johannes-garstenauer commited on
Commit
e5a0fe8
·
1 Parent(s): 69a6035

Training in progress, step 2016, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc36958f0d68239928fd9e88f39aa9b1067621438731f1e2fa75969244c0d9ed
3
  size 532568837
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa2c356101491597f7a0ce61a3b8b01ec1d3fd26166c4b95987460d555c49048
3
  size 532568837
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:346d2ff76f572eeab4506b4f8d781c3c978fa7ecd8d557649e4ee5d898d20573
3
  size 266276525
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5d4c6b6022e2fae7b7aeac737e4cf889e8965c9c5da26a210699ac4a3fde7c3
3
  size 266276525
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41b4b156e2adf75330c5ed1cccc716cfb855ef4062e969e77b0b4886293f2efd
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a7ea7cefeab456039eef182cdc8efaacec0f725cebf586b06e0e49cc1b9e274
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e95ad10f3a60bd11528f3fc0d6dfd96c7b82f3fa50d289fc35103d1ac00a5a4d
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c36a3a505404eb618d7df1e82c0073512be4502f2d0402e1c9fba3d999e4cea2
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.8007149240393209,
5
  "eval_steps": 600,
6
- "global_step": 1792,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -47,13 +47,30 @@
47
  "learning_rate": 1.648793565683646e-05,
48
  "loss": 0.0117,
49
  "step": 1500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
50
  }
51
  ],
52
  "logging_steps": 500,
53
  "max_steps": 2238,
54
  "num_train_epochs": 1,
55
  "save_steps": 112,
56
- "total_flos": 1.519323382284288e+16,
57
  "trial_name": null,
58
  "trial_params": null
59
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.900804289544236,
5
  "eval_steps": 600,
6
+ "global_step": 2016,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
47
  "learning_rate": 1.648793565683646e-05,
48
  "loss": 0.0117,
49
  "step": 1500
50
+ },
51
+ {
52
+ "epoch": 0.8,
53
+ "eval_accuracy": {
54
+ "accuracy": 0.9982754046166091
55
+ },
56
+ "eval_loss": 0.008614551275968552,
57
+ "eval_runtime": 47.6659,
58
+ "eval_samples_per_second": 158.143,
59
+ "eval_steps_per_second": 2.476,
60
+ "step": 1800
61
+ },
62
+ {
63
+ "epoch": 0.89,
64
+ "learning_rate": 5.317247542448615e-06,
65
+ "loss": 0.0127,
66
+ "step": 2000
67
  }
68
  ],
69
  "logging_steps": 500,
70
  "max_steps": 2238,
71
  "num_train_epochs": 1,
72
  "save_steps": 112,
73
+ "total_flos": 1.709238805069824e+16,
74
  "trial_name": null,
75
  "trial_params": null
76
  }