rbelanec commited on
Commit
3097690
·
verified ·
1 Parent(s): adce554

Training in progress, step 2490

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. trainer_log.jsonl +21 -0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4cc2f9e4c8cc94a17bc6eb491ce8ac514192598f2b007067da3d4063e270d1bd
3
  size 8388736
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3a5d458e566297e9d60fe09cca5dd18ebdf5ae8c633e447714e689cef395909
3
  size 8388736
trainer_log.jsonl CHANGED
@@ -495,3 +495,24 @@
495
  {"current_steps": 2380, "total_steps": 2490, "loss": 0.3326, "lr": 3.020615880420713e-07, "epoch": 9.558232931726907, "percentage": 95.58, "elapsed_time": "0:04:06", "remaining_time": "0:00:11", "throughput": 1698.3, "total_tokens": 418400}
496
  {"current_steps": 2385, "total_steps": 2490, "loss": 0.3449, "lr": 2.7551070247990305e-07, "epoch": 9.578313253012048, "percentage": 95.78, "elapsed_time": "0:04:06", "remaining_time": "0:00:10", "throughput": 1698.89, "total_tokens": 419248}
497
  {"current_steps": 2390, "total_steps": 2490, "loss": 0.3481, "lr": 2.501745520509552e-07, "epoch": 9.598393574297189, "percentage": 95.98, "elapsed_time": "0:04:07", "remaining_time": "0:00:10", "throughput": 1699.53, "total_tokens": 420096}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
495
  {"current_steps": 2380, "total_steps": 2490, "loss": 0.3326, "lr": 3.020615880420713e-07, "epoch": 9.558232931726907, "percentage": 95.58, "elapsed_time": "0:04:06", "remaining_time": "0:00:11", "throughput": 1698.3, "total_tokens": 418400}
496
  {"current_steps": 2385, "total_steps": 2490, "loss": 0.3449, "lr": 2.7551070247990305e-07, "epoch": 9.578313253012048, "percentage": 95.78, "elapsed_time": "0:04:06", "remaining_time": "0:00:10", "throughput": 1698.89, "total_tokens": 419248}
497
  {"current_steps": 2390, "total_steps": 2490, "loss": 0.3481, "lr": 2.501745520509552e-07, "epoch": 9.598393574297189, "percentage": 95.98, "elapsed_time": "0:04:07", "remaining_time": "0:00:10", "throughput": 1699.53, "total_tokens": 420096}
498
+ {"current_steps": 2395, "total_steps": 2490, "loss": 0.3386, "lr": 2.2605438154179038e-07, "epoch": 9.61847389558233, "percentage": 96.18, "elapsed_time": "0:04:07", "remaining_time": "0:00:09", "throughput": 1699.77, "total_tokens": 420848}
499
+ {"current_steps": 2400, "total_steps": 2490, "loss": 0.3294, "lr": 2.0315137599685174e-07, "epoch": 9.638554216867469, "percentage": 96.39, "elapsed_time": "0:04:07", "remaining_time": "0:00:09", "throughput": 1700.53, "total_tokens": 421728}
500
+ {"current_steps": 2405, "total_steps": 2490, "loss": 0.3604, "lr": 1.814666606602261e-07, "epoch": 9.65863453815261, "percentage": 96.59, "elapsed_time": "0:04:08", "remaining_time": "0:00:08", "throughput": 1701.45, "total_tokens": 422656}
501
+ {"current_steps": 2410, "total_steps": 2490, "loss": 0.3457, "lr": 1.6100130092037703e-07, "epoch": 9.67871485943775, "percentage": 96.79, "elapsed_time": "0:04:08", "remaining_time": "0:00:08", "throughput": 1702.45, "total_tokens": 423600}
502
+ {"current_steps": 2415, "total_steps": 2490, "loss": 0.3447, "lr": 1.4175630225778947e-07, "epoch": 9.698795180722891, "percentage": 96.99, "elapsed_time": "0:04:09", "remaining_time": "0:00:07", "throughput": 1703.09, "total_tokens": 424448}
503
+ {"current_steps": 2420, "total_steps": 2490, "loss": 0.3544, "lr": 1.237326101955677e-07, "epoch": 9.718875502008032, "percentage": 97.19, "elapsed_time": "0:04:09", "remaining_time": "0:00:07", "throughput": 1704.91, "total_tokens": 425632}
504
+ {"current_steps": 2425, "total_steps": 2490, "loss": 0.3385, "lr": 1.0693111025300017e-07, "epoch": 9.738955823293173, "percentage": 97.39, "elapsed_time": "0:04:10", "remaining_time": "0:00:06", "throughput": 1705.86, "total_tokens": 426576}
505
+ {"current_steps": 2430, "total_steps": 2490, "loss": 0.3296, "lr": 9.13526279020277e-08, "epoch": 9.759036144578314, "percentage": 97.59, "elapsed_time": "0:04:10", "remaining_time": "0:00:06", "throughput": 1706.3, "total_tokens": 427376}
506
+ {"current_steps": 2435, "total_steps": 2490, "loss": 0.3514, "lr": 7.699792852670362e-08, "epoch": 9.779116465863455, "percentage": 97.79, "elapsed_time": "0:04:10", "remaining_time": "0:00:05", "throughput": 1707.06, "total_tokens": 428256}
507
+ {"current_steps": 2440, "total_steps": 2490, "loss": 0.3389, "lr": 6.386771738558506e-08, "epoch": 9.799196787148594, "percentage": 97.99, "elapsed_time": "0:04:11", "remaining_time": "0:00:05", "throughput": 1708.13, "total_tokens": 429216}
508
+ {"current_steps": 2445, "total_steps": 2490, "loss": 0.3542, "lr": 5.196263957708836e-08, "epoch": 9.819277108433734, "percentage": 98.19, "elapsed_time": "0:04:11", "remaining_time": "0:00:04", "throughput": 1709.26, "total_tokens": 430208}
509
+ {"current_steps": 2450, "total_steps": 2490, "loss": 0.3292, "lr": 4.1283280007778366e-08, "epoch": 9.839357429718875, "percentage": 98.39, "elapsed_time": "0:04:12", "remaining_time": "0:00:04", "throughput": 1709.51, "total_tokens": 430960}
510
+ {"current_steps": 2455, "total_steps": 2490, "loss": 0.355, "lr": 3.1830163363655296e-08, "epoch": 9.859437751004016, "percentage": 98.59, "elapsed_time": "0:04:12", "remaining_time": "0:00:03", "throughput": 1710.64, "total_tokens": 431936}
511
+ {"current_steps": 2460, "total_steps": 2490, "loss": 0.3425, "lr": 2.3603754084358663e-08, "epoch": 9.879518072289157, "percentage": 98.8, "elapsed_time": "0:04:12", "remaining_time": "0:00:03", "throughput": 1711.74, "total_tokens": 432912}
512
+ {"current_steps": 2465, "total_steps": 2490, "loss": 0.3449, "lr": 1.6604456340352235e-08, "epoch": 9.899598393574298, "percentage": 99.0, "elapsed_time": "0:04:13", "remaining_time": "0:00:02", "throughput": 1712.11, "total_tokens": 433696}
513
+ {"current_steps": 2470, "total_steps": 2490, "loss": 0.3513, "lr": 1.0832614013073228e-08, "epoch": 9.919678714859439, "percentage": 99.2, "elapsed_time": "0:04:13", "remaining_time": "0:00:02", "throughput": 1712.67, "total_tokens": 434528}
514
+ {"current_steps": 2475, "total_steps": 2490, "loss": 0.3633, "lr": 6.288510678031934e-09, "epoch": 9.939759036144578, "percentage": 99.4, "elapsed_time": "0:04:14", "remaining_time": "0:00:01", "throughput": 1712.91, "total_tokens": 435280}
515
+ {"current_steps": 2480, "total_steps": 2490, "loss": 0.3483, "lr": 2.972369590878432e-09, "epoch": 9.959839357429718, "percentage": 99.6, "elapsed_time": "0:04:14", "remaining_time": "0:00:01", "throughput": 1713.4, "total_tokens": 436096}
516
+ {"current_steps": 2485, "total_steps": 2490, "loss": 0.3521, "lr": 8.843536764419069e-10, "epoch": 9.97991967871486, "percentage": 99.8, "elapsed_time": "0:04:14", "remaining_time": "0:00:00", "throughput": 1714.28, "total_tokens": 437008}
517
+ {"current_steps": 2490, "total_steps": 2490, "loss": 0.3294, "lr": 2.4565520709285417e-11, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:04:15", "remaining_time": "0:00:00", "throughput": 1713.86, "total_tokens": 437760}
518
+ {"current_steps": 2490, "total_steps": 2490, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:04:16", "remaining_time": "0:00:00", "throughput": 1705.85, "total_tokens": 437760}