nat-hunt commited on
Commit
64e173a
·
verified ·
1 Parent(s): 6b68ef9

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 sha256:82c5bdf552f8e812f3f5aaefec23f717932366b8a0766aa46b18831b7ebde5b9
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:731363e7b40c82994a08a181aa4502633bf3f2c6370a8c9ee6c5bf32c7ba252c
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1677df82531d60196cdc25653022b7f05567a7309f11631aeb0ef66f6625d262
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67c20ea9a29fe862879631891876caccbaacfcf36ae2be6b21ae061da790a5c1
3
  size 13685516
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c577fa0d5440076aa59215302dbde6f36234cd1bbefdcf145b0d95592f175e6c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85b0ae6c3bd2ac4ea01467a5edbc086cdc303e1ace1b12b41ab97be3e932f8c7
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": 0.012752391073326248,
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": 55.572,
45
  "eval_steps_per_second": 27.786,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 76737593475072.0,
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": 0.025504782146652496,
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": 55.572,
45
  "eval_steps_per_second": 27.786,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.01700318809776833,
50
+ "grad_norm": 0.708982527256012,
51
+ "learning_rate": 8e-05,
52
+ "loss": 1.5621,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.021253985122210415,
57
+ "grad_norm": 0.8289952874183655,
58
+ "learning_rate": 0.0001,
59
+ "loss": 1.5821,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.025504782146652496,
64
+ "grad_norm": 0.7642757296562195,
65
+ "learning_rate": 0.00012,
66
+ "loss": 1.6416,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.025504782146652496,
71
+ "eval_loss": 1.5391772985458374,
72
+ "eval_runtime": 1.8384,
73
+ "eval_samples_per_second": 54.395,
74
+ "eval_steps_per_second": 27.198,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 153475186950144.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null