nathanialhunt commited on
Commit
ffdcf8f
·
verified ·
1 Parent(s): 92383d1

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 sha256:7468a8b9a71e1df8ea43e0fa1cecddc2c87465c1b3d881fbebbb02cb5f26ce93
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14ea9eace0983b8ab7ab37ac3ee148b5f22c268a9bef96e70e48684558eb681b
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6fa52631247cab508775c599456e6b8c1a5bbd64ee2d14f7e48c110557e92c2
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:429bc256558d0d0ff4fdd23b31696725692981cc7432c370d38da6c8fe99a378
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9bfb4cc0c317cbad244c7ab49ee125c6bbae21d937536e8ee5c950edc6176278
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01fc1ce580e28a619d9332a6abc08d276d77522f73350afe3c772a2760eb6750
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": 0.0018438844499078057,
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": 22.251,
45
  "eval_steps_per_second": 11.142,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 832303911665664.0,
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": 0.0036877688998156115,
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": 22.251,
45
  "eval_steps_per_second": 11.142,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.002458512599877074,
50
+ "grad_norm": 0.30434760451316833,
51
+ "learning_rate": 8e-05,
52
+ "loss": 0.799,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.003073140749846343,
57
+ "grad_norm": 0.41436293721199036,
58
+ "learning_rate": 0.0001,
59
+ "loss": 1.2349,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.0036877688998156115,
64
+ "grad_norm": 0.4243198037147522,
65
+ "learning_rate": 0.00012,
66
+ "loss": 0.9476,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0036877688998156115,
71
+ "eval_loss": 1.4463762044906616,
72
+ "eval_runtime": 30.8197,
73
+ "eval_samples_per_second": 22.226,
74
+ "eval_steps_per_second": 11.129,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1803325141942272.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null