Training in progress, epoch 1, checkpoint
Browse files- last-checkpoint/config.json +37 -0
- last-checkpoint/dict.txt +0 -0
- last-checkpoint/generation_config.json +9 -0
- last-checkpoint/model.safetensors +3 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/sentencepiece.bpe.model +3 -0
- last-checkpoint/special_tokens_map.json +15 -0
- last-checkpoint/tokenizer_config.json +55 -0
- last-checkpoint/trainer_state.json +83 -0
- last-checkpoint/training_args.bin +3 -0
last-checkpoint/config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "vinai/bartpho-syllable",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"architectures": [
|
6 |
+
"MBartForConditionalGeneration"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"bos_token_id": 0,
|
10 |
+
"classifier_dropout": 0.0,
|
11 |
+
"d_model": 1024,
|
12 |
+
"decoder_attention_heads": 16,
|
13 |
+
"decoder_ffn_dim": 4096,
|
14 |
+
"decoder_layerdrop": 0.0,
|
15 |
+
"decoder_layers": 12,
|
16 |
+
"decoder_start_token_id": 2,
|
17 |
+
"dropout": 0.1,
|
18 |
+
"encoder_attention_heads": 16,
|
19 |
+
"encoder_ffn_dim": 4096,
|
20 |
+
"encoder_layerdrop": 0.0,
|
21 |
+
"encoder_layers": 12,
|
22 |
+
"eos_token_id": 2,
|
23 |
+
"forced_eos_token_id": 2,
|
24 |
+
"gradient_checkpointing": false,
|
25 |
+
"init_std": 0.02,
|
26 |
+
"is_encoder_decoder": true,
|
27 |
+
"max_position_embeddings": 1024,
|
28 |
+
"model_type": "mbart",
|
29 |
+
"num_hidden_layers": 12,
|
30 |
+
"pad_token_id": 1,
|
31 |
+
"scale_embedding": false,
|
32 |
+
"tokenizer_class": "BartphoTokenizer",
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.44.2",
|
35 |
+
"use_cache": true,
|
36 |
+
"vocab_size": 40030
|
37 |
+
}
|
last-checkpoint/dict.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
last-checkpoint/generation_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"decoder_start_token_id": 2,
|
5 |
+
"eos_token_id": 2,
|
6 |
+
"forced_eos_token_id": 2,
|
7 |
+
"pad_token_id": 1,
|
8 |
+
"transformers_version": "4.44.2"
|
9 |
+
}
|
last-checkpoint/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ef0a1e7b598baa0c24d42edbc80888e5cd56018af792c62351d4fe2357feba0
|
3 |
+
size 1583480280
|
last-checkpoint/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7b9bb13ef6e2498710620be2bbc305ff4126b827456102c552499a45b0528f4
|
3 |
+
size 3166950939
|
last-checkpoint/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35c014650e3c84b215306c3bf7757946cefea7c103430a269c3bbbc1c4778734
|
3 |
+
size 14244
|
last-checkpoint/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2dfae99b7c7eb9c1ab60d210efed69fa581dc2f02540b0acffc43b5e4c1c5aa0
|
3 |
+
size 1064
|
last-checkpoint/sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
last-checkpoint/special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
last-checkpoint/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"40029": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": true,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"eos_token": "</s>",
|
48 |
+
"mask_token": "<mask>",
|
49 |
+
"model_max_length": 1000000000000000019884624838656,
|
50 |
+
"pad_token": "<pad>",
|
51 |
+
"sep_token": "</s>",
|
52 |
+
"sp_model_kwargs": {},
|
53 |
+
"tokenizer_class": "BartphoTokenizer",
|
54 |
+
"unk_token": "<unk>"
|
55 |
+
}
|
last-checkpoint/trainer_state.json
ADDED
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.1306794434785843,
|
3 |
+
"best_model_checkpoint": "./vit5_qqp/checkpoint-3285",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 3285,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.15220700152207,
|
13 |
+
"grad_norm": 0.6250647902488708,
|
14 |
+
"learning_rate": 4.7463216641298836e-05,
|
15 |
+
"loss": 0.5593,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.30441400304414,
|
20 |
+
"grad_norm": 0.41860121488571167,
|
21 |
+
"learning_rate": 4.492643328259767e-05,
|
22 |
+
"loss": 0.2028,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.45662100456621,
|
27 |
+
"grad_norm": 0.5042670369148254,
|
28 |
+
"learning_rate": 4.2389649923896504e-05,
|
29 |
+
"loss": 0.1702,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.60882800608828,
|
34 |
+
"grad_norm": 0.357123464345932,
|
35 |
+
"learning_rate": 3.985286656519534e-05,
|
36 |
+
"loss": 0.1601,
|
37 |
+
"step": 2000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.76103500761035,
|
41 |
+
"grad_norm": 0.398662805557251,
|
42 |
+
"learning_rate": 3.731608320649417e-05,
|
43 |
+
"loss": 0.1551,
|
44 |
+
"step": 2500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.91324200913242,
|
48 |
+
"grad_norm": 1.139906644821167,
|
49 |
+
"learning_rate": 3.4779299847793e-05,
|
50 |
+
"loss": 0.1485,
|
51 |
+
"step": 3000
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.0,
|
55 |
+
"eval_loss": 0.1306794434785843,
|
56 |
+
"eval_runtime": 178.8964,
|
57 |
+
"eval_samples_per_second": 73.16,
|
58 |
+
"eval_steps_per_second": 2.035,
|
59 |
+
"step": 3285
|
60 |
+
}
|
61 |
+
],
|
62 |
+
"logging_steps": 500,
|
63 |
+
"max_steps": 9855,
|
64 |
+
"num_input_tokens_seen": 0,
|
65 |
+
"num_train_epochs": 3,
|
66 |
+
"save_steps": 500,
|
67 |
+
"stateful_callbacks": {
|
68 |
+
"TrainerControl": {
|
69 |
+
"args": {
|
70 |
+
"should_epoch_stop": false,
|
71 |
+
"should_evaluate": false,
|
72 |
+
"should_log": false,
|
73 |
+
"should_save": true,
|
74 |
+
"should_training_stop": false
|
75 |
+
},
|
76 |
+
"attributes": {}
|
77 |
+
}
|
78 |
+
},
|
79 |
+
"total_flos": 2.50210369339392e+16,
|
80 |
+
"train_batch_size": 36,
|
81 |
+
"trial_name": null,
|
82 |
+
"trial_params": null
|
83 |
+
}
|
last-checkpoint/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec1515f162a029fab7e155228ed70c0938ac4053dd64d85109ee8cebf8125d90
|
3 |
+
size 5176
|