Upload folder using huggingface_hub
Browse files- config.json +61 -0
- generation_config.json +15 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- source.spm +0 -0
- special_tokens_map.json +5 -0
- target.spm +0 -0
- tokenizer_config.json +40 -0
- trainer_state.json +307 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Sunbird/sunbird-en-mul",
|
| 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 |
+
"bad_words_ids": [
|
| 12 |
+
[
|
| 13 |
+
64109
|
| 14 |
+
]
|
| 15 |
+
],
|
| 16 |
+
"bos_token_id": 0,
|
| 17 |
+
"classif_dropout": 0.0,
|
| 18 |
+
"classifier_dropout": 0.0,
|
| 19 |
+
"d_model": 512,
|
| 20 |
+
"decoder_attention_heads": 8,
|
| 21 |
+
"decoder_ffn_dim": 2048,
|
| 22 |
+
"decoder_layerdrop": 0.0,
|
| 23 |
+
"decoder_layers": 6,
|
| 24 |
+
"decoder_start_token_id": 64109,
|
| 25 |
+
"decoder_vocab_size": 64110,
|
| 26 |
+
"dropout": 0.1,
|
| 27 |
+
"encoder_attention_heads": 8,
|
| 28 |
+
"encoder_ffn_dim": 2048,
|
| 29 |
+
"encoder_layerdrop": 0.0,
|
| 30 |
+
"encoder_layers": 6,
|
| 31 |
+
"eos_token_id": 0,
|
| 32 |
+
"extra_pos_embeddings": 64110,
|
| 33 |
+
"forced_eos_token_id": 0,
|
| 34 |
+
"id2label": {
|
| 35 |
+
"0": "LABEL_0",
|
| 36 |
+
"1": "LABEL_1",
|
| 37 |
+
"2": "LABEL_2"
|
| 38 |
+
},
|
| 39 |
+
"init_std": 0.02,
|
| 40 |
+
"is_encoder_decoder": true,
|
| 41 |
+
"label2id": {
|
| 42 |
+
"LABEL_0": 0,
|
| 43 |
+
"LABEL_1": 1,
|
| 44 |
+
"LABEL_2": 2
|
| 45 |
+
},
|
| 46 |
+
"max_length": 512,
|
| 47 |
+
"max_position_embeddings": 512,
|
| 48 |
+
"model_type": "marian",
|
| 49 |
+
"normalize_before": false,
|
| 50 |
+
"normalize_embedding": false,
|
| 51 |
+
"num_beams": 4,
|
| 52 |
+
"num_hidden_layers": 6,
|
| 53 |
+
"pad_token_id": 64109,
|
| 54 |
+
"scale_embedding": true,
|
| 55 |
+
"share_encoder_decoder_embeddings": true,
|
| 56 |
+
"static_position_embeddings": true,
|
| 57 |
+
"torch_dtype": "float32",
|
| 58 |
+
"transformers_version": "4.42.3",
|
| 59 |
+
"use_cache": true,
|
| 60 |
+
"vocab_size": 64110
|
| 61 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bad_words_ids": [
|
| 3 |
+
[
|
| 4 |
+
64109
|
| 5 |
+
]
|
| 6 |
+
],
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"decoder_start_token_id": 64109,
|
| 9 |
+
"eos_token_id": 0,
|
| 10 |
+
"forced_eos_token_id": 0,
|
| 11 |
+
"max_length": 512,
|
| 12 |
+
"num_beams": 4,
|
| 13 |
+
"pad_token_id": 64109,
|
| 14 |
+
"transformers_version": "4.42.3"
|
| 15 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f3b76e2fd91bb500b4ba2e119c0e247aa20878b3958b52e4005795911e4472f
|
| 3 |
+
size 308136760
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53b1fad9f6859580f2b1286fc9e5ab4e9b98448e13e353a481fe5d16750ec81e
|
| 3 |
+
size 615914106
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:978de5ea732400c1030e6151dbd2f7da1685b2766cd3dbd76ad9e6ca76c73905
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:addf6ed2edfb91e5799707ef8ad563521651e0e38e75b9389ea7f0c4c79ff9b3
|
| 3 |
+
size 1064
|
source.spm
ADDED
|
Binary file (790 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 (707 kB). View file
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"64109": {
|
| 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": true,
|
| 29 |
+
"eos_token": "</s>",
|
| 30 |
+
"model_max_length": 512,
|
| 31 |
+
"pad_token": "<pad>",
|
| 32 |
+
"separate_vocabs": false,
|
| 33 |
+
"source_lang": "eng",
|
| 34 |
+
"sp_model_kwargs": {},
|
| 35 |
+
"src_lang": "eng_Latn",
|
| 36 |
+
"target_lang": "mul",
|
| 37 |
+
"tgt_lang": "lug_Latn",
|
| 38 |
+
"tokenizer_class": "MarianTokenizer",
|
| 39 |
+
"unk_token": "<unk>"
|
| 40 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,307 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 4.029151439666748,
|
| 3 |
+
"best_model_checkpoint": "continued-finetuned-en-to-lg/checkpoint-39",
|
| 4 |
+
"epoch": 26.0,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 1027,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.9873417721518988,
|
| 13 |
+
"eval_bleu": 0.8383,
|
| 14 |
+
"eval_gen_len": 20.509,
|
| 15 |
+
"eval_loss": 4.029151439666748,
|
| 16 |
+
"eval_runtime": 478.8606,
|
| 17 |
+
"eval_samples_per_second": 25.387,
|
| 18 |
+
"eval_steps_per_second": 0.794,
|
| 19 |
+
"step": 39
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 2.0,
|
| 23 |
+
"eval_bleu": 0.8282,
|
| 24 |
+
"eval_gen_len": 20.3936,
|
| 25 |
+
"eval_loss": 4.243524074554443,
|
| 26 |
+
"eval_runtime": 474.9597,
|
| 27 |
+
"eval_samples_per_second": 25.596,
|
| 28 |
+
"eval_steps_per_second": 0.8,
|
| 29 |
+
"step": 79
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.9873417721518987,
|
| 33 |
+
"eval_bleu": 0.8032,
|
| 34 |
+
"eval_gen_len": 20.33,
|
| 35 |
+
"eval_loss": 4.359070301055908,
|
| 36 |
+
"eval_runtime": 475.0262,
|
| 37 |
+
"eval_samples_per_second": 25.592,
|
| 38 |
+
"eval_steps_per_second": 0.8,
|
| 39 |
+
"step": 118
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 4.0,
|
| 43 |
+
"eval_bleu": 0.8038,
|
| 44 |
+
"eval_gen_len": 20.2033,
|
| 45 |
+
"eval_loss": 4.451895236968994,
|
| 46 |
+
"eval_runtime": 473.6738,
|
| 47 |
+
"eval_samples_per_second": 25.665,
|
| 48 |
+
"eval_steps_per_second": 0.802,
|
| 49 |
+
"step": 158
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 4.987341772151899,
|
| 53 |
+
"eval_bleu": 0.8017,
|
| 54 |
+
"eval_gen_len": 20.0283,
|
| 55 |
+
"eval_loss": 4.547088146209717,
|
| 56 |
+
"eval_runtime": 476.3005,
|
| 57 |
+
"eval_samples_per_second": 25.524,
|
| 58 |
+
"eval_steps_per_second": 0.798,
|
| 59 |
+
"step": 197
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 6.0,
|
| 63 |
+
"eval_bleu": 0.7828,
|
| 64 |
+
"eval_gen_len": 20.1771,
|
| 65 |
+
"eval_loss": 4.555694103240967,
|
| 66 |
+
"eval_runtime": 473.4342,
|
| 67 |
+
"eval_samples_per_second": 25.678,
|
| 68 |
+
"eval_steps_per_second": 0.803,
|
| 69 |
+
"step": 237
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 6.987341772151899,
|
| 73 |
+
"eval_bleu": 0.771,
|
| 74 |
+
"eval_gen_len": 20.3172,
|
| 75 |
+
"eval_loss": 4.672959327697754,
|
| 76 |
+
"eval_runtime": 476.2521,
|
| 77 |
+
"eval_samples_per_second": 25.526,
|
| 78 |
+
"eval_steps_per_second": 0.798,
|
| 79 |
+
"step": 276
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 8.0,
|
| 83 |
+
"eval_bleu": 0.7971,
|
| 84 |
+
"eval_gen_len": 20.2095,
|
| 85 |
+
"eval_loss": 4.719875812530518,
|
| 86 |
+
"eval_runtime": 472.5874,
|
| 87 |
+
"eval_samples_per_second": 25.724,
|
| 88 |
+
"eval_steps_per_second": 0.804,
|
| 89 |
+
"step": 316
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 8.987341772151899,
|
| 93 |
+
"eval_bleu": 0.7587,
|
| 94 |
+
"eval_gen_len": 20.4253,
|
| 95 |
+
"eval_loss": 4.758220672607422,
|
| 96 |
+
"eval_runtime": 477.573,
|
| 97 |
+
"eval_samples_per_second": 25.456,
|
| 98 |
+
"eval_steps_per_second": 0.796,
|
| 99 |
+
"step": 355
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 10.0,
|
| 103 |
+
"eval_bleu": 0.7975,
|
| 104 |
+
"eval_gen_len": 20.3643,
|
| 105 |
+
"eval_loss": 4.771291255950928,
|
| 106 |
+
"eval_runtime": 477.1681,
|
| 107 |
+
"eval_samples_per_second": 25.477,
|
| 108 |
+
"eval_steps_per_second": 0.796,
|
| 109 |
+
"step": 395
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 10.987341772151899,
|
| 113 |
+
"eval_bleu": 0.7619,
|
| 114 |
+
"eval_gen_len": 20.4121,
|
| 115 |
+
"eval_loss": 4.748700141906738,
|
| 116 |
+
"eval_runtime": 479.5702,
|
| 117 |
+
"eval_samples_per_second": 25.35,
|
| 118 |
+
"eval_steps_per_second": 0.792,
|
| 119 |
+
"step": 434
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 12.0,
|
| 123 |
+
"eval_bleu": 0.7865,
|
| 124 |
+
"eval_gen_len": 20.3477,
|
| 125 |
+
"eval_loss": 4.832670211791992,
|
| 126 |
+
"eval_runtime": 473.4727,
|
| 127 |
+
"eval_samples_per_second": 25.676,
|
| 128 |
+
"eval_steps_per_second": 0.803,
|
| 129 |
+
"step": 474
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 12.658227848101266,
|
| 133 |
+
"grad_norm": 1.2026784420013428,
|
| 134 |
+
"learning_rate": 1.1452991452991454e-05,
|
| 135 |
+
"loss": 0.1585,
|
| 136 |
+
"step": 500
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 12.987341772151899,
|
| 140 |
+
"eval_bleu": 0.7909,
|
| 141 |
+
"eval_gen_len": 20.307,
|
| 142 |
+
"eval_loss": 4.844118595123291,
|
| 143 |
+
"eval_runtime": 475.2982,
|
| 144 |
+
"eval_samples_per_second": 25.578,
|
| 145 |
+
"eval_steps_per_second": 0.799,
|
| 146 |
+
"step": 513
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 14.0,
|
| 150 |
+
"eval_bleu": 0.8004,
|
| 151 |
+
"eval_gen_len": 20.3038,
|
| 152 |
+
"eval_loss": 4.876136302947998,
|
| 153 |
+
"eval_runtime": 475.2478,
|
| 154 |
+
"eval_samples_per_second": 25.58,
|
| 155 |
+
"eval_steps_per_second": 0.8,
|
| 156 |
+
"step": 553
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 14.987341772151899,
|
| 160 |
+
"eval_bleu": 0.7823,
|
| 161 |
+
"eval_gen_len": 20.2747,
|
| 162 |
+
"eval_loss": 4.92393684387207,
|
| 163 |
+
"eval_runtime": 476.8033,
|
| 164 |
+
"eval_samples_per_second": 25.497,
|
| 165 |
+
"eval_steps_per_second": 0.797,
|
| 166 |
+
"step": 592
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 16.0,
|
| 170 |
+
"eval_bleu": 0.79,
|
| 171 |
+
"eval_gen_len": 20.226,
|
| 172 |
+
"eval_loss": 4.880424976348877,
|
| 173 |
+
"eval_runtime": 474.5946,
|
| 174 |
+
"eval_samples_per_second": 25.616,
|
| 175 |
+
"eval_steps_per_second": 0.801,
|
| 176 |
+
"step": 632
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 16.9873417721519,
|
| 180 |
+
"eval_bleu": 0.7821,
|
| 181 |
+
"eval_gen_len": 20.3653,
|
| 182 |
+
"eval_loss": 4.9470534324646,
|
| 183 |
+
"eval_runtime": 477.2511,
|
| 184 |
+
"eval_samples_per_second": 25.473,
|
| 185 |
+
"eval_steps_per_second": 0.796,
|
| 186 |
+
"step": 671
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 18.0,
|
| 190 |
+
"eval_bleu": 0.7876,
|
| 191 |
+
"eval_gen_len": 20.3285,
|
| 192 |
+
"eval_loss": 4.9639482498168945,
|
| 193 |
+
"eval_runtime": 477.3388,
|
| 194 |
+
"eval_samples_per_second": 25.468,
|
| 195 |
+
"eval_steps_per_second": 0.796,
|
| 196 |
+
"step": 711
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 18.9873417721519,
|
| 200 |
+
"eval_bleu": 0.7895,
|
| 201 |
+
"eval_gen_len": 20.3364,
|
| 202 |
+
"eval_loss": 4.970686912536621,
|
| 203 |
+
"eval_runtime": 476.4474,
|
| 204 |
+
"eval_samples_per_second": 25.516,
|
| 205 |
+
"eval_steps_per_second": 0.798,
|
| 206 |
+
"step": 750
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 20.0,
|
| 210 |
+
"eval_bleu": 0.784,
|
| 211 |
+
"eval_gen_len": 20.3641,
|
| 212 |
+
"eval_loss": 4.984948635101318,
|
| 213 |
+
"eval_runtime": 477.378,
|
| 214 |
+
"eval_samples_per_second": 25.466,
|
| 215 |
+
"eval_steps_per_second": 0.796,
|
| 216 |
+
"step": 790
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 20.9873417721519,
|
| 220 |
+
"eval_bleu": 0.7838,
|
| 221 |
+
"eval_gen_len": 20.3852,
|
| 222 |
+
"eval_loss": 5.011585712432861,
|
| 223 |
+
"eval_runtime": 477.6336,
|
| 224 |
+
"eval_samples_per_second": 25.453,
|
| 225 |
+
"eval_steps_per_second": 0.796,
|
| 226 |
+
"step": 829
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 22.0,
|
| 230 |
+
"eval_bleu": 0.7874,
|
| 231 |
+
"eval_gen_len": 20.3104,
|
| 232 |
+
"eval_loss": 5.026498794555664,
|
| 233 |
+
"eval_runtime": 477.8381,
|
| 234 |
+
"eval_samples_per_second": 25.442,
|
| 235 |
+
"eval_steps_per_second": 0.795,
|
| 236 |
+
"step": 869
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 22.9873417721519,
|
| 240 |
+
"eval_bleu": 0.7886,
|
| 241 |
+
"eval_gen_len": 20.3484,
|
| 242 |
+
"eval_loss": 5.026541233062744,
|
| 243 |
+
"eval_runtime": 478.7469,
|
| 244 |
+
"eval_samples_per_second": 25.393,
|
| 245 |
+
"eval_steps_per_second": 0.794,
|
| 246 |
+
"step": 908
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 24.0,
|
| 250 |
+
"eval_bleu": 0.7833,
|
| 251 |
+
"eval_gen_len": 20.3558,
|
| 252 |
+
"eval_loss": 5.028345584869385,
|
| 253 |
+
"eval_runtime": 476.6444,
|
| 254 |
+
"eval_samples_per_second": 25.505,
|
| 255 |
+
"eval_steps_per_second": 0.797,
|
| 256 |
+
"step": 948
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 24.9873417721519,
|
| 260 |
+
"eval_bleu": 0.7835,
|
| 261 |
+
"eval_gen_len": 20.313,
|
| 262 |
+
"eval_loss": 5.029706001281738,
|
| 263 |
+
"eval_runtime": 478.6376,
|
| 264 |
+
"eval_samples_per_second": 25.399,
|
| 265 |
+
"eval_steps_per_second": 0.794,
|
| 266 |
+
"step": 987
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 25.31645569620253,
|
| 270 |
+
"grad_norm": 0.5030060410499573,
|
| 271 |
+
"learning_rate": 2.9059829059829063e-06,
|
| 272 |
+
"loss": 0.0263,
|
| 273 |
+
"step": 1000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 26.0,
|
| 277 |
+
"eval_bleu": 0.7812,
|
| 278 |
+
"eval_gen_len": 20.3503,
|
| 279 |
+
"eval_loss": 5.040848731994629,
|
| 280 |
+
"eval_runtime": 478.615,
|
| 281 |
+
"eval_samples_per_second": 25.4,
|
| 282 |
+
"eval_steps_per_second": 0.794,
|
| 283 |
+
"step": 1027
|
| 284 |
+
}
|
| 285 |
+
],
|
| 286 |
+
"logging_steps": 500,
|
| 287 |
+
"max_steps": 1170,
|
| 288 |
+
"num_input_tokens_seen": 0,
|
| 289 |
+
"num_train_epochs": 30,
|
| 290 |
+
"save_steps": 1000,
|
| 291 |
+
"stateful_callbacks": {
|
| 292 |
+
"TrainerControl": {
|
| 293 |
+
"args": {
|
| 294 |
+
"should_epoch_stop": false,
|
| 295 |
+
"should_evaluate": false,
|
| 296 |
+
"should_log": false,
|
| 297 |
+
"should_save": true,
|
| 298 |
+
"should_training_stop": false
|
| 299 |
+
},
|
| 300 |
+
"attributes": {}
|
| 301 |
+
}
|
| 302 |
+
},
|
| 303 |
+
"total_flos": 346447645507584.0,
|
| 304 |
+
"train_batch_size": 32,
|
| 305 |
+
"trial_name": null,
|
| 306 |
+
"trial_params": null
|
| 307 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:308614a7c1143402fb2b7f47f4e5b67e0ad8de478d93377850387da73b823bf1
|
| 3 |
+
size 5304
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|