kostiantynk commited on
Commit
9ee901b
·
verified ·
1 Parent(s): 47b9212

Training in progress, step 10, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:301767e54e8519964a0bf777ccff1446f5d554d0d04e2bad2c9b66481f9a9af3
3
  size 100059752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a0b1ec93bcde5a2ff94d41c8110159402d8cce75bef5bdf36ba085edaa79461
3
  size 100059752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:467a56c5398c91854ab4096a0b434d7ddc9db3102df765975cfabe69af9ec0bf
3
  size 51244020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b33659a2bd44ddf10e1a01325cdd3f8e03512a982cc70baf315d84653cb97f0a
3
  size 51244020
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b70f29a81cab5749b7acb47c2046572b3022dd01b41109c8e1baa88cfd573b4b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaaae57ea544793f8498ea930cc6022c0875d69417c53b70b22c86f3547c7459
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
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": 0.0003625231612019657,
5
  "eval_steps": 3,
6
- "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -102,6 +102,13 @@
102
  "eval_samples_per_second": 28.423,
103
  "eval_steps_per_second": 14.212,
104
  "step": 9
 
 
 
 
 
 
 
105
  }
106
  ],
107
  "logging_steps": 1,
@@ -116,12 +123,12 @@
116
  "should_evaluate": false,
117
  "should_log": false,
118
  "should_save": true,
119
- "should_training_stop": false
120
  },
121
  "attributes": {}
122
  }
123
  },
124
- "total_flos": 1719982274641920.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.00040280351244662856,
5
  "eval_steps": 3,
6
+ "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
102
  "eval_samples_per_second": 28.423,
103
  "eval_steps_per_second": 14.212,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.00040280351244662856,
108
+ "grad_norm": 2.1753973960876465,
109
+ "learning_rate": 0.0002,
110
+ "loss": 0.4438,
111
+ "step": 10
112
  }
113
  ],
114
  "logging_steps": 1,
 
123
  "should_evaluate": false,
124
  "should_log": false,
125
  "should_save": true,
126
+ "should_training_stop": true
127
  },
128
  "attributes": {}
129
  }
130
  },
131
+ "total_flos": 1911091416268800.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null