mamung commited on
Commit
78ed8a1
·
verified ·
1 Parent(s): ad46f42

Training in progress, step 72, 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:eb21bf989f86c1250694c521911a5c4e807f15873a4a1149177d7e4ed7477774
3
  size 500770656
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a1a22bac447f521541000ddb6b6e0e8ac4d6b303cdfc9f48951f1c83b8e5fcd
3
  size 500770656
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b9000026ffc303174b533a7b3a182a4746ea9e6a9d18ef6c3882c6f50c20fae
3
  size 1001863522
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3317b15544592a0c20ef65c5ac64d41e4f81ac0cd743c47fd45c0fd04c6b820f
3
  size 1001863522
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f473197e3945b712b588c91a49e61dd14ca66a40e94039d856a91e5cc8f0b34
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07073a90bdf3e732061566c5b42d050f1b26b432d530817aa7e81ebe9cdc3fda
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03b2d2818ab3151c9ed744a4cb682fe1730b800005846a54cc3da941ac8ce20d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f9245597e5014ecf432f2646dbac4f88c26cbc6ab1676ee7be71281b45d826d
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": 1.8277727682596934,
5
  "eval_steps": 9,
6
- "global_step": 63,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -218,6 +218,35 @@
218
  "eval_samples_per_second": 1.848,
219
  "eval_steps_per_second": 0.932,
220
  "step": 63
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
221
  }
222
  ],
223
  "logging_steps": 3,
@@ -237,7 +266,7 @@
237
  "attributes": {}
238
  }
239
  },
240
- "total_flos": 6.4296214069248e+17,
241
  "train_batch_size": 2,
242
  "trial_name": null,
243
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 2.097385031559964,
5
  "eval_steps": 9,
6
+ "global_step": 72,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
218
  "eval_samples_per_second": 1.848,
219
  "eval_steps_per_second": 0.932,
220
  "step": 63
221
+ },
222
+ {
223
+ "epoch": 1.914337240757439,
224
+ "grad_norm": 9.028271675109863,
225
+ "learning_rate": 7.66554636144095e-05,
226
+ "loss": 40.7417,
227
+ "step": 66
228
+ },
229
+ {
230
+ "epoch": 2.010820559062218,
231
+ "grad_norm": 9.204501152038574,
232
+ "learning_rate": 6.538829429225069e-05,
233
+ "loss": 41.2274,
234
+ "step": 69
235
+ },
236
+ {
237
+ "epoch": 2.097385031559964,
238
+ "grad_norm": 9.566389083862305,
239
+ "learning_rate": 5.4600950026045326e-05,
240
+ "loss": 37.3547,
241
+ "step": 72
242
+ },
243
+ {
244
+ "epoch": 2.097385031559964,
245
+ "eval_loss": 1.3545383214950562,
246
+ "eval_runtime": 63.2718,
247
+ "eval_samples_per_second": 1.849,
248
+ "eval_steps_per_second": 0.932,
249
+ "step": 72
250
  }
251
  ],
252
  "logging_steps": 3,
 
266
  "attributes": {}
267
  }
268
  },
269
+ "total_flos": 7.3481387507712e+17,
270
  "train_batch_size": 2,
271
  "trial_name": null,
272
  "trial_params": null