Commit
·
ed61330
1
Parent(s):
ac21502
commit files to HF hub
Browse files- config.json +31 -0
- hyper_params.json +8 -0
- pytorch_model.bin +3 -0
- trainer_state.json +25 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "logoyazilim/qna_model_2023-02-25-00-31-12-689646",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MT5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 1024,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 512,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "gelu_new",
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"eos_token_id": 1,
|
| 13 |
+
"feed_forward_proj": "gated-gelu",
|
| 14 |
+
"initializer_factor": 1.0,
|
| 15 |
+
"is_encoder_decoder": true,
|
| 16 |
+
"is_gated_act": true,
|
| 17 |
+
"layer_norm_epsilon": 1e-06,
|
| 18 |
+
"model_type": "mt5",
|
| 19 |
+
"num_decoder_layers": 8,
|
| 20 |
+
"num_heads": 6,
|
| 21 |
+
"num_layers": 8,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"relative_attention_max_distance": 128,
|
| 24 |
+
"relative_attention_num_buckets": 32,
|
| 25 |
+
"tie_word_embeddings": false,
|
| 26 |
+
"tokenizer_class": "T5Tokenizer",
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.22.2",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 250102
|
| 31 |
+
}
|
hyper_params.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"per_device_train_batch_size": 4,
|
| 3 |
+
"per_device_eval_batch_size": 4,
|
| 4 |
+
"gradient_accumulation_steps": 8,
|
| 5 |
+
"learning_rate": 0.0003,
|
| 6 |
+
"num_train_epochs": 15,
|
| 7 |
+
"max_steps": -1
|
| 8 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17953ff66de60b1194e62b703cf735b30beaca923f6085939ff4ed5b6c33bbfc
|
| 3 |
+
size 1200729797
|
trainer_state.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 14.955974842767295,
|
| 5 |
+
"global_step": 285,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 14.96,
|
| 12 |
+
"step": 285,
|
| 13 |
+
"total_flos": 5005524420526080.0,
|
| 14 |
+
"train_loss": 0.7459469443873356,
|
| 15 |
+
"train_runtime": 839.4691,
|
| 16 |
+
"train_samples_per_second": 11.329,
|
| 17 |
+
"train_steps_per_second": 0.34
|
| 18 |
+
}
|
| 19 |
+
],
|
| 20 |
+
"max_steps": 285,
|
| 21 |
+
"num_train_epochs": 15,
|
| 22 |
+
"total_flos": 5005524420526080.0,
|
| 23 |
+
"trial_name": null,
|
| 24 |
+
"trial_params": null
|
| 25 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad3078628b800f103ae511c9faaa58e397c7a1bc80fe6b4ed983b232cb9857a1
|
| 3 |
+
size 3375
|