duyphu commited on
Commit
8daa140
·
verified ·
1 Parent(s): b81ee14

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 sha256:0ecc426604bb34e2d8087f5686b9100063bd46cf7469e55012d15bf45e378835
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6887678d017ac4b5aac9a62bbaff2a87dcc28275c7e1fe275e6f9619050c116
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:427ce89452605ce37cb74d340d1e403655745622bfdad86d9013f6ee8cbc73c2
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b551b2a682aa7877aee613fa664e957dd47b28f50e8b1de8643e57be1ba32a0
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7cb92806e57e387dc4287cb8248c41b4894921324de83cad277fe9afa6586b2d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2754112ba4bf0b24ea7bba3dafb4e4d8bcdb84cd2b6baeabdacd60495750e552
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": 0.24018475750577367,
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": 9.3983,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4688397062897664.0,
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": 0.36027713625866054,
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": 9.3983,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.27713625866050806,
72
+ "grad_norm": 12.325895309448242,
73
+ "learning_rate": 5e-05,
74
+ "loss": 8.6908,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.27713625866050806,
79
+ "eval_loss": 2.1261730194091797,
80
+ "eval_runtime": 3.4805,
81
+ "eval_samples_per_second": 13.216,
82
+ "eval_steps_per_second": 6.608,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.3233256351039261,
87
+ "grad_norm": 11.397773742675781,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 8.3931,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 7054503991836672.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null