lesso commited on
Commit
aa4f2e8
·
verified ·
1 Parent(s): 149b409

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 sha256:3083c31e7624313a37661f7cee7d7afdcba6fc9e54839bbb6aed7a4c6a7ff311
3
  size 101752088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18dee917a82c0cd3f8b22fc775f911fc2985e5a6819ca527a437e09325065030
3
  size 101752088
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0d631d114fdc9fa49d6deb0160925c7d29e3617efab5aed7438ca9a351d9a20
3
  size 52046596
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9978179418825fa35b1b213bf00a68ae1fcb605a0e222018a48899f1f697f069
3
  size 52046596
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80f07cf6216070249033266c72356977f28fb9e105b042f5a3ae5146b4bf1b83
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78e5401df11dd3624fee459283e2e08af2ce66ceee0ceb1f3f9d611620307a05
3
  size 14512
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c72842717b2036b82a63b7b12be12f81cb3652b8a69815f17f509d3428f86bdb
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8712572bbb70c81eddf90cb978e2877afe5101ef9379856c06bfb55ce6838ff1
3
  size 14512
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": 0.006609142647328804,
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": 6.715,
103
  "eval_steps_per_second": 1.68,
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": 1.1853691380301824e+16,
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": 0.007343491830365339,
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": 6.715,
103
  "eval_steps_per_second": 1.68,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.007343491830365339,
108
+ "grad_norm": 0.7014135718345642,
109
+ "learning_rate": 0.0002,
110
+ "loss": 0.3319,
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": 1.317076820033536e+16,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null