Commit
•
e97c8b9
1
Parent(s):
28613c9
Upload 11 files
Browse files- all_results.json +15 -0
- config.json +62 -0
- eval_results.json +10 -0
- generation_config.json +15 -0
- source.spm +0 -0
- special_tokens_map.json +5 -0
- target.spm +0 -0
- tokenizer_config.json +12 -0
- train_results.json +8 -0
- trainer_state.json +55 -0
- vocab.json +0 -0
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_bleu": 57.269,
|
4 |
+
"eval_gen_len": 36.1375,
|
5 |
+
"eval_loss": 0.7390245199203491,
|
6 |
+
"eval_runtime": 5.0819,
|
7 |
+
"eval_samples": 80,
|
8 |
+
"eval_samples_per_second": 15.742,
|
9 |
+
"eval_steps_per_second": 1.968,
|
10 |
+
"train_loss": 0.6587849299112956,
|
11 |
+
"train_runtime": 25.0068,
|
12 |
+
"train_samples": 319,
|
13 |
+
"train_samples_per_second": 38.27,
|
14 |
+
"train_steps_per_second": 4.799
|
15 |
+
}
|
config.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Helsinki-NLP/opus-mt-en-fr",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "swish",
|
6 |
+
"add_bias_logits": false,
|
7 |
+
"add_final_layer_norm": false,
|
8 |
+
"architectures": [
|
9 |
+
"MarianMTModel"
|
10 |
+
],
|
11 |
+
"attention_dropout": 0.0,
|
12 |
+
"bad_words_ids": [
|
13 |
+
[
|
14 |
+
59513
|
15 |
+
]
|
16 |
+
],
|
17 |
+
"bos_token_id": 0,
|
18 |
+
"classif_dropout": 0.0,
|
19 |
+
"classifier_dropout": 0.0,
|
20 |
+
"d_model": 512,
|
21 |
+
"decoder_attention_heads": 8,
|
22 |
+
"decoder_ffn_dim": 2048,
|
23 |
+
"decoder_layerdrop": 0.0,
|
24 |
+
"decoder_layers": 6,
|
25 |
+
"decoder_start_token_id": 59513,
|
26 |
+
"decoder_vocab_size": 59514,
|
27 |
+
"dropout": 0.1,
|
28 |
+
"encoder_attention_heads": 8,
|
29 |
+
"encoder_ffn_dim": 2048,
|
30 |
+
"encoder_layerdrop": 0.0,
|
31 |
+
"encoder_layers": 6,
|
32 |
+
"eos_token_id": 0,
|
33 |
+
"forced_eos_token_id": 0,
|
34 |
+
"gradient_checkpointing": false,
|
35 |
+
"id2label": {
|
36 |
+
"0": "LABEL_0",
|
37 |
+
"1": "LABEL_1",
|
38 |
+
"2": "LABEL_2"
|
39 |
+
},
|
40 |
+
"init_std": 0.02,
|
41 |
+
"is_encoder_decoder": true,
|
42 |
+
"label2id": {
|
43 |
+
"LABEL_0": 0,
|
44 |
+
"LABEL_1": 1,
|
45 |
+
"LABEL_2": 2
|
46 |
+
},
|
47 |
+
"max_length": 512,
|
48 |
+
"max_position_embeddings": 512,
|
49 |
+
"model_type": "marian",
|
50 |
+
"normalize_before": false,
|
51 |
+
"normalize_embedding": false,
|
52 |
+
"num_beams": 4,
|
53 |
+
"num_hidden_layers": 6,
|
54 |
+
"pad_token_id": 59513,
|
55 |
+
"scale_embedding": true,
|
56 |
+
"share_encoder_decoder_embeddings": true,
|
57 |
+
"static_position_embeddings": true,
|
58 |
+
"torch_dtype": "float32",
|
59 |
+
"transformers_version": "4.31.0.dev0",
|
60 |
+
"use_cache": true,
|
61 |
+
"vocab_size": 59514
|
62 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_bleu": 57.269,
|
4 |
+
"eval_gen_len": 36.1375,
|
5 |
+
"eval_loss": 0.7390245199203491,
|
6 |
+
"eval_runtime": 5.0819,
|
7 |
+
"eval_samples": 80,
|
8 |
+
"eval_samples_per_second": 15.742,
|
9 |
+
"eval_steps_per_second": 1.968
|
10 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bad_words_ids": [
|
3 |
+
[
|
4 |
+
59513
|
5 |
+
]
|
6 |
+
],
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"decoder_start_token_id": 59513,
|
9 |
+
"eos_token_id": 0,
|
10 |
+
"forced_eos_token_id": 0,
|
11 |
+
"max_length": 512,
|
12 |
+
"num_beams": 4,
|
13 |
+
"pad_token_id": 59513,
|
14 |
+
"transformers_version": "4.31.0.dev0"
|
15 |
+
}
|
source.spm
ADDED
Binary file (778 kB). View file
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "</s>",
|
3 |
+
"pad_token": "<pad>",
|
4 |
+
"unk_token": "<unk>"
|
5 |
+
}
|
target.spm
ADDED
Binary file (802 kB). View file
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"model_max_length": 512,
|
5 |
+
"pad_token": "<pad>",
|
6 |
+
"separate_vocabs": false,
|
7 |
+
"source_lang": "en",
|
8 |
+
"sp_model_kwargs": {},
|
9 |
+
"target_lang": "fr",
|
10 |
+
"tokenizer_class": "MarianTokenizer",
|
11 |
+
"unk_token": "<unk>"
|
12 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"train_loss": 0.6587849299112956,
|
4 |
+
"train_runtime": 25.0068,
|
5 |
+
"train_samples": 319,
|
6 |
+
"train_samples_per_second": 38.27,
|
7 |
+
"train_steps_per_second": 4.799
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"global_step": 120,
|
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 |
+
"eval_bleu": 56.4458,
|
13 |
+
"eval_gen_len": 36.4625,
|
14 |
+
"eval_loss": 0.7646628618240356,
|
15 |
+
"eval_runtime": 5.0083,
|
16 |
+
"eval_samples_per_second": 15.973,
|
17 |
+
"eval_steps_per_second": 1.997,
|
18 |
+
"step": 40
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_bleu": 55.8074,
|
23 |
+
"eval_gen_len": 36.4625,
|
24 |
+
"eval_loss": 0.7441360354423523,
|
25 |
+
"eval_runtime": 4.9818,
|
26 |
+
"eval_samples_per_second": 16.059,
|
27 |
+
"eval_steps_per_second": 2.007,
|
28 |
+
"step": 80
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 3.0,
|
32 |
+
"eval_bleu": 57.269,
|
33 |
+
"eval_gen_len": 36.1375,
|
34 |
+
"eval_loss": 0.7390245199203491,
|
35 |
+
"eval_runtime": 4.9371,
|
36 |
+
"eval_samples_per_second": 16.204,
|
37 |
+
"eval_steps_per_second": 2.025,
|
38 |
+
"step": 120
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 3.0,
|
42 |
+
"step": 120,
|
43 |
+
"total_flos": 14405745770496.0,
|
44 |
+
"train_loss": 0.6587849299112956,
|
45 |
+
"train_runtime": 25.0068,
|
46 |
+
"train_samples_per_second": 38.27,
|
47 |
+
"train_steps_per_second": 4.799
|
48 |
+
}
|
49 |
+
],
|
50 |
+
"max_steps": 120,
|
51 |
+
"num_train_epochs": 3,
|
52 |
+
"total_flos": 14405745770496.0,
|
53 |
+
"trial_name": null,
|
54 |
+
"trial_params": null
|
55 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|