rbelanec commited on
Commit
fbc5273
verified
1 Parent(s): 4f6f97c

Training in progress, step 2686

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. trainer_log.jsonl +32 -0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c15a253221934ec374168f4f7c34ade4860407be5640a3275393938f2385e6b
3
  size 798032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:decf8af647aa00c3b3d0c537082eb84dea7596be94c58fa27691fa5bc82449e7
3
  size 798032
trainer_log.jsonl CHANGED
@@ -524,3 +524,35 @@
524
  {"current_steps": 2540, "total_steps": 3160, "loss": 0.1161, "lr": 5.655044284927657e-06, "epoch": 16.075949367088608, "percentage": 80.38, "elapsed_time": "0:07:42", "remaining_time": "0:01:52", "throughput": 2489.11, "total_tokens": 1149984}
525
  {"current_steps": 2545, "total_steps": 3160, "loss": 0.0489, "lr": 5.567875579246817e-06, "epoch": 16.10759493670886, "percentage": 80.54, "elapsed_time": "0:07:42", "remaining_time": "0:01:51", "throughput": 2488.9, "total_tokens": 1152192}
526
  {"current_steps": 2550, "total_steps": 3160, "loss": 0.0859, "lr": 5.481299662036793e-06, "epoch": 16.139240506329113, "percentage": 80.7, "elapsed_time": "0:07:43", "remaining_time": "0:01:50", "throughput": 2489.48, "total_tokens": 1154592}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
524
  {"current_steps": 2540, "total_steps": 3160, "loss": 0.1161, "lr": 5.655044284927657e-06, "epoch": 16.075949367088608, "percentage": 80.38, "elapsed_time": "0:07:42", "remaining_time": "0:01:52", "throughput": 2489.11, "total_tokens": 1149984}
525
  {"current_steps": 2545, "total_steps": 3160, "loss": 0.0489, "lr": 5.567875579246817e-06, "epoch": 16.10759493670886, "percentage": 80.54, "elapsed_time": "0:07:42", "remaining_time": "0:01:51", "throughput": 2488.9, "total_tokens": 1152192}
526
  {"current_steps": 2550, "total_steps": 3160, "loss": 0.0859, "lr": 5.481299662036793e-06, "epoch": 16.139240506329113, "percentage": 80.7, "elapsed_time": "0:07:43", "remaining_time": "0:01:50", "throughput": 2489.48, "total_tokens": 1154592}
527
+ {"current_steps": 2555, "total_steps": 3160, "loss": 0.113, "lr": 5.395319174347244e-06, "epoch": 16.170886075949365, "percentage": 80.85, "elapsed_time": "0:07:44", "remaining_time": "0:01:50", "throughput": 2489.71, "total_tokens": 1156800}
528
+ {"current_steps": 2560, "total_steps": 3160, "loss": 0.0657, "lr": 5.309936739063909e-06, "epoch": 16.20253164556962, "percentage": 81.01, "elapsed_time": "0:07:45", "remaining_time": "0:01:49", "throughput": 2490.12, "total_tokens": 1159104}
529
+ {"current_steps": 2565, "total_steps": 3160, "loss": 0.0707, "lr": 5.225154960828557e-06, "epoch": 16.234177215189874, "percentage": 81.17, "elapsed_time": "0:07:46", "remaining_time": "0:01:48", "throughput": 2490.48, "total_tokens": 1161312}
530
+ {"current_steps": 2570, "total_steps": 3160, "loss": 0.0969, "lr": 5.140976425959579e-06, "epoch": 16.265822784810126, "percentage": 81.33, "elapsed_time": "0:07:47", "remaining_time": "0:01:47", "throughput": 2490.71, "total_tokens": 1163520}
531
+ {"current_steps": 2575, "total_steps": 3160, "loss": 0.047, "lr": 5.057403702373076e-06, "epoch": 16.29746835443038, "percentage": 81.49, "elapsed_time": "0:07:47", "remaining_time": "0:01:46", "throughput": 2491.05, "total_tokens": 1165792}
532
+ {"current_steps": 2580, "total_steps": 3160, "loss": 0.1036, "lr": 4.9744393395044884e-06, "epoch": 16.32911392405063, "percentage": 81.65, "elapsed_time": "0:07:48", "remaining_time": "0:01:45", "throughput": 2491.28, "total_tokens": 1168000}
533
+ {"current_steps": 2585, "total_steps": 3160, "loss": 0.0438, "lr": 4.892085868230881e-06, "epoch": 16.360759493670887, "percentage": 81.8, "elapsed_time": "0:07:49", "remaining_time": "0:01:44", "throughput": 2491.51, "total_tokens": 1170208}
534
+ {"current_steps": 2590, "total_steps": 3160, "loss": 0.0658, "lr": 4.8103458007936915e-06, "epoch": 16.39240506329114, "percentage": 81.96, "elapsed_time": "0:07:50", "remaining_time": "0:01:43", "throughput": 2491.96, "total_tokens": 1172544}
535
+ {"current_steps": 2595, "total_steps": 3160, "loss": 0.0559, "lr": 4.729221630722128e-06, "epoch": 16.424050632911392, "percentage": 82.12, "elapsed_time": "0:07:51", "remaining_time": "0:01:42", "throughput": 2492.3, "total_tokens": 1174816}
536
+ {"current_steps": 2600, "total_steps": 3160, "loss": 0.0967, "lr": 4.648715832757056e-06, "epoch": 16.455696202531644, "percentage": 82.28, "elapsed_time": "0:07:52", "remaining_time": "0:01:41", "throughput": 2492.58, "total_tokens": 1177056}
537
+ {"current_steps": 2605, "total_steps": 3160, "loss": 0.0829, "lr": 4.568830862775556e-06, "epoch": 16.4873417721519, "percentage": 82.44, "elapsed_time": "0:07:53", "remaining_time": "0:01:40", "throughput": 2493.02, "total_tokens": 1179392}
538
+ {"current_steps": 2610, "total_steps": 3160, "loss": 0.1337, "lr": 4.489569157715976e-06, "epoch": 16.518987341772153, "percentage": 82.59, "elapsed_time": "0:07:53", "remaining_time": "0:01:39", "throughput": 2493.35, "total_tokens": 1181664}
539
+ {"current_steps": 2615, "total_steps": 3160, "loss": 0.0897, "lr": 4.4109331355036085e-06, "epoch": 16.550632911392405, "percentage": 82.75, "elapsed_time": "0:07:54", "remaining_time": "0:01:38", "throughput": 2493.58, "total_tokens": 1183808}
540
+ {"current_steps": 2620, "total_steps": 3160, "loss": 0.0869, "lr": 4.332925194976894e-06, "epoch": 16.582278481012658, "percentage": 82.91, "elapsed_time": "0:07:55", "remaining_time": "0:01:38", "throughput": 2494.18, "total_tokens": 1186240}
541
+ {"current_steps": 2625, "total_steps": 3160, "loss": 0.1057, "lr": 4.255547715814296e-06, "epoch": 16.61392405063291, "percentage": 83.07, "elapsed_time": "0:07:56", "remaining_time": "0:01:37", "throughput": 2494.83, "total_tokens": 1188704}
542
+ {"current_steps": 2630, "total_steps": 3160, "loss": 0.1033, "lr": 4.178803058461664e-06, "epoch": 16.645569620253166, "percentage": 83.23, "elapsed_time": "0:07:57", "remaining_time": "0:01:36", "throughput": 2495.09, "total_tokens": 1190944}
543
+ {"current_steps": 2635, "total_steps": 3160, "loss": 0.1631, "lr": 4.102693564060258e-06, "epoch": 16.67721518987342, "percentage": 83.39, "elapsed_time": "0:07:58", "remaining_time": "0:01:35", "throughput": 2495.43, "total_tokens": 1193216}
544
+ {"current_steps": 2640, "total_steps": 3160, "loss": 0.0924, "lr": 4.027221554375296e-06, "epoch": 16.70886075949367, "percentage": 83.54, "elapsed_time": "0:07:59", "remaining_time": "0:01:34", "throughput": 2495.92, "total_tokens": 1195584}
545
+ {"current_steps": 2645, "total_steps": 3160, "loss": 0.0989, "lr": 3.952389331725162e-06, "epoch": 16.740506329113924, "percentage": 83.7, "elapsed_time": "0:07:59", "remaining_time": "0:01:33", "throughput": 2496.19, "total_tokens": 1197824}
546
+ {"current_steps": 2650, "total_steps": 3160, "loss": 0.0296, "lr": 3.87819917891116e-06, "epoch": 16.772151898734176, "percentage": 83.86, "elapsed_time": "0:08:00", "remaining_time": "0:01:32", "throughput": 2496.39, "total_tokens": 1200032}
547
+ {"current_steps": 2655, "total_steps": 3160, "loss": 0.0656, "lr": 3.8046533591478556e-06, "epoch": 16.803797468354432, "percentage": 84.02, "elapsed_time": "0:08:01", "remaining_time": "0:01:31", "throughput": 2496.6, "total_tokens": 1202240}
548
+ {"current_steps": 2660, "total_steps": 3160, "loss": 0.0615, "lr": 3.7317541159940657e-06, "epoch": 16.835443037974684, "percentage": 84.18, "elapsed_time": "0:08:02", "remaining_time": "0:01:30", "throughput": 2496.94, "total_tokens": 1204576}
549
+ {"current_steps": 2665, "total_steps": 3160, "loss": 0.099, "lr": 3.659503673284409e-06, "epoch": 16.867088607594937, "percentage": 84.34, "elapsed_time": "0:08:03", "remaining_time": "0:01:29", "throughput": 2497.21, "total_tokens": 1206816}
550
+ {"current_steps": 2670, "total_steps": 3160, "loss": 0.1582, "lr": 3.5879042350614482e-06, "epoch": 16.89873417721519, "percentage": 84.49, "elapsed_time": "0:08:04", "remaining_time": "0:01:28", "throughput": 2497.58, "total_tokens": 1209120}
551
+ {"current_steps": 2675, "total_steps": 3160, "loss": 0.0654, "lr": 3.516957985508476e-06, "epoch": 16.930379746835442, "percentage": 84.65, "elapsed_time": "0:08:04", "remaining_time": "0:01:27", "throughput": 2498.16, "total_tokens": 1211552}
552
+ {"current_steps": 2680, "total_steps": 3160, "loss": 0.0446, "lr": 3.4466670888828794e-06, "epoch": 16.962025316455698, "percentage": 84.81, "elapsed_time": "0:08:05", "remaining_time": "0:01:27", "throughput": 2498.3, "total_tokens": 1213632}
553
+ {"current_steps": 2685, "total_steps": 3160, "loss": 0.0959, "lr": 3.377033689450115e-06, "epoch": 16.99367088607595, "percentage": 84.97, "elapsed_time": "0:08:06", "remaining_time": "0:01:26", "throughput": 2498.73, "total_tokens": 1215968}
554
+ {"current_steps": 2686, "total_steps": 3160, "eval_loss": 0.2168864607810974, "epoch": 17.0, "percentage": 85.0, "elapsed_time": "0:08:07", "remaining_time": "0:01:26", "throughput": 2492.79, "total_tokens": 1216160}
555
+ {"current_steps": 2690, "total_steps": 3160, "loss": 0.1202, "lr": 3.3080599114183043e-06, "epoch": 17.025316455696203, "percentage": 85.13, "elapsed_time": "0:08:09", "remaining_time": "0:01:25", "throughput": 2488.68, "total_tokens": 1217888}
556
+ {"current_steps": 2695, "total_steps": 3160, "loss": 0.1354, "lr": 3.2397478588734043e-06, "epoch": 17.056962025316455, "percentage": 85.28, "elapsed_time": "0:08:10", "remaining_time": "0:01:24", "throughput": 2488.96, "total_tokens": 1220128}
557
+ {"current_steps": 2700, "total_steps": 3160, "loss": 0.077, "lr": 3.1720996157150657e-06, "epoch": 17.088607594936708, "percentage": 85.44, "elapsed_time": "0:08:11", "remaining_time": "0:01:23", "throughput": 2488.83, "total_tokens": 1222432}
558
+ {"current_steps": 2705, "total_steps": 3160, "loss": 0.0669, "lr": 3.1051172455930394e-06, "epoch": 17.120253164556964, "percentage": 85.6, "elapsed_time": "0:08:12", "remaining_time": "0:01:22", "throughput": 2489.25, "total_tokens": 1224768}