great0001 commited on
Commit
160e030
·
verified ·
1 Parent(s): f9e09a2

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:e5ea0672518bb84f88dabecf1e19b6831f4fb3046433b8c1d06369f781f98fe1
3
  size 319876032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7ceee14bf2e61853ed50e21050fcc63c88106780dd28d1d8b2a73005228e62b
3
  size 319876032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e3710370595f6334b69517967b42cd92102fe19e29ac1818197d62cf9eb8848
3
  size 162933396
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efc08b9773e64d985348b41d27ebdd399dcd8890d1aaa0a684b1543a459f42e9
3
  size 162933396
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bec698543fc8efe1c42cfec18e55613892ce220f315dbecc631afb9ede0781a9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b94df67cebc93285d21c464d3c29886c2ff2744436493b9e22205a3c16ee5eb
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": 0.006349723217193097,
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": 27.888,
61
  "eval_steps_per_second": 13.944,
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": 3451287509139456.0,
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": 0.0081406707912732,
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": 27.888,
61
  "eval_steps_per_second": 13.944,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.0065125366330185605,
66
+ "grad_norm": 1.840118169784546,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 1.9702,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.0081406707912732,
73
+ "grad_norm": 1.935214638710022,
74
+ "learning_rate": 0.0,
75
+ "loss": 2.3779,
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": 4396282898546688.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null