TachyHealthResearch commited on
Commit
10d5fab
·
1 Parent(s): 1d53e0d

Training in progress, step 60, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22660376d335aa7c59ae2006d76a706940c8aef4af7c011c7e7d2abeea1a39af
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e7e060c76e33b4ea8f472bc3ffe35c3c89700f29dc8ddf1785b36bfc5783f0d
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99711f18552ca634897d88e6cf50fb107c5ac591d8d935086635c8d58ba450dc
3
  size 63350356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d9a325ae4a57eb8dda64125b9bda977c4f29163f541340e3166315d367c30e7
3
  size 63350356
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47f6661d5d07de5b2df0d6c9e638f52a46b71c0872bae5b8e7ca87f35bf01fa4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78da1da061288012ca67a39eca3ceec230fb3877f3be89de615db089beb7984c
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa5dbfbb9e4d48e480300700a77d16d14549c19a56fbfb81fe15f5b2fffbce24
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0f02c8a54d03bd9dfb0939ad3018ed1dc368b994677a1af7e7d58a0b3322f4b
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.02,
5
  "eval_steps": 1000,
6
- "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -307,13 +307,73 @@
307
  "learning_rate": 0.00013605442176870748,
308
  "loss": 1.3797,
309
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
310
  }
311
  ],
312
  "logging_steps": 1,
313
  "max_steps": 150,
314
  "num_train_epochs": 1,
315
  "save_steps": 5,
316
- "total_flos": 5737824304988160.0,
317
  "trial_name": null,
318
  "trial_params": null
319
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.024,
5
  "eval_steps": 1000,
6
+ "global_step": 60,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
307
  "learning_rate": 0.00013605442176870748,
308
  "loss": 1.3797,
309
  "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.02,
313
+ "learning_rate": 0.0001346938775510204,
314
+ "loss": 1.7408,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.02,
319
+ "learning_rate": 0.00013333333333333334,
320
+ "loss": 1.6008,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.02,
325
+ "learning_rate": 0.00013197278911564626,
326
+ "loss": 1.5121,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.02,
331
+ "learning_rate": 0.00013061224489795917,
332
+ "loss": 1.3599,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.02,
337
+ "learning_rate": 0.00012925170068027212,
338
+ "loss": 1.4465,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.02,
343
+ "learning_rate": 0.00012789115646258506,
344
+ "loss": 1.6332,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.02,
349
+ "learning_rate": 0.00012653061224489798,
350
+ "loss": 1.6305,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.02,
355
+ "learning_rate": 0.0001251700680272109,
356
+ "loss": 1.5599,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.02,
361
+ "learning_rate": 0.0001238095238095238,
362
+ "loss": 1.8265,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.02,
367
+ "learning_rate": 0.00012244897959183676,
368
+ "loss": 1.7149,
369
+ "step": 60
370
  }
371
  ],
372
  "logging_steps": 1,
373
  "max_steps": 150,
374
  "num_train_epochs": 1,
375
  "save_steps": 5,
376
+ "total_flos": 6638833090068480.0,
377
  "trial_name": null,
378
  "trial_params": null
379
  }