PaulDrm
commited on
Commit
•
9d26fad
1
Parent(s):
a5a4154
first commit model
Browse files- config.json +27 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +1096 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "roberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "roberta",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.13.0.dev0",
|
| 24 |
+
"type_vocab_size": 1,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 50265
|
| 27 |
+
}
|
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 sha256:1d13e896a4176b834de04ead67ac56f152ef86c826e79e6cc214457c9853869d
|
| 3 |
+
size 997696473
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f791190f60ceb242946db533b01262507c89022f36eb3746e39c9ab65e60c9d
|
| 3 |
+
size 498875371
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e49c7fbb73c8f0a1ba658bbde48e5c945b75819c14ba504d0242181057af6aa8
|
| 3 |
+
size 17563
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52d0c776f9430e2857f421df871588edf488262f8e998f8a9e39cccc73085f1c
|
| 3 |
+
size 623
|
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>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1096 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 35.026963262554766,
|
| 5 |
+
"global_step": 12960,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.32,
|
| 12 |
+
"learning_rate": 8e-05,
|
| 13 |
+
"loss": 1.9241,
|
| 14 |
+
"step": 120
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.65,
|
| 18 |
+
"learning_rate": 0.00016,
|
| 19 |
+
"loss": 1.8026,
|
| 20 |
+
"step": 240
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.65,
|
| 24 |
+
"eval_loss": 1.7006735801696777,
|
| 25 |
+
"eval_runtime": 120.5725,
|
| 26 |
+
"eval_samples_per_second": 46.437,
|
| 27 |
+
"eval_steps_per_second": 0.73,
|
| 28 |
+
"step": 240
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.97,
|
| 32 |
+
"learning_rate": 0.0002,
|
| 33 |
+
"loss": 1.7588,
|
| 34 |
+
"step": 360
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 1.3,
|
| 38 |
+
"learning_rate": 0.0002,
|
| 39 |
+
"loss": 1.7242,
|
| 40 |
+
"step": 480
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 1.3,
|
| 44 |
+
"eval_loss": 1.6368365287780762,
|
| 45 |
+
"eval_runtime": 123.5326,
|
| 46 |
+
"eval_samples_per_second": 45.324,
|
| 47 |
+
"eval_steps_per_second": 0.712,
|
| 48 |
+
"step": 480
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 1.62,
|
| 52 |
+
"learning_rate": 0.0002,
|
| 53 |
+
"loss": 1.6797,
|
| 54 |
+
"step": 600
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.94,
|
| 58 |
+
"learning_rate": 0.0002,
|
| 59 |
+
"loss": 1.6544,
|
| 60 |
+
"step": 720
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.94,
|
| 64 |
+
"eval_loss": 1.589858889579773,
|
| 65 |
+
"eval_runtime": 121.9204,
|
| 66 |
+
"eval_samples_per_second": 45.923,
|
| 67 |
+
"eval_steps_per_second": 0.722,
|
| 68 |
+
"step": 720
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 2.27,
|
| 72 |
+
"learning_rate": 0.0002,
|
| 73 |
+
"loss": 1.639,
|
| 74 |
+
"step": 840
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.59,
|
| 78 |
+
"learning_rate": 0.0002,
|
| 79 |
+
"loss": 1.6103,
|
| 80 |
+
"step": 960
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 2.59,
|
| 84 |
+
"eval_loss": 1.559193730354309,
|
| 85 |
+
"eval_runtime": 118.3836,
|
| 86 |
+
"eval_samples_per_second": 47.295,
|
| 87 |
+
"eval_steps_per_second": 0.743,
|
| 88 |
+
"step": 960
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 2.92,
|
| 92 |
+
"learning_rate": 0.0002,
|
| 93 |
+
"loss": 1.5982,
|
| 94 |
+
"step": 1080
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 3.24,
|
| 98 |
+
"learning_rate": 0.0002,
|
| 99 |
+
"loss": 1.5858,
|
| 100 |
+
"step": 1200
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 3.24,
|
| 104 |
+
"eval_loss": 1.5362491607666016,
|
| 105 |
+
"eval_runtime": 123.4422,
|
| 106 |
+
"eval_samples_per_second": 45.357,
|
| 107 |
+
"eval_steps_per_second": 0.713,
|
| 108 |
+
"step": 1200
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 3.57,
|
| 112 |
+
"learning_rate": 0.0002,
|
| 113 |
+
"loss": 1.5684,
|
| 114 |
+
"step": 1320
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 3.89,
|
| 118 |
+
"learning_rate": 0.0002,
|
| 119 |
+
"loss": 1.5566,
|
| 120 |
+
"step": 1440
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 3.89,
|
| 124 |
+
"eval_loss": 1.51528799533844,
|
| 125 |
+
"eval_runtime": 120.2858,
|
| 126 |
+
"eval_samples_per_second": 46.547,
|
| 127 |
+
"eval_steps_per_second": 0.732,
|
| 128 |
+
"step": 1440
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 4.22,
|
| 132 |
+
"learning_rate": 0.0002,
|
| 133 |
+
"loss": 1.5593,
|
| 134 |
+
"step": 1560
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 4.54,
|
| 138 |
+
"learning_rate": 0.0002,
|
| 139 |
+
"loss": 1.5322,
|
| 140 |
+
"step": 1680
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 4.54,
|
| 144 |
+
"eval_loss": 1.5114836692810059,
|
| 145 |
+
"eval_runtime": 117.8482,
|
| 146 |
+
"eval_samples_per_second": 47.51,
|
| 147 |
+
"eval_steps_per_second": 0.747,
|
| 148 |
+
"step": 1680
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 4.86,
|
| 152 |
+
"learning_rate": 0.0002,
|
| 153 |
+
"loss": 1.5285,
|
| 154 |
+
"step": 1800
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 5.19,
|
| 158 |
+
"learning_rate": 0.0002,
|
| 159 |
+
"loss": 1.5359,
|
| 160 |
+
"step": 1920
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 5.19,
|
| 164 |
+
"eval_loss": 1.48625910282135,
|
| 165 |
+
"eval_runtime": 123.7493,
|
| 166 |
+
"eval_samples_per_second": 45.245,
|
| 167 |
+
"eval_steps_per_second": 0.711,
|
| 168 |
+
"step": 1920
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 5.51,
|
| 172 |
+
"learning_rate": 0.0002,
|
| 173 |
+
"loss": 1.5207,
|
| 174 |
+
"step": 2040
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 5.84,
|
| 178 |
+
"learning_rate": 0.0002,
|
| 179 |
+
"loss": 1.5079,
|
| 180 |
+
"step": 2160
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 5.84,
|
| 184 |
+
"eval_loss": 1.4822603464126587,
|
| 185 |
+
"eval_runtime": 119.2091,
|
| 186 |
+
"eval_samples_per_second": 46.968,
|
| 187 |
+
"eval_steps_per_second": 0.738,
|
| 188 |
+
"step": 2160
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 6.16,
|
| 192 |
+
"learning_rate": 0.0002,
|
| 193 |
+
"loss": 1.51,
|
| 194 |
+
"step": 2280
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 6.49,
|
| 198 |
+
"learning_rate": 0.0002,
|
| 199 |
+
"loss": 1.4909,
|
| 200 |
+
"step": 2400
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 6.49,
|
| 204 |
+
"eval_loss": 1.4646539688110352,
|
| 205 |
+
"eval_runtime": 122.8427,
|
| 206 |
+
"eval_samples_per_second": 45.579,
|
| 207 |
+
"eval_steps_per_second": 0.716,
|
| 208 |
+
"step": 2400
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 6.81,
|
| 212 |
+
"learning_rate": 0.0002,
|
| 213 |
+
"loss": 1.4869,
|
| 214 |
+
"step": 2520
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 7.13,
|
| 218 |
+
"learning_rate": 0.0002,
|
| 219 |
+
"loss": 1.4894,
|
| 220 |
+
"step": 2640
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 7.13,
|
| 224 |
+
"eval_loss": 1.4567737579345703,
|
| 225 |
+
"eval_runtime": 112.4698,
|
| 226 |
+
"eval_samples_per_second": 49.782,
|
| 227 |
+
"eval_steps_per_second": 0.782,
|
| 228 |
+
"step": 2640
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 7.46,
|
| 232 |
+
"learning_rate": 0.0002,
|
| 233 |
+
"loss": 1.4705,
|
| 234 |
+
"step": 2760
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 7.78,
|
| 238 |
+
"learning_rate": 0.0002,
|
| 239 |
+
"loss": 1.469,
|
| 240 |
+
"step": 2880
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 7.78,
|
| 244 |
+
"eval_loss": 1.447322130203247,
|
| 245 |
+
"eval_runtime": 124.434,
|
| 246 |
+
"eval_samples_per_second": 44.996,
|
| 247 |
+
"eval_steps_per_second": 0.707,
|
| 248 |
+
"step": 2880
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 8.11,
|
| 252 |
+
"learning_rate": 0.0002,
|
| 253 |
+
"loss": 1.4716,
|
| 254 |
+
"step": 3000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 8.43,
|
| 258 |
+
"learning_rate": 0.0002,
|
| 259 |
+
"loss": 1.4525,
|
| 260 |
+
"step": 3120
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 8.43,
|
| 264 |
+
"eval_loss": 1.4480490684509277,
|
| 265 |
+
"eval_runtime": 120.9825,
|
| 266 |
+
"eval_samples_per_second": 46.279,
|
| 267 |
+
"eval_steps_per_second": 0.727,
|
| 268 |
+
"step": 3120
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 8.75,
|
| 272 |
+
"learning_rate": 0.0002,
|
| 273 |
+
"loss": 1.452,
|
| 274 |
+
"step": 3240
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 9.08,
|
| 278 |
+
"learning_rate": 0.0002,
|
| 279 |
+
"loss": 1.4552,
|
| 280 |
+
"step": 3360
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 9.08,
|
| 284 |
+
"eval_loss": 1.4297771453857422,
|
| 285 |
+
"eval_runtime": 119.4349,
|
| 286 |
+
"eval_samples_per_second": 46.879,
|
| 287 |
+
"eval_steps_per_second": 0.737,
|
| 288 |
+
"step": 3360
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 9.4,
|
| 292 |
+
"learning_rate": 0.0002,
|
| 293 |
+
"loss": 1.4369,
|
| 294 |
+
"step": 3480
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 9.73,
|
| 298 |
+
"learning_rate": 0.0002,
|
| 299 |
+
"loss": 1.4357,
|
| 300 |
+
"step": 3600
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 9.73,
|
| 304 |
+
"eval_loss": 1.4253787994384766,
|
| 305 |
+
"eval_runtime": 123.7286,
|
| 306 |
+
"eval_samples_per_second": 45.252,
|
| 307 |
+
"eval_steps_per_second": 0.711,
|
| 308 |
+
"step": 3600
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 10.05,
|
| 312 |
+
"learning_rate": 0.0002,
|
| 313 |
+
"loss": 1.4449,
|
| 314 |
+
"step": 3720
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 10.38,
|
| 318 |
+
"learning_rate": 0.0002,
|
| 319 |
+
"loss": 1.4245,
|
| 320 |
+
"step": 3840
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 10.38,
|
| 324 |
+
"eval_loss": 1.419893741607666,
|
| 325 |
+
"eval_runtime": 122.5962,
|
| 326 |
+
"eval_samples_per_second": 45.67,
|
| 327 |
+
"eval_steps_per_second": 0.718,
|
| 328 |
+
"step": 3840
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 10.7,
|
| 332 |
+
"learning_rate": 0.0002,
|
| 333 |
+
"loss": 1.4259,
|
| 334 |
+
"step": 3960
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 11.03,
|
| 338 |
+
"learning_rate": 0.0002,
|
| 339 |
+
"loss": 1.4317,
|
| 340 |
+
"step": 4080
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 11.03,
|
| 344 |
+
"eval_loss": 1.4151264429092407,
|
| 345 |
+
"eval_runtime": 120.6018,
|
| 346 |
+
"eval_samples_per_second": 46.426,
|
| 347 |
+
"eval_steps_per_second": 0.73,
|
| 348 |
+
"step": 4080
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 11.35,
|
| 352 |
+
"learning_rate": 0.0002,
|
| 353 |
+
"loss": 1.4133,
|
| 354 |
+
"step": 4200
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 11.67,
|
| 358 |
+
"learning_rate": 0.0002,
|
| 359 |
+
"loss": 1.4119,
|
| 360 |
+
"step": 4320
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 11.67,
|
| 364 |
+
"eval_loss": 1.4069455862045288,
|
| 365 |
+
"eval_runtime": 123.9031,
|
| 366 |
+
"eval_samples_per_second": 45.189,
|
| 367 |
+
"eval_steps_per_second": 0.71,
|
| 368 |
+
"step": 4320
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 12.0,
|
| 372 |
+
"learning_rate": 0.0002,
|
| 373 |
+
"loss": 1.4096,
|
| 374 |
+
"step": 4440
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 12.32,
|
| 378 |
+
"learning_rate": 0.0002,
|
| 379 |
+
"loss": 1.4086,
|
| 380 |
+
"step": 4560
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 12.32,
|
| 384 |
+
"eval_loss": 1.4099173545837402,
|
| 385 |
+
"eval_runtime": 121.1011,
|
| 386 |
+
"eval_samples_per_second": 46.234,
|
| 387 |
+
"eval_steps_per_second": 0.727,
|
| 388 |
+
"step": 4560
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 12.65,
|
| 392 |
+
"learning_rate": 0.0002,
|
| 393 |
+
"loss": 1.4031,
|
| 394 |
+
"step": 4680
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 12.97,
|
| 398 |
+
"learning_rate": 0.0002,
|
| 399 |
+
"loss": 1.401,
|
| 400 |
+
"step": 4800
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 12.97,
|
| 404 |
+
"eval_loss": 1.4046831130981445,
|
| 405 |
+
"eval_runtime": 121.8177,
|
| 406 |
+
"eval_samples_per_second": 45.962,
|
| 407 |
+
"eval_steps_per_second": 0.722,
|
| 408 |
+
"step": 4800
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 13.3,
|
| 412 |
+
"learning_rate": 0.0002,
|
| 413 |
+
"loss": 1.4031,
|
| 414 |
+
"step": 4920
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 13.62,
|
| 418 |
+
"learning_rate": 0.0002,
|
| 419 |
+
"loss": 1.394,
|
| 420 |
+
"step": 5040
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 13.62,
|
| 424 |
+
"eval_loss": 1.401537299156189,
|
| 425 |
+
"eval_runtime": 121.4356,
|
| 426 |
+
"eval_samples_per_second": 46.107,
|
| 427 |
+
"eval_steps_per_second": 0.725,
|
| 428 |
+
"step": 5040
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 13.94,
|
| 432 |
+
"learning_rate": 0.0002,
|
| 433 |
+
"loss": 1.3922,
|
| 434 |
+
"step": 5160
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 14.27,
|
| 438 |
+
"learning_rate": 0.0002,
|
| 439 |
+
"loss": 1.3945,
|
| 440 |
+
"step": 5280
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 14.27,
|
| 444 |
+
"eval_loss": 1.3918230533599854,
|
| 445 |
+
"eval_runtime": 119.2233,
|
| 446 |
+
"eval_samples_per_second": 46.962,
|
| 447 |
+
"eval_steps_per_second": 0.738,
|
| 448 |
+
"step": 5280
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 14.59,
|
| 452 |
+
"learning_rate": 0.0002,
|
| 453 |
+
"loss": 1.3836,
|
| 454 |
+
"step": 5400
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 14.92,
|
| 458 |
+
"learning_rate": 0.0002,
|
| 459 |
+
"loss": 1.3838,
|
| 460 |
+
"step": 5520
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 14.92,
|
| 464 |
+
"eval_loss": 1.385350227355957,
|
| 465 |
+
"eval_runtime": 113.4489,
|
| 466 |
+
"eval_samples_per_second": 49.353,
|
| 467 |
+
"eval_steps_per_second": 0.776,
|
| 468 |
+
"step": 5520
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 15.24,
|
| 472 |
+
"learning_rate": 0.0002,
|
| 473 |
+
"loss": 1.387,
|
| 474 |
+
"step": 5640
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 15.57,
|
| 478 |
+
"learning_rate": 0.0002,
|
| 479 |
+
"loss": 1.3722,
|
| 480 |
+
"step": 5760
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 15.57,
|
| 484 |
+
"eval_loss": 1.379088282585144,
|
| 485 |
+
"eval_runtime": 116.4932,
|
| 486 |
+
"eval_samples_per_second": 48.063,
|
| 487 |
+
"eval_steps_per_second": 0.755,
|
| 488 |
+
"step": 5760
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 15.89,
|
| 492 |
+
"learning_rate": 0.0002,
|
| 493 |
+
"loss": 1.3757,
|
| 494 |
+
"step": 5880
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 16.22,
|
| 498 |
+
"learning_rate": 0.0002,
|
| 499 |
+
"loss": 1.3775,
|
| 500 |
+
"step": 6000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 16.22,
|
| 504 |
+
"eval_loss": 1.384007453918457,
|
| 505 |
+
"eval_runtime": 115.8099,
|
| 506 |
+
"eval_samples_per_second": 48.346,
|
| 507 |
+
"eval_steps_per_second": 0.76,
|
| 508 |
+
"step": 6000
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 16.54,
|
| 512 |
+
"learning_rate": 0.0002,
|
| 513 |
+
"loss": 1.3683,
|
| 514 |
+
"step": 6120
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 16.86,
|
| 518 |
+
"learning_rate": 0.0002,
|
| 519 |
+
"loss": 1.3675,
|
| 520 |
+
"step": 6240
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 16.86,
|
| 524 |
+
"eval_loss": 1.3760778903961182,
|
| 525 |
+
"eval_runtime": 113.2638,
|
| 526 |
+
"eval_samples_per_second": 49.433,
|
| 527 |
+
"eval_steps_per_second": 0.777,
|
| 528 |
+
"step": 6240
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 17.19,
|
| 532 |
+
"learning_rate": 0.0002,
|
| 533 |
+
"loss": 1.375,
|
| 534 |
+
"step": 6360
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 17.51,
|
| 538 |
+
"learning_rate": 0.0002,
|
| 539 |
+
"loss": 1.358,
|
| 540 |
+
"step": 6480
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 17.51,
|
| 544 |
+
"eval_loss": 1.3729970455169678,
|
| 545 |
+
"eval_runtime": 119.1962,
|
| 546 |
+
"eval_samples_per_second": 46.973,
|
| 547 |
+
"eval_steps_per_second": 0.738,
|
| 548 |
+
"step": 6480
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 17.84,
|
| 552 |
+
"learning_rate": 0.0002,
|
| 553 |
+
"loss": 1.3617,
|
| 554 |
+
"step": 6600
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 18.16,
|
| 558 |
+
"learning_rate": 0.0002,
|
| 559 |
+
"loss": 1.3679,
|
| 560 |
+
"step": 6720
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 18.16,
|
| 564 |
+
"eval_loss": 1.3826600313186646,
|
| 565 |
+
"eval_runtime": 118.9849,
|
| 566 |
+
"eval_samples_per_second": 47.056,
|
| 567 |
+
"eval_steps_per_second": 0.74,
|
| 568 |
+
"step": 6720
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 18.49,
|
| 572 |
+
"learning_rate": 0.0002,
|
| 573 |
+
"loss": 1.3592,
|
| 574 |
+
"step": 6840
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 18.81,
|
| 578 |
+
"learning_rate": 0.0002,
|
| 579 |
+
"loss": 1.3602,
|
| 580 |
+
"step": 6960
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 18.81,
|
| 584 |
+
"eval_loss": 1.3659363985061646,
|
| 585 |
+
"eval_runtime": 120.7081,
|
| 586 |
+
"eval_samples_per_second": 46.385,
|
| 587 |
+
"eval_steps_per_second": 0.729,
|
| 588 |
+
"step": 6960
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 19.13,
|
| 592 |
+
"learning_rate": 0.0002,
|
| 593 |
+
"loss": 1.3633,
|
| 594 |
+
"step": 7080
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 19.46,
|
| 598 |
+
"learning_rate": 0.0002,
|
| 599 |
+
"loss": 1.3522,
|
| 600 |
+
"step": 7200
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 19.46,
|
| 604 |
+
"eval_loss": 1.372406244277954,
|
| 605 |
+
"eval_runtime": 113.6178,
|
| 606 |
+
"eval_samples_per_second": 49.279,
|
| 607 |
+
"eval_steps_per_second": 0.775,
|
| 608 |
+
"step": 7200
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 19.78,
|
| 612 |
+
"learning_rate": 0.0002,
|
| 613 |
+
"loss": 1.345,
|
| 614 |
+
"step": 7320
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 20.11,
|
| 618 |
+
"learning_rate": 0.0002,
|
| 619 |
+
"loss": 1.3555,
|
| 620 |
+
"step": 7440
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 20.11,
|
| 624 |
+
"eval_loss": 1.368371844291687,
|
| 625 |
+
"eval_runtime": 118.9369,
|
| 626 |
+
"eval_samples_per_second": 47.075,
|
| 627 |
+
"eval_steps_per_second": 0.74,
|
| 628 |
+
"step": 7440
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 20.43,
|
| 632 |
+
"learning_rate": 0.0002,
|
| 633 |
+
"loss": 1.3396,
|
| 634 |
+
"step": 7560
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 20.75,
|
| 638 |
+
"learning_rate": 0.0002,
|
| 639 |
+
"loss": 1.3536,
|
| 640 |
+
"step": 7680
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 20.75,
|
| 644 |
+
"eval_loss": 1.3611598014831543,
|
| 645 |
+
"eval_runtime": 119.3386,
|
| 646 |
+
"eval_samples_per_second": 46.917,
|
| 647 |
+
"eval_steps_per_second": 0.737,
|
| 648 |
+
"step": 7680
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 21.08,
|
| 652 |
+
"learning_rate": 0.0002,
|
| 653 |
+
"loss": 1.3506,
|
| 654 |
+
"step": 7800
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 21.4,
|
| 658 |
+
"learning_rate": 0.0002,
|
| 659 |
+
"loss": 1.3347,
|
| 660 |
+
"step": 7920
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 21.4,
|
| 664 |
+
"eval_loss": 1.3598804473876953,
|
| 665 |
+
"eval_runtime": 114.0961,
|
| 666 |
+
"eval_samples_per_second": 49.073,
|
| 667 |
+
"eval_steps_per_second": 0.771,
|
| 668 |
+
"step": 7920
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 21.73,
|
| 672 |
+
"learning_rate": 0.0002,
|
| 673 |
+
"loss": 1.338,
|
| 674 |
+
"step": 8040
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 22.05,
|
| 678 |
+
"learning_rate": 0.0002,
|
| 679 |
+
"loss": 1.3463,
|
| 680 |
+
"step": 8160
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 22.05,
|
| 684 |
+
"eval_loss": 1.3614617586135864,
|
| 685 |
+
"eval_runtime": 121.7757,
|
| 686 |
+
"eval_samples_per_second": 45.978,
|
| 687 |
+
"eval_steps_per_second": 0.723,
|
| 688 |
+
"step": 8160
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 22.38,
|
| 692 |
+
"learning_rate": 0.0002,
|
| 693 |
+
"loss": 1.3305,
|
| 694 |
+
"step": 8280
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 22.7,
|
| 698 |
+
"learning_rate": 0.0002,
|
| 699 |
+
"loss": 1.3296,
|
| 700 |
+
"step": 8400
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 22.7,
|
| 704 |
+
"eval_loss": 1.359055519104004,
|
| 705 |
+
"eval_runtime": 113.3148,
|
| 706 |
+
"eval_samples_per_second": 49.411,
|
| 707 |
+
"eval_steps_per_second": 0.777,
|
| 708 |
+
"step": 8400
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 23.03,
|
| 712 |
+
"learning_rate": 0.0002,
|
| 713 |
+
"loss": 1.344,
|
| 714 |
+
"step": 8520
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 23.35,
|
| 718 |
+
"learning_rate": 0.0002,
|
| 719 |
+
"loss": 1.3201,
|
| 720 |
+
"step": 8640
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 23.35,
|
| 724 |
+
"eval_loss": 1.358960509300232,
|
| 725 |
+
"eval_runtime": 122.2886,
|
| 726 |
+
"eval_samples_per_second": 45.785,
|
| 727 |
+
"eval_steps_per_second": 0.72,
|
| 728 |
+
"step": 8640
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 23.67,
|
| 732 |
+
"learning_rate": 0.0002,
|
| 733 |
+
"loss": 1.3302,
|
| 734 |
+
"step": 8760
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 24.0,
|
| 738 |
+
"learning_rate": 0.0002,
|
| 739 |
+
"loss": 1.3292,
|
| 740 |
+
"step": 8880
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 24.0,
|
| 744 |
+
"eval_loss": 1.3509206771850586,
|
| 745 |
+
"eval_runtime": 99.6058,
|
| 746 |
+
"eval_samples_per_second": 56.212,
|
| 747 |
+
"eval_steps_per_second": 0.883,
|
| 748 |
+
"step": 8880
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 24.32,
|
| 752 |
+
"learning_rate": 0.0002,
|
| 753 |
+
"loss": 1.3294,
|
| 754 |
+
"step": 9000
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 24.65,
|
| 758 |
+
"learning_rate": 0.0002,
|
| 759 |
+
"loss": 1.3207,
|
| 760 |
+
"step": 9120
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 24.65,
|
| 764 |
+
"eval_loss": 1.357851505279541,
|
| 765 |
+
"eval_runtime": 105.9073,
|
| 766 |
+
"eval_samples_per_second": 52.867,
|
| 767 |
+
"eval_steps_per_second": 0.831,
|
| 768 |
+
"step": 9120
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 24.97,
|
| 772 |
+
"learning_rate": 0.0002,
|
| 773 |
+
"loss": 1.3215,
|
| 774 |
+
"step": 9240
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 25.3,
|
| 778 |
+
"learning_rate": 0.0002,
|
| 779 |
+
"loss": 1.3231,
|
| 780 |
+
"step": 9360
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 25.3,
|
| 784 |
+
"eval_loss": 1.3393853902816772,
|
| 785 |
+
"eval_runtime": 99.7219,
|
| 786 |
+
"eval_samples_per_second": 56.146,
|
| 787 |
+
"eval_steps_per_second": 0.882,
|
| 788 |
+
"step": 9360
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 25.62,
|
| 792 |
+
"learning_rate": 0.0002,
|
| 793 |
+
"loss": 1.3121,
|
| 794 |
+
"step": 9480
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 25.94,
|
| 798 |
+
"learning_rate": 0.0002,
|
| 799 |
+
"loss": 1.3176,
|
| 800 |
+
"step": 9600
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 25.94,
|
| 804 |
+
"eval_loss": 1.3441215753555298,
|
| 805 |
+
"eval_runtime": 101.3937,
|
| 806 |
+
"eval_samples_per_second": 55.22,
|
| 807 |
+
"eval_steps_per_second": 0.868,
|
| 808 |
+
"step": 9600
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 26.27,
|
| 812 |
+
"learning_rate": 0.0002,
|
| 813 |
+
"loss": 1.3188,
|
| 814 |
+
"step": 9720
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 26.59,
|
| 818 |
+
"learning_rate": 0.0002,
|
| 819 |
+
"loss": 1.3103,
|
| 820 |
+
"step": 9840
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 26.59,
|
| 824 |
+
"eval_loss": 1.3429008722305298,
|
| 825 |
+
"eval_runtime": 100.8116,
|
| 826 |
+
"eval_samples_per_second": 55.539,
|
| 827 |
+
"eval_steps_per_second": 0.873,
|
| 828 |
+
"step": 9840
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 26.92,
|
| 832 |
+
"learning_rate": 0.0002,
|
| 833 |
+
"loss": 1.313,
|
| 834 |
+
"step": 9960
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 27.24,
|
| 838 |
+
"learning_rate": 0.0002,
|
| 839 |
+
"loss": 1.3156,
|
| 840 |
+
"step": 10080
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 27.24,
|
| 844 |
+
"eval_loss": 1.3400343656539917,
|
| 845 |
+
"eval_runtime": 98.2948,
|
| 846 |
+
"eval_samples_per_second": 56.961,
|
| 847 |
+
"eval_steps_per_second": 0.895,
|
| 848 |
+
"step": 10080
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 27.57,
|
| 852 |
+
"learning_rate": 0.0002,
|
| 853 |
+
"loss": 1.3064,
|
| 854 |
+
"step": 10200
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 27.89,
|
| 858 |
+
"learning_rate": 0.0002,
|
| 859 |
+
"loss": 1.306,
|
| 860 |
+
"step": 10320
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 27.89,
|
| 864 |
+
"eval_loss": 1.339460015296936,
|
| 865 |
+
"eval_runtime": 97.8707,
|
| 866 |
+
"eval_samples_per_second": 57.208,
|
| 867 |
+
"eval_steps_per_second": 0.899,
|
| 868 |
+
"step": 10320
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 28.22,
|
| 872 |
+
"learning_rate": 0.0002,
|
| 873 |
+
"loss": 1.3093,
|
| 874 |
+
"step": 10440
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 28.54,
|
| 878 |
+
"learning_rate": 0.0002,
|
| 879 |
+
"loss": 1.3026,
|
| 880 |
+
"step": 10560
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 28.54,
|
| 884 |
+
"eval_loss": 1.3380861282348633,
|
| 885 |
+
"eval_runtime": 99.7827,
|
| 886 |
+
"eval_samples_per_second": 56.112,
|
| 887 |
+
"eval_steps_per_second": 0.882,
|
| 888 |
+
"step": 10560
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 28.86,
|
| 892 |
+
"learning_rate": 0.0002,
|
| 893 |
+
"loss": 1.3014,
|
| 894 |
+
"step": 10680
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 29.19,
|
| 898 |
+
"learning_rate": 0.0002,
|
| 899 |
+
"loss": 1.3093,
|
| 900 |
+
"step": 10800
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 29.19,
|
| 904 |
+
"eval_loss": 1.335351824760437,
|
| 905 |
+
"eval_runtime": 99.7514,
|
| 906 |
+
"eval_samples_per_second": 56.13,
|
| 907 |
+
"eval_steps_per_second": 0.882,
|
| 908 |
+
"step": 10800
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 29.51,
|
| 912 |
+
"learning_rate": 0.0002,
|
| 913 |
+
"loss": 1.2954,
|
| 914 |
+
"step": 10920
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 29.84,
|
| 918 |
+
"learning_rate": 0.0002,
|
| 919 |
+
"loss": 1.2982,
|
| 920 |
+
"step": 11040
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 29.84,
|
| 924 |
+
"eval_loss": 1.33037269115448,
|
| 925 |
+
"eval_runtime": 111.392,
|
| 926 |
+
"eval_samples_per_second": 50.264,
|
| 927 |
+
"eval_steps_per_second": 0.79,
|
| 928 |
+
"step": 11040
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 30.16,
|
| 932 |
+
"learning_rate": 0.0002,
|
| 933 |
+
"loss": 1.3032,
|
| 934 |
+
"step": 11160
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 30.49,
|
| 938 |
+
"learning_rate": 0.0002,
|
| 939 |
+
"loss": 1.2927,
|
| 940 |
+
"step": 11280
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 30.49,
|
| 944 |
+
"eval_loss": 1.3423055410385132,
|
| 945 |
+
"eval_runtime": 110.815,
|
| 946 |
+
"eval_samples_per_second": 50.526,
|
| 947 |
+
"eval_steps_per_second": 0.794,
|
| 948 |
+
"step": 11280
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 30.81,
|
| 952 |
+
"learning_rate": 0.0002,
|
| 953 |
+
"loss": 1.2968,
|
| 954 |
+
"step": 11400
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 31.13,
|
| 958 |
+
"learning_rate": 0.0002,
|
| 959 |
+
"loss": 1.3003,
|
| 960 |
+
"step": 11520
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 31.13,
|
| 964 |
+
"eval_loss": 1.3345474004745483,
|
| 965 |
+
"eval_runtime": 100.6956,
|
| 966 |
+
"eval_samples_per_second": 55.603,
|
| 967 |
+
"eval_steps_per_second": 0.874,
|
| 968 |
+
"step": 11520
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 31.46,
|
| 972 |
+
"learning_rate": 0.0002,
|
| 973 |
+
"loss": 1.2865,
|
| 974 |
+
"step": 11640
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 31.78,
|
| 978 |
+
"learning_rate": 0.0002,
|
| 979 |
+
"loss": 1.2928,
|
| 980 |
+
"step": 11760
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 31.78,
|
| 984 |
+
"eval_loss": 1.337437629699707,
|
| 985 |
+
"eval_runtime": 97.2235,
|
| 986 |
+
"eval_samples_per_second": 57.589,
|
| 987 |
+
"eval_steps_per_second": 0.905,
|
| 988 |
+
"step": 11760
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 32.11,
|
| 992 |
+
"learning_rate": 0.0002,
|
| 993 |
+
"loss": 1.2981,
|
| 994 |
+
"step": 11880
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 32.43,
|
| 998 |
+
"learning_rate": 0.0002,
|
| 999 |
+
"loss": 1.2847,
|
| 1000 |
+
"step": 12000
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 32.43,
|
| 1004 |
+
"eval_loss": 1.3236644268035889,
|
| 1005 |
+
"eval_runtime": 97.4026,
|
| 1006 |
+
"eval_samples_per_second": 57.483,
|
| 1007 |
+
"eval_steps_per_second": 0.903,
|
| 1008 |
+
"step": 12000
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 32.75,
|
| 1012 |
+
"learning_rate": 0.0002,
|
| 1013 |
+
"loss": 1.2871,
|
| 1014 |
+
"step": 12120
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 33.08,
|
| 1018 |
+
"learning_rate": 0.0002,
|
| 1019 |
+
"loss": 1.2966,
|
| 1020 |
+
"step": 12240
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 33.08,
|
| 1024 |
+
"eval_loss": 1.332656741142273,
|
| 1025 |
+
"eval_runtime": 97.3643,
|
| 1026 |
+
"eval_samples_per_second": 57.506,
|
| 1027 |
+
"eval_steps_per_second": 0.904,
|
| 1028 |
+
"step": 12240
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 33.4,
|
| 1032 |
+
"learning_rate": 0.0002,
|
| 1033 |
+
"loss": 1.2789,
|
| 1034 |
+
"step": 12360
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 33.73,
|
| 1038 |
+
"learning_rate": 0.0002,
|
| 1039 |
+
"loss": 1.2829,
|
| 1040 |
+
"step": 12480
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 33.73,
|
| 1044 |
+
"eval_loss": 1.3252918720245361,
|
| 1045 |
+
"eval_runtime": 104.7279,
|
| 1046 |
+
"eval_samples_per_second": 53.462,
|
| 1047 |
+
"eval_steps_per_second": 0.84,
|
| 1048 |
+
"step": 12480
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 34.05,
|
| 1052 |
+
"learning_rate": 0.0002,
|
| 1053 |
+
"loss": 1.2926,
|
| 1054 |
+
"step": 12600
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 34.38,
|
| 1058 |
+
"learning_rate": 0.0002,
|
| 1059 |
+
"loss": 1.2756,
|
| 1060 |
+
"step": 12720
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 34.38,
|
| 1064 |
+
"eval_loss": 1.326663613319397,
|
| 1065 |
+
"eval_runtime": 98.2526,
|
| 1066 |
+
"eval_samples_per_second": 56.986,
|
| 1067 |
+
"eval_steps_per_second": 0.896,
|
| 1068 |
+
"step": 12720
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 34.7,
|
| 1072 |
+
"learning_rate": 0.0002,
|
| 1073 |
+
"loss": 1.2801,
|
| 1074 |
+
"step": 12840
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 35.03,
|
| 1078 |
+
"learning_rate": 0.0002,
|
| 1079 |
+
"loss": 1.2919,
|
| 1080 |
+
"step": 12960
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 35.03,
|
| 1084 |
+
"eval_loss": 1.3183717727661133,
|
| 1085 |
+
"eval_runtime": 99.1376,
|
| 1086 |
+
"eval_samples_per_second": 56.477,
|
| 1087 |
+
"eval_steps_per_second": 0.888,
|
| 1088 |
+
"step": 12960
|
| 1089 |
+
}
|
| 1090 |
+
],
|
| 1091 |
+
"max_steps": 14000,
|
| 1092 |
+
"num_train_epochs": 38,
|
| 1093 |
+
"total_flos": 1.7505797492048026e+18,
|
| 1094 |
+
"trial_name": null,
|
| 1095 |
+
"trial_params": null
|
| 1096 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f036c9bbb0eda92a44e02d76db6576bc9d95c2b29eb730aa7ceb1ee9e9f0b599
|
| 3 |
+
size 2991
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|