SystemAdmin123 commited on
Commit
c197c5b
·
verified ·
1 Parent(s): 235c1e3

Training in progress, step 60, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ff04ffbfa8bc5bb3e988c8bb45003fcadd064e85f411987ddd44c15d8d57974
3
  size 250490408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07f20642645957edae2ce7c265e225e4b56cff6574adf38e81ae104351b0a523
3
  size 250490408
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d243f90d71e2db4783c193c779aa1f22097b9f05a55dcf25053864cf43dd5dfa
3
  size 255265850
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb92f5e9d43c62bfc8384c770c60b8f905fc63e20919d6d54f8f08372119a898
3
  size 255265850
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d0bc5c92e4fdea01d3fa32e0069da72f87be35dfa69240211a2193fb469268f
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed64e0e27f410ed20158985bfa09c9103bc78ccd30e02605475adc9ee8711d22
3
  size 14512
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fed34d3582eb7589bf4ae83ba37735e55c58c1dcea5c7b347cc4732a41c1fa84
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef152eb96e063e261cf4df880cb4e01fe8cf9df29ac68b58ffc75651778615d7
3
  size 14512
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:572996e9dc190ff3f3a6efdf58de929f593fa2dd2f97d74fed7646828651b17f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3671bd7fce476af6c5d68b2346a8d63f3c9e317781066d2c00973b04663cf26
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": 3.3333333333333335,
5
  "eval_steps": 40,
6
- "global_step": 40,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -51,6 +51,20 @@
51
  "eval_samples_per_second": 141.117,
52
  "eval_steps_per_second": 2.256,
53
  "step": 40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
54
  }
55
  ],
56
  "logging_steps": 10,
@@ -70,7 +84,7 @@
70
  "attributes": {}
71
  }
72
  },
73
- "total_flos": 2598287911682048.0,
74
  "train_batch_size": 32,
75
  "trial_name": null,
76
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
  "eval_steps": 40,
6
+ "global_step": 60,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
51
  "eval_samples_per_second": 141.117,
52
  "eval_steps_per_second": 2.256,
53
  "step": 40
54
+ },
55
+ {
56
+ "epoch": 4.166666666666667,
57
+ "grad_norm": 5.5,
58
+ "learning_rate": 0.00019939306773179497,
59
+ "loss": 5.0645,
60
+ "step": 50
61
+ },
62
+ {
63
+ "epoch": 5.0,
64
+ "grad_norm": 6.53125,
65
+ "learning_rate": 0.00019863613034027224,
66
+ "loss": 4.7735,
67
+ "step": 60
68
  }
69
  ],
70
  "logging_steps": 10,
 
84
  "attributes": {}
85
  }
86
  },
87
+ "total_flos": 3885935078932480.0,
88
  "train_batch_size": 32,
89
  "trial_name": null,
90
  "trial_params": null