tensor24 commited on
Commit
55927f0
·
verified ·
1 Parent(s): 2299e72

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:d21f55455722d053515580408d99cda248d50c0fa47561f0185f325fe43b964d
3
  size 83115256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae98d54a0275297103c0cd8b271ea96638b185d0d23af2b79dc10b7bc8fd3c7b
3
  size 83115256
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:276f6cc5675d9ca44d29ff8707e6bc1abb99ccbf1347e7cff58ad33ff3fd06d6
3
  size 42608388
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:707c02b4fce280dcd474f320cf052e8c04230af3b169de82a6bfa8df1a560cbf
3
  size 42608388
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db13dd957a33e561e20367fe3aa0d58ccdccd5ed65c6b37c646151e1dbd0766a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:463c0fba7ade4e33699ecce9cf05418a5fc3cc71ff3fc3ff1afcaf0781921491
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": 0.019427954668105773,
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": 3.485,
103
  "eval_steps_per_second": 1.752,
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": 3619073845886976.0,
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": 0.021586616297895305,
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": 3.485,
103
  "eval_steps_per_second": 1.752,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.021586616297895305,
108
+ "grad_norm": 1.224662184715271,
109
+ "learning_rate": 0.0002,
110
+ "loss": 1.3615,
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": 4021193162096640.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null