cwaud commited on
Commit
225d788
·
verified ·
1 Parent(s): b51c26e

Training in progress, step 6, 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:a08e4674eeb7bc6b9513c33c2a1586a51d7214463f7c3253375e381ba72273f5
3
  size 100059752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06abf4e737c770dd0d7aa96bbd6a1f33ed7db94e669e9def9399a0338f115fa1
3
  size 100059752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2292512f24822f366e9140b9c8ff885ddd0fa1ef3e1baaa6382c745418146ca9
3
  size 51244020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ffe571eb1bf2bcbc4bc178c435acfcb4a2e2fa7d27c32e68d2eabcc5186bd1b
3
  size 51244020
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:babaa05bea140ed430130d9c5aedbd588775a3218c0384a058097771d851af24
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:087b559ee49306e16fdc13f29acc389befd2841b572cff929aadbbb2e36c89c7
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": 4.139458351874657e-05,
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": 7.401,
45
  "eval_steps_per_second": 3.7,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 573327424880640.0,
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": 8.278916703749314e-05,
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": 7.401,
45
  "eval_steps_per_second": 3.7,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 5.519277802499543e-05,
50
+ "grad_norm": 11.607290267944336,
51
+ "learning_rate": 8e-05,
52
+ "loss": 9.734,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 6.899097253124429e-05,
57
+ "grad_norm": 13.406005859375,
58
+ "learning_rate": 0.0001,
59
+ "loss": 7.917,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 8.278916703749314e-05,
64
+ "grad_norm": 12.174226760864258,
65
+ "learning_rate": 0.00012,
66
+ "loss": 8.65,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 8.278916703749314e-05,
71
+ "eval_loss": 7.667308807373047,
72
+ "eval_runtime": 4120.9144,
73
+ "eval_samples_per_second": 7.405,
74
+ "eval_steps_per_second": 3.703,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1146654849761280.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null