Upload fine-tuned translation model
Browse files- .gitattributes +8 -0
- checkpoint-113/config.json +56 -0
- checkpoint-113/generation_config.json +16 -0
- checkpoint-113/model.safetensors +3 -0
- checkpoint-113/optimizer.pt +3 -0
- checkpoint-113/rng_state.pth +3 -0
- checkpoint-113/scheduler.pt +3 -0
- checkpoint-113/source.spm +3 -0
- checkpoint-113/special_tokens_map.json +5 -0
- checkpoint-113/target.spm +3 -0
- checkpoint-113/tokenizer_config.json +39 -0
- checkpoint-113/trainer_state.json +41 -0
- checkpoint-113/training_args.bin +3 -0
- checkpoint-113/vocab.json +0 -0
- checkpoint-226/config.json +56 -0
- checkpoint-226/generation_config.json +16 -0
- checkpoint-226/model.safetensors +3 -0
- checkpoint-226/optimizer.pt +3 -0
- checkpoint-226/rng_state.pth +3 -0
- checkpoint-226/scheduler.pt +3 -0
- checkpoint-226/source.spm +3 -0
- checkpoint-226/special_tokens_map.json +5 -0
- checkpoint-226/target.spm +3 -0
- checkpoint-226/tokenizer_config.json +39 -0
- checkpoint-226/trainer_state.json +49 -0
- checkpoint-226/training_args.bin +3 -0
- checkpoint-226/vocab.json +0 -0
- checkpoint-339/config.json +56 -0
- checkpoint-339/generation_config.json +16 -0
- checkpoint-339/model.safetensors +3 -0
- checkpoint-339/optimizer.pt +3 -0
- checkpoint-339/rng_state.pth +3 -0
- checkpoint-339/scheduler.pt +3 -0
- checkpoint-339/source.spm +3 -0
- checkpoint-339/special_tokens_map.json +5 -0
- checkpoint-339/target.spm +3 -0
- checkpoint-339/tokenizer_config.json +39 -0
- checkpoint-339/trainer_state.json +57 -0
- checkpoint-339/training_args.bin +3 -0
- checkpoint-339/vocab.json +0 -0
- config.json +56 -0
- generation_config.json +16 -0
- model.safetensors +3 -0
- source.spm +3 -0
- special_tokens_map.json +5 -0
- target.spm +3 -0
- tokenizer_config.json +39 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
checkpoint-113/source.spm filter=lfs diff=lfs merge=lfs -text
|
37 |
+
checkpoint-113/target.spm filter=lfs diff=lfs merge=lfs -text
|
38 |
+
checkpoint-226/source.spm filter=lfs diff=lfs merge=lfs -text
|
39 |
+
checkpoint-226/target.spm filter=lfs diff=lfs merge=lfs -text
|
40 |
+
checkpoint-339/source.spm filter=lfs diff=lfs merge=lfs -text
|
41 |
+
checkpoint-339/target.spm filter=lfs diff=lfs merge=lfs -text
|
42 |
+
source.spm filter=lfs diff=lfs merge=lfs -text
|
43 |
+
target.spm filter=lfs diff=lfs merge=lfs -text
|
checkpoint-113/config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Helsinki-NLP/opus-mt-en-ar",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "swish",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"MarianMTModel"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.0,
|
11 |
+
"bos_token_id": 0,
|
12 |
+
"classif_dropout": 0.0,
|
13 |
+
"classifier_dropout": 0.0,
|
14 |
+
"d_model": 512,
|
15 |
+
"decoder_attention_heads": 8,
|
16 |
+
"decoder_ffn_dim": 2048,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 6,
|
19 |
+
"decoder_start_token_id": 62801,
|
20 |
+
"decoder_vocab_size": 62802,
|
21 |
+
"dropout": 0.1,
|
22 |
+
"encoder_attention_heads": 8,
|
23 |
+
"encoder_ffn_dim": 2048,
|
24 |
+
"encoder_layerdrop": 0.0,
|
25 |
+
"encoder_layers": 6,
|
26 |
+
"eos_token_id": 0,
|
27 |
+
"extra_pos_embeddings": 62802,
|
28 |
+
"forced_eos_token_id": 0,
|
29 |
+
"id2label": {
|
30 |
+
"0": "LABEL_0",
|
31 |
+
"1": "LABEL_1",
|
32 |
+
"2": "LABEL_2"
|
33 |
+
},
|
34 |
+
"init_std": 0.02,
|
35 |
+
"is_encoder_decoder": true,
|
36 |
+
"label2id": {
|
37 |
+
"LABEL_0": 0,
|
38 |
+
"LABEL_1": 1,
|
39 |
+
"LABEL_2": 2
|
40 |
+
},
|
41 |
+
"max_length": null,
|
42 |
+
"max_position_embeddings": 512,
|
43 |
+
"model_type": "marian",
|
44 |
+
"normalize_before": false,
|
45 |
+
"normalize_embedding": false,
|
46 |
+
"num_beams": null,
|
47 |
+
"num_hidden_layers": 6,
|
48 |
+
"pad_token_id": 62801,
|
49 |
+
"scale_embedding": true,
|
50 |
+
"share_encoder_decoder_embeddings": true,
|
51 |
+
"static_position_embeddings": true,
|
52 |
+
"torch_dtype": "float32",
|
53 |
+
"transformers_version": "4.48.3",
|
54 |
+
"use_cache": true,
|
55 |
+
"vocab_size": 62802
|
56 |
+
}
|
checkpoint-113/generation_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bad_words_ids": [
|
3 |
+
[
|
4 |
+
62801
|
5 |
+
]
|
6 |
+
],
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"decoder_start_token_id": 62801,
|
9 |
+
"eos_token_id": 0,
|
10 |
+
"forced_eos_token_id": 0,
|
11 |
+
"max_length": 512,
|
12 |
+
"num_beams": 4,
|
13 |
+
"pad_token_id": 62801,
|
14 |
+
"renormalize_logits": true,
|
15 |
+
"transformers_version": "4.48.3"
|
16 |
+
}
|
checkpoint-113/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a838f491dc995d06eb08d5c6f6da17c009f0981c3ddec8ef52c22c8eb7cec415
|
3 |
+
size 305452744
|
checkpoint-113/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7acd56aa5e1a8a32a93a33d2ed2418f0314888f79ff43daca65fdc62b12f614
|
3 |
+
size 610549434
|
checkpoint-113/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bea13cce92e11d7816094927a749997c20c737e40d32086d5fe54c766a13310f
|
3 |
+
size 13990
|
checkpoint-113/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:550c602138554e7c4c31c6865545588f3eeb5cf23ce0402326f54e760f3584c2
|
3 |
+
size 1064
|
checkpoint-113/source.spm
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81ac8f4d4ee271f4109eac67560a31f9c2d555463ba5eb95c32c6deee8ae819d
|
3 |
+
size 801074
|
checkpoint-113/special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "</s>",
|
3 |
+
"pad_token": "<pad>",
|
4 |
+
"unk_token": "<unk>"
|
5 |
+
}
|
checkpoint-113/target.spm
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67d0f6afb87768c078ee46c0756b8cc94b1ec23c5526b49ecf6c3b2f9197ec39
|
3 |
+
size 916890
|
checkpoint-113/tokenizer_config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<unk>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"62801": {
|
20 |
+
"content": "<pad>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
}
|
27 |
+
},
|
28 |
+
"clean_up_tokenization_spaces": false,
|
29 |
+
"eos_token": "</s>",
|
30 |
+
"extra_special_tokens": {},
|
31 |
+
"model_max_length": 512,
|
32 |
+
"pad_token": "<pad>",
|
33 |
+
"separate_vocabs": false,
|
34 |
+
"source_lang": "eng",
|
35 |
+
"sp_model_kwargs": {},
|
36 |
+
"target_lang": "ara",
|
37 |
+
"tokenizer_class": "MarianTokenizer",
|
38 |
+
"unk_token": "<unk>"
|
39 |
+
}
|
checkpoint-113/trainer_state.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 113,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.006068581715226173,
|
14 |
+
"eval_runtime": 40.8123,
|
15 |
+
"eval_samples_per_second": 2.45,
|
16 |
+
"eval_steps_per_second": 0.319,
|
17 |
+
"step": 113
|
18 |
+
}
|
19 |
+
],
|
20 |
+
"logging_steps": 500,
|
21 |
+
"max_steps": 339,
|
22 |
+
"num_input_tokens_seen": 0,
|
23 |
+
"num_train_epochs": 3,
|
24 |
+
"save_steps": 500,
|
25 |
+
"stateful_callbacks": {
|
26 |
+
"TrainerControl": {
|
27 |
+
"args": {
|
28 |
+
"should_epoch_stop": false,
|
29 |
+
"should_evaluate": false,
|
30 |
+
"should_log": false,
|
31 |
+
"should_save": true,
|
32 |
+
"should_training_stop": false
|
33 |
+
},
|
34 |
+
"attributes": {}
|
35 |
+
}
|
36 |
+
},
|
37 |
+
"total_flos": 30508528435200.0,
|
38 |
+
"train_batch_size": 8,
|
39 |
+
"trial_name": null,
|
40 |
+
"trial_params": null
|
41 |
+
}
|
checkpoint-113/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a70566903a3c841c5b21227d794f8a34554ed4102489f98d35df8d9f3021d4b6
|
3 |
+
size 5432
|
checkpoint-113/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-226/config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Helsinki-NLP/opus-mt-en-ar",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "swish",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"MarianMTModel"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.0,
|
11 |
+
"bos_token_id": 0,
|
12 |
+
"classif_dropout": 0.0,
|
13 |
+
"classifier_dropout": 0.0,
|
14 |
+
"d_model": 512,
|
15 |
+
"decoder_attention_heads": 8,
|
16 |
+
"decoder_ffn_dim": 2048,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 6,
|
19 |
+
"decoder_start_token_id": 62801,
|
20 |
+
"decoder_vocab_size": 62802,
|
21 |
+
"dropout": 0.1,
|
22 |
+
"encoder_attention_heads": 8,
|
23 |
+
"encoder_ffn_dim": 2048,
|
24 |
+
"encoder_layerdrop": 0.0,
|
25 |
+
"encoder_layers": 6,
|
26 |
+
"eos_token_id": 0,
|
27 |
+
"extra_pos_embeddings": 62802,
|
28 |
+
"forced_eos_token_id": 0,
|
29 |
+
"id2label": {
|
30 |
+
"0": "LABEL_0",
|
31 |
+
"1": "LABEL_1",
|
32 |
+
"2": "LABEL_2"
|
33 |
+
},
|
34 |
+
"init_std": 0.02,
|
35 |
+
"is_encoder_decoder": true,
|
36 |
+
"label2id": {
|
37 |
+
"LABEL_0": 0,
|
38 |
+
"LABEL_1": 1,
|
39 |
+
"LABEL_2": 2
|
40 |
+
},
|
41 |
+
"max_length": null,
|
42 |
+
"max_position_embeddings": 512,
|
43 |
+
"model_type": "marian",
|
44 |
+
"normalize_before": false,
|
45 |
+
"normalize_embedding": false,
|
46 |
+
"num_beams": null,
|
47 |
+
"num_hidden_layers": 6,
|
48 |
+
"pad_token_id": 62801,
|
49 |
+
"scale_embedding": true,
|
50 |
+
"share_encoder_decoder_embeddings": true,
|
51 |
+
"static_position_embeddings": true,
|
52 |
+
"torch_dtype": "float32",
|
53 |
+
"transformers_version": "4.48.3",
|
54 |
+
"use_cache": true,
|
55 |
+
"vocab_size": 62802
|
56 |
+
}
|
checkpoint-226/generation_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bad_words_ids": [
|
3 |
+
[
|
4 |
+
62801
|
5 |
+
]
|
6 |
+
],
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"decoder_start_token_id": 62801,
|
9 |
+
"eos_token_id": 0,
|
10 |
+
"forced_eos_token_id": 0,
|
11 |
+
"max_length": 512,
|
12 |
+
"num_beams": 4,
|
13 |
+
"pad_token_id": 62801,
|
14 |
+
"renormalize_logits": true,
|
15 |
+
"transformers_version": "4.48.3"
|
16 |
+
}
|
checkpoint-226/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9dd83d69f5a81e54d88fa4a00f16ea3fdcca2ffa72824088a7320dd6a7c4618
|
3 |
+
size 305452744
|
checkpoint-226/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3167f22c547f043249d2a062414f29d19ede1401869b41c31ecf3a02c9a9617
|
3 |
+
size 610549434
|
checkpoint-226/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e58b026aef094ef16d60699a1a49cd0f3727ac1c37aed0c37951b768a8add7da
|
3 |
+
size 13990
|
checkpoint-226/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd61d00c57e3ab9f0207f053f5a1afd256b259193b1a6c7fd536650a2436bb96
|
3 |
+
size 1064
|
checkpoint-226/source.spm
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81ac8f4d4ee271f4109eac67560a31f9c2d555463ba5eb95c32c6deee8ae819d
|
3 |
+
size 801074
|
checkpoint-226/special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "</s>",
|
3 |
+
"pad_token": "<pad>",
|
4 |
+
"unk_token": "<unk>"
|
5 |
+
}
|
checkpoint-226/target.spm
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67d0f6afb87768c078ee46c0756b8cc94b1ec23c5526b49ecf6c3b2f9197ec39
|
3 |
+
size 916890
|
checkpoint-226/tokenizer_config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<unk>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"62801": {
|
20 |
+
"content": "<pad>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
}
|
27 |
+
},
|
28 |
+
"clean_up_tokenization_spaces": false,
|
29 |
+
"eos_token": "</s>",
|
30 |
+
"extra_special_tokens": {},
|
31 |
+
"model_max_length": 512,
|
32 |
+
"pad_token": "<pad>",
|
33 |
+
"separate_vocabs": false,
|
34 |
+
"source_lang": "eng",
|
35 |
+
"sp_model_kwargs": {},
|
36 |
+
"target_lang": "ara",
|
37 |
+
"tokenizer_class": "MarianTokenizer",
|
38 |
+
"unk_token": "<unk>"
|
39 |
+
}
|
checkpoint-226/trainer_state.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 226,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.006068581715226173,
|
14 |
+
"eval_runtime": 40.8123,
|
15 |
+
"eval_samples_per_second": 2.45,
|
16 |
+
"eval_steps_per_second": 0.319,
|
17 |
+
"step": 113
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 2.0,
|
21 |
+
"eval_loss": 0.0017003302928060293,
|
22 |
+
"eval_runtime": 40.4782,
|
23 |
+
"eval_samples_per_second": 2.47,
|
24 |
+
"eval_steps_per_second": 0.321,
|
25 |
+
"step": 226
|
26 |
+
}
|
27 |
+
],
|
28 |
+
"logging_steps": 500,
|
29 |
+
"max_steps": 339,
|
30 |
+
"num_input_tokens_seen": 0,
|
31 |
+
"num_train_epochs": 3,
|
32 |
+
"save_steps": 500,
|
33 |
+
"stateful_callbacks": {
|
34 |
+
"TrainerControl": {
|
35 |
+
"args": {
|
36 |
+
"should_epoch_stop": false,
|
37 |
+
"should_evaluate": false,
|
38 |
+
"should_log": false,
|
39 |
+
"should_save": true,
|
40 |
+
"should_training_stop": false
|
41 |
+
},
|
42 |
+
"attributes": {}
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"total_flos": 61017056870400.0,
|
46 |
+
"train_batch_size": 8,
|
47 |
+
"trial_name": null,
|
48 |
+
"trial_params": null
|
49 |
+
}
|
checkpoint-226/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a70566903a3c841c5b21227d794f8a34554ed4102489f98d35df8d9f3021d4b6
|
3 |
+
size 5432
|
checkpoint-226/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-339/config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Helsinki-NLP/opus-mt-en-ar",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "swish",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"MarianMTModel"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.0,
|
11 |
+
"bos_token_id": 0,
|
12 |
+
"classif_dropout": 0.0,
|
13 |
+
"classifier_dropout": 0.0,
|
14 |
+
"d_model": 512,
|
15 |
+
"decoder_attention_heads": 8,
|
16 |
+
"decoder_ffn_dim": 2048,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 6,
|
19 |
+
"decoder_start_token_id": 62801,
|
20 |
+
"decoder_vocab_size": 62802,
|
21 |
+
"dropout": 0.1,
|
22 |
+
"encoder_attention_heads": 8,
|
23 |
+
"encoder_ffn_dim": 2048,
|
24 |
+
"encoder_layerdrop": 0.0,
|
25 |
+
"encoder_layers": 6,
|
26 |
+
"eos_token_id": 0,
|
27 |
+
"extra_pos_embeddings": 62802,
|
28 |
+
"forced_eos_token_id": 0,
|
29 |
+
"id2label": {
|
30 |
+
"0": "LABEL_0",
|
31 |
+
"1": "LABEL_1",
|
32 |
+
"2": "LABEL_2"
|
33 |
+
},
|
34 |
+
"init_std": 0.02,
|
35 |
+
"is_encoder_decoder": true,
|
36 |
+
"label2id": {
|
37 |
+
"LABEL_0": 0,
|
38 |
+
"LABEL_1": 1,
|
39 |
+
"LABEL_2": 2
|
40 |
+
},
|
41 |
+
"max_length": null,
|
42 |
+
"max_position_embeddings": 512,
|
43 |
+
"model_type": "marian",
|
44 |
+
"normalize_before": false,
|
45 |
+
"normalize_embedding": false,
|
46 |
+
"num_beams": null,
|
47 |
+
"num_hidden_layers": 6,
|
48 |
+
"pad_token_id": 62801,
|
49 |
+
"scale_embedding": true,
|
50 |
+
"share_encoder_decoder_embeddings": true,
|
51 |
+
"static_position_embeddings": true,
|
52 |
+
"torch_dtype": "float32",
|
53 |
+
"transformers_version": "4.48.3",
|
54 |
+
"use_cache": true,
|
55 |
+
"vocab_size": 62802
|
56 |
+
}
|
checkpoint-339/generation_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bad_words_ids": [
|
3 |
+
[
|
4 |
+
62801
|
5 |
+
]
|
6 |
+
],
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"decoder_start_token_id": 62801,
|
9 |
+
"eos_token_id": 0,
|
10 |
+
"forced_eos_token_id": 0,
|
11 |
+
"max_length": 512,
|
12 |
+
"num_beams": 4,
|
13 |
+
"pad_token_id": 62801,
|
14 |
+
"renormalize_logits": true,
|
15 |
+
"transformers_version": "4.48.3"
|
16 |
+
}
|
checkpoint-339/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5edb391db8a60ebfbd9e49d347bfba731edf644ba4d82233d87f8d2f01d88c31
|
3 |
+
size 305452744
|
checkpoint-339/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43ccf46d4ad38955bcf68fb190aee71a293b9774c120a561dae0fe46d1007e02
|
3 |
+
size 610549434
|
checkpoint-339/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98705e9622fa211711ed98d98c0b53104bfabcf1b61930fc128eb4ad63042f7a
|
3 |
+
size 13990
|
checkpoint-339/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60820f265e8bc795851f3b3193b3a026c471535f3ef3f62d39441a184d5393a0
|
3 |
+
size 1064
|
checkpoint-339/source.spm
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81ac8f4d4ee271f4109eac67560a31f9c2d555463ba5eb95c32c6deee8ae819d
|
3 |
+
size 801074
|
checkpoint-339/special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "</s>",
|
3 |
+
"pad_token": "<pad>",
|
4 |
+
"unk_token": "<unk>"
|
5 |
+
}
|
checkpoint-339/target.spm
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67d0f6afb87768c078ee46c0756b8cc94b1ec23c5526b49ecf6c3b2f9197ec39
|
3 |
+
size 916890
|
checkpoint-339/tokenizer_config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<unk>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"62801": {
|
20 |
+
"content": "<pad>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
}
|
27 |
+
},
|
28 |
+
"clean_up_tokenization_spaces": false,
|
29 |
+
"eos_token": "</s>",
|
30 |
+
"extra_special_tokens": {},
|
31 |
+
"model_max_length": 512,
|
32 |
+
"pad_token": "<pad>",
|
33 |
+
"separate_vocabs": false,
|
34 |
+
"source_lang": "eng",
|
35 |
+
"sp_model_kwargs": {},
|
36 |
+
"target_lang": "ara",
|
37 |
+
"tokenizer_class": "MarianTokenizer",
|
38 |
+
"unk_token": "<unk>"
|
39 |
+
}
|
checkpoint-339/trainer_state.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 339,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.006068581715226173,
|
14 |
+
"eval_runtime": 40.8123,
|
15 |
+
"eval_samples_per_second": 2.45,
|
16 |
+
"eval_steps_per_second": 0.319,
|
17 |
+
"step": 113
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 2.0,
|
21 |
+
"eval_loss": 0.0017003302928060293,
|
22 |
+
"eval_runtime": 40.4782,
|
23 |
+
"eval_samples_per_second": 2.47,
|
24 |
+
"eval_steps_per_second": 0.321,
|
25 |
+
"step": 226
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 3.0,
|
29 |
+
"eval_loss": 0.000951059686485678,
|
30 |
+
"eval_runtime": 45.9277,
|
31 |
+
"eval_samples_per_second": 2.177,
|
32 |
+
"eval_steps_per_second": 0.283,
|
33 |
+
"step": 339
|
34 |
+
}
|
35 |
+
],
|
36 |
+
"logging_steps": 500,
|
37 |
+
"max_steps": 339,
|
38 |
+
"num_input_tokens_seen": 0,
|
39 |
+
"num_train_epochs": 3,
|
40 |
+
"save_steps": 500,
|
41 |
+
"stateful_callbacks": {
|
42 |
+
"TrainerControl": {
|
43 |
+
"args": {
|
44 |
+
"should_epoch_stop": false,
|
45 |
+
"should_evaluate": false,
|
46 |
+
"should_log": false,
|
47 |
+
"should_save": true,
|
48 |
+
"should_training_stop": true
|
49 |
+
},
|
50 |
+
"attributes": {}
|
51 |
+
}
|
52 |
+
},
|
53 |
+
"total_flos": 91525585305600.0,
|
54 |
+
"train_batch_size": 8,
|
55 |
+
"trial_name": null,
|
56 |
+
"trial_params": null
|
57 |
+
}
|
checkpoint-339/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a70566903a3c841c5b21227d794f8a34554ed4102489f98d35df8d9f3021d4b6
|
3 |
+
size 5432
|
checkpoint-339/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Helsinki-NLP/opus-mt-en-ar",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "swish",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"MarianMTModel"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.0,
|
11 |
+
"bos_token_id": 0,
|
12 |
+
"classif_dropout": 0.0,
|
13 |
+
"classifier_dropout": 0.0,
|
14 |
+
"d_model": 512,
|
15 |
+
"decoder_attention_heads": 8,
|
16 |
+
"decoder_ffn_dim": 2048,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 6,
|
19 |
+
"decoder_start_token_id": 62801,
|
20 |
+
"decoder_vocab_size": 62802,
|
21 |
+
"dropout": 0.1,
|
22 |
+
"encoder_attention_heads": 8,
|
23 |
+
"encoder_ffn_dim": 2048,
|
24 |
+
"encoder_layerdrop": 0.0,
|
25 |
+
"encoder_layers": 6,
|
26 |
+
"eos_token_id": 0,
|
27 |
+
"extra_pos_embeddings": 62802,
|
28 |
+
"forced_eos_token_id": 0,
|
29 |
+
"id2label": {
|
30 |
+
"0": "LABEL_0",
|
31 |
+
"1": "LABEL_1",
|
32 |
+
"2": "LABEL_2"
|
33 |
+
},
|
34 |
+
"init_std": 0.02,
|
35 |
+
"is_encoder_decoder": true,
|
36 |
+
"label2id": {
|
37 |
+
"LABEL_0": 0,
|
38 |
+
"LABEL_1": 1,
|
39 |
+
"LABEL_2": 2
|
40 |
+
},
|
41 |
+
"max_length": null,
|
42 |
+
"max_position_embeddings": 512,
|
43 |
+
"model_type": "marian",
|
44 |
+
"normalize_before": false,
|
45 |
+
"normalize_embedding": false,
|
46 |
+
"num_beams": null,
|
47 |
+
"num_hidden_layers": 6,
|
48 |
+
"pad_token_id": 62801,
|
49 |
+
"scale_embedding": true,
|
50 |
+
"share_encoder_decoder_embeddings": true,
|
51 |
+
"static_position_embeddings": true,
|
52 |
+
"torch_dtype": "float32",
|
53 |
+
"transformers_version": "4.48.3",
|
54 |
+
"use_cache": true,
|
55 |
+
"vocab_size": 62802
|
56 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bad_words_ids": [
|
3 |
+
[
|
4 |
+
62801
|
5 |
+
]
|
6 |
+
],
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"decoder_start_token_id": 62801,
|
9 |
+
"eos_token_id": 0,
|
10 |
+
"forced_eos_token_id": 0,
|
11 |
+
"max_length": 512,
|
12 |
+
"num_beams": 4,
|
13 |
+
"pad_token_id": 62801,
|
14 |
+
"renormalize_logits": true,
|
15 |
+
"transformers_version": "4.48.3"
|
16 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5edb391db8a60ebfbd9e49d347bfba731edf644ba4d82233d87f8d2f01d88c31
|
3 |
+
size 305452744
|
source.spm
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81ac8f4d4ee271f4109eac67560a31f9c2d555463ba5eb95c32c6deee8ae819d
|
3 |
+
size 801074
|
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
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67d0f6afb87768c078ee46c0756b8cc94b1ec23c5526b49ecf6c3b2f9197ec39
|
3 |
+
size 916890
|
tokenizer_config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<unk>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"62801": {
|
20 |
+
"content": "<pad>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
}
|
27 |
+
},
|
28 |
+
"clean_up_tokenization_spaces": false,
|
29 |
+
"eos_token": "</s>",
|
30 |
+
"extra_special_tokens": {},
|
31 |
+
"model_max_length": 512,
|
32 |
+
"pad_token": "<pad>",
|
33 |
+
"separate_vocabs": false,
|
34 |
+
"source_lang": "eng",
|
35 |
+
"sp_model_kwargs": {},
|
36 |
+
"target_lang": "ara",
|
37 |
+
"tokenizer_class": "MarianTokenizer",
|
38 |
+
"unk_token": "<unk>"
|
39 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|