nathanialhunt commited on
Commit
a73f421
·
verified ·
1 Parent(s): c060628

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 sha256:5f2d6f9dd100d02d60cda9ea2e62dcd89bec3232de82a2d61d2d1062c6105bb4
3
  size 14696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c89968e23d526c39127a4670698a1094d86bb5b4ca8303dc8c7807dbf2afba09
3
  size 14696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:afb6f866b6cffe38a24f34ed45c9cd1e315934404c8024f845b56921933e256c
3
  size 39398
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:973b09ea8f7a4867329cd91d7a9010f3ff289a3acf77b6f0ec4cc52bac975d12
3
  size 39398
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48d41985628b63b1f03308534e42f5f4fade1dc9f1a7ca147144af3b829d1153
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a2809375c44051deea8394ef4e524b537561ea599f6f054cbc21229ed9516f2
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": 0.14233576642335766,
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": 287.298,
61
  "eval_steps_per_second": 143.649,
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": 4608294912.0,
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": 0.18248175182481752,
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": 287.298,
61
  "eval_steps_per_second": 143.649,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.145985401459854,
66
+ "grad_norm": 0.009486264549195766,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 11.9358,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.18248175182481752,
73
+ "grad_norm": 0.011738108471035957,
74
+ "learning_rate": 0.0,
75
+ "loss": 11.9366,
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": 5908070400.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null