vertings6 commited on
Commit
ab22694
·
verified ·
1 Parent(s): 37d7a41

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:f2f98e81acb3bcef9815dd85b8262f4fa3e244210784029fb36f82cade0c2e0d
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b770c2325c1145e9ba34e528fc2c71ff0df10f58f17c6d87d5cb4b45c5a0301
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee663349008075136808a01594b5236eb268e7bf1a426e2d6ca6918e12f05c7b
3
  size 335922386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d99428662c1f8788022555564a707d87a4ed7c79df32b1445953fee5d9b05b7d
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:e6685af762555f9221bb666aae648429b9e4c5993296a9d847639b05d9002261
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95f23e0c172630a8f64cf6905e630743369246c588591c18ff8c868e616f8bd8
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.54878169298172,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-10",
4
- "epoch": 0.0003246252607146625,
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": 6.409,
53
  "eval_steps_per_second": 1.602,
54
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  }
56
  ],
57
  "logging_steps": 3,
@@ -80,7 +117,7 @@
80
  "attributes": {}
81
  }
82
  },
83
- "total_flos": 9668030606868480.0,
84
  "train_batch_size": 4,
85
  "trial_name": null,
86
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.5194941163063049,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-20",
4
+ "epoch": 0.000649250521429325,
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": 6.409,
53
  "eval_steps_per_second": 1.602,
54
  "step": 10
55
+ },
56
+ {
57
+ "epoch": 0.00038955031285759504,
58
+ "grad_norm": 2.115870475769043,
59
+ "learning_rate": 0.000163742398974869,
60
+ "loss": 2.2148,
61
+ "step": 12
62
+ },
63
+ {
64
+ "epoch": 0.00048693789107199376,
65
+ "grad_norm": 1.991878867149353,
66
+ "learning_rate": 0.00013090169943749476,
67
+ "loss": 2.0272,
68
+ "step": 15
69
+ },
70
+ {
71
+ "epoch": 0.00048693789107199376,
72
+ "eval_loss": 0.5279491543769836,
73
+ "eval_runtime": 4050.7843,
74
+ "eval_samples_per_second": 6.404,
75
+ "eval_steps_per_second": 1.601,
76
+ "step": 15
77
+ },
78
+ {
79
+ "epoch": 0.0005843254692863925,
80
+ "grad_norm": 2.2681803703308105,
81
+ "learning_rate": 9.372094804706867e-05,
82
+ "loss": 1.8646,
83
+ "step": 18
84
+ },
85
+ {
86
+ "epoch": 0.000649250521429325,
87
+ "eval_loss": 0.5194941163063049,
88
+ "eval_runtime": 4049.4194,
89
+ "eval_samples_per_second": 6.406,
90
+ "eval_steps_per_second": 1.602,
91
+ "step": 20
92
  }
93
  ],
94
  "logging_steps": 3,
 
117
  "attributes": {}
118
  }
119
  },
120
+ "total_flos": 1.669932559368192e+16,
121
  "train_batch_size": 4,
122
  "trial_name": null,
123
  "trial_params": null