jssky commited on
Commit
14b8b24
·
verified ·
1 Parent(s): 9dfee7b

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 sha256:0217886443f6fe7c6d89eca636eea483df3efe025187a56f04b8d2cd80882363
3
  size 35237104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f36d77963c88da69290297e957d04e6c55cd7c6df5894f52b9e13c962083daab
3
  size 35237104
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8dd28d19ccb89482d6781a1c266089d17d257cc5d214f51e58037fd6b7bdd16
3
  size 18810036
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c92bc24eb6790ada5169d6e57f73b984eae1fff15dd8cfc959b73f4cf194f88
3
  size 18810036
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6043865080f608c46dc46323e200a9a8606f0801d521ba06c9fa277a73d7fc02
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffb2992691eec47b0e9b589ac15a9e917fa5cde0fc126fb596a03fce2287d142
3
  size 15984
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96c06a6bf750d63b16b1b63011e5e4b8ec1e2c4eda2fb612d28daa31614ac326
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2ff787d5c7db764fcbd048bc7054f01ffa6f4bf0e3324f2fadb7e75de4d5b12
3
  size 15984
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2528a29ddeca8b52d807d6f4c424b3cb94775a14aec9d1a23a7c4c7e441fd41
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0ed2a44d728d6067d01e4c6765e8d3ef7f83d87913a4e8d82e56a414e3d387a
3
  size 15984
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3156052393e0a3fdcd202f02b651042b4101e63e3463501b15eddc72ac8b15c8
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d089a84c980b0574f4f5f08c15d6cf3d9ccd9e224c149492ea0ceaca6ab68c1a
3
  size 15984
last-checkpoint/rng_state_4.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f39cdd1141208d914d89cb8902479069d66725570eee027f0de0b0e47bd74705
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e3c53275e225ff40b8dafad07c568cd5a63ec0e8018dc249845915a7ea0a4d9
3
  size 15984
last-checkpoint/rng_state_5.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4620c91d0a5c061ba516bfafacdf660963a14755b7f76df96d58f8743527ff26
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:745c7ef07d4e46e97cbcf306576eb2e4b11b4fc31f91991eb223507f2f16eb6b
3
  size 15984
last-checkpoint/rng_state_6.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:026c75bf6107188c4b889c3a461135ef3dec293b17a4687d65de6c7b9f8dbd57
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:483beb55139220151af22d80ae33654f35ffef0f4ae18cd06a56825a3cc8a021
3
  size 15984
last-checkpoint/rng_state_7.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ede4241516dbbc7b4545b6b94efb66aa42d8f4d73efd81e9d209f2d5070c287
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e30579dd3d94da8b78c27ff84a1a1b1f8efbd79288ffee4580e54793e8d5987f
3
  size 15984
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": 0.07100591715976332,
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": 114.06,
103
  "eval_steps_per_second": 14.391,
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": 2595435482972160.0,
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": 0.07889546351084813,
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": 114.06,
103
  "eval_steps_per_second": 14.391,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.07889546351084813,
108
+ "grad_norm": 0.7767159938812256,
109
+ "learning_rate": 0.0002,
110
+ "loss": 2.3549,
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": 2883817203302400.0,
132
  "train_batch_size": 1,
133
  "trial_name": null,
134
  "trial_params": null