add T5 model
Browse files- added_tokens.json +1 -0
- config.json +31 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- rng_state_4.pth +3 -0
- rng_state_5.pth +3 -0
- rng_state_6.pth +3 -0
- rng_state_7.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +1702 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{" <": 32101, " <=": 32100}
|
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/safekeeping/t5-1.1.lm100k/t5.1.1.lm100k.large/pytorch_model/",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 2816,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 1024,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"diversity_penalty": null,
|
11 |
+
"dropout_rate": 0.1,
|
12 |
+
"eos_token_id": 1,
|
13 |
+
"feed_forward_proj": "gated-gelu",
|
14 |
+
"gradient_checkpointing": false,
|
15 |
+
"initializer_factor": 1.0,
|
16 |
+
"is_encoder_decoder": true,
|
17 |
+
"layer_norm_epsilon": 1e-06,
|
18 |
+
"max_length": 512,
|
19 |
+
"model_type": "t5",
|
20 |
+
"num_beams": 4,
|
21 |
+
"num_decoder_layers": 24,
|
22 |
+
"num_heads": 16,
|
23 |
+
"num_layers": 24,
|
24 |
+
"output_past": true,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"relative_attention_num_buckets": 32,
|
27 |
+
"tie_word_embeddings": false,
|
28 |
+
"transformers_version": "4.8.2",
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 32102
|
31 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c654c80aba83fdadba92120cb8c085019ff49904f1179612e1114c39bc23d46a
|
3 |
+
size 5806399
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d80a53d0754ac270c7f7b29fb077ebef654a915d8bd4c23e7823ef34c0510788
|
3 |
+
size 3132653069
|
rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d3d4b8adfd2297bbf6d4ee0d5bf1e22b4d82010b06f492b517adddfb2b5d8b4
|
3 |
+
size 14657
|
rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f354def1210dbd11519acfebbd4164e14e79347d7fa68124a9711cf917e0bd57
|
3 |
+
size 14657
|
rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94d0c6fc7686ed9ecf9662020cb6edb2752ad6af1d6a22bb246239b6d81069c2
|
3 |
+
size 14657
|
rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7bdd81d4cf1ecc28d2066d290117d72ef46ea2cf735e83db8ca49d07e6450dcc
|
3 |
+
size 14657
|
rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:500f63cc677c3436e0c67f69255e1cced8186bb50ed0aa710b06b2b6a77130f0
|
3 |
+
size 14657
|
rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9246f1b4d26a5af1b72ad245a87c8851fc6c58607cd939ea96cfca32f87f0f0
|
3 |
+
size 14657
|
rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b337591d3706f63345f54db1096739ebe3c85a90969296c448abe9360b824ff
|
3 |
+
size 14657
|
rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bab1d4470516cd6478b4782624da02b52b5c0f60a259e5c7ffa44a7a6b8a46aa
|
3 |
+
size 14657
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9aae2a5f0926e2a8e1ac8082e1b2c75c3660f813263ad59913548f00a9ac89f9
|
3 |
+
size 623
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
3 |
+
size 791656
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "name_or_path": "/safekeeping/t5-1.1.lm100k/t5.1.1.lm100k.large/pytorch_model/", "special_tokens_map_file": "/safekeeping/t5-1.1.lm100k/t5.1.1.lm100k.large/pytorch_model/special_tokens_map.json", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}
|
trainer_state.json
ADDED
@@ -0,0 +1,1702 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6963249516441006,
|
3 |
+
"best_model_checkpoint": "/experiments/spider/d6368230-e8a6-4e57-923c-f0938a9bcf7b/checkpoint-1024",
|
4 |
+
"epoch": 341.2922374429224,
|
5 |
+
"global_step": 1024,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.29,
|
12 |
+
"learning_rate": 0.0001,
|
13 |
+
"loss": 3.2183,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.29,
|
18 |
+
"learning_rate": 0.0001,
|
19 |
+
"loss": 2.451,
|
20 |
+
"step": 4
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 2.58,
|
24 |
+
"learning_rate": 0.0001,
|
25 |
+
"loss": 1.2943,
|
26 |
+
"step": 8
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 3.88,
|
30 |
+
"learning_rate": 0.0001,
|
31 |
+
"loss": 0.8542,
|
32 |
+
"step": 12
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 5.29,
|
36 |
+
"learning_rate": 0.0001,
|
37 |
+
"loss": 0.7239,
|
38 |
+
"step": 16
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 6.58,
|
42 |
+
"learning_rate": 0.0001,
|
43 |
+
"loss": 0.5427,
|
44 |
+
"step": 20
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 7.88,
|
48 |
+
"learning_rate": 0.0001,
|
49 |
+
"loss": 0.4532,
|
50 |
+
"step": 24
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 9.29,
|
54 |
+
"learning_rate": 0.0001,
|
55 |
+
"loss": 0.4275,
|
56 |
+
"step": 28
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 10.58,
|
60 |
+
"learning_rate": 0.0001,
|
61 |
+
"loss": 0.3646,
|
62 |
+
"step": 32
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 11.88,
|
66 |
+
"learning_rate": 0.0001,
|
67 |
+
"loss": 0.3155,
|
68 |
+
"step": 36
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 13.29,
|
72 |
+
"learning_rate": 0.0001,
|
73 |
+
"loss": 0.3455,
|
74 |
+
"step": 40
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 14.58,
|
78 |
+
"learning_rate": 0.0001,
|
79 |
+
"loss": 0.2804,
|
80 |
+
"step": 44
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 15.88,
|
84 |
+
"learning_rate": 0.0001,
|
85 |
+
"loss": 0.2518,
|
86 |
+
"step": 48
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 17.29,
|
90 |
+
"learning_rate": 0.0001,
|
91 |
+
"loss": 0.248,
|
92 |
+
"step": 52
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 18.58,
|
96 |
+
"learning_rate": 0.0001,
|
97 |
+
"loss": 0.2021,
|
98 |
+
"step": 56
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 19.88,
|
102 |
+
"learning_rate": 0.0001,
|
103 |
+
"loss": 0.212,
|
104 |
+
"step": 60
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 21.29,
|
108 |
+
"learning_rate": 0.0001,
|
109 |
+
"loss": 0.203,
|
110 |
+
"step": 64
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 21.29,
|
114 |
+
"eval_exact_match": 0.42359767891682787,
|
115 |
+
"eval_exec": 0.4284332688588008,
|
116 |
+
"eval_loss": 0.1833169162273407,
|
117 |
+
"eval_runtime": 682.1232,
|
118 |
+
"eval_samples_per_second": 1.516,
|
119 |
+
"step": 64
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 22.58,
|
123 |
+
"learning_rate": 0.0001,
|
124 |
+
"loss": 0.1895,
|
125 |
+
"step": 68
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 23.88,
|
129 |
+
"learning_rate": 0.0001,
|
130 |
+
"loss": 0.166,
|
131 |
+
"step": 72
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 25.29,
|
135 |
+
"learning_rate": 0.0001,
|
136 |
+
"loss": 0.1833,
|
137 |
+
"step": 76
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 26.58,
|
141 |
+
"learning_rate": 0.0001,
|
142 |
+
"loss": 0.1503,
|
143 |
+
"step": 80
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 27.88,
|
147 |
+
"learning_rate": 0.0001,
|
148 |
+
"loss": 0.1485,
|
149 |
+
"step": 84
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 29.29,
|
153 |
+
"learning_rate": 0.0001,
|
154 |
+
"loss": 0.1574,
|
155 |
+
"step": 88
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 30.58,
|
159 |
+
"learning_rate": 0.0001,
|
160 |
+
"loss": 0.1295,
|
161 |
+
"step": 92
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 31.88,
|
165 |
+
"learning_rate": 0.0001,
|
166 |
+
"loss": 0.1199,
|
167 |
+
"step": 96
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 33.29,
|
171 |
+
"learning_rate": 0.0001,
|
172 |
+
"loss": 0.1262,
|
173 |
+
"step": 100
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 34.58,
|
177 |
+
"learning_rate": 0.0001,
|
178 |
+
"loss": 0.1153,
|
179 |
+
"step": 104
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 35.88,
|
183 |
+
"learning_rate": 0.0001,
|
184 |
+
"loss": 0.1067,
|
185 |
+
"step": 108
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 37.29,
|
189 |
+
"learning_rate": 0.0001,
|
190 |
+
"loss": 0.1086,
|
191 |
+
"step": 112
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 38.58,
|
195 |
+
"learning_rate": 0.0001,
|
196 |
+
"loss": 0.0934,
|
197 |
+
"step": 116
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 39.88,
|
201 |
+
"learning_rate": 0.0001,
|
202 |
+
"loss": 0.096,
|
203 |
+
"step": 120
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 41.29,
|
207 |
+
"learning_rate": 0.0001,
|
208 |
+
"loss": 0.1075,
|
209 |
+
"step": 124
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 42.58,
|
213 |
+
"learning_rate": 0.0001,
|
214 |
+
"loss": 0.0984,
|
215 |
+
"step": 128
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 42.58,
|
219 |
+
"eval_exact_match": 0.5938104448742747,
|
220 |
+
"eval_exec": 0.5764023210831721,
|
221 |
+
"eval_loss": 0.16683875024318695,
|
222 |
+
"eval_runtime": 703.3328,
|
223 |
+
"eval_samples_per_second": 1.47,
|
224 |
+
"step": 128
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 43.88,
|
228 |
+
"learning_rate": 0.0001,
|
229 |
+
"loss": 0.0842,
|
230 |
+
"step": 132
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 45.29,
|
234 |
+
"learning_rate": 0.0001,
|
235 |
+
"loss": 0.0954,
|
236 |
+
"step": 136
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 46.58,
|
240 |
+
"learning_rate": 0.0001,
|
241 |
+
"loss": 0.0842,
|
242 |
+
"step": 140
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 47.88,
|
246 |
+
"learning_rate": 0.0001,
|
247 |
+
"loss": 0.0724,
|
248 |
+
"step": 144
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 49.29,
|
252 |
+
"learning_rate": 0.0001,
|
253 |
+
"loss": 0.0805,
|
254 |
+
"step": 148
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 50.58,
|
258 |
+
"learning_rate": 0.0001,
|
259 |
+
"loss": 0.0745,
|
260 |
+
"step": 152
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 51.88,
|
264 |
+
"learning_rate": 0.0001,
|
265 |
+
"loss": 0.0685,
|
266 |
+
"step": 156
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 53.29,
|
270 |
+
"learning_rate": 0.0001,
|
271 |
+
"loss": 0.0709,
|
272 |
+
"step": 160
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 54.58,
|
276 |
+
"learning_rate": 0.0001,
|
277 |
+
"loss": 0.0744,
|
278 |
+
"step": 164
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 55.88,
|
282 |
+
"learning_rate": 0.0001,
|
283 |
+
"loss": 0.0603,
|
284 |
+
"step": 168
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 57.29,
|
288 |
+
"learning_rate": 0.0001,
|
289 |
+
"loss": 0.0607,
|
290 |
+
"step": 172
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 58.58,
|
294 |
+
"learning_rate": 0.0001,
|
295 |
+
"loss": 0.0652,
|
296 |
+
"step": 176
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 59.88,
|
300 |
+
"learning_rate": 0.0001,
|
301 |
+
"loss": 0.0592,
|
302 |
+
"step": 180
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 61.29,
|
306 |
+
"learning_rate": 0.0001,
|
307 |
+
"loss": 0.0584,
|
308 |
+
"step": 184
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 62.58,
|
312 |
+
"learning_rate": 0.0001,
|
313 |
+
"loss": 0.0507,
|
314 |
+
"step": 188
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 63.88,
|
318 |
+
"learning_rate": 0.0001,
|
319 |
+
"loss": 0.0523,
|
320 |
+
"step": 192
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 63.88,
|
324 |
+
"eval_exact_match": 0.6266924564796905,
|
325 |
+
"eval_exec": 0.620889748549323,
|
326 |
+
"eval_loss": 0.16735364496707916,
|
327 |
+
"eval_runtime": 843.3561,
|
328 |
+
"eval_samples_per_second": 1.226,
|
329 |
+
"step": 192
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 65.29,
|
333 |
+
"learning_rate": 0.0001,
|
334 |
+
"loss": 0.0576,
|
335 |
+
"step": 196
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 66.58,
|
339 |
+
"learning_rate": 0.0001,
|
340 |
+
"loss": 0.0539,
|
341 |
+
"step": 200
|
342 |
+
},
|
343 |
+
{
|
344 |
+
"epoch": 67.88,
|
345 |
+
"learning_rate": 0.0001,
|
346 |
+
"loss": 0.0443,
|
347 |
+
"step": 204
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 69.29,
|
351 |
+
"learning_rate": 0.0001,
|
352 |
+
"loss": 0.0518,
|
353 |
+
"step": 208
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 70.58,
|
357 |
+
"learning_rate": 0.0001,
|
358 |
+
"loss": 0.0435,
|
359 |
+
"step": 212
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 71.88,
|
363 |
+
"learning_rate": 0.0001,
|
364 |
+
"loss": 0.0428,
|
365 |
+
"step": 216
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 73.29,
|
369 |
+
"learning_rate": 0.0001,
|
370 |
+
"loss": 0.043,
|
371 |
+
"step": 220
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 74.58,
|
375 |
+
"learning_rate": 0.0001,
|
376 |
+
"loss": 0.0383,
|
377 |
+
"step": 224
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 75.88,
|
381 |
+
"learning_rate": 0.0001,
|
382 |
+
"loss": 0.0399,
|
383 |
+
"step": 228
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 77.29,
|
387 |
+
"learning_rate": 0.0001,
|
388 |
+
"loss": 0.0422,
|
389 |
+
"step": 232
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 78.58,
|
393 |
+
"learning_rate": 0.0001,
|
394 |
+
"loss": 0.0357,
|
395 |
+
"step": 236
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 79.88,
|
399 |
+
"learning_rate": 0.0001,
|
400 |
+
"loss": 0.0346,
|
401 |
+
"step": 240
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 81.29,
|
405 |
+
"learning_rate": 0.0001,
|
406 |
+
"loss": 0.0433,
|
407 |
+
"step": 244
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"epoch": 82.58,
|
411 |
+
"learning_rate": 0.0001,
|
412 |
+
"loss": 0.0339,
|
413 |
+
"step": 248
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 83.88,
|
417 |
+
"learning_rate": 0.0001,
|
418 |
+
"loss": 0.0353,
|
419 |
+
"step": 252
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 85.29,
|
423 |
+
"learning_rate": 0.0001,
|
424 |
+
"loss": 0.0326,
|
425 |
+
"step": 256
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 85.29,
|
429 |
+
"eval_exact_match": 0.6586073500967118,
|
430 |
+
"eval_exec": 0.6450676982591876,
|
431 |
+
"eval_loss": 0.21498563885688782,
|
432 |
+
"eval_runtime": 824.5584,
|
433 |
+
"eval_samples_per_second": 1.254,
|
434 |
+
"step": 256
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 86.58,
|
438 |
+
"learning_rate": 0.0001,
|
439 |
+
"loss": 0.0301,
|
440 |
+
"step": 260
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 87.88,
|
444 |
+
"learning_rate": 0.0001,
|
445 |
+
"loss": 0.0302,
|
446 |
+
"step": 264
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 89.29,
|
450 |
+
"learning_rate": 0.0001,
|
451 |
+
"loss": 0.0322,
|
452 |
+
"step": 268
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 90.58,
|
456 |
+
"learning_rate": 0.0001,
|
457 |
+
"loss": 0.0248,
|
458 |
+
"step": 272
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 91.88,
|
462 |
+
"learning_rate": 0.0001,
|
463 |
+
"loss": 0.026,
|
464 |
+
"step": 276
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 93.29,
|
468 |
+
"learning_rate": 0.0001,
|
469 |
+
"loss": 0.0297,
|
470 |
+
"step": 280
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 94.58,
|
474 |
+
"learning_rate": 0.0001,
|
475 |
+
"loss": 0.0276,
|
476 |
+
"step": 284
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 95.88,
|
480 |
+
"learning_rate": 0.0001,
|
481 |
+
"loss": 0.0253,
|
482 |
+
"step": 288
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 97.29,
|
486 |
+
"learning_rate": 0.0001,
|
487 |
+
"loss": 0.0282,
|
488 |
+
"step": 292
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 98.58,
|
492 |
+
"learning_rate": 0.0001,
|
493 |
+
"loss": 0.0252,
|
494 |
+
"step": 296
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 99.88,
|
498 |
+
"learning_rate": 0.0001,
|
499 |
+
"loss": 0.0234,
|
500 |
+
"step": 300
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 101.29,
|
504 |
+
"learning_rate": 0.0001,
|
505 |
+
"loss": 0.0225,
|
506 |
+
"step": 304
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 102.58,
|
510 |
+
"learning_rate": 0.0001,
|
511 |
+
"loss": 0.0254,
|
512 |
+
"step": 308
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 103.88,
|
516 |
+
"learning_rate": 0.0001,
|
517 |
+
"loss": 0.0201,
|
518 |
+
"step": 312
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 105.29,
|
522 |
+
"learning_rate": 0.0001,
|
523 |
+
"loss": 0.022,
|
524 |
+
"step": 316
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 106.58,
|
528 |
+
"learning_rate": 0.0001,
|
529 |
+
"loss": 0.0206,
|
530 |
+
"step": 320
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 106.58,
|
534 |
+
"eval_exact_match": 0.6644100580270793,
|
535 |
+
"eval_exec": 0.6499032882011605,
|
536 |
+
"eval_loss": 0.21441736817359924,
|
537 |
+
"eval_runtime": 835.4598,
|
538 |
+
"eval_samples_per_second": 1.238,
|
539 |
+
"step": 320
|
540 |
+
},
|
541 |
+
{
|
542 |
+
"epoch": 107.88,
|
543 |
+
"learning_rate": 0.0001,
|
544 |
+
"loss": 0.0178,
|
545 |
+
"step": 324
|
546 |
+
},
|
547 |
+
{
|
548 |
+
"epoch": 109.29,
|
549 |
+
"learning_rate": 0.0001,
|
550 |
+
"loss": 0.0172,
|
551 |
+
"step": 328
|
552 |
+
},
|
553 |
+
{
|
554 |
+
"epoch": 110.58,
|
555 |
+
"learning_rate": 0.0001,
|
556 |
+
"loss": 0.0175,
|
557 |
+
"step": 332
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 111.88,
|
561 |
+
"learning_rate": 0.0001,
|
562 |
+
"loss": 0.0155,
|
563 |
+
"step": 336
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 113.29,
|
567 |
+
"learning_rate": 0.0001,
|
568 |
+
"loss": 0.0187,
|
569 |
+
"step": 340
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 114.58,
|
573 |
+
"learning_rate": 0.0001,
|
574 |
+
"loss": 0.0142,
|
575 |
+
"step": 344
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"epoch": 115.88,
|
579 |
+
"learning_rate": 0.0001,
|
580 |
+
"loss": 0.0149,
|
581 |
+
"step": 348
|
582 |
+
},
|
583 |
+
{
|
584 |
+
"epoch": 117.29,
|
585 |
+
"learning_rate": 0.0001,
|
586 |
+
"loss": 0.0155,
|
587 |
+
"step": 352
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 118.58,
|
591 |
+
"learning_rate": 0.0001,
|
592 |
+
"loss": 0.0148,
|
593 |
+
"step": 356
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 119.88,
|
597 |
+
"learning_rate": 0.0001,
|
598 |
+
"loss": 0.0138,
|
599 |
+
"step": 360
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 121.29,
|
603 |
+
"learning_rate": 0.0001,
|
604 |
+
"loss": 0.0154,
|
605 |
+
"step": 364
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 122.58,
|
609 |
+
"learning_rate": 0.0001,
|
610 |
+
"loss": 0.0145,
|
611 |
+
"step": 368
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 123.88,
|
615 |
+
"learning_rate": 0.0001,
|
616 |
+
"loss": 0.0172,
|
617 |
+
"step": 372
|
618 |
+
},
|
619 |
+
{
|
620 |
+
"epoch": 125.29,
|
621 |
+
"learning_rate": 0.0001,
|
622 |
+
"loss": 0.0146,
|
623 |
+
"step": 376
|
624 |
+
},
|
625 |
+
{
|
626 |
+
"epoch": 126.58,
|
627 |
+
"learning_rate": 0.0001,
|
628 |
+
"loss": 0.0156,
|
629 |
+
"step": 380
|
630 |
+
},
|
631 |
+
{
|
632 |
+
"epoch": 127.88,
|
633 |
+
"learning_rate": 0.0001,
|
634 |
+
"loss": 0.0177,
|
635 |
+
"step": 384
|
636 |
+
},
|
637 |
+
{
|
638 |
+
"epoch": 127.88,
|
639 |
+
"eval_exact_match": 0.6682785299806576,
|
640 |
+
"eval_exec": 0.6518375241779497,
|
641 |
+
"eval_loss": 0.24249066412448883,
|
642 |
+
"eval_runtime": 822.9024,
|
643 |
+
"eval_samples_per_second": 1.257,
|
644 |
+
"step": 384
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 129.29,
|
648 |
+
"learning_rate": 0.0001,
|
649 |
+
"loss": 0.0134,
|
650 |
+
"step": 388
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 130.58,
|
654 |
+
"learning_rate": 0.0001,
|
655 |
+
"loss": 0.0119,
|
656 |
+
"step": 392
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 131.88,
|
660 |
+
"learning_rate": 0.0001,
|
661 |
+
"loss": 0.01,
|
662 |
+
"step": 396
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 133.29,
|
666 |
+
"learning_rate": 0.0001,
|
667 |
+
"loss": 0.0105,
|
668 |
+
"step": 400
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 134.58,
|
672 |
+
"learning_rate": 0.0001,
|
673 |
+
"loss": 0.0086,
|
674 |
+
"step": 404
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 135.88,
|
678 |
+
"learning_rate": 0.0001,
|
679 |
+
"loss": 0.0118,
|
680 |
+
"step": 408
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 137.29,
|
684 |
+
"learning_rate": 0.0001,
|
685 |
+
"loss": 0.01,
|
686 |
+
"step": 412
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 138.58,
|
690 |
+
"learning_rate": 0.0001,
|
691 |
+
"loss": 0.0102,
|
692 |
+
"step": 416
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 139.88,
|
696 |
+
"learning_rate": 0.0001,
|
697 |
+
"loss": 0.0106,
|
698 |
+
"step": 420
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 141.29,
|
702 |
+
"learning_rate": 0.0001,
|
703 |
+
"loss": 0.0087,
|
704 |
+
"step": 424
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 142.58,
|
708 |
+
"learning_rate": 0.0001,
|
709 |
+
"loss": 0.0089,
|
710 |
+
"step": 428
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 143.88,
|
714 |
+
"learning_rate": 0.0001,
|
715 |
+
"loss": 0.0099,
|
716 |
+
"step": 432
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 145.29,
|
720 |
+
"learning_rate": 0.0001,
|
721 |
+
"loss": 0.0092,
|
722 |
+
"step": 436
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 146.58,
|
726 |
+
"learning_rate": 0.0001,
|
727 |
+
"loss": 0.0081,
|
728 |
+
"step": 440
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 147.88,
|
732 |
+
"learning_rate": 0.0001,
|
733 |
+
"loss": 0.0088,
|
734 |
+
"step": 444
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 149.29,
|
738 |
+
"learning_rate": 0.0001,
|
739 |
+
"loss": 0.0079,
|
740 |
+
"step": 448
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 149.29,
|
744 |
+
"eval_exact_match": 0.6499032882011605,
|
745 |
+
"eval_exec": 0.6353965183752418,
|
746 |
+
"eval_loss": 0.2822052538394928,
|
747 |
+
"eval_runtime": 813.617,
|
748 |
+
"eval_samples_per_second": 1.271,
|
749 |
+
"step": 448
|
750 |
+
},
|
751 |
+
{
|
752 |
+
"epoch": 150.58,
|
753 |
+
"learning_rate": 0.0001,
|
754 |
+
"loss": 0.0077,
|
755 |
+
"step": 452
|
756 |
+
},
|
757 |
+
{
|
758 |
+
"epoch": 151.88,
|
759 |
+
"learning_rate": 0.0001,
|
760 |
+
"loss": 0.0075,
|
761 |
+
"step": 456
|
762 |
+
},
|
763 |
+
{
|
764 |
+
"epoch": 153.29,
|
765 |
+
"learning_rate": 0.0001,
|
766 |
+
"loss": 0.0071,
|
767 |
+
"step": 460
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 154.58,
|
771 |
+
"learning_rate": 0.0001,
|
772 |
+
"loss": 0.008,
|
773 |
+
"step": 464
|
774 |
+
},
|
775 |
+
{
|
776 |
+
"epoch": 155.88,
|
777 |
+
"learning_rate": 0.0001,
|
778 |
+
"loss": 0.0063,
|
779 |
+
"step": 468
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 157.29,
|
783 |
+
"learning_rate": 0.0001,
|
784 |
+
"loss": 0.0078,
|
785 |
+
"step": 472
|
786 |
+
},
|
787 |
+
{
|
788 |
+
"epoch": 158.58,
|
789 |
+
"learning_rate": 0.0001,
|
790 |
+
"loss": 0.0069,
|
791 |
+
"step": 476
|
792 |
+
},
|
793 |
+
{
|
794 |
+
"epoch": 159.88,
|
795 |
+
"learning_rate": 0.0001,
|
796 |
+
"loss": 0.0073,
|
797 |
+
"step": 480
|
798 |
+
},
|
799 |
+
{
|
800 |
+
"epoch": 161.29,
|
801 |
+
"learning_rate": 0.0001,
|
802 |
+
"loss": 0.0111,
|
803 |
+
"step": 484
|
804 |
+
},
|
805 |
+
{
|
806 |
+
"epoch": 162.58,
|
807 |
+
"learning_rate": 0.0001,
|
808 |
+
"loss": 0.0063,
|
809 |
+
"step": 488
|
810 |
+
},
|
811 |
+
{
|
812 |
+
"epoch": 163.88,
|
813 |
+
"learning_rate": 0.0001,
|
814 |
+
"loss": 0.0078,
|
815 |
+
"step": 492
|
816 |
+
},
|
817 |
+
{
|
818 |
+
"epoch": 165.29,
|
819 |
+
"learning_rate": 0.0001,
|
820 |
+
"loss": 0.0121,
|
821 |
+
"step": 496
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 166.58,
|
825 |
+
"learning_rate": 0.0001,
|
826 |
+
"loss": 0.0086,
|
827 |
+
"step": 500
|
828 |
+
},
|
829 |
+
{
|
830 |
+
"epoch": 167.88,
|
831 |
+
"learning_rate": 0.0001,
|
832 |
+
"loss": 0.0066,
|
833 |
+
"step": 504
|
834 |
+
},
|
835 |
+
{
|
836 |
+
"epoch": 169.29,
|
837 |
+
"learning_rate": 0.0001,
|
838 |
+
"loss": 0.0064,
|
839 |
+
"step": 508
|
840 |
+
},
|
841 |
+
{
|
842 |
+
"epoch": 170.58,
|
843 |
+
"learning_rate": 0.0001,
|
844 |
+
"loss": 0.0046,
|
845 |
+
"step": 512
|
846 |
+
},
|
847 |
+
{
|
848 |
+
"epoch": 170.58,
|
849 |
+
"eval_exact_match": 0.660541586073501,
|
850 |
+
"eval_exec": 0.6479690522243714,
|
851 |
+
"eval_loss": 0.29858535528182983,
|
852 |
+
"eval_runtime": 852.1163,
|
853 |
+
"eval_samples_per_second": 1.213,
|
854 |
+
"step": 512
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 171.88,
|
858 |
+
"learning_rate": 0.0001,
|
859 |
+
"loss": 0.0051,
|
860 |
+
"step": 516
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 173.29,
|
864 |
+
"learning_rate": 0.0001,
|
865 |
+
"loss": 0.0053,
|
866 |
+
"step": 520
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 174.58,
|
870 |
+
"learning_rate": 0.0001,
|
871 |
+
"loss": 0.0054,
|
872 |
+
"step": 524
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 175.88,
|
876 |
+
"learning_rate": 0.0001,
|
877 |
+
"loss": 0.0052,
|
878 |
+
"step": 528
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 177.29,
|
882 |
+
"learning_rate": 0.0001,
|
883 |
+
"loss": 0.0051,
|
884 |
+
"step": 532
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 178.58,
|
888 |
+
"learning_rate": 0.0001,
|
889 |
+
"loss": 0.0043,
|
890 |
+
"step": 536
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"epoch": 179.88,
|
894 |
+
"learning_rate": 0.0001,
|
895 |
+
"loss": 0.0047,
|
896 |
+
"step": 540
|
897 |
+
},
|
898 |
+
{
|
899 |
+
"epoch": 181.29,
|
900 |
+
"learning_rate": 0.0001,
|
901 |
+
"loss": 0.0051,
|
902 |
+
"step": 544
|
903 |
+
},
|
904 |
+
{
|
905 |
+
"epoch": 182.58,
|
906 |
+
"learning_rate": 0.0001,
|
907 |
+
"loss": 0.0164,
|
908 |
+
"step": 548
|
909 |
+
},
|
910 |
+
{
|
911 |
+
"epoch": 183.88,
|
912 |
+
"learning_rate": 0.0001,
|
913 |
+
"loss": 0.0044,
|
914 |
+
"step": 552
|
915 |
+
},
|
916 |
+
{
|
917 |
+
"epoch": 185.29,
|
918 |
+
"learning_rate": 0.0001,
|
919 |
+
"loss": 0.0048,
|
920 |
+
"step": 556
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 186.58,
|
924 |
+
"learning_rate": 0.0001,
|
925 |
+
"loss": 0.0038,
|
926 |
+
"step": 560
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 187.88,
|
930 |
+
"learning_rate": 0.0001,
|
931 |
+
"loss": 0.0033,
|
932 |
+
"step": 564
|
933 |
+
},
|
934 |
+
{
|
935 |
+
"epoch": 189.29,
|
936 |
+
"learning_rate": 0.0001,
|
937 |
+
"loss": 0.0041,
|
938 |
+
"step": 568
|
939 |
+
},
|
940 |
+
{
|
941 |
+
"epoch": 190.58,
|
942 |
+
"learning_rate": 0.0001,
|
943 |
+
"loss": 0.0038,
|
944 |
+
"step": 572
|
945 |
+
},
|
946 |
+
{
|
947 |
+
"epoch": 191.88,
|
948 |
+
"learning_rate": 0.0001,
|
949 |
+
"loss": 0.0044,
|
950 |
+
"step": 576
|
951 |
+
},
|
952 |
+
{
|
953 |
+
"epoch": 191.88,
|
954 |
+
"eval_exact_match": 0.6663442940038685,
|
955 |
+
"eval_exec": 0.6479690522243714,
|
956 |
+
"eval_loss": 0.3111841380596161,
|
957 |
+
"eval_runtime": 837.4186,
|
958 |
+
"eval_samples_per_second": 1.235,
|
959 |
+
"step": 576
|
960 |
+
},
|
961 |
+
{
|
962 |
+
"epoch": 193.29,
|
963 |
+
"learning_rate": 0.0001,
|
964 |
+
"loss": 0.0045,
|
965 |
+
"step": 580
|
966 |
+
},
|
967 |
+
{
|
968 |
+
"epoch": 194.58,
|
969 |
+
"learning_rate": 0.0001,
|
970 |
+
"loss": 0.0027,
|
971 |
+
"step": 584
|
972 |
+
},
|
973 |
+
{
|
974 |
+
"epoch": 195.88,
|
975 |
+
"learning_rate": 0.0001,
|
976 |
+
"loss": 0.0024,
|
977 |
+
"step": 588
|
978 |
+
},
|
979 |
+
{
|
980 |
+
"epoch": 197.29,
|
981 |
+
"learning_rate": 0.0001,
|
982 |
+
"loss": 0.0034,
|
983 |
+
"step": 592
|
984 |
+
},
|
985 |
+
{
|
986 |
+
"epoch": 198.58,
|
987 |
+
"learning_rate": 0.0001,
|
988 |
+
"loss": 0.0037,
|
989 |
+
"step": 596
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 199.88,
|
993 |
+
"learning_rate": 0.0001,
|
994 |
+
"loss": 0.0037,
|
995 |
+
"step": 600
|
996 |
+
},
|
997 |
+
{
|
998 |
+
"epoch": 201.29,
|
999 |
+
"learning_rate": 0.0001,
|
1000 |
+
"loss": 0.0036,
|
1001 |
+
"step": 604
|
1002 |
+
},
|
1003 |
+
{
|
1004 |
+
"epoch": 202.58,
|
1005 |
+
"learning_rate": 0.0001,
|
1006 |
+
"loss": 0.0029,
|
1007 |
+
"step": 608
|
1008 |
+
},
|
1009 |
+
{
|
1010 |
+
"epoch": 203.88,
|
1011 |
+
"learning_rate": 0.0001,
|
1012 |
+
"loss": 0.0019,
|
1013 |
+
"step": 612
|
1014 |
+
},
|
1015 |
+
{
|
1016 |
+
"epoch": 205.29,
|
1017 |
+
"learning_rate": 0.0001,
|
1018 |
+
"loss": 0.0028,
|
1019 |
+
"step": 616
|
1020 |
+
},
|
1021 |
+
{
|
1022 |
+
"epoch": 206.58,
|
1023 |
+
"learning_rate": 0.0001,
|
1024 |
+
"loss": 0.0038,
|
1025 |
+
"step": 620
|
1026 |
+
},
|
1027 |
+
{
|
1028 |
+
"epoch": 207.88,
|
1029 |
+
"learning_rate": 0.0001,
|
1030 |
+
"loss": 0.003,
|
1031 |
+
"step": 624
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 209.29,
|
1035 |
+
"learning_rate": 0.0001,
|
1036 |
+
"loss": 0.0033,
|
1037 |
+
"step": 628
|
1038 |
+
},
|
1039 |
+
{
|
1040 |
+
"epoch": 210.58,
|
1041 |
+
"learning_rate": 0.0001,
|
1042 |
+
"loss": 0.0028,
|
1043 |
+
"step": 632
|
1044 |
+
},
|
1045 |
+
{
|
1046 |
+
"epoch": 211.88,
|
1047 |
+
"learning_rate": 0.0001,
|
1048 |
+
"loss": 0.0028,
|
1049 |
+
"step": 636
|
1050 |
+
},
|
1051 |
+
{
|
1052 |
+
"epoch": 213.29,
|
1053 |
+
"learning_rate": 0.0001,
|
1054 |
+
"loss": 0.0025,
|
1055 |
+
"step": 640
|
1056 |
+
},
|
1057 |
+
{
|
1058 |
+
"epoch": 213.29,
|
1059 |
+
"eval_exact_match": 0.660541586073501,
|
1060 |
+
"eval_exec": 0.648936170212766,
|
1061 |
+
"eval_loss": 0.3557709753513336,
|
1062 |
+
"eval_runtime": 807.1499,
|
1063 |
+
"eval_samples_per_second": 1.281,
|
1064 |
+
"step": 640
|
1065 |
+
},
|
1066 |
+
{
|
1067 |
+
"epoch": 214.58,
|
1068 |
+
"learning_rate": 0.0001,
|
1069 |
+
"loss": 0.0024,
|
1070 |
+
"step": 644
|
1071 |
+
},
|
1072 |
+
{
|
1073 |
+
"epoch": 215.88,
|
1074 |
+
"learning_rate": 0.0001,
|
1075 |
+
"loss": 0.0034,
|
1076 |
+
"step": 648
|
1077 |
+
},
|
1078 |
+
{
|
1079 |
+
"epoch": 217.29,
|
1080 |
+
"learning_rate": 0.0001,
|
1081 |
+
"loss": 0.0023,
|
1082 |
+
"step": 652
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 218.58,
|
1086 |
+
"learning_rate": 0.0001,
|
1087 |
+
"loss": 0.0021,
|
1088 |
+
"step": 656
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 219.88,
|
1092 |
+
"learning_rate": 0.0001,
|
1093 |
+
"loss": 0.0026,
|
1094 |
+
"step": 660
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 221.29,
|
1098 |
+
"learning_rate": 0.0001,
|
1099 |
+
"loss": 0.0035,
|
1100 |
+
"step": 664
|
1101 |
+
},
|
1102 |
+
{
|
1103 |
+
"epoch": 222.58,
|
1104 |
+
"learning_rate": 0.0001,
|
1105 |
+
"loss": 0.0022,
|
1106 |
+
"step": 668
|
1107 |
+
},
|
1108 |
+
{
|
1109 |
+
"epoch": 223.88,
|
1110 |
+
"learning_rate": 0.0001,
|
1111 |
+
"loss": 0.002,
|
1112 |
+
"step": 672
|
1113 |
+
},
|
1114 |
+
{
|
1115 |
+
"epoch": 225.29,
|
1116 |
+
"learning_rate": 0.0001,
|
1117 |
+
"loss": 0.0029,
|
1118 |
+
"step": 676
|
1119 |
+
},
|
1120 |
+
{
|
1121 |
+
"epoch": 226.58,
|
1122 |
+
"learning_rate": 0.0001,
|
1123 |
+
"loss": 0.0029,
|
1124 |
+
"step": 680
|
1125 |
+
},
|
1126 |
+
{
|
1127 |
+
"epoch": 227.88,
|
1128 |
+
"learning_rate": 0.0001,
|
1129 |
+
"loss": 0.0058,
|
1130 |
+
"step": 684
|
1131 |
+
},
|
1132 |
+
{
|
1133 |
+
"epoch": 229.29,
|
1134 |
+
"learning_rate": 0.0001,
|
1135 |
+
"loss": 0.0085,
|
1136 |
+
"step": 688
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 230.58,
|
1140 |
+
"learning_rate": 0.0001,
|
1141 |
+
"loss": 0.0049,
|
1142 |
+
"step": 692
|
1143 |
+
},
|
1144 |
+
{
|
1145 |
+
"epoch": 231.88,
|
1146 |
+
"learning_rate": 0.0001,
|
1147 |
+
"loss": 0.0026,
|
1148 |
+
"step": 696
|
1149 |
+
},
|
1150 |
+
{
|
1151 |
+
"epoch": 233.29,
|
1152 |
+
"learning_rate": 0.0001,
|
1153 |
+
"loss": 0.0028,
|
1154 |
+
"step": 700
|
1155 |
+
},
|
1156 |
+
{
|
1157 |
+
"epoch": 234.58,
|
1158 |
+
"learning_rate": 0.0001,
|
1159 |
+
"loss": 0.0026,
|
1160 |
+
"step": 704
|
1161 |
+
},
|
1162 |
+
{
|
1163 |
+
"epoch": 234.58,
|
1164 |
+
"eval_exact_match": 0.6682785299806576,
|
1165 |
+
"eval_exec": 0.6528046421663443,
|
1166 |
+
"eval_loss": 0.34394705295562744,
|
1167 |
+
"eval_runtime": 890.2876,
|
1168 |
+
"eval_samples_per_second": 1.161,
|
1169 |
+
"step": 704
|
1170 |
+
},
|
1171 |
+
{
|
1172 |
+
"epoch": 235.88,
|
1173 |
+
"learning_rate": 0.0001,
|
1174 |
+
"loss": 0.0019,
|
1175 |
+
"step": 708
|
1176 |
+
},
|
1177 |
+
{
|
1178 |
+
"epoch": 237.29,
|
1179 |
+
"learning_rate": 0.0001,
|
1180 |
+
"loss": 0.003,
|
1181 |
+
"step": 712
|
1182 |
+
},
|
1183 |
+
{
|
1184 |
+
"epoch": 238.58,
|
1185 |
+
"learning_rate": 0.0001,
|
1186 |
+
"loss": 0.0027,
|
1187 |
+
"step": 716
|
1188 |
+
},
|
1189 |
+
{
|
1190 |
+
"epoch": 239.88,
|
1191 |
+
"learning_rate": 0.0001,
|
1192 |
+
"loss": 0.0021,
|
1193 |
+
"step": 720
|
1194 |
+
},
|
1195 |
+
{
|
1196 |
+
"epoch": 241.29,
|
1197 |
+
"learning_rate": 0.0001,
|
1198 |
+
"loss": 0.0023,
|
1199 |
+
"step": 724
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 242.58,
|
1203 |
+
"learning_rate": 0.0001,
|
1204 |
+
"loss": 0.0017,
|
1205 |
+
"step": 728
|
1206 |
+
},
|
1207 |
+
{
|
1208 |
+
"epoch": 243.88,
|
1209 |
+
"learning_rate": 0.0001,
|
1210 |
+
"loss": 0.0018,
|
1211 |
+
"step": 732
|
1212 |
+
},
|
1213 |
+
{
|
1214 |
+
"epoch": 245.29,
|
1215 |
+
"learning_rate": 0.0001,
|
1216 |
+
"loss": 0.0028,
|
1217 |
+
"step": 736
|
1218 |
+
},
|
1219 |
+
{
|
1220 |
+
"epoch": 246.58,
|
1221 |
+
"learning_rate": 0.0001,
|
1222 |
+
"loss": 0.0058,
|
1223 |
+
"step": 740
|
1224 |
+
},
|
1225 |
+
{
|
1226 |
+
"epoch": 247.88,
|
1227 |
+
"learning_rate": 0.0001,
|
1228 |
+
"loss": 0.0021,
|
1229 |
+
"step": 744
|
1230 |
+
},
|
1231 |
+
{
|
1232 |
+
"epoch": 249.29,
|
1233 |
+
"learning_rate": 0.0001,
|
1234 |
+
"loss": 0.0023,
|
1235 |
+
"step": 748
|
1236 |
+
},
|
1237 |
+
{
|
1238 |
+
"epoch": 250.58,
|
1239 |
+
"learning_rate": 0.0001,
|
1240 |
+
"loss": 0.003,
|
1241 |
+
"step": 752
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 251.88,
|
1245 |
+
"learning_rate": 0.0001,
|
1246 |
+
"loss": 0.0027,
|
1247 |
+
"step": 756
|
1248 |
+
},
|
1249 |
+
{
|
1250 |
+
"epoch": 253.29,
|
1251 |
+
"learning_rate": 0.0001,
|
1252 |
+
"loss": 0.0029,
|
1253 |
+
"step": 760
|
1254 |
+
},
|
1255 |
+
{
|
1256 |
+
"epoch": 254.58,
|
1257 |
+
"learning_rate": 0.0001,
|
1258 |
+
"loss": 0.0023,
|
1259 |
+
"step": 764
|
1260 |
+
},
|
1261 |
+
{
|
1262 |
+
"epoch": 255.88,
|
1263 |
+
"learning_rate": 0.0001,
|
1264 |
+
"loss": 0.0017,
|
1265 |
+
"step": 768
|
1266 |
+
},
|
1267 |
+
{
|
1268 |
+
"epoch": 255.88,
|
1269 |
+
"eval_exact_match": 0.6702127659574468,
|
1270 |
+
"eval_exec": 0.6576402321083172,
|
1271 |
+
"eval_loss": 0.3505505919456482,
|
1272 |
+
"eval_runtime": 849.5769,
|
1273 |
+
"eval_samples_per_second": 1.217,
|
1274 |
+
"step": 768
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"epoch": 257.29,
|
1278 |
+
"learning_rate": 0.0001,
|
1279 |
+
"loss": 0.0014,
|
1280 |
+
"step": 772
|
1281 |
+
},
|
1282 |
+
{
|
1283 |
+
"epoch": 258.58,
|
1284 |
+
"learning_rate": 0.0001,
|
1285 |
+
"loss": 0.0017,
|
1286 |
+
"step": 776
|
1287 |
+
},
|
1288 |
+
{
|
1289 |
+
"epoch": 259.88,
|
1290 |
+
"learning_rate": 0.0001,
|
1291 |
+
"loss": 0.0023,
|
1292 |
+
"step": 780
|
1293 |
+
},
|
1294 |
+
{
|
1295 |
+
"epoch": 261.29,
|
1296 |
+
"learning_rate": 0.0001,
|
1297 |
+
"loss": 0.0031,
|
1298 |
+
"step": 784
|
1299 |
+
},
|
1300 |
+
{
|
1301 |
+
"epoch": 262.58,
|
1302 |
+
"learning_rate": 0.0001,
|
1303 |
+
"loss": 0.0015,
|
1304 |
+
"step": 788
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 263.88,
|
1308 |
+
"learning_rate": 0.0001,
|
1309 |
+
"loss": 0.0018,
|
1310 |
+
"step": 792
|
1311 |
+
},
|
1312 |
+
{
|
1313 |
+
"epoch": 265.29,
|
1314 |
+
"learning_rate": 0.0001,
|
1315 |
+
"loss": 0.0019,
|
1316 |
+
"step": 796
|
1317 |
+
},
|
1318 |
+
{
|
1319 |
+
"epoch": 266.58,
|
1320 |
+
"learning_rate": 0.0001,
|
1321 |
+
"loss": 0.0017,
|
1322 |
+
"step": 800
|
1323 |
+
},
|
1324 |
+
{
|
1325 |
+
"epoch": 267.88,
|
1326 |
+
"learning_rate": 0.0001,
|
1327 |
+
"loss": 0.0019,
|
1328 |
+
"step": 804
|
1329 |
+
},
|
1330 |
+
{
|
1331 |
+
"epoch": 269.29,
|
1332 |
+
"learning_rate": 0.0001,
|
1333 |
+
"loss": 0.0018,
|
1334 |
+
"step": 808
|
1335 |
+
},
|
1336 |
+
{
|
1337 |
+
"epoch": 270.58,
|
1338 |
+
"learning_rate": 0.0001,
|
1339 |
+
"loss": 0.0021,
|
1340 |
+
"step": 812
|
1341 |
+
},
|
1342 |
+
{
|
1343 |
+
"epoch": 271.88,
|
1344 |
+
"learning_rate": 0.0001,
|
1345 |
+
"loss": 0.0022,
|
1346 |
+
"step": 816
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 273.29,
|
1350 |
+
"learning_rate": 0.0001,
|
1351 |
+
"loss": 0.0013,
|
1352 |
+
"step": 820
|
1353 |
+
},
|
1354 |
+
{
|
1355 |
+
"epoch": 274.58,
|
1356 |
+
"learning_rate": 0.0001,
|
1357 |
+
"loss": 0.0016,
|
1358 |
+
"step": 824
|
1359 |
+
},
|
1360 |
+
{
|
1361 |
+
"epoch": 275.88,
|
1362 |
+
"learning_rate": 0.0001,
|
1363 |
+
"loss": 0.0016,
|
1364 |
+
"step": 828
|
1365 |
+
},
|
1366 |
+
{
|
1367 |
+
"epoch": 277.29,
|
1368 |
+
"learning_rate": 0.0001,
|
1369 |
+
"loss": 0.0017,
|
1370 |
+
"step": 832
|
1371 |
+
},
|
1372 |
+
{
|
1373 |
+
"epoch": 277.29,
|
1374 |
+
"eval_exact_match": 0.6789168278529981,
|
1375 |
+
"eval_exec": 0.6615087040618955,
|
1376 |
+
"eval_loss": 0.36397507786750793,
|
1377 |
+
"eval_runtime": 827.3744,
|
1378 |
+
"eval_samples_per_second": 1.25,
|
1379 |
+
"step": 832
|
1380 |
+
},
|
1381 |
+
{
|
1382 |
+
"epoch": 278.58,
|
1383 |
+
"learning_rate": 0.0001,
|
1384 |
+
"loss": 0.0016,
|
1385 |
+
"step": 836
|
1386 |
+
},
|
1387 |
+
{
|
1388 |
+
"epoch": 279.88,
|
1389 |
+
"learning_rate": 0.0001,
|
1390 |
+
"loss": 0.0019,
|
1391 |
+
"step": 840
|
1392 |
+
},
|
1393 |
+
{
|
1394 |
+
"epoch": 281.29,
|
1395 |
+
"learning_rate": 0.0001,
|
1396 |
+
"loss": 0.002,
|
1397 |
+
"step": 844
|
1398 |
+
},
|
1399 |
+
{
|
1400 |
+
"epoch": 282.58,
|
1401 |
+
"learning_rate": 0.0001,
|
1402 |
+
"loss": 0.0011,
|
1403 |
+
"step": 848
|
1404 |
+
},
|
1405 |
+
{
|
1406 |
+
"epoch": 283.88,
|
1407 |
+
"learning_rate": 0.0001,
|
1408 |
+
"loss": 0.0014,
|
1409 |
+
"step": 852
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 285.29,
|
1413 |
+
"learning_rate": 0.0001,
|
1414 |
+
"loss": 0.0017,
|
1415 |
+
"step": 856
|
1416 |
+
},
|
1417 |
+
{
|
1418 |
+
"epoch": 286.58,
|
1419 |
+
"learning_rate": 0.0001,
|
1420 |
+
"loss": 0.0016,
|
1421 |
+
"step": 860
|
1422 |
+
},
|
1423 |
+
{
|
1424 |
+
"epoch": 287.88,
|
1425 |
+
"learning_rate": 0.0001,
|
1426 |
+
"loss": 0.0075,
|
1427 |
+
"step": 864
|
1428 |
+
},
|
1429 |
+
{
|
1430 |
+
"epoch": 289.29,
|
1431 |
+
"learning_rate": 0.0001,
|
1432 |
+
"loss": 0.0018,
|
1433 |
+
"step": 868
|
1434 |
+
},
|
1435 |
+
{
|
1436 |
+
"epoch": 290.58,
|
1437 |
+
"learning_rate": 0.0001,
|
1438 |
+
"loss": 0.0013,
|
1439 |
+
"step": 872
|
1440 |
+
},
|
1441 |
+
{
|
1442 |
+
"epoch": 291.88,
|
1443 |
+
"learning_rate": 0.0001,
|
1444 |
+
"loss": 0.0021,
|
1445 |
+
"step": 876
|
1446 |
+
},
|
1447 |
+
{
|
1448 |
+
"epoch": 293.29,
|
1449 |
+
"learning_rate": 0.0001,
|
1450 |
+
"loss": 0.002,
|
1451 |
+
"step": 880
|
1452 |
+
},
|
1453 |
+
{
|
1454 |
+
"epoch": 294.58,
|
1455 |
+
"learning_rate": 0.0001,
|
1456 |
+
"loss": 0.0012,
|
1457 |
+
"step": 884
|
1458 |
+
},
|
1459 |
+
{
|
1460 |
+
"epoch": 295.88,
|
1461 |
+
"learning_rate": 0.0001,
|
1462 |
+
"loss": 0.0015,
|
1463 |
+
"step": 888
|
1464 |
+
},
|
1465 |
+
{
|
1466 |
+
"epoch": 297.29,
|
1467 |
+
"learning_rate": 0.0001,
|
1468 |
+
"loss": 0.0013,
|
1469 |
+
"step": 892
|
1470 |
+
},
|
1471 |
+
{
|
1472 |
+
"epoch": 298.58,
|
1473 |
+
"learning_rate": 0.0001,
|
1474 |
+
"loss": 0.0012,
|
1475 |
+
"step": 896
|
1476 |
+
},
|
1477 |
+
{
|
1478 |
+
"epoch": 298.58,
|
1479 |
+
"eval_exact_match": 0.6740812379110251,
|
1480 |
+
"eval_exec": 0.6576402321083172,
|
1481 |
+
"eval_loss": 0.39234504103660583,
|
1482 |
+
"eval_runtime": 785.534,
|
1483 |
+
"eval_samples_per_second": 1.316,
|
1484 |
+
"step": 896
|
1485 |
+
},
|
1486 |
+
{
|
1487 |
+
"epoch": 299.88,
|
1488 |
+
"learning_rate": 0.0001,
|
1489 |
+
"loss": 0.0014,
|
1490 |
+
"step": 900
|
1491 |
+
},
|
1492 |
+
{
|
1493 |
+
"epoch": 301.29,
|
1494 |
+
"learning_rate": 0.0001,
|
1495 |
+
"loss": 0.0069,
|
1496 |
+
"step": 904
|
1497 |
+
},
|
1498 |
+
{
|
1499 |
+
"epoch": 302.58,
|
1500 |
+
"learning_rate": 0.0001,
|
1501 |
+
"loss": 0.0018,
|
1502 |
+
"step": 908
|
1503 |
+
},
|
1504 |
+
{
|
1505 |
+
"epoch": 303.88,
|
1506 |
+
"learning_rate": 0.0001,
|
1507 |
+
"loss": 0.0009,
|
1508 |
+
"step": 912
|
1509 |
+
},
|
1510 |
+
{
|
1511 |
+
"epoch": 305.29,
|
1512 |
+
"learning_rate": 0.0001,
|
1513 |
+
"loss": 0.0015,
|
1514 |
+
"step": 916
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 306.58,
|
1518 |
+
"learning_rate": 0.0001,
|
1519 |
+
"loss": 0.0012,
|
1520 |
+
"step": 920
|
1521 |
+
},
|
1522 |
+
{
|
1523 |
+
"epoch": 307.88,
|
1524 |
+
"learning_rate": 0.0001,
|
1525 |
+
"loss": 0.0013,
|
1526 |
+
"step": 924
|
1527 |
+
},
|
1528 |
+
{
|
1529 |
+
"epoch": 309.29,
|
1530 |
+
"learning_rate": 0.0001,
|
1531 |
+
"loss": 0.002,
|
1532 |
+
"step": 928
|
1533 |
+
},
|
1534 |
+
{
|
1535 |
+
"epoch": 310.58,
|
1536 |
+
"learning_rate": 0.0001,
|
1537 |
+
"loss": 0.0011,
|
1538 |
+
"step": 932
|
1539 |
+
},
|
1540 |
+
{
|
1541 |
+
"epoch": 311.88,
|
1542 |
+
"learning_rate": 0.0001,
|
1543 |
+
"loss": 0.0011,
|
1544 |
+
"step": 936
|
1545 |
+
},
|
1546 |
+
{
|
1547 |
+
"epoch": 313.29,
|
1548 |
+
"learning_rate": 0.0001,
|
1549 |
+
"loss": 0.0008,
|
1550 |
+
"step": 940
|
1551 |
+
},
|
1552 |
+
{
|
1553 |
+
"epoch": 314.58,
|
1554 |
+
"learning_rate": 0.0001,
|
1555 |
+
"loss": 0.0011,
|
1556 |
+
"step": 944
|
1557 |
+
},
|
1558 |
+
{
|
1559 |
+
"epoch": 315.88,
|
1560 |
+
"learning_rate": 0.0001,
|
1561 |
+
"loss": 0.0009,
|
1562 |
+
"step": 948
|
1563 |
+
},
|
1564 |
+
{
|
1565 |
+
"epoch": 317.29,
|
1566 |
+
"learning_rate": 0.0001,
|
1567 |
+
"loss": 0.0009,
|
1568 |
+
"step": 952
|
1569 |
+
},
|
1570 |
+
{
|
1571 |
+
"epoch": 318.58,
|
1572 |
+
"learning_rate": 0.0001,
|
1573 |
+
"loss": 0.0013,
|
1574 |
+
"step": 956
|
1575 |
+
},
|
1576 |
+
{
|
1577 |
+
"epoch": 319.88,
|
1578 |
+
"learning_rate": 0.0001,
|
1579 |
+
"loss": 0.0009,
|
1580 |
+
"step": 960
|
1581 |
+
},
|
1582 |
+
{
|
1583 |
+
"epoch": 319.88,
|
1584 |
+
"eval_exact_match": 0.6740812379110251,
|
1585 |
+
"eval_exec": 0.655705996131528,
|
1586 |
+
"eval_loss": 0.40166109800338745,
|
1587 |
+
"eval_runtime": 799.99,
|
1588 |
+
"eval_samples_per_second": 1.293,
|
1589 |
+
"step": 960
|
1590 |
+
},
|
1591 |
+
{
|
1592 |
+
"epoch": 321.29,
|
1593 |
+
"learning_rate": 0.0001,
|
1594 |
+
"loss": 0.0012,
|
1595 |
+
"step": 964
|
1596 |
+
},
|
1597 |
+
{
|
1598 |
+
"epoch": 322.58,
|
1599 |
+
"learning_rate": 0.0001,
|
1600 |
+
"loss": 0.0012,
|
1601 |
+
"step": 968
|
1602 |
+
},
|
1603 |
+
{
|
1604 |
+
"epoch": 323.88,
|
1605 |
+
"learning_rate": 0.0001,
|
1606 |
+
"loss": 0.0011,
|
1607 |
+
"step": 972
|
1608 |
+
},
|
1609 |
+
{
|
1610 |
+
"epoch": 325.29,
|
1611 |
+
"learning_rate": 0.0001,
|
1612 |
+
"loss": 0.0021,
|
1613 |
+
"step": 976
|
1614 |
+
},
|
1615 |
+
{
|
1616 |
+
"epoch": 326.58,
|
1617 |
+
"learning_rate": 0.0001,
|
1618 |
+
"loss": 0.0011,
|
1619 |
+
"step": 980
|
1620 |
+
},
|
1621 |
+
{
|
1622 |
+
"epoch": 327.88,
|
1623 |
+
"learning_rate": 0.0001,
|
1624 |
+
"loss": 0.0019,
|
1625 |
+
"step": 984
|
1626 |
+
},
|
1627 |
+
{
|
1628 |
+
"epoch": 329.29,
|
1629 |
+
"learning_rate": 0.0001,
|
1630 |
+
"loss": 0.001,
|
1631 |
+
"step": 988
|
1632 |
+
},
|
1633 |
+
{
|
1634 |
+
"epoch": 330.58,
|
1635 |
+
"learning_rate": 0.0001,
|
1636 |
+
"loss": 0.0008,
|
1637 |
+
"step": 992
|
1638 |
+
},
|
1639 |
+
{
|
1640 |
+
"epoch": 331.88,
|
1641 |
+
"learning_rate": 0.0001,
|
1642 |
+
"loss": 0.0009,
|
1643 |
+
"step": 996
|
1644 |
+
},
|
1645 |
+
{
|
1646 |
+
"epoch": 333.29,
|
1647 |
+
"learning_rate": 0.0001,
|
1648 |
+
"loss": 0.0012,
|
1649 |
+
"step": 1000
|
1650 |
+
},
|
1651 |
+
{
|
1652 |
+
"epoch": 334.58,
|
1653 |
+
"learning_rate": 0.0001,
|
1654 |
+
"loss": 0.0011,
|
1655 |
+
"step": 1004
|
1656 |
+
},
|
1657 |
+
{
|
1658 |
+
"epoch": 335.88,
|
1659 |
+
"learning_rate": 0.0001,
|
1660 |
+
"loss": 0.0013,
|
1661 |
+
"step": 1008
|
1662 |
+
},
|
1663 |
+
{
|
1664 |
+
"epoch": 337.29,
|
1665 |
+
"learning_rate": 0.0001,
|
1666 |
+
"loss": 0.0006,
|
1667 |
+
"step": 1012
|
1668 |
+
},
|
1669 |
+
{
|
1670 |
+
"epoch": 338.58,
|
1671 |
+
"learning_rate": 0.0001,
|
1672 |
+
"loss": 0.0015,
|
1673 |
+
"step": 1016
|
1674 |
+
},
|
1675 |
+
{
|
1676 |
+
"epoch": 339.88,
|
1677 |
+
"learning_rate": 0.0001,
|
1678 |
+
"loss": 0.0012,
|
1679 |
+
"step": 1020
|
1680 |
+
},
|
1681 |
+
{
|
1682 |
+
"epoch": 341.29,
|
1683 |
+
"learning_rate": 0.0001,
|
1684 |
+
"loss": 0.0098,
|
1685 |
+
"step": 1024
|
1686 |
+
},
|
1687 |
+
{
|
1688 |
+
"epoch": 341.29,
|
1689 |
+
"eval_exact_match": 0.6963249516441006,
|
1690 |
+
"eval_exec": 0.6721470019342359,
|
1691 |
+
"eval_loss": 0.3228262662887573,
|
1692 |
+
"eval_runtime": 823.0842,
|
1693 |
+
"eval_samples_per_second": 1.256,
|
1694 |
+
"step": 1024
|
1695 |
+
}
|
1696 |
+
],
|
1697 |
+
"max_steps": 9216,
|
1698 |
+
"num_train_epochs": 3072,
|
1699 |
+
"total_flos": 4.710057387539562e+18,
|
1700 |
+
"trial_name": null,
|
1701 |
+
"trial_params": null
|
1702 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0868dff65625d28408737b7217c68e86d01510fbe1d74a54d3f52c4282da8742
|
3 |
+
size 2799
|