lesso commited on
Commit
425b994
·
verified ·
1 Parent(s): 9abb9b1

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 sha256:7ef5379668c99b968c4bcb60184dd146809d97ddfe90d2d51a303e9d10f48ce9
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbf189ec605e8f63ca0b1c2622f580fd24b8a10c32770f7ef1c9eb981b6ce16c
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4ff918aa82d9658ea4b9b36ac8d0b51406293f2951a34eae4d6e1f144319a49
3
  size 160172858
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea6d48a1187ae29a360eeed71c7651f43f8895252d3516bfe27904377f101fee
3
  size 160172858
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1fc55e46f74fe1e2e19c9e192915616355e27c05ef750c64fd8b2b37786c93c3
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6a28b3cdae7b41816520743d6945c0e38f469a36f02ca51efa060727ee1b256
3
  size 14512
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2f78b0455452857cdb1835c39eb64ab9332e969a942073abdb8307a1f1fcb3d
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83a4718d70b23207ce408aed0c30e10b1919ff4746a8e570a6ea8c01a6d9665b
3
  size 14512
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": 0.004838709677419355,
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": 15.465,
103
  "eval_steps_per_second": 7.733,
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": 2931748635672576.0,
125
  "train_batch_size": 1,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.005376344086021506,
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": 15.465,
103
  "eval_steps_per_second": 7.733,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.005376344086021506,
108
+ "grad_norm": 0.5231564044952393,
109
+ "learning_rate": 0.0002,
110
+ "loss": 0.9745,
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": 3257498484080640.0,
132
  "train_batch_size": 1,
133
  "trial_name": null,
134
  "trial_params": null