TachyHealthResearch commited on
Commit
699abf7
·
1 Parent(s): 04bcde7

Training in progress, step 55, 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:b7aa8a98b6e70791a74e60e208c3ac40c8361199195dd54e893d808393c784d3
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0e0eb082c4f1dd4257fbf614281eb38ae5666f2324f7454c80b6d28a83f8a9a
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:04c7916ae0a42a86555408ab18196278c14a6105644f0d14991b727630eb3e96
3
  size 63350356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2bd466ee16f91e3e98e56a76339242f278026071594a9e25971dba5bdd7a306
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:bd7553ed48fb9af9185475a0992950d3f88e91369c31402fc9b619ffc0bfb053
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:665ffd1cb27f6d4a3bbab7649499cc3101941b8519900e461c1e61f814d0ed81
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30f8e86cd65221b2d68c30f7fa44bf055b87fd8f319383787431dfc91b0128d9
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ff4b774c2195b377ebcd6befd4adf040c7c0761573dd4fd2f6253d5f4f39124
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": 0.018,
5
  "eval_steps": 1000,
6
- "global_step": 45,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -277,13 +277,73 @@
277
  "learning_rate": 0.0001134020618556701,
278
  "loss": 1.8157,
279
  "step": 45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
280
  }
281
  ],
282
  "logging_steps": 1,
283
  "max_steps": 100,
284
  "num_train_epochs": 1,
285
  "save_steps": 5,
286
- "total_flos": 5322104911872000.0,
287
  "trial_name": null,
288
  "trial_params": null
289
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.022,
5
  "eval_steps": 1000,
6
+ "global_step": 55,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
277
  "learning_rate": 0.0001134020618556701,
278
  "loss": 1.8157,
279
  "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.02,
283
+ "learning_rate": 0.00011134020618556702,
284
+ "loss": 1.436,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.02,
289
+ "learning_rate": 0.00010927835051546391,
290
+ "loss": 1.8154,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.02,
295
+ "learning_rate": 0.00010721649484536083,
296
+ "loss": 1.5157,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.02,
301
+ "learning_rate": 0.00010515463917525774,
302
+ "loss": 1.7832,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.02,
307
+ "learning_rate": 0.00010309278350515463,
308
+ "loss": 1.3788,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.02,
313
+ "learning_rate": 0.00010103092783505155,
314
+ "loss": 1.7474,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.02,
319
+ "learning_rate": 9.896907216494846e-05,
320
+ "loss": 1.6072,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.02,
325
+ "learning_rate": 9.690721649484537e-05,
326
+ "loss": 1.5144,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.02,
331
+ "learning_rate": 9.484536082474227e-05,
332
+ "loss": 1.3593,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.02,
337
+ "learning_rate": 9.278350515463918e-05,
338
+ "loss": 1.4519,
339
+ "step": 55
340
  }
341
  ],
342
  "logging_steps": 1,
343
  "max_steps": 100,
344
  "num_train_epochs": 1,
345
  "save_steps": 5,
346
+ "total_flos": 6122623698616320.0,
347
  "trial_name": null,
348
  "trial_params": null
349
  }