phungkhaccuong commited on
Commit
1cc84b4
·
verified ·
1 Parent(s): d04b2fe

Training in progress, step 39, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25f4716b28ad59c0dd064174057a0824180bab033ece62a306adb4663476d923
3
  size 48679352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af7228f2f7f7c0bd02e410e8792a3a9a248b5c3b30105ff92560843fb0256ac6
3
  size 48679352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4b8d94d5a6a5584dd61706cbbbb17094890df32a33749fabee57304b8782632
3
  size 25152500
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37c6fadc733fb68c680e6428db145c1fcbe10677c173fc250bad8daa59298145
3
  size 25152500
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89bb461df6a538dc9cf3275177e4f9fd762c40b1b3778ab893c52f4f184369b0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1542c12b1c38878d0bf713af077c56cb60e0f19147c5c8f6f20fb0942baee8b8
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.06636885768985322,
5
  "eval_steps": 10,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -66,6 +66,28 @@
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 2.7201,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 2452423736033280.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.09955328653477984,
5
  "eval_steps": 10,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 2.7201,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.07657945118059988,
72
+ "grad_norm": 0.6069520711898804,
73
+ "learning_rate": 5e-05,
74
+ "loss": 2.7406,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.07657945118059988,
79
+ "eval_loss": 2.727977991104126,
80
+ "eval_runtime": 9.3209,
81
+ "eval_samples_per_second": 17.702,
82
+ "eval_steps_per_second": 8.905,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.08934269304403318,
87
+ "grad_norm": 0.5778947472572327,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.6019,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 3722118294405120.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null