Upload 12 files
Browse files- all_results.json +13 -0
- config.json +33 -0
- eval_results.json +8 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- special_tokens_map.json +23 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +38 -0
- train_results.json +8 -0
- trainer_state.json +2998 -0
- training_args.bin +3 -0
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_loss": 0.793541669845581,
|
4 |
+
"eval_runtime": 146.5228,
|
5 |
+
"eval_samples": 7539,
|
6 |
+
"eval_samples_per_second": 51.453,
|
7 |
+
"eval_steps_per_second": 6.436,
|
8 |
+
"train_loss": 0.9690902242330864,
|
9 |
+
"train_runtime": 18755.4157,
|
10 |
+
"train_samples": 56618,
|
11 |
+
"train_samples_per_second": 9.056,
|
12 |
+
"train_steps_per_second": 1.132
|
13 |
+
}
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "allegro/plt5-base",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 2048,
|
8 |
+
"d_kv": 64,
|
9 |
+
"d_model": 768,
|
10 |
+
"decoder_start_token_id": 0,
|
11 |
+
"dense_act_fn": "gelu_new",
|
12 |
+
"dropout_rate": 0.1,
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"feed_forward_proj": "gated-gelu",
|
15 |
+
"initializer_factor": 1.0,
|
16 |
+
"is_encoder_decoder": true,
|
17 |
+
"is_gated_act": true,
|
18 |
+
"layer_norm_epsilon": 1e-06,
|
19 |
+
"model_type": "t5",
|
20 |
+
"num_decoder_layers": 12,
|
21 |
+
"num_heads": 12,
|
22 |
+
"num_layers": 12,
|
23 |
+
"output_past": true,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"relative_attention_max_distance": 128,
|
26 |
+
"relative_attention_num_buckets": 32,
|
27 |
+
"tie_word_embeddings": false,
|
28 |
+
"tokenizer_class": "T5Tokenizer",
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.36.0",
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 50048
|
33 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_loss": 0.793541669845581,
|
4 |
+
"eval_runtime": 146.5228,
|
5 |
+
"eval_samples": 7539,
|
6 |
+
"eval_samples_per_second": 51.453,
|
7 |
+
"eval_steps_per_second": 6.436
|
8 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"decoder_start_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.36.0"
|
7 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb269433bfa67dd2bf66029db94574653dd143d5e91d2006a24f035c43dd02bc
|
3 |
+
size 1100445544
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": {
|
3 |
+
"content": "</s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"pad_token": {
|
10 |
+
"content": "<pad>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a200b4b9d7106b32ea2340e5cd27033a5c03ae5ece9241ab6e1f685b938800b9
|
3 |
+
size 1124950
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<pad>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "</s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "<unk>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
}
|
27 |
+
},
|
28 |
+
"additional_special_tokens": [],
|
29 |
+
"clean_up_tokenization_spaces": true,
|
30 |
+
"eos_token": "</s>",
|
31 |
+
"extra_ids": 0,
|
32 |
+
"legacy": true,
|
33 |
+
"model_max_length": 1000000000000000019884624838656,
|
34 |
+
"pad_token": "<pad>",
|
35 |
+
"sp_model_kwargs": {},
|
36 |
+
"tokenizer_class": "T5Tokenizer",
|
37 |
+
"unk_token": "<unk>"
|
38 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"train_loss": 0.9690902242330864,
|
4 |
+
"train_runtime": 18755.4157,
|
5 |
+
"train_samples": 56618,
|
6 |
+
"train_samples_per_second": 9.056,
|
7 |
+
"train_steps_per_second": 1.132
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,2998 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 400,
|
6 |
+
"global_step": 21234,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.01,
|
13 |
+
"learning_rate": 2.992935857586889e-05,
|
14 |
+
"loss": 14.6395,
|
15 |
+
"step": 50
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.01,
|
19 |
+
"learning_rate": 2.985871715173778e-05,
|
20 |
+
"loss": 8.6304,
|
21 |
+
"step": 100
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.02,
|
25 |
+
"learning_rate": 2.978807572760667e-05,
|
26 |
+
"loss": 6.1691,
|
27 |
+
"step": 150
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.03,
|
31 |
+
"learning_rate": 2.9717434303475558e-05,
|
32 |
+
"loss": 5.4462,
|
33 |
+
"step": 200
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.04,
|
37 |
+
"learning_rate": 2.964679287934445e-05,
|
38 |
+
"loss": 4.827,
|
39 |
+
"step": 250
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.04,
|
43 |
+
"learning_rate": 2.9576151455213337e-05,
|
44 |
+
"loss": 4.2751,
|
45 |
+
"step": 300
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.05,
|
49 |
+
"learning_rate": 2.9505510031082228e-05,
|
50 |
+
"loss": 3.9951,
|
51 |
+
"step": 350
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.06,
|
55 |
+
"learning_rate": 2.9434868606951115e-05,
|
56 |
+
"loss": 3.8793,
|
57 |
+
"step": 400
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.06,
|
61 |
+
"eval_loss": 2.5431909561157227,
|
62 |
+
"eval_runtime": 146.3919,
|
63 |
+
"eval_samples_per_second": 51.499,
|
64 |
+
"eval_steps_per_second": 6.442,
|
65 |
+
"step": 400
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.06,
|
69 |
+
"learning_rate": 2.9364227182820006e-05,
|
70 |
+
"loss": 3.5368,
|
71 |
+
"step": 450
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 0.07,
|
75 |
+
"learning_rate": 2.9293585758688894e-05,
|
76 |
+
"loss": 3.243,
|
77 |
+
"step": 500
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 0.08,
|
81 |
+
"learning_rate": 2.9222944334557785e-05,
|
82 |
+
"loss": 3.3564,
|
83 |
+
"step": 550
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 0.08,
|
87 |
+
"learning_rate": 2.9152302910426676e-05,
|
88 |
+
"loss": 3.1593,
|
89 |
+
"step": 600
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.09,
|
93 |
+
"learning_rate": 2.9081661486295564e-05,
|
94 |
+
"loss": 2.9504,
|
95 |
+
"step": 650
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 0.1,
|
99 |
+
"learning_rate": 2.901102006216445e-05,
|
100 |
+
"loss": 2.6833,
|
101 |
+
"step": 700
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 0.11,
|
105 |
+
"learning_rate": 2.8940378638033346e-05,
|
106 |
+
"loss": 2.5516,
|
107 |
+
"step": 750
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.11,
|
111 |
+
"learning_rate": 2.8869737213902233e-05,
|
112 |
+
"loss": 2.3584,
|
113 |
+
"step": 800
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 0.11,
|
117 |
+
"eval_loss": 2.064560651779175,
|
118 |
+
"eval_runtime": 146.3705,
|
119 |
+
"eval_samples_per_second": 51.506,
|
120 |
+
"eval_steps_per_second": 6.443,
|
121 |
+
"step": 800
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.12,
|
125 |
+
"learning_rate": 2.879909578977112e-05,
|
126 |
+
"loss": 2.3706,
|
127 |
+
"step": 850
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"epoch": 0.13,
|
131 |
+
"learning_rate": 2.8728454365640012e-05,
|
132 |
+
"loss": 2.3712,
|
133 |
+
"step": 900
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 0.13,
|
137 |
+
"learning_rate": 2.8657812941508903e-05,
|
138 |
+
"loss": 2.454,
|
139 |
+
"step": 950
|
140 |
+
},
|
141 |
+
{
|
142 |
+
"epoch": 0.14,
|
143 |
+
"learning_rate": 2.858717151737779e-05,
|
144 |
+
"loss": 2.3754,
|
145 |
+
"step": 1000
|
146 |
+
},
|
147 |
+
{
|
148 |
+
"epoch": 0.15,
|
149 |
+
"learning_rate": 2.851653009324668e-05,
|
150 |
+
"loss": 2.2086,
|
151 |
+
"step": 1050
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 0.16,
|
155 |
+
"learning_rate": 2.844588866911557e-05,
|
156 |
+
"loss": 2.4654,
|
157 |
+
"step": 1100
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.16,
|
161 |
+
"learning_rate": 2.837524724498446e-05,
|
162 |
+
"loss": 2.2728,
|
163 |
+
"step": 1150
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.17,
|
167 |
+
"learning_rate": 2.8304605820853348e-05,
|
168 |
+
"loss": 2.1175,
|
169 |
+
"step": 1200
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 0.17,
|
173 |
+
"eval_loss": 1.9099233150482178,
|
174 |
+
"eval_runtime": 146.2849,
|
175 |
+
"eval_samples_per_second": 51.536,
|
176 |
+
"eval_steps_per_second": 6.446,
|
177 |
+
"step": 1200
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.18,
|
181 |
+
"learning_rate": 2.823396439672224e-05,
|
182 |
+
"loss": 1.9796,
|
183 |
+
"step": 1250
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.18,
|
187 |
+
"learning_rate": 2.8163322972591127e-05,
|
188 |
+
"loss": 2.1218,
|
189 |
+
"step": 1300
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.19,
|
193 |
+
"learning_rate": 2.8092681548460018e-05,
|
194 |
+
"loss": 2.0264,
|
195 |
+
"step": 1350
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.2,
|
199 |
+
"learning_rate": 2.802204012432891e-05,
|
200 |
+
"loss": 2.0893,
|
201 |
+
"step": 1400
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.2,
|
205 |
+
"learning_rate": 2.7951398700197796e-05,
|
206 |
+
"loss": 2.0299,
|
207 |
+
"step": 1450
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.21,
|
211 |
+
"learning_rate": 2.7880757276066684e-05,
|
212 |
+
"loss": 1.8765,
|
213 |
+
"step": 1500
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.22,
|
217 |
+
"learning_rate": 2.781011585193558e-05,
|
218 |
+
"loss": 1.8572,
|
219 |
+
"step": 1550
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.23,
|
223 |
+
"learning_rate": 2.7739474427804466e-05,
|
224 |
+
"loss": 1.7761,
|
225 |
+
"step": 1600
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.23,
|
229 |
+
"eval_loss": 1.8229914903640747,
|
230 |
+
"eval_runtime": 146.5454,
|
231 |
+
"eval_samples_per_second": 51.445,
|
232 |
+
"eval_steps_per_second": 6.435,
|
233 |
+
"step": 1600
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.23,
|
237 |
+
"learning_rate": 2.7668833003673354e-05,
|
238 |
+
"loss": 1.7773,
|
239 |
+
"step": 1650
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 0.24,
|
243 |
+
"learning_rate": 2.7598191579542245e-05,
|
244 |
+
"loss": 1.8014,
|
245 |
+
"step": 1700
|
246 |
+
},
|
247 |
+
{
|
248 |
+
"epoch": 0.25,
|
249 |
+
"learning_rate": 2.7527550155411136e-05,
|
250 |
+
"loss": 1.8682,
|
251 |
+
"step": 1750
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 0.25,
|
255 |
+
"learning_rate": 2.7456908731280023e-05,
|
256 |
+
"loss": 1.9171,
|
257 |
+
"step": 1800
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 0.26,
|
261 |
+
"learning_rate": 2.7386267307148914e-05,
|
262 |
+
"loss": 1.7615,
|
263 |
+
"step": 1850
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 0.27,
|
267 |
+
"learning_rate": 2.7315625883017802e-05,
|
268 |
+
"loss": 1.7201,
|
269 |
+
"step": 1900
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.28,
|
273 |
+
"learning_rate": 2.7244984458886693e-05,
|
274 |
+
"loss": 1.6485,
|
275 |
+
"step": 1950
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.28,
|
279 |
+
"learning_rate": 2.717434303475558e-05,
|
280 |
+
"loss": 1.6427,
|
281 |
+
"step": 2000
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 0.28,
|
285 |
+
"eval_loss": 1.7565761804580688,
|
286 |
+
"eval_runtime": 146.4911,
|
287 |
+
"eval_samples_per_second": 51.464,
|
288 |
+
"eval_steps_per_second": 6.437,
|
289 |
+
"step": 2000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.29,
|
293 |
+
"learning_rate": 2.710370161062447e-05,
|
294 |
+
"loss": 1.9137,
|
295 |
+
"step": 2050
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"epoch": 0.3,
|
299 |
+
"learning_rate": 2.703306018649336e-05,
|
300 |
+
"loss": 1.8964,
|
301 |
+
"step": 2100
|
302 |
+
},
|
303 |
+
{
|
304 |
+
"epoch": 0.3,
|
305 |
+
"learning_rate": 2.696241876236225e-05,
|
306 |
+
"loss": 1.7006,
|
307 |
+
"step": 2150
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 0.31,
|
311 |
+
"learning_rate": 2.689177733823114e-05,
|
312 |
+
"loss": 1.7578,
|
313 |
+
"step": 2200
|
314 |
+
},
|
315 |
+
{
|
316 |
+
"epoch": 0.32,
|
317 |
+
"learning_rate": 2.682113591410003e-05,
|
318 |
+
"loss": 1.7194,
|
319 |
+
"step": 2250
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"epoch": 0.32,
|
323 |
+
"learning_rate": 2.6750494489968917e-05,
|
324 |
+
"loss": 1.8679,
|
325 |
+
"step": 2300
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 0.33,
|
329 |
+
"learning_rate": 2.667985306583781e-05,
|
330 |
+
"loss": 1.5503,
|
331 |
+
"step": 2350
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.34,
|
335 |
+
"learning_rate": 2.66092116417067e-05,
|
336 |
+
"loss": 1.5331,
|
337 |
+
"step": 2400
|
338 |
+
},
|
339 |
+
{
|
340 |
+
"epoch": 0.34,
|
341 |
+
"eval_loss": 1.6002424955368042,
|
342 |
+
"eval_runtime": 146.4497,
|
343 |
+
"eval_samples_per_second": 51.478,
|
344 |
+
"eval_steps_per_second": 6.439,
|
345 |
+
"step": 2400
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.35,
|
349 |
+
"learning_rate": 2.6538570217575586e-05,
|
350 |
+
"loss": 1.5046,
|
351 |
+
"step": 2450
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 0.35,
|
355 |
+
"learning_rate": 2.6467928793444477e-05,
|
356 |
+
"loss": 1.4923,
|
357 |
+
"step": 2500
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 0.36,
|
361 |
+
"learning_rate": 2.6397287369313365e-05,
|
362 |
+
"loss": 1.4884,
|
363 |
+
"step": 2550
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 0.37,
|
367 |
+
"learning_rate": 2.6326645945182256e-05,
|
368 |
+
"loss": 1.4889,
|
369 |
+
"step": 2600
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.37,
|
373 |
+
"learning_rate": 2.6256004521051143e-05,
|
374 |
+
"loss": 1.4259,
|
375 |
+
"step": 2650
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.38,
|
379 |
+
"learning_rate": 2.6185363096920034e-05,
|
380 |
+
"loss": 1.4368,
|
381 |
+
"step": 2700
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.39,
|
385 |
+
"learning_rate": 2.6114721672788922e-05,
|
386 |
+
"loss": 1.3874,
|
387 |
+
"step": 2750
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.4,
|
391 |
+
"learning_rate": 2.6044080248657813e-05,
|
392 |
+
"loss": 1.2631,
|
393 |
+
"step": 2800
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 0.4,
|
397 |
+
"eval_loss": 1.2792493104934692,
|
398 |
+
"eval_runtime": 146.3888,
|
399 |
+
"eval_samples_per_second": 51.5,
|
400 |
+
"eval_steps_per_second": 6.442,
|
401 |
+
"step": 2800
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.4,
|
405 |
+
"learning_rate": 2.5973438824526704e-05,
|
406 |
+
"loss": 1.3781,
|
407 |
+
"step": 2850
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"epoch": 0.41,
|
411 |
+
"learning_rate": 2.5902797400395592e-05,
|
412 |
+
"loss": 1.2868,
|
413 |
+
"step": 2900
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 0.42,
|
417 |
+
"learning_rate": 2.583215597626448e-05,
|
418 |
+
"loss": 1.3965,
|
419 |
+
"step": 2950
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 0.42,
|
423 |
+
"learning_rate": 2.5761514552133374e-05,
|
424 |
+
"loss": 1.1789,
|
425 |
+
"step": 3000
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 0.43,
|
429 |
+
"learning_rate": 2.569087312800226e-05,
|
430 |
+
"loss": 1.1915,
|
431 |
+
"step": 3050
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.44,
|
435 |
+
"learning_rate": 2.562023170387115e-05,
|
436 |
+
"loss": 1.1582,
|
437 |
+
"step": 3100
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 0.45,
|
441 |
+
"learning_rate": 2.554959027974004e-05,
|
442 |
+
"loss": 1.3444,
|
443 |
+
"step": 3150
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.45,
|
447 |
+
"learning_rate": 2.547894885560893e-05,
|
448 |
+
"loss": 1.3403,
|
449 |
+
"step": 3200
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 0.45,
|
453 |
+
"eval_loss": 1.1806565523147583,
|
454 |
+
"eval_runtime": 146.4657,
|
455 |
+
"eval_samples_per_second": 51.473,
|
456 |
+
"eval_steps_per_second": 6.438,
|
457 |
+
"step": 3200
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.46,
|
461 |
+
"learning_rate": 2.540830743147782e-05,
|
462 |
+
"loss": 1.2903,
|
463 |
+
"step": 3250
|
464 |
+
},
|
465 |
+
{
|
466 |
+
"epoch": 0.47,
|
467 |
+
"learning_rate": 2.533766600734671e-05,
|
468 |
+
"loss": 1.2086,
|
469 |
+
"step": 3300
|
470 |
+
},
|
471 |
+
{
|
472 |
+
"epoch": 0.47,
|
473 |
+
"learning_rate": 2.5267024583215597e-05,
|
474 |
+
"loss": 1.2047,
|
475 |
+
"step": 3350
|
476 |
+
},
|
477 |
+
{
|
478 |
+
"epoch": 0.48,
|
479 |
+
"learning_rate": 2.519638315908449e-05,
|
480 |
+
"loss": 1.1538,
|
481 |
+
"step": 3400
|
482 |
+
},
|
483 |
+
{
|
484 |
+
"epoch": 0.49,
|
485 |
+
"learning_rate": 2.5125741734953376e-05,
|
486 |
+
"loss": 1.184,
|
487 |
+
"step": 3450
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 0.49,
|
491 |
+
"learning_rate": 2.5055100310822267e-05,
|
492 |
+
"loss": 1.0577,
|
493 |
+
"step": 3500
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 0.5,
|
497 |
+
"learning_rate": 2.4984458886691155e-05,
|
498 |
+
"loss": 1.1838,
|
499 |
+
"step": 3550
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.51,
|
503 |
+
"learning_rate": 2.4913817462560046e-05,
|
504 |
+
"loss": 1.1105,
|
505 |
+
"step": 3600
|
506 |
+
},
|
507 |
+
{
|
508 |
+
"epoch": 0.51,
|
509 |
+
"eval_loss": 1.1069550514221191,
|
510 |
+
"eval_runtime": 146.67,
|
511 |
+
"eval_samples_per_second": 51.401,
|
512 |
+
"eval_steps_per_second": 6.429,
|
513 |
+
"step": 3600
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.52,
|
517 |
+
"learning_rate": 2.4843176038428937e-05,
|
518 |
+
"loss": 1.0968,
|
519 |
+
"step": 3650
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.52,
|
523 |
+
"learning_rate": 2.4772534614297824e-05,
|
524 |
+
"loss": 1.0911,
|
525 |
+
"step": 3700
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 0.53,
|
529 |
+
"learning_rate": 2.4701893190166712e-05,
|
530 |
+
"loss": 0.9316,
|
531 |
+
"step": 3750
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 0.54,
|
535 |
+
"learning_rate": 2.4631251766035606e-05,
|
536 |
+
"loss": 1.1932,
|
537 |
+
"step": 3800
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.54,
|
541 |
+
"learning_rate": 2.4560610341904494e-05,
|
542 |
+
"loss": 1.1092,
|
543 |
+
"step": 3850
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.55,
|
547 |
+
"learning_rate": 2.448996891777338e-05,
|
548 |
+
"loss": 0.9679,
|
549 |
+
"step": 3900
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.56,
|
553 |
+
"learning_rate": 2.4419327493642273e-05,
|
554 |
+
"loss": 1.0059,
|
555 |
+
"step": 3950
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.57,
|
559 |
+
"learning_rate": 2.4348686069511164e-05,
|
560 |
+
"loss": 1.1187,
|
561 |
+
"step": 4000
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 0.57,
|
565 |
+
"eval_loss": 1.0644315481185913,
|
566 |
+
"eval_runtime": 146.3933,
|
567 |
+
"eval_samples_per_second": 51.498,
|
568 |
+
"eval_steps_per_second": 6.442,
|
569 |
+
"step": 4000
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.57,
|
573 |
+
"learning_rate": 2.427804464538005e-05,
|
574 |
+
"loss": 1.0207,
|
575 |
+
"step": 4050
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"epoch": 0.58,
|
579 |
+
"learning_rate": 2.420740322124894e-05,
|
580 |
+
"loss": 1.074,
|
581 |
+
"step": 4100
|
582 |
+
},
|
583 |
+
{
|
584 |
+
"epoch": 0.59,
|
585 |
+
"learning_rate": 2.413676179711783e-05,
|
586 |
+
"loss": 1.0159,
|
587 |
+
"step": 4150
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 0.59,
|
591 |
+
"learning_rate": 2.406612037298672e-05,
|
592 |
+
"loss": 1.0128,
|
593 |
+
"step": 4200
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 0.6,
|
597 |
+
"learning_rate": 2.399547894885561e-05,
|
598 |
+
"loss": 1.0398,
|
599 |
+
"step": 4250
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 0.61,
|
603 |
+
"learning_rate": 2.39248375247245e-05,
|
604 |
+
"loss": 1.0713,
|
605 |
+
"step": 4300
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 0.61,
|
609 |
+
"learning_rate": 2.3854196100593387e-05,
|
610 |
+
"loss": 0.9827,
|
611 |
+
"step": 4350
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.62,
|
615 |
+
"learning_rate": 2.378355467646228e-05,
|
616 |
+
"loss": 1.0307,
|
617 |
+
"step": 4400
|
618 |
+
},
|
619 |
+
{
|
620 |
+
"epoch": 0.62,
|
621 |
+
"eval_loss": 1.053775668144226,
|
622 |
+
"eval_runtime": 146.3869,
|
623 |
+
"eval_samples_per_second": 51.501,
|
624 |
+
"eval_steps_per_second": 6.442,
|
625 |
+
"step": 4400
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.63,
|
629 |
+
"learning_rate": 2.371291325233117e-05,
|
630 |
+
"loss": 0.9596,
|
631 |
+
"step": 4450
|
632 |
+
},
|
633 |
+
{
|
634 |
+
"epoch": 0.64,
|
635 |
+
"learning_rate": 2.3642271828200057e-05,
|
636 |
+
"loss": 0.9598,
|
637 |
+
"step": 4500
|
638 |
+
},
|
639 |
+
{
|
640 |
+
"epoch": 0.64,
|
641 |
+
"learning_rate": 2.3571630404068945e-05,
|
642 |
+
"loss": 0.9912,
|
643 |
+
"step": 4550
|
644 |
+
},
|
645 |
+
{
|
646 |
+
"epoch": 0.65,
|
647 |
+
"learning_rate": 2.350098897993784e-05,
|
648 |
+
"loss": 0.9629,
|
649 |
+
"step": 4600
|
650 |
+
},
|
651 |
+
{
|
652 |
+
"epoch": 0.66,
|
653 |
+
"learning_rate": 2.3430347555806727e-05,
|
654 |
+
"loss": 0.9623,
|
655 |
+
"step": 4650
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 0.66,
|
659 |
+
"learning_rate": 2.3359706131675614e-05,
|
660 |
+
"loss": 0.9315,
|
661 |
+
"step": 4700
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 0.67,
|
665 |
+
"learning_rate": 2.3289064707544505e-05,
|
666 |
+
"loss": 0.9403,
|
667 |
+
"step": 4750
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.68,
|
671 |
+
"learning_rate": 2.3218423283413396e-05,
|
672 |
+
"loss": 0.9285,
|
673 |
+
"step": 4800
|
674 |
+
},
|
675 |
+
{
|
676 |
+
"epoch": 0.68,
|
677 |
+
"eval_loss": 1.0219874382019043,
|
678 |
+
"eval_runtime": 146.3894,
|
679 |
+
"eval_samples_per_second": 51.5,
|
680 |
+
"eval_steps_per_second": 6.442,
|
681 |
+
"step": 4800
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.69,
|
685 |
+
"learning_rate": 2.3147781859282284e-05,
|
686 |
+
"loss": 0.8947,
|
687 |
+
"step": 4850
|
688 |
+
},
|
689 |
+
{
|
690 |
+
"epoch": 0.69,
|
691 |
+
"learning_rate": 2.307714043515117e-05,
|
692 |
+
"loss": 0.9009,
|
693 |
+
"step": 4900
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 0.7,
|
697 |
+
"learning_rate": 2.3006499011020063e-05,
|
698 |
+
"loss": 0.888,
|
699 |
+
"step": 4950
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.71,
|
703 |
+
"learning_rate": 2.2935857586888954e-05,
|
704 |
+
"loss": 0.9096,
|
705 |
+
"step": 5000
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 0.71,
|
709 |
+
"learning_rate": 2.286521616275784e-05,
|
710 |
+
"loss": 0.926,
|
711 |
+
"step": 5050
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.72,
|
715 |
+
"learning_rate": 2.2794574738626732e-05,
|
716 |
+
"loss": 0.9217,
|
717 |
+
"step": 5100
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 0.73,
|
721 |
+
"learning_rate": 2.272393331449562e-05,
|
722 |
+
"loss": 0.9105,
|
723 |
+
"step": 5150
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.73,
|
727 |
+
"learning_rate": 2.2653291890364508e-05,
|
728 |
+
"loss": 0.8917,
|
729 |
+
"step": 5200
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.73,
|
733 |
+
"eval_loss": 0.9944532513618469,
|
734 |
+
"eval_runtime": 146.4135,
|
735 |
+
"eval_samples_per_second": 51.491,
|
736 |
+
"eval_steps_per_second": 6.441,
|
737 |
+
"step": 5200
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.74,
|
741 |
+
"learning_rate": 2.2582650466233402e-05,
|
742 |
+
"loss": 0.8959,
|
743 |
+
"step": 5250
|
744 |
+
},
|
745 |
+
{
|
746 |
+
"epoch": 0.75,
|
747 |
+
"learning_rate": 2.251200904210229e-05,
|
748 |
+
"loss": 0.8332,
|
749 |
+
"step": 5300
|
750 |
+
},
|
751 |
+
{
|
752 |
+
"epoch": 0.76,
|
753 |
+
"learning_rate": 2.2441367617971177e-05,
|
754 |
+
"loss": 0.9235,
|
755 |
+
"step": 5350
|
756 |
+
},
|
757 |
+
{
|
758 |
+
"epoch": 0.76,
|
759 |
+
"learning_rate": 2.2370726193840068e-05,
|
760 |
+
"loss": 0.7935,
|
761 |
+
"step": 5400
|
762 |
+
},
|
763 |
+
{
|
764 |
+
"epoch": 0.77,
|
765 |
+
"learning_rate": 2.230008476970896e-05,
|
766 |
+
"loss": 0.9101,
|
767 |
+
"step": 5450
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 0.78,
|
771 |
+
"learning_rate": 2.2229443345577847e-05,
|
772 |
+
"loss": 0.9317,
|
773 |
+
"step": 5500
|
774 |
+
},
|
775 |
+
{
|
776 |
+
"epoch": 0.78,
|
777 |
+
"learning_rate": 2.2158801921446738e-05,
|
778 |
+
"loss": 0.9412,
|
779 |
+
"step": 5550
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 0.79,
|
783 |
+
"learning_rate": 2.2088160497315626e-05,
|
784 |
+
"loss": 0.9018,
|
785 |
+
"step": 5600
|
786 |
+
},
|
787 |
+
{
|
788 |
+
"epoch": 0.79,
|
789 |
+
"eval_loss": 0.961943507194519,
|
790 |
+
"eval_runtime": 146.3492,
|
791 |
+
"eval_samples_per_second": 51.514,
|
792 |
+
"eval_steps_per_second": 6.443,
|
793 |
+
"step": 5600
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.8,
|
797 |
+
"learning_rate": 2.2017519073184517e-05,
|
798 |
+
"loss": 0.9469,
|
799 |
+
"step": 5650
|
800 |
+
},
|
801 |
+
{
|
802 |
+
"epoch": 0.81,
|
803 |
+
"learning_rate": 2.1946877649053404e-05,
|
804 |
+
"loss": 0.8957,
|
805 |
+
"step": 5700
|
806 |
+
},
|
807 |
+
{
|
808 |
+
"epoch": 0.81,
|
809 |
+
"learning_rate": 2.1876236224922295e-05,
|
810 |
+
"loss": 0.9212,
|
811 |
+
"step": 5750
|
812 |
+
},
|
813 |
+
{
|
814 |
+
"epoch": 0.82,
|
815 |
+
"learning_rate": 2.1805594800791183e-05,
|
816 |
+
"loss": 0.9815,
|
817 |
+
"step": 5800
|
818 |
+
},
|
819 |
+
{
|
820 |
+
"epoch": 0.83,
|
821 |
+
"learning_rate": 2.1734953376660074e-05,
|
822 |
+
"loss": 0.8364,
|
823 |
+
"step": 5850
|
824 |
+
},
|
825 |
+
{
|
826 |
+
"epoch": 0.83,
|
827 |
+
"learning_rate": 2.1664311952528965e-05,
|
828 |
+
"loss": 0.9239,
|
829 |
+
"step": 5900
|
830 |
+
},
|
831 |
+
{
|
832 |
+
"epoch": 0.84,
|
833 |
+
"learning_rate": 2.1593670528397852e-05,
|
834 |
+
"loss": 0.8507,
|
835 |
+
"step": 5950
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.85,
|
839 |
+
"learning_rate": 2.152302910426674e-05,
|
840 |
+
"loss": 0.8455,
|
841 |
+
"step": 6000
|
842 |
+
},
|
843 |
+
{
|
844 |
+
"epoch": 0.85,
|
845 |
+
"eval_loss": 0.9640973210334778,
|
846 |
+
"eval_runtime": 146.216,
|
847 |
+
"eval_samples_per_second": 51.561,
|
848 |
+
"eval_steps_per_second": 6.449,
|
849 |
+
"step": 6000
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.85,
|
853 |
+
"learning_rate": 2.1452387680135635e-05,
|
854 |
+
"loss": 0.873,
|
855 |
+
"step": 6050
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 0.86,
|
859 |
+
"learning_rate": 2.1381746256004522e-05,
|
860 |
+
"loss": 0.9022,
|
861 |
+
"step": 6100
|
862 |
+
},
|
863 |
+
{
|
864 |
+
"epoch": 0.87,
|
865 |
+
"learning_rate": 2.131110483187341e-05,
|
866 |
+
"loss": 0.9067,
|
867 |
+
"step": 6150
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 0.88,
|
871 |
+
"learning_rate": 2.12404634077423e-05,
|
872 |
+
"loss": 0.8156,
|
873 |
+
"step": 6200
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 0.88,
|
877 |
+
"learning_rate": 2.1169821983611192e-05,
|
878 |
+
"loss": 0.7626,
|
879 |
+
"step": 6250
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.89,
|
883 |
+
"learning_rate": 2.109918055948008e-05,
|
884 |
+
"loss": 0.9551,
|
885 |
+
"step": 6300
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 0.9,
|
889 |
+
"learning_rate": 2.1028539135348967e-05,
|
890 |
+
"loss": 0.7957,
|
891 |
+
"step": 6350
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.9,
|
895 |
+
"learning_rate": 2.0957897711217858e-05,
|
896 |
+
"loss": 0.8259,
|
897 |
+
"step": 6400
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 0.9,
|
901 |
+
"eval_loss": 0.9384291768074036,
|
902 |
+
"eval_runtime": 146.2207,
|
903 |
+
"eval_samples_per_second": 51.559,
|
904 |
+
"eval_steps_per_second": 6.449,
|
905 |
+
"step": 6400
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 0.91,
|
909 |
+
"learning_rate": 2.088725628708675e-05,
|
910 |
+
"loss": 0.7219,
|
911 |
+
"step": 6450
|
912 |
+
},
|
913 |
+
{
|
914 |
+
"epoch": 0.92,
|
915 |
+
"learning_rate": 2.0816614862955637e-05,
|
916 |
+
"loss": 0.8212,
|
917 |
+
"step": 6500
|
918 |
+
},
|
919 |
+
{
|
920 |
+
"epoch": 0.93,
|
921 |
+
"learning_rate": 2.0745973438824528e-05,
|
922 |
+
"loss": 0.7422,
|
923 |
+
"step": 6550
|
924 |
+
},
|
925 |
+
{
|
926 |
+
"epoch": 0.93,
|
927 |
+
"learning_rate": 2.0675332014693415e-05,
|
928 |
+
"loss": 0.8335,
|
929 |
+
"step": 6600
|
930 |
+
},
|
931 |
+
{
|
932 |
+
"epoch": 0.94,
|
933 |
+
"learning_rate": 2.0604690590562306e-05,
|
934 |
+
"loss": 0.8139,
|
935 |
+
"step": 6650
|
936 |
+
},
|
937 |
+
{
|
938 |
+
"epoch": 0.95,
|
939 |
+
"learning_rate": 2.0534049166431197e-05,
|
940 |
+
"loss": 0.8703,
|
941 |
+
"step": 6700
|
942 |
+
},
|
943 |
+
{
|
944 |
+
"epoch": 0.95,
|
945 |
+
"learning_rate": 2.0463407742300085e-05,
|
946 |
+
"loss": 0.9146,
|
947 |
+
"step": 6750
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 0.96,
|
951 |
+
"learning_rate": 2.0392766318168973e-05,
|
952 |
+
"loss": 0.7593,
|
953 |
+
"step": 6800
|
954 |
+
},
|
955 |
+
{
|
956 |
+
"epoch": 0.96,
|
957 |
+
"eval_loss": 0.9210972785949707,
|
958 |
+
"eval_runtime": 146.1977,
|
959 |
+
"eval_samples_per_second": 51.567,
|
960 |
+
"eval_steps_per_second": 6.45,
|
961 |
+
"step": 6800
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 0.97,
|
965 |
+
"learning_rate": 2.0322124894037867e-05,
|
966 |
+
"loss": 0.8349,
|
967 |
+
"step": 6850
|
968 |
+
},
|
969 |
+
{
|
970 |
+
"epoch": 0.97,
|
971 |
+
"learning_rate": 2.0251483469906755e-05,
|
972 |
+
"loss": 0.8791,
|
973 |
+
"step": 6900
|
974 |
+
},
|
975 |
+
{
|
976 |
+
"epoch": 0.98,
|
977 |
+
"learning_rate": 2.0180842045775642e-05,
|
978 |
+
"loss": 0.9861,
|
979 |
+
"step": 6950
|
980 |
+
},
|
981 |
+
{
|
982 |
+
"epoch": 0.99,
|
983 |
+
"learning_rate": 2.0110200621644533e-05,
|
984 |
+
"loss": 0.7273,
|
985 |
+
"step": 7000
|
986 |
+
},
|
987 |
+
{
|
988 |
+
"epoch": 1.0,
|
989 |
+
"learning_rate": 2.0039559197513424e-05,
|
990 |
+
"loss": 0.8075,
|
991 |
+
"step": 7050
|
992 |
+
},
|
993 |
+
{
|
994 |
+
"epoch": 1.0,
|
995 |
+
"learning_rate": 1.9968917773382312e-05,
|
996 |
+
"loss": 0.7553,
|
997 |
+
"step": 7100
|
998 |
+
},
|
999 |
+
{
|
1000 |
+
"epoch": 1.01,
|
1001 |
+
"learning_rate": 1.98982763492512e-05,
|
1002 |
+
"loss": 0.7873,
|
1003 |
+
"step": 7150
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 1.02,
|
1007 |
+
"learning_rate": 1.982763492512009e-05,
|
1008 |
+
"loss": 0.8176,
|
1009 |
+
"step": 7200
|
1010 |
+
},
|
1011 |
+
{
|
1012 |
+
"epoch": 1.02,
|
1013 |
+
"eval_loss": 0.910588264465332,
|
1014 |
+
"eval_runtime": 146.2211,
|
1015 |
+
"eval_samples_per_second": 51.559,
|
1016 |
+
"eval_steps_per_second": 6.449,
|
1017 |
+
"step": 7200
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 1.02,
|
1021 |
+
"learning_rate": 1.9756993500988982e-05,
|
1022 |
+
"loss": 0.7748,
|
1023 |
+
"step": 7250
|
1024 |
+
},
|
1025 |
+
{
|
1026 |
+
"epoch": 1.03,
|
1027 |
+
"learning_rate": 1.968635207685787e-05,
|
1028 |
+
"loss": 0.8337,
|
1029 |
+
"step": 7300
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 1.04,
|
1033 |
+
"learning_rate": 1.961571065272676e-05,
|
1034 |
+
"loss": 0.7968,
|
1035 |
+
"step": 7350
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 1.05,
|
1039 |
+
"learning_rate": 1.9545069228595648e-05,
|
1040 |
+
"loss": 0.7117,
|
1041 |
+
"step": 7400
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"epoch": 1.05,
|
1045 |
+
"learning_rate": 1.947442780446454e-05,
|
1046 |
+
"loss": 0.7323,
|
1047 |
+
"step": 7450
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 1.06,
|
1051 |
+
"learning_rate": 1.940378638033343e-05,
|
1052 |
+
"loss": 0.7593,
|
1053 |
+
"step": 7500
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 1.07,
|
1057 |
+
"learning_rate": 1.9333144956202318e-05,
|
1058 |
+
"loss": 0.7826,
|
1059 |
+
"step": 7550
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 1.07,
|
1063 |
+
"learning_rate": 1.9262503532071205e-05,
|
1064 |
+
"loss": 0.881,
|
1065 |
+
"step": 7600
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 1.07,
|
1069 |
+
"eval_loss": 0.8992499709129333,
|
1070 |
+
"eval_runtime": 146.4953,
|
1071 |
+
"eval_samples_per_second": 51.462,
|
1072 |
+
"eval_steps_per_second": 6.437,
|
1073 |
+
"step": 7600
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 1.08,
|
1077 |
+
"learning_rate": 1.9191862107940096e-05,
|
1078 |
+
"loss": 0.6995,
|
1079 |
+
"step": 7650
|
1080 |
+
},
|
1081 |
+
{
|
1082 |
+
"epoch": 1.09,
|
1083 |
+
"learning_rate": 1.9121220683808987e-05,
|
1084 |
+
"loss": 0.6882,
|
1085 |
+
"step": 7700
|
1086 |
+
},
|
1087 |
+
{
|
1088 |
+
"epoch": 1.09,
|
1089 |
+
"learning_rate": 1.9050579259677875e-05,
|
1090 |
+
"loss": 0.7669,
|
1091 |
+
"step": 7750
|
1092 |
+
},
|
1093 |
+
{
|
1094 |
+
"epoch": 1.1,
|
1095 |
+
"learning_rate": 1.8979937835546766e-05,
|
1096 |
+
"loss": 0.7485,
|
1097 |
+
"step": 7800
|
1098 |
+
},
|
1099 |
+
{
|
1100 |
+
"epoch": 1.11,
|
1101 |
+
"learning_rate": 1.8909296411415654e-05,
|
1102 |
+
"loss": 0.8179,
|
1103 |
+
"step": 7850
|
1104 |
+
},
|
1105 |
+
{
|
1106 |
+
"epoch": 1.12,
|
1107 |
+
"learning_rate": 1.8838654987284545e-05,
|
1108 |
+
"loss": 0.6935,
|
1109 |
+
"step": 7900
|
1110 |
+
},
|
1111 |
+
{
|
1112 |
+
"epoch": 1.12,
|
1113 |
+
"learning_rate": 1.8768013563153432e-05,
|
1114 |
+
"loss": 0.7565,
|
1115 |
+
"step": 7950
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 1.13,
|
1119 |
+
"learning_rate": 1.8697372139022323e-05,
|
1120 |
+
"loss": 0.7842,
|
1121 |
+
"step": 8000
|
1122 |
+
},
|
1123 |
+
{
|
1124 |
+
"epoch": 1.13,
|
1125 |
+
"eval_loss": 0.8948126435279846,
|
1126 |
+
"eval_runtime": 146.2227,
|
1127 |
+
"eval_samples_per_second": 51.558,
|
1128 |
+
"eval_steps_per_second": 6.449,
|
1129 |
+
"step": 8000
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 1.14,
|
1133 |
+
"learning_rate": 1.862673071489121e-05,
|
1134 |
+
"loss": 0.7082,
|
1135 |
+
"step": 8050
|
1136 |
+
},
|
1137 |
+
{
|
1138 |
+
"epoch": 1.14,
|
1139 |
+
"learning_rate": 1.8556089290760102e-05,
|
1140 |
+
"loss": 0.712,
|
1141 |
+
"step": 8100
|
1142 |
+
},
|
1143 |
+
{
|
1144 |
+
"epoch": 1.15,
|
1145 |
+
"learning_rate": 1.8485447866628993e-05,
|
1146 |
+
"loss": 0.7024,
|
1147 |
+
"step": 8150
|
1148 |
+
},
|
1149 |
+
{
|
1150 |
+
"epoch": 1.16,
|
1151 |
+
"learning_rate": 1.841480644249788e-05,
|
1152 |
+
"loss": 0.7146,
|
1153 |
+
"step": 8200
|
1154 |
+
},
|
1155 |
+
{
|
1156 |
+
"epoch": 1.17,
|
1157 |
+
"learning_rate": 1.8344165018366768e-05,
|
1158 |
+
"loss": 0.7073,
|
1159 |
+
"step": 8250
|
1160 |
+
},
|
1161 |
+
{
|
1162 |
+
"epoch": 1.17,
|
1163 |
+
"learning_rate": 1.8273523594235663e-05,
|
1164 |
+
"loss": 0.72,
|
1165 |
+
"step": 8300
|
1166 |
+
},
|
1167 |
+
{
|
1168 |
+
"epoch": 1.18,
|
1169 |
+
"learning_rate": 1.820288217010455e-05,
|
1170 |
+
"loss": 0.7678,
|
1171 |
+
"step": 8350
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 1.19,
|
1175 |
+
"learning_rate": 1.8132240745973438e-05,
|
1176 |
+
"loss": 0.698,
|
1177 |
+
"step": 8400
|
1178 |
+
},
|
1179 |
+
{
|
1180 |
+
"epoch": 1.19,
|
1181 |
+
"eval_loss": 0.8967130780220032,
|
1182 |
+
"eval_runtime": 146.58,
|
1183 |
+
"eval_samples_per_second": 51.433,
|
1184 |
+
"eval_steps_per_second": 6.433,
|
1185 |
+
"step": 8400
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 1.19,
|
1189 |
+
"learning_rate": 1.806159932184233e-05,
|
1190 |
+
"loss": 0.6976,
|
1191 |
+
"step": 8450
|
1192 |
+
},
|
1193 |
+
{
|
1194 |
+
"epoch": 1.2,
|
1195 |
+
"learning_rate": 1.799095789771122e-05,
|
1196 |
+
"loss": 0.74,
|
1197 |
+
"step": 8500
|
1198 |
+
},
|
1199 |
+
{
|
1200 |
+
"epoch": 1.21,
|
1201 |
+
"learning_rate": 1.7920316473580108e-05,
|
1202 |
+
"loss": 0.7858,
|
1203 |
+
"step": 8550
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"epoch": 1.22,
|
1207 |
+
"learning_rate": 1.7849675049448995e-05,
|
1208 |
+
"loss": 0.6905,
|
1209 |
+
"step": 8600
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 1.22,
|
1213 |
+
"learning_rate": 1.7779033625317886e-05,
|
1214 |
+
"loss": 0.7195,
|
1215 |
+
"step": 8650
|
1216 |
+
},
|
1217 |
+
{
|
1218 |
+
"epoch": 1.23,
|
1219 |
+
"learning_rate": 1.7708392201186777e-05,
|
1220 |
+
"loss": 0.6889,
|
1221 |
+
"step": 8700
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 1.24,
|
1225 |
+
"learning_rate": 1.7637750777055665e-05,
|
1226 |
+
"loss": 0.7499,
|
1227 |
+
"step": 8750
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 1.24,
|
1231 |
+
"learning_rate": 1.7567109352924556e-05,
|
1232 |
+
"loss": 0.649,
|
1233 |
+
"step": 8800
|
1234 |
+
},
|
1235 |
+
{
|
1236 |
+
"epoch": 1.24,
|
1237 |
+
"eval_loss": 0.8673287630081177,
|
1238 |
+
"eval_runtime": 146.2981,
|
1239 |
+
"eval_samples_per_second": 51.532,
|
1240 |
+
"eval_steps_per_second": 6.446,
|
1241 |
+
"step": 8800
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 1.25,
|
1245 |
+
"learning_rate": 1.7496467928793444e-05,
|
1246 |
+
"loss": 0.6689,
|
1247 |
+
"step": 8850
|
1248 |
+
},
|
1249 |
+
{
|
1250 |
+
"epoch": 1.26,
|
1251 |
+
"learning_rate": 1.7425826504662335e-05,
|
1252 |
+
"loss": 0.7401,
|
1253 |
+
"step": 8900
|
1254 |
+
},
|
1255 |
+
{
|
1256 |
+
"epoch": 1.26,
|
1257 |
+
"learning_rate": 1.7355185080531226e-05,
|
1258 |
+
"loss": 0.6371,
|
1259 |
+
"step": 8950
|
1260 |
+
},
|
1261 |
+
{
|
1262 |
+
"epoch": 1.27,
|
1263 |
+
"learning_rate": 1.7284543656400113e-05,
|
1264 |
+
"loss": 0.6743,
|
1265 |
+
"step": 9000
|
1266 |
+
},
|
1267 |
+
{
|
1268 |
+
"epoch": 1.28,
|
1269 |
+
"learning_rate": 1.7213902232269e-05,
|
1270 |
+
"loss": 0.7858,
|
1271 |
+
"step": 9050
|
1272 |
+
},
|
1273 |
+
{
|
1274 |
+
"epoch": 1.29,
|
1275 |
+
"learning_rate": 1.7143260808137895e-05,
|
1276 |
+
"loss": 0.6682,
|
1277 |
+
"step": 9100
|
1278 |
+
},
|
1279 |
+
{
|
1280 |
+
"epoch": 1.29,
|
1281 |
+
"learning_rate": 1.7072619384006783e-05,
|
1282 |
+
"loss": 0.6313,
|
1283 |
+
"step": 9150
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 1.3,
|
1287 |
+
"learning_rate": 1.700197795987567e-05,
|
1288 |
+
"loss": 0.7243,
|
1289 |
+
"step": 9200
|
1290 |
+
},
|
1291 |
+
{
|
1292 |
+
"epoch": 1.3,
|
1293 |
+
"eval_loss": 0.8753476738929749,
|
1294 |
+
"eval_runtime": 146.7694,
|
1295 |
+
"eval_samples_per_second": 51.366,
|
1296 |
+
"eval_steps_per_second": 6.425,
|
1297 |
+
"step": 9200
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 1.31,
|
1301 |
+
"learning_rate": 1.693133653574456e-05,
|
1302 |
+
"loss": 0.723,
|
1303 |
+
"step": 9250
|
1304 |
+
},
|
1305 |
+
{
|
1306 |
+
"epoch": 1.31,
|
1307 |
+
"learning_rate": 1.6860695111613453e-05,
|
1308 |
+
"loss": 0.6731,
|
1309 |
+
"step": 9300
|
1310 |
+
},
|
1311 |
+
{
|
1312 |
+
"epoch": 1.32,
|
1313 |
+
"learning_rate": 1.679005368748234e-05,
|
1314 |
+
"loss": 0.7232,
|
1315 |
+
"step": 9350
|
1316 |
+
},
|
1317 |
+
{
|
1318 |
+
"epoch": 1.33,
|
1319 |
+
"learning_rate": 1.6719412263351228e-05,
|
1320 |
+
"loss": 0.802,
|
1321 |
+
"step": 9400
|
1322 |
+
},
|
1323 |
+
{
|
1324 |
+
"epoch": 1.34,
|
1325 |
+
"learning_rate": 1.664877083922012e-05,
|
1326 |
+
"loss": 0.7172,
|
1327 |
+
"step": 9450
|
1328 |
+
},
|
1329 |
+
{
|
1330 |
+
"epoch": 1.34,
|
1331 |
+
"learning_rate": 1.657812941508901e-05,
|
1332 |
+
"loss": 0.6294,
|
1333 |
+
"step": 9500
|
1334 |
+
},
|
1335 |
+
{
|
1336 |
+
"epoch": 1.35,
|
1337 |
+
"learning_rate": 1.6507487990957897e-05,
|
1338 |
+
"loss": 0.6319,
|
1339 |
+
"step": 9550
|
1340 |
+
},
|
1341 |
+
{
|
1342 |
+
"epoch": 1.36,
|
1343 |
+
"learning_rate": 1.643684656682679e-05,
|
1344 |
+
"loss": 0.7411,
|
1345 |
+
"step": 9600
|
1346 |
+
},
|
1347 |
+
{
|
1348 |
+
"epoch": 1.36,
|
1349 |
+
"eval_loss": 0.8756875991821289,
|
1350 |
+
"eval_runtime": 146.4905,
|
1351 |
+
"eval_samples_per_second": 51.464,
|
1352 |
+
"eval_steps_per_second": 6.437,
|
1353 |
+
"step": 9600
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 1.36,
|
1357 |
+
"learning_rate": 1.6366205142695676e-05,
|
1358 |
+
"loss": 0.6805,
|
1359 |
+
"step": 9650
|
1360 |
+
},
|
1361 |
+
{
|
1362 |
+
"epoch": 1.37,
|
1363 |
+
"learning_rate": 1.6295563718564567e-05,
|
1364 |
+
"loss": 0.7114,
|
1365 |
+
"step": 9700
|
1366 |
+
},
|
1367 |
+
{
|
1368 |
+
"epoch": 1.38,
|
1369 |
+
"learning_rate": 1.6224922294433458e-05,
|
1370 |
+
"loss": 0.6841,
|
1371 |
+
"step": 9750
|
1372 |
+
},
|
1373 |
+
{
|
1374 |
+
"epoch": 1.38,
|
1375 |
+
"learning_rate": 1.6154280870302346e-05,
|
1376 |
+
"loss": 0.6689,
|
1377 |
+
"step": 9800
|
1378 |
+
},
|
1379 |
+
{
|
1380 |
+
"epoch": 1.39,
|
1381 |
+
"learning_rate": 1.6083639446171233e-05,
|
1382 |
+
"loss": 0.7589,
|
1383 |
+
"step": 9850
|
1384 |
+
},
|
1385 |
+
{
|
1386 |
+
"epoch": 1.4,
|
1387 |
+
"learning_rate": 1.6012998022040128e-05,
|
1388 |
+
"loss": 0.7229,
|
1389 |
+
"step": 9900
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 1.41,
|
1393 |
+
"learning_rate": 1.5942356597909015e-05,
|
1394 |
+
"loss": 0.6673,
|
1395 |
+
"step": 9950
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 1.41,
|
1399 |
+
"learning_rate": 1.5871715173777903e-05,
|
1400 |
+
"loss": 0.702,
|
1401 |
+
"step": 10000
|
1402 |
+
},
|
1403 |
+
{
|
1404 |
+
"epoch": 1.41,
|
1405 |
+
"eval_loss": 0.8556445837020874,
|
1406 |
+
"eval_runtime": 146.5096,
|
1407 |
+
"eval_samples_per_second": 51.457,
|
1408 |
+
"eval_steps_per_second": 6.436,
|
1409 |
+
"step": 10000
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 1.42,
|
1413 |
+
"learning_rate": 1.580107374964679e-05,
|
1414 |
+
"loss": 0.7646,
|
1415 |
+
"step": 10050
|
1416 |
+
},
|
1417 |
+
{
|
1418 |
+
"epoch": 1.43,
|
1419 |
+
"learning_rate": 1.5730432325515685e-05,
|
1420 |
+
"loss": 0.7534,
|
1421 |
+
"step": 10100
|
1422 |
+
},
|
1423 |
+
{
|
1424 |
+
"epoch": 1.43,
|
1425 |
+
"learning_rate": 1.5659790901384573e-05,
|
1426 |
+
"loss": 0.6328,
|
1427 |
+
"step": 10150
|
1428 |
+
},
|
1429 |
+
{
|
1430 |
+
"epoch": 1.44,
|
1431 |
+
"learning_rate": 1.558914947725346e-05,
|
1432 |
+
"loss": 0.62,
|
1433 |
+
"step": 10200
|
1434 |
+
},
|
1435 |
+
{
|
1436 |
+
"epoch": 1.45,
|
1437 |
+
"learning_rate": 1.551850805312235e-05,
|
1438 |
+
"loss": 0.6525,
|
1439 |
+
"step": 10250
|
1440 |
+
},
|
1441 |
+
{
|
1442 |
+
"epoch": 1.46,
|
1443 |
+
"learning_rate": 1.544786662899124e-05,
|
1444 |
+
"loss": 0.7223,
|
1445 |
+
"step": 10300
|
1446 |
+
},
|
1447 |
+
{
|
1448 |
+
"epoch": 1.46,
|
1449 |
+
"learning_rate": 1.537722520486013e-05,
|
1450 |
+
"loss": 0.6904,
|
1451 |
+
"step": 10350
|
1452 |
+
},
|
1453 |
+
{
|
1454 |
+
"epoch": 1.47,
|
1455 |
+
"learning_rate": 1.530658378072902e-05,
|
1456 |
+
"loss": 0.6655,
|
1457 |
+
"step": 10400
|
1458 |
+
},
|
1459 |
+
{
|
1460 |
+
"epoch": 1.47,
|
1461 |
+
"eval_loss": 0.8510493040084839,
|
1462 |
+
"eval_runtime": 146.5188,
|
1463 |
+
"eval_samples_per_second": 51.454,
|
1464 |
+
"eval_steps_per_second": 6.436,
|
1465 |
+
"step": 10400
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 1.48,
|
1469 |
+
"learning_rate": 1.5235942356597909e-05,
|
1470 |
+
"loss": 0.6835,
|
1471 |
+
"step": 10450
|
1472 |
+
},
|
1473 |
+
{
|
1474 |
+
"epoch": 1.48,
|
1475 |
+
"learning_rate": 1.5165300932466798e-05,
|
1476 |
+
"loss": 0.6766,
|
1477 |
+
"step": 10500
|
1478 |
+
},
|
1479 |
+
{
|
1480 |
+
"epoch": 1.49,
|
1481 |
+
"learning_rate": 1.5094659508335689e-05,
|
1482 |
+
"loss": 0.6127,
|
1483 |
+
"step": 10550
|
1484 |
+
},
|
1485 |
+
{
|
1486 |
+
"epoch": 1.5,
|
1487 |
+
"learning_rate": 1.5024018084204578e-05,
|
1488 |
+
"loss": 0.6755,
|
1489 |
+
"step": 10600
|
1490 |
+
},
|
1491 |
+
{
|
1492 |
+
"epoch": 1.5,
|
1493 |
+
"learning_rate": 1.4953376660073466e-05,
|
1494 |
+
"loss": 0.749,
|
1495 |
+
"step": 10650
|
1496 |
+
},
|
1497 |
+
{
|
1498 |
+
"epoch": 1.51,
|
1499 |
+
"learning_rate": 1.4882735235942357e-05,
|
1500 |
+
"loss": 0.6164,
|
1501 |
+
"step": 10700
|
1502 |
+
},
|
1503 |
+
{
|
1504 |
+
"epoch": 1.52,
|
1505 |
+
"learning_rate": 1.4812093811811246e-05,
|
1506 |
+
"loss": 0.6659,
|
1507 |
+
"step": 10750
|
1508 |
+
},
|
1509 |
+
{
|
1510 |
+
"epoch": 1.53,
|
1511 |
+
"learning_rate": 1.4741452387680136e-05,
|
1512 |
+
"loss": 0.6577,
|
1513 |
+
"step": 10800
|
1514 |
+
},
|
1515 |
+
{
|
1516 |
+
"epoch": 1.53,
|
1517 |
+
"eval_loss": 0.8637193441390991,
|
1518 |
+
"eval_runtime": 146.2948,
|
1519 |
+
"eval_samples_per_second": 51.533,
|
1520 |
+
"eval_steps_per_second": 6.446,
|
1521 |
+
"step": 10800
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 1.53,
|
1525 |
+
"learning_rate": 1.4670810963549025e-05,
|
1526 |
+
"loss": 0.7381,
|
1527 |
+
"step": 10850
|
1528 |
+
},
|
1529 |
+
{
|
1530 |
+
"epoch": 1.54,
|
1531 |
+
"learning_rate": 1.4600169539417916e-05,
|
1532 |
+
"loss": 0.6131,
|
1533 |
+
"step": 10900
|
1534 |
+
},
|
1535 |
+
{
|
1536 |
+
"epoch": 1.55,
|
1537 |
+
"learning_rate": 1.4529528115286804e-05,
|
1538 |
+
"loss": 0.6697,
|
1539 |
+
"step": 10950
|
1540 |
+
},
|
1541 |
+
{
|
1542 |
+
"epoch": 1.55,
|
1543 |
+
"learning_rate": 1.4458886691155695e-05,
|
1544 |
+
"loss": 0.6415,
|
1545 |
+
"step": 11000
|
1546 |
+
},
|
1547 |
+
{
|
1548 |
+
"epoch": 1.56,
|
1549 |
+
"learning_rate": 1.4388245267024582e-05,
|
1550 |
+
"loss": 0.6193,
|
1551 |
+
"step": 11050
|
1552 |
+
},
|
1553 |
+
{
|
1554 |
+
"epoch": 1.57,
|
1555 |
+
"learning_rate": 1.4317603842893473e-05,
|
1556 |
+
"loss": 0.6082,
|
1557 |
+
"step": 11100
|
1558 |
+
},
|
1559 |
+
{
|
1560 |
+
"epoch": 1.58,
|
1561 |
+
"learning_rate": 1.4246962418762363e-05,
|
1562 |
+
"loss": 0.7267,
|
1563 |
+
"step": 11150
|
1564 |
+
},
|
1565 |
+
{
|
1566 |
+
"epoch": 1.58,
|
1567 |
+
"learning_rate": 1.4176320994631252e-05,
|
1568 |
+
"loss": 0.5725,
|
1569 |
+
"step": 11200
|
1570 |
+
},
|
1571 |
+
{
|
1572 |
+
"epoch": 1.58,
|
1573 |
+
"eval_loss": 0.8456605076789856,
|
1574 |
+
"eval_runtime": 146.5267,
|
1575 |
+
"eval_samples_per_second": 51.451,
|
1576 |
+
"eval_steps_per_second": 6.436,
|
1577 |
+
"step": 11200
|
1578 |
+
},
|
1579 |
+
{
|
1580 |
+
"epoch": 1.59,
|
1581 |
+
"learning_rate": 1.4105679570500141e-05,
|
1582 |
+
"loss": 0.6639,
|
1583 |
+
"step": 11250
|
1584 |
+
},
|
1585 |
+
{
|
1586 |
+
"epoch": 1.6,
|
1587 |
+
"learning_rate": 1.4035038146369032e-05,
|
1588 |
+
"loss": 0.6161,
|
1589 |
+
"step": 11300
|
1590 |
+
},
|
1591 |
+
{
|
1592 |
+
"epoch": 1.6,
|
1593 |
+
"learning_rate": 1.396439672223792e-05,
|
1594 |
+
"loss": 0.6083,
|
1595 |
+
"step": 11350
|
1596 |
+
},
|
1597 |
+
{
|
1598 |
+
"epoch": 1.61,
|
1599 |
+
"learning_rate": 1.3893755298106811e-05,
|
1600 |
+
"loss": 0.5692,
|
1601 |
+
"step": 11400
|
1602 |
+
},
|
1603 |
+
{
|
1604 |
+
"epoch": 1.62,
|
1605 |
+
"learning_rate": 1.3823113873975699e-05,
|
1606 |
+
"loss": 0.6962,
|
1607 |
+
"step": 11450
|
1608 |
+
},
|
1609 |
+
{
|
1610 |
+
"epoch": 1.62,
|
1611 |
+
"learning_rate": 1.375247244984459e-05,
|
1612 |
+
"loss": 0.6135,
|
1613 |
+
"step": 11500
|
1614 |
+
},
|
1615 |
+
{
|
1616 |
+
"epoch": 1.63,
|
1617 |
+
"learning_rate": 1.3681831025713479e-05,
|
1618 |
+
"loss": 0.6544,
|
1619 |
+
"step": 11550
|
1620 |
+
},
|
1621 |
+
{
|
1622 |
+
"epoch": 1.64,
|
1623 |
+
"learning_rate": 1.3611189601582368e-05,
|
1624 |
+
"loss": 0.6225,
|
1625 |
+
"step": 11600
|
1626 |
+
},
|
1627 |
+
{
|
1628 |
+
"epoch": 1.64,
|
1629 |
+
"eval_loss": 0.8483865857124329,
|
1630 |
+
"eval_runtime": 146.5858,
|
1631 |
+
"eval_samples_per_second": 51.431,
|
1632 |
+
"eval_steps_per_second": 6.433,
|
1633 |
+
"step": 11600
|
1634 |
+
},
|
1635 |
+
{
|
1636 |
+
"epoch": 1.65,
|
1637 |
+
"learning_rate": 1.3540548177451258e-05,
|
1638 |
+
"loss": 0.6596,
|
1639 |
+
"step": 11650
|
1640 |
+
},
|
1641 |
+
{
|
1642 |
+
"epoch": 1.65,
|
1643 |
+
"learning_rate": 1.3469906753320149e-05,
|
1644 |
+
"loss": 0.624,
|
1645 |
+
"step": 11700
|
1646 |
+
},
|
1647 |
+
{
|
1648 |
+
"epoch": 1.66,
|
1649 |
+
"learning_rate": 1.3399265329189036e-05,
|
1650 |
+
"loss": 0.6327,
|
1651 |
+
"step": 11750
|
1652 |
+
},
|
1653 |
+
{
|
1654 |
+
"epoch": 1.67,
|
1655 |
+
"learning_rate": 1.3328623905057927e-05,
|
1656 |
+
"loss": 0.6095,
|
1657 |
+
"step": 11800
|
1658 |
+
},
|
1659 |
+
{
|
1660 |
+
"epoch": 1.67,
|
1661 |
+
"learning_rate": 1.3257982480926815e-05,
|
1662 |
+
"loss": 0.6864,
|
1663 |
+
"step": 11850
|
1664 |
+
},
|
1665 |
+
{
|
1666 |
+
"epoch": 1.68,
|
1667 |
+
"learning_rate": 1.3187341056795706e-05,
|
1668 |
+
"loss": 0.7451,
|
1669 |
+
"step": 11900
|
1670 |
+
},
|
1671 |
+
{
|
1672 |
+
"epoch": 1.69,
|
1673 |
+
"learning_rate": 1.3116699632664595e-05,
|
1674 |
+
"loss": 0.6118,
|
1675 |
+
"step": 11950
|
1676 |
+
},
|
1677 |
+
{
|
1678 |
+
"epoch": 1.7,
|
1679 |
+
"learning_rate": 1.3046058208533485e-05,
|
1680 |
+
"loss": 0.6571,
|
1681 |
+
"step": 12000
|
1682 |
+
},
|
1683 |
+
{
|
1684 |
+
"epoch": 1.7,
|
1685 |
+
"eval_loss": 0.8351559638977051,
|
1686 |
+
"eval_runtime": 146.3219,
|
1687 |
+
"eval_samples_per_second": 51.523,
|
1688 |
+
"eval_steps_per_second": 6.445,
|
1689 |
+
"step": 12000
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 1.7,
|
1693 |
+
"learning_rate": 1.2975416784402374e-05,
|
1694 |
+
"loss": 0.6203,
|
1695 |
+
"step": 12050
|
1696 |
+
},
|
1697 |
+
{
|
1698 |
+
"epoch": 1.71,
|
1699 |
+
"learning_rate": 1.2904775360271263e-05,
|
1700 |
+
"loss": 0.7048,
|
1701 |
+
"step": 12100
|
1702 |
+
},
|
1703 |
+
{
|
1704 |
+
"epoch": 1.72,
|
1705 |
+
"learning_rate": 1.2834133936140153e-05,
|
1706 |
+
"loss": 0.6577,
|
1707 |
+
"step": 12150
|
1708 |
+
},
|
1709 |
+
{
|
1710 |
+
"epoch": 1.72,
|
1711 |
+
"learning_rate": 1.2763492512009044e-05,
|
1712 |
+
"loss": 0.5403,
|
1713 |
+
"step": 12200
|
1714 |
+
},
|
1715 |
+
{
|
1716 |
+
"epoch": 1.73,
|
1717 |
+
"learning_rate": 1.2692851087877931e-05,
|
1718 |
+
"loss": 0.6941,
|
1719 |
+
"step": 12250
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 1.74,
|
1723 |
+
"learning_rate": 1.2622209663746822e-05,
|
1724 |
+
"loss": 0.6098,
|
1725 |
+
"step": 12300
|
1726 |
+
},
|
1727 |
+
{
|
1728 |
+
"epoch": 1.74,
|
1729 |
+
"learning_rate": 1.2551568239615712e-05,
|
1730 |
+
"loss": 0.5796,
|
1731 |
+
"step": 12350
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 1.75,
|
1735 |
+
"learning_rate": 1.2480926815484601e-05,
|
1736 |
+
"loss": 0.6302,
|
1737 |
+
"step": 12400
|
1738 |
+
},
|
1739 |
+
{
|
1740 |
+
"epoch": 1.75,
|
1741 |
+
"eval_loss": 0.8377495408058167,
|
1742 |
+
"eval_runtime": 146.3733,
|
1743 |
+
"eval_samples_per_second": 51.505,
|
1744 |
+
"eval_steps_per_second": 6.442,
|
1745 |
+
"step": 12400
|
1746 |
+
},
|
1747 |
+
{
|
1748 |
+
"epoch": 1.76,
|
1749 |
+
"learning_rate": 1.241028539135349e-05,
|
1750 |
+
"loss": 0.6653,
|
1751 |
+
"step": 12450
|
1752 |
+
},
|
1753 |
+
{
|
1754 |
+
"epoch": 1.77,
|
1755 |
+
"learning_rate": 1.233964396722238e-05,
|
1756 |
+
"loss": 0.5894,
|
1757 |
+
"step": 12500
|
1758 |
+
},
|
1759 |
+
{
|
1760 |
+
"epoch": 1.77,
|
1761 |
+
"learning_rate": 1.2269002543091269e-05,
|
1762 |
+
"loss": 0.6507,
|
1763 |
+
"step": 12550
|
1764 |
+
},
|
1765 |
+
{
|
1766 |
+
"epoch": 1.78,
|
1767 |
+
"learning_rate": 1.219836111896016e-05,
|
1768 |
+
"loss": 0.6557,
|
1769 |
+
"step": 12600
|
1770 |
+
},
|
1771 |
+
{
|
1772 |
+
"epoch": 1.79,
|
1773 |
+
"learning_rate": 1.2127719694829047e-05,
|
1774 |
+
"loss": 0.6185,
|
1775 |
+
"step": 12650
|
1776 |
+
},
|
1777 |
+
{
|
1778 |
+
"epoch": 1.79,
|
1779 |
+
"learning_rate": 1.2057078270697937e-05,
|
1780 |
+
"loss": 0.5889,
|
1781 |
+
"step": 12700
|
1782 |
+
},
|
1783 |
+
{
|
1784 |
+
"epoch": 1.8,
|
1785 |
+
"learning_rate": 1.1986436846566828e-05,
|
1786 |
+
"loss": 0.6514,
|
1787 |
+
"step": 12750
|
1788 |
+
},
|
1789 |
+
{
|
1790 |
+
"epoch": 1.81,
|
1791 |
+
"learning_rate": 1.1915795422435715e-05,
|
1792 |
+
"loss": 0.6231,
|
1793 |
+
"step": 12800
|
1794 |
+
},
|
1795 |
+
{
|
1796 |
+
"epoch": 1.81,
|
1797 |
+
"eval_loss": 0.8342207670211792,
|
1798 |
+
"eval_runtime": 146.3255,
|
1799 |
+
"eval_samples_per_second": 51.522,
|
1800 |
+
"eval_steps_per_second": 6.445,
|
1801 |
+
"step": 12800
|
1802 |
+
},
|
1803 |
+
{
|
1804 |
+
"epoch": 1.82,
|
1805 |
+
"learning_rate": 1.1845153998304606e-05,
|
1806 |
+
"loss": 0.7848,
|
1807 |
+
"step": 12850
|
1808 |
+
},
|
1809 |
+
{
|
1810 |
+
"epoch": 1.82,
|
1811 |
+
"learning_rate": 1.1774512574173494e-05,
|
1812 |
+
"loss": 0.762,
|
1813 |
+
"step": 12900
|
1814 |
+
},
|
1815 |
+
{
|
1816 |
+
"epoch": 1.83,
|
1817 |
+
"learning_rate": 1.1703871150042385e-05,
|
1818 |
+
"loss": 0.586,
|
1819 |
+
"step": 12950
|
1820 |
+
},
|
1821 |
+
{
|
1822 |
+
"epoch": 1.84,
|
1823 |
+
"learning_rate": 1.1633229725911274e-05,
|
1824 |
+
"loss": 0.6209,
|
1825 |
+
"step": 13000
|
1826 |
+
},
|
1827 |
+
{
|
1828 |
+
"epoch": 1.84,
|
1829 |
+
"learning_rate": 1.1562588301780164e-05,
|
1830 |
+
"loss": 0.6537,
|
1831 |
+
"step": 13050
|
1832 |
+
},
|
1833 |
+
{
|
1834 |
+
"epoch": 1.85,
|
1835 |
+
"learning_rate": 1.1491946877649053e-05,
|
1836 |
+
"loss": 0.5856,
|
1837 |
+
"step": 13100
|
1838 |
+
},
|
1839 |
+
{
|
1840 |
+
"epoch": 1.86,
|
1841 |
+
"learning_rate": 1.1421305453517944e-05,
|
1842 |
+
"loss": 0.7796,
|
1843 |
+
"step": 13150
|
1844 |
+
},
|
1845 |
+
{
|
1846 |
+
"epoch": 1.86,
|
1847 |
+
"learning_rate": 1.1350664029386832e-05,
|
1848 |
+
"loss": 0.5718,
|
1849 |
+
"step": 13200
|
1850 |
+
},
|
1851 |
+
{
|
1852 |
+
"epoch": 1.86,
|
1853 |
+
"eval_loss": 0.8108465671539307,
|
1854 |
+
"eval_runtime": 146.303,
|
1855 |
+
"eval_samples_per_second": 51.53,
|
1856 |
+
"eval_steps_per_second": 6.446,
|
1857 |
+
"step": 13200
|
1858 |
+
},
|
1859 |
+
{
|
1860 |
+
"epoch": 1.87,
|
1861 |
+
"learning_rate": 1.1280022605255723e-05,
|
1862 |
+
"loss": 0.6347,
|
1863 |
+
"step": 13250
|
1864 |
+
},
|
1865 |
+
{
|
1866 |
+
"epoch": 1.88,
|
1867 |
+
"learning_rate": 1.120938118112461e-05,
|
1868 |
+
"loss": 0.6508,
|
1869 |
+
"step": 13300
|
1870 |
+
},
|
1871 |
+
{
|
1872 |
+
"epoch": 1.89,
|
1873 |
+
"learning_rate": 1.1138739756993501e-05,
|
1874 |
+
"loss": 0.6238,
|
1875 |
+
"step": 13350
|
1876 |
+
},
|
1877 |
+
{
|
1878 |
+
"epoch": 1.89,
|
1879 |
+
"learning_rate": 1.106809833286239e-05,
|
1880 |
+
"loss": 0.6448,
|
1881 |
+
"step": 13400
|
1882 |
+
},
|
1883 |
+
{
|
1884 |
+
"epoch": 1.9,
|
1885 |
+
"learning_rate": 1.099745690873128e-05,
|
1886 |
+
"loss": 0.6704,
|
1887 |
+
"step": 13450
|
1888 |
+
},
|
1889 |
+
{
|
1890 |
+
"epoch": 1.91,
|
1891 |
+
"learning_rate": 1.092681548460017e-05,
|
1892 |
+
"loss": 0.574,
|
1893 |
+
"step": 13500
|
1894 |
+
},
|
1895 |
+
{
|
1896 |
+
"epoch": 1.91,
|
1897 |
+
"learning_rate": 1.085617406046906e-05,
|
1898 |
+
"loss": 0.7448,
|
1899 |
+
"step": 13550
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 1.92,
|
1903 |
+
"learning_rate": 1.0785532636337948e-05,
|
1904 |
+
"loss": 0.6936,
|
1905 |
+
"step": 13600
|
1906 |
+
},
|
1907 |
+
{
|
1908 |
+
"epoch": 1.92,
|
1909 |
+
"eval_loss": 0.8107577562332153,
|
1910 |
+
"eval_runtime": 146.3517,
|
1911 |
+
"eval_samples_per_second": 51.513,
|
1912 |
+
"eval_steps_per_second": 6.443,
|
1913 |
+
"step": 13600
|
1914 |
+
},
|
1915 |
+
{
|
1916 |
+
"epoch": 1.93,
|
1917 |
+
"learning_rate": 1.0714891212206839e-05,
|
1918 |
+
"loss": 0.6312,
|
1919 |
+
"step": 13650
|
1920 |
+
},
|
1921 |
+
{
|
1922 |
+
"epoch": 1.94,
|
1923 |
+
"learning_rate": 1.0644249788075727e-05,
|
1924 |
+
"loss": 0.62,
|
1925 |
+
"step": 13700
|
1926 |
+
},
|
1927 |
+
{
|
1928 |
+
"epoch": 1.94,
|
1929 |
+
"learning_rate": 1.0573608363944618e-05,
|
1930 |
+
"loss": 0.686,
|
1931 |
+
"step": 13750
|
1932 |
+
},
|
1933 |
+
{
|
1934 |
+
"epoch": 1.95,
|
1935 |
+
"learning_rate": 1.0502966939813507e-05,
|
1936 |
+
"loss": 0.7155,
|
1937 |
+
"step": 13800
|
1938 |
+
},
|
1939 |
+
{
|
1940 |
+
"epoch": 1.96,
|
1941 |
+
"learning_rate": 1.0432325515682396e-05,
|
1942 |
+
"loss": 0.6248,
|
1943 |
+
"step": 13850
|
1944 |
+
},
|
1945 |
+
{
|
1946 |
+
"epoch": 1.96,
|
1947 |
+
"learning_rate": 1.0361684091551286e-05,
|
1948 |
+
"loss": 0.6356,
|
1949 |
+
"step": 13900
|
1950 |
+
},
|
1951 |
+
{
|
1952 |
+
"epoch": 1.97,
|
1953 |
+
"learning_rate": 1.0291042667420175e-05,
|
1954 |
+
"loss": 0.6264,
|
1955 |
+
"step": 13950
|
1956 |
+
},
|
1957 |
+
{
|
1958 |
+
"epoch": 1.98,
|
1959 |
+
"learning_rate": 1.0220401243289064e-05,
|
1960 |
+
"loss": 0.6367,
|
1961 |
+
"step": 14000
|
1962 |
+
},
|
1963 |
+
{
|
1964 |
+
"epoch": 1.98,
|
1965 |
+
"eval_loss": 0.8052195906639099,
|
1966 |
+
"eval_runtime": 146.3569,
|
1967 |
+
"eval_samples_per_second": 51.511,
|
1968 |
+
"eval_steps_per_second": 6.443,
|
1969 |
+
"step": 14000
|
1970 |
+
},
|
1971 |
+
{
|
1972 |
+
"epoch": 1.99,
|
1973 |
+
"learning_rate": 1.0149759819157955e-05,
|
1974 |
+
"loss": 0.5832,
|
1975 |
+
"step": 14050
|
1976 |
+
},
|
1977 |
+
{
|
1978 |
+
"epoch": 1.99,
|
1979 |
+
"learning_rate": 1.0079118395026843e-05,
|
1980 |
+
"loss": 0.7692,
|
1981 |
+
"step": 14100
|
1982 |
+
},
|
1983 |
+
{
|
1984 |
+
"epoch": 2.0,
|
1985 |
+
"learning_rate": 1.0008476970895734e-05,
|
1986 |
+
"loss": 0.6246,
|
1987 |
+
"step": 14150
|
1988 |
+
},
|
1989 |
+
{
|
1990 |
+
"epoch": 2.01,
|
1991 |
+
"learning_rate": 9.937835546764623e-06,
|
1992 |
+
"loss": 0.562,
|
1993 |
+
"step": 14200
|
1994 |
+
},
|
1995 |
+
{
|
1996 |
+
"epoch": 2.01,
|
1997 |
+
"learning_rate": 9.867194122633513e-06,
|
1998 |
+
"loss": 0.6346,
|
1999 |
+
"step": 14250
|
2000 |
+
},
|
2001 |
+
{
|
2002 |
+
"epoch": 2.02,
|
2003 |
+
"learning_rate": 9.796552698502402e-06,
|
2004 |
+
"loss": 0.6442,
|
2005 |
+
"step": 14300
|
2006 |
+
},
|
2007 |
+
{
|
2008 |
+
"epoch": 2.03,
|
2009 |
+
"learning_rate": 9.725911274371291e-06,
|
2010 |
+
"loss": 0.534,
|
2011 |
+
"step": 14350
|
2012 |
+
},
|
2013 |
+
{
|
2014 |
+
"epoch": 2.03,
|
2015 |
+
"learning_rate": 9.65526985024018e-06,
|
2016 |
+
"loss": 0.5806,
|
2017 |
+
"step": 14400
|
2018 |
+
},
|
2019 |
+
{
|
2020 |
+
"epoch": 2.03,
|
2021 |
+
"eval_loss": 0.815026044845581,
|
2022 |
+
"eval_runtime": 146.3828,
|
2023 |
+
"eval_samples_per_second": 51.502,
|
2024 |
+
"eval_steps_per_second": 6.442,
|
2025 |
+
"step": 14400
|
2026 |
+
},
|
2027 |
+
{
|
2028 |
+
"epoch": 2.04,
|
2029 |
+
"learning_rate": 9.584628426109072e-06,
|
2030 |
+
"loss": 0.5669,
|
2031 |
+
"step": 14450
|
2032 |
+
},
|
2033 |
+
{
|
2034 |
+
"epoch": 2.05,
|
2035 |
+
"learning_rate": 9.51398700197796e-06,
|
2036 |
+
"loss": 0.5238,
|
2037 |
+
"step": 14500
|
2038 |
+
},
|
2039 |
+
{
|
2040 |
+
"epoch": 2.06,
|
2041 |
+
"learning_rate": 9.44334557784685e-06,
|
2042 |
+
"loss": 0.6376,
|
2043 |
+
"step": 14550
|
2044 |
+
},
|
2045 |
+
{
|
2046 |
+
"epoch": 2.06,
|
2047 |
+
"learning_rate": 9.37270415371574e-06,
|
2048 |
+
"loss": 0.6301,
|
2049 |
+
"step": 14600
|
2050 |
+
},
|
2051 |
+
{
|
2052 |
+
"epoch": 2.07,
|
2053 |
+
"learning_rate": 9.302062729584629e-06,
|
2054 |
+
"loss": 0.5822,
|
2055 |
+
"step": 14650
|
2056 |
+
},
|
2057 |
+
{
|
2058 |
+
"epoch": 2.08,
|
2059 |
+
"learning_rate": 9.231421305453518e-06,
|
2060 |
+
"loss": 0.533,
|
2061 |
+
"step": 14700
|
2062 |
+
},
|
2063 |
+
{
|
2064 |
+
"epoch": 2.08,
|
2065 |
+
"learning_rate": 9.160779881322408e-06,
|
2066 |
+
"loss": 0.5156,
|
2067 |
+
"step": 14750
|
2068 |
+
},
|
2069 |
+
{
|
2070 |
+
"epoch": 2.09,
|
2071 |
+
"learning_rate": 9.090138457191297e-06,
|
2072 |
+
"loss": 0.6329,
|
2073 |
+
"step": 14800
|
2074 |
+
},
|
2075 |
+
{
|
2076 |
+
"epoch": 2.09,
|
2077 |
+
"eval_loss": 0.8057652711868286,
|
2078 |
+
"eval_runtime": 146.3678,
|
2079 |
+
"eval_samples_per_second": 51.507,
|
2080 |
+
"eval_steps_per_second": 6.443,
|
2081 |
+
"step": 14800
|
2082 |
+
},
|
2083 |
+
{
|
2084 |
+
"epoch": 2.1,
|
2085 |
+
"learning_rate": 9.019497033060188e-06,
|
2086 |
+
"loss": 0.555,
|
2087 |
+
"step": 14850
|
2088 |
+
},
|
2089 |
+
{
|
2090 |
+
"epoch": 2.11,
|
2091 |
+
"learning_rate": 8.948855608929076e-06,
|
2092 |
+
"loss": 0.546,
|
2093 |
+
"step": 14900
|
2094 |
+
},
|
2095 |
+
{
|
2096 |
+
"epoch": 2.11,
|
2097 |
+
"learning_rate": 8.878214184797967e-06,
|
2098 |
+
"loss": 0.6075,
|
2099 |
+
"step": 14950
|
2100 |
+
},
|
2101 |
+
{
|
2102 |
+
"epoch": 2.12,
|
2103 |
+
"learning_rate": 8.807572760666856e-06,
|
2104 |
+
"loss": 0.5868,
|
2105 |
+
"step": 15000
|
2106 |
+
},
|
2107 |
+
{
|
2108 |
+
"epoch": 2.13,
|
2109 |
+
"learning_rate": 8.736931336535745e-06,
|
2110 |
+
"loss": 0.6193,
|
2111 |
+
"step": 15050
|
2112 |
+
},
|
2113 |
+
{
|
2114 |
+
"epoch": 2.13,
|
2115 |
+
"learning_rate": 8.666289912404635e-06,
|
2116 |
+
"loss": 0.6052,
|
2117 |
+
"step": 15100
|
2118 |
+
},
|
2119 |
+
{
|
2120 |
+
"epoch": 2.14,
|
2121 |
+
"learning_rate": 8.595648488273524e-06,
|
2122 |
+
"loss": 0.6021,
|
2123 |
+
"step": 15150
|
2124 |
+
},
|
2125 |
+
{
|
2126 |
+
"epoch": 2.15,
|
2127 |
+
"learning_rate": 8.525007064142413e-06,
|
2128 |
+
"loss": 0.5913,
|
2129 |
+
"step": 15200
|
2130 |
+
},
|
2131 |
+
{
|
2132 |
+
"epoch": 2.15,
|
2133 |
+
"eval_loss": 0.8025009036064148,
|
2134 |
+
"eval_runtime": 146.3582,
|
2135 |
+
"eval_samples_per_second": 51.511,
|
2136 |
+
"eval_steps_per_second": 6.443,
|
2137 |
+
"step": 15200
|
2138 |
+
},
|
2139 |
+
{
|
2140 |
+
"epoch": 2.15,
|
2141 |
+
"learning_rate": 8.454365640011303e-06,
|
2142 |
+
"loss": 0.587,
|
2143 |
+
"step": 15250
|
2144 |
+
},
|
2145 |
+
{
|
2146 |
+
"epoch": 2.16,
|
2147 |
+
"learning_rate": 8.383724215880192e-06,
|
2148 |
+
"loss": 0.5106,
|
2149 |
+
"step": 15300
|
2150 |
+
},
|
2151 |
+
{
|
2152 |
+
"epoch": 2.17,
|
2153 |
+
"learning_rate": 8.313082791749081e-06,
|
2154 |
+
"loss": 0.5606,
|
2155 |
+
"step": 15350
|
2156 |
+
},
|
2157 |
+
{
|
2158 |
+
"epoch": 2.18,
|
2159 |
+
"learning_rate": 8.242441367617972e-06,
|
2160 |
+
"loss": 0.5843,
|
2161 |
+
"step": 15400
|
2162 |
+
},
|
2163 |
+
{
|
2164 |
+
"epoch": 2.18,
|
2165 |
+
"learning_rate": 8.17179994348686e-06,
|
2166 |
+
"loss": 0.5879,
|
2167 |
+
"step": 15450
|
2168 |
+
},
|
2169 |
+
{
|
2170 |
+
"epoch": 2.19,
|
2171 |
+
"learning_rate": 8.101158519355751e-06,
|
2172 |
+
"loss": 0.5804,
|
2173 |
+
"step": 15500
|
2174 |
+
},
|
2175 |
+
{
|
2176 |
+
"epoch": 2.2,
|
2177 |
+
"learning_rate": 8.030517095224639e-06,
|
2178 |
+
"loss": 0.5332,
|
2179 |
+
"step": 15550
|
2180 |
+
},
|
2181 |
+
{
|
2182 |
+
"epoch": 2.2,
|
2183 |
+
"learning_rate": 7.95987567109353e-06,
|
2184 |
+
"loss": 0.5891,
|
2185 |
+
"step": 15600
|
2186 |
+
},
|
2187 |
+
{
|
2188 |
+
"epoch": 2.2,
|
2189 |
+
"eval_loss": 0.8068730235099792,
|
2190 |
+
"eval_runtime": 146.6368,
|
2191 |
+
"eval_samples_per_second": 51.413,
|
2192 |
+
"eval_steps_per_second": 6.431,
|
2193 |
+
"step": 15600
|
2194 |
+
},
|
2195 |
+
{
|
2196 |
+
"epoch": 2.21,
|
2197 |
+
"learning_rate": 7.889234246962419e-06,
|
2198 |
+
"loss": 0.6205,
|
2199 |
+
"step": 15650
|
2200 |
+
},
|
2201 |
+
{
|
2202 |
+
"epoch": 2.22,
|
2203 |
+
"learning_rate": 7.818592822831308e-06,
|
2204 |
+
"loss": 0.5775,
|
2205 |
+
"step": 15700
|
2206 |
+
},
|
2207 |
+
{
|
2208 |
+
"epoch": 2.23,
|
2209 |
+
"learning_rate": 7.747951398700198e-06,
|
2210 |
+
"loss": 0.5515,
|
2211 |
+
"step": 15750
|
2212 |
+
},
|
2213 |
+
{
|
2214 |
+
"epoch": 2.23,
|
2215 |
+
"learning_rate": 7.677309974569087e-06,
|
2216 |
+
"loss": 0.6581,
|
2217 |
+
"step": 15800
|
2218 |
+
},
|
2219 |
+
{
|
2220 |
+
"epoch": 2.24,
|
2221 |
+
"learning_rate": 7.606668550437977e-06,
|
2222 |
+
"loss": 0.5393,
|
2223 |
+
"step": 15850
|
2224 |
+
},
|
2225 |
+
{
|
2226 |
+
"epoch": 2.25,
|
2227 |
+
"learning_rate": 7.536027126306867e-06,
|
2228 |
+
"loss": 0.6666,
|
2229 |
+
"step": 15900
|
2230 |
+
},
|
2231 |
+
{
|
2232 |
+
"epoch": 2.25,
|
2233 |
+
"learning_rate": 7.4653857021757565e-06,
|
2234 |
+
"loss": 0.6101,
|
2235 |
+
"step": 15950
|
2236 |
+
},
|
2237 |
+
{
|
2238 |
+
"epoch": 2.26,
|
2239 |
+
"learning_rate": 7.394744278044646e-06,
|
2240 |
+
"loss": 0.5265,
|
2241 |
+
"step": 16000
|
2242 |
+
},
|
2243 |
+
{
|
2244 |
+
"epoch": 2.26,
|
2245 |
+
"eval_loss": 0.7969786524772644,
|
2246 |
+
"eval_runtime": 146.4757,
|
2247 |
+
"eval_samples_per_second": 51.469,
|
2248 |
+
"eval_steps_per_second": 6.438,
|
2249 |
+
"step": 16000
|
2250 |
+
},
|
2251 |
+
{
|
2252 |
+
"epoch": 2.27,
|
2253 |
+
"learning_rate": 7.324102853913535e-06,
|
2254 |
+
"loss": 0.5849,
|
2255 |
+
"step": 16050
|
2256 |
+
},
|
2257 |
+
{
|
2258 |
+
"epoch": 2.27,
|
2259 |
+
"learning_rate": 7.2534614297824245e-06,
|
2260 |
+
"loss": 0.4989,
|
2261 |
+
"step": 16100
|
2262 |
+
},
|
2263 |
+
{
|
2264 |
+
"epoch": 2.28,
|
2265 |
+
"learning_rate": 7.182820005651315e-06,
|
2266 |
+
"loss": 0.5835,
|
2267 |
+
"step": 16150
|
2268 |
+
},
|
2269 |
+
{
|
2270 |
+
"epoch": 2.29,
|
2271 |
+
"learning_rate": 7.112178581520204e-06,
|
2272 |
+
"loss": 0.598,
|
2273 |
+
"step": 16200
|
2274 |
+
},
|
2275 |
+
{
|
2276 |
+
"epoch": 2.3,
|
2277 |
+
"learning_rate": 7.041537157389093e-06,
|
2278 |
+
"loss": 0.5479,
|
2279 |
+
"step": 16250
|
2280 |
+
},
|
2281 |
+
{
|
2282 |
+
"epoch": 2.3,
|
2283 |
+
"learning_rate": 6.970895733257983e-06,
|
2284 |
+
"loss": 0.6026,
|
2285 |
+
"step": 16300
|
2286 |
+
},
|
2287 |
+
{
|
2288 |
+
"epoch": 2.31,
|
2289 |
+
"learning_rate": 6.900254309126873e-06,
|
2290 |
+
"loss": 0.4896,
|
2291 |
+
"step": 16350
|
2292 |
+
},
|
2293 |
+
{
|
2294 |
+
"epoch": 2.32,
|
2295 |
+
"learning_rate": 6.829612884995762e-06,
|
2296 |
+
"loss": 0.6014,
|
2297 |
+
"step": 16400
|
2298 |
+
},
|
2299 |
+
{
|
2300 |
+
"epoch": 2.32,
|
2301 |
+
"eval_loss": 0.7993112802505493,
|
2302 |
+
"eval_runtime": 146.4005,
|
2303 |
+
"eval_samples_per_second": 51.496,
|
2304 |
+
"eval_steps_per_second": 6.441,
|
2305 |
+
"step": 16400
|
2306 |
+
},
|
2307 |
+
{
|
2308 |
+
"epoch": 2.32,
|
2309 |
+
"learning_rate": 6.7589714608646515e-06,
|
2310 |
+
"loss": 0.6562,
|
2311 |
+
"step": 16450
|
2312 |
+
},
|
2313 |
+
{
|
2314 |
+
"epoch": 2.33,
|
2315 |
+
"learning_rate": 6.688330036733541e-06,
|
2316 |
+
"loss": 0.5241,
|
2317 |
+
"step": 16500
|
2318 |
+
},
|
2319 |
+
{
|
2320 |
+
"epoch": 2.34,
|
2321 |
+
"learning_rate": 6.61768861260243e-06,
|
2322 |
+
"loss": 0.6455,
|
2323 |
+
"step": 16550
|
2324 |
+
},
|
2325 |
+
{
|
2326 |
+
"epoch": 2.35,
|
2327 |
+
"learning_rate": 6.5470471884713194e-06,
|
2328 |
+
"loss": 0.5524,
|
2329 |
+
"step": 16600
|
2330 |
+
},
|
2331 |
+
{
|
2332 |
+
"epoch": 2.35,
|
2333 |
+
"learning_rate": 6.476405764340209e-06,
|
2334 |
+
"loss": 0.5883,
|
2335 |
+
"step": 16650
|
2336 |
+
},
|
2337 |
+
{
|
2338 |
+
"epoch": 2.36,
|
2339 |
+
"learning_rate": 6.405764340209098e-06,
|
2340 |
+
"loss": 0.6005,
|
2341 |
+
"step": 16700
|
2342 |
+
},
|
2343 |
+
{
|
2344 |
+
"epoch": 2.37,
|
2345 |
+
"learning_rate": 6.335122916077988e-06,
|
2346 |
+
"loss": 0.6611,
|
2347 |
+
"step": 16750
|
2348 |
+
},
|
2349 |
+
{
|
2350 |
+
"epoch": 2.37,
|
2351 |
+
"learning_rate": 6.264481491946878e-06,
|
2352 |
+
"loss": 0.5392,
|
2353 |
+
"step": 16800
|
2354 |
+
},
|
2355 |
+
{
|
2356 |
+
"epoch": 2.37,
|
2357 |
+
"eval_loss": 0.8024877905845642,
|
2358 |
+
"eval_runtime": 146.2872,
|
2359 |
+
"eval_samples_per_second": 51.536,
|
2360 |
+
"eval_steps_per_second": 6.446,
|
2361 |
+
"step": 16800
|
2362 |
+
},
|
2363 |
+
{
|
2364 |
+
"epoch": 2.38,
|
2365 |
+
"learning_rate": 6.193840067815767e-06,
|
2366 |
+
"loss": 0.5831,
|
2367 |
+
"step": 16850
|
2368 |
+
},
|
2369 |
+
{
|
2370 |
+
"epoch": 2.39,
|
2371 |
+
"learning_rate": 6.123198643684656e-06,
|
2372 |
+
"loss": 0.5662,
|
2373 |
+
"step": 16900
|
2374 |
+
},
|
2375 |
+
{
|
2376 |
+
"epoch": 2.39,
|
2377 |
+
"learning_rate": 6.052557219553546e-06,
|
2378 |
+
"loss": 0.5643,
|
2379 |
+
"step": 16950
|
2380 |
+
},
|
2381 |
+
{
|
2382 |
+
"epoch": 2.4,
|
2383 |
+
"learning_rate": 5.981915795422436e-06,
|
2384 |
+
"loss": 0.6554,
|
2385 |
+
"step": 17000
|
2386 |
+
},
|
2387 |
+
{
|
2388 |
+
"epoch": 2.41,
|
2389 |
+
"learning_rate": 5.911274371291325e-06,
|
2390 |
+
"loss": 0.5664,
|
2391 |
+
"step": 17050
|
2392 |
+
},
|
2393 |
+
{
|
2394 |
+
"epoch": 2.42,
|
2395 |
+
"learning_rate": 5.840632947160214e-06,
|
2396 |
+
"loss": 0.586,
|
2397 |
+
"step": 17100
|
2398 |
+
},
|
2399 |
+
{
|
2400 |
+
"epoch": 2.42,
|
2401 |
+
"learning_rate": 5.7699915230291046e-06,
|
2402 |
+
"loss": 0.53,
|
2403 |
+
"step": 17150
|
2404 |
+
},
|
2405 |
+
{
|
2406 |
+
"epoch": 2.43,
|
2407 |
+
"learning_rate": 5.699350098897994e-06,
|
2408 |
+
"loss": 0.6073,
|
2409 |
+
"step": 17200
|
2410 |
+
},
|
2411 |
+
{
|
2412 |
+
"epoch": 2.43,
|
2413 |
+
"eval_loss": 0.7982571125030518,
|
2414 |
+
"eval_runtime": 146.4741,
|
2415 |
+
"eval_samples_per_second": 51.47,
|
2416 |
+
"eval_steps_per_second": 6.438,
|
2417 |
+
"step": 17200
|
2418 |
+
},
|
2419 |
+
{
|
2420 |
+
"epoch": 2.44,
|
2421 |
+
"learning_rate": 5.628708674766883e-06,
|
2422 |
+
"loss": 0.5988,
|
2423 |
+
"step": 17250
|
2424 |
+
},
|
2425 |
+
{
|
2426 |
+
"epoch": 2.44,
|
2427 |
+
"learning_rate": 5.5580672506357725e-06,
|
2428 |
+
"loss": 0.5899,
|
2429 |
+
"step": 17300
|
2430 |
+
},
|
2431 |
+
{
|
2432 |
+
"epoch": 2.45,
|
2433 |
+
"learning_rate": 5.487425826504663e-06,
|
2434 |
+
"loss": 0.5709,
|
2435 |
+
"step": 17350
|
2436 |
+
},
|
2437 |
+
{
|
2438 |
+
"epoch": 2.46,
|
2439 |
+
"learning_rate": 5.416784402373552e-06,
|
2440 |
+
"loss": 0.6798,
|
2441 |
+
"step": 17400
|
2442 |
+
},
|
2443 |
+
{
|
2444 |
+
"epoch": 2.47,
|
2445 |
+
"learning_rate": 5.346142978242441e-06,
|
2446 |
+
"loss": 0.6366,
|
2447 |
+
"step": 17450
|
2448 |
+
},
|
2449 |
+
{
|
2450 |
+
"epoch": 2.47,
|
2451 |
+
"learning_rate": 5.275501554111331e-06,
|
2452 |
+
"loss": 0.678,
|
2453 |
+
"step": 17500
|
2454 |
+
},
|
2455 |
+
{
|
2456 |
+
"epoch": 2.48,
|
2457 |
+
"learning_rate": 5.204860129980221e-06,
|
2458 |
+
"loss": 0.5061,
|
2459 |
+
"step": 17550
|
2460 |
+
},
|
2461 |
+
{
|
2462 |
+
"epoch": 2.49,
|
2463 |
+
"learning_rate": 5.13421870584911e-06,
|
2464 |
+
"loss": 0.5536,
|
2465 |
+
"step": 17600
|
2466 |
+
},
|
2467 |
+
{
|
2468 |
+
"epoch": 2.49,
|
2469 |
+
"eval_loss": 0.7959641814231873,
|
2470 |
+
"eval_runtime": 146.5594,
|
2471 |
+
"eval_samples_per_second": 51.44,
|
2472 |
+
"eval_steps_per_second": 6.434,
|
2473 |
+
"step": 17600
|
2474 |
+
},
|
2475 |
+
{
|
2476 |
+
"epoch": 2.49,
|
2477 |
+
"learning_rate": 5.0635772817179995e-06,
|
2478 |
+
"loss": 0.6453,
|
2479 |
+
"step": 17650
|
2480 |
+
},
|
2481 |
+
{
|
2482 |
+
"epoch": 2.5,
|
2483 |
+
"learning_rate": 4.992935857586889e-06,
|
2484 |
+
"loss": 0.5388,
|
2485 |
+
"step": 17700
|
2486 |
+
},
|
2487 |
+
{
|
2488 |
+
"epoch": 2.51,
|
2489 |
+
"learning_rate": 4.922294433455779e-06,
|
2490 |
+
"loss": 0.5864,
|
2491 |
+
"step": 17750
|
2492 |
+
},
|
2493 |
+
{
|
2494 |
+
"epoch": 2.51,
|
2495 |
+
"learning_rate": 4.851653009324668e-06,
|
2496 |
+
"loss": 0.5365,
|
2497 |
+
"step": 17800
|
2498 |
+
},
|
2499 |
+
{
|
2500 |
+
"epoch": 2.52,
|
2501 |
+
"learning_rate": 4.781011585193558e-06,
|
2502 |
+
"loss": 0.5472,
|
2503 |
+
"step": 17850
|
2504 |
+
},
|
2505 |
+
{
|
2506 |
+
"epoch": 2.53,
|
2507 |
+
"learning_rate": 4.710370161062447e-06,
|
2508 |
+
"loss": 0.6661,
|
2509 |
+
"step": 17900
|
2510 |
+
},
|
2511 |
+
{
|
2512 |
+
"epoch": 2.54,
|
2513 |
+
"learning_rate": 4.639728736931336e-06,
|
2514 |
+
"loss": 0.6971,
|
2515 |
+
"step": 17950
|
2516 |
+
},
|
2517 |
+
{
|
2518 |
+
"epoch": 2.54,
|
2519 |
+
"learning_rate": 4.5690873128002265e-06,
|
2520 |
+
"loss": 0.5196,
|
2521 |
+
"step": 18000
|
2522 |
+
},
|
2523 |
+
{
|
2524 |
+
"epoch": 2.54,
|
2525 |
+
"eval_loss": 0.7836597561836243,
|
2526 |
+
"eval_runtime": 146.6328,
|
2527 |
+
"eval_samples_per_second": 51.414,
|
2528 |
+
"eval_steps_per_second": 6.431,
|
2529 |
+
"step": 18000
|
2530 |
+
},
|
2531 |
+
{
|
2532 |
+
"epoch": 2.55,
|
2533 |
+
"learning_rate": 4.498445888669116e-06,
|
2534 |
+
"loss": 0.6394,
|
2535 |
+
"step": 18050
|
2536 |
+
},
|
2537 |
+
{
|
2538 |
+
"epoch": 2.56,
|
2539 |
+
"learning_rate": 4.427804464538005e-06,
|
2540 |
+
"loss": 0.4884,
|
2541 |
+
"step": 18100
|
2542 |
+
},
|
2543 |
+
{
|
2544 |
+
"epoch": 2.56,
|
2545 |
+
"learning_rate": 4.3571630404068945e-06,
|
2546 |
+
"loss": 0.514,
|
2547 |
+
"step": 18150
|
2548 |
+
},
|
2549 |
+
{
|
2550 |
+
"epoch": 2.57,
|
2551 |
+
"learning_rate": 4.286521616275785e-06,
|
2552 |
+
"loss": 0.5209,
|
2553 |
+
"step": 18200
|
2554 |
+
},
|
2555 |
+
{
|
2556 |
+
"epoch": 2.58,
|
2557 |
+
"learning_rate": 4.215880192144674e-06,
|
2558 |
+
"loss": 0.5669,
|
2559 |
+
"step": 18250
|
2560 |
+
},
|
2561 |
+
{
|
2562 |
+
"epoch": 2.59,
|
2563 |
+
"learning_rate": 4.145238768013563e-06,
|
2564 |
+
"loss": 0.5224,
|
2565 |
+
"step": 18300
|
2566 |
+
},
|
2567 |
+
{
|
2568 |
+
"epoch": 2.59,
|
2569 |
+
"learning_rate": 4.074597343882453e-06,
|
2570 |
+
"loss": 0.5607,
|
2571 |
+
"step": 18350
|
2572 |
+
},
|
2573 |
+
{
|
2574 |
+
"epoch": 2.6,
|
2575 |
+
"learning_rate": 4.003955919751343e-06,
|
2576 |
+
"loss": 0.5776,
|
2577 |
+
"step": 18400
|
2578 |
+
},
|
2579 |
+
{
|
2580 |
+
"epoch": 2.6,
|
2581 |
+
"eval_loss": 0.7881141901016235,
|
2582 |
+
"eval_runtime": 146.3758,
|
2583 |
+
"eval_samples_per_second": 51.504,
|
2584 |
+
"eval_steps_per_second": 6.442,
|
2585 |
+
"step": 18400
|
2586 |
+
},
|
2587 |
+
{
|
2588 |
+
"epoch": 2.61,
|
2589 |
+
"learning_rate": 3.933314495620232e-06,
|
2590 |
+
"loss": 0.5759,
|
2591 |
+
"step": 18450
|
2592 |
+
},
|
2593 |
+
{
|
2594 |
+
"epoch": 2.61,
|
2595 |
+
"learning_rate": 3.8626730714891214e-06,
|
2596 |
+
"loss": 0.5871,
|
2597 |
+
"step": 18500
|
2598 |
+
},
|
2599 |
+
{
|
2600 |
+
"epoch": 2.62,
|
2601 |
+
"learning_rate": 3.7920316473580103e-06,
|
2602 |
+
"loss": 0.5992,
|
2603 |
+
"step": 18550
|
2604 |
+
},
|
2605 |
+
{
|
2606 |
+
"epoch": 2.63,
|
2607 |
+
"learning_rate": 3.7213902232269e-06,
|
2608 |
+
"loss": 0.5106,
|
2609 |
+
"step": 18600
|
2610 |
+
},
|
2611 |
+
{
|
2612 |
+
"epoch": 2.63,
|
2613 |
+
"learning_rate": 3.65074879909579e-06,
|
2614 |
+
"loss": 0.5211,
|
2615 |
+
"step": 18650
|
2616 |
+
},
|
2617 |
+
{
|
2618 |
+
"epoch": 2.64,
|
2619 |
+
"learning_rate": 3.580107374964679e-06,
|
2620 |
+
"loss": 0.5794,
|
2621 |
+
"step": 18700
|
2622 |
+
},
|
2623 |
+
{
|
2624 |
+
"epoch": 2.65,
|
2625 |
+
"learning_rate": 3.509465950833569e-06,
|
2626 |
+
"loss": 0.6017,
|
2627 |
+
"step": 18750
|
2628 |
+
},
|
2629 |
+
{
|
2630 |
+
"epoch": 2.66,
|
2631 |
+
"learning_rate": 3.4388245267024582e-06,
|
2632 |
+
"loss": 0.5981,
|
2633 |
+
"step": 18800
|
2634 |
+
},
|
2635 |
+
{
|
2636 |
+
"epoch": 2.66,
|
2637 |
+
"eval_loss": 0.7939748167991638,
|
2638 |
+
"eval_runtime": 146.5246,
|
2639 |
+
"eval_samples_per_second": 51.452,
|
2640 |
+
"eval_steps_per_second": 6.436,
|
2641 |
+
"step": 18800
|
2642 |
+
},
|
2643 |
+
{
|
2644 |
+
"epoch": 2.66,
|
2645 |
+
"learning_rate": 3.368183102571348e-06,
|
2646 |
+
"loss": 0.6937,
|
2647 |
+
"step": 18850
|
2648 |
+
},
|
2649 |
+
{
|
2650 |
+
"epoch": 2.67,
|
2651 |
+
"learning_rate": 3.2975416784402373e-06,
|
2652 |
+
"loss": 0.6696,
|
2653 |
+
"step": 18900
|
2654 |
+
},
|
2655 |
+
{
|
2656 |
+
"epoch": 2.68,
|
2657 |
+
"learning_rate": 3.226900254309127e-06,
|
2658 |
+
"loss": 0.639,
|
2659 |
+
"step": 18950
|
2660 |
+
},
|
2661 |
+
{
|
2662 |
+
"epoch": 2.68,
|
2663 |
+
"learning_rate": 3.1562588301780164e-06,
|
2664 |
+
"loss": 0.5565,
|
2665 |
+
"step": 19000
|
2666 |
+
},
|
2667 |
+
{
|
2668 |
+
"epoch": 2.69,
|
2669 |
+
"learning_rate": 3.085617406046906e-06,
|
2670 |
+
"loss": 0.4692,
|
2671 |
+
"step": 19050
|
2672 |
+
},
|
2673 |
+
{
|
2674 |
+
"epoch": 2.7,
|
2675 |
+
"learning_rate": 3.0149759819157954e-06,
|
2676 |
+
"loss": 0.5703,
|
2677 |
+
"step": 19100
|
2678 |
+
},
|
2679 |
+
{
|
2680 |
+
"epoch": 2.71,
|
2681 |
+
"learning_rate": 2.944334557784685e-06,
|
2682 |
+
"loss": 0.4944,
|
2683 |
+
"step": 19150
|
2684 |
+
},
|
2685 |
+
{
|
2686 |
+
"epoch": 2.71,
|
2687 |
+
"learning_rate": 2.8736931336535745e-06,
|
2688 |
+
"loss": 0.6101,
|
2689 |
+
"step": 19200
|
2690 |
+
},
|
2691 |
+
{
|
2692 |
+
"epoch": 2.71,
|
2693 |
+
"eval_loss": 0.7930362224578857,
|
2694 |
+
"eval_runtime": 146.3443,
|
2695 |
+
"eval_samples_per_second": 51.515,
|
2696 |
+
"eval_steps_per_second": 6.444,
|
2697 |
+
"step": 19200
|
2698 |
+
},
|
2699 |
+
{
|
2700 |
+
"epoch": 2.72,
|
2701 |
+
"learning_rate": 2.8030517095224643e-06,
|
2702 |
+
"loss": 0.59,
|
2703 |
+
"step": 19250
|
2704 |
+
},
|
2705 |
+
{
|
2706 |
+
"epoch": 2.73,
|
2707 |
+
"learning_rate": 2.7324102853913536e-06,
|
2708 |
+
"loss": 0.5799,
|
2709 |
+
"step": 19300
|
2710 |
+
},
|
2711 |
+
{
|
2712 |
+
"epoch": 2.73,
|
2713 |
+
"learning_rate": 2.6617688612602433e-06,
|
2714 |
+
"loss": 0.5569,
|
2715 |
+
"step": 19350
|
2716 |
+
},
|
2717 |
+
{
|
2718 |
+
"epoch": 2.74,
|
2719 |
+
"learning_rate": 2.5911274371291327e-06,
|
2720 |
+
"loss": 0.5548,
|
2721 |
+
"step": 19400
|
2722 |
+
},
|
2723 |
+
{
|
2724 |
+
"epoch": 2.75,
|
2725 |
+
"learning_rate": 2.5204860129980224e-06,
|
2726 |
+
"loss": 0.5544,
|
2727 |
+
"step": 19450
|
2728 |
+
},
|
2729 |
+
{
|
2730 |
+
"epoch": 2.76,
|
2731 |
+
"learning_rate": 2.4498445888669117e-06,
|
2732 |
+
"loss": 0.6427,
|
2733 |
+
"step": 19500
|
2734 |
+
},
|
2735 |
+
{
|
2736 |
+
"epoch": 2.76,
|
2737 |
+
"learning_rate": 2.3792031647358015e-06,
|
2738 |
+
"loss": 0.5027,
|
2739 |
+
"step": 19550
|
2740 |
+
},
|
2741 |
+
{
|
2742 |
+
"epoch": 2.77,
|
2743 |
+
"learning_rate": 2.308561740604691e-06,
|
2744 |
+
"loss": 0.5696,
|
2745 |
+
"step": 19600
|
2746 |
+
},
|
2747 |
+
{
|
2748 |
+
"epoch": 2.77,
|
2749 |
+
"eval_loss": 0.7890626192092896,
|
2750 |
+
"eval_runtime": 146.5527,
|
2751 |
+
"eval_samples_per_second": 51.442,
|
2752 |
+
"eval_steps_per_second": 6.435,
|
2753 |
+
"step": 19600
|
2754 |
+
},
|
2755 |
+
{
|
2756 |
+
"epoch": 2.78,
|
2757 |
+
"learning_rate": 2.2379203164735806e-06,
|
2758 |
+
"loss": 0.509,
|
2759 |
+
"step": 19650
|
2760 |
+
},
|
2761 |
+
{
|
2762 |
+
"epoch": 2.78,
|
2763 |
+
"learning_rate": 2.1672788923424695e-06,
|
2764 |
+
"loss": 0.5078,
|
2765 |
+
"step": 19700
|
2766 |
+
},
|
2767 |
+
{
|
2768 |
+
"epoch": 2.79,
|
2769 |
+
"learning_rate": 2.096637468211359e-06,
|
2770 |
+
"loss": 0.563,
|
2771 |
+
"step": 19750
|
2772 |
+
},
|
2773 |
+
{
|
2774 |
+
"epoch": 2.8,
|
2775 |
+
"learning_rate": 2.0259960440802485e-06,
|
2776 |
+
"loss": 0.6039,
|
2777 |
+
"step": 19800
|
2778 |
+
},
|
2779 |
+
{
|
2780 |
+
"epoch": 2.8,
|
2781 |
+
"learning_rate": 1.955354619949138e-06,
|
2782 |
+
"loss": 0.5289,
|
2783 |
+
"step": 19850
|
2784 |
+
},
|
2785 |
+
{
|
2786 |
+
"epoch": 2.81,
|
2787 |
+
"learning_rate": 1.8847131958180278e-06,
|
2788 |
+
"loss": 0.5394,
|
2789 |
+
"step": 19900
|
2790 |
+
},
|
2791 |
+
{
|
2792 |
+
"epoch": 2.82,
|
2793 |
+
"learning_rate": 1.8140717716869174e-06,
|
2794 |
+
"loss": 0.6539,
|
2795 |
+
"step": 19950
|
2796 |
+
},
|
2797 |
+
{
|
2798 |
+
"epoch": 2.83,
|
2799 |
+
"learning_rate": 1.743430347555807e-06,
|
2800 |
+
"loss": 0.563,
|
2801 |
+
"step": 20000
|
2802 |
+
},
|
2803 |
+
{
|
2804 |
+
"epoch": 2.83,
|
2805 |
+
"eval_loss": 0.7903943657875061,
|
2806 |
+
"eval_runtime": 146.7425,
|
2807 |
+
"eval_samples_per_second": 51.376,
|
2808 |
+
"eval_steps_per_second": 6.426,
|
2809 |
+
"step": 20000
|
2810 |
+
},
|
2811 |
+
{
|
2812 |
+
"epoch": 2.83,
|
2813 |
+
"learning_rate": 1.6727889234246962e-06,
|
2814 |
+
"loss": 0.5043,
|
2815 |
+
"step": 20050
|
2816 |
+
},
|
2817 |
+
{
|
2818 |
+
"epoch": 2.84,
|
2819 |
+
"learning_rate": 1.6021474992935858e-06,
|
2820 |
+
"loss": 0.5243,
|
2821 |
+
"step": 20100
|
2822 |
+
},
|
2823 |
+
{
|
2824 |
+
"epoch": 2.85,
|
2825 |
+
"learning_rate": 1.5315060751624753e-06,
|
2826 |
+
"loss": 0.6144,
|
2827 |
+
"step": 20150
|
2828 |
+
},
|
2829 |
+
{
|
2830 |
+
"epoch": 2.85,
|
2831 |
+
"learning_rate": 1.4608646510313648e-06,
|
2832 |
+
"loss": 0.5324,
|
2833 |
+
"step": 20200
|
2834 |
+
},
|
2835 |
+
{
|
2836 |
+
"epoch": 2.86,
|
2837 |
+
"learning_rate": 1.3902232269002544e-06,
|
2838 |
+
"loss": 0.5494,
|
2839 |
+
"step": 20250
|
2840 |
+
},
|
2841 |
+
{
|
2842 |
+
"epoch": 2.87,
|
2843 |
+
"learning_rate": 1.319581802769144e-06,
|
2844 |
+
"loss": 0.5302,
|
2845 |
+
"step": 20300
|
2846 |
+
},
|
2847 |
+
{
|
2848 |
+
"epoch": 2.88,
|
2849 |
+
"learning_rate": 1.2489403786380335e-06,
|
2850 |
+
"loss": 0.6458,
|
2851 |
+
"step": 20350
|
2852 |
+
},
|
2853 |
+
{
|
2854 |
+
"epoch": 2.88,
|
2855 |
+
"learning_rate": 1.178298954506923e-06,
|
2856 |
+
"loss": 0.5361,
|
2857 |
+
"step": 20400
|
2858 |
+
},
|
2859 |
+
{
|
2860 |
+
"epoch": 2.88,
|
2861 |
+
"eval_loss": 0.7929331660270691,
|
2862 |
+
"eval_runtime": 146.7924,
|
2863 |
+
"eval_samples_per_second": 51.358,
|
2864 |
+
"eval_steps_per_second": 6.424,
|
2865 |
+
"step": 20400
|
2866 |
+
},
|
2867 |
+
{
|
2868 |
+
"epoch": 2.89,
|
2869 |
+
"learning_rate": 1.1076575303758125e-06,
|
2870 |
+
"loss": 0.5857,
|
2871 |
+
"step": 20450
|
2872 |
+
},
|
2873 |
+
{
|
2874 |
+
"epoch": 2.9,
|
2875 |
+
"learning_rate": 1.037016106244702e-06,
|
2876 |
+
"loss": 0.5542,
|
2877 |
+
"step": 20500
|
2878 |
+
},
|
2879 |
+
{
|
2880 |
+
"epoch": 2.9,
|
2881 |
+
"learning_rate": 9.663746821135916e-07,
|
2882 |
+
"loss": 0.6382,
|
2883 |
+
"step": 20550
|
2884 |
+
},
|
2885 |
+
{
|
2886 |
+
"epoch": 2.91,
|
2887 |
+
"learning_rate": 8.957332579824809e-07,
|
2888 |
+
"loss": 0.5708,
|
2889 |
+
"step": 20600
|
2890 |
+
},
|
2891 |
+
{
|
2892 |
+
"epoch": 2.92,
|
2893 |
+
"learning_rate": 8.250918338513705e-07,
|
2894 |
+
"loss": 0.5726,
|
2895 |
+
"step": 20650
|
2896 |
+
},
|
2897 |
+
{
|
2898 |
+
"epoch": 2.92,
|
2899 |
+
"learning_rate": 7.5445040972026e-07,
|
2900 |
+
"loss": 0.5438,
|
2901 |
+
"step": 20700
|
2902 |
+
},
|
2903 |
+
{
|
2904 |
+
"epoch": 2.93,
|
2905 |
+
"learning_rate": 6.838089855891495e-07,
|
2906 |
+
"loss": 0.5833,
|
2907 |
+
"step": 20750
|
2908 |
+
},
|
2909 |
+
{
|
2910 |
+
"epoch": 2.94,
|
2911 |
+
"learning_rate": 6.13167561458039e-07,
|
2912 |
+
"loss": 0.5654,
|
2913 |
+
"step": 20800
|
2914 |
+
},
|
2915 |
+
{
|
2916 |
+
"epoch": 2.94,
|
2917 |
+
"eval_loss": 0.7940900325775146,
|
2918 |
+
"eval_runtime": 146.3661,
|
2919 |
+
"eval_samples_per_second": 51.508,
|
2920 |
+
"eval_steps_per_second": 6.443,
|
2921 |
+
"step": 20800
|
2922 |
+
},
|
2923 |
+
{
|
2924 |
+
"epoch": 2.95,
|
2925 |
+
"learning_rate": 5.425261373269285e-07,
|
2926 |
+
"loss": 0.5341,
|
2927 |
+
"step": 20850
|
2928 |
+
},
|
2929 |
+
{
|
2930 |
+
"epoch": 2.95,
|
2931 |
+
"learning_rate": 4.7188471319581804e-07,
|
2932 |
+
"loss": 0.5934,
|
2933 |
+
"step": 20900
|
2934 |
+
},
|
2935 |
+
{
|
2936 |
+
"epoch": 2.96,
|
2937 |
+
"learning_rate": 4.012432890647076e-07,
|
2938 |
+
"loss": 0.6293,
|
2939 |
+
"step": 20950
|
2940 |
+
},
|
2941 |
+
{
|
2942 |
+
"epoch": 2.97,
|
2943 |
+
"learning_rate": 3.3060186493359706e-07,
|
2944 |
+
"loss": 0.6117,
|
2945 |
+
"step": 21000
|
2946 |
+
},
|
2947 |
+
{
|
2948 |
+
"epoch": 2.97,
|
2949 |
+
"learning_rate": 2.5996044080248655e-07,
|
2950 |
+
"loss": 0.602,
|
2951 |
+
"step": 21050
|
2952 |
+
},
|
2953 |
+
{
|
2954 |
+
"epoch": 2.98,
|
2955 |
+
"learning_rate": 1.8931901667137608e-07,
|
2956 |
+
"loss": 0.538,
|
2957 |
+
"step": 21100
|
2958 |
+
},
|
2959 |
+
{
|
2960 |
+
"epoch": 2.99,
|
2961 |
+
"learning_rate": 1.1867759254026561e-07,
|
2962 |
+
"loss": 0.5409,
|
2963 |
+
"step": 21150
|
2964 |
+
},
|
2965 |
+
{
|
2966 |
+
"epoch": 3.0,
|
2967 |
+
"learning_rate": 4.803616840915513e-08,
|
2968 |
+
"loss": 0.5808,
|
2969 |
+
"step": 21200
|
2970 |
+
},
|
2971 |
+
{
|
2972 |
+
"epoch": 3.0,
|
2973 |
+
"eval_loss": 0.7935702800750732,
|
2974 |
+
"eval_runtime": 146.4206,
|
2975 |
+
"eval_samples_per_second": 51.489,
|
2976 |
+
"eval_steps_per_second": 6.44,
|
2977 |
+
"step": 21200
|
2978 |
+
},
|
2979 |
+
{
|
2980 |
+
"epoch": 3.0,
|
2981 |
+
"step": 21234,
|
2982 |
+
"total_flos": 9.26174715028439e+16,
|
2983 |
+
"train_loss": 0.9690902242330864,
|
2984 |
+
"train_runtime": 18755.4157,
|
2985 |
+
"train_samples_per_second": 9.056,
|
2986 |
+
"train_steps_per_second": 1.132
|
2987 |
+
}
|
2988 |
+
],
|
2989 |
+
"logging_steps": 50,
|
2990 |
+
"max_steps": 21234,
|
2991 |
+
"num_input_tokens_seen": 0,
|
2992 |
+
"num_train_epochs": 3,
|
2993 |
+
"save_steps": 400,
|
2994 |
+
"total_flos": 9.26174715028439e+16,
|
2995 |
+
"train_batch_size": 8,
|
2996 |
+
"trial_name": null,
|
2997 |
+
"trial_params": null
|
2998 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d46a6887e0a0dfa1c1c1e49e4b35bb53418a0b17f57090b77915de1fe0f56219
|
3 |
+
size 4411
|