Best000 commited on
Commit
11493fb
·
verified ·
1 Parent(s): cf388fe

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:d33411c39f918231215db01b0ab60e1ad6edd256a517ac443f48759a0d7067bd
3
  size 66103768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a20c701da19dd85897596c11089ac3e89c2eee9e383cacfaf23e1a0bfbda933
3
  size 66103768
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e92e4a796399883134093636b528d46f0aa7d0af7300f04248ea592d8381b2d8
3
  size 33939412
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddaf1fa0ccd194d9e43a22129be39d9bf61746e8f45dc55f236e1a00725fc086
3
  size 33939412
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:bb8533fae84b8bbe35ecff98d5d66a1e19344edfcde38ca202b781a73c8943ca
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": 0.0025778732545649837,
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": 18.562,
45
  "eval_steps_per_second": 9.281,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 648175681253376.0,
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": 0.0051557465091299675,
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": 18.562,
45
  "eval_steps_per_second": 9.281,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0034371643394199786,
50
+ "grad_norm": 1.006024956703186,
51
+ "learning_rate": 8e-05,
52
+ "loss": 3.2906,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.004296455424274973,
57
+ "grad_norm": 1.3687950372695923,
58
+ "learning_rate": 0.0001,
59
+ "loss": 4.1415,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.0051557465091299675,
64
+ "grad_norm": 1.1862958669662476,
65
+ "learning_rate": 0.00012,
66
+ "loss": 4.4577,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0051557465091299675,
71
+ "eval_loss": 1.045850157737732,
72
+ "eval_runtime": 26.4326,
73
+ "eval_samples_per_second": 18.538,
74
+ "eval_steps_per_second": 9.269,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1368370882646016.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null