trenden commited on
Commit
8f3b7a9
·
verified ·
1 Parent(s): 772f1eb

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 sha256:4745544e8452f62da2f5e7614702dda03692627e60a93027dbf20ef97add81c8
3
  size 27024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe00509e8bd97c7f34d96a5912260c7c26b586b3f0c29b2ac4d72509475df158
3
  size 27024
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1cc02f2b59fa72ab4057b31589f5f205ee577f597e9c03c76376c3d38688076a
3
  size 63974
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f22a42612e960fff91c74434a32345430306e5fe9da7c67cd9c78eeeffaa613a
3
  size 63974
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56e4c605570ee3c73fe8ff5167e52a53ea3100415d1bfd842431b5b9a62a411e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c12066a9c624fe38430ff3feea2dc6451e9f1a920255c11680c737a33d2c53a0
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": 0.0028308563340410475,
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": 319.671,
103
  "eval_steps_per_second": 159.955,
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": 148705443840.0,
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": 0.003145395926712275,
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": 319.671,
103
  "eval_steps_per_second": 159.955,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.003145395926712275,
108
+ "grad_norm": 0.03568054735660553,
109
+ "learning_rate": 0.0002,
110
+ "loss": 10.3718,
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": 168101806080.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null