ramdhanfirdaus commited on
Commit
dedc085
1 Parent(s): 8d8595c

Training in progress, step 200, 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:c4db597585670bdda4120a29b4325b8a1e12d1a0b42214c5db37f578b4de0b4d
3
  size 50338848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0c75b2e3ff637690a7ecbe33171cc0b4bfcae91e962f68b3cb156c9a2fcdd27
3
  size 50338848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e45149a015c2e5778b724d1176260e2e114ac1e99a0c371e7139eaa35753df70
3
  size 100692937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47cae5f20c559a9fa51f9c88a974f02ae3eb88240b4976a3e43c6fa3fd87aa7a
3
  size 100692937
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f02fec353056cad903a43332075b538723a0bfc64a8e822e143d9e4f821bf2c0
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb8f7036efb8a3a0ffb7840b82cd4a522708dd4a2413a602db7d4f3544d8821e
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:216f76b8039f833c337db298c81f13b12082d5fd4f9d866cecd34b2ca7550b37
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.0239477157592773,
3
- "best_model_checkpoint": "./outputs/checkpoint-100",
4
- "epoch": 0.07285974499089254,
5
  "eval_steps": 100,
6
- "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -21,13 +21,27 @@
21
  "eval_samples_per_second": 43.689,
22
  "eval_steps_per_second": 5.466,
23
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
24
  }
25
  ],
26
  "logging_steps": 100,
27
  "max_steps": 4116,
28
  "num_train_epochs": 3,
29
  "save_steps": 100,
30
- "total_flos": 5958555009515520.0,
31
  "trial_name": null,
32
  "trial_params": null
33
  }
 
1
  {
2
+ "best_metric": 1.93068528175354,
3
+ "best_model_checkpoint": "./outputs/checkpoint-200",
4
+ "epoch": 0.14571948998178508,
5
  "eval_steps": 100,
6
+ "global_step": 200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
21
  "eval_samples_per_second": 43.689,
22
  "eval_steps_per_second": 5.466,
23
  "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.15,
27
+ "learning_rate": 0.0002,
28
+ "loss": 1.9736,
29
+ "step": 200
30
+ },
31
+ {
32
+ "epoch": 0.15,
33
+ "eval_loss": 1.93068528175354,
34
+ "eval_runtime": 143.6288,
35
+ "eval_samples_per_second": 43.682,
36
+ "eval_steps_per_second": 5.465,
37
+ "step": 200
38
  }
39
  ],
40
  "logging_steps": 100,
41
  "max_steps": 4116,
42
  "num_train_epochs": 3,
43
  "save_steps": 100,
44
+ "total_flos": 1.1916113531633664e+16,
45
  "trial_name": null,
46
  "trial_params": null
47
  }