ClarenceDan commited on
Commit
8be6180
·
verified ·
1 Parent(s): 1473a4f

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:cc553bd8d273fbf0caa32a6b5a4ac1a06ff221672f152c29a2f60fe9d57be791
3
  size 39256456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6e9b5cc86a439c28d2ccb2515f91e24f550c258c9e2c8ce2da58a8d7c6e8d02
3
  size 39256456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:412c276c87e6e73c12d8aaa2725c5bce52a268de24ee3b54fc48714856479189
3
  size 20632826
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f21e169308e6eddfcb414c42c6d0c82e5ecb19190bfc8cfc2de01da40327f968
3
  size 20632826
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b74e3c925ceec40baf5d508fc3d6ea8a468f31ee20a14f9330a7ee79c304b1d4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d4d6f0339a64145471a731f39983c4abd2c3231f0b38c2e13cc0df069dada1e
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": 0.0007270377251797399,
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": 61.527,
103
  "eval_steps_per_second": 30.769,
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": 440530014044160.0,
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": 0.0008078196946441554,
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": 61.527,
103
  "eval_steps_per_second": 30.769,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.0008078196946441554,
108
+ "grad_norm": 9.221755981445312,
109
+ "learning_rate": 0.0002,
110
+ "loss": 2.0402,
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": 489477793382400.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null