Aivesa commited on
Commit
69dfc75
·
verified ·
1 Parent(s): f714f1e

Training in progress, step 9, 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:d8e24d8977b04ed67f3e015b0698d712f57cd266bee8f38861e9360a3b45f969
3
  size 1579352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d8e1dc55afbed77d1c5c68d6df440c9362e9c3d78949c397bf1ee756e7f3311
3
  size 1579352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:67889d205fe0466c783c12df8fb4c612f8da52de233b455e1bb5f8f7fbe9af4b
3
  size 857338
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40c4097d0de2ea997fd62b3e6acc105dcf31b753fe01c82bdfe808efe6b0a089
3
  size 857338
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd910d4cf35c746d41dd642c825d4de369b0bdac6b91d822ac300a0dbd53f5f6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d70977ec6530d43e599ca7d587b1138b61a93425b51288df4f64ae4a9c457640
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 0.0002330481729994271,
5
  "eval_steps": 3,
6
- "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -65,6 +65,35 @@
65
  "eval_samples_per_second": 41.71,
66
  "eval_steps_per_second": 20.857,
67
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  }
69
  ],
70
  "logging_steps": 1,
@@ -84,7 +113,7 @@
84
  "attributes": {}
85
  }
86
  },
87
- "total_flos": 11628724617216.0,
88
  "train_batch_size": 2,
89
  "trial_name": null,
90
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.00034957225949914063,
5
  "eval_steps": 3,
6
+ "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
65
  "eval_samples_per_second": 41.71,
66
  "eval_steps_per_second": 20.857,
67
  "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.00027188953516599825,
71
+ "grad_norm": 1034.145263671875,
72
+ "learning_rate": 0.00014,
73
+ "loss": 48.4583,
74
+ "step": 7
75
+ },
76
+ {
77
+ "epoch": 0.00031073089733256947,
78
+ "grad_norm": 1013.7915649414062,
79
+ "learning_rate": 0.00016,
80
+ "loss": 32.965,
81
+ "step": 8
82
+ },
83
+ {
84
+ "epoch": 0.00034957225949914063,
85
+ "grad_norm": 1290.4112548828125,
86
+ "learning_rate": 0.00018,
87
+ "loss": 63.7696,
88
+ "step": 9
89
+ },
90
+ {
91
+ "epoch": 0.00034957225949914063,
92
+ "eval_loss": 11.457053184509277,
93
+ "eval_runtime": 264.0088,
94
+ "eval_samples_per_second": 41.063,
95
+ "eval_steps_per_second": 20.533,
96
+ "step": 9
97
  }
98
  ],
99
  "logging_steps": 1,
 
113
  "attributes": {}
114
  }
115
  },
116
+ "total_flos": 16335589343232.0,
117
  "train_batch_size": 2,
118
  "trial_name": null,
119
  "trial_params": null