ramdhanfirdaus commited on
Commit
1850931
1 Parent(s): d4f4d1b

Training in progress, step 400, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ac2758969d27b972ccfb227304f1d22b8596825fbac07a1dcf399c63e809e79
3
  size 50338848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b24f72ce1a90a21c496f1a3c9645ab47018fac5b29d110ff82663261550b8ef7
3
  size 50338848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25d9422249bd4621a210cfeaa29ac3102b9a54b5901ef1621054d16fc95094bc
3
  size 100693001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d8dbd8b2ebf32b6530d0eb8a60d831c953fe8a28e4968436688d5ba12bac5c8
3
  size 100693001
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4e1c216ad0e3fdde267e30a9c468cf226b7b8f0a5659507396b5a46e5e857b8
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eed793b152ba29811eeaef2ddd85ed3082303355a228268d2b4d8d4cf2e23e4f
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3e02e4b8a74e841ee5a1ce8c453a9becb15f5be6cbcdd100b814e93235dab36
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13276f15dd2b6acc19b970176aa2db4ac9b58241843e72c89b50e3094e903b19
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.8703595399856567,
3
- "best_model_checkpoint": "./outputs/checkpoint-300",
4
- "epoch": 0.2185792349726776,
5
  "eval_steps": 100,
6
- "global_step": 300,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -49,13 +49,27 @@
49
  "eval_samples_per_second": 43.723,
50
  "eval_steps_per_second": 5.471,
51
  "step": 300
 
 
 
 
 
 
 
 
 
 
 
 
 
 
52
  }
53
  ],
54
  "logging_steps": 100,
55
  "max_steps": 4116,
56
  "num_train_epochs": 3,
57
  "save_steps": 100,
58
- "total_flos": 1.7886831549087744e+16,
59
  "trial_name": null,
60
  "trial_params": null
61
  }
 
1
  {
2
+ "best_metric": 1.8250001668930054,
3
+ "best_model_checkpoint": "./outputs/checkpoint-400",
4
+ "epoch": 0.29143897996357016,
5
  "eval_steps": 100,
6
+ "global_step": 400,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
49
  "eval_samples_per_second": 43.723,
50
  "eval_steps_per_second": 5.471,
51
  "step": 300
52
+ },
53
+ {
54
+ "epoch": 0.29,
55
+ "learning_rate": 0.0002,
56
+ "loss": 1.8484,
57
+ "step": 400
58
+ },
59
+ {
60
+ "epoch": 0.29,
61
+ "eval_loss": 1.8250001668930054,
62
+ "eval_runtime": 143.5707,
63
+ "eval_samples_per_second": 43.7,
64
+ "eval_steps_per_second": 5.468,
65
+ "step": 400
66
  }
67
  ],
68
  "logging_steps": 100,
69
  "max_steps": 4116,
70
  "num_train_epochs": 3,
71
  "save_steps": 100,
72
+ "total_flos": 2.386786614194995e+16,
73
  "trial_name": null,
74
  "trial_params": null
75
  }