Add files using upload-large-folder tool
Browse files- all_results.json +19 -0
- config.json +30 -0
- eval_results.json +13 -0
- model.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +17 -0
- train_results.json +9 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
all_results.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"eval_0_to_0": 9464,
|
| 4 |
+
"eval_0_to_1": 575,
|
| 5 |
+
"eval_1_to_0": 708,
|
| 6 |
+
"eval_1_to_1": 9253,
|
| 7 |
+
"eval_accuracy": 0.93585,
|
| 8 |
+
"eval_loss": 0.5719918608665466,
|
| 9 |
+
"eval_runtime": 107.5664,
|
| 10 |
+
"eval_samples": 20000,
|
| 11 |
+
"eval_samples_per_second": 185.932,
|
| 12 |
+
"eval_steps_per_second": 11.621,
|
| 13 |
+
"total_flos": 1.1183176359936e+18,
|
| 14 |
+
"train_loss": 0.2879694655368725,
|
| 15 |
+
"train_runtime": 108889.4327,
|
| 16 |
+
"train_samples": 80000,
|
| 17 |
+
"train_samples_per_second": 11.02,
|
| 18 |
+
"train_steps_per_second": 0.138
|
| 19 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 1024,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 4096,
|
| 16 |
+
"is_decoder": false,
|
| 17 |
+
"layer_norm_eps": 1e-05,
|
| 18 |
+
"max_position_embeddings": 514,
|
| 19 |
+
"model_type": "roberta",
|
| 20 |
+
"num_attention_heads": 16,
|
| 21 |
+
"num_hidden_layers": 24,
|
| 22 |
+
"pad_token_id": 1,
|
| 23 |
+
"position_embedding_type": "absolute",
|
| 24 |
+
"problem_type": "single_label_classification",
|
| 25 |
+
"tie_word_embeddings": true,
|
| 26 |
+
"transformers_version": "5.3.0",
|
| 27 |
+
"type_vocab_size": 1,
|
| 28 |
+
"use_cache": false,
|
| 29 |
+
"vocab_size": 50265
|
| 30 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"eval_0_to_0": 9464,
|
| 4 |
+
"eval_0_to_1": 575,
|
| 5 |
+
"eval_1_to_0": 708,
|
| 6 |
+
"eval_1_to_1": 9253,
|
| 7 |
+
"eval_accuracy": 0.93585,
|
| 8 |
+
"eval_loss": 0.5719918608665466,
|
| 9 |
+
"eval_runtime": 107.5664,
|
| 10 |
+
"eval_samples": 20000,
|
| 11 |
+
"eval_samples_per_second": 185.932,
|
| 12 |
+
"eval_steps_per_second": 11.621
|
| 13 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:273d9c1711488b3c5ff902f558c335a2e3264f595740697d5387199153ed2161
|
| 3 |
+
size 1421495360
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"cls_token": "<s>",
|
| 7 |
+
"eos_token": "</s>",
|
| 8 |
+
"errors": "replace",
|
| 9 |
+
"is_local": true,
|
| 10 |
+
"mask_token": "<mask>",
|
| 11 |
+
"model_max_length": 512,
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 15 |
+
"trim_offsets": true,
|
| 16 |
+
"unk_token": "<unk>"
|
| 17 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"total_flos": 1.1183176359936e+18,
|
| 4 |
+
"train_loss": 0.2879694655368725,
|
| 5 |
+
"train_runtime": 108889.4327,
|
| 6 |
+
"train_samples": 80000,
|
| 7 |
+
"train_samples_per_second": 11.02,
|
| 8 |
+
"train_steps_per_second": 0.138
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a1df8fc443e4852e0cc357ed89ccfbf0244f95e3bb97863a271cdd5f837e822
|
| 3 |
+
size 5265
|