clarxus commited on
Commit
b1a32ba
·
verified ·
1 Parent(s): fb8549a

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 sha256:5873d1383584948a3d38fae98287e1b387aad0d1ee8973b96120ec22a1cb4114
3
  size 161533192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbf4b36e48ff516d866d955e7eda077c33631c4860ad1f608d6c85e11b966eb1
3
  size 161533192
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d04b9fb2eaa2d3722eb6c6b0b3735ed394aa7e72e0c71edc4b6e8ee3a768e6c
3
  size 82460660
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8138898e31cebb7d8def282d3bf3228bc6a4c074b9ed4d461c41b9deb11ca12d
3
  size 82460660
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c31810ad875dd7e946b118571d514f7b65886850eb7e803620def1b522979375
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:424cf404966254c904350610f1e2f75e30dbe16c3b30615e8044e71b30df9995
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc389ed2ec8a0148b9b29024154a8f2f11c6a7454ef1d0724563562d03a46e01
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": 0.3068181818181818,
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": 8.68,
103
  "eval_steps_per_second": 1.114,
104
  "step": 27
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
105
  }
106
  ],
107
  "logging_steps": 3,
@@ -121,7 +150,7 @@
121
  "attributes": {}
122
  }
123
  },
124
- "total_flos": 6.221444370608947e+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": 0.4090909090909091,
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": 8.68,
103
  "eval_steps_per_second": 1.114,
104
  "step": 27
105
+ },
106
+ {
107
+ "epoch": 0.3409090909090909,
108
+ "grad_norm": 1.427184820175171,
109
+ "learning_rate": 4.415111107797445e-05,
110
+ "loss": 2.1669,
111
+ "step": 30
112
+ },
113
+ {
114
+ "epoch": 0.375,
115
+ "grad_norm": 1.5676186084747314,
116
+ "learning_rate": 4.2366459261474933e-05,
117
+ "loss": 2.2602,
118
+ "step": 33
119
+ },
120
+ {
121
+ "epoch": 0.4090909090909091,
122
+ "grad_norm": 1.4393879175186157,
123
+ "learning_rate": 4.039153688314145e-05,
124
+ "loss": 2.3522,
125
+ "step": 36
126
+ },
127
+ {
128
+ "epoch": 0.4090909090909091,
129
+ "eval_loss": 2.0838232040405273,
130
+ "eval_runtime": 17.0641,
131
+ "eval_samples_per_second": 8.673,
132
+ "eval_steps_per_second": 1.113,
133
+ "step": 36
134
  }
135
  ],
136
  "logging_steps": 3,
 
150
  "attributes": {}
151
  }
152
  },
153
+ "total_flos": 8.318560450589491e+16,
154
  "train_batch_size": 8,
155
  "trial_name": null,
156
  "trial_params": null