ramdhanfirdaus commited on
Commit
6db2665
1 Parent(s): 4dcd199

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 sha256:264e4607558613b4a0bcec5d055fbffbad1311b86c7aedffa0b393bfceeca70d
3
  size 50338848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9902761dfb3698eca87f5ead41ea9eea52e5996bd1b9c30ab8e82247d2abf729
3
  size 50338848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a137376c95f4682b3cb50c655e1becbb1d6ca89f14c213e7d9ed2567dcb7071c
3
  size 100693001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d2a4ad63afe748b055da23cfae531cd1b4bd259fd254d6d65b869b3309a3793
3
  size 100693001
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8cb585a748a6df427c7d10de4790a4f273c745429b7f17704596f5b448d6d2ce
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bf0e7c8e6f58ca05bfa9a01c0e15652940b7d2d941987650d7e5fe4b9d6deb1
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": 1.6456865072250366,
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": 43.705,
148
  "eval_steps_per_second": 5.468,
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": 5.961752561722982e+16,
157
  "trial_name": null,
158
  "trial_params": null
159
  }
 
1
  {
2
+ "best_metric": 1.6236809492111206,
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": 43.705,
148
  "eval_steps_per_second": 5.468,
149
  "step": 1000
150
+ },
151
+ {
152
+ "epoch": 0.8,
153
+ "learning_rate": 0.0002,
154
+ "loss": 1.6381,
155
+ "step": 1100
156
+ },
157
+ {
158
+ "epoch": 0.8,
159
+ "eval_loss": 1.6236809492111206,
160
+ "eval_runtime": 143.4948,
161
+ "eval_samples_per_second": 43.723,
162
+ "eval_steps_per_second": 5.471,
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": 6.556878282198221e+16,
171
  "trial_name": null,
172
  "trial_params": null
173
  }