End of training
Browse files- README.md +47 -0
- model.safetensors +3 -0
- trainer_state.json +32 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: tmp_trainer
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# tmp_trainer
|
| 14 |
+
|
| 15 |
+
This model was trained from scratch on an unknown dataset.
|
| 16 |
+
|
| 17 |
+
## Model description
|
| 18 |
+
|
| 19 |
+
More information needed
|
| 20 |
+
|
| 21 |
+
## Intended uses & limitations
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Training and evaluation data
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training procedure
|
| 30 |
+
|
| 31 |
+
### Training hyperparameters
|
| 32 |
+
|
| 33 |
+
The following hyperparameters were used during training:
|
| 34 |
+
- learning_rate: 5e-05
|
| 35 |
+
- train_batch_size: 8
|
| 36 |
+
- eval_batch_size: 8
|
| 37 |
+
- seed: 42
|
| 38 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 39 |
+
- lr_scheduler_type: linear
|
| 40 |
+
- num_epochs: 3.0
|
| 41 |
+
|
| 42 |
+
### Framework versions
|
| 43 |
+
|
| 44 |
+
- Transformers 4.44.2
|
| 45 |
+
- Pytorch 2.4.0+cu124
|
| 46 |
+
- Datasets 2.20.0
|
| 47 |
+
- Tokenizers 0.19.1
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:040e0f67acf5450cc251902d4aafbe1a6f12ff7e55e75fa7dd802e6b08bb5f8f
|
| 3 |
+
size 683204372
|
trainer_state.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": null,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 0,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [],
|
| 11 |
+
"logging_steps": 500,
|
| 12 |
+
"max_steps": 0,
|
| 13 |
+
"num_input_tokens_seen": 0,
|
| 14 |
+
"num_train_epochs": 0,
|
| 15 |
+
"save_steps": 500,
|
| 16 |
+
"stateful_callbacks": {
|
| 17 |
+
"TrainerControl": {
|
| 18 |
+
"args": {
|
| 19 |
+
"should_epoch_stop": false,
|
| 20 |
+
"should_evaluate": false,
|
| 21 |
+
"should_log": false,
|
| 22 |
+
"should_save": false,
|
| 23 |
+
"should_training_stop": false
|
| 24 |
+
},
|
| 25 |
+
"attributes": {}
|
| 26 |
+
}
|
| 27 |
+
},
|
| 28 |
+
"total_flos": 0,
|
| 29 |
+
"train_batch_size": null,
|
| 30 |
+
"trial_name": null,
|
| 31 |
+
"trial_params": null
|
| 32 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05c92ba7db09b05aa6b3230e1d6f3e8e8d9cb637c92343f915ed252de5ef45a4
|
| 3 |
+
size 5176
|