Commit ·
7aabd9d
1
Parent(s): 0abf20d
End of training
Browse files
README.md
CHANGED
|
@@ -15,12 +15,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- eval_loss:
|
| 19 |
-
- eval_runtime:
|
| 20 |
-
- eval_samples_per_second: 59.
|
| 21 |
-
- eval_steps_per_second: 0.
|
| 22 |
-
- epoch: 0.
|
| 23 |
-
- step:
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- eval_loss: 8.6995
|
| 19 |
+
- eval_runtime: 83.8513
|
| 20 |
+
- eval_samples_per_second: 59.629
|
| 21 |
+
- eval_steps_per_second: 0.942
|
| 22 |
+
- epoch: 0.03
|
| 23 |
+
- step: 40
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 535667604
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d798163ba1887a6557a6b3f33e6aa239ed97bbbd2c9f931d72c44c7cd8eeb88
|
| 3 |
size 535667604
|
runs/Jan05_08-54-19_4b3636b992a4/events.out.tfevents.1704444861.4b3636b992a4.42.2
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c265108734da9282c8f4472a75294b8805f1a2ce8750fae89fa3375cfaba904
|
| 3 |
+
size 1717702
|
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint":
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 20,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -21,6 +21,20 @@
|
|
| 21 |
"eval_samples_per_second": 59.418,
|
| 22 |
"eval_steps_per_second": 0.939,
|
| 23 |
"step": 20
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
}
|
| 25 |
],
|
| 26 |
"logging_steps": 20,
|
|
@@ -28,7 +42,7 @@
|
|
| 28 |
"num_input_tokens_seen": 0,
|
| 29 |
"num_train_epochs": 50,
|
| 30 |
"save_steps": 20,
|
| 31 |
-
"total_flos":
|
| 32 |
"train_batch_size": 16,
|
| 33 |
"trial_name": null,
|
| 34 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 9.321273803710938,
|
| 3 |
+
"best_model_checkpoint": "ner-bert-ingredients/checkpoint-20",
|
| 4 |
+
"epoch": 0.02694509936005389,
|
| 5 |
"eval_steps": 20,
|
| 6 |
+
"global_step": 40,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 21 |
"eval_samples_per_second": 59.418,
|
| 22 |
"eval_steps_per_second": 0.939,
|
| 23 |
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03,
|
| 27 |
+
"learning_rate": 4.9973045822102424e-05,
|
| 28 |
+
"loss": 9.0849,
|
| 29 |
+
"step": 40
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.03,
|
| 33 |
+
"eval_loss": 8.699505805969238,
|
| 34 |
+
"eval_runtime": 83.8513,
|
| 35 |
+
"eval_samples_per_second": 59.629,
|
| 36 |
+
"eval_steps_per_second": 0.942,
|
| 37 |
+
"step": 40
|
| 38 |
}
|
| 39 |
],
|
| 40 |
"logging_steps": 20,
|
|
|
|
| 42 |
"num_input_tokens_seen": 0,
|
| 43 |
"num_train_epochs": 50,
|
| 44 |
"save_steps": 20,
|
| 45 |
+
"total_flos": 865668287692800.0,
|
| 46 |
"train_batch_size": 16,
|
| 47 |
"trial_name": null,
|
| 48 |
"trial_params": null
|