cwaud commited on
Commit
6d86737
1 Parent(s): 1488ead

Training in progress, step 6, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d91c832b67c02aa33888ab224c025cb43af148cb1da4b1553a7c01333d38b303
3
  size 19859140
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0716e8cd0716ed13e89d4d72d43d071a71741c79c2d481e68fc4ba0145fb0c6d
3
  size 19859140
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e80a7d8e0dc1686cec3bd1a5de2902a6893738a61badd7e84819aeb4283f57a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:700c29f7c7e847cf7983434a2b0e9f8b263641f80cbb6174649fd91f517fbb15
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
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": 0.002094972067039106,
5
  "eval_steps": 3,
6
- "global_step": 3,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -44,6 +44,35 @@
44
  "eval_samples_per_second": 29.263,
45
  "eval_steps_per_second": 14.656,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 97289477554176.0,
67
  "train_batch_size": 2,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.004189944134078212,
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,
 
44
  "eval_samples_per_second": 29.263,
45
  "eval_steps_per_second": 14.656,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.002793296089385475,
50
+ "grad_norm": NaN,
51
+ "learning_rate": 8e-05,
52
+ "loss": 0.0,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0034916201117318434,
57
+ "grad_norm": NaN,
58
+ "learning_rate": 0.0001,
59
+ "loss": 0.0,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.004189944134078212,
64
+ "grad_norm": NaN,
65
+ "learning_rate": 0.00012,
66
+ "loss": 0.0,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.004189944134078212,
71
+ "eval_loss": NaN,
72
+ "eval_runtime": 20.9351,
73
+ "eval_samples_per_second": 28.803,
74
+ "eval_steps_per_second": 14.426,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 194578955108352.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null