nathanialhunt commited on
Commit
6e567c2
·
verified ·
1 Parent(s): f1f13c7

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:cc3fb6a23957e47be3d02cf288b1172a31942d8467efaa161354dc2583b62906
3
  size 41581360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d600a7b414b59981bc0a04c3c9e360d253cc4066d061d344da9277da124449b
3
  size 41581360
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce71160653747b679a6bd1f8d86fe756f496a8477f5918357c4f49b57b22512b
3
  size 21505540
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b66f506f41ff241d38348f7e7defdb75a45343db0379970960ca505f78b86a89
3
  size 21505540
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c355234cd01e17910d17252e2407e84f87b4e7cc69b0dd7cbeeb135ace16e17
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2416d7133f59b0362c1f01a206ee7c20d23a2af18f87294400359b887a65e192
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": 0.001915097350781998,
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": 26.282,
103
  "eval_steps_per_second": 13.148,
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": 900175195275264.0,
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": 0.002127885945313331,
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": 26.282,
103
  "eval_steps_per_second": 13.148,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.002127885945313331,
108
+ "grad_norm": 1.0102648735046387,
109
+ "learning_rate": 0.0002,
110
+ "loss": 1.7388,
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": 1000194661416960.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null