Commit
•
9d7bff3
1
Parent(s):
b78c388
First model version
Browse files- .DS_Store +0 -0
- config.json +31 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- requirements.txt +1 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +885 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.DS_Store
ADDED
|
Binary file (6.15 kB). View file
|
|
|
config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/deberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DebertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 3072,
|
| 12 |
+
"layer_norm_eps": 1e-07,
|
| 13 |
+
"max_position_embeddings": 512,
|
| 14 |
+
"max_relative_positions": -1,
|
| 15 |
+
"model_type": "deberta",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 12,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"pooler_dropout": 0,
|
| 20 |
+
"pooler_hidden_act": "gelu",
|
| 21 |
+
"pooler_hidden_size": 768,
|
| 22 |
+
"pos_att_type": [
|
| 23 |
+
"c2p",
|
| 24 |
+
"p2c"
|
| 25 |
+
],
|
| 26 |
+
"position_biased_input": false,
|
| 27 |
+
"relative_attention": true,
|
| 28 |
+
"transformers_version": "4.7.0.dev0",
|
| 29 |
+
"type_vocab_size": 0,
|
| 30 |
+
"vocab_size": 50265
|
| 31 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b34a7d65c3a3eb10ec013123d2845d0cc6d7a1ead9862309725baa8423b315e2
|
| 3 |
+
size 556866752
|
requirements.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
transformers
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "[UNK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "[PAD]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
|
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": {"content": "[UNK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "[PAD]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "do_lower_case": false, "vocab_type": "gpt2", "model_max_length": 512, "name_or_path": "microsoft/deberta-base"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,885 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7949723601341248,
|
| 3 |
+
"best_model_checkpoint": "/jmain02/home/J2AD002/jxm09/hrk35-jxm09/hatemoji_r7_data/output/hs_data--prior_rounds--r7--5/deberta123/checkpoint-46574",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 69861,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.02,
|
| 12 |
+
"learning_rate": 1.9856858619258244e-05,
|
| 13 |
+
"loss": 0.53,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.04,
|
| 18 |
+
"learning_rate": 1.9713717238516486e-05,
|
| 19 |
+
"loss": 0.308,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.06,
|
| 24 |
+
"learning_rate": 1.9570575857774725e-05,
|
| 25 |
+
"loss": 0.2211,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.09,
|
| 30 |
+
"learning_rate": 1.9427434477032967e-05,
|
| 31 |
+
"loss": 0.1787,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.11,
|
| 36 |
+
"learning_rate": 1.928429309629121e-05,
|
| 37 |
+
"loss": 0.1482,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.13,
|
| 42 |
+
"learning_rate": 1.914115171554945e-05,
|
| 43 |
+
"loss": 0.1392,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.15,
|
| 48 |
+
"learning_rate": 1.899801033480769e-05,
|
| 49 |
+
"loss": 0.1246,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.17,
|
| 54 |
+
"learning_rate": 1.8854868954065932e-05,
|
| 55 |
+
"loss": 0.1191,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.19,
|
| 60 |
+
"learning_rate": 1.8711727573324174e-05,
|
| 61 |
+
"loss": 0.115,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.21,
|
| 66 |
+
"learning_rate": 1.8568586192582416e-05,
|
| 67 |
+
"loss": 0.1038,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.24,
|
| 72 |
+
"learning_rate": 1.8425444811840655e-05,
|
| 73 |
+
"loss": 0.098,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.26,
|
| 78 |
+
"learning_rate": 1.8282303431098897e-05,
|
| 79 |
+
"loss": 0.1044,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.28,
|
| 84 |
+
"learning_rate": 1.813916205035714e-05,
|
| 85 |
+
"loss": 0.1011,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.3,
|
| 90 |
+
"learning_rate": 1.799602066961538e-05,
|
| 91 |
+
"loss": 0.0935,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.32,
|
| 96 |
+
"learning_rate": 1.785287928887362e-05,
|
| 97 |
+
"loss": 0.0926,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.34,
|
| 102 |
+
"learning_rate": 1.7709737908131862e-05,
|
| 103 |
+
"loss": 0.095,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.37,
|
| 108 |
+
"learning_rate": 1.7566596527390104e-05,
|
| 109 |
+
"loss": 0.0863,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.39,
|
| 114 |
+
"learning_rate": 1.7423455146648346e-05,
|
| 115 |
+
"loss": 0.0886,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.41,
|
| 120 |
+
"learning_rate": 1.7280313765906588e-05,
|
| 121 |
+
"loss": 0.0876,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.43,
|
| 126 |
+
"learning_rate": 1.713717238516483e-05,
|
| 127 |
+
"loss": 0.089,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.45,
|
| 132 |
+
"learning_rate": 1.699403100442307e-05,
|
| 133 |
+
"loss": 0.0871,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.47,
|
| 138 |
+
"learning_rate": 1.685088962368131e-05,
|
| 139 |
+
"loss": 0.0874,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.49,
|
| 144 |
+
"learning_rate": 1.6707748242939553e-05,
|
| 145 |
+
"loss": 0.0802,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.52,
|
| 150 |
+
"learning_rate": 1.6564606862197795e-05,
|
| 151 |
+
"loss": 0.0826,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.54,
|
| 156 |
+
"learning_rate": 1.6421465481456037e-05,
|
| 157 |
+
"loss": 0.08,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.56,
|
| 162 |
+
"learning_rate": 1.627832410071428e-05,
|
| 163 |
+
"loss": 0.081,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.58,
|
| 168 |
+
"learning_rate": 1.6135182719972518e-05,
|
| 169 |
+
"loss": 0.0798,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.6,
|
| 174 |
+
"learning_rate": 1.599204133923076e-05,
|
| 175 |
+
"loss": 0.0813,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.62,
|
| 180 |
+
"learning_rate": 1.5848899958489002e-05,
|
| 181 |
+
"loss": 0.0779,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.64,
|
| 186 |
+
"learning_rate": 1.5705758577747244e-05,
|
| 187 |
+
"loss": 0.0769,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.67,
|
| 192 |
+
"learning_rate": 1.5562617197005483e-05,
|
| 193 |
+
"loss": 0.0817,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.69,
|
| 198 |
+
"learning_rate": 1.5419475816263725e-05,
|
| 199 |
+
"loss": 0.0765,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.71,
|
| 204 |
+
"learning_rate": 1.5276334435521967e-05,
|
| 205 |
+
"loss": 0.0784,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.73,
|
| 210 |
+
"learning_rate": 1.5133193054780208e-05,
|
| 211 |
+
"loss": 0.0763,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.75,
|
| 216 |
+
"learning_rate": 1.4990051674038448e-05,
|
| 217 |
+
"loss": 0.0795,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.77,
|
| 222 |
+
"learning_rate": 1.484691029329669e-05,
|
| 223 |
+
"loss": 0.0758,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.79,
|
| 228 |
+
"learning_rate": 1.4703768912554932e-05,
|
| 229 |
+
"loss": 0.0748,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.82,
|
| 234 |
+
"learning_rate": 1.4560627531813175e-05,
|
| 235 |
+
"loss": 0.0741,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.84,
|
| 240 |
+
"learning_rate": 1.4417486151071413e-05,
|
| 241 |
+
"loss": 0.0726,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.86,
|
| 246 |
+
"learning_rate": 1.4274344770329655e-05,
|
| 247 |
+
"loss": 0.0752,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.88,
|
| 252 |
+
"learning_rate": 1.4131203389587897e-05,
|
| 253 |
+
"loss": 0.0746,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.9,
|
| 258 |
+
"learning_rate": 1.398806200884614e-05,
|
| 259 |
+
"loss": 0.0733,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.92,
|
| 264 |
+
"learning_rate": 1.3844920628104378e-05,
|
| 265 |
+
"loss": 0.071,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.94,
|
| 270 |
+
"learning_rate": 1.370177924736262e-05,
|
| 271 |
+
"loss": 0.0745,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.97,
|
| 276 |
+
"learning_rate": 1.3558637866620862e-05,
|
| 277 |
+
"loss": 0.0751,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.99,
|
| 282 |
+
"learning_rate": 1.3415496485879105e-05,
|
| 283 |
+
"loss": 0.0722,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.0,
|
| 288 |
+
"eval_accuracy": 0.8151779770851135,
|
| 289 |
+
"eval_loss": 0.8366696834564209,
|
| 290 |
+
"eval_runtime": 23.897,
|
| 291 |
+
"eval_samples_per_second": 196.301,
|
| 292 |
+
"eval_steps_per_second": 3.097,
|
| 293 |
+
"step": 23287
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.01,
|
| 297 |
+
"learning_rate": 1.3272355105137345e-05,
|
| 298 |
+
"loss": 0.0662,
|
| 299 |
+
"step": 23500
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.03,
|
| 303 |
+
"learning_rate": 1.3129213724395587e-05,
|
| 304 |
+
"loss": 0.0602,
|
| 305 |
+
"step": 24000
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.05,
|
| 309 |
+
"learning_rate": 1.2986072343653827e-05,
|
| 310 |
+
"loss": 0.0619,
|
| 311 |
+
"step": 24500
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.07,
|
| 315 |
+
"learning_rate": 1.284293096291207e-05,
|
| 316 |
+
"loss": 0.0583,
|
| 317 |
+
"step": 25000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.1,
|
| 321 |
+
"learning_rate": 1.269978958217031e-05,
|
| 322 |
+
"loss": 0.0586,
|
| 323 |
+
"step": 25500
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 1.12,
|
| 327 |
+
"learning_rate": 1.2556648201428552e-05,
|
| 328 |
+
"loss": 0.0585,
|
| 329 |
+
"step": 26000
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.14,
|
| 333 |
+
"learning_rate": 1.2413506820686794e-05,
|
| 334 |
+
"loss": 0.059,
|
| 335 |
+
"step": 26500
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 1.16,
|
| 339 |
+
"learning_rate": 1.2270365439945036e-05,
|
| 340 |
+
"loss": 0.0575,
|
| 341 |
+
"step": 27000
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 1.18,
|
| 345 |
+
"learning_rate": 1.2127224059203275e-05,
|
| 346 |
+
"loss": 0.0596,
|
| 347 |
+
"step": 27500
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 1.2,
|
| 351 |
+
"learning_rate": 1.1984082678461517e-05,
|
| 352 |
+
"loss": 0.0595,
|
| 353 |
+
"step": 28000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.22,
|
| 357 |
+
"learning_rate": 1.184094129771976e-05,
|
| 358 |
+
"loss": 0.0588,
|
| 359 |
+
"step": 28500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.25,
|
| 363 |
+
"learning_rate": 1.1697799916978001e-05,
|
| 364 |
+
"loss": 0.0593,
|
| 365 |
+
"step": 29000
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 1.27,
|
| 369 |
+
"learning_rate": 1.155465853623624e-05,
|
| 370 |
+
"loss": 0.0612,
|
| 371 |
+
"step": 29500
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 1.29,
|
| 375 |
+
"learning_rate": 1.1411517155494482e-05,
|
| 376 |
+
"loss": 0.059,
|
| 377 |
+
"step": 30000
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.31,
|
| 381 |
+
"learning_rate": 1.1268375774752724e-05,
|
| 382 |
+
"loss": 0.0566,
|
| 383 |
+
"step": 30500
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.33,
|
| 387 |
+
"learning_rate": 1.1125234394010966e-05,
|
| 388 |
+
"loss": 0.0589,
|
| 389 |
+
"step": 31000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.35,
|
| 393 |
+
"learning_rate": 1.0982093013269207e-05,
|
| 394 |
+
"loss": 0.0601,
|
| 395 |
+
"step": 31500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.37,
|
| 399 |
+
"learning_rate": 1.0838951632527447e-05,
|
| 400 |
+
"loss": 0.0601,
|
| 401 |
+
"step": 32000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.4,
|
| 405 |
+
"learning_rate": 1.069581025178569e-05,
|
| 406 |
+
"loss": 0.0595,
|
| 407 |
+
"step": 32500
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 1.42,
|
| 411 |
+
"learning_rate": 1.0552668871043931e-05,
|
| 412 |
+
"loss": 0.0603,
|
| 413 |
+
"step": 33000
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.44,
|
| 417 |
+
"learning_rate": 1.0409527490302172e-05,
|
| 418 |
+
"loss": 0.0571,
|
| 419 |
+
"step": 33500
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 1.46,
|
| 423 |
+
"learning_rate": 1.0266386109560414e-05,
|
| 424 |
+
"loss": 0.0587,
|
| 425 |
+
"step": 34000
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 1.48,
|
| 429 |
+
"learning_rate": 1.0123244728818656e-05,
|
| 430 |
+
"loss": 0.0565,
|
| 431 |
+
"step": 34500
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 1.5,
|
| 435 |
+
"learning_rate": 9.980103348076896e-06,
|
| 436 |
+
"loss": 0.0579,
|
| 437 |
+
"step": 35000
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.52,
|
| 441 |
+
"learning_rate": 9.836961967335139e-06,
|
| 442 |
+
"loss": 0.0619,
|
| 443 |
+
"step": 35500
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.55,
|
| 447 |
+
"learning_rate": 9.693820586593379e-06,
|
| 448 |
+
"loss": 0.0563,
|
| 449 |
+
"step": 36000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.57,
|
| 453 |
+
"learning_rate": 9.550679205851621e-06,
|
| 454 |
+
"loss": 0.0548,
|
| 455 |
+
"step": 36500
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 1.59,
|
| 459 |
+
"learning_rate": 9.407537825109861e-06,
|
| 460 |
+
"loss": 0.0581,
|
| 461 |
+
"step": 37000
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 1.61,
|
| 465 |
+
"learning_rate": 9.264396444368104e-06,
|
| 466 |
+
"loss": 0.0568,
|
| 467 |
+
"step": 37500
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 1.63,
|
| 471 |
+
"learning_rate": 9.121255063626344e-06,
|
| 472 |
+
"loss": 0.055,
|
| 473 |
+
"step": 38000
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 1.65,
|
| 477 |
+
"learning_rate": 8.978113682884586e-06,
|
| 478 |
+
"loss": 0.0598,
|
| 479 |
+
"step": 38500
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.67,
|
| 483 |
+
"learning_rate": 8.834972302142826e-06,
|
| 484 |
+
"loss": 0.0597,
|
| 485 |
+
"step": 39000
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.7,
|
| 489 |
+
"learning_rate": 8.691830921401069e-06,
|
| 490 |
+
"loss": 0.058,
|
| 491 |
+
"step": 39500
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 1.72,
|
| 495 |
+
"learning_rate": 8.548689540659309e-06,
|
| 496 |
+
"loss": 0.0554,
|
| 497 |
+
"step": 40000
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.74,
|
| 501 |
+
"learning_rate": 8.405548159917551e-06,
|
| 502 |
+
"loss": 0.0563,
|
| 503 |
+
"step": 40500
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 1.76,
|
| 507 |
+
"learning_rate": 8.262406779175792e-06,
|
| 508 |
+
"loss": 0.0571,
|
| 509 |
+
"step": 41000
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.78,
|
| 513 |
+
"learning_rate": 8.119265398434034e-06,
|
| 514 |
+
"loss": 0.0579,
|
| 515 |
+
"step": 41500
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.8,
|
| 519 |
+
"learning_rate": 7.976124017692276e-06,
|
| 520 |
+
"loss": 0.0564,
|
| 521 |
+
"step": 42000
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.83,
|
| 525 |
+
"learning_rate": 7.832982636950516e-06,
|
| 526 |
+
"loss": 0.0577,
|
| 527 |
+
"step": 42500
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.85,
|
| 531 |
+
"learning_rate": 7.689841256208758e-06,
|
| 532 |
+
"loss": 0.0568,
|
| 533 |
+
"step": 43000
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.87,
|
| 537 |
+
"learning_rate": 7.5466998754669995e-06,
|
| 538 |
+
"loss": 0.0596,
|
| 539 |
+
"step": 43500
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 1.89,
|
| 543 |
+
"learning_rate": 7.403558494725241e-06,
|
| 544 |
+
"loss": 0.057,
|
| 545 |
+
"step": 44000
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 1.91,
|
| 549 |
+
"learning_rate": 7.260417113983482e-06,
|
| 550 |
+
"loss": 0.0579,
|
| 551 |
+
"step": 44500
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 1.93,
|
| 555 |
+
"learning_rate": 7.117275733241723e-06,
|
| 556 |
+
"loss": 0.0561,
|
| 557 |
+
"step": 45000
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 1.95,
|
| 561 |
+
"learning_rate": 6.9741343524999645e-06,
|
| 562 |
+
"loss": 0.0548,
|
| 563 |
+
"step": 45500
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.98,
|
| 567 |
+
"learning_rate": 6.830992971758206e-06,
|
| 568 |
+
"loss": 0.0571,
|
| 569 |
+
"step": 46000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 2.0,
|
| 573 |
+
"learning_rate": 6.687851591016448e-06,
|
| 574 |
+
"loss": 0.055,
|
| 575 |
+
"step": 46500
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 2.0,
|
| 579 |
+
"eval_accuracy": 0.8311660885810852,
|
| 580 |
+
"eval_loss": 0.7949723601341248,
|
| 581 |
+
"eval_runtime": 27.7911,
|
| 582 |
+
"eval_samples_per_second": 168.795,
|
| 583 |
+
"eval_steps_per_second": 2.663,
|
| 584 |
+
"step": 46574
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 2.02,
|
| 588 |
+
"learning_rate": 6.544710210274688e-06,
|
| 589 |
+
"loss": 0.0471,
|
| 590 |
+
"step": 47000
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 2.04,
|
| 594 |
+
"learning_rate": 6.40156882953293e-06,
|
| 595 |
+
"loss": 0.0435,
|
| 596 |
+
"step": 47500
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 2.06,
|
| 600 |
+
"learning_rate": 6.258427448791171e-06,
|
| 601 |
+
"loss": 0.043,
|
| 602 |
+
"step": 48000
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 2.08,
|
| 606 |
+
"learning_rate": 6.115286068049413e-06,
|
| 607 |
+
"loss": 0.0431,
|
| 608 |
+
"step": 48500
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 2.1,
|
| 612 |
+
"learning_rate": 5.972144687307654e-06,
|
| 613 |
+
"loss": 0.0433,
|
| 614 |
+
"step": 49000
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 2.13,
|
| 618 |
+
"learning_rate": 5.8290033065658954e-06,
|
| 619 |
+
"loss": 0.0442,
|
| 620 |
+
"step": 49500
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.15,
|
| 624 |
+
"learning_rate": 5.685861925824137e-06,
|
| 625 |
+
"loss": 0.0447,
|
| 626 |
+
"step": 50000
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 2.17,
|
| 630 |
+
"learning_rate": 5.542720545082379e-06,
|
| 631 |
+
"loss": 0.0454,
|
| 632 |
+
"step": 50500
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 2.19,
|
| 636 |
+
"learning_rate": 5.399579164340619e-06,
|
| 637 |
+
"loss": 0.0441,
|
| 638 |
+
"step": 51000
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 2.21,
|
| 642 |
+
"learning_rate": 5.256437783598861e-06,
|
| 643 |
+
"loss": 0.0441,
|
| 644 |
+
"step": 51500
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 2.23,
|
| 648 |
+
"learning_rate": 5.113296402857102e-06,
|
| 649 |
+
"loss": 0.0444,
|
| 650 |
+
"step": 52000
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 2.25,
|
| 654 |
+
"learning_rate": 4.970155022115344e-06,
|
| 655 |
+
"loss": 0.0435,
|
| 656 |
+
"step": 52500
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 2.28,
|
| 660 |
+
"learning_rate": 4.827013641373585e-06,
|
| 661 |
+
"loss": 0.0445,
|
| 662 |
+
"step": 53000
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.3,
|
| 666 |
+
"learning_rate": 4.683872260631826e-06,
|
| 667 |
+
"loss": 0.041,
|
| 668 |
+
"step": 53500
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 2.32,
|
| 672 |
+
"learning_rate": 4.540730879890068e-06,
|
| 673 |
+
"loss": 0.0461,
|
| 674 |
+
"step": 54000
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 2.34,
|
| 678 |
+
"learning_rate": 4.397589499148309e-06,
|
| 679 |
+
"loss": 0.0421,
|
| 680 |
+
"step": 54500
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 2.36,
|
| 684 |
+
"learning_rate": 4.254448118406551e-06,
|
| 685 |
+
"loss": 0.0423,
|
| 686 |
+
"step": 55000
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 2.38,
|
| 690 |
+
"learning_rate": 4.111306737664792e-06,
|
| 691 |
+
"loss": 0.0448,
|
| 692 |
+
"step": 55500
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 2.4,
|
| 696 |
+
"learning_rate": 3.9681653569230335e-06,
|
| 697 |
+
"loss": 0.0447,
|
| 698 |
+
"step": 56000
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 2.43,
|
| 702 |
+
"learning_rate": 3.825023976181275e-06,
|
| 703 |
+
"loss": 0.0461,
|
| 704 |
+
"step": 56500
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.45,
|
| 708 |
+
"learning_rate": 3.681882595439516e-06,
|
| 709 |
+
"loss": 0.0444,
|
| 710 |
+
"step": 57000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 2.47,
|
| 714 |
+
"learning_rate": 3.5387412146977573e-06,
|
| 715 |
+
"loss": 0.0431,
|
| 716 |
+
"step": 57500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 2.49,
|
| 720 |
+
"learning_rate": 3.3955998339559985e-06,
|
| 721 |
+
"loss": 0.042,
|
| 722 |
+
"step": 58000
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 2.51,
|
| 726 |
+
"learning_rate": 3.25245845321424e-06,
|
| 727 |
+
"loss": 0.0415,
|
| 728 |
+
"step": 58500
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 2.53,
|
| 732 |
+
"learning_rate": 3.1093170724724815e-06,
|
| 733 |
+
"loss": 0.0433,
|
| 734 |
+
"step": 59000
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 2.56,
|
| 738 |
+
"learning_rate": 2.9661756917307227e-06,
|
| 739 |
+
"loss": 0.0422,
|
| 740 |
+
"step": 59500
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 2.58,
|
| 744 |
+
"learning_rate": 2.823034310988964e-06,
|
| 745 |
+
"loss": 0.0389,
|
| 746 |
+
"step": 60000
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 2.6,
|
| 750 |
+
"learning_rate": 2.6798929302472052e-06,
|
| 751 |
+
"loss": 0.0424,
|
| 752 |
+
"step": 60500
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 2.62,
|
| 756 |
+
"learning_rate": 2.536751549505447e-06,
|
| 757 |
+
"loss": 0.0397,
|
| 758 |
+
"step": 61000
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 2.64,
|
| 762 |
+
"learning_rate": 2.393610168763688e-06,
|
| 763 |
+
"loss": 0.044,
|
| 764 |
+
"step": 61500
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 2.66,
|
| 768 |
+
"learning_rate": 2.2504687880219294e-06,
|
| 769 |
+
"loss": 0.0443,
|
| 770 |
+
"step": 62000
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 2.68,
|
| 774 |
+
"learning_rate": 2.1073274072801707e-06,
|
| 775 |
+
"loss": 0.0414,
|
| 776 |
+
"step": 62500
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 2.71,
|
| 780 |
+
"learning_rate": 1.9641860265384124e-06,
|
| 781 |
+
"loss": 0.041,
|
| 782 |
+
"step": 63000
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 2.73,
|
| 786 |
+
"learning_rate": 1.8210446457966536e-06,
|
| 787 |
+
"loss": 0.0389,
|
| 788 |
+
"step": 63500
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 2.75,
|
| 792 |
+
"learning_rate": 1.6779032650548949e-06,
|
| 793 |
+
"loss": 0.0433,
|
| 794 |
+
"step": 64000
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 2.77,
|
| 798 |
+
"learning_rate": 1.5347618843131361e-06,
|
| 799 |
+
"loss": 0.0417,
|
| 800 |
+
"step": 64500
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 2.79,
|
| 804 |
+
"learning_rate": 1.3916205035713776e-06,
|
| 805 |
+
"loss": 0.0416,
|
| 806 |
+
"step": 65000
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 2.81,
|
| 810 |
+
"learning_rate": 1.2484791228296189e-06,
|
| 811 |
+
"loss": 0.0424,
|
| 812 |
+
"step": 65500
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 2.83,
|
| 816 |
+
"learning_rate": 1.1053377420878603e-06,
|
| 817 |
+
"loss": 0.0431,
|
| 818 |
+
"step": 66000
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 2.86,
|
| 822 |
+
"learning_rate": 9.621963613461016e-07,
|
| 823 |
+
"loss": 0.0417,
|
| 824 |
+
"step": 66500
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 2.88,
|
| 828 |
+
"learning_rate": 8.19054980604343e-07,
|
| 829 |
+
"loss": 0.0418,
|
| 830 |
+
"step": 67000
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 2.9,
|
| 834 |
+
"learning_rate": 6.759135998625843e-07,
|
| 835 |
+
"loss": 0.0399,
|
| 836 |
+
"step": 67500
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 2.92,
|
| 840 |
+
"learning_rate": 5.327722191208257e-07,
|
| 841 |
+
"loss": 0.0416,
|
| 842 |
+
"step": 68000
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 2.94,
|
| 846 |
+
"learning_rate": 3.89630838379067e-07,
|
| 847 |
+
"loss": 0.0424,
|
| 848 |
+
"step": 68500
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 2.96,
|
| 852 |
+
"learning_rate": 2.464894576373084e-07,
|
| 853 |
+
"loss": 0.0418,
|
| 854 |
+
"step": 69000
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 2.98,
|
| 858 |
+
"learning_rate": 1.0334807689554974e-07,
|
| 859 |
+
"loss": 0.0399,
|
| 860 |
+
"step": 69500
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 3.0,
|
| 864 |
+
"eval_accuracy": 0.8266894221305847,
|
| 865 |
+
"eval_loss": 0.950989842414856,
|
| 866 |
+
"eval_runtime": 23.2697,
|
| 867 |
+
"eval_samples_per_second": 201.593,
|
| 868 |
+
"eval_steps_per_second": 3.18,
|
| 869 |
+
"step": 69861
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 3.0,
|
| 873 |
+
"step": 69861,
|
| 874 |
+
"total_flos": 1.9117803270808904e+18,
|
| 875 |
+
"train_runtime": 54665.4444,
|
| 876 |
+
"train_samples_per_second": 81.787,
|
| 877 |
+
"train_steps_per_second": 1.278
|
| 878 |
+
}
|
| 879 |
+
],
|
| 880 |
+
"max_steps": 69861,
|
| 881 |
+
"num_train_epochs": 3,
|
| 882 |
+
"total_flos": 1.9117803270808904e+18,
|
| 883 |
+
"trial_name": null,
|
| 884 |
+
"trial_params": null
|
| 885 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46e4f52766da5b0c57d3e7e5174aa9776f1013a63ea0ff59b90f33c7dd16f3b7
|
| 3 |
+
size 2543
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|