Hanzalwi commited on
Commit
a9ecf64
1 Parent(s): cd0341d

Training in progress, step 2100, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:293329d0741cc1856c548d638747a30933f3a1d030ce1cfb5aaa7057b27b2e97
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcabaed6893efa8ef18e367a7c349f30f7459129da1774cae9415a644f7bfc7b
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08d276c8bc8959315bbc1efc9063b98b0ea40f2026efc2282a2d4bce72dd49a1
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b650644f03d39399c2028cd9c8ada111e6d80bc59e58a3fb5366e9f4fd8ef80
3
  size 18902665
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb50e2bd42723bb54172691df4d73f85a33829b8a1f4dc1ca27fee83c3724b7c
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8665825c42a3d9f7e4d6ea045efe267b7c691410421807dc2f776850b81af2bb
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1238b3bfa75e49a19396161e9e7b72ab89cdd1a3f63b51c0ab4d6e8d216c5a5
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.3689783811569214,
3
- "best_model_checkpoint": "./outputs/checkpoint-2000",
4
- "epoch": 2.6666666666666665,
5
  "eval_steps": 100,
6
- "global_step": 2000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -287,6 +287,20 @@
287
  "eval_samples_per_second": 15.548,
288
  "eval_steps_per_second": 1.95,
289
  "step": 2000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
290
  }
291
  ],
292
  "logging_steps": 100,
@@ -294,7 +308,7 @@
294
  "num_input_tokens_seen": 0,
295
  "num_train_epochs": 3,
296
  "save_steps": 100,
297
- "total_flos": 1.1694767356919808e+17,
298
  "trial_name": null,
299
  "trial_params": null
300
  }
 
1
  {
2
+ "best_metric": 1.364682912826538,
3
+ "best_model_checkpoint": "./outputs/checkpoint-2100",
4
+ "epoch": 2.8,
5
  "eval_steps": 100,
6
+ "global_step": 2100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
287
  "eval_samples_per_second": 15.548,
288
  "eval_steps_per_second": 1.95,
289
  "step": 2000
290
+ },
291
+ {
292
+ "epoch": 2.8,
293
+ "learning_rate": 0.0002,
294
+ "loss": 1.1343,
295
+ "step": 2100
296
+ },
297
+ {
298
+ "epoch": 2.8,
299
+ "eval_loss": 1.364682912826538,
300
+ "eval_runtime": 93.3562,
301
+ "eval_samples_per_second": 15.543,
302
+ "eval_steps_per_second": 1.95,
303
+ "step": 2100
304
  }
305
  ],
306
  "logging_steps": 100,
 
308
  "num_input_tokens_seen": 0,
309
  "num_train_epochs": 3,
310
  "save_steps": 100,
311
+ "total_flos": 1.2278575092252672e+17,
312
  "trial_name": null,
313
  "trial_params": null
314
  }