adammandic87 commited on
Commit
19ae563
·
verified ·
1 Parent(s): 0d735d7

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:af365a018660eaeb234dd89306b2ab35b515d2b1df75be03c4ce1baa5ac37085
3
  size 12609416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a01d1f2e2441d80f84373304bfe08c12e696d7a954313ecd9db1dee285d48c4
3
  size 12609416
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29e6bddd66bb05ec5f2c7e8a685001574207e728c1802736c3402f736ae721d3
3
  size 6615034
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb4b1b51674b65ea1fab94a8ed07a40b0226fc7f7cdd8eec61463ea2933508e9
3
  size 6615034
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4dd2959c43a2400319de9619aa75664f6053b7ca8bf12b1e8d41e00d166b414
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79477d972881a72719e3d28a4dd10f6eb66dbbd7a10c0fca90693fb637afd868
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": 0.039045553145336226,
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": 55.243,
103
  "eval_steps_per_second": 27.906,
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": 114481220812800.0,
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": 0.04338394793926247,
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": 55.243,
103
  "eval_steps_per_second": 27.906,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.04338394793926247,
108
+ "grad_norm": 1.9527268409729004,
109
+ "learning_rate": 0.0002,
110
+ "loss": 16.0408,
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": 129495151411200.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null