tensor24 commited on
Commit
a3814d2
1 Parent(s): dc867aa

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:a81dcf912672011d6b18d72c3e98c0268c510dd41186ed4a57d8dcb6115db9ba
3
  size 45118424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:231a0b2e2c3eb92d59f780a92371830900e0501f2b6b23a1fb714ac905cec1c0
3
  size 45118424
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a3454901f405a347de0afd1164ef364e26f1b70296934e8574a3eaad23667aa
3
  size 23159290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a81918c6c54b55a54c756fc85d4e211c8922176bbf6ea9b3e3aa555425dc566
3
  size 23159290
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3bfdd4759d022b9b654d7221f1024352678ea5e8b079c7927af8bde5f8ffd92c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32fae2f082bc2b8a4f93f074fb88d1c6113a4081d21b0babdad2ac6534f83080
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": 0.01366223908918406,
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": 6.692,
103
  "eval_steps_per_second": 3.346,
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": 1741900625215488.0,
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": 0.015180265654648957,
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": 6.692,
103
  "eval_steps_per_second": 3.346,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.015180265654648957,
108
+ "grad_norm": 4.6534504890441895,
109
+ "learning_rate": 0.0002,
110
+ "loss": 1.4058,
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": 1935445139128320.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null