ardaspear commited on
Commit
935e58b
·
verified ·
1 Parent(s): f9d6f99

Training in progress, step 35, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22cac41c482c8faca513db9f7db53b24749d07cb82eec510352f41af2e784ba5
3
  size 201892112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70641b75a24f1905ea3041488857c83c86285e6bb826b69e9d8602b6309b8550
3
  size 201892112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb1f53a378f949f188dd08f454444580c1f8c28c90388060c6c2568d80cba068
3
  size 102864548
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:619b7e0f4381d83682e22e320752df54a30df85bb540bf33d4a04e8f0012e653
3
  size 102864548
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5b0cb815397e3c92225b2dab264a7d448e514e16e7690c2e9a5cf6380cd5479
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2828d79a8bfdc705c4be7a188bf42698dbef96bc353b2ee5b661629dc0009e73
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d37b0dad6b9c48822da5c83a071d50252502799ad22c4c4907147ad4e4f8e2f4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
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": 0.005251870979036281,
5
  "eval_steps": 5,
6
- "global_step": 30,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -133,6 +133,21 @@
133
  "eval_samples_per_second": 23.666,
134
  "eval_steps_per_second": 2.959,
135
  "step": 30
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
136
  }
137
  ],
138
  "logging_steps": 3,
@@ -152,7 +167,7 @@
152
  "attributes": {}
153
  }
154
  },
155
- "total_flos": 1.2745558418522112e+16,
156
  "train_batch_size": 8,
157
  "trial_name": null,
158
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.006127182808875662,
5
  "eval_steps": 5,
6
+ "global_step": 35,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
133
  "eval_samples_per_second": 23.666,
134
  "eval_steps_per_second": 2.959,
135
  "step": 30
136
+ },
137
+ {
138
+ "epoch": 0.00577705807693991,
139
+ "grad_norm": 5.948985576629639,
140
+ "learning_rate": 3.832773180720475e-05,
141
+ "loss": 1.2086,
142
+ "step": 33
143
+ },
144
+ {
145
+ "epoch": 0.006127182808875662,
146
+ "eval_loss": 1.0342975854873657,
147
+ "eval_runtime": 406.3239,
148
+ "eval_samples_per_second": 23.678,
149
+ "eval_steps_per_second": 2.961,
150
+ "step": 35
151
  }
152
  ],
153
  "logging_steps": 3,
 
167
  "attributes": {}
168
  }
169
  },
170
+ "total_flos": 1.4878706270994432e+16,
171
  "train_batch_size": 8,
172
  "trial_name": null,
173
  "trial_params": null