trenden commited on
Commit
a01b87b
·
verified ·
1 Parent(s): 17e11b2

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:abf464ab44a6b268b5f0d615d85cda20c9bf8c3588e311c9390619256d016099
3
  size 80792096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1784815460a778a9d9ce30545b3b9c50bb48094036976953f25a77b9be35e72
3
  size 80792096
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dca12bbe912643be94ee2fecc6238b85399352b74c40ca558913f17f9a2cfdf3
3
  size 41459700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386e69483f5cec4deb5f9ef2deb381ad320d81dd095238978fffc8ce11fc1e40
3
  size 41459700
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6006d4561685548269dc3760edfdd78993880331462b6db75c8c15089ff4fc66
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6341238930f2666c44e2dc3ca807c74ee7c07947554137c5acb46010f0870d99
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": 0.003933136676499509,
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": 23.28,
45
  "eval_steps_per_second": 11.64,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 914883924197376.0,
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": 0.007866273352999017,
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": 23.28,
45
  "eval_steps_per_second": 11.64,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.005244182235332678,
50
+ "grad_norm": 0.6242678165435791,
51
+ "learning_rate": 8e-05,
52
+ "loss": 2.7061,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.006555227794165847,
57
+ "grad_norm": 0.9453555345535278,
58
+ "learning_rate": 0.0001,
59
+ "loss": 3.5085,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.007866273352999017,
64
+ "grad_norm": 0.7568758726119995,
65
+ "learning_rate": 0.00012,
66
+ "loss": 3.4138,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.007866273352999017,
71
+ "eval_loss": 3.364776372909546,
72
+ "eval_runtime": 13.863,
73
+ "eval_samples_per_second": 23.227,
74
+ "eval_steps_per_second": 11.614,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1829767848394752.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null