auxyus commited on
Commit
a60ef9d
·
verified ·
1 Parent(s): 5da604a

Training in progress, step 99, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:922633770e20a9bd5656be2419109555ce79eddfb692cda47a1deb6ef05e6a07
3
  size 119801528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0738cb1ec19eba7735f6d9f6d9c768c3927bb5311f8f1116c3baae0946a1d4bb
3
  size 119801528
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:82c494764f3a58fa0dcfcffedb9b743070f882a3ad1c7f815e5d59e98a0cf21f
3
  size 61392180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38f2e693578186bca673d66a96f10cb935ae0c1e5abbd0aad06a0f85c21bf58f
3
  size 61392180
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:299c2a5dee9014b1d317f23971e89df11f84eb593c90763d8431d0400db79ba5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:337d7d0d639a0bb50bd9f1cb682c4eb015b37015e99559747139ae978eb00aa0
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43444b0a2aaeda40531bf13a694e8a3eeeb489f81435e9521c012609a5be4dc4
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": 0.20466173962478681,
5
  "eval_steps": 9,
6
- "global_step": 90,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -305,6 +305,35 @@
305
  "eval_samples_per_second": 20.624,
306
  "eval_steps_per_second": 2.588,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 5.39020770630697e+16,
328
  "train_batch_size": 8,
329
  "trial_name": null,
330
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.2251279135872655,
5
  "eval_steps": 9,
6
+ "global_step": 99,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
305
  "eval_samples_per_second": 20.624,
306
  "eval_steps_per_second": 2.588,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.2114837976122797,
311
+ "grad_norm": 0.4519857168197632,
312
+ "learning_rate": 1.4852136862001764e-06,
313
+ "loss": 1.394,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.21830585559977259,
318
+ "grad_norm": 0.6549511551856995,
319
+ "learning_rate": 4.865965629214819e-07,
320
+ "loss": 1.6634,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.2251279135872655,
325
+ "grad_norm": 0.3595646619796753,
326
+ "learning_rate": 3.04586490452119e-08,
327
+ "loss": 1.9199,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.2251279135872655,
332
+ "eval_loss": 1.6768484115600586,
333
+ "eval_runtime": 35.9594,
334
+ "eval_samples_per_second": 20.607,
335
+ "eval_steps_per_second": 2.586,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 5.955421302108979e+16,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null