JacksonBrune commited on
Commit
e4fa7b5
·
verified ·
1 Parent(s): f7f4676

Training in progress, step 50, 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:ac93b1ee5ec0a841bd9dff907be72c77f4215bd3d5153dd06adc9bb324846501
3
  size 104902272
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04cba70134aa8685eda0f1721b9458cfb382a2ab4fc6260699e30ea642c9ea69
3
  size 104902272
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cdde8291440be3aba20196ebd926a4c43fba552f56fd5078bcdb079af351ccf6
3
  size 53622996
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3ba8cf8623502918a1788ed86aa20110de46a5b53aea6d2d11d0c0ccde0d0ee
3
  size 53622996
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c67a3447d55006c2777019c4d6c4c7c5f9aa8bb2d7d1d12706ce84756770d0a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff1b24772818b4ab2f99a8085b6fc6630d3d168446cfccc0d33eaa83714de74a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
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": 0.007791818590479996,
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,
@@ -60,6 +60,20 @@
60
  "eval_samples_per_second": 15.309,
61
  "eval_steps_per_second": 7.655,
62
  "step": 39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 10,
@@ -74,12 +88,12 @@
74
  "should_evaluate": false,
75
  "should_log": false,
76
  "should_save": true,
77
- "should_training_stop": false
78
  },
79
  "attributes": {}
80
  }
81
  },
82
- "total_flos": 2.172597653471232e+16,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.009989511013435893,
5
  "eval_steps": 13,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 15.309,
61
  "eval_steps_per_second": 7.655,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.007991608810748714,
66
+ "grad_norm": 1.4676873683929443,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 1.4961,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.009989511013435893,
73
+ "grad_norm": 1.6997168064117432,
74
+ "learning_rate": 0.0,
75
+ "loss": 1.4626,
76
+ "step": 50
77
  }
78
  ],
79
  "logging_steps": 10,
 
88
  "should_evaluate": false,
89
  "should_log": false,
90
  "should_save": true,
91
+ "should_training_stop": true
92
  },
93
  "attributes": {}
94
  }
95
  },
96
+ "total_flos": 2.776532741259264e+16,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null