Upload 6 files
Browse files- config.json +55 -0
- generation_config.json +13 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +32 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/pegasus-cnn_dailymail",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"activation_function": "relu",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": true,
|
7 |
+
"architectures": [
|
8 |
+
"PegasusForConditionalGeneration"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.1,
|
11 |
+
"bos_token_id": 0,
|
12 |
+
"classif_dropout": 0.0,
|
13 |
+
"d_model": 1024,
|
14 |
+
"decoder_attention_heads": 16,
|
15 |
+
"decoder_ffn_dim": 4096,
|
16 |
+
"decoder_layerdrop": 0.0,
|
17 |
+
"decoder_layers": 16,
|
18 |
+
"decoder_start_token_id": 0,
|
19 |
+
"dropout": 0.1,
|
20 |
+
"encoder_attention_heads": 16,
|
21 |
+
"encoder_ffn_dim": 4096,
|
22 |
+
"encoder_layerdrop": 0.0,
|
23 |
+
"encoder_layers": 16,
|
24 |
+
"eos_token_id": 1,
|
25 |
+
"extra_pos_embeddings": 1,
|
26 |
+
"forced_eos_token_id": 1,
|
27 |
+
"id2label": {
|
28 |
+
"0": "LABEL_0",
|
29 |
+
"1": "LABEL_1",
|
30 |
+
"2": "LABEL_2"
|
31 |
+
},
|
32 |
+
"init_std": 0.02,
|
33 |
+
"is_encoder_decoder": true,
|
34 |
+
"label2id": {
|
35 |
+
"LABEL_0": 0,
|
36 |
+
"LABEL_1": 1,
|
37 |
+
"LABEL_2": 2
|
38 |
+
},
|
39 |
+
"length_penalty": 0.8,
|
40 |
+
"max_length": 128,
|
41 |
+
"max_position_embeddings": 1024,
|
42 |
+
"min_length": 32,
|
43 |
+
"model_type": "pegasus",
|
44 |
+
"normalize_before": true,
|
45 |
+
"normalize_embedding": false,
|
46 |
+
"num_beams": 8,
|
47 |
+
"num_hidden_layers": 16,
|
48 |
+
"pad_token_id": 0,
|
49 |
+
"scale_embedding": true,
|
50 |
+
"static_position_embeddings": true,
|
51 |
+
"torch_dtype": "float32",
|
52 |
+
"transformers_version": "4.42.3",
|
53 |
+
"use_cache": true,
|
54 |
+
"vocab_size": 96103
|
55 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"decoder_start_token_id": 0,
|
5 |
+
"eos_token_id": 1,
|
6 |
+
"forced_eos_token_id": 1,
|
7 |
+
"length_penalty": 0.8,
|
8 |
+
"max_length": 128,
|
9 |
+
"min_length": 32,
|
10 |
+
"num_beams": 8,
|
11 |
+
"pad_token_id": 0,
|
12 |
+
"transformers_version": "4.42.3"
|
13 |
+
}
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5dad7652ecc5b119273aac05f820bdb2e2a5ac09c466123459ae5c9176a12d20
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e47041feb44e78328d111bd8d0527543ae3a2a173bdbbdf0c9a8062bcd9e9f16
|
3 |
+
size 1064
|
trainer_state.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 125,
|
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": 125,
|
13 |
+
"num_input_tokens_seen": 0,
|
14 |
+
"num_train_epochs": 1,
|
15 |
+
"save_steps": 30000,
|
16 |
+
"stateful_callbacks": {
|
17 |
+
"TrainerControl": {
|
18 |
+
"args": {
|
19 |
+
"should_epoch_stop": false,
|
20 |
+
"should_evaluate": false,
|
21 |
+
"should_log": false,
|
22 |
+
"should_save": true,
|
23 |
+
"should_training_stop": true
|
24 |
+
},
|
25 |
+
"attributes": {}
|
26 |
+
}
|
27 |
+
},
|
28 |
+
"total_flos": 361183051776000.0,
|
29 |
+
"train_batch_size": 8,
|
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 sha256:7d3f5a9695433c161f0ffe21fbe424f7d4396ae0c1742970c7825b22c32fa122
|
3 |
+
size 5112
|