trenden commited on
Commit
e5f4507
·
verified ·
1 Parent(s): d21ce7e

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 sha256:16b449e3a16d6eeb94f13e3d2be28fde9b4f5cb0168b779af2f72823b1edbb3d
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32f7bfc6cf8992379ed257c4e3f200046e818c7fd8bb702e36cff2366b5d7f9c
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ef06a49a0d527c88d8bb75a85410bf695c09ac129de095e6759803fbfa271f6
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26be9a0dd1aa463b700fbb45d805aac59733a74eda796ca73aa2d80fa7068ad3
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f005639ce0865eae9775065c9fed38932da15f22f9e96d8e1fc81a298bdf6ae
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e0cecd4fa0b346dabc60917e1b3ca1c91ce878034ad78d001aa7d9a1f75d88e
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": 0.0009354536950420954,
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": 24.253,
45
  "eval_steps_per_second": 12.135,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 786064805462016.0,
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": 0.0018709073900841909,
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": 24.253,
45
  "eval_steps_per_second": 12.135,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0012472715933894605,
50
+ "grad_norm": 0.6629976034164429,
51
+ "learning_rate": 8e-05,
52
+ "loss": 1.7424,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0015590894917368258,
57
+ "grad_norm": 0.7607347965240479,
58
+ "learning_rate": 0.0001,
59
+ "loss": 1.7342,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.0018709073900841909,
64
+ "grad_norm": 0.728712260723114,
65
+ "learning_rate": 0.00012,
66
+ "loss": 1.6289,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0018709073900841909,
71
+ "eval_loss": 1.7151895761489868,
72
+ "eval_runtime": 55.8278,
73
+ "eval_samples_per_second": 24.199,
74
+ "eval_steps_per_second": 12.109,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1618368717127680.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null