rizkyjun commited on
Commit
745a4eb
1 Parent(s): 81efbf1

Training in progress, step 1100, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c5f0dbf90ce0773bf366132a2914c1c76cc6844b8bd1dd3d373932871fc8f5f
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88b044e52c3b59ff7fdae2531e3135c2036842592ae84bd45e99c04c6a9aebb9
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4ff097348929f737de5e1f3683a008f91e1ba74accb6599c925eb581c325f4b
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41938fb73ccec05ca574eb60bdc917842fa31d5cb2a544e416d67ea215e44661
3
  size 18902665
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:741013df0f2c38258d3aad4259e56feb3245d57324e1c9624b55abdc9cee37a6
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f20c2190e118e996b514a3787fd9ec2b8fad8f8e5b5e6e65b3757eac6356c279
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3bb7339d1d2da342a44f3ba5e076fb6e5d93aee86f890c002703d2b3a0750820
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f5f3a2d7191245a70e1410d8951fd2f5c94b0b91f13bf39c3f76fe8aaf57fd4
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.463895559310913,
3
- "best_model_checkpoint": "./outputs/checkpoint-1000",
4
- "epoch": 0.7285974499089253,
5
  "eval_steps": 100,
6
- "global_step": 1000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -147,13 +147,27 @@
147
  "eval_samples_per_second": 30.659,
148
  "eval_steps_per_second": 3.836,
149
  "step": 1000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
150
  }
151
  ],
152
  "logging_steps": 100,
153
  "max_steps": 4116,
154
  "num_train_epochs": 3,
155
  "save_steps": 100,
156
- "total_flos": 2.84738668720128e+16,
157
  "trial_name": null,
158
  "trial_params": null
159
  }
 
1
  {
2
+ "best_metric": 2.439748525619507,
3
+ "best_model_checkpoint": "./outputs/checkpoint-1100",
4
+ "epoch": 0.8014571948998178,
5
  "eval_steps": 100,
6
+ "global_step": 1100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
147
  "eval_samples_per_second": 30.659,
148
  "eval_steps_per_second": 3.836,
149
  "step": 1000
150
+ },
151
+ {
152
+ "epoch": 0.8,
153
+ "learning_rate": 0.0002,
154
+ "loss": 2.4666,
155
+ "step": 1100
156
+ },
157
+ {
158
+ "epoch": 0.8,
159
+ "eval_loss": 2.439748525619507,
160
+ "eval_runtime": 204.5892,
161
+ "eval_samples_per_second": 30.666,
162
+ "eval_steps_per_second": 3.837,
163
+ "step": 1100
164
  }
165
  ],
166
  "logging_steps": 100,
167
  "max_steps": 4116,
168
  "num_train_epochs": 3,
169
  "save_steps": 100,
170
+ "total_flos": 3.13118620803072e+16,
171
  "trial_name": null,
172
  "trial_params": null
173
  }