ClarenceDan commited on
Commit
a6c4a74
·
verified ·
1 Parent(s): 055c150

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:c6fa9f9c791e18c95d2271f87af0e7ac47313961b8db900dc667be9bb05cf270
3
  size 41581360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de0f164b4a111f2e0310a440b32dfaa8b4cbb2484a6ac1d34fb1abc7a9f04862
3
  size 41581360
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a089dcc1c93e669698367b35a6a375c35d785c495f818edd6e8361462ab5fdc9
3
  size 21505540
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44dedaad705cab65cc92432030e35aabccf4c7d6998b86f8665d6be985b03652
3
  size 21505540
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da662baf38cac1b2e9945c5822d11e6b74700c077b7f37965a15cb65da3f166a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17ec2e8c04cc751a5a6af7513d2ea83ef31ac2783cc9bedae94e23c77cbfc450
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": 0.042105263157894736,
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": 36.623,
103
  "eval_steps_per_second": 18.311,
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": 475092464173056.0,
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": 0.04678362573099415,
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": 36.623,
103
  "eval_steps_per_second": 18.311,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.04678362573099415,
108
+ "grad_norm": 1.013899326324463,
109
+ "learning_rate": 0.0002,
110
+ "loss": 0.7326,
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": 525102197243904.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null