nathanialhunt commited on
Commit
eaab917
·
verified ·
1 Parent(s): 16f4de4

Training in progress, step 39, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2be94ed05bfd415376f67129a4c5c04b229063e56e2efb5459ddf2d2bfdae979
3
  size 5327496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8ca3b0716e56023b96164d93c3d477797ea44e27e53cd252fafc55577a4c2f4
3
  size 5327496
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4c3a713e32c9dab68e8db523868331f46e9ea02b8aa5c63b4101da16ee1cf87
3
  size 2857722
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c3afeb95dde7f969f7923175ee5fae9fb43d28869d6ac7f8aaf8ea7a45f3f41
3
  size 2857722
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:010e132abf426e750cdf77aab6b91b602b4ddf7f0774904162110d4e9efa064a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17a957f0f2267f58e45ddfbca17dd498db3212e514a026d7a2bce1483c389333
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
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": 0.0050828405258785,
5
  "eval_steps": 13,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -45,6 +45,21 @@
45
  "eval_samples_per_second": 123.536,
46
  "eval_steps_per_second": 61.768,
47
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 59954175148032.0,
68
  "train_batch_size": 2,
69
  "trial_name": null,
70
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.007624260788817751,
5
  "eval_steps": 13,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
45
  "eval_samples_per_second": 123.536,
46
  "eval_steps_per_second": 61.768,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.00586481599139827,
51
+ "grad_norm": 2.059757709503174,
52
+ "learning_rate": 8.263518223330697e-05,
53
+ "loss": 11.4724,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.007624260788817751,
58
+ "eval_loss": 2.7590079307556152,
59
+ "eval_runtime": 17.3534,
60
+ "eval_samples_per_second": 124.126,
61
+ "eval_steps_per_second": 62.063,
62
+ "step": 39
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 90727114604544.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null