rbelanec commited on
Commit
4ac5478
·
verified ·
1 Parent(s): 97b80cf

Training in progress, step 1350

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. trainer_log.jsonl +24 -0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c188fc63bbb131a8476cae6f99f9ace622cc6e99dd61c04b1b4651729ff1671
3
  size 58745928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25ee9022fdd3e9466b208ba0dc7da9cbc8e833246b4e8d575a0adfb7ffa1c6cf
3
  size 58745928
trainer_log.jsonl CHANGED
@@ -274,3 +274,27 @@
274
  {"current_steps": 1300, "total_steps": 1800, "loss": 0.0, "lr": 1.0899836048749645e-05, "epoch": 14.444444444444445, "percentage": 72.22, "elapsed_time": "0:04:57", "remaining_time": "0:01:54", "throughput": 1372.93, "total_tokens": 407776}
275
  {"current_steps": 1305, "total_steps": 1800, "loss": 0.0, "lr": 1.0700329641296541e-05, "epoch": 14.5, "percentage": 72.5, "elapsed_time": "0:04:58", "remaining_time": "0:01:53", "throughput": 1373.51, "total_tokens": 409312}
276
  {"current_steps": 1310, "total_steps": 1800, "loss": 0.0, "lr": 1.0502167645744895e-05, "epoch": 14.555555555555555, "percentage": 72.78, "elapsed_time": "0:04:59", "remaining_time": "0:01:51", "throughput": 1373.96, "total_tokens": 410816}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
274
  {"current_steps": 1300, "total_steps": 1800, "loss": 0.0, "lr": 1.0899836048749645e-05, "epoch": 14.444444444444445, "percentage": 72.22, "elapsed_time": "0:04:57", "remaining_time": "0:01:54", "throughput": 1372.93, "total_tokens": 407776}
275
  {"current_steps": 1305, "total_steps": 1800, "loss": 0.0, "lr": 1.0700329641296541e-05, "epoch": 14.5, "percentage": 72.5, "elapsed_time": "0:04:58", "remaining_time": "0:01:53", "throughput": 1373.51, "total_tokens": 409312}
276
  {"current_steps": 1310, "total_steps": 1800, "loss": 0.0, "lr": 1.0502167645744895e-05, "epoch": 14.555555555555555, "percentage": 72.78, "elapsed_time": "0:04:59", "remaining_time": "0:01:51", "throughput": 1373.96, "total_tokens": 410816}
277
+ {"current_steps": 1315, "total_steps": 1800, "loss": 0.0, "lr": 1.0305368692688174e-05, "epoch": 14.61111111111111, "percentage": 73.06, "elapsed_time": "0:05:00", "remaining_time": "0:01:50", "throughput": 1374.66, "total_tokens": 412416}
278
+ {"current_steps": 1320, "total_steps": 1800, "loss": 0.0, "lr": 1.01099512845707e-05, "epoch": 14.666666666666666, "percentage": 73.33, "elapsed_time": "0:05:01", "remaining_time": "0:01:49", "throughput": 1375.4, "total_tokens": 414016}
279
+ {"current_steps": 1325, "total_steps": 1800, "loss": 0.0, "lr": 9.91593379394811e-06, "epoch": 14.722222222222221, "percentage": 73.61, "elapsed_time": "0:05:01", "remaining_time": "0:01:48", "throughput": 1376.02, "total_tokens": 415552}
280
+ {"current_steps": 1330, "total_steps": 1800, "loss": 0.0, "lr": 9.723334461760006e-06, "epoch": 14.777777777777779, "percentage": 73.89, "elapsed_time": "0:05:02", "remaining_time": "0:01:47", "throughput": 1376.61, "total_tokens": 417088}
281
+ {"current_steps": 1335, "total_steps": 1800, "loss": 0.0, "lr": 9.532171395615036e-06, "epoch": 14.833333333333334, "percentage": 74.17, "elapsed_time": "0:05:03", "remaining_time": "0:01:45", "throughput": 1377.27, "total_tokens": 418656}
282
+ {"current_steps": 1340, "total_steps": 1800, "loss": 0.0, "lr": 9.342462568088416e-06, "epoch": 14.88888888888889, "percentage": 74.44, "elapsed_time": "0:05:04", "remaining_time": "0:01:44", "throughput": 1377.96, "total_tokens": 420256}
283
+ {"current_steps": 1345, "total_steps": 1800, "loss": 0.0, "lr": 9.154225815032242e-06, "epoch": 14.944444444444445, "percentage": 74.72, "elapsed_time": "0:05:05", "remaining_time": "0:01:43", "throughput": 1378.5, "total_tokens": 421792}
284
+ {"current_steps": 1350, "total_steps": 1800, "loss": 0.0, "lr": 8.967478833898612e-06, "epoch": 15.0, "percentage": 75.0, "elapsed_time": "0:05:07", "remaining_time": "0:01:42", "throughput": 1378.99, "total_tokens": 423360}
285
+ {"current_steps": 1350, "total_steps": 1800, "eval_loss": 0.09843109548091888, "epoch": 15.0, "percentage": 75.0, "elapsed_time": "0:05:07", "remaining_time": "0:01:42", "throughput": 1376.29, "total_tokens": 423360}
286
+ {"current_steps": 1355, "total_steps": 1800, "loss": 0.0, "lr": 8.78223918207575e-06, "epoch": 15.055555555555555, "percentage": 75.28, "elapsed_time": "0:05:09", "remaining_time": "0:01:41", "throughput": 1371.14, "total_tokens": 424992}
287
+ {"current_steps": 1360, "total_steps": 1800, "loss": 0.0, "lr": 8.598524275237322e-06, "epoch": 15.11111111111111, "percentage": 75.56, "elapsed_time": "0:05:10", "remaining_time": "0:01:40", "throughput": 1371.62, "total_tokens": 426528}
288
+ {"current_steps": 1365, "total_steps": 1800, "loss": 0.0, "lr": 8.41635138570507e-06, "epoch": 15.166666666666666, "percentage": 75.83, "elapsed_time": "0:05:11", "remaining_time": "0:01:39", "throughput": 1372.2, "total_tokens": 428096}
289
+ {"current_steps": 1370, "total_steps": 1800, "loss": 0.0, "lr": 8.235737640824908e-06, "epoch": 15.222222222222221, "percentage": 76.11, "elapsed_time": "0:05:12", "remaining_time": "0:01:38", "throughput": 1372.58, "total_tokens": 429600}
290
+ {"current_steps": 1375, "total_steps": 1800, "loss": 0.0, "lr": 8.056700021356694e-06, "epoch": 15.277777777777779, "percentage": 76.39, "elapsed_time": "0:05:14", "remaining_time": "0:01:37", "throughput": 1371.67, "total_tokens": 431200}
291
+ {"current_steps": 1380, "total_steps": 1800, "loss": 0.0, "lr": 7.879255359877705e-06, "epoch": 15.333333333333334, "percentage": 76.67, "elapsed_time": "0:05:15", "remaining_time": "0:01:35", "throughput": 1372.18, "total_tokens": 432736}
292
+ {"current_steps": 1385, "total_steps": 1800, "loss": 0.0, "lr": 7.703420339200101e-06, "epoch": 15.38888888888889, "percentage": 76.94, "elapsed_time": "0:05:16", "remaining_time": "0:01:34", "throughput": 1372.85, "total_tokens": 434336}
293
+ {"current_steps": 1390, "total_steps": 1800, "loss": 0.0, "lr": 7.529211490802498e-06, "epoch": 15.444444444444445, "percentage": 77.22, "elapsed_time": "0:05:17", "remaining_time": "0:01:33", "throughput": 1373.48, "total_tokens": 435904}
294
+ {"current_steps": 1395, "total_steps": 1800, "loss": 0.0, "lr": 7.3566451932756744e-06, "epoch": 15.5, "percentage": 77.5, "elapsed_time": "0:05:18", "remaining_time": "0:01:32", "throughput": 1373.99, "total_tokens": 437440}
295
+ {"current_steps": 1400, "total_steps": 1800, "loss": 0.0, "lr": 7.185737670782727e-06, "epoch": 15.555555555555555, "percentage": 77.78, "elapsed_time": "0:05:19", "remaining_time": "0:01:31", "throughput": 1374.5, "total_tokens": 438976}
296
+ {"current_steps": 1405, "total_steps": 1800, "loss": 0.0, "lr": 7.016504991533726e-06, "epoch": 15.61111111111111, "percentage": 78.06, "elapsed_time": "0:05:20", "remaining_time": "0:01:30", "throughput": 1374.97, "total_tokens": 440512}
297
+ {"current_steps": 1410, "total_steps": 1800, "loss": 0.0, "lr": 6.848963066275027e-06, "epoch": 15.666666666666666, "percentage": 78.33, "elapsed_time": "0:05:21", "remaining_time": "0:01:28", "throughput": 1375.63, "total_tokens": 442112}
298
+ {"current_steps": 1415, "total_steps": 1800, "loss": 0.0, "lr": 6.683127646793411e-06, "epoch": 15.722222222222221, "percentage": 78.61, "elapsed_time": "0:05:22", "remaining_time": "0:01:27", "throughput": 1375.98, "total_tokens": 443616}
299
+ {"current_steps": 1420, "total_steps": 1800, "loss": 0.0, "lr": 6.519014324435102e-06, "epoch": 15.777777777777779, "percentage": 78.89, "elapsed_time": "0:05:23", "remaining_time": "0:01:26", "throughput": 1376.53, "total_tokens": 445184}
300
+ {"current_steps": 1425, "total_steps": 1800, "loss": 0.0, "lr": 6.356638528639955e-06, "epoch": 15.833333333333334, "percentage": 79.17, "elapsed_time": "0:05:24", "remaining_time": "0:01:25", "throughput": 1377.1, "total_tokens": 446752}