End of training
Browse files- README.md +6 -6
- logs/events.out.tfevents.1705983419.70e47a1f5afe.42.15 +3 -0
- model.safetensors +1 -1
- trainer_state.json +17 -3
README.md
CHANGED
|
@@ -13,12 +13,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
This model was trained from scratch on an unknown dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
-
- eval_loss: 5.
|
| 17 |
-
- eval_runtime: 0.
|
| 18 |
-
- eval_samples_per_second:
|
| 19 |
-
- eval_steps_per_second:
|
| 20 |
-
- epoch:
|
| 21 |
-
- step:
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 13 |
|
| 14 |
This model was trained from scratch on an unknown dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
+
- eval_loss: 5.3555
|
| 17 |
+
- eval_runtime: 0.0182
|
| 18 |
+
- eval_samples_per_second: 55.091
|
| 19 |
+
- eval_steps_per_second: 55.091
|
| 20 |
+
- epoch: 50.0
|
| 21 |
+
- step: 50
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
logs/events.out.tfevents.1705983419.70e47a1f5afe.42.15
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb242beabbd921fd08ac78989fe5c9c76825dbe29cfaa8cee47aab4b361be341
|
| 3 |
+
size 7086
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 435756040
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c839309986c2e3deebcb4dff61f0cc17ea04289c9211db54f017e6729a356c2f
|
| 3 |
size 435756040
|
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 4.924107074737549,
|
| 3 |
"best_model_checkpoint": "ner-bert-ingredients/checkpoint-20",
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 10,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -63,6 +63,20 @@
|
|
| 63 |
"eval_samples_per_second": 54.098,
|
| 64 |
"eval_steps_per_second": 54.098,
|
| 65 |
"step": 40
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 66 |
}
|
| 67 |
],
|
| 68 |
"logging_steps": 10,
|
|
@@ -70,7 +84,7 @@
|
|
| 70 |
"num_input_tokens_seen": 0,
|
| 71 |
"num_train_epochs": 50,
|
| 72 |
"save_steps": 10,
|
| 73 |
-
"total_flos":
|
| 74 |
"train_batch_size": 16,
|
| 75 |
"trial_name": null,
|
| 76 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 4.924107074737549,
|
| 3 |
"best_model_checkpoint": "ner-bert-ingredients/checkpoint-20",
|
| 4 |
+
"epoch": 50.0,
|
| 5 |
"eval_steps": 10,
|
| 6 |
+
"global_step": 50,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 63 |
"eval_samples_per_second": 54.098,
|
| 64 |
"eval_steps_per_second": 54.098,
|
| 65 |
"step": 40
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 50.0,
|
| 69 |
+
"learning_rate": 4e-05,
|
| 70 |
+
"loss": 0.0043,
|
| 71 |
+
"step": 50
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 50.0,
|
| 75 |
+
"eval_loss": 5.35546875,
|
| 76 |
+
"eval_runtime": 0.0182,
|
| 77 |
+
"eval_samples_per_second": 55.091,
|
| 78 |
+
"eval_steps_per_second": 55.091,
|
| 79 |
+
"step": 50
|
| 80 |
}
|
| 81 |
],
|
| 82 |
"logging_steps": 10,
|
|
|
|
| 84 |
"num_input_tokens_seen": 0,
|
| 85 |
"num_train_epochs": 50,
|
| 86 |
"save_steps": 10,
|
| 87 |
+
"total_flos": 32856154788600.0,
|
| 88 |
"train_batch_size": 16,
|
| 89 |
"trial_name": null,
|
| 90 |
"trial_params": null
|