ardaspear commited on
Commit
ff93a37
·
verified ·
1 Parent(s): ef242fa

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 sha256:005e80a0da39dc5a9402a1c6eae4c4259ff55441b8c8e0f354d2bedb6e1a4150
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:155aff1ad127fcdb772bc62310c86b295b1e4b7e21a26dcf250038cdcc89f3e1
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb940ebf47f948dde819a227650a19932f8170cea411fe83bc640234ac5b89b3
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53b0e1d63b70898f4b958af784e4ed06908d3ee6e7aaed9019a5474f1d24eb08
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4bc0fbdde4f390cae1da26df59eb2c832095420c66886351f99a6e9b7aa264e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6c760e18afd0b6280aeb7d401fe56fa9e714d09b578fad90d37a6e9ad6827b0
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": 0.01698994761432819,
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": 12.498,
134
  "eval_steps_per_second": 3.127,
135
  "step": 30
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
136
  }
137
  ],
138
  "logging_steps": 3,
@@ -152,7 +167,7 @@
152
  "attributes": {}
153
  }
154
  },
155
- "total_flos": 4.525540736237568e+16,
156
  "train_batch_size": 4,
157
  "trial_name": null,
158
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.019821605550049554,
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": 12.498,
134
  "eval_steps_per_second": 3.127,
135
  "step": 30
136
+ },
137
+ {
138
+ "epoch": 0.01868894237576101,
139
+ "grad_norm": 3.493994951248169,
140
+ "learning_rate": 3.832773180720475e-05,
141
+ "loss": 4.0664,
142
+ "step": 33
143
+ },
144
+ {
145
+ "epoch": 0.019821605550049554,
146
+ "eval_loss": 4.008715629577637,
147
+ "eval_runtime": 237.9336,
148
+ "eval_samples_per_second": 12.499,
149
+ "eval_steps_per_second": 3.127,
150
+ "step": 35
151
  }
152
  ],
153
  "logging_steps": 3,
 
167
  "attributes": {}
168
  }
169
  },
170
+ "total_flos": 5.279797525610496e+16,
171
  "train_batch_size": 4,
172
  "trial_name": null,
173
  "trial_params": null