gavrilstep commited on
Commit
6b8376c
·
verified ·
1 Parent(s): a5830e9

Training in progress, step 20, 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:c0a26fee8ab2955c4de33980fb436829892693f95b899a0b004990c3a4c0887b
3
  size 2269195160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:507ffae19608e05d267d8fc7426f662c43799c93b0d70a96acd68b1ce8c6914e
3
  size 2269195160
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5df2d03de9af300798927fa90c740106385c33492c551e7ce38bbf0911487e21
3
  size 335922386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76cd945f1ecedbe508e5d2e0a7e736275edf9bf451a1a75b71369a5ca9e1ef20
3
  size 335922386
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94eb3af0be59b8022e591483a56634de67b6ec709d4a7976205940027b927a1a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8d0ca5f94c74be21f7e258f478e4f1bcf339ab697a95d852a0fd9b800d39d6b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7bb161926d3ea8b8ad8b5d8af1ee3fd436d358e0f6304d9f88656b94d5968bb
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": 0.4878048780487805,
5
  "eval_steps": 5,
6
- "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -52,6 +52,43 @@
52
  "eval_samples_per_second": 10.019,
53
  "eval_steps_per_second": 5.566,
54
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  }
56
  ],
57
  "logging_steps": 3,
@@ -71,7 +108,7 @@
71
  "attributes": {}
72
  }
73
  },
74
- "total_flos": 3709438431068160.0,
75
  "train_batch_size": 2,
76
  "trial_name": null,
77
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.975609756097561,
5
  "eval_steps": 5,
6
+ "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
52
  "eval_samples_per_second": 10.019,
53
  "eval_steps_per_second": 5.566,
54
  "step": 10
55
+ },
56
+ {
57
+ "epoch": 0.5853658536585366,
58
+ "grad_norm": 2.2389755249023438,
59
+ "learning_rate": 0.00018412535328311814,
60
+ "loss": 1.4023,
61
+ "step": 12
62
+ },
63
+ {
64
+ "epoch": 0.7317073170731707,
65
+ "grad_norm": 1.7021565437316895,
66
+ "learning_rate": 0.00011423148382732853,
67
+ "loss": 1.212,
68
+ "step": 15
69
+ },
70
+ {
71
+ "epoch": 0.7317073170731707,
72
+ "eval_loss": 1.0455703735351562,
73
+ "eval_runtime": 1.8834,
74
+ "eval_samples_per_second": 4.779,
75
+ "eval_steps_per_second": 2.655,
76
+ "step": 15
77
+ },
78
+ {
79
+ "epoch": 0.8780487804878049,
80
+ "grad_norm": 1.394986867904663,
81
+ "learning_rate": 3.45139266054715e-05,
82
+ "loss": 1.1363,
83
+ "step": 18
84
+ },
85
+ {
86
+ "epoch": 0.975609756097561,
87
+ "eval_loss": 0.9808509349822998,
88
+ "eval_runtime": 1.8786,
89
+ "eval_samples_per_second": 4.791,
90
+ "eval_steps_per_second": 2.662,
91
+ "step": 20
92
  }
93
  ],
94
  "logging_steps": 3,
 
108
  "attributes": {}
109
  }
110
  },
111
+ "total_flos": 7418876862136320.0,
112
  "train_batch_size": 2,
113
  "trial_name": null,
114
  "trial_params": null