Training in progress, epoch 8, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2371770
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:080554e1afdea12f81011ab0ae0ef25478ce9dcd247e7b25f2c94ee9a6223771
|
| 3 |
size 2371770
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 990409330
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10e85ece5a992a1a0ab63f817a0f6162f66c8f288c8a6045ee940c7e3235378b
|
| 3 |
size 990409330
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9690a12a9a42c35516e6fbfe26ab2d65dfa0fd3e0c6b66b4b634b579ffec391
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1dfc5d86de55408c234cae75695e57cabf239fe23cf052735ae3cd35550d49f7
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 2.
|
| 3 |
-
"best_model_checkpoint": "dq158/coqui/checkpoint-
|
| 4 |
-
"epoch": 8.
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -237,13 +237,38 @@
|
|
| 237 |
"eval_steps_per_second": 0.607,
|
| 238 |
"eval_translation_length": 56070,
|
| 239 |
"step": 6650
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 240 |
}
|
| 241 |
],
|
| 242 |
"logging_steps": 500,
|
| 243 |
"max_steps": 16620,
|
| 244 |
"num_train_epochs": 20,
|
| 245 |
"save_steps": 500,
|
| 246 |
-
"total_flos": 1.
|
| 247 |
"trial_name": null,
|
| 248 |
"trial_params": null
|
| 249 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 2.0124728679656982,
|
| 3 |
+
"best_model_checkpoint": "dq158/coqui/checkpoint-7481",
|
| 4 |
+
"epoch": 8.9996992481203,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 7481,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 237 |
"eval_steps_per_second": 0.607,
|
| 238 |
"eval_translation_length": 56070,
|
| 239 |
"step": 6650
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 8.42,
|
| 243 |
+
"learning_rate": 5.8471340533801125e-05,
|
| 244 |
+
"loss": 1.986,
|
| 245 |
+
"step": 7000
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 9.0,
|
| 249 |
+
"eval_bleu": 1.0,
|
| 250 |
+
"eval_brevity_penalty": 1.0,
|
| 251 |
+
"eval_length_ratio": 1.0,
|
| 252 |
+
"eval_loss": 2.0124728679656982,
|
| 253 |
+
"eval_precisions": [
|
| 254 |
+
1.0,
|
| 255 |
+
1.0,
|
| 256 |
+
1.0,
|
| 257 |
+
1.0
|
| 258 |
+
],
|
| 259 |
+
"eval_reference_length": 56071,
|
| 260 |
+
"eval_runtime": 610.7638,
|
| 261 |
+
"eval_samples_per_second": 4.84,
|
| 262 |
+
"eval_steps_per_second": 0.606,
|
| 263 |
+
"eval_translation_length": 56071,
|
| 264 |
+
"step": 7481
|
| 265 |
}
|
| 266 |
],
|
| 267 |
"logging_steps": 500,
|
| 268 |
"max_steps": 16620,
|
| 269 |
"num_train_epochs": 20,
|
| 270 |
"save_steps": 500,
|
| 271 |
+
"total_flos": 1.6391858454370714e+17,
|
| 272 |
"trial_name": null,
|
| 273 |
"trial_params": null
|
| 274 |
}
|