smilemikan commited on
Commit
5a9097f
1 Parent(s): 8b695a5

Training in progress, step 6000, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bf67f214d2d4e04492d314ab34ac1fdc2714f0dde52c3dfa7ff635857bdde52
3
  size 5125261
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:215003a50b8f24c7272539832a0fb14618692b2ee0b017b4e7d1318e49efe1b3
3
  size 5125261
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ed3be09a65e64adc9ac662a4e9b6726128dcf8d3656f943b0c1d4393ed64569
3
  size 2460465086
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67b8d47dfc827744bf2df7d7a5f49592571325ea98986d1c3a06ba257bc4050a
3
  size 2460465086
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:67ef553c0666c5e78541d49d1d2043c7e12ed2e656211745d937c9224dbbb6fe
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0be28834dc48bfbc1da80285e00e53316bd7a8fe69a474f8af17af734e5ba2f9
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c5b2dbba6c496d61a9ce914a9739f6bcf62ef28874b0004019b350031bc2708
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc464c2cb7393ae85c5c74058e5c9d9f714a415cb50f7138fd5f72ac09ddf910
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.0449471473693848,
3
- "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-5500",
4
- "epoch": 1.2117206433135053,
5
  "eval_steps": 500,
6
- "global_step": 5500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -161,13 +161,27 @@
161
  "eval_samples_per_second": 209.874,
162
  "eval_steps_per_second": 13.132,
163
  "step": 5500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
164
  }
165
  ],
166
  "logging_steps": 500,
167
  "max_steps": 60000,
168
  "num_train_epochs": 14,
169
  "save_steps": 500,
170
- "total_flos": 5568442997145600.0,
171
  "trial_name": null,
172
  "trial_params": null
173
  }
 
1
  {
2
+ "best_metric": 2.0015575885772705,
3
+ "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-6000",
4
+ "epoch": 1.3218770654329148,
5
  "eval_steps": 500,
6
+ "global_step": 6000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
161
  "eval_samples_per_second": 209.874,
162
  "eval_steps_per_second": 13.132,
163
  "step": 5500
164
+ },
165
+ {
166
+ "epoch": 1.32,
167
+ "learning_rate": 1.800066666666667e-05,
168
+ "loss": 2.1012,
169
+ "step": 6000
170
+ },
171
+ {
172
+ "epoch": 1.32,
173
+ "eval_loss": 2.0015575885772705,
174
+ "eval_runtime": 43.2116,
175
+ "eval_samples_per_second": 210.083,
176
+ "eval_steps_per_second": 13.145,
177
+ "step": 6000
178
  }
179
  ],
180
  "logging_steps": 500,
181
  "max_steps": 60000,
182
  "num_train_epochs": 14,
183
  "save_steps": 500,
184
+ "total_flos": 6071109681807360.0,
185
  "trial_name": null,
186
  "trial_params": null
187
  }