ZhangYunchenY
commited on
Commit
·
426b5ab
1
Parent(s):
32703c7
[Model] bart-base-xsum
Browse files- config.json +76 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +1080 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/mnt/lustre/zhangyunchen/transformers/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_eos_token_id": 2,
|
| 28 |
+
"gradient_checkpointing": false,
|
| 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": 62,
|
| 42 |
+
"max_position_embeddings": 1024,
|
| 43 |
+
"min_length": 11,
|
| 44 |
+
"model_type": "bart",
|
| 45 |
+
"no_repeat_ngram_size": 3,
|
| 46 |
+
"normalize_before": false,
|
| 47 |
+
"normalize_embedding": true,
|
| 48 |
+
"num_beams": 6,
|
| 49 |
+
"num_hidden_layers": 6,
|
| 50 |
+
"pad_token_id": 1,
|
| 51 |
+
"scale_embedding": false,
|
| 52 |
+
"task_specific_params": {
|
| 53 |
+
"summarization": {
|
| 54 |
+
"length_penalty": 1.0,
|
| 55 |
+
"max_length": 128,
|
| 56 |
+
"min_length": 12,
|
| 57 |
+
"num_beams": 4
|
| 58 |
+
},
|
| 59 |
+
"summarization_cnn": {
|
| 60 |
+
"length_penalty": 2.0,
|
| 61 |
+
"max_length": 142,
|
| 62 |
+
"min_length": 56,
|
| 63 |
+
"num_beams": 4
|
| 64 |
+
},
|
| 65 |
+
"summarization_xsum": {
|
| 66 |
+
"length_penalty": 1.0,
|
| 67 |
+
"max_length": 62,
|
| 68 |
+
"min_length": 11,
|
| 69 |
+
"num_beams": 6
|
| 70 |
+
}
|
| 71 |
+
},
|
| 72 |
+
"torch_dtype": "float32",
|
| 73 |
+
"transformers_version": "4.16.2",
|
| 74 |
+
"use_cache": true,
|
| 75 |
+
"vocab_size": 50265
|
| 76 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a196d5ba128b5eb44bc2e6151bcb783ca392b1bdd2168ed3f4f4c4a99b42dad
|
| 3 |
+
size 1115527467
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0b86faab03570f1fc461375c131869c09823b9cca68b1e43956547b5c623ad7
|
| 3 |
+
size 557986199
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d80e5d4701cb1988acad5c269e31fefd56007b39b1a0ae15ae75d78e08de92df
|
| 3 |
+
size 14595
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a4d52ca32d90c332eea073c953c4ddc1ae9cfc78a8e90e95dedece59d83b3b2
|
| 3 |
+
size 623
|
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}}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
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, "special_tokens_map_file": null, "name_or_path": "/mnt/lustre/zhangyunchen/transformers/bart-base", "tokenizer_class": "BartTokenizer"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1080 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 11.91962675448914,
|
| 5 |
+
"global_step": 76000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.16,
|
| 12 |
+
"learning_rate": 8.712319219376199e-06,
|
| 13 |
+
"loss": 3.9787,
|
| 14 |
+
"step": 1000
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.16,
|
| 18 |
+
"eval_loss": 3.446138381958008,
|
| 19 |
+
"eval_runtime": 172.8011,
|
| 20 |
+
"eval_samples_per_second": 65.578,
|
| 21 |
+
"eval_steps_per_second": 16.395,
|
| 22 |
+
"step": 1000
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.31,
|
| 26 |
+
"learning_rate": 1.7424638438752397e-05,
|
| 27 |
+
"loss": 3.6486,
|
| 28 |
+
"step": 2000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.31,
|
| 32 |
+
"eval_loss": 3.351425886154175,
|
| 33 |
+
"eval_runtime": 164.1827,
|
| 34 |
+
"eval_samples_per_second": 69.021,
|
| 35 |
+
"eval_steps_per_second": 17.255,
|
| 36 |
+
"step": 2000
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.47,
|
| 40 |
+
"learning_rate": 2.6136957658128598e-05,
|
| 41 |
+
"loss": 3.5509,
|
| 42 |
+
"step": 3000
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.47,
|
| 46 |
+
"eval_loss": 3.2961513996124268,
|
| 47 |
+
"eval_runtime": 164.8921,
|
| 48 |
+
"eval_samples_per_second": 68.724,
|
| 49 |
+
"eval_steps_per_second": 17.181,
|
| 50 |
+
"step": 3000
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.63,
|
| 54 |
+
"learning_rate": 3.4849276877504794e-05,
|
| 55 |
+
"loss": 3.488,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.63,
|
| 60 |
+
"eval_loss": 3.2645070552825928,
|
| 61 |
+
"eval_runtime": 175.5668,
|
| 62 |
+
"eval_samples_per_second": 64.545,
|
| 63 |
+
"eval_steps_per_second": 16.136,
|
| 64 |
+
"step": 4000
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.78,
|
| 68 |
+
"learning_rate": 4.356159609688099e-05,
|
| 69 |
+
"loss": 3.4485,
|
| 70 |
+
"step": 5000
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.78,
|
| 74 |
+
"eval_loss": 3.236461877822876,
|
| 75 |
+
"eval_runtime": 172.1625,
|
| 76 |
+
"eval_samples_per_second": 65.822,
|
| 77 |
+
"eval_steps_per_second": 16.455,
|
| 78 |
+
"step": 5000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.94,
|
| 82 |
+
"learning_rate": 4.985484032435679e-05,
|
| 83 |
+
"loss": 3.4183,
|
| 84 |
+
"step": 6000
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.94,
|
| 88 |
+
"eval_loss": 3.213158130645752,
|
| 89 |
+
"eval_runtime": 165.7563,
|
| 90 |
+
"eval_samples_per_second": 68.365,
|
| 91 |
+
"eval_steps_per_second": 17.091,
|
| 92 |
+
"step": 6000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.1,
|
| 96 |
+
"learning_rate": 4.9298672984727646e-05,
|
| 97 |
+
"loss": 3.3437,
|
| 98 |
+
"step": 7000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.1,
|
| 102 |
+
"eval_loss": 3.199575185775757,
|
| 103 |
+
"eval_runtime": 155.1508,
|
| 104 |
+
"eval_samples_per_second": 73.039,
|
| 105 |
+
"eval_steps_per_second": 18.26,
|
| 106 |
+
"step": 7000
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 1.25,
|
| 110 |
+
"learning_rate": 4.87425056450985e-05,
|
| 111 |
+
"loss": 3.2964,
|
| 112 |
+
"step": 8000
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 1.25,
|
| 116 |
+
"eval_loss": 3.1807236671447754,
|
| 117 |
+
"eval_runtime": 156.1445,
|
| 118 |
+
"eval_samples_per_second": 72.574,
|
| 119 |
+
"eval_steps_per_second": 18.143,
|
| 120 |
+
"step": 8000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 1.41,
|
| 124 |
+
"learning_rate": 4.8186338305469355e-05,
|
| 125 |
+
"loss": 3.2813,
|
| 126 |
+
"step": 9000
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 1.41,
|
| 130 |
+
"eval_loss": 3.1617496013641357,
|
| 131 |
+
"eval_runtime": 169.4771,
|
| 132 |
+
"eval_samples_per_second": 66.864,
|
| 133 |
+
"eval_steps_per_second": 16.716,
|
| 134 |
+
"step": 9000
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.57,
|
| 138 |
+
"learning_rate": 4.76301709658402e-05,
|
| 139 |
+
"loss": 3.2586,
|
| 140 |
+
"step": 10000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.57,
|
| 144 |
+
"eval_loss": 3.14561128616333,
|
| 145 |
+
"eval_runtime": 169.05,
|
| 146 |
+
"eval_samples_per_second": 67.033,
|
| 147 |
+
"eval_steps_per_second": 16.758,
|
| 148 |
+
"step": 10000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 1.73,
|
| 152 |
+
"learning_rate": 4.7074003626211057e-05,
|
| 153 |
+
"loss": 3.248,
|
| 154 |
+
"step": 11000
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.73,
|
| 158 |
+
"eval_loss": 3.1361846923828125,
|
| 159 |
+
"eval_runtime": 165.9904,
|
| 160 |
+
"eval_samples_per_second": 68.269,
|
| 161 |
+
"eval_steps_per_second": 17.067,
|
| 162 |
+
"step": 11000
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.88,
|
| 166 |
+
"learning_rate": 4.651783628658191e-05,
|
| 167 |
+
"loss": 3.2413,
|
| 168 |
+
"step": 12000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.88,
|
| 172 |
+
"eval_loss": 3.1259961128234863,
|
| 173 |
+
"eval_runtime": 167.4544,
|
| 174 |
+
"eval_samples_per_second": 67.672,
|
| 175 |
+
"eval_steps_per_second": 16.918,
|
| 176 |
+
"step": 12000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.04,
|
| 180 |
+
"learning_rate": 4.5961668946952765e-05,
|
| 181 |
+
"loss": 3.1974,
|
| 182 |
+
"step": 13000
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.04,
|
| 186 |
+
"eval_loss": 3.121722459793091,
|
| 187 |
+
"eval_runtime": 167.3385,
|
| 188 |
+
"eval_samples_per_second": 67.719,
|
| 189 |
+
"eval_steps_per_second": 16.93,
|
| 190 |
+
"step": 13000
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 2.2,
|
| 194 |
+
"learning_rate": 4.540550160732361e-05,
|
| 195 |
+
"loss": 3.1014,
|
| 196 |
+
"step": 14000
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 2.2,
|
| 200 |
+
"eval_loss": 3.1170709133148193,
|
| 201 |
+
"eval_runtime": 166.2081,
|
| 202 |
+
"eval_samples_per_second": 68.18,
|
| 203 |
+
"eval_steps_per_second": 17.045,
|
| 204 |
+
"step": 14000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 2.35,
|
| 208 |
+
"learning_rate": 4.484933426769447e-05,
|
| 209 |
+
"loss": 3.1037,
|
| 210 |
+
"step": 15000
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 2.35,
|
| 214 |
+
"eval_loss": 3.1060075759887695,
|
| 215 |
+
"eval_runtime": 163.3667,
|
| 216 |
+
"eval_samples_per_second": 69.365,
|
| 217 |
+
"eval_steps_per_second": 17.341,
|
| 218 |
+
"step": 15000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.51,
|
| 222 |
+
"learning_rate": 4.4293166928065315e-05,
|
| 223 |
+
"loss": 3.1047,
|
| 224 |
+
"step": 16000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.51,
|
| 228 |
+
"eval_loss": 3.1029844284057617,
|
| 229 |
+
"eval_runtime": 166.2417,
|
| 230 |
+
"eval_samples_per_second": 68.166,
|
| 231 |
+
"eval_steps_per_second": 17.041,
|
| 232 |
+
"step": 16000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 2.67,
|
| 236 |
+
"learning_rate": 4.3736999588436176e-05,
|
| 237 |
+
"loss": 3.1004,
|
| 238 |
+
"step": 17000
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 2.67,
|
| 242 |
+
"eval_loss": 3.0984201431274414,
|
| 243 |
+
"eval_runtime": 156.2961,
|
| 244 |
+
"eval_samples_per_second": 72.503,
|
| 245 |
+
"eval_steps_per_second": 18.126,
|
| 246 |
+
"step": 17000
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 2.82,
|
| 250 |
+
"learning_rate": 4.3180832248807023e-05,
|
| 251 |
+
"loss": 3.0932,
|
| 252 |
+
"step": 18000
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 2.82,
|
| 256 |
+
"eval_loss": 3.0867185592651367,
|
| 257 |
+
"eval_runtime": 163.2041,
|
| 258 |
+
"eval_samples_per_second": 69.435,
|
| 259 |
+
"eval_steps_per_second": 17.359,
|
| 260 |
+
"step": 18000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.98,
|
| 264 |
+
"learning_rate": 4.262466490917788e-05,
|
| 265 |
+
"loss": 3.0966,
|
| 266 |
+
"step": 19000
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.98,
|
| 270 |
+
"eval_loss": 3.0811350345611572,
|
| 271 |
+
"eval_runtime": 165.6977,
|
| 272 |
+
"eval_samples_per_second": 68.39,
|
| 273 |
+
"eval_steps_per_second": 17.097,
|
| 274 |
+
"step": 19000
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 3.14,
|
| 278 |
+
"learning_rate": 4.2068497569548725e-05,
|
| 279 |
+
"loss": 2.9921,
|
| 280 |
+
"step": 20000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 3.14,
|
| 284 |
+
"eval_loss": 3.089102029800415,
|
| 285 |
+
"eval_runtime": 158.578,
|
| 286 |
+
"eval_samples_per_second": 71.46,
|
| 287 |
+
"eval_steps_per_second": 17.865,
|
| 288 |
+
"step": 20000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 3.29,
|
| 292 |
+
"learning_rate": 4.151233022991958e-05,
|
| 293 |
+
"loss": 2.9753,
|
| 294 |
+
"step": 21000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 3.29,
|
| 298 |
+
"eval_loss": 3.0833535194396973,
|
| 299 |
+
"eval_runtime": 156.4016,
|
| 300 |
+
"eval_samples_per_second": 72.454,
|
| 301 |
+
"eval_steps_per_second": 18.114,
|
| 302 |
+
"step": 21000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 3.45,
|
| 306 |
+
"learning_rate": 4.0956162890290434e-05,
|
| 307 |
+
"loss": 2.9872,
|
| 308 |
+
"step": 22000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 3.45,
|
| 312 |
+
"eval_loss": 3.0813159942626953,
|
| 313 |
+
"eval_runtime": 154.7129,
|
| 314 |
+
"eval_samples_per_second": 73.245,
|
| 315 |
+
"eval_steps_per_second": 18.311,
|
| 316 |
+
"step": 22000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 3.61,
|
| 320 |
+
"learning_rate": 4.039999555066128e-05,
|
| 321 |
+
"loss": 2.9916,
|
| 322 |
+
"step": 23000
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 3.61,
|
| 326 |
+
"eval_loss": 3.069411516189575,
|
| 327 |
+
"eval_runtime": 157.7992,
|
| 328 |
+
"eval_samples_per_second": 71.813,
|
| 329 |
+
"eval_steps_per_second": 17.953,
|
| 330 |
+
"step": 23000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 3.76,
|
| 334 |
+
"learning_rate": 3.9843828211032136e-05,
|
| 335 |
+
"loss": 2.9885,
|
| 336 |
+
"step": 24000
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 3.76,
|
| 340 |
+
"eval_loss": 3.0638270378112793,
|
| 341 |
+
"eval_runtime": 155.9919,
|
| 342 |
+
"eval_samples_per_second": 72.645,
|
| 343 |
+
"eval_steps_per_second": 18.161,
|
| 344 |
+
"step": 24000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 3.92,
|
| 348 |
+
"learning_rate": 3.928766087140299e-05,
|
| 349 |
+
"loss": 2.9925,
|
| 350 |
+
"step": 25000
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 3.92,
|
| 354 |
+
"eval_loss": 3.0645134449005127,
|
| 355 |
+
"eval_runtime": 154.9825,
|
| 356 |
+
"eval_samples_per_second": 73.118,
|
| 357 |
+
"eval_steps_per_second": 18.279,
|
| 358 |
+
"step": 25000
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 4.08,
|
| 362 |
+
"learning_rate": 3.8731493531773845e-05,
|
| 363 |
+
"loss": 2.9338,
|
| 364 |
+
"step": 26000
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 4.08,
|
| 368 |
+
"eval_loss": 3.072267770767212,
|
| 369 |
+
"eval_runtime": 160.362,
|
| 370 |
+
"eval_samples_per_second": 70.665,
|
| 371 |
+
"eval_steps_per_second": 17.666,
|
| 372 |
+
"step": 26000
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 4.23,
|
| 376 |
+
"learning_rate": 3.817532619214469e-05,
|
| 377 |
+
"loss": 2.8808,
|
| 378 |
+
"step": 27000
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 4.23,
|
| 382 |
+
"eval_loss": 3.0753729343414307,
|
| 383 |
+
"eval_runtime": 154.306,
|
| 384 |
+
"eval_samples_per_second": 73.439,
|
| 385 |
+
"eval_steps_per_second": 18.36,
|
| 386 |
+
"step": 27000
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 4.39,
|
| 390 |
+
"learning_rate": 3.7619158852515547e-05,
|
| 391 |
+
"loss": 2.8947,
|
| 392 |
+
"step": 28000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 4.39,
|
| 396 |
+
"eval_loss": 3.0727920532226562,
|
| 397 |
+
"eval_runtime": 155.5666,
|
| 398 |
+
"eval_samples_per_second": 72.843,
|
| 399 |
+
"eval_steps_per_second": 18.211,
|
| 400 |
+
"step": 28000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 4.55,
|
| 404 |
+
"learning_rate": 3.7062991512886394e-05,
|
| 405 |
+
"loss": 2.8972,
|
| 406 |
+
"step": 29000
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 4.55,
|
| 410 |
+
"eval_loss": 3.0629560947418213,
|
| 411 |
+
"eval_runtime": 155.1806,
|
| 412 |
+
"eval_samples_per_second": 73.025,
|
| 413 |
+
"eval_steps_per_second": 18.256,
|
| 414 |
+
"step": 29000
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 4.71,
|
| 418 |
+
"learning_rate": 3.6506824173257255e-05,
|
| 419 |
+
"loss": 2.8965,
|
| 420 |
+
"step": 30000
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 4.71,
|
| 424 |
+
"eval_loss": 3.063514471054077,
|
| 425 |
+
"eval_runtime": 154.5456,
|
| 426 |
+
"eval_samples_per_second": 73.325,
|
| 427 |
+
"eval_steps_per_second": 18.331,
|
| 428 |
+
"step": 30000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 4.86,
|
| 432 |
+
"learning_rate": 3.59506568336281e-05,
|
| 433 |
+
"loss": 2.9067,
|
| 434 |
+
"step": 31000
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 4.86,
|
| 438 |
+
"eval_loss": 3.055640697479248,
|
| 439 |
+
"eval_runtime": 154.9311,
|
| 440 |
+
"eval_samples_per_second": 73.142,
|
| 441 |
+
"eval_steps_per_second": 18.286,
|
| 442 |
+
"step": 31000
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 5.02,
|
| 446 |
+
"learning_rate": 3.539448949399896e-05,
|
| 447 |
+
"loss": 2.8863,
|
| 448 |
+
"step": 32000
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 5.02,
|
| 452 |
+
"eval_loss": 3.0722622871398926,
|
| 453 |
+
"eval_runtime": 154.3548,
|
| 454 |
+
"eval_samples_per_second": 73.415,
|
| 455 |
+
"eval_steps_per_second": 18.354,
|
| 456 |
+
"step": 32000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 5.18,
|
| 460 |
+
"learning_rate": 3.4838322154369805e-05,
|
| 461 |
+
"loss": 2.8005,
|
| 462 |
+
"step": 33000
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 5.18,
|
| 466 |
+
"eval_loss": 3.072225332260132,
|
| 467 |
+
"eval_runtime": 168.3304,
|
| 468 |
+
"eval_samples_per_second": 67.32,
|
| 469 |
+
"eval_steps_per_second": 16.83,
|
| 470 |
+
"step": 33000
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 5.33,
|
| 474 |
+
"learning_rate": 3.4282154814740666e-05,
|
| 475 |
+
"loss": 2.8136,
|
| 476 |
+
"step": 34000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 5.33,
|
| 480 |
+
"eval_loss": 3.067979097366333,
|
| 481 |
+
"eval_runtime": 164.2522,
|
| 482 |
+
"eval_samples_per_second": 68.991,
|
| 483 |
+
"eval_steps_per_second": 17.248,
|
| 484 |
+
"step": 34000
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 5.49,
|
| 488 |
+
"learning_rate": 3.3725987475111513e-05,
|
| 489 |
+
"loss": 2.8092,
|
| 490 |
+
"step": 35000
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 5.49,
|
| 494 |
+
"eval_loss": 3.0639047622680664,
|
| 495 |
+
"eval_runtime": 167.1507,
|
| 496 |
+
"eval_samples_per_second": 67.795,
|
| 497 |
+
"eval_steps_per_second": 16.949,
|
| 498 |
+
"step": 35000
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 5.65,
|
| 502 |
+
"learning_rate": 3.316982013548237e-05,
|
| 503 |
+
"loss": 2.8186,
|
| 504 |
+
"step": 36000
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 5.65,
|
| 508 |
+
"eval_loss": 3.0562849044799805,
|
| 509 |
+
"eval_runtime": 158.9079,
|
| 510 |
+
"eval_samples_per_second": 71.312,
|
| 511 |
+
"eval_steps_per_second": 17.828,
|
| 512 |
+
"step": 36000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 5.8,
|
| 516 |
+
"learning_rate": 3.2613652795853215e-05,
|
| 517 |
+
"loss": 2.8306,
|
| 518 |
+
"step": 37000
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 5.8,
|
| 522 |
+
"eval_loss": 3.0535264015197754,
|
| 523 |
+
"eval_runtime": 150.4043,
|
| 524 |
+
"eval_samples_per_second": 75.344,
|
| 525 |
+
"eval_steps_per_second": 18.836,
|
| 526 |
+
"step": 37000
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 5.96,
|
| 530 |
+
"learning_rate": 3.205748545622407e-05,
|
| 531 |
+
"loss": 2.8327,
|
| 532 |
+
"step": 38000
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 5.96,
|
| 536 |
+
"eval_loss": 3.0540544986724854,
|
| 537 |
+
"eval_runtime": 159.9431,
|
| 538 |
+
"eval_samples_per_second": 70.85,
|
| 539 |
+
"eval_steps_per_second": 17.713,
|
| 540 |
+
"step": 38000
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 6.12,
|
| 544 |
+
"learning_rate": 3.1501318116594924e-05,
|
| 545 |
+
"loss": 2.7548,
|
| 546 |
+
"step": 39000
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 6.12,
|
| 550 |
+
"eval_loss": 3.068983554840088,
|
| 551 |
+
"eval_runtime": 157.2439,
|
| 552 |
+
"eval_samples_per_second": 72.066,
|
| 553 |
+
"eval_steps_per_second": 18.017,
|
| 554 |
+
"step": 39000
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 6.27,
|
| 558 |
+
"learning_rate": 3.094515077696578e-05,
|
| 559 |
+
"loss": 2.7369,
|
| 560 |
+
"step": 40000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 6.27,
|
| 564 |
+
"eval_loss": 3.067845344543457,
|
| 565 |
+
"eval_runtime": 151.1866,
|
| 566 |
+
"eval_samples_per_second": 74.954,
|
| 567 |
+
"eval_steps_per_second": 18.738,
|
| 568 |
+
"step": 40000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 6.43,
|
| 572 |
+
"learning_rate": 3.0388983437336626e-05,
|
| 573 |
+
"loss": 2.7471,
|
| 574 |
+
"step": 41000
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 6.43,
|
| 578 |
+
"eval_loss": 3.063314914703369,
|
| 579 |
+
"eval_runtime": 150.8738,
|
| 580 |
+
"eval_samples_per_second": 75.109,
|
| 581 |
+
"eval_steps_per_second": 18.777,
|
| 582 |
+
"step": 41000
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 6.59,
|
| 586 |
+
"learning_rate": 2.9832816097707477e-05,
|
| 587 |
+
"loss": 2.7576,
|
| 588 |
+
"step": 42000
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 6.59,
|
| 592 |
+
"eval_loss": 3.0629308223724365,
|
| 593 |
+
"eval_runtime": 170.5929,
|
| 594 |
+
"eval_samples_per_second": 66.427,
|
| 595 |
+
"eval_steps_per_second": 16.607,
|
| 596 |
+
"step": 42000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 6.74,
|
| 600 |
+
"learning_rate": 2.9276648758078335e-05,
|
| 601 |
+
"loss": 2.7566,
|
| 602 |
+
"step": 43000
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 6.74,
|
| 606 |
+
"eval_loss": 3.0592966079711914,
|
| 607 |
+
"eval_runtime": 152.4939,
|
| 608 |
+
"eval_samples_per_second": 74.311,
|
| 609 |
+
"eval_steps_per_second": 18.578,
|
| 610 |
+
"step": 43000
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 6.9,
|
| 614 |
+
"learning_rate": 2.8720481418449186e-05,
|
| 615 |
+
"loss": 2.7642,
|
| 616 |
+
"step": 44000
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 6.9,
|
| 620 |
+
"eval_loss": 3.055969715118408,
|
| 621 |
+
"eval_runtime": 152.0719,
|
| 622 |
+
"eval_samples_per_second": 74.517,
|
| 623 |
+
"eval_steps_per_second": 18.629,
|
| 624 |
+
"step": 44000
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 7.06,
|
| 628 |
+
"learning_rate": 2.8164314078820037e-05,
|
| 629 |
+
"loss": 2.7268,
|
| 630 |
+
"step": 45000
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 7.06,
|
| 634 |
+
"eval_loss": 3.0751819610595703,
|
| 635 |
+
"eval_runtime": 150.8723,
|
| 636 |
+
"eval_samples_per_second": 75.11,
|
| 637 |
+
"eval_steps_per_second": 18.777,
|
| 638 |
+
"step": 45000
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 7.21,
|
| 642 |
+
"learning_rate": 2.7608146739190888e-05,
|
| 643 |
+
"loss": 2.6778,
|
| 644 |
+
"step": 46000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 7.21,
|
| 648 |
+
"eval_loss": 3.0745816230773926,
|
| 649 |
+
"eval_runtime": 150.773,
|
| 650 |
+
"eval_samples_per_second": 75.159,
|
| 651 |
+
"eval_steps_per_second": 18.79,
|
| 652 |
+
"step": 46000
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 7.37,
|
| 656 |
+
"learning_rate": 2.705197939956174e-05,
|
| 657 |
+
"loss": 2.6895,
|
| 658 |
+
"step": 47000
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 7.37,
|
| 662 |
+
"eval_loss": 3.071889877319336,
|
| 663 |
+
"eval_runtime": 151.4074,
|
| 664 |
+
"eval_samples_per_second": 74.844,
|
| 665 |
+
"eval_steps_per_second": 18.711,
|
| 666 |
+
"step": 47000
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 7.53,
|
| 670 |
+
"learning_rate": 2.6495812059932596e-05,
|
| 671 |
+
"loss": 2.6908,
|
| 672 |
+
"step": 48000
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 7.53,
|
| 676 |
+
"eval_loss": 3.0682897567749023,
|
| 677 |
+
"eval_runtime": 150.9084,
|
| 678 |
+
"eval_samples_per_second": 75.092,
|
| 679 |
+
"eval_steps_per_second": 18.773,
|
| 680 |
+
"step": 48000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 7.69,
|
| 684 |
+
"learning_rate": 2.5939644720303447e-05,
|
| 685 |
+
"loss": 2.6985,
|
| 686 |
+
"step": 49000
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 7.69,
|
| 690 |
+
"eval_loss": 3.06658935546875,
|
| 691 |
+
"eval_runtime": 151.6999,
|
| 692 |
+
"eval_samples_per_second": 74.7,
|
| 693 |
+
"eval_steps_per_second": 18.675,
|
| 694 |
+
"step": 49000
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 7.84,
|
| 698 |
+
"learning_rate": 2.5383477380674298e-05,
|
| 699 |
+
"loss": 2.6969,
|
| 700 |
+
"step": 50000
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 7.84,
|
| 704 |
+
"eval_loss": 3.0591042041778564,
|
| 705 |
+
"eval_runtime": 161.1961,
|
| 706 |
+
"eval_samples_per_second": 70.299,
|
| 707 |
+
"eval_steps_per_second": 17.575,
|
| 708 |
+
"step": 50000
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 8.0,
|
| 712 |
+
"learning_rate": 2.4827310041045153e-05,
|
| 713 |
+
"loss": 2.7043,
|
| 714 |
+
"step": 51000
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 8.0,
|
| 718 |
+
"eval_loss": 3.0611181259155273,
|
| 719 |
+
"eval_runtime": 152.3504,
|
| 720 |
+
"eval_samples_per_second": 74.381,
|
| 721 |
+
"eval_steps_per_second": 18.595,
|
| 722 |
+
"step": 51000
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 8.16,
|
| 726 |
+
"learning_rate": 2.4271142701416004e-05,
|
| 727 |
+
"loss": 2.6225,
|
| 728 |
+
"step": 52000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 8.16,
|
| 732 |
+
"eval_loss": 3.080932378768921,
|
| 733 |
+
"eval_runtime": 150.5999,
|
| 734 |
+
"eval_samples_per_second": 75.246,
|
| 735 |
+
"eval_steps_per_second": 18.811,
|
| 736 |
+
"step": 52000
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 8.31,
|
| 740 |
+
"learning_rate": 2.3714975361786858e-05,
|
| 741 |
+
"loss": 2.636,
|
| 742 |
+
"step": 53000
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 8.31,
|
| 746 |
+
"eval_loss": 3.0787675380706787,
|
| 747 |
+
"eval_runtime": 152.1353,
|
| 748 |
+
"eval_samples_per_second": 74.486,
|
| 749 |
+
"eval_steps_per_second": 18.622,
|
| 750 |
+
"step": 53000
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 8.47,
|
| 754 |
+
"learning_rate": 2.315880802215771e-05,
|
| 755 |
+
"loss": 2.6379,
|
| 756 |
+
"step": 54000
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 8.47,
|
| 760 |
+
"eval_loss": 3.0813567638397217,
|
| 761 |
+
"eval_runtime": 150.7408,
|
| 762 |
+
"eval_samples_per_second": 75.175,
|
| 763 |
+
"eval_steps_per_second": 18.794,
|
| 764 |
+
"step": 54000
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 8.63,
|
| 768 |
+
"learning_rate": 2.260264068252856e-05,
|
| 769 |
+
"loss": 2.6423,
|
| 770 |
+
"step": 55000
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 8.63,
|
| 774 |
+
"eval_loss": 3.0757715702056885,
|
| 775 |
+
"eval_runtime": 151.7054,
|
| 776 |
+
"eval_samples_per_second": 74.697,
|
| 777 |
+
"eval_steps_per_second": 18.674,
|
| 778 |
+
"step": 55000
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 8.78,
|
| 782 |
+
"learning_rate": 2.2046473342899414e-05,
|
| 783 |
+
"loss": 2.6417,
|
| 784 |
+
"step": 56000
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 8.78,
|
| 788 |
+
"eval_loss": 3.074010133743286,
|
| 789 |
+
"eval_runtime": 151.6069,
|
| 790 |
+
"eval_samples_per_second": 74.746,
|
| 791 |
+
"eval_steps_per_second": 18.686,
|
| 792 |
+
"step": 56000
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 8.94,
|
| 796 |
+
"learning_rate": 2.1490306003270265e-05,
|
| 797 |
+
"loss": 2.6507,
|
| 798 |
+
"step": 57000
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 8.94,
|
| 802 |
+
"eval_loss": 3.07344388961792,
|
| 803 |
+
"eval_runtime": 158.2388,
|
| 804 |
+
"eval_samples_per_second": 71.613,
|
| 805 |
+
"eval_steps_per_second": 17.903,
|
| 806 |
+
"step": 57000
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 9.1,
|
| 810 |
+
"learning_rate": 2.0934138663641116e-05,
|
| 811 |
+
"loss": 2.6058,
|
| 812 |
+
"step": 58000
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 9.1,
|
| 816 |
+
"eval_loss": 3.086090087890625,
|
| 817 |
+
"eval_runtime": 151.6749,
|
| 818 |
+
"eval_samples_per_second": 74.712,
|
| 819 |
+
"eval_steps_per_second": 18.678,
|
| 820 |
+
"step": 58000
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 9.25,
|
| 824 |
+
"learning_rate": 2.0377971324011967e-05,
|
| 825 |
+
"loss": 2.5833,
|
| 826 |
+
"step": 59000
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 9.25,
|
| 830 |
+
"eval_loss": 3.086378812789917,
|
| 831 |
+
"eval_runtime": 150.5584,
|
| 832 |
+
"eval_samples_per_second": 75.266,
|
| 833 |
+
"eval_steps_per_second": 18.817,
|
| 834 |
+
"step": 59000
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 9.41,
|
| 838 |
+
"learning_rate": 1.982180398438282e-05,
|
| 839 |
+
"loss": 2.5864,
|
| 840 |
+
"step": 60000
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 9.41,
|
| 844 |
+
"eval_loss": 3.081770896911621,
|
| 845 |
+
"eval_runtime": 152.7908,
|
| 846 |
+
"eval_samples_per_second": 74.167,
|
| 847 |
+
"eval_steps_per_second": 18.542,
|
| 848 |
+
"step": 60000
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 9.57,
|
| 852 |
+
"learning_rate": 1.9265636644753672e-05,
|
| 853 |
+
"loss": 2.5952,
|
| 854 |
+
"step": 61000
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 9.57,
|
| 858 |
+
"eval_loss": 3.0846848487854004,
|
| 859 |
+
"eval_runtime": 158.7675,
|
| 860 |
+
"eval_samples_per_second": 71.375,
|
| 861 |
+
"eval_steps_per_second": 17.844,
|
| 862 |
+
"step": 61000
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 9.72,
|
| 866 |
+
"learning_rate": 1.8709469305124527e-05,
|
| 867 |
+
"loss": 2.6003,
|
| 868 |
+
"step": 62000
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 9.72,
|
| 872 |
+
"eval_loss": 3.0796427726745605,
|
| 873 |
+
"eval_runtime": 151.7749,
|
| 874 |
+
"eval_samples_per_second": 74.663,
|
| 875 |
+
"eval_steps_per_second": 18.666,
|
| 876 |
+
"step": 62000
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 9.88,
|
| 880 |
+
"learning_rate": 1.8153301965495378e-05,
|
| 881 |
+
"loss": 2.6024,
|
| 882 |
+
"step": 63000
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 9.88,
|
| 886 |
+
"eval_loss": 3.076544761657715,
|
| 887 |
+
"eval_runtime": 150.8625,
|
| 888 |
+
"eval_samples_per_second": 75.115,
|
| 889 |
+
"eval_steps_per_second": 18.779,
|
| 890 |
+
"step": 63000
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 10.04,
|
| 894 |
+
"learning_rate": 1.7597134625866232e-05,
|
| 895 |
+
"loss": 2.5883,
|
| 896 |
+
"step": 64000
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 10.04,
|
| 900 |
+
"eval_loss": 3.0901451110839844,
|
| 901 |
+
"eval_runtime": 150.7672,
|
| 902 |
+
"eval_samples_per_second": 75.162,
|
| 903 |
+
"eval_steps_per_second": 18.791,
|
| 904 |
+
"step": 64000
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 10.19,
|
| 908 |
+
"learning_rate": 1.7040967286237083e-05,
|
| 909 |
+
"loss": 2.5393,
|
| 910 |
+
"step": 65000
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 10.19,
|
| 914 |
+
"eval_loss": 3.0962793827056885,
|
| 915 |
+
"eval_runtime": 158.5186,
|
| 916 |
+
"eval_samples_per_second": 71.487,
|
| 917 |
+
"eval_steps_per_second": 17.872,
|
| 918 |
+
"step": 65000
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 10.35,
|
| 922 |
+
"learning_rate": 1.6484799946607937e-05,
|
| 923 |
+
"loss": 2.5485,
|
| 924 |
+
"step": 66000
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 10.35,
|
| 928 |
+
"eval_loss": 3.0939271450042725,
|
| 929 |
+
"eval_runtime": 150.6091,
|
| 930 |
+
"eval_samples_per_second": 75.241,
|
| 931 |
+
"eval_steps_per_second": 18.81,
|
| 932 |
+
"step": 66000
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 10.51,
|
| 936 |
+
"learning_rate": 1.5928632606978788e-05,
|
| 937 |
+
"loss": 2.5496,
|
| 938 |
+
"step": 67000
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 10.51,
|
| 942 |
+
"eval_loss": 3.092724084854126,
|
| 943 |
+
"eval_runtime": 151.4272,
|
| 944 |
+
"eval_samples_per_second": 74.835,
|
| 945 |
+
"eval_steps_per_second": 18.709,
|
| 946 |
+
"step": 67000
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 10.66,
|
| 950 |
+
"learning_rate": 1.5372465267349643e-05,
|
| 951 |
+
"loss": 2.5577,
|
| 952 |
+
"step": 68000
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 10.66,
|
| 956 |
+
"eval_loss": 3.0966575145721436,
|
| 957 |
+
"eval_runtime": 152.0136,
|
| 958 |
+
"eval_samples_per_second": 74.546,
|
| 959 |
+
"eval_steps_per_second": 18.636,
|
| 960 |
+
"step": 68000
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 10.82,
|
| 964 |
+
"learning_rate": 1.4816297927720494e-05,
|
| 965 |
+
"loss": 2.5598,
|
| 966 |
+
"step": 69000
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 10.82,
|
| 970 |
+
"eval_loss": 3.091947078704834,
|
| 971 |
+
"eval_runtime": 150.5612,
|
| 972 |
+
"eval_samples_per_second": 75.265,
|
| 973 |
+
"eval_steps_per_second": 18.816,
|
| 974 |
+
"step": 69000
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 10.98,
|
| 978 |
+
"learning_rate": 1.4260130588091345e-05,
|
| 979 |
+
"loss": 2.5623,
|
| 980 |
+
"step": 70000
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 10.98,
|
| 984 |
+
"eval_loss": 3.090240955352783,
|
| 985 |
+
"eval_runtime": 151.6176,
|
| 986 |
+
"eval_samples_per_second": 74.741,
|
| 987 |
+
"eval_steps_per_second": 18.685,
|
| 988 |
+
"step": 70000
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 11.14,
|
| 992 |
+
"learning_rate": 1.3703963248462199e-05,
|
| 993 |
+
"loss": 2.5138,
|
| 994 |
+
"step": 71000
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 11.14,
|
| 998 |
+
"eval_loss": 3.103158473968506,
|
| 999 |
+
"eval_runtime": 150.096,
|
| 1000 |
+
"eval_samples_per_second": 75.498,
|
| 1001 |
+
"eval_steps_per_second": 18.875,
|
| 1002 |
+
"step": 71000
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 11.29,
|
| 1006 |
+
"learning_rate": 1.314779590883305e-05,
|
| 1007 |
+
"loss": 2.5142,
|
| 1008 |
+
"step": 72000
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 11.29,
|
| 1012 |
+
"eval_loss": 3.1014111042022705,
|
| 1013 |
+
"eval_runtime": 151.6463,
|
| 1014 |
+
"eval_samples_per_second": 74.727,
|
| 1015 |
+
"eval_steps_per_second": 18.682,
|
| 1016 |
+
"step": 72000
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 11.45,
|
| 1020 |
+
"learning_rate": 1.2591628569203902e-05,
|
| 1021 |
+
"loss": 2.514,
|
| 1022 |
+
"step": 73000
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 11.45,
|
| 1026 |
+
"eval_loss": 3.1006739139556885,
|
| 1027 |
+
"eval_runtime": 158.2805,
|
| 1028 |
+
"eval_samples_per_second": 71.594,
|
| 1029 |
+
"eval_steps_per_second": 17.899,
|
| 1030 |
+
"step": 73000
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 11.61,
|
| 1034 |
+
"learning_rate": 1.2035461229574755e-05,
|
| 1035 |
+
"loss": 2.5206,
|
| 1036 |
+
"step": 74000
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 11.61,
|
| 1040 |
+
"eval_loss": 3.1010029315948486,
|
| 1041 |
+
"eval_runtime": 150.3118,
|
| 1042 |
+
"eval_samples_per_second": 75.39,
|
| 1043 |
+
"eval_steps_per_second": 18.847,
|
| 1044 |
+
"step": 74000
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 11.76,
|
| 1048 |
+
"learning_rate": 1.1479293889945606e-05,
|
| 1049 |
+
"loss": 2.52,
|
| 1050 |
+
"step": 75000
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 11.76,
|
| 1054 |
+
"eval_loss": 3.098405361175537,
|
| 1055 |
+
"eval_runtime": 156.5194,
|
| 1056 |
+
"eval_samples_per_second": 72.4,
|
| 1057 |
+
"eval_steps_per_second": 18.1,
|
| 1058 |
+
"step": 75000
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 11.92,
|
| 1062 |
+
"learning_rate": 1.0923126550316459e-05,
|
| 1063 |
+
"loss": 2.5204,
|
| 1064 |
+
"step": 76000
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 11.92,
|
| 1068 |
+
"eval_loss": 3.0984325408935547,
|
| 1069 |
+
"eval_runtime": 151.2164,
|
| 1070 |
+
"eval_samples_per_second": 74.939,
|
| 1071 |
+
"eval_steps_per_second": 18.735,
|
| 1072 |
+
"step": 76000
|
| 1073 |
+
}
|
| 1074 |
+
],
|
| 1075 |
+
"max_steps": 95640,
|
| 1076 |
+
"num_train_epochs": 15,
|
| 1077 |
+
"total_flos": 1.1223588676956365e+18,
|
| 1078 |
+
"trial_name": null,
|
| 1079 |
+
"trial_params": null
|
| 1080 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6add11d31386a3b4a153ab52e630b6d43be42e2d14fedb249c32f294570a4203
|
| 3 |
+
size 3183
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|