ramdhanfirdaus commited on
Commit
3b98954
1 Parent(s): 2ee410d

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 sha256:3f6070ee13ab9feebbcb509567a6d105caa73918f26b75f35c969364b563f833
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc8def1e784a55a2f5e856ef9fa9de1efe28f6f4025b739b6243fe39ca5ef93d
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:840d7b72ea135ef106e2bfe399a59b76bdd79c85babaf070c139da64759bd2d2
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d616f9de60090e34c526a5f831d1c88e212ea1fe0379820ea89bfcfea87f7de
3
  size 18902665
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b26837cce4b9686e80c01fd503576bec322032548fab3bb432c6bb17f35ea1da
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56c7d9acd97a65ba6f52bddd9c1a7be0b5f95308e5fa05bcc7a62b6822eb6d6f
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": 2.551574468612671,
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": 30.615,
50
  "eval_steps_per_second": 3.831,
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": 8750270976491520.0,
59
  "trial_name": null,
60
  "trial_params": null
61
  }
 
1
  {
2
+ "best_metric": 2.517575263977051,
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": 30.615,
50
  "eval_steps_per_second": 3.831,
51
  "step": 300
52
+ },
53
+ {
54
+ "epoch": 0.29,
55
+ "learning_rate": 0.0002,
56
+ "loss": 2.5366,
57
+ "step": 400
58
+ },
59
+ {
60
+ "epoch": 0.29,
61
+ "eval_loss": 2.517575263977051,
62
+ "eval_runtime": 204.3925,
63
+ "eval_samples_per_second": 30.696,
64
+ "eval_steps_per_second": 3.841,
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": 1.167856193839104e+16,
73
  "trial_name": null,
74
  "trial_params": null
75
  }