great0001 commited on
Commit
b77ba4c
·
verified ·
1 Parent(s): b3ce14a

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 sha256:222e4a5ab3cef2d5653c6457623e02caf50f041c150b1d8de143bc322cac8760
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98956ad068dff07653e6406ac05b2b71b06d3e554daf87e1593eca9c7031f862
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0a3e9fa6e567a42828fdd7b17985f8ce29e38604cfbaba95c7cd1c2f0a8b916
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52e38a8ce06a1f3cbf8010e1e7f8c171c324cb161e63909ed95e8ea58bb773ee
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:200897803867d9476163ce84baa477ea4bfc2d20fbca1d606afa2d969206fa8c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3efe221c4a0adf497082884c488f9d91c42d1d873e72d47409fbf104eb83048
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": 0.03515625,
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": 34.121,
103
  "eval_steps_per_second": 17.06,
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": 1465859822321664.0,
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": 0.0390625,
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": 34.121,
103
  "eval_steps_per_second": 17.06,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.0390625,
108
+ "grad_norm": 0.6203467845916748,
109
+ "learning_rate": 0.0002,
110
+ "loss": 1.7594,
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": 1628733135912960.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null