auxyus commited on
Commit
87d3009
·
verified ·
1 Parent(s): 52f8129

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:bf48441b08c53faf26416b92e6cf27759e05864c554d9121e1376695c9dfe4dd
3
  size 125918320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f4eaa606d55b5fe4be1afa42144ddf19f58b4f71c074a700dc6b500cb822876
3
  size 125918320
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d28092ae4ba860e9ee59f87ecfa7652da3e4dbd57981fa1b69303f06c5db5542
3
  size 64683604
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5cb844d77e153849473e951ffaa2ec74b6ae0ec9ee1b750d56d98bc807582bf
3
  size 64683604
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24ed531d47d9748066003ce04a655430b7139ae911545d5e2ef089a3ca71f5bf
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d418c60342ae0fb2e1e1281bc58b64184d3379e8c3817b87d96da1c05389f215
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": 0.034123222748815164,
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": 7.849,
306
  "eval_steps_per_second": 0.982,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 2.4195435926755738e+17,
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": 0.03753554502369668,
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": 7.849,
306
  "eval_steps_per_second": 0.982,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.035260663507109005,
311
+ "grad_norm": 3.7425358295440674,
312
+ "learning_rate": 1.4852136862001764e-06,
313
+ "loss": 1.9,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.036398104265402846,
318
+ "grad_norm": 3.9407403469085693,
319
+ "learning_rate": 4.865965629214819e-07,
320
+ "loss": 1.9243,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.03753554502369668,
325
+ "grad_norm": 3.88885760307312,
326
+ "learning_rate": 3.04586490452119e-08,
327
+ "loss": 1.9794,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.03753554502369668,
332
+ "eval_loss": 0.4799988865852356,
333
+ "eval_runtime": 565.6344,
334
+ "eval_samples_per_second": 7.853,
335
+ "eval_steps_per_second": 0.983,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 2.6599302131141837e+17,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null