mgh6 commited on
Commit
e5860dd
·
verified ·
1 Parent(s): 01b55cf

Training in progress, epoch 9, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8dabb6381d952326c916117be53ef1632bcb8adcf5513d34c49ab5dc703c54e
3
  size 2708729576
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f033c90df504f6c4972eba991929a6421a54945f068503730b752f96b531eb0
3
  size 2708729576
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4555c70942753f71d1b1e4a42b999ef15aebf24c06f2a43463e0b20ae30a0caa
3
  size 52499200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ace64f2844fe7a82dd3119734be8296f7f20ef3dbfcfd3ae2940ccbb4edb319
3
  size 52499200
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:335263bbdf55dec07c081046e09f117f40eceefa6f3b02ab74e94e4a08e084ac
3
  size 15006
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bb8d68660a612d8ec9c8c416aefe8428f3513be5c4861a31d9b4fa8efd65694
3
  size 15006
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17d282d44e6a12e9ca82ec6b42e7f212659678f5fe8c9a58e24a30599040d3e5
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c42147d2487e975dcb8b015449194c61c9350b5c1b3a114ecd6e3942d3403969
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": 9.0,
5
  "eval_steps": 50,
6
- "global_step": 1161,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -329,6 +329,34 @@
329
  "eval_samples_per_second": 21.988,
330
  "eval_steps_per_second": 5.497,
331
  "step": 1150
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
332
  }
333
  ],
334
  "logging_steps": 50,
@@ -343,7 +371,7 @@
343
  "should_evaluate": false,
344
  "should_log": false,
345
  "should_save": true,
346
- "should_training_stop": false
347
  },
348
  "attributes": {}
349
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 9.929233772571987,
5
  "eval_steps": 50,
6
+ "global_step": 1280,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
329
  "eval_samples_per_second": 21.988,
330
  "eval_steps_per_second": 5.497,
331
  "step": 1150
332
+ },
333
+ {
334
+ "epoch": 9.304538799414349,
335
+ "grad_norm": 266.43023681640625,
336
+ "learning_rate": 6.25e-06,
337
+ "loss": 1.049,
338
+ "step": 1200
339
+ },
340
+ {
341
+ "epoch": 9.304538799414349,
342
+ "eval_runtime": 19.6329,
343
+ "eval_samples_per_second": 22.004,
344
+ "eval_steps_per_second": 5.501,
345
+ "step": 1200
346
+ },
347
+ {
348
+ "epoch": 9.694973157637872,
349
+ "grad_norm": 144.0484161376953,
350
+ "learning_rate": 2.3437500000000002e-06,
351
+ "loss": 1.0052,
352
+ "step": 1250
353
+ },
354
+ {
355
+ "epoch": 9.694973157637872,
356
+ "eval_runtime": 19.6249,
357
+ "eval_samples_per_second": 22.013,
358
+ "eval_steps_per_second": 5.503,
359
+ "step": 1250
360
  }
361
  ],
362
  "logging_steps": 50,
 
371
  "should_evaluate": false,
372
  "should_log": false,
373
  "should_save": true,
374
+ "should_training_stop": true
375
  },
376
  "attributes": {}
377
  }