flytech commited on
Commit
9d9ae8e
·
1 Parent(s): c7cde00

Training in progress, step 120, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:388e352e490c7c07c63732e2b742baa0a969730393d5a2bf201812e0b31feda9
3
  size 40036040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f69bce4cc58bbdb4323c3c3550fa2115444ee354e82ae39b92b8d8905afca073
3
  size 40036040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9e5bf96fdf048e33cfee7751db160fd1f2699828fb4c237a2411e9f8b1338b7
3
  size 20523679
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3cb0ae8b0b925a5af2d8fc2210ee367e753d3a1353a63aa682106d8fafa7fbb
3
  size 20523679
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61a77da5f8afb832d0ec049d33138c45da3fedbbc97d06ece6bd28476b8acaa8
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5111b5dea332c1cd30e5870ce7258f151150fd53dd88928b6856d5be7edf3d46
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0262ad1fd2065e06b394e89a7d49732da015d3f50d2a7d8b2a4ac8f4b299d5c9
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49b9a13b0ac3118ed00c8e97345502f26f83f63898783cc817ebe103e6695bb7
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.17777777777777778,
5
  "eval_steps": 60,
6
- "global_step": 60,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -20,13 +20,26 @@
20
  "eval_samples_per_second": 1.914,
21
  "eval_steps_per_second": 0.239,
22
  "step": 60
 
 
 
 
 
 
 
 
 
 
 
 
 
23
  }
24
  ],
25
  "logging_steps": 60,
26
  "max_steps": 1011,
27
  "num_train_epochs": 3,
28
  "save_steps": 60,
29
- "total_flos": 9966064930652160.0,
30
  "trial_name": null,
31
  "trial_params": null
32
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.35555555555555557,
5
  "eval_steps": 60,
6
+ "global_step": 120,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
20
  "eval_samples_per_second": 1.914,
21
  "eval_steps_per_second": 0.239,
22
  "step": 60
23
+ },
24
+ {
25
+ "epoch": 0.36,
26
+ "learning_rate": 0.0002,
27
+ "loss": 0.6736,
28
+ "step": 120
29
+ },
30
+ {
31
+ "epoch": 0.36,
32
+ "eval_runtime": 313.3616,
33
+ "eval_samples_per_second": 1.915,
34
+ "eval_steps_per_second": 0.239,
35
+ "step": 120
36
  }
37
  ],
38
  "logging_steps": 60,
39
  "max_steps": 1011,
40
  "num_train_epochs": 3,
41
  "save_steps": 60,
42
+ "total_flos": 1.993212986130432e+16,
43
  "trial_name": null,
44
  "trial_params": null
45
  }