daniel40 commited on
Commit
f12ad0e
·
verified ·
1 Parent(s): 01d8722

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:fc708f488c87dfacc58b27754e2a0a109cc8b6726e6ffef955af585a65e6b416
3
  size 556856304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a3bc23cd4eaf49160ab465ebe0cb85ed7e7a2f2205178f1cfe519787b6c4120
3
  size 556856304
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46bebd7d96c7a506c0caf17d4f11d635dba6bd1bc6996f9ff80c877c79386927
3
  size 21599060
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8b1f8f66ef17ad3b2052d4d2a459246ca058cc0d02774fa769b69934827863e
3
  size 21599060
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62708c636bc8cc7b15d22a9dcde570698e82a0c4bc55a7697cb5721a614ef94f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16d14b92c6dadc4a845a4add95ab9cec7b1ee94ab044c4e4a55b9e68638c17c4
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
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": 0.06842105263157895,
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": 59.315,
61
  "eval_steps_per_second": 29.658,
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": 2546502362726400.0,
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": 0.08771929824561403,
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": 59.315,
61
  "eval_steps_per_second": 29.658,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.07017543859649122,
66
+ "grad_norm": 6.99767541885376,
67
+ "learning_rate": 2.9289321881345254e-05,
68
+ "loss": 6.7869,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.08771929824561403,
73
+ "grad_norm": 6.338110446929932,
74
+ "learning_rate": 0.0,
75
+ "loss": 6.4316,
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": 3264746618880000.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null