nathanialhunt commited on
Commit
b221d80
·
verified ·
1 Parent(s): 30adfaf

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 sha256:105845ba42da00fe01c142829f8a56583ea961925c63088640df6d3e58f91400
3
  size 94412008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d57b45737f1ad7f28b1e074270298a7463b0b02c74fc9835d85c8d795768a2e
3
  size 94412008
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f80c864b251f03f70c96c3ebe13355970b01f20c97a7d17229666e572c0bb6e4
3
  size 48260756
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b334044cf3c342986be6fe1ec1eedb0a3a59079793c52e0d1ac951909711736c
3
  size 48260756
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3609245ce206c841b7e43f48fe1b3115f8ac278c18fd086c7c823ea252639c54
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c972796619e858bb767b916dc5bb8f6ea7a4b1f4ef85a988373da5f475a4e0ca
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": 0.0009643201542912247,
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": 21.939,
45
  "eval_steps_per_second": 10.97,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 1212442277314560.0,
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": 0.0019286403085824494,
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": 21.939,
45
  "eval_steps_per_second": 10.97,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0012857602057216328,
50
+ "grad_norm": 2.1928322315216064,
51
+ "learning_rate": 8e-05,
52
+ "loss": 8.4298,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0016072002571520412,
57
+ "grad_norm": 2.4467806816101074,
58
+ "learning_rate": 0.0001,
59
+ "loss": 9.1291,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.0019286403085824494,
64
+ "grad_norm": 1.8387688398361206,
65
+ "learning_rate": 0.00012,
66
+ "loss": 7.5879,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0019286403085824494,
71
+ "eval_loss": 1.9823801517486572,
72
+ "eval_runtime": 59.7435,
73
+ "eval_samples_per_second": 21.927,
74
+ "eval_steps_per_second": 10.964,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 2424884554629120.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null