Model save
Browse files- README.md +2 -2
- all_results.json +15 -0
- eval_results.json +10 -0
- train_results.json +8 -0
- trainer_state.json +60 -0
README.md
CHANGED
|
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 1.
|
| 21 |
-
- Accuracy: 0.
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 1.6915
|
| 21 |
+
- Accuracy: 0.6749
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.0,
|
| 3 |
+
"eval_accuracy": 0.6748837865685497,
|
| 4 |
+
"eval_loss": 1.6915348768234253,
|
| 5 |
+
"eval_runtime": 75.3619,
|
| 6 |
+
"eval_samples": 15520,
|
| 7 |
+
"eval_samples_per_second": 205.94,
|
| 8 |
+
"eval_steps_per_second": 25.742,
|
| 9 |
+
"perplexity": 5.427805327461157,
|
| 10 |
+
"train_loss": 1.9789411544799804,
|
| 11 |
+
"train_runtime": 156.255,
|
| 12 |
+
"train_samples": 124120,
|
| 13 |
+
"train_samples_per_second": 1.024,
|
| 14 |
+
"train_steps_per_second": 0.064
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.0,
|
| 3 |
+
"eval_accuracy": 0.6748837865685497,
|
| 4 |
+
"eval_loss": 1.6915348768234253,
|
| 5 |
+
"eval_runtime": 75.3619,
|
| 6 |
+
"eval_samples": 15520,
|
| 7 |
+
"eval_samples_per_second": 205.94,
|
| 8 |
+
"eval_steps_per_second": 25.742,
|
| 9 |
+
"perplexity": 5.427805327461157
|
| 10 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.0,
|
| 3 |
+
"train_loss": 1.9789411544799804,
|
| 4 |
+
"train_runtime": 156.255,
|
| 5 |
+
"train_samples": 124120,
|
| 6 |
+
"train_samples_per_second": 1.024,
|
| 7 |
+
"train_steps_per_second": 0.064
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.0012890750886239124,
|
| 5 |
+
"eval_steps": 5,
|
| 6 |
+
"global_step": 10,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 5e-05,
|
| 14 |
+
"loss": 2.0686,
|
| 15 |
+
"step": 5
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.0,
|
| 19 |
+
"eval_accuracy": 0.6686630088781412,
|
| 20 |
+
"eval_loss": 1.7577065229415894,
|
| 21 |
+
"eval_runtime": 76.2786,
|
| 22 |
+
"eval_samples_per_second": 203.465,
|
| 23 |
+
"eval_steps_per_second": 25.433,
|
| 24 |
+
"step": 5
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.0,
|
| 28 |
+
"learning_rate": 0.0,
|
| 29 |
+
"loss": 1.8893,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0,
|
| 34 |
+
"eval_accuracy": 0.6742729158223068,
|
| 35 |
+
"eval_loss": 1.6961551904678345,
|
| 36 |
+
"eval_runtime": 76.8494,
|
| 37 |
+
"eval_samples_per_second": 201.953,
|
| 38 |
+
"eval_steps_per_second": 25.244,
|
| 39 |
+
"step": 10
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.0,
|
| 43 |
+
"step": 10,
|
| 44 |
+
"total_flos": 42112770048000.0,
|
| 45 |
+
"train_loss": 1.9789411544799804,
|
| 46 |
+
"train_runtime": 156.255,
|
| 47 |
+
"train_samples_per_second": 1.024,
|
| 48 |
+
"train_steps_per_second": 0.064
|
| 49 |
+
}
|
| 50 |
+
],
|
| 51 |
+
"logging_steps": 5,
|
| 52 |
+
"max_steps": 10,
|
| 53 |
+
"num_input_tokens_seen": 0,
|
| 54 |
+
"num_train_epochs": 1,
|
| 55 |
+
"save_steps": 500,
|
| 56 |
+
"total_flos": 42112770048000.0,
|
| 57 |
+
"train_batch_size": 8,
|
| 58 |
+
"trial_name": null,
|
| 59 |
+
"trial_params": null
|
| 60 |
+
}
|