brixeus commited on
Commit
6d12b70
·
verified ·
1 Parent(s): 8b90e83

Training in progress, step 36, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8354570fb497f9a3376c9622903a026631f74201972848896a8830f91128ee6d
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f4ef18667cb45fc42a9bd8331414640f5fef275137ef4fdde8a461d57fc4257
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed6d653f5d3cfb5cfb7843e2e1ee22d85138f82efc41e1aa1ca99e635ac78db7
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16caa162391e5d2cd2758fafe671b8da923fb0c5d6b9b102fe7ebabe09ac3e3d
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b4f63aec6d8b3291c19fe2b4497f750eeddd6b87b84886cefc94a6bfc39de55
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d74b05f2720b311440022765a28fc8006a7374957aaca6aca1b5e6bc5db4cbaa
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
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": 0.031159838430467397,
5
  "eval_steps": 9,
6
- "global_step": 27,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -102,6 +102,35 @@
102
  "eval_samples_per_second": 13.964,
103
  "eval_steps_per_second": 1.75,
104
  "step": 27
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
105
  }
106
  ],
107
  "logging_steps": 3,
@@ -121,7 +150,7 @@
121
  "attributes": {}
122
  }
123
  },
124
- "total_flos": 3.785771086302413e+16,
125
  "train_batch_size": 8,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0415464512406232,
5
  "eval_steps": 9,
6
+ "global_step": 36,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
102
  "eval_samples_per_second": 13.964,
103
  "eval_steps_per_second": 1.75,
104
  "step": 27
105
+ },
106
+ {
107
+ "epoch": 0.03462204270051933,
108
+ "grad_norm": 3.892972230911255,
109
+ "learning_rate": 8.83022221559489e-05,
110
+ "loss": 7.737,
111
+ "step": 30
112
+ },
113
+ {
114
+ "epoch": 0.038084246970571264,
115
+ "grad_norm": 4.205379962921143,
116
+ "learning_rate": 8.473291852294987e-05,
117
+ "loss": 7.7768,
118
+ "step": 33
119
+ },
120
+ {
121
+ "epoch": 0.0415464512406232,
122
+ "grad_norm": 4.217511177062988,
123
+ "learning_rate": 8.07830737662829e-05,
124
+ "loss": 7.7462,
125
+ "step": 36
126
+ },
127
+ {
128
+ "epoch": 0.0415464512406232,
129
+ "eval_loss": 1.9257190227508545,
130
+ "eval_runtime": 104.5925,
131
+ "eval_samples_per_second": 13.959,
132
+ "eval_steps_per_second": 1.75,
133
+ "step": 36
134
  }
135
  ],
136
  "logging_steps": 3,
 
150
  "attributes": {}
151
  }
152
  },
153
+ "total_flos": 5.04769478173655e+16,
154
  "train_batch_size": 8,
155
  "trial_name": null,
156
  "trial_params": null