willtensora commited on
Commit
682826f
·
verified ·
1 Parent(s): 636c2e8

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 sha256:7bc7a3dcaa0936d88e3c4e6301833d8df12db7c199911f4fe07ffeec9b60201f
3
  size 14696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e4fc91b5b15f5867d1a7cd3e8f087ae342818f37446ea0e462c8829bea9cf83
3
  size 14696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9169737eff5da66f3d68a19bab412e4b34d0490c48a12f738affef168e29ae99
3
  size 39398
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abe6fb12c4a7eac7403ae28746ebe4773ef59bd2b81414c2cde757be4b72ab5e
3
  size 39398
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8931450438ae8b2419522305b04898208d1e1d8a63833a5b129ef7578886f1d
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d72d7ea22c77570d9f0b88ee6c374873539a76f4bdfadda50933cc65992b9c8
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:ea7a5d7f6a3e29c541f8194ea05fcd850e8a829cfe8d61c1d58566b8e5a092cf
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8acd44aea89adc155a830cbfb990e7f2a2f3c98d29366996401b6b1b0b798b77
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": 0.010095344924284913,
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": 456.359,
103
  "eval_steps_per_second": 114.242,
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": 2156445696.0,
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": 0.011217049915872126,
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": 456.359,
103
  "eval_steps_per_second": 114.242,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.011217049915872126,
108
+ "grad_norm": 0.010091469623148441,
109
+ "learning_rate": 0.0002,
110
+ "loss": 11.9328,
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": 2392768512.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null