Best000 commited on
Commit
896e65b
·
verified ·
1 Parent(s): db35c0d

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 sha256:632800e0e42776865b190618b8fe2941d26d893df86617b55747d2f376168cba
3
  size 28348936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be653978c832b37220939dbfc80cb338ad18c54c73591368cee0d7c5ff0e8fa2
3
  size 28348936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37ece672f895663b50663384b74dba68a082121a8b91ea4886e53588fd4d1f2b
3
  size 14714068
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88416e640648944ed778ed60d1991c9c9307a748aeabf4254955c9811c498207
3
  size 14714068
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d670c618d79bdc2e410e7f7ea3101bf3177edddd27da2f41c9be9cd60667b9ab
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95e1ce9bb60ab00f99c593a82d96879a8e2a46d1d822f5dfb0aa269b464ba842
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": 0.024226110363391656,
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": 41.515,
103
  "eval_steps_per_second": 20.889,
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": 584142966226944.0,
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": 0.026917900403768506,
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": 41.515,
103
  "eval_steps_per_second": 20.889,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.026917900403768506,
108
+ "grad_norm": 1.6788541078567505,
109
+ "learning_rate": 0.0002,
110
+ "loss": 4.1978,
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": 649047740252160.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null