kostiantynk1205 commited on
Commit
cf36716
·
verified ·
1 Parent(s): 1ab03bf

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:e1bafde6190bf393d5a43cca1214bb1d26e55b1bd37773c39ce87b58633bf4fa
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e976a5966abff95f9a49593db00e4987a9510b362f2b7df9a4a01dba68a177d
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e81f2c9c5b65c85ea16b57791b6ea086d0eb6e13bc66eebaa5ae17f3e1de69d6
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b1a4cd2d51d997c45d74c248d55be0ed9afc9c93821396eea7e37eb6400c431
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5aafb8ab294e642bd9cd6e7b59765339e35bee3de9252e2fa6f291603fa21e04
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c6138fe7a3d5c98b34d01248eab605da023807e65a2a3b0000010e89e6f1f27
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": 0.014035087719298246,
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": 19.401,
103
  "eval_steps_per_second": 9.736,
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": 2850282987847680.0,
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": 0.015594541910331383,
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": 19.401,
103
  "eval_steps_per_second": 9.736,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.015594541910331383,
108
+ "grad_norm": 0.6715533137321472,
109
+ "learning_rate": 0.0002,
110
+ "loss": 1.6847,
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": 3176029615030272.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null