ "grad_norm": 0.23047080636024475,
931
+ "learning_rate": 3.293283761691182e-06,
932
+ "loss": 0.0218,
933
+ "step": 2640
934
+ },
935
+ {
936
+ "epoch": 42.56,
937
+ "grad_norm": 0.2625073492527008,
938
+ "learning_rate": 3.0195058361772277e-06,
939
+ "loss": 0.0315,
940
+ "step": 2660
941
+ },
942
+ {
943
+ "epoch": 42.88,
944
+ "grad_norm": 0.22485554218292236,
945
+ "learning_rate": 2.756875229603295e-06,
946
+ "loss": 0.022,
947
+ "step": 2680
948
+ },
949
+ {
950
+ "epoch": 43.2,
951
+ "grad_norm": 0.001550053246319294,
952
+ "learning_rate": 2.5055251340219855e-06,
953
+ "loss": 0.016,
954
+ "step": 2700
955
+ },
956
+ {
957
+ "epoch": 43.52,
958
+ "grad_norm": 0.22042883932590485,
959
+ "learning_rate": 2.2655830206202655e-06,
960
+ "loss": 0.0267,
961
+ "step": 2720
962
+ },
963
+ {
964
+ "epoch": 43.84,
965
+ "grad_norm": 0.08822102099657059,
966
+ "learning_rate": 2.037170575072944e-06,
967
+ "loss": 0.0167,
968
+ "step": 2740
969
+ },
970
+ {
971
+ "epoch": 44.16,
972
+ "grad_norm": 0.0016505387611687183,
973
+ "learning_rate": 1.8204036358303173e-06,
974
+ "loss": 0.0492,
975
+ "step": 2760
976
+ },
977
+ {
978
+ "epoch": 44.48,
979
+ "grad_norm": 0.3908143639564514,
980
+ "learning_rate": 1.615392135371116e-06,
981
+ "loss": 0.0254,
982
+ "step": 2780
983
+ },
984
+ {
985
+ "epoch": 44.8,
986
+ "grad_norm": 0.3156016767024994,
987
+ "learning_rate": 1.4222400444507318e-06,
988
+ "loss": 0.0136,
989
+ "step": 2800
990
+ },
991
+ {
992
+ "epoch": 45.12,
993
+ "grad_norm": 0.001897096517495811,
994
+ "learning_rate": 1.2410453193728493e-06,
995
+ "loss": 0.0116,
996
+ "step": 2820
997
+ },
998
+ {
999
+ "epoch": 45.44,
1000
+ "grad_norm": 0.20051489770412445,
1001
+ "learning_rate": 1.0718998523113004e-06,
1002
+ "loss": 0.0311,
1003
+ "step": 2840
1004
+ },
1005
+ {
1006
+ "epoch": 45.76,
1007
+ "grad_norm": 0.0016040581976994872,
1008
+ "learning_rate": 9.148894247073298e-07,
1009
+ "loss": 0.0283,
1010
+ "step": 2860
1011
+ },
1012
+ {
1013
+ "epoch": 46.08,
1014
+ "grad_norm": 0.0015667045954614878,
1015
+ "learning_rate": 7.700936637658779e-07,
1016
+ "loss": 0.0186,
1017
+ "step": 2880
1018
+ },
1019
+ {
1020
+ "epoch": 46.4,
1021
+ "grad_norm": 0.04447433352470398,
1022
+ "learning_rate": 6.375860020729541e-07,
1023
+ "loss": 0.0229,
1024
+ "step": 2900
1025
+ },
1026
+ {
1027
+ "epoch": 46.72,
1028
+ "grad_norm": 0.20941714942455292,
1029
+ "learning_rate": 5.174336403546226e-07,
1030
+ "loss": 0.0268,
1031
+ "step": 2920
1032
+ },
1033
+ {
1034
+ "epoch": 47.04,
1035
+ "grad_norm": 0.0015096565475687385,
1036
+ "learning_rate": 4.096975133963954e-07,
1037
+ "loss": 0.0161,
1038
+ "step": 2940
1039
+ },
1040
+ {
1041
+ "epoch": 47.36,
1042
+ "grad_norm": 0.19307351112365723,
1043
+ "learning_rate": 3.144322591404292e-07,
1044
+ "loss": 0.0113,
1045
+ "step": 2960
1046
+ },
1047
+ {
1048
+ "epoch": 47.68,
1049
+ "grad_norm": 0.002177381655201316,
1050
+ "learning_rate": 2.316861909760909e-07,
1051
+ "loss": 0.0222,
1052
+ "step": 2980
1053
+ },
1054
+ {
1055
+ "epoch": 48.0,
1056
+ "grad_norm": 0.09334852546453476,
1057
+ "learning_rate": 1.6150127323803222e-07,
1058
+ "loss": 0.028,
1059
+ "step": 3000
1060
+ },
1061
+ {
1062
+ "epoch": 48.32,
1063
+ "grad_norm": 0.09507758915424347,
1064
+ "learning_rate": 1.0391309992413833e-07,
1065
+ "loss": 0.0217,
1066
+ "step": 3020
1067
+ },
1068
+ {
1069
+ "epoch": 48.64,
1070
+ "grad_norm": 0.0010601489339023829,
1071
+ "learning_rate": 5.895087664417876e-08,
1072
+ "loss": 0.0191,
1073
+ "step": 3040
1074
+ },
1075
+ {
1076
+ "epoch": 48.96,
1077
+ "grad_norm": 0.001158875529654324,
1078
+ "learning_rate": 2.6637405808302428e-08,
1079
+ "loss": 0.0162,
1080
+ "step": 3060
1081
+ },
1082
+ {
1083
+ "epoch": 49.28,
1084
+ "grad_norm": 0.0015347091248258948,
1085
+ "learning_rate": 6.989075062879824e-09,
1086
+ "loss": 0.0146,
1087
+ "step": 3080
1088
+ },
1089
+ {
1090
+ "epoch": 49.6,
1091
+ "grad_norm": 0.0010455228621140122,
1092
+ "learning_rate": 1.584897958428755e-11,
1093
+ "loss": 0.0217,
1094
+ "step": 3100
1095
  },
1096
  {
1097
+ "epoch": 49.6,
1098
+ "step": 3100,
1099
+ "total_flos": 1.7939255986343117e+17,
1100
+ "train_loss": 0.172668604437382,
1101
+ "train_runtime": 11274.7291,
1102
+ "train_samples_per_second": 2.217,
1103
+ "train_steps_per_second": 0.275
1104
  }
1105
  ],
1106
+ "logging_steps": 20,
1107
+ "max_steps": 3100,
1108
  "num_input_tokens_seen": 0,
1109
+ "num_train_epochs": 50,
1110
  "save_steps": 1000,
1111
  "stateful_callbacks": {
1112
  "TrainerControl": {
 
1114
  "should_epoch_stop": false,
1115
  "should_evaluate": false,
1116
  "should_log": false,
1117
+ "should_save": true,
1118
  "should_training_stop": false
1119
  },
1120
  "attributes": {}
1121
  }
1122
  },
1123
+ "total_flos": 1.7939255986343117e+17,
1124
  "train_batch_size": 2,
1125
  "trial_name": null,
1126
  "trial_params": null
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2279126ecb259d79e6f80d283859e888f52e7d60a121995c376e249f6287582a
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4feb1ab5744e1b2819b309b2001c004a373fe1e946dea49af8b0cd713f11d50f
3
  size 5240