model commit
Browse files- config.json +75 -0
- generation_config.json +12 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- trainer_state.json +861 -0
- training_args.bin +3 -0
- vocab.json +0 -0
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": "4.36.2",
|
| 73 |
+
"use_cache": true,
|
| 74 |
+
"vocab_size": 50265
|
| 75 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 0,
|
| 3 |
+
"decoder_start_token_id": 2,
|
| 4 |
+
"early_stopping": true,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"forced_bos_token_id": 0,
|
| 7 |
+
"forced_eos_token_id": 2,
|
| 8 |
+
"no_repeat_ngram_size": 3,
|
| 9 |
+
"num_beams": 4,
|
| 10 |
+
"pad_token_id": 1,
|
| 11 |
+
"transformers_version": "4.36.2"
|
| 12 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ecc803ceb87868ffa78f53ec771c5560515785802ca22015d9cf838cb590062f
|
| 3 |
+
size 557912620
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1b11cde7772a71a2e70fff84c5bdd0e93a292e95b2042cb0e9ec264d5cf49e7
|
| 3 |
+
size 1115579461
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15685c271ad4c80a17917de266d3acafcd366bb317a51ee551f85837b5593c3b
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d1b953ca68d04d1d42c9566838dec216667e2950e6a1fe5cd76b0b386e94733
|
| 3 |
+
size 627
|
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 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 1024,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "BartTokenizer",
|
| 55 |
+
"trim_offsets": true,
|
| 56 |
+
"unk_token": "<unk>"
|
| 57 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,861 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 42.8213,
|
| 3 |
+
"best_model_checkpoint": "facebook/bart-base-finetuned/checkpoint-60000",
|
| 4 |
+
"epoch": 7.8237058286608425,
|
| 5 |
+
"eval_steps": 5000,
|
| 6 |
+
"global_step": 60000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.07,
|
| 13 |
+
"learning_rate": 3.967401225713913e-05,
|
| 14 |
+
"loss": 1.5862,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.13,
|
| 19 |
+
"learning_rate": 3.9348024514278265e-05,
|
| 20 |
+
"loss": 1.0258,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.2,
|
| 25 |
+
"learning_rate": 3.90220367714174e-05,
|
| 26 |
+
"loss": 0.8928,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.26,
|
| 31 |
+
"learning_rate": 3.869604902855653e-05,
|
| 32 |
+
"loss": 0.8012,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.33,
|
| 37 |
+
"learning_rate": 3.837006128569566e-05,
|
| 38 |
+
"loss": 0.7591,
|
| 39 |
+
"step": 2500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.39,
|
| 43 |
+
"learning_rate": 3.804407354283479e-05,
|
| 44 |
+
"loss": 0.7188,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.46,
|
| 49 |
+
"learning_rate": 3.7718085799973924e-05,
|
| 50 |
+
"loss": 0.6802,
|
| 51 |
+
"step": 3500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.52,
|
| 55 |
+
"learning_rate": 3.739209805711306e-05,
|
| 56 |
+
"loss": 0.6529,
|
| 57 |
+
"step": 4000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.59,
|
| 61 |
+
"learning_rate": 3.7066110314252186e-05,
|
| 62 |
+
"loss": 0.6373,
|
| 63 |
+
"step": 4500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.65,
|
| 67 |
+
"learning_rate": 3.674012257139132e-05,
|
| 68 |
+
"loss": 0.6121,
|
| 69 |
+
"step": 5000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.65,
|
| 73 |
+
"eval_bleu": 37.8898,
|
| 74 |
+
"eval_gen_len": 18.0188,
|
| 75 |
+
"eval_loss": 0.5747564435005188,
|
| 76 |
+
"eval_runtime": 121.8837,
|
| 77 |
+
"eval_samples_per_second": 41.105,
|
| 78 |
+
"eval_steps_per_second": 0.648,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.72,
|
| 83 |
+
"learning_rate": 3.641413482853045e-05,
|
| 84 |
+
"loss": 0.5929,
|
| 85 |
+
"step": 5500
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.78,
|
| 89 |
+
"learning_rate": 3.608814708566958e-05,
|
| 90 |
+
"loss": 0.5763,
|
| 91 |
+
"step": 6000
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.85,
|
| 95 |
+
"learning_rate": 3.576215934280872e-05,
|
| 96 |
+
"loss": 0.5636,
|
| 97 |
+
"step": 6500
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.91,
|
| 101 |
+
"learning_rate": 3.5436171599947845e-05,
|
| 102 |
+
"loss": 0.5576,
|
| 103 |
+
"step": 7000
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 0.98,
|
| 107 |
+
"learning_rate": 3.511018385708698e-05,
|
| 108 |
+
"loss": 0.5442,
|
| 109 |
+
"step": 7500
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.04,
|
| 113 |
+
"learning_rate": 3.478419611422611e-05,
|
| 114 |
+
"loss": 0.5211,
|
| 115 |
+
"step": 8000
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 1.11,
|
| 119 |
+
"learning_rate": 3.445820837136524e-05,
|
| 120 |
+
"loss": 0.508,
|
| 121 |
+
"step": 8500
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.17,
|
| 125 |
+
"learning_rate": 3.413222062850437e-05,
|
| 126 |
+
"loss": 0.5007,
|
| 127 |
+
"step": 9000
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 1.24,
|
| 131 |
+
"learning_rate": 3.38062328856435e-05,
|
| 132 |
+
"loss": 0.5062,
|
| 133 |
+
"step": 9500
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 1.3,
|
| 137 |
+
"learning_rate": 3.348024514278264e-05,
|
| 138 |
+
"loss": 0.4967,
|
| 139 |
+
"step": 10000
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 1.3,
|
| 143 |
+
"eval_bleu": 39.3429,
|
| 144 |
+
"eval_gen_len": 18.0347,
|
| 145 |
+
"eval_loss": 0.4752778112888336,
|
| 146 |
+
"eval_runtime": 118.4418,
|
| 147 |
+
"eval_samples_per_second": 42.299,
|
| 148 |
+
"eval_steps_per_second": 0.667,
|
| 149 |
+
"step": 10000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.37,
|
| 153 |
+
"learning_rate": 3.3154257399921765e-05,
|
| 154 |
+
"loss": 0.4876,
|
| 155 |
+
"step": 10500
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.43,
|
| 159 |
+
"learning_rate": 3.282826965706089e-05,
|
| 160 |
+
"loss": 0.4762,
|
| 161 |
+
"step": 11000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.5,
|
| 165 |
+
"learning_rate": 3.250228191420003e-05,
|
| 166 |
+
"loss": 0.4716,
|
| 167 |
+
"step": 11500
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.56,
|
| 171 |
+
"learning_rate": 3.217629417133916e-05,
|
| 172 |
+
"loss": 0.4632,
|
| 173 |
+
"step": 12000
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.63,
|
| 177 |
+
"learning_rate": 3.185030642847829e-05,
|
| 178 |
+
"loss": 0.4588,
|
| 179 |
+
"step": 12500
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.7,
|
| 183 |
+
"learning_rate": 3.1524318685617424e-05,
|
| 184 |
+
"loss": 0.4605,
|
| 185 |
+
"step": 13000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.76,
|
| 189 |
+
"learning_rate": 3.119833094275655e-05,
|
| 190 |
+
"loss": 0.457,
|
| 191 |
+
"step": 13500
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.83,
|
| 195 |
+
"learning_rate": 3.0872343199895686e-05,
|
| 196 |
+
"loss": 0.4573,
|
| 197 |
+
"step": 14000
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.89,
|
| 201 |
+
"learning_rate": 3.054635545703482e-05,
|
| 202 |
+
"loss": 0.4527,
|
| 203 |
+
"step": 14500
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.96,
|
| 207 |
+
"learning_rate": 3.0220367714173952e-05,
|
| 208 |
+
"loss": 0.4437,
|
| 209 |
+
"step": 15000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.96,
|
| 213 |
+
"eval_bleu": 40.7435,
|
| 214 |
+
"eval_gen_len": 18.2399,
|
| 215 |
+
"eval_loss": 0.4312632977962494,
|
| 216 |
+
"eval_runtime": 118.0141,
|
| 217 |
+
"eval_samples_per_second": 42.453,
|
| 218 |
+
"eval_steps_per_second": 0.669,
|
| 219 |
+
"step": 15000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 2.02,
|
| 223 |
+
"learning_rate": 2.9894379971313083e-05,
|
| 224 |
+
"loss": 0.442,
|
| 225 |
+
"step": 15500
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 2.09,
|
| 229 |
+
"learning_rate": 2.956839222845221e-05,
|
| 230 |
+
"loss": 0.4233,
|
| 231 |
+
"step": 16000
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 2.15,
|
| 235 |
+
"learning_rate": 2.924240448559134e-05,
|
| 236 |
+
"loss": 0.4186,
|
| 237 |
+
"step": 16500
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.22,
|
| 241 |
+
"learning_rate": 2.891641674273048e-05,
|
| 242 |
+
"loss": 0.4156,
|
| 243 |
+
"step": 17000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 2.28,
|
| 247 |
+
"learning_rate": 2.8590428999869607e-05,
|
| 248 |
+
"loss": 0.4211,
|
| 249 |
+
"step": 17500
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 2.35,
|
| 253 |
+
"learning_rate": 2.8264441257008738e-05,
|
| 254 |
+
"loss": 0.4177,
|
| 255 |
+
"step": 18000
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 2.41,
|
| 259 |
+
"learning_rate": 2.793845351414787e-05,
|
| 260 |
+
"loss": 0.4088,
|
| 261 |
+
"step": 18500
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.48,
|
| 265 |
+
"learning_rate": 2.7612465771287e-05,
|
| 266 |
+
"loss": 0.4082,
|
| 267 |
+
"step": 19000
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 2.54,
|
| 271 |
+
"learning_rate": 2.7286478028426135e-05,
|
| 272 |
+
"loss": 0.4094,
|
| 273 |
+
"step": 19500
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 2.61,
|
| 277 |
+
"learning_rate": 2.6960490285565266e-05,
|
| 278 |
+
"loss": 0.4064,
|
| 279 |
+
"step": 20000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.61,
|
| 283 |
+
"eval_bleu": 41.105,
|
| 284 |
+
"eval_gen_len": 18.2493,
|
| 285 |
+
"eval_loss": 0.4060722589492798,
|
| 286 |
+
"eval_runtime": 118.819,
|
| 287 |
+
"eval_samples_per_second": 42.165,
|
| 288 |
+
"eval_steps_per_second": 0.665,
|
| 289 |
+
"step": 20000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 2.67,
|
| 293 |
+
"learning_rate": 2.6634502542704397e-05,
|
| 294 |
+
"loss": 0.4069,
|
| 295 |
+
"step": 20500
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 2.74,
|
| 299 |
+
"learning_rate": 2.6308514799843528e-05,
|
| 300 |
+
"loss": 0.4023,
|
| 301 |
+
"step": 21000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 2.8,
|
| 305 |
+
"learning_rate": 2.598252705698266e-05,
|
| 306 |
+
"loss": 0.3994,
|
| 307 |
+
"step": 21500
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 2.87,
|
| 311 |
+
"learning_rate": 2.5656539314121793e-05,
|
| 312 |
+
"loss": 0.4005,
|
| 313 |
+
"step": 22000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 2.93,
|
| 317 |
+
"learning_rate": 2.5330551571260924e-05,
|
| 318 |
+
"loss": 0.4006,
|
| 319 |
+
"step": 22500
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 3.0,
|
| 323 |
+
"learning_rate": 2.5004563828400055e-05,
|
| 324 |
+
"loss": 0.4013,
|
| 325 |
+
"step": 23000
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 3.06,
|
| 329 |
+
"learning_rate": 2.4678576085539186e-05,
|
| 330 |
+
"loss": 0.3765,
|
| 331 |
+
"step": 23500
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 3.13,
|
| 335 |
+
"learning_rate": 2.4352588342678317e-05,
|
| 336 |
+
"loss": 0.3796,
|
| 337 |
+
"step": 24000
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 3.19,
|
| 341 |
+
"learning_rate": 2.402660059981745e-05,
|
| 342 |
+
"loss": 0.3726,
|
| 343 |
+
"step": 24500
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 3.26,
|
| 347 |
+
"learning_rate": 2.3700612856956583e-05,
|
| 348 |
+
"loss": 0.3795,
|
| 349 |
+
"step": 25000
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 3.26,
|
| 353 |
+
"eval_bleu": 42.0027,
|
| 354 |
+
"eval_gen_len": 18.2441,
|
| 355 |
+
"eval_loss": 0.3876380920410156,
|
| 356 |
+
"eval_runtime": 120.3412,
|
| 357 |
+
"eval_samples_per_second": 41.632,
|
| 358 |
+
"eval_steps_per_second": 0.656,
|
| 359 |
+
"step": 25000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 3.33,
|
| 363 |
+
"learning_rate": 2.3374625114095714e-05,
|
| 364 |
+
"loss": 0.3766,
|
| 365 |
+
"step": 25500
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 3.39,
|
| 369 |
+
"learning_rate": 2.304863737123484e-05,
|
| 370 |
+
"loss": 0.38,
|
| 371 |
+
"step": 26000
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 3.46,
|
| 375 |
+
"learning_rate": 2.2722649628373973e-05,
|
| 376 |
+
"loss": 0.3732,
|
| 377 |
+
"step": 26500
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 3.52,
|
| 381 |
+
"learning_rate": 2.2396661885513104e-05,
|
| 382 |
+
"loss": 0.3719,
|
| 383 |
+
"step": 27000
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 3.59,
|
| 387 |
+
"learning_rate": 2.2070674142652238e-05,
|
| 388 |
+
"loss": 0.3693,
|
| 389 |
+
"step": 27500
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 3.65,
|
| 393 |
+
"learning_rate": 2.174468639979137e-05,
|
| 394 |
+
"loss": 0.3758,
|
| 395 |
+
"step": 28000
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 3.72,
|
| 399 |
+
"learning_rate": 2.14186986569305e-05,
|
| 400 |
+
"loss": 0.3599,
|
| 401 |
+
"step": 28500
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 3.78,
|
| 405 |
+
"learning_rate": 2.109271091406963e-05,
|
| 406 |
+
"loss": 0.3673,
|
| 407 |
+
"step": 29000
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 3.85,
|
| 411 |
+
"learning_rate": 2.0766723171208762e-05,
|
| 412 |
+
"loss": 0.369,
|
| 413 |
+
"step": 29500
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 3.91,
|
| 417 |
+
"learning_rate": 2.0440735428347897e-05,
|
| 418 |
+
"loss": 0.3728,
|
| 419 |
+
"step": 30000
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 3.91,
|
| 423 |
+
"eval_bleu": 42.191,
|
| 424 |
+
"eval_gen_len": 18.2934,
|
| 425 |
+
"eval_loss": 0.3774366080760956,
|
| 426 |
+
"eval_runtime": 118.342,
|
| 427 |
+
"eval_samples_per_second": 42.335,
|
| 428 |
+
"eval_steps_per_second": 0.668,
|
| 429 |
+
"step": 30000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 3.98,
|
| 433 |
+
"learning_rate": 2.0114747685487028e-05,
|
| 434 |
+
"loss": 0.3673,
|
| 435 |
+
"step": 30500
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 4.04,
|
| 439 |
+
"learning_rate": 1.978875994262616e-05,
|
| 440 |
+
"loss": 0.3562,
|
| 441 |
+
"step": 31000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 4.11,
|
| 445 |
+
"learning_rate": 1.946277219976529e-05,
|
| 446 |
+
"loss": 0.3518,
|
| 447 |
+
"step": 31500
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 4.17,
|
| 451 |
+
"learning_rate": 1.913678445690442e-05,
|
| 452 |
+
"loss": 0.3484,
|
| 453 |
+
"step": 32000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 4.24,
|
| 457 |
+
"learning_rate": 1.8810796714043552e-05,
|
| 458 |
+
"loss": 0.3489,
|
| 459 |
+
"step": 32500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 4.3,
|
| 463 |
+
"learning_rate": 1.8484808971182686e-05,
|
| 464 |
+
"loss": 0.3529,
|
| 465 |
+
"step": 33000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 4.37,
|
| 469 |
+
"learning_rate": 1.8158821228321817e-05,
|
| 470 |
+
"loss": 0.347,
|
| 471 |
+
"step": 33500
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 4.43,
|
| 475 |
+
"learning_rate": 1.783283348546095e-05,
|
| 476 |
+
"loss": 0.3442,
|
| 477 |
+
"step": 34000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 4.5,
|
| 481 |
+
"learning_rate": 1.750684574260008e-05,
|
| 482 |
+
"loss": 0.3498,
|
| 483 |
+
"step": 34500
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 4.56,
|
| 487 |
+
"learning_rate": 1.718085799973921e-05,
|
| 488 |
+
"loss": 0.3464,
|
| 489 |
+
"step": 35000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 4.56,
|
| 493 |
+
"eval_bleu": 42.1307,
|
| 494 |
+
"eval_gen_len": 18.2251,
|
| 495 |
+
"eval_loss": 0.3665723502635956,
|
| 496 |
+
"eval_runtime": 117.0033,
|
| 497 |
+
"eval_samples_per_second": 42.819,
|
| 498 |
+
"eval_steps_per_second": 0.675,
|
| 499 |
+
"step": 35000
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 4.63,
|
| 503 |
+
"learning_rate": 1.685487025687834e-05,
|
| 504 |
+
"loss": 0.3484,
|
| 505 |
+
"step": 35500
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 4.69,
|
| 509 |
+
"learning_rate": 1.6528882514017476e-05,
|
| 510 |
+
"loss": 0.3432,
|
| 511 |
+
"step": 36000
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 4.76,
|
| 515 |
+
"learning_rate": 1.6202894771156604e-05,
|
| 516 |
+
"loss": 0.3477,
|
| 517 |
+
"step": 36500
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 4.82,
|
| 521 |
+
"learning_rate": 1.5876907028295738e-05,
|
| 522 |
+
"loss": 0.3476,
|
| 523 |
+
"step": 37000
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 4.89,
|
| 527 |
+
"learning_rate": 1.555091928543487e-05,
|
| 528 |
+
"loss": 0.3471,
|
| 529 |
+
"step": 37500
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 4.96,
|
| 533 |
+
"learning_rate": 1.5224931542574e-05,
|
| 534 |
+
"loss": 0.3462,
|
| 535 |
+
"step": 38000
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 5.02,
|
| 539 |
+
"learning_rate": 1.4898943799713133e-05,
|
| 540 |
+
"loss": 0.3407,
|
| 541 |
+
"step": 38500
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 5.09,
|
| 545 |
+
"learning_rate": 1.4572956056852262e-05,
|
| 546 |
+
"loss": 0.3312,
|
| 547 |
+
"step": 39000
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 5.15,
|
| 551 |
+
"learning_rate": 1.4246968313991397e-05,
|
| 552 |
+
"loss": 0.3297,
|
| 553 |
+
"step": 39500
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 5.22,
|
| 557 |
+
"learning_rate": 1.3920980571130526e-05,
|
| 558 |
+
"loss": 0.3321,
|
| 559 |
+
"step": 40000
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 5.22,
|
| 563 |
+
"eval_bleu": 42.2362,
|
| 564 |
+
"eval_gen_len": 18.1764,
|
| 565 |
+
"eval_loss": 0.36170148849487305,
|
| 566 |
+
"eval_runtime": 117.3524,
|
| 567 |
+
"eval_samples_per_second": 42.692,
|
| 568 |
+
"eval_steps_per_second": 0.673,
|
| 569 |
+
"step": 40000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 5.28,
|
| 573 |
+
"learning_rate": 1.3594992828269657e-05,
|
| 574 |
+
"loss": 0.33,
|
| 575 |
+
"step": 40500
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 5.35,
|
| 579 |
+
"learning_rate": 1.326900508540879e-05,
|
| 580 |
+
"loss": 0.3308,
|
| 581 |
+
"step": 41000
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 5.41,
|
| 585 |
+
"learning_rate": 1.2943017342547921e-05,
|
| 586 |
+
"loss": 0.3305,
|
| 587 |
+
"step": 41500
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 5.48,
|
| 591 |
+
"learning_rate": 1.2617029599687052e-05,
|
| 592 |
+
"loss": 0.3259,
|
| 593 |
+
"step": 42000
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 5.54,
|
| 597 |
+
"learning_rate": 1.2291041856826185e-05,
|
| 598 |
+
"loss": 0.3337,
|
| 599 |
+
"step": 42500
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 5.61,
|
| 603 |
+
"learning_rate": 1.1965054113965316e-05,
|
| 604 |
+
"loss": 0.3334,
|
| 605 |
+
"step": 43000
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 5.67,
|
| 609 |
+
"learning_rate": 1.1639066371104449e-05,
|
| 610 |
+
"loss": 0.329,
|
| 611 |
+
"step": 43500
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 5.74,
|
| 615 |
+
"learning_rate": 1.131307862824358e-05,
|
| 616 |
+
"loss": 0.3306,
|
| 617 |
+
"step": 44000
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 5.8,
|
| 621 |
+
"learning_rate": 1.0987090885382709e-05,
|
| 622 |
+
"loss": 0.33,
|
| 623 |
+
"step": 44500
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 5.87,
|
| 627 |
+
"learning_rate": 1.0661103142521842e-05,
|
| 628 |
+
"loss": 0.3264,
|
| 629 |
+
"step": 45000
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 5.87,
|
| 633 |
+
"eval_bleu": 42.4323,
|
| 634 |
+
"eval_gen_len": 18.2745,
|
| 635 |
+
"eval_loss": 0.3556722104549408,
|
| 636 |
+
"eval_runtime": 116.9876,
|
| 637 |
+
"eval_samples_per_second": 42.825,
|
| 638 |
+
"eval_steps_per_second": 0.675,
|
| 639 |
+
"step": 45000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 5.93,
|
| 643 |
+
"learning_rate": 1.0335115399660973e-05,
|
| 644 |
+
"loss": 0.3275,
|
| 645 |
+
"step": 45500
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 6.0,
|
| 649 |
+
"learning_rate": 1.0009127656800106e-05,
|
| 650 |
+
"loss": 0.3225,
|
| 651 |
+
"step": 46000
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 6.06,
|
| 655 |
+
"learning_rate": 9.683139913939237e-06,
|
| 656 |
+
"loss": 0.3143,
|
| 657 |
+
"step": 46500
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 6.13,
|
| 661 |
+
"learning_rate": 9.35715217107837e-06,
|
| 662 |
+
"loss": 0.3169,
|
| 663 |
+
"step": 47000
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 6.19,
|
| 667 |
+
"learning_rate": 9.031164428217499e-06,
|
| 668 |
+
"loss": 0.3134,
|
| 669 |
+
"step": 47500
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 6.26,
|
| 673 |
+
"learning_rate": 8.705176685356631e-06,
|
| 674 |
+
"loss": 0.3218,
|
| 675 |
+
"step": 48000
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 6.32,
|
| 679 |
+
"learning_rate": 8.379188942495763e-06,
|
| 680 |
+
"loss": 0.3169,
|
| 681 |
+
"step": 48500
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 6.39,
|
| 685 |
+
"learning_rate": 8.053201199634895e-06,
|
| 686 |
+
"loss": 0.3163,
|
| 687 |
+
"step": 49000
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 6.45,
|
| 691 |
+
"learning_rate": 7.727213456774026e-06,
|
| 692 |
+
"loss": 0.3199,
|
| 693 |
+
"step": 49500
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 6.52,
|
| 697 |
+
"learning_rate": 7.401225713913157e-06,
|
| 698 |
+
"loss": 0.321,
|
| 699 |
+
"step": 50000
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 6.52,
|
| 703 |
+
"eval_bleu": 42.797,
|
| 704 |
+
"eval_gen_len": 18.177,
|
| 705 |
+
"eval_loss": 0.3521122634410858,
|
| 706 |
+
"eval_runtime": 118.7785,
|
| 707 |
+
"eval_samples_per_second": 42.179,
|
| 708 |
+
"eval_steps_per_second": 0.665,
|
| 709 |
+
"step": 50000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 6.58,
|
| 713 |
+
"learning_rate": 7.075237971052289e-06,
|
| 714 |
+
"loss": 0.3166,
|
| 715 |
+
"step": 50500
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 6.65,
|
| 719 |
+
"learning_rate": 6.74925022819142e-06,
|
| 720 |
+
"loss": 0.3137,
|
| 721 |
+
"step": 51000
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 6.72,
|
| 725 |
+
"learning_rate": 6.423262485330552e-06,
|
| 726 |
+
"loss": 0.314,
|
| 727 |
+
"step": 51500
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 6.78,
|
| 731 |
+
"learning_rate": 6.097274742469683e-06,
|
| 732 |
+
"loss": 0.3163,
|
| 733 |
+
"step": 52000
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 6.85,
|
| 737 |
+
"learning_rate": 5.771286999608815e-06,
|
| 738 |
+
"loss": 0.3177,
|
| 739 |
+
"step": 52500
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 6.91,
|
| 743 |
+
"learning_rate": 5.445299256747947e-06,
|
| 744 |
+
"loss": 0.3153,
|
| 745 |
+
"step": 53000
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 6.98,
|
| 749 |
+
"learning_rate": 5.119311513887079e-06,
|
| 750 |
+
"loss": 0.3153,
|
| 751 |
+
"step": 53500
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 7.04,
|
| 755 |
+
"learning_rate": 4.79332377102621e-06,
|
| 756 |
+
"loss": 0.3095,
|
| 757 |
+
"step": 54000
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 7.11,
|
| 761 |
+
"learning_rate": 4.467336028165342e-06,
|
| 762 |
+
"loss": 0.3073,
|
| 763 |
+
"step": 54500
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 7.17,
|
| 767 |
+
"learning_rate": 4.141348285304473e-06,
|
| 768 |
+
"loss": 0.3063,
|
| 769 |
+
"step": 55000
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 7.17,
|
| 773 |
+
"eval_bleu": 42.6295,
|
| 774 |
+
"eval_gen_len": 18.2265,
|
| 775 |
+
"eval_loss": 0.3495286703109741,
|
| 776 |
+
"eval_runtime": 120.504,
|
| 777 |
+
"eval_samples_per_second": 41.575,
|
| 778 |
+
"eval_steps_per_second": 0.656,
|
| 779 |
+
"step": 55000
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 7.24,
|
| 783 |
+
"learning_rate": 3.815360542443605e-06,
|
| 784 |
+
"loss": 0.3107,
|
| 785 |
+
"step": 55500
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 7.3,
|
| 789 |
+
"learning_rate": 3.489372799582736e-06,
|
| 790 |
+
"loss": 0.3138,
|
| 791 |
+
"step": 56000
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 7.37,
|
| 795 |
+
"learning_rate": 3.163385056721868e-06,
|
| 796 |
+
"loss": 0.3092,
|
| 797 |
+
"step": 56500
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 7.43,
|
| 801 |
+
"learning_rate": 2.837397313860999e-06,
|
| 802 |
+
"loss": 0.3097,
|
| 803 |
+
"step": 57000
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 7.5,
|
| 807 |
+
"learning_rate": 2.5114095710001308e-06,
|
| 808 |
+
"loss": 0.3057,
|
| 809 |
+
"step": 57500
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 7.56,
|
| 813 |
+
"learning_rate": 2.1854218281392622e-06,
|
| 814 |
+
"loss": 0.3045,
|
| 815 |
+
"step": 58000
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 7.63,
|
| 819 |
+
"learning_rate": 1.8594340852783937e-06,
|
| 820 |
+
"loss": 0.3088,
|
| 821 |
+
"step": 58500
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 7.69,
|
| 825 |
+
"learning_rate": 1.5334463424175252e-06,
|
| 826 |
+
"loss": 0.306,
|
| 827 |
+
"step": 59000
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 7.76,
|
| 831 |
+
"learning_rate": 1.2074585995566569e-06,
|
| 832 |
+
"loss": 0.3118,
|
| 833 |
+
"step": 59500
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 7.82,
|
| 837 |
+
"learning_rate": 8.814708566957883e-07,
|
| 838 |
+
"loss": 0.3043,
|
| 839 |
+
"step": 60000
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 7.82,
|
| 843 |
+
"eval_bleu": 42.8213,
|
| 844 |
+
"eval_gen_len": 18.2248,
|
| 845 |
+
"eval_loss": 0.34873583912849426,
|
| 846 |
+
"eval_runtime": 121.0894,
|
| 847 |
+
"eval_samples_per_second": 41.374,
|
| 848 |
+
"eval_steps_per_second": 0.652,
|
| 849 |
+
"step": 60000
|
| 850 |
+
}
|
| 851 |
+
],
|
| 852 |
+
"logging_steps": 500,
|
| 853 |
+
"max_steps": 61352,
|
| 854 |
+
"num_input_tokens_seen": 0,
|
| 855 |
+
"num_train_epochs": 8,
|
| 856 |
+
"save_steps": 5000,
|
| 857 |
+
"total_flos": 3.672168663840768e+16,
|
| 858 |
+
"train_batch_size": 64,
|
| 859 |
+
"trial_name": null,
|
| 860 |
+
"trial_params": null
|
| 861 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de90077c282c0c6afd2990fd90aa4499e892c55dd47efd5ca9ce0e74561bfadf
|
| 3 |
+
size 4411
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|