Hanzalwi commited on
Commit
5e8cf45
1 Parent(s): d0f266a

Training in progress, step 2200, 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:ab364c6c93d69b87a2bcb5ab23b2b2f47336dc799e5922e1f20fa34a7a8210c8
3
  size 6304192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a42b3907e7f8aea7846f4b49be6d2858b839b3d23dcafb49a738a9518f21039
3
  size 6304192
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d375ab0412c0efb384db11223526c0934d3212360852c91620bd5073d5a15f1
3
  size 12639429
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2c9ba921ceb3f2538fe002983bc2dd92c2ed87bf8800927bb857bf42aa552fb
3
  size 12639429
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72ca6365dbbc2f86eaa3db35582d2708ce0b1665aa0b50d90a15b774de232618
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f9f6b90727f763e225653866388919108823474c7eb02d67d864e53ff7938d0
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1238b3bfa75e49a19396161e9e7b72ab89cdd1a3f63b51c0ab4d6e8d216c5a5
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e2a7616f99506ce2115c2b51a0c8d6af99dd5ac2b72ef98b701eba7ab661118
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.2366259098052979,
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,
@@ -301,6 +301,20 @@
301
  "eval_samples_per_second": 15.265,
302
  "eval_steps_per_second": 1.914,
303
  "step": 2100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
304
  }
305
  ],
306
  "logging_steps": 100,
@@ -308,7 +322,7 @@
308
  "num_input_tokens_seen": 0,
309
  "num_train_epochs": 3,
310
  "save_steps": 100,
311
- "total_flos": 7.44517848768553e+16,
312
  "trial_name": null,
313
  "trial_params": null
314
  }
 
1
  {
2
+ "best_metric": 1.233094334602356,
3
+ "best_model_checkpoint": "./outputs/checkpoint-2200",
4
+ "epoch": 2.9333333333333336,
5
  "eval_steps": 100,
6
+ "global_step": 2200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
301
  "eval_samples_per_second": 15.265,
302
  "eval_steps_per_second": 1.914,
303
  "step": 2100
304
+ },
305
+ {
306
+ "epoch": 2.93,
307
+ "learning_rate": 0.0002,
308
+ "loss": 1.0592,
309
+ "step": 2200
310
+ },
311
+ {
312
+ "epoch": 2.93,
313
+ "eval_loss": 1.233094334602356,
314
+ "eval_runtime": 126.9974,
315
+ "eval_samples_per_second": 15.197,
316
+ "eval_steps_per_second": 1.906,
317
+ "step": 2200
318
  }
319
  ],
320
  "logging_steps": 100,
 
322
  "num_input_tokens_seen": 0,
323
  "num_train_epochs": 3,
324
  "save_steps": 100,
325
+ "total_flos": 7.800080571706982e+16,
326
  "trial_name": null,
327
  "trial_params": null
328
  }