Training in progress, epoch 1
Browse files- checkpoint-270/added_tokens.json +1 -0
- checkpoint-270/config.json +75 -0
- checkpoint-270/merges.txt +0 -0
- checkpoint-270/optimizer.pt +3 -0
- checkpoint-270/pytorch_model.bin +3 -0
- checkpoint-270/rng_state.pth +3 -0
- checkpoint-270/scaler.pt +3 -0
- checkpoint-270/scheduler.pt +3 -0
- checkpoint-270/special_tokens_map.json +1 -0
- checkpoint-270/tokenizer.json +0 -0
- checkpoint-270/tokenizer_config.json +1 -0
- checkpoint-270/trainer_state.json +44 -0
- checkpoint-270/training_args.bin +3 -0
- checkpoint-270/vocab.json +0 -0
- pytorch_model.bin +1 -1
checkpoint-270/added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<CSD>": 50265}
|
checkpoint-270/config.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/bart-base",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"BartForConditionalGeneration"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.1,
|
11 |
+
"bos_token_id": 0,
|
12 |
+
"classif_dropout": 0.1,
|
13 |
+
"classifier_dropout": 0.0,
|
14 |
+
"d_model": 768,
|
15 |
+
"decoder_attention_heads": 12,
|
16 |
+
"decoder_ffn_dim": 3072,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 6,
|
19 |
+
"decoder_start_token_id": 2,
|
20 |
+
"dropout": 0.1,
|
21 |
+
"early_stopping": true,
|
22 |
+
"encoder_attention_heads": 12,
|
23 |
+
"encoder_ffn_dim": 3072,
|
24 |
+
"encoder_layerdrop": 0.0,
|
25 |
+
"encoder_layers": 6,
|
26 |
+
"eos_token_id": 2,
|
27 |
+
"forced_bos_token_id": 0,
|
28 |
+
"forced_eos_token_id": 2,
|
29 |
+
"gradient_checkpointing": false,
|
30 |
+
"id2label": {
|
31 |
+
"0": "LABEL_0",
|
32 |
+
"1": "LABEL_1",
|
33 |
+
"2": "LABEL_2"
|
34 |
+
},
|
35 |
+
"init_std": 0.02,
|
36 |
+
"is_encoder_decoder": true,
|
37 |
+
"label2id": {
|
38 |
+
"LABEL_0": 0,
|
39 |
+
"LABEL_1": 1,
|
40 |
+
"LABEL_2": 2
|
41 |
+
},
|
42 |
+
"max_position_embeddings": 1024,
|
43 |
+
"model_type": "bart",
|
44 |
+
"no_repeat_ngram_size": 3,
|
45 |
+
"normalize_before": false,
|
46 |
+
"normalize_embedding": true,
|
47 |
+
"num_beams": 4,
|
48 |
+
"num_hidden_layers": 6,
|
49 |
+
"pad_token_id": 1,
|
50 |
+
"scale_embedding": false,
|
51 |
+
"task_specific_params": {
|
52 |
+
"summarization": {
|
53 |
+
"length_penalty": 1.0,
|
54 |
+
"max_length": 128,
|
55 |
+
"min_length": 12,
|
56 |
+
"num_beams": 4
|
57 |
+
},
|
58 |
+
"summarization_cnn": {
|
59 |
+
"length_penalty": 2.0,
|
60 |
+
"max_length": 142,
|
61 |
+
"min_length": 56,
|
62 |
+
"num_beams": 4
|
63 |
+
},
|
64 |
+
"summarization_xsum": {
|
65 |
+
"length_penalty": 1.0,
|
66 |
+
"max_length": 62,
|
67 |
+
"min_length": 11,
|
68 |
+
"num_beams": 6
|
69 |
+
}
|
70 |
+
},
|
71 |
+
"torch_dtype": "float32",
|
72 |
+
"transformers_version": "4.16.2",
|
73 |
+
"use_cache": false,
|
74 |
+
"vocab_size": 50266
|
75 |
+
}
|
checkpoint-270/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-270/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45c4cd16a429a960f155b74cb52c7870d82160f0c49328faab31eaabde91c3d8
|
3 |
+
size 1115518581
|
checkpoint-270/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6cda356bb2460d5eb07d886f9da9cae5d5a5e81b62d6724fcbbed4dcb5ea98aa
|
3 |
+
size 557982265
|
checkpoint-270/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c4768f7a0a6e8284d2505123c4e3318be184713b0f86efe7fe13ffe7f7eed09
|
3 |
+
size 14503
|
checkpoint-270/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f544ff901c5748bf937092f718bc41fe9330ec3ad118d36bc0ebd6b57d312598
|
3 |
+
size 559
|
checkpoint-270/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3789084b3957d535de03fff0cbe6118954d10f7a12c1943ab4113c93077c02f
|
3 |
+
size 623
|
checkpoint-270/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
checkpoint-270/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-270/tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "trim_offsets": true, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "facebook/bart-base", "tokenizer_class": "BartTokenizer"}
|
checkpoint-270/trainer_state.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.18728719651699066,
|
3 |
+
"best_model_checkpoint": "outputs/bart-base-detox/checkpoint-270",
|
4 |
+
"epoch": 1.9953917050691246,
|
5 |
+
"global_step": 270,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"learning_rate": 9e-05,
|
13 |
+
"loss": 0.3171,
|
14 |
+
"step": 135
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_loss": 0.20179320871829987,
|
19 |
+
"eval_runtime": 11.3072,
|
20 |
+
"eval_samples_per_second": 274.16,
|
21 |
+
"eval_steps_per_second": 34.314,
|
22 |
+
"step": 135
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 2.0,
|
26 |
+
"learning_rate": 8e-05,
|
27 |
+
"loss": 0.1852,
|
28 |
+
"step": 270
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 2.0,
|
32 |
+
"eval_loss": 0.18728719651699066,
|
33 |
+
"eval_runtime": 11.1563,
|
34 |
+
"eval_samples_per_second": 277.869,
|
35 |
+
"eval_steps_per_second": 34.778,
|
36 |
+
"step": 270
|
37 |
+
}
|
38 |
+
],
|
39 |
+
"max_steps": 1350,
|
40 |
+
"num_train_epochs": 10,
|
41 |
+
"total_flos": 1076013360414720.0,
|
42 |
+
"trial_name": null,
|
43 |
+
"trial_params": null
|
44 |
+
}
|
checkpoint-270/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6779c0d7bfc5cc8b7f502411db449902ffdb3fd6d5cc4758f90defaa037cdfa
|
3 |
+
size 3183
|
checkpoint-270/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557982265
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6cda356bb2460d5eb07d886f9da9cae5d5a5e81b62d6724fcbbed4dcb5ea98aa
|
3 |
size 557982265
|