rbelanec commited on
Commit
5aa3f73
verified
1 Parent(s): fbc5273

Training in progress, step 2844

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. trainer_log.jsonl +33 -0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:decf8af647aa00c3b3d0c537082eb84dea7596be94c58fa27691fa5bc82449e7
3
  size 798032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c67f09fa851c84c5d72da056a026a6687231d473807062f8ecd710431e09c2e
3
  size 798032
trainer_log.jsonl CHANGED
@@ -556,3 +556,36 @@
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}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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}
559
+ {"current_steps": 2710, "total_steps": 3160, "loss": 0.1163, "lr": 3.0388027918442086e-06, "epoch": 17.151898734177216, "percentage": 85.76, "elapsed_time": "0:08:12", "remaining_time": "0:01:21", "throughput": 2489.73, "total_tokens": 1227136}
560
+ {"current_steps": 2715, "total_steps": 3160, "loss": 0.0665, "lr": 2.9731582774302905e-06, "epoch": 17.18354430379747, "percentage": 85.92, "elapsed_time": "0:08:13", "remaining_time": "0:01:20", "throughput": 2489.95, "total_tokens": 1229344}
561
+ {"current_steps": 2720, "total_steps": 3160, "loss": 0.0772, "lr": 2.908185704876101e-06, "epoch": 17.21518987341772, "percentage": 86.08, "elapsed_time": "0:08:14", "remaining_time": "0:01:20", "throughput": 2490.17, "total_tokens": 1231552}
562
+ {"current_steps": 2725, "total_steps": 3160, "loss": 0.0804, "lr": 2.8438870562084523e-06, "epoch": 17.246835443037973, "percentage": 86.23, "elapsed_time": "0:08:15", "remaining_time": "0:01:19", "throughput": 2490.47, "total_tokens": 1233824}
563
+ {"current_steps": 2730, "total_steps": 3160, "loss": 0.0775, "lr": 2.7802642928957458e-06, "epoch": 17.27848101265823, "percentage": 86.39, "elapsed_time": "0:08:16", "remaining_time": "0:01:18", "throughput": 2490.89, "total_tokens": 1236160}
564
+ {"current_steps": 2735, "total_steps": 3160, "loss": 0.0984, "lr": 2.7173193557880615e-06, "epoch": 17.310126582278482, "percentage": 86.55, "elapsed_time": "0:08:17", "remaining_time": "0:01:17", "throughput": 2491.27, "total_tokens": 1238464}
565
+ {"current_steps": 2740, "total_steps": 3160, "loss": 0.1213, "lr": 2.6550541650580186e-06, "epoch": 17.341772151898734, "percentage": 86.71, "elapsed_time": "0:08:17", "remaining_time": "0:01:16", "throughput": 2491.66, "total_tokens": 1240704}
566
+ {"current_steps": 2745, "total_steps": 3160, "loss": 0.0808, "lr": 2.593470620142155e-06, "epoch": 17.373417721518987, "percentage": 86.87, "elapsed_time": "0:08:18", "remaining_time": "0:01:15", "throughput": 2492.17, "total_tokens": 1243008}
567
+ {"current_steps": 2750, "total_steps": 3160, "loss": 0.0544, "lr": 2.5325705996829956e-06, "epoch": 17.40506329113924, "percentage": 87.03, "elapsed_time": "0:08:19", "remaining_time": "0:01:14", "throughput": 2492.33, "total_tokens": 1245184}
568
+ {"current_steps": 2755, "total_steps": 3160, "loss": 0.0512, "lr": 2.472355961471762e-06, "epoch": 17.436708860759495, "percentage": 87.18, "elapsed_time": "0:08:20", "remaining_time": "0:01:13", "throughput": 2492.63, "total_tokens": 1247456}
569
+ {"current_steps": 2760, "total_steps": 3160, "loss": 0.0646, "lr": 2.4128285423916735e-06, "epoch": 17.468354430379748, "percentage": 87.34, "elapsed_time": "0:08:21", "remaining_time": "0:01:12", "throughput": 2493.0, "total_tokens": 1249760}
570
+ {"current_steps": 2765, "total_steps": 3160, "loss": 0.0874, "lr": 2.3539901583619185e-06, "epoch": 17.5, "percentage": 87.5, "elapsed_time": "0:08:22", "remaining_time": "0:01:11", "throughput": 2493.32, "total_tokens": 1252032}
571
+ {"current_steps": 2770, "total_steps": 3160, "loss": 0.1236, "lr": 2.2958426042822806e-06, "epoch": 17.531645569620252, "percentage": 87.66, "elapsed_time": "0:08:22", "remaining_time": "0:01:10", "throughput": 2493.53, "total_tokens": 1254240}
572
+ {"current_steps": 2775, "total_steps": 3160, "loss": 0.1414, "lr": 2.2383876539783493e-06, "epoch": 17.563291139240505, "percentage": 87.82, "elapsed_time": "0:08:23", "remaining_time": "0:01:09", "throughput": 2493.76, "total_tokens": 1256512}
573
+ {"current_steps": 2780, "total_steps": 3160, "loss": 0.0315, "lr": 2.181627060147423e-06, "epoch": 17.59493670886076, "percentage": 87.97, "elapsed_time": "0:08:24", "remaining_time": "0:01:08", "throughput": 2494.07, "total_tokens": 1258784}
574
+ {"current_steps": 2785, "total_steps": 3160, "loss": 0.0901, "lr": 2.125562554305069e-06, "epoch": 17.626582278481013, "percentage": 88.13, "elapsed_time": "0:08:25", "remaining_time": "0:01:08", "throughput": 2494.33, "total_tokens": 1261024}
575
+ {"current_steps": 2790, "total_steps": 3160, "loss": 0.0821, "lr": 2.0701958467322452e-06, "epoch": 17.658227848101266, "percentage": 88.29, "elapsed_time": "0:08:26", "remaining_time": "0:01:07", "throughput": 2494.79, "total_tokens": 1263392}
576
+ {"current_steps": 2795, "total_steps": 3160, "loss": 0.1439, "lr": 2.0155286264231856e-06, "epoch": 17.689873417721518, "percentage": 88.45, "elapsed_time": "0:08:27", "remaining_time": "0:01:06", "throughput": 2495.13, "total_tokens": 1265600}
577
+ {"current_steps": 2800, "total_steps": 3160, "loss": 0.0505, "lr": 1.9615625610338445e-06, "epoch": 17.72151898734177, "percentage": 88.61, "elapsed_time": "0:08:28", "remaining_time": "0:01:05", "throughput": 2495.34, "total_tokens": 1267808}
578
+ {"current_steps": 2805, "total_steps": 3160, "loss": 0.0594, "lr": 1.908299296831012e-06, "epoch": 17.753164556962027, "percentage": 88.77, "elapsed_time": "0:08:28", "remaining_time": "0:01:04", "throughput": 2495.55, "total_tokens": 1270016}
579
+ {"current_steps": 2810, "total_steps": 3160, "loss": 0.0716, "lr": 1.8557404586421413e-06, "epoch": 17.78481012658228, "percentage": 88.92, "elapsed_time": "0:08:29", "remaining_time": "0:01:03", "throughput": 2496.1, "total_tokens": 1272448}
580
+ {"current_steps": 2815, "total_steps": 3160, "loss": 0.1263, "lr": 1.8038876498057329e-06, "epoch": 17.81645569620253, "percentage": 89.08, "elapsed_time": "0:08:30", "remaining_time": "0:01:02", "throughput": 2496.59, "total_tokens": 1274848}
581
+ {"current_steps": 2820, "total_steps": 3160, "loss": 0.074, "lr": 1.7527424521224384e-06, "epoch": 17.848101265822784, "percentage": 89.24, "elapsed_time": "0:08:31", "remaining_time": "0:01:01", "throughput": 2496.94, "total_tokens": 1277152}
582
+ {"current_steps": 2825, "total_steps": 3160, "loss": 0.0599, "lr": 1.7023064258068377e-06, "epoch": 17.879746835443036, "percentage": 89.4, "elapsed_time": "0:08:32", "remaining_time": "0:01:00", "throughput": 2497.34, "total_tokens": 1279488}
583
+ {"current_steps": 2830, "total_steps": 3160, "loss": 0.1143, "lr": 1.652581109439788e-06, "epoch": 17.911392405063292, "percentage": 89.56, "elapsed_time": "0:08:33", "remaining_time": "0:00:59", "throughput": 2497.58, "total_tokens": 1281728}
584
+ {"current_steps": 2835, "total_steps": 3160, "loss": 0.1011, "lr": 1.6035680199215391e-06, "epoch": 17.943037974683545, "percentage": 89.72, "elapsed_time": "0:08:34", "remaining_time": "0:00:58", "throughput": 2497.88, "total_tokens": 1284000}
585
+ {"current_steps": 2840, "total_steps": 3160, "loss": 0.0386, "lr": 1.5552686524254345e-06, "epoch": 17.974683544303797, "percentage": 89.87, "elapsed_time": "0:08:34", "remaining_time": "0:00:58", "throughput": 2498.02, "total_tokens": 1286176}
586
+ {"current_steps": 2844, "total_steps": 3160, "eval_loss": 0.2155109941959381, "epoch": 18.0, "percentage": 90.0, "elapsed_time": "0:08:36", "remaining_time": "0:00:57", "throughput": 2492.57, "total_tokens": 1287728}
587
+ {"current_steps": 2845, "total_steps": 3160, "loss": 0.1161, "lr": 1.5076844803522922e-06, "epoch": 18.00632911392405, "percentage": 90.03, "elapsed_time": "0:08:37", "remaining_time": "0:00:57", "throughput": 2488.65, "total_tokens": 1288176}
588
+ {"current_steps": 2850, "total_steps": 3160, "loss": 0.0729, "lr": 1.460816955285485e-06, "epoch": 18.037974683544302, "percentage": 90.19, "elapsed_time": "0:08:38", "remaining_time": "0:00:56", "throughput": 2488.85, "total_tokens": 1290384}
589
+ {"current_steps": 2855, "total_steps": 3160, "loss": 0.1043, "lr": 1.4146675069466403e-06, "epoch": 18.069620253164558, "percentage": 90.35, "elapsed_time": "0:08:39", "remaining_time": "0:00:55", "throughput": 2489.17, "total_tokens": 1292592}
590
+ {"current_steps": 2860, "total_steps": 3160, "loss": 0.0525, "lr": 1.369237543152016e-06, "epoch": 18.10126582278481, "percentage": 90.51, "elapsed_time": "0:08:40", "remaining_time": "0:00:54", "throughput": 2489.01, "total_tokens": 1294864}
591
+ {"current_steps": 2865, "total_steps": 3160, "loss": 0.0617, "lr": 1.3245284497695993e-06, "epoch": 18.132911392405063, "percentage": 90.66, "elapsed_time": "0:08:41", "remaining_time": "0:00:53", "throughput": 2489.36, "total_tokens": 1297168}