nathanialhunt commited on
Commit
ff456ea
·
verified ·
1 Parent(s): 95d8728

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 sha256:71ee84a7cf148435ec287dde80eb584ee57ca44e5d430c3c7cbbb994405227cc
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01cca6061f441a1dcafc8c9f6e2dd2f9834ff3d90e9fa2d23072cf49089d9307
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a7a598005777a9f9744c3fe31d5035976a1bcea825a32159a0eac7fd09eb0ab
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c95aeb20333e74e2dd00709d818f16bf90ae79cbd5c35a4dbdef9fac7270dda9
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8b29aef03c991f6bab85ca61524ae5fbc2dacc16323d80f5f5b89b12d9af90c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2500323a43460211890b7e0b52df9c31e138aa542ecb0e21dfbcd59897076546
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": 0.0063399170933918555,
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": 28.859,
61
  "eval_steps_per_second": 14.435,
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": 6677871892365312.0,
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": 0.008128098837681867,
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": 28.859,
61
  "eval_steps_per_second": 14.435,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.006502479070145493,
66
+ "grad_norm": 2.5585081577301025,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 4.9833,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.008128098837681867,
73
+ "grad_norm": 1.630866289138794,
74
+ "learning_rate": 0.0,
75
+ "loss": 4.8532,
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": 8835964638068736.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null