Hanzalwi commited on
Commit
bd2da1c
1 Parent(s): 8b3e188

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 sha256:0c28661f13098cde8b959bdc0ab28bd6ff85326b0963262e0cc321286af0afdf
3
  size 6298560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:664454268bdc914d4d231ee85faa636b3b26a0639c58e8b50d3b3d6d75a9a140
3
  size 6298560
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f181058c6bef9cb26abab97e22e6e0f74ebc6d54739b0ae2f1df3c13b5f9cca
3
  size 12611081
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:833f8f495cbb68603e262f04f7416d2eae63d63cc878c1edb4faed317a188769
3
  size 12611081
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:225b583421d24eb621d9afb7a8350c8cc752e7fe95214cd43be011984e35bfc9
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:914d66e5e379e4cfd8e3c151fb439a74f39ae2645cf3cf7ec31a3328442be621
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": 1.350274920463562,
3
- "best_model_checkpoint": "./outputs/checkpoint-100",
4
- "epoch": 0.13333333333333333,
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,
@@ -21,6 +21,20 @@
21
  "eval_samples_per_second": 3.533,
22
  "eval_steps_per_second": 0.443,
23
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
24
  }
25
  ],
26
  "logging_steps": 100,
@@ -28,7 +42,7 @@
28
  "num_input_tokens_seen": 0,
29
  "num_train_epochs": 3,
30
  "save_steps": 100,
31
- "total_flos": 3328459744935936.0,
32
  "trial_name": null,
33
  "trial_params": null
34
  }
 
1
  {
2
+ "best_metric": 1.3182251453399658,
3
+ "best_model_checkpoint": "./outputs/checkpoint-200",
4
+ "epoch": 0.26666666666666666,
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": 3.533,
22
  "eval_steps_per_second": 0.443,
23
  "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.27,
27
+ "learning_rate": 0.0002,
28
+ "loss": 1.103,
29
+ "step": 200
30
+ },
31
+ {
32
+ "epoch": 0.27,
33
+ "eval_loss": 1.3182251453399658,
34
+ "eval_runtime": 459.6303,
35
+ "eval_samples_per_second": 4.199,
36
+ "eval_steps_per_second": 0.527,
37
+ "step": 200
38
  }
39
  ],
40
  "logging_steps": 100,
 
42
  "num_input_tokens_seen": 0,
43
  "num_train_epochs": 3,
44
  "save_steps": 100,
45
+ "total_flos": 6647423649644544.0,
46
  "trial_name": null,
47
  "trial_params": null
48
  }