clarxus commited on
Commit
a02d57d
·
verified ·
1 Parent(s): f61f5f3

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:ddc0eca6c84a110d01eac301f4eb3b325474c0c38d7b00faf9c4adbf0ec0274c
3
  size 2264640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d92ebbef45756bd4e855bfc450d00e6f2d8fdc4cceb2eb8afeca6d7c290f0a4
3
  size 2264640
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e6391ff7be40c1353f6e3c7cf7cffd05020cbfec62f8c7dcc8010f9fad400d00
3
  size 1183674
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8269d11901d8dfddc203815e7064f8e3a42ba33f8584ba5ea0a5be3db1679d6f
3
  size 1183674
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:683579e6a4e531b635154a102854d233c0780acdf55cf1d2eb4d7bfa7e3e8607
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:785cb22f7dae101b2ada102c39c8104abc5b7575c9c0d8d0d07d237969af222c
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b64833e2721bfb57dae2a544bde34ace02492c2f80bfbff48034c9946dc6b4a
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": 0.05349182763744428,
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": 230.073,
306
  "eval_steps_per_second": 28.82,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 1557823896944640.0,
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": 0.058841010401188706,
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": 230.073,
306
  "eval_steps_per_second": 28.82,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.05527488855869242,
311
+ "grad_norm": 2.346513271331787,
312
+ "learning_rate": 7.426068431000882e-07,
313
+ "loss": 3.9167,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.05705794947994056,
318
+ "grad_norm": 2.8069913387298584,
319
+ "learning_rate": 2.4329828146074095e-07,
320
+ "loss": 3.705,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.058841010401188706,
325
+ "grad_norm": 2.7186665534973145,
326
+ "learning_rate": 1.522932452260595e-08,
327
+ "loss": 3.8988,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.058841010401188706,
332
+ "eval_loss": 3.8997690677642822,
333
+ "eval_runtime": 12.3959,
334
+ "eval_samples_per_second": 228.623,
335
+ "eval_steps_per_second": 28.638,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 1713606286639104.0,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null