philip-hightech commited on
Commit
f23559e
·
verified ·
1 Parent(s): 8ab7509

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:fbe431a2ba926ce777e7f9b02271966c1cecf4832f8df19cd004c3973e26d5a1
3
  size 80792096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8499e727cdfc0f4d915a86f8180f77bf32b288eeddca27378bb1b86580e8599b
3
  size 80792096
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98685801bb794c4f4d8ddc8c6f8e8c34ad9e718146700ef13c513bc1678b8f25
3
  size 41459700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31ae0998e20e73779ebc75d5428ae8b9c7b7f05b53e1e0a1b17e26751a427419
3
  size 41459700
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0b77f278dcace3954c8a0406b8cd521a9f7d5e54485350ef22d7ee85c9deea8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:362068f071c066a9d898607e7ea5073f2cf9c4561b0c7ca71c5e406114a72d0d
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": 0.004648160103292447,
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": 28.651,
103
  "eval_steps_per_second": 14.325,
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": 2091163255308288.0,
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": 0.005164622336991607,
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": 28.651,
103
  "eval_steps_per_second": 14.325,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.005164622336991607,
108
+ "grad_norm": 2.194230318069458,
109
+ "learning_rate": 0.0002,
110
+ "loss": 2.4902,
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": 2352558662221824.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null