submit for max EX in SParC
Browse files- config.json +60 -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
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +2074 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "t5-3b",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 16384,
|
7 |
+
"d_kv": 128,
|
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": "relu",
|
14 |
+
"initializer_factor": 1.0,
|
15 |
+
"is_encoder_decoder": true,
|
16 |
+
"layer_norm_epsilon": 1e-06,
|
17 |
+
"max_length": 512,
|
18 |
+
"model_type": "t5",
|
19 |
+
"n_positions": 512,
|
20 |
+
"num_beams": 4,
|
21 |
+
"num_decoder_layers": 24,
|
22 |
+
"num_heads": 32,
|
23 |
+
"num_layers": 24,
|
24 |
+
"output_past": true,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"relative_attention_num_buckets": 32,
|
27 |
+
"task_specific_params": {
|
28 |
+
"summarization": {
|
29 |
+
"early_stopping": true,
|
30 |
+
"length_penalty": 2.0,
|
31 |
+
"max_length": 200,
|
32 |
+
"min_length": 30,
|
33 |
+
"no_repeat_ngram_size": 3,
|
34 |
+
"num_beams": 4,
|
35 |
+
"prefix": "summarize: "
|
36 |
+
},
|
37 |
+
"translation_en_to_de": {
|
38 |
+
"early_stopping": true,
|
39 |
+
"max_length": 300,
|
40 |
+
"num_beams": 4,
|
41 |
+
"prefix": "translate English to German: "
|
42 |
+
},
|
43 |
+
"translation_en_to_fr": {
|
44 |
+
"early_stopping": true,
|
45 |
+
"max_length": 300,
|
46 |
+
"num_beams": 4,
|
47 |
+
"prefix": "translate English to French: "
|
48 |
+
},
|
49 |
+
"translation_en_to_ro": {
|
50 |
+
"early_stopping": true,
|
51 |
+
"max_length": 300,
|
52 |
+
"num_beams": 4,
|
53 |
+
"prefix": "translate English to Romanian: "
|
54 |
+
}
|
55 |
+
},
|
56 |
+
"torch_dtype": "float32",
|
57 |
+
"transformers_version": "4.17.0",
|
58 |
+
"use_cache": false,
|
59 |
+
"vocab_size": 32102
|
60 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1820e9f12030909a5a03616ca42f41011efb7a77c22711b3c1ca677cc1e82e62
|
3 |
+
size 13613718
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60af3f5320a1bf766ada933781269b2110eb51da4b8e89dbc6363368cda8edb7
|
3 |
+
size 11406576835
|
rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f956a9cf987a59b3f3a1fa2cc22b9a8df69a862458c71ac2b1c21aabd385ca0
|
3 |
+
size 14503
|
rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e354c43ea23e99bf27a56d5783e75e574ba9d248ee690650c07ead10c6af77d
|
3 |
+
size 14503
|
rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b123df7045ef87ce59e784032e9d80e7644941b958996f6bfe575b13208c8d8
|
3 |
+
size 14503
|
rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ed28902aa51a2407905d46c0ec092e2c84eafb8d09f46450b847c2bc69d1a7a
|
3 |
+
size 14503
|
rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2197f13e9f3fa575ddcc68dd390cab73eb1f8db70fe340d63b81403de3899f8d
|
3 |
+
size 14503
|
rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d79aea9badbc5558d4eaf7d524d7435cf1ad0c71c52ea6951b095fdc349263ba
|
3 |
+
size 14503
|
rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1b88131de0867e0068adeb4521701a8137d69c14decec62c5db3c1302a8bdeb
|
3 |
+
size 14503
|
rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:489c0c6bba2a8d33b3c97fdc9c21ff179a0274029b7b88e0f76558c3b65acf0a
|
3 |
+
size 14503
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ac15ce6ca89432d059ee479e43a0b52ed372774e3b8158aac5909adc2268e06
|
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>"]}
|
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, "special_tokens_map_file": null, "name_or_path": "t5-3b", "tokenizer_class": "T5Tokenizer"}
|
trainer_state.json
ADDED
@@ -0,0 +1,2074 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6359102244389028,
|
3 |
+
"best_model_checkpoint": "./experiment/train_0501_sparc_add_coref_denpendency/checkpoint-2304",
|
4 |
+
"epoch": 255.96644295302013,
|
5 |
+
"global_step": 2304,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.11,
|
12 |
+
"learning_rate": 0.0001,
|
13 |
+
"loss": 3.6078,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.86,
|
18 |
+
"learning_rate": 0.0001,
|
19 |
+
"loss": 1.5566,
|
20 |
+
"step": 8
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 1.75,
|
24 |
+
"learning_rate": 0.0001,
|
25 |
+
"loss": 0.5692,
|
26 |
+
"step": 16
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 2.64,
|
30 |
+
"learning_rate": 0.0001,
|
31 |
+
"loss": 0.3415,
|
32 |
+
"step": 24
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 3.54,
|
36 |
+
"learning_rate": 0.0001,
|
37 |
+
"loss": 0.2727,
|
38 |
+
"step": 32
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 4.43,
|
42 |
+
"learning_rate": 0.0001,
|
43 |
+
"loss": 0.2052,
|
44 |
+
"step": 40
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 5.32,
|
48 |
+
"learning_rate": 0.0001,
|
49 |
+
"loss": 0.1592,
|
50 |
+
"step": 48
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 6.21,
|
54 |
+
"learning_rate": 0.0001,
|
55 |
+
"loss": 0.1344,
|
56 |
+
"step": 56
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 7.11,
|
60 |
+
"learning_rate": 0.0001,
|
61 |
+
"loss": 0.1275,
|
62 |
+
"step": 64
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 7.11,
|
66 |
+
"eval_exact_match": 0.48129675810473815,
|
67 |
+
"eval_exec": 0.5386533665835411,
|
68 |
+
"eval_loss": 0.17057272791862488,
|
69 |
+
"eval_runtime": 517.9951,
|
70 |
+
"eval_samples_per_second": 3.137,
|
71 |
+
"step": 64
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 7.97,
|
75 |
+
"learning_rate": 0.0001,
|
76 |
+
"loss": 0.094,
|
77 |
+
"step": 72
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 8.86,
|
81 |
+
"learning_rate": 0.0001,
|
82 |
+
"loss": 0.1076,
|
83 |
+
"step": 80
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 9.75,
|
87 |
+
"learning_rate": 0.0001,
|
88 |
+
"loss": 0.0796,
|
89 |
+
"step": 88
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 10.64,
|
93 |
+
"learning_rate": 0.0001,
|
94 |
+
"loss": 0.0729,
|
95 |
+
"step": 96
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 11.54,
|
99 |
+
"learning_rate": 0.0001,
|
100 |
+
"loss": 0.0847,
|
101 |
+
"step": 104
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 12.43,
|
105 |
+
"learning_rate": 0.0001,
|
106 |
+
"loss": 0.0582,
|
107 |
+
"step": 112
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 13.32,
|
111 |
+
"learning_rate": 0.0001,
|
112 |
+
"loss": 0.0533,
|
113 |
+
"step": 120
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 14.21,
|
117 |
+
"learning_rate": 0.0001,
|
118 |
+
"loss": 0.0504,
|
119 |
+
"step": 128
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 14.21,
|
123 |
+
"eval_exact_match": 0.5469659185369908,
|
124 |
+
"eval_exec": 0.600166251039069,
|
125 |
+
"eval_loss": 0.18190230429172516,
|
126 |
+
"eval_runtime": 531.6846,
|
127 |
+
"eval_samples_per_second": 3.056,
|
128 |
+
"step": 128
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 15.11,
|
132 |
+
"learning_rate": 0.0001,
|
133 |
+
"loss": 0.0441,
|
134 |
+
"step": 136
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 15.97,
|
138 |
+
"learning_rate": 0.0001,
|
139 |
+
"loss": 0.0423,
|
140 |
+
"step": 144
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 16.86,
|
144 |
+
"learning_rate": 0.0001,
|
145 |
+
"loss": 0.0371,
|
146 |
+
"step": 152
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 17.75,
|
150 |
+
"learning_rate": 0.0001,
|
151 |
+
"loss": 0.0354,
|
152 |
+
"step": 160
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 18.64,
|
156 |
+
"learning_rate": 0.0001,
|
157 |
+
"loss": 0.0315,
|
158 |
+
"step": 168
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 19.54,
|
162 |
+
"learning_rate": 0.0001,
|
163 |
+
"loss": 0.0277,
|
164 |
+
"step": 176
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 20.43,
|
168 |
+
"learning_rate": 0.0001,
|
169 |
+
"loss": 0.0274,
|
170 |
+
"step": 184
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 21.32,
|
174 |
+
"learning_rate": 0.0001,
|
175 |
+
"loss": 0.0257,
|
176 |
+
"step": 192
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 21.32,
|
180 |
+
"eval_exact_match": 0.5627597672485453,
|
181 |
+
"eval_exec": 0.6217788861180382,
|
182 |
+
"eval_loss": 0.21687868237495422,
|
183 |
+
"eval_runtime": 659.6767,
|
184 |
+
"eval_samples_per_second": 2.463,
|
185 |
+
"step": 192
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 22.21,
|
189 |
+
"learning_rate": 0.0001,
|
190 |
+
"loss": 0.022,
|
191 |
+
"step": 200
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 23.11,
|
195 |
+
"learning_rate": 0.0001,
|
196 |
+
"loss": 0.0203,
|
197 |
+
"step": 208
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 23.97,
|
201 |
+
"learning_rate": 0.0001,
|
202 |
+
"loss": 0.0181,
|
203 |
+
"step": 216
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 24.86,
|
207 |
+
"learning_rate": 0.0001,
|
208 |
+
"loss": 0.0181,
|
209 |
+
"step": 224
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 25.75,
|
213 |
+
"learning_rate": 0.0001,
|
214 |
+
"loss": 0.0176,
|
215 |
+
"step": 232
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 26.64,
|
219 |
+
"learning_rate": 0.0001,
|
220 |
+
"loss": 0.0145,
|
221 |
+
"step": 240
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 27.54,
|
225 |
+
"learning_rate": 0.0001,
|
226 |
+
"loss": 0.0132,
|
227 |
+
"step": 248
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 28.43,
|
231 |
+
"learning_rate": 0.0001,
|
232 |
+
"loss": 0.0156,
|
233 |
+
"step": 256
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 28.43,
|
237 |
+
"eval_exact_match": 0.4239401496259352,
|
238 |
+
"eval_exec": 0.4397339983374896,
|
239 |
+
"eval_loss": 0.3322429060935974,
|
240 |
+
"eval_runtime": 617.5714,
|
241 |
+
"eval_samples_per_second": 2.631,
|
242 |
+
"step": 256
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 29.32,
|
246 |
+
"learning_rate": 0.0001,
|
247 |
+
"loss": 0.0295,
|
248 |
+
"step": 264
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 30.21,
|
252 |
+
"learning_rate": 0.0001,
|
253 |
+
"loss": 0.0102,
|
254 |
+
"step": 272
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 31.11,
|
258 |
+
"learning_rate": 0.0001,
|
259 |
+
"loss": 0.0094,
|
260 |
+
"step": 280
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 31.97,
|
264 |
+
"learning_rate": 0.0001,
|
265 |
+
"loss": 0.0082,
|
266 |
+
"step": 288
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 32.86,
|
270 |
+
"learning_rate": 0.0001,
|
271 |
+
"loss": 0.0088,
|
272 |
+
"step": 296
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 33.75,
|
276 |
+
"learning_rate": 0.0001,
|
277 |
+
"loss": 0.011,
|
278 |
+
"step": 304
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 34.64,
|
282 |
+
"learning_rate": 0.0001,
|
283 |
+
"loss": 0.01,
|
284 |
+
"step": 312
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 35.54,
|
288 |
+
"learning_rate": 0.0001,
|
289 |
+
"loss": 0.0082,
|
290 |
+
"step": 320
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 35.54,
|
294 |
+
"eval_exact_match": 0.6018287614297589,
|
295 |
+
"eval_exec": 0.6458852867830424,
|
296 |
+
"eval_loss": 0.2703750431537628,
|
297 |
+
"eval_runtime": 591.5567,
|
298 |
+
"eval_samples_per_second": 2.747,
|
299 |
+
"step": 320
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 36.43,
|
303 |
+
"learning_rate": 0.0001,
|
304 |
+
"loss": 0.0072,
|
305 |
+
"step": 328
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 37.32,
|
309 |
+
"learning_rate": 0.0001,
|
310 |
+
"loss": 0.0063,
|
311 |
+
"step": 336
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 38.21,
|
315 |
+
"learning_rate": 0.0001,
|
316 |
+
"loss": 0.0061,
|
317 |
+
"step": 344
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 39.11,
|
321 |
+
"learning_rate": 0.0001,
|
322 |
+
"loss": 0.0062,
|
323 |
+
"step": 352
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 39.97,
|
327 |
+
"learning_rate": 0.0001,
|
328 |
+
"loss": 0.0051,
|
329 |
+
"step": 360
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 40.86,
|
333 |
+
"learning_rate": 0.0001,
|
334 |
+
"loss": 0.005,
|
335 |
+
"step": 368
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 41.75,
|
339 |
+
"learning_rate": 0.0001,
|
340 |
+
"loss": 0.0051,
|
341 |
+
"step": 376
|
342 |
+
},
|
343 |
+
{
|
344 |
+
"epoch": 42.64,
|
345 |
+
"learning_rate": 0.0001,
|
346 |
+
"loss": 0.0054,
|
347 |
+
"step": 384
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 42.64,
|
351 |
+
"eval_exact_match": 0.600997506234414,
|
352 |
+
"eval_exec": 0.6500415627597672,
|
353 |
+
"eval_loss": 0.2921164035797119,
|
354 |
+
"eval_runtime": 612.6538,
|
355 |
+
"eval_samples_per_second": 2.652,
|
356 |
+
"step": 384
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 43.54,
|
360 |
+
"learning_rate": 0.0001,
|
361 |
+
"loss": 0.0106,
|
362 |
+
"step": 392
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 44.43,
|
366 |
+
"learning_rate": 0.0001,
|
367 |
+
"loss": 0.0053,
|
368 |
+
"step": 400
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 45.32,
|
372 |
+
"learning_rate": 0.0001,
|
373 |
+
"loss": 0.005,
|
374 |
+
"step": 408
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 46.21,
|
378 |
+
"learning_rate": 0.0001,
|
379 |
+
"loss": 0.0043,
|
380 |
+
"step": 416
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 47.11,
|
384 |
+
"learning_rate": 0.0001,
|
385 |
+
"loss": 0.0043,
|
386 |
+
"step": 424
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 47.97,
|
390 |
+
"learning_rate": 0.0001,
|
391 |
+
"loss": 0.0037,
|
392 |
+
"step": 432
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 48.86,
|
396 |
+
"learning_rate": 0.0001,
|
397 |
+
"loss": 0.0043,
|
398 |
+
"step": 440
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 49.75,
|
402 |
+
"learning_rate": 0.0001,
|
403 |
+
"loss": 0.0077,
|
404 |
+
"step": 448
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 49.75,
|
408 |
+
"eval_exact_match": 0.6101413133832086,
|
409 |
+
"eval_exec": 0.6483790523690773,
|
410 |
+
"eval_loss": 0.29036417603492737,
|
411 |
+
"eval_runtime": 632.4401,
|
412 |
+
"eval_samples_per_second": 2.569,
|
413 |
+
"step": 448
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 50.64,
|
417 |
+
"learning_rate": 0.0001,
|
418 |
+
"loss": 0.004,
|
419 |
+
"step": 456
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 51.54,
|
423 |
+
"learning_rate": 0.0001,
|
424 |
+
"loss": 0.004,
|
425 |
+
"step": 464
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 52.43,
|
429 |
+
"learning_rate": 0.0001,
|
430 |
+
"loss": 0.0141,
|
431 |
+
"step": 472
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 53.32,
|
435 |
+
"learning_rate": 0.0001,
|
436 |
+
"loss": 0.0131,
|
437 |
+
"step": 480
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 54.21,
|
441 |
+
"learning_rate": 0.0001,
|
442 |
+
"loss": 0.0034,
|
443 |
+
"step": 488
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 55.11,
|
447 |
+
"learning_rate": 0.0001,
|
448 |
+
"loss": 0.0033,
|
449 |
+
"step": 496
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 55.97,
|
453 |
+
"learning_rate": 0.0001,
|
454 |
+
"loss": 0.0029,
|
455 |
+
"step": 504
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 56.86,
|
459 |
+
"learning_rate": 0.0001,
|
460 |
+
"loss": 0.003,
|
461 |
+
"step": 512
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 56.86,
|
465 |
+
"eval_exact_match": 0.6176226101413134,
|
466 |
+
"eval_exec": 0.6716541978387365,
|
467 |
+
"eval_loss": 0.3254193067550659,
|
468 |
+
"eval_runtime": 623.8474,
|
469 |
+
"eval_samples_per_second": 2.605,
|
470 |
+
"step": 512
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 57.75,
|
474 |
+
"learning_rate": 0.0001,
|
475 |
+
"loss": 0.003,
|
476 |
+
"step": 520
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 58.64,
|
480 |
+
"learning_rate": 0.0001,
|
481 |
+
"loss": 0.0027,
|
482 |
+
"step": 528
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 59.54,
|
486 |
+
"learning_rate": 0.0001,
|
487 |
+
"loss": 0.0026,
|
488 |
+
"step": 536
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 60.43,
|
492 |
+
"learning_rate": 0.0001,
|
493 |
+
"loss": 0.0028,
|
494 |
+
"step": 544
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 61.32,
|
498 |
+
"learning_rate": 0.0001,
|
499 |
+
"loss": 0.0024,
|
500 |
+
"step": 552
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 62.21,
|
504 |
+
"learning_rate": 0.0001,
|
505 |
+
"loss": 0.0026,
|
506 |
+
"step": 560
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 63.11,
|
510 |
+
"learning_rate": 0.0001,
|
511 |
+
"loss": 0.0024,
|
512 |
+
"step": 568
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 63.97,
|
516 |
+
"learning_rate": 0.0001,
|
517 |
+
"loss": 0.002,
|
518 |
+
"step": 576
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 63.97,
|
522 |
+
"eval_exact_match": 0.6176226101413134,
|
523 |
+
"eval_exec": 0.6600166251039069,
|
524 |
+
"eval_loss": 0.34047040343284607,
|
525 |
+
"eval_runtime": 625.6853,
|
526 |
+
"eval_samples_per_second": 2.597,
|
527 |
+
"step": 576
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 64.86,
|
531 |
+
"learning_rate": 0.0001,
|
532 |
+
"loss": 0.0026,
|
533 |
+
"step": 584
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 65.75,
|
537 |
+
"learning_rate": 0.0001,
|
538 |
+
"loss": 0.0025,
|
539 |
+
"step": 592
|
540 |
+
},
|
541 |
+
{
|
542 |
+
"epoch": 66.64,
|
543 |
+
"learning_rate": 0.0001,
|
544 |
+
"loss": 0.0022,
|
545 |
+
"step": 600
|
546 |
+
},
|
547 |
+
{
|
548 |
+
"epoch": 67.54,
|
549 |
+
"learning_rate": 0.0001,
|
550 |
+
"loss": 0.0026,
|
551 |
+
"step": 608
|
552 |
+
},
|
553 |
+
{
|
554 |
+
"epoch": 68.43,
|
555 |
+
"learning_rate": 0.0001,
|
556 |
+
"loss": 0.0031,
|
557 |
+
"step": 616
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 69.32,
|
561 |
+
"learning_rate": 0.0001,
|
562 |
+
"loss": 0.0022,
|
563 |
+
"step": 624
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 70.21,
|
567 |
+
"learning_rate": 0.0001,
|
568 |
+
"loss": 0.002,
|
569 |
+
"step": 632
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 71.11,
|
573 |
+
"learning_rate": 0.0001,
|
574 |
+
"loss": 0.0023,
|
575 |
+
"step": 640
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"epoch": 71.11,
|
579 |
+
"eval_exact_match": 0.5935162094763092,
|
580 |
+
"eval_exec": 0.6367414796342478,
|
581 |
+
"eval_loss": 0.3419930040836334,
|
582 |
+
"eval_runtime": 628.956,
|
583 |
+
"eval_samples_per_second": 2.584,
|
584 |
+
"step": 640
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 71.97,
|
588 |
+
"learning_rate": 0.0001,
|
589 |
+
"loss": 0.0021,
|
590 |
+
"step": 648
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 72.86,
|
594 |
+
"learning_rate": 0.0001,
|
595 |
+
"loss": 0.0019,
|
596 |
+
"step": 656
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 73.75,
|
600 |
+
"learning_rate": 0.0001,
|
601 |
+
"loss": 0.0023,
|
602 |
+
"step": 664
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 74.64,
|
606 |
+
"learning_rate": 0.0001,
|
607 |
+
"loss": 0.002,
|
608 |
+
"step": 672
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 75.54,
|
612 |
+
"learning_rate": 0.0001,
|
613 |
+
"loss": 0.0025,
|
614 |
+
"step": 680
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 76.43,
|
618 |
+
"learning_rate": 0.0001,
|
619 |
+
"loss": 0.002,
|
620 |
+
"step": 688
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 77.32,
|
624 |
+
"learning_rate": 0.0001,
|
625 |
+
"loss": 0.0066,
|
626 |
+
"step": 696
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 78.21,
|
630 |
+
"learning_rate": 0.0001,
|
631 |
+
"loss": 0.0081,
|
632 |
+
"step": 704
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 78.21,
|
636 |
+
"eval_exact_match": 0.6101413133832086,
|
637 |
+
"eval_exec": 0.6658354114713217,
|
638 |
+
"eval_loss": 0.3075915575027466,
|
639 |
+
"eval_runtime": 610.1005,
|
640 |
+
"eval_samples_per_second": 2.663,
|
641 |
+
"step": 704
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 79.11,
|
645 |
+
"learning_rate": 0.0001,
|
646 |
+
"loss": 0.0025,
|
647 |
+
"step": 712
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 79.97,
|
651 |
+
"learning_rate": 0.0001,
|
652 |
+
"loss": 0.0025,
|
653 |
+
"step": 720
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 80.86,
|
657 |
+
"learning_rate": 0.0001,
|
658 |
+
"loss": 0.0017,
|
659 |
+
"step": 728
|
660 |
+
},
|
661 |
+
{
|
662 |
+
"epoch": 81.75,
|
663 |
+
"learning_rate": 0.0001,
|
664 |
+
"loss": 0.0019,
|
665 |
+
"step": 736
|
666 |
+
},
|
667 |
+
{
|
668 |
+
"epoch": 82.64,
|
669 |
+
"learning_rate": 0.0001,
|
670 |
+
"loss": 0.0017,
|
671 |
+
"step": 744
|
672 |
+
},
|
673 |
+
{
|
674 |
+
"epoch": 83.54,
|
675 |
+
"learning_rate": 0.0001,
|
676 |
+
"loss": 0.0015,
|
677 |
+
"step": 752
|
678 |
+
},
|
679 |
+
{
|
680 |
+
"epoch": 84.43,
|
681 |
+
"learning_rate": 0.0001,
|
682 |
+
"loss": 0.0022,
|
683 |
+
"step": 760
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 85.32,
|
687 |
+
"learning_rate": 0.0001,
|
688 |
+
"loss": 0.0085,
|
689 |
+
"step": 768
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 85.32,
|
693 |
+
"eval_exact_match": 0.6267664172901081,
|
694 |
+
"eval_exec": 0.6783042394014963,
|
695 |
+
"eval_loss": 0.34360331296920776,
|
696 |
+
"eval_runtime": 719.9169,
|
697 |
+
"eval_samples_per_second": 2.257,
|
698 |
+
"step": 768
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 86.21,
|
702 |
+
"learning_rate": 0.0001,
|
703 |
+
"loss": 0.0016,
|
704 |
+
"step": 776
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 87.11,
|
708 |
+
"learning_rate": 0.0001,
|
709 |
+
"loss": 0.0018,
|
710 |
+
"step": 784
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 87.97,
|
714 |
+
"learning_rate": 0.0001,
|
715 |
+
"loss": 0.0036,
|
716 |
+
"step": 792
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 88.86,
|
720 |
+
"learning_rate": 0.0001,
|
721 |
+
"loss": 0.0016,
|
722 |
+
"step": 800
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 89.75,
|
726 |
+
"learning_rate": 0.0001,
|
727 |
+
"loss": 0.0015,
|
728 |
+
"step": 808
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 90.64,
|
732 |
+
"learning_rate": 0.0001,
|
733 |
+
"loss": 0.0015,
|
734 |
+
"step": 816
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 91.54,
|
738 |
+
"learning_rate": 0.0001,
|
739 |
+
"loss": 0.0035,
|
740 |
+
"step": 824
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 92.43,
|
744 |
+
"learning_rate": 0.0001,
|
745 |
+
"loss": 0.0053,
|
746 |
+
"step": 832
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 92.43,
|
750 |
+
"eval_exact_match": 0.6051537822111388,
|
751 |
+
"eval_exec": 0.6674979218620116,
|
752 |
+
"eval_loss": 0.3258628249168396,
|
753 |
+
"eval_runtime": 632.8345,
|
754 |
+
"eval_samples_per_second": 2.568,
|
755 |
+
"step": 832
|
756 |
+
},
|
757 |
+
{
|
758 |
+
"epoch": 93.32,
|
759 |
+
"learning_rate": 0.0001,
|
760 |
+
"loss": 0.0016,
|
761 |
+
"step": 840
|
762 |
+
},
|
763 |
+
{
|
764 |
+
"epoch": 94.21,
|
765 |
+
"learning_rate": 0.0001,
|
766 |
+
"loss": 0.0063,
|
767 |
+
"step": 848
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 95.11,
|
771 |
+
"learning_rate": 0.0001,
|
772 |
+
"loss": 0.0021,
|
773 |
+
"step": 856
|
774 |
+
},
|
775 |
+
{
|
776 |
+
"epoch": 95.97,
|
777 |
+
"learning_rate": 0.0001,
|
778 |
+
"loss": 0.0015,
|
779 |
+
"step": 864
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 96.86,
|
783 |
+
"learning_rate": 0.0001,
|
784 |
+
"loss": 0.0013,
|
785 |
+
"step": 872
|
786 |
+
},
|
787 |
+
{
|
788 |
+
"epoch": 97.75,
|
789 |
+
"learning_rate": 0.0001,
|
790 |
+
"loss": 0.0015,
|
791 |
+
"step": 880
|
792 |
+
},
|
793 |
+
{
|
794 |
+
"epoch": 98.64,
|
795 |
+
"learning_rate": 0.0001,
|
796 |
+
"loss": 0.0024,
|
797 |
+
"step": 888
|
798 |
+
},
|
799 |
+
{
|
800 |
+
"epoch": 99.54,
|
801 |
+
"learning_rate": 0.0001,
|
802 |
+
"loss": 0.0014,
|
803 |
+
"step": 896
|
804 |
+
},
|
805 |
+
{
|
806 |
+
"epoch": 99.54,
|
807 |
+
"eval_exact_match": 0.6126350789692435,
|
808 |
+
"eval_exec": 0.6625103906899418,
|
809 |
+
"eval_loss": 0.3495762348175049,
|
810 |
+
"eval_runtime": 646.5878,
|
811 |
+
"eval_samples_per_second": 2.513,
|
812 |
+
"step": 896
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 100.43,
|
816 |
+
"learning_rate": 0.0001,
|
817 |
+
"loss": 0.0012,
|
818 |
+
"step": 904
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 101.32,
|
822 |
+
"learning_rate": 0.0001,
|
823 |
+
"loss": 0.0015,
|
824 |
+
"step": 912
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 102.21,
|
828 |
+
"learning_rate": 0.0001,
|
829 |
+
"loss": 0.0013,
|
830 |
+
"step": 920
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 103.11,
|
834 |
+
"learning_rate": 0.0001,
|
835 |
+
"loss": 0.0013,
|
836 |
+
"step": 928
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 103.97,
|
840 |
+
"learning_rate": 0.0001,
|
841 |
+
"loss": 0.0013,
|
842 |
+
"step": 936
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 104.86,
|
846 |
+
"learning_rate": 0.0001,
|
847 |
+
"loss": 0.0014,
|
848 |
+
"step": 944
|
849 |
+
},
|
850 |
+
{
|
851 |
+
"epoch": 105.75,
|
852 |
+
"learning_rate": 0.0001,
|
853 |
+
"loss": 0.0012,
|
854 |
+
"step": 952
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 106.64,
|
858 |
+
"learning_rate": 0.0001,
|
859 |
+
"loss": 0.0012,
|
860 |
+
"step": 960
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 106.64,
|
864 |
+
"eval_exact_match": 0.6267664172901081,
|
865 |
+
"eval_exec": 0.6749792186201163,
|
866 |
+
"eval_loss": 0.3583427369594574,
|
867 |
+
"eval_runtime": 675.9856,
|
868 |
+
"eval_samples_per_second": 2.404,
|
869 |
+
"step": 960
|
870 |
+
},
|
871 |
+
{
|
872 |
+
"epoch": 107.54,
|
873 |
+
"learning_rate": 0.0001,
|
874 |
+
"loss": 0.0018,
|
875 |
+
"step": 968
|
876 |
+
},
|
877 |
+
{
|
878 |
+
"epoch": 108.43,
|
879 |
+
"learning_rate": 0.0001,
|
880 |
+
"loss": 0.0014,
|
881 |
+
"step": 976
|
882 |
+
},
|
883 |
+
{
|
884 |
+
"epoch": 109.32,
|
885 |
+
"learning_rate": 0.0001,
|
886 |
+
"loss": 0.0013,
|
887 |
+
"step": 984
|
888 |
+
},
|
889 |
+
{
|
890 |
+
"epoch": 110.21,
|
891 |
+
"learning_rate": 0.0001,
|
892 |
+
"loss": 0.0015,
|
893 |
+
"step": 992
|
894 |
+
},
|
895 |
+
{
|
896 |
+
"epoch": 111.11,
|
897 |
+
"learning_rate": 0.0001,
|
898 |
+
"loss": 0.0039,
|
899 |
+
"step": 1000
|
900 |
+
},
|
901 |
+
{
|
902 |
+
"epoch": 111.97,
|
903 |
+
"learning_rate": 0.0001,
|
904 |
+
"loss": 0.0013,
|
905 |
+
"step": 1008
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 112.86,
|
909 |
+
"learning_rate": 0.0001,
|
910 |
+
"loss": 0.0013,
|
911 |
+
"step": 1016
|
912 |
+
},
|
913 |
+
{
|
914 |
+
"epoch": 113.75,
|
915 |
+
"learning_rate": 0.0001,
|
916 |
+
"loss": 0.0013,
|
917 |
+
"step": 1024
|
918 |
+
},
|
919 |
+
{
|
920 |
+
"epoch": 113.75,
|
921 |
+
"eval_exact_match": 0.6134663341645885,
|
922 |
+
"eval_exec": 0.6625103906899418,
|
923 |
+
"eval_loss": 0.36480623483657837,
|
924 |
+
"eval_runtime": 687.3703,
|
925 |
+
"eval_samples_per_second": 2.364,
|
926 |
+
"step": 1024
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 114.64,
|
930 |
+
"learning_rate": 0.0001,
|
931 |
+
"loss": 0.0013,
|
932 |
+
"step": 1032
|
933 |
+
},
|
934 |
+
{
|
935 |
+
"epoch": 115.54,
|
936 |
+
"learning_rate": 0.0001,
|
937 |
+
"loss": 0.0018,
|
938 |
+
"step": 1040
|
939 |
+
},
|
940 |
+
{
|
941 |
+
"epoch": 116.43,
|
942 |
+
"learning_rate": 0.0001,
|
943 |
+
"loss": 0.0013,
|
944 |
+
"step": 1048
|
945 |
+
},
|
946 |
+
{
|
947 |
+
"epoch": 117.32,
|
948 |
+
"learning_rate": 0.0001,
|
949 |
+
"loss": 0.0012,
|
950 |
+
"step": 1056
|
951 |
+
},
|
952 |
+
{
|
953 |
+
"epoch": 118.21,
|
954 |
+
"learning_rate": 0.0001,
|
955 |
+
"loss": 0.0011,
|
956 |
+
"step": 1064
|
957 |
+
},
|
958 |
+
{
|
959 |
+
"epoch": 119.11,
|
960 |
+
"learning_rate": 0.0001,
|
961 |
+
"loss": 0.0013,
|
962 |
+
"step": 1072
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 119.97,
|
966 |
+
"learning_rate": 0.0001,
|
967 |
+
"loss": 0.0011,
|
968 |
+
"step": 1080
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 120.86,
|
972 |
+
"learning_rate": 0.0001,
|
973 |
+
"loss": 0.0011,
|
974 |
+
"step": 1088
|
975 |
+
},
|
976 |
+
{
|
977 |
+
"epoch": 120.86,
|
978 |
+
"eval_exact_match": 0.6034912718204489,
|
979 |
+
"eval_exec": 0.6525353283458022,
|
980 |
+
"eval_loss": 0.38511478900909424,
|
981 |
+
"eval_runtime": 1089.0696,
|
982 |
+
"eval_samples_per_second": 1.492,
|
983 |
+
"step": 1088
|
984 |
+
},
|
985 |
+
{
|
986 |
+
"epoch": 121.75,
|
987 |
+
"learning_rate": 0.0001,
|
988 |
+
"loss": 0.0013,
|
989 |
+
"step": 1096
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 122.64,
|
993 |
+
"learning_rate": 0.0001,
|
994 |
+
"loss": 0.0088,
|
995 |
+
"step": 1104
|
996 |
+
},
|
997 |
+
{
|
998 |
+
"epoch": 123.54,
|
999 |
+
"learning_rate": 0.0001,
|
1000 |
+
"loss": 0.0022,
|
1001 |
+
"step": 1112
|
1002 |
+
},
|
1003 |
+
{
|
1004 |
+
"epoch": 124.43,
|
1005 |
+
"learning_rate": 0.0001,
|
1006 |
+
"loss": 0.0012,
|
1007 |
+
"step": 1120
|
1008 |
+
},
|
1009 |
+
{
|
1010 |
+
"epoch": 125.32,
|
1011 |
+
"learning_rate": 0.0001,
|
1012 |
+
"loss": 0.0011,
|
1013 |
+
"step": 1128
|
1014 |
+
},
|
1015 |
+
{
|
1016 |
+
"epoch": 126.21,
|
1017 |
+
"learning_rate": 0.0001,
|
1018 |
+
"loss": 0.0012,
|
1019 |
+
"step": 1136
|
1020 |
+
},
|
1021 |
+
{
|
1022 |
+
"epoch": 127.11,
|
1023 |
+
"learning_rate": 0.0001,
|
1024 |
+
"loss": 0.0012,
|
1025 |
+
"step": 1144
|
1026 |
+
},
|
1027 |
+
{
|
1028 |
+
"epoch": 127.97,
|
1029 |
+
"learning_rate": 0.0001,
|
1030 |
+
"loss": 0.0013,
|
1031 |
+
"step": 1152
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 127.97,
|
1035 |
+
"eval_exact_match": 0.6126350789692435,
|
1036 |
+
"eval_exec": 0.6616791354945969,
|
1037 |
+
"eval_loss": 0.3620198965072632,
|
1038 |
+
"eval_runtime": 625.7472,
|
1039 |
+
"eval_samples_per_second": 2.597,
|
1040 |
+
"step": 1152
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 128.86,
|
1044 |
+
"learning_rate": 0.0001,
|
1045 |
+
"loss": 0.001,
|
1046 |
+
"step": 1160
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 129.75,
|
1050 |
+
"learning_rate": 0.0001,
|
1051 |
+
"loss": 0.0022,
|
1052 |
+
"step": 1168
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 130.64,
|
1056 |
+
"learning_rate": 0.0001,
|
1057 |
+
"loss": 0.0012,
|
1058 |
+
"step": 1176
|
1059 |
+
},
|
1060 |
+
{
|
1061 |
+
"epoch": 131.54,
|
1062 |
+
"learning_rate": 0.0001,
|
1063 |
+
"loss": 0.0013,
|
1064 |
+
"step": 1184
|
1065 |
+
},
|
1066 |
+
{
|
1067 |
+
"epoch": 132.43,
|
1068 |
+
"learning_rate": 0.0001,
|
1069 |
+
"loss": 0.0012,
|
1070 |
+
"step": 1192
|
1071 |
+
},
|
1072 |
+
{
|
1073 |
+
"epoch": 133.32,
|
1074 |
+
"learning_rate": 0.0001,
|
1075 |
+
"loss": 0.001,
|
1076 |
+
"step": 1200
|
1077 |
+
},
|
1078 |
+
{
|
1079 |
+
"epoch": 134.21,
|
1080 |
+
"learning_rate": 0.0001,
|
1081 |
+
"loss": 0.0011,
|
1082 |
+
"step": 1208
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 135.11,
|
1086 |
+
"learning_rate": 0.0001,
|
1087 |
+
"loss": 0.0009,
|
1088 |
+
"step": 1216
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 135.11,
|
1092 |
+
"eval_exact_match": 0.6109725685785536,
|
1093 |
+
"eval_exec": 0.6625103906899418,
|
1094 |
+
"eval_loss": 0.38990598917007446,
|
1095 |
+
"eval_runtime": 672.2153,
|
1096 |
+
"eval_samples_per_second": 2.417,
|
1097 |
+
"step": 1216
|
1098 |
+
},
|
1099 |
+
{
|
1100 |
+
"epoch": 135.97,
|
1101 |
+
"learning_rate": 0.0001,
|
1102 |
+
"loss": 0.001,
|
1103 |
+
"step": 1224
|
1104 |
+
},
|
1105 |
+
{
|
1106 |
+
"epoch": 136.86,
|
1107 |
+
"learning_rate": 0.0001,
|
1108 |
+
"loss": 0.001,
|
1109 |
+
"step": 1232
|
1110 |
+
},
|
1111 |
+
{
|
1112 |
+
"epoch": 137.75,
|
1113 |
+
"learning_rate": 0.0001,
|
1114 |
+
"loss": 0.001,
|
1115 |
+
"step": 1240
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 138.64,
|
1119 |
+
"learning_rate": 0.0001,
|
1120 |
+
"loss": 0.0011,
|
1121 |
+
"step": 1248
|
1122 |
+
},
|
1123 |
+
{
|
1124 |
+
"epoch": 139.54,
|
1125 |
+
"learning_rate": 0.0001,
|
1126 |
+
"loss": 0.0011,
|
1127 |
+
"step": 1256
|
1128 |
+
},
|
1129 |
+
{
|
1130 |
+
"epoch": 140.43,
|
1131 |
+
"learning_rate": 0.0001,
|
1132 |
+
"loss": 0.0014,
|
1133 |
+
"step": 1264
|
1134 |
+
},
|
1135 |
+
{
|
1136 |
+
"epoch": 141.32,
|
1137 |
+
"learning_rate": 0.0001,
|
1138 |
+
"loss": 0.0011,
|
1139 |
+
"step": 1272
|
1140 |
+
},
|
1141 |
+
{
|
1142 |
+
"epoch": 142.21,
|
1143 |
+
"learning_rate": 0.0001,
|
1144 |
+
"loss": 0.001,
|
1145 |
+
"step": 1280
|
1146 |
+
},
|
1147 |
+
{
|
1148 |
+
"epoch": 142.21,
|
1149 |
+
"eval_exact_match": 0.6192851205320034,
|
1150 |
+
"eval_exec": 0.6766417290108063,
|
1151 |
+
"eval_loss": 0.3710319697856903,
|
1152 |
+
"eval_runtime": 681.1968,
|
1153 |
+
"eval_samples_per_second": 2.386,
|
1154 |
+
"step": 1280
|
1155 |
+
},
|
1156 |
+
{
|
1157 |
+
"epoch": 143.11,
|
1158 |
+
"learning_rate": 0.0001,
|
1159 |
+
"loss": 0.0009,
|
1160 |
+
"step": 1288
|
1161 |
+
},
|
1162 |
+
{
|
1163 |
+
"epoch": 143.97,
|
1164 |
+
"learning_rate": 0.0001,
|
1165 |
+
"loss": 0.0009,
|
1166 |
+
"step": 1296
|
1167 |
+
},
|
1168 |
+
{
|
1169 |
+
"epoch": 144.86,
|
1170 |
+
"learning_rate": 0.0001,
|
1171 |
+
"loss": 0.0011,
|
1172 |
+
"step": 1304
|
1173 |
+
},
|
1174 |
+
{
|
1175 |
+
"epoch": 145.75,
|
1176 |
+
"learning_rate": 0.0001,
|
1177 |
+
"loss": 0.0059,
|
1178 |
+
"step": 1312
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 146.64,
|
1182 |
+
"learning_rate": 0.0001,
|
1183 |
+
"loss": 0.0019,
|
1184 |
+
"step": 1320
|
1185 |
+
},
|
1186 |
+
{
|
1187 |
+
"epoch": 147.54,
|
1188 |
+
"learning_rate": 0.0001,
|
1189 |
+
"loss": 0.0013,
|
1190 |
+
"step": 1328
|
1191 |
+
},
|
1192 |
+
{
|
1193 |
+
"epoch": 148.43,
|
1194 |
+
"learning_rate": 0.0001,
|
1195 |
+
"loss": 0.001,
|
1196 |
+
"step": 1336
|
1197 |
+
},
|
1198 |
+
{
|
1199 |
+
"epoch": 149.32,
|
1200 |
+
"learning_rate": 0.0001,
|
1201 |
+
"loss": 0.001,
|
1202 |
+
"step": 1344
|
1203 |
+
},
|
1204 |
+
{
|
1205 |
+
"epoch": 149.32,
|
1206 |
+
"eval_exact_match": 0.6126350789692435,
|
1207 |
+
"eval_exec": 0.6541978387364921,
|
1208 |
+
"eval_loss": 0.38512444496154785,
|
1209 |
+
"eval_runtime": 658.6422,
|
1210 |
+
"eval_samples_per_second": 2.467,
|
1211 |
+
"step": 1344
|
1212 |
+
},
|
1213 |
+
{
|
1214 |
+
"epoch": 150.21,
|
1215 |
+
"learning_rate": 0.0001,
|
1216 |
+
"loss": 0.001,
|
1217 |
+
"step": 1352
|
1218 |
+
},
|
1219 |
+
{
|
1220 |
+
"epoch": 151.11,
|
1221 |
+
"learning_rate": 0.0001,
|
1222 |
+
"loss": 0.0011,
|
1223 |
+
"step": 1360
|
1224 |
+
},
|
1225 |
+
{
|
1226 |
+
"epoch": 151.97,
|
1227 |
+
"learning_rate": 0.0001,
|
1228 |
+
"loss": 0.0009,
|
1229 |
+
"step": 1368
|
1230 |
+
},
|
1231 |
+
{
|
1232 |
+
"epoch": 152.86,
|
1233 |
+
"learning_rate": 0.0001,
|
1234 |
+
"loss": 0.0013,
|
1235 |
+
"step": 1376
|
1236 |
+
},
|
1237 |
+
{
|
1238 |
+
"epoch": 153.75,
|
1239 |
+
"learning_rate": 0.0001,
|
1240 |
+
"loss": 0.0011,
|
1241 |
+
"step": 1384
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 154.64,
|
1245 |
+
"learning_rate": 0.0001,
|
1246 |
+
"loss": 0.0022,
|
1247 |
+
"step": 1392
|
1248 |
+
},
|
1249 |
+
{
|
1250 |
+
"epoch": 155.54,
|
1251 |
+
"learning_rate": 0.0001,
|
1252 |
+
"loss": 0.0011,
|
1253 |
+
"step": 1400
|
1254 |
+
},
|
1255 |
+
{
|
1256 |
+
"epoch": 156.43,
|
1257 |
+
"learning_rate": 0.0001,
|
1258 |
+
"loss": 0.001,
|
1259 |
+
"step": 1408
|
1260 |
+
},
|
1261 |
+
{
|
1262 |
+
"epoch": 156.43,
|
1263 |
+
"eval_exact_match": 0.6134663341645885,
|
1264 |
+
"eval_exec": 0.6716541978387365,
|
1265 |
+
"eval_loss": 0.37701520323753357,
|
1266 |
+
"eval_runtime": 671.9945,
|
1267 |
+
"eval_samples_per_second": 2.418,
|
1268 |
+
"step": 1408
|
1269 |
+
},
|
1270 |
+
{
|
1271 |
+
"epoch": 157.32,
|
1272 |
+
"learning_rate": 0.0001,
|
1273 |
+
"loss": 0.0011,
|
1274 |
+
"step": 1416
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"epoch": 158.21,
|
1278 |
+
"learning_rate": 0.0001,
|
1279 |
+
"loss": 0.0008,
|
1280 |
+
"step": 1424
|
1281 |
+
},
|
1282 |
+
{
|
1283 |
+
"epoch": 159.11,
|
1284 |
+
"learning_rate": 0.0001,
|
1285 |
+
"loss": 0.001,
|
1286 |
+
"step": 1432
|
1287 |
+
},
|
1288 |
+
{
|
1289 |
+
"epoch": 159.97,
|
1290 |
+
"learning_rate": 0.0001,
|
1291 |
+
"loss": 0.0009,
|
1292 |
+
"step": 1440
|
1293 |
+
},
|
1294 |
+
{
|
1295 |
+
"epoch": 160.86,
|
1296 |
+
"learning_rate": 0.0001,
|
1297 |
+
"loss": 0.0009,
|
1298 |
+
"step": 1448
|
1299 |
+
},
|
1300 |
+
{
|
1301 |
+
"epoch": 161.75,
|
1302 |
+
"learning_rate": 0.0001,
|
1303 |
+
"loss": 0.001,
|
1304 |
+
"step": 1456
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 162.64,
|
1308 |
+
"learning_rate": 0.0001,
|
1309 |
+
"loss": 0.0009,
|
1310 |
+
"step": 1464
|
1311 |
+
},
|
1312 |
+
{
|
1313 |
+
"epoch": 163.54,
|
1314 |
+
"learning_rate": 0.0001,
|
1315 |
+
"loss": 0.001,
|
1316 |
+
"step": 1472
|
1317 |
+
},
|
1318 |
+
{
|
1319 |
+
"epoch": 163.54,
|
1320 |
+
"eval_exact_match": 0.6093100581878637,
|
1321 |
+
"eval_exec": 0.6683291770573566,
|
1322 |
+
"eval_loss": 0.38139888644218445,
|
1323 |
+
"eval_runtime": 629.7005,
|
1324 |
+
"eval_samples_per_second": 2.581,
|
1325 |
+
"step": 1472
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 164.43,
|
1329 |
+
"learning_rate": 0.0001,
|
1330 |
+
"loss": 0.0009,
|
1331 |
+
"step": 1480
|
1332 |
+
},
|
1333 |
+
{
|
1334 |
+
"epoch": 165.32,
|
1335 |
+
"learning_rate": 0.0001,
|
1336 |
+
"loss": 0.0012,
|
1337 |
+
"step": 1488
|
1338 |
+
},
|
1339 |
+
{
|
1340 |
+
"epoch": 166.21,
|
1341 |
+
"learning_rate": 0.0001,
|
1342 |
+
"loss": 0.0009,
|
1343 |
+
"step": 1496
|
1344 |
+
},
|
1345 |
+
{
|
1346 |
+
"epoch": 167.11,
|
1347 |
+
"learning_rate": 0.0001,
|
1348 |
+
"loss": 0.001,
|
1349 |
+
"step": 1504
|
1350 |
+
},
|
1351 |
+
{
|
1352 |
+
"epoch": 167.97,
|
1353 |
+
"learning_rate": 0.0001,
|
1354 |
+
"loss": 0.001,
|
1355 |
+
"step": 1512
|
1356 |
+
},
|
1357 |
+
{
|
1358 |
+
"epoch": 168.86,
|
1359 |
+
"learning_rate": 0.0001,
|
1360 |
+
"loss": 0.0009,
|
1361 |
+
"step": 1520
|
1362 |
+
},
|
1363 |
+
{
|
1364 |
+
"epoch": 169.75,
|
1365 |
+
"learning_rate": 0.0001,
|
1366 |
+
"loss": 0.0009,
|
1367 |
+
"step": 1528
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 170.64,
|
1371 |
+
"learning_rate": 0.0001,
|
1372 |
+
"loss": 0.0015,
|
1373 |
+
"step": 1536
|
1374 |
+
},
|
1375 |
+
{
|
1376 |
+
"epoch": 170.64,
|
1377 |
+
"eval_exact_match": 0.6259351620947631,
|
1378 |
+
"eval_exec": 0.6683291770573566,
|
1379 |
+
"eval_loss": 0.3713288903236389,
|
1380 |
+
"eval_runtime": 663.4255,
|
1381 |
+
"eval_samples_per_second": 2.449,
|
1382 |
+
"step": 1536
|
1383 |
+
},
|
1384 |
+
{
|
1385 |
+
"epoch": 171.54,
|
1386 |
+
"learning_rate": 0.0001,
|
1387 |
+
"loss": 0.0011,
|
1388 |
+
"step": 1544
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 172.43,
|
1392 |
+
"learning_rate": 0.0001,
|
1393 |
+
"loss": 0.0013,
|
1394 |
+
"step": 1552
|
1395 |
+
},
|
1396 |
+
{
|
1397 |
+
"epoch": 173.32,
|
1398 |
+
"learning_rate": 0.0001,
|
1399 |
+
"loss": 0.001,
|
1400 |
+
"step": 1560
|
1401 |
+
},
|
1402 |
+
{
|
1403 |
+
"epoch": 174.21,
|
1404 |
+
"learning_rate": 0.0001,
|
1405 |
+
"loss": 0.0008,
|
1406 |
+
"step": 1568
|
1407 |
+
},
|
1408 |
+
{
|
1409 |
+
"epoch": 175.11,
|
1410 |
+
"learning_rate": 0.0001,
|
1411 |
+
"loss": 0.0008,
|
1412 |
+
"step": 1576
|
1413 |
+
},
|
1414 |
+
{
|
1415 |
+
"epoch": 175.97,
|
1416 |
+
"learning_rate": 0.0001,
|
1417 |
+
"loss": 0.0014,
|
1418 |
+
"step": 1584
|
1419 |
+
},
|
1420 |
+
{
|
1421 |
+
"epoch": 176.86,
|
1422 |
+
"learning_rate": 0.0001,
|
1423 |
+
"loss": 0.0008,
|
1424 |
+
"step": 1592
|
1425 |
+
},
|
1426 |
+
{
|
1427 |
+
"epoch": 177.75,
|
1428 |
+
"learning_rate": 0.0001,
|
1429 |
+
"loss": 0.0011,
|
1430 |
+
"step": 1600
|
1431 |
+
},
|
1432 |
+
{
|
1433 |
+
"epoch": 177.75,
|
1434 |
+
"eval_exact_match": 0.6251039068994181,
|
1435 |
+
"eval_exec": 0.6674979218620116,
|
1436 |
+
"eval_loss": 0.37738731503486633,
|
1437 |
+
"eval_runtime": 559.3099,
|
1438 |
+
"eval_samples_per_second": 2.905,
|
1439 |
+
"step": 1600
|
1440 |
+
},
|
1441 |
+
{
|
1442 |
+
"epoch": 178.64,
|
1443 |
+
"learning_rate": 0.0001,
|
1444 |
+
"loss": 0.0007,
|
1445 |
+
"step": 1608
|
1446 |
+
},
|
1447 |
+
{
|
1448 |
+
"epoch": 179.54,
|
1449 |
+
"learning_rate": 0.0001,
|
1450 |
+
"loss": 0.001,
|
1451 |
+
"step": 1616
|
1452 |
+
},
|
1453 |
+
{
|
1454 |
+
"epoch": 180.43,
|
1455 |
+
"learning_rate": 0.0001,
|
1456 |
+
"loss": 0.0008,
|
1457 |
+
"step": 1624
|
1458 |
+
},
|
1459 |
+
{
|
1460 |
+
"epoch": 181.32,
|
1461 |
+
"learning_rate": 0.0001,
|
1462 |
+
"loss": 0.0008,
|
1463 |
+
"step": 1632
|
1464 |
+
},
|
1465 |
+
{
|
1466 |
+
"epoch": 182.21,
|
1467 |
+
"learning_rate": 0.0001,
|
1468 |
+
"loss": 0.001,
|
1469 |
+
"step": 1640
|
1470 |
+
},
|
1471 |
+
{
|
1472 |
+
"epoch": 183.11,
|
1473 |
+
"learning_rate": 0.0001,
|
1474 |
+
"loss": 0.0009,
|
1475 |
+
"step": 1648
|
1476 |
+
},
|
1477 |
+
{
|
1478 |
+
"epoch": 183.97,
|
1479 |
+
"learning_rate": 0.0001,
|
1480 |
+
"loss": 0.003,
|
1481 |
+
"step": 1656
|
1482 |
+
},
|
1483 |
+
{
|
1484 |
+
"epoch": 184.86,
|
1485 |
+
"learning_rate": 0.0001,
|
1486 |
+
"loss": 0.001,
|
1487 |
+
"step": 1664
|
1488 |
+
},
|
1489 |
+
{
|
1490 |
+
"epoch": 184.86,
|
1491 |
+
"eval_exact_match": 0.6118038237738986,
|
1492 |
+
"eval_exec": 0.6616791354945969,
|
1493 |
+
"eval_loss": 0.37692150473594666,
|
1494 |
+
"eval_runtime": 654.8531,
|
1495 |
+
"eval_samples_per_second": 2.481,
|
1496 |
+
"step": 1664
|
1497 |
+
},
|
1498 |
+
{
|
1499 |
+
"epoch": 185.75,
|
1500 |
+
"learning_rate": 0.0001,
|
1501 |
+
"loss": 0.0013,
|
1502 |
+
"step": 1672
|
1503 |
+
},
|
1504 |
+
{
|
1505 |
+
"epoch": 186.64,
|
1506 |
+
"learning_rate": 0.0001,
|
1507 |
+
"loss": 0.001,
|
1508 |
+
"step": 1680
|
1509 |
+
},
|
1510 |
+
{
|
1511 |
+
"epoch": 187.54,
|
1512 |
+
"learning_rate": 0.0001,
|
1513 |
+
"loss": 0.0009,
|
1514 |
+
"step": 1688
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 188.43,
|
1518 |
+
"learning_rate": 0.0001,
|
1519 |
+
"loss": 0.0022,
|
1520 |
+
"step": 1696
|
1521 |
+
},
|
1522 |
+
{
|
1523 |
+
"epoch": 189.32,
|
1524 |
+
"learning_rate": 0.0001,
|
1525 |
+
"loss": 0.0011,
|
1526 |
+
"step": 1704
|
1527 |
+
},
|
1528 |
+
{
|
1529 |
+
"epoch": 190.21,
|
1530 |
+
"learning_rate": 0.0001,
|
1531 |
+
"loss": 0.0009,
|
1532 |
+
"step": 1712
|
1533 |
+
},
|
1534 |
+
{
|
1535 |
+
"epoch": 191.11,
|
1536 |
+
"learning_rate": 0.0001,
|
1537 |
+
"loss": 0.0009,
|
1538 |
+
"step": 1720
|
1539 |
+
},
|
1540 |
+
{
|
1541 |
+
"epoch": 191.97,
|
1542 |
+
"learning_rate": 0.0001,
|
1543 |
+
"loss": 0.0009,
|
1544 |
+
"step": 1728
|
1545 |
+
},
|
1546 |
+
{
|
1547 |
+
"epoch": 191.97,
|
1548 |
+
"eval_exact_match": 0.6226101413133832,
|
1549 |
+
"eval_exec": 0.6758104738154613,
|
1550 |
+
"eval_loss": 0.3892926275730133,
|
1551 |
+
"eval_runtime": 604.6134,
|
1552 |
+
"eval_samples_per_second": 2.688,
|
1553 |
+
"step": 1728
|
1554 |
+
},
|
1555 |
+
{
|
1556 |
+
"epoch": 192.86,
|
1557 |
+
"learning_rate": 0.0001,
|
1558 |
+
"loss": 0.001,
|
1559 |
+
"step": 1736
|
1560 |
+
},
|
1561 |
+
{
|
1562 |
+
"epoch": 193.75,
|
1563 |
+
"learning_rate": 0.0001,
|
1564 |
+
"loss": 0.0009,
|
1565 |
+
"step": 1744
|
1566 |
+
},
|
1567 |
+
{
|
1568 |
+
"epoch": 194.64,
|
1569 |
+
"learning_rate": 0.0001,
|
1570 |
+
"loss": 0.0007,
|
1571 |
+
"step": 1752
|
1572 |
+
},
|
1573 |
+
{
|
1574 |
+
"epoch": 195.54,
|
1575 |
+
"learning_rate": 0.0001,
|
1576 |
+
"loss": 0.001,
|
1577 |
+
"step": 1760
|
1578 |
+
},
|
1579 |
+
{
|
1580 |
+
"epoch": 196.43,
|
1581 |
+
"learning_rate": 0.0001,
|
1582 |
+
"loss": 0.0008,
|
1583 |
+
"step": 1768
|
1584 |
+
},
|
1585 |
+
{
|
1586 |
+
"epoch": 197.32,
|
1587 |
+
"learning_rate": 0.0001,
|
1588 |
+
"loss": 0.0009,
|
1589 |
+
"step": 1776
|
1590 |
+
},
|
1591 |
+
{
|
1592 |
+
"epoch": 198.21,
|
1593 |
+
"learning_rate": 0.0001,
|
1594 |
+
"loss": 0.0008,
|
1595 |
+
"step": 1784
|
1596 |
+
},
|
1597 |
+
{
|
1598 |
+
"epoch": 199.11,
|
1599 |
+
"learning_rate": 0.0001,
|
1600 |
+
"loss": 0.0009,
|
1601 |
+
"step": 1792
|
1602 |
+
},
|
1603 |
+
{
|
1604 |
+
"epoch": 199.11,
|
1605 |
+
"eval_exact_match": 0.6275976724854531,
|
1606 |
+
"eval_exec": 0.6758104738154613,
|
1607 |
+
"eval_loss": 0.3943491578102112,
|
1608 |
+
"eval_runtime": 616.8463,
|
1609 |
+
"eval_samples_per_second": 2.634,
|
1610 |
+
"step": 1792
|
1611 |
+
},
|
1612 |
+
{
|
1613 |
+
"epoch": 199.97,
|
1614 |
+
"learning_rate": 0.0001,
|
1615 |
+
"loss": 0.0009,
|
1616 |
+
"step": 1800
|
1617 |
+
},
|
1618 |
+
{
|
1619 |
+
"epoch": 200.86,
|
1620 |
+
"learning_rate": 0.0001,
|
1621 |
+
"loss": 0.0033,
|
1622 |
+
"step": 1808
|
1623 |
+
},
|
1624 |
+
{
|
1625 |
+
"epoch": 201.75,
|
1626 |
+
"learning_rate": 0.0001,
|
1627 |
+
"loss": 0.0008,
|
1628 |
+
"step": 1816
|
1629 |
+
},
|
1630 |
+
{
|
1631 |
+
"epoch": 202.64,
|
1632 |
+
"learning_rate": 0.0001,
|
1633 |
+
"loss": 0.002,
|
1634 |
+
"step": 1824
|
1635 |
+
},
|
1636 |
+
{
|
1637 |
+
"epoch": 203.54,
|
1638 |
+
"learning_rate": 0.0001,
|
1639 |
+
"loss": 0.0011,
|
1640 |
+
"step": 1832
|
1641 |
+
},
|
1642 |
+
{
|
1643 |
+
"epoch": 204.43,
|
1644 |
+
"learning_rate": 0.0001,
|
1645 |
+
"loss": 0.0014,
|
1646 |
+
"step": 1840
|
1647 |
+
},
|
1648 |
+
{
|
1649 |
+
"epoch": 205.32,
|
1650 |
+
"learning_rate": 0.0001,
|
1651 |
+
"loss": 0.001,
|
1652 |
+
"step": 1848
|
1653 |
+
},
|
1654 |
+
{
|
1655 |
+
"epoch": 206.21,
|
1656 |
+
"learning_rate": 0.0001,
|
1657 |
+
"loss": 0.0009,
|
1658 |
+
"step": 1856
|
1659 |
+
},
|
1660 |
+
{
|
1661 |
+
"epoch": 206.21,
|
1662 |
+
"eval_exact_match": 0.6350789692435578,
|
1663 |
+
"eval_exec": 0.6816292601828762,
|
1664 |
+
"eval_loss": 0.3747319281101227,
|
1665 |
+
"eval_runtime": 608.1838,
|
1666 |
+
"eval_samples_per_second": 2.672,
|
1667 |
+
"step": 1856
|
1668 |
+
},
|
1669 |
+
{
|
1670 |
+
"epoch": 207.11,
|
1671 |
+
"learning_rate": 0.0001,
|
1672 |
+
"loss": 0.0008,
|
1673 |
+
"step": 1864
|
1674 |
+
},
|
1675 |
+
{
|
1676 |
+
"epoch": 207.97,
|
1677 |
+
"learning_rate": 0.0001,
|
1678 |
+
"loss": 0.0009,
|
1679 |
+
"step": 1872
|
1680 |
+
},
|
1681 |
+
{
|
1682 |
+
"epoch": 208.86,
|
1683 |
+
"learning_rate": 0.0001,
|
1684 |
+
"loss": 0.0009,
|
1685 |
+
"step": 1880
|
1686 |
+
},
|
1687 |
+
{
|
1688 |
+
"epoch": 209.75,
|
1689 |
+
"learning_rate": 0.0001,
|
1690 |
+
"loss": 0.001,
|
1691 |
+
"step": 1888
|
1692 |
+
},
|
1693 |
+
{
|
1694 |
+
"epoch": 210.64,
|
1695 |
+
"learning_rate": 0.0001,
|
1696 |
+
"loss": 0.0013,
|
1697 |
+
"step": 1896
|
1698 |
+
},
|
1699 |
+
{
|
1700 |
+
"epoch": 211.54,
|
1701 |
+
"learning_rate": 0.0001,
|
1702 |
+
"loss": 0.0204,
|
1703 |
+
"step": 1904
|
1704 |
+
},
|
1705 |
+
{
|
1706 |
+
"epoch": 212.43,
|
1707 |
+
"learning_rate": 0.0001,
|
1708 |
+
"loss": 0.0007,
|
1709 |
+
"step": 1912
|
1710 |
+
},
|
1711 |
+
{
|
1712 |
+
"epoch": 213.32,
|
1713 |
+
"learning_rate": 0.0001,
|
1714 |
+
"loss": 0.0006,
|
1715 |
+
"step": 1920
|
1716 |
+
},
|
1717 |
+
{
|
1718 |
+
"epoch": 213.32,
|
1719 |
+
"eval_exact_match": 0.628428927680798,
|
1720 |
+
"eval_exec": 0.6749792186201163,
|
1721 |
+
"eval_loss": 0.3832400143146515,
|
1722 |
+
"eval_runtime": 602.0466,
|
1723 |
+
"eval_samples_per_second": 2.699,
|
1724 |
+
"step": 1920
|
1725 |
+
},
|
1726 |
+
{
|
1727 |
+
"epoch": 214.21,
|
1728 |
+
"learning_rate": 0.0001,
|
1729 |
+
"loss": 0.0007,
|
1730 |
+
"step": 1928
|
1731 |
+
},
|
1732 |
+
{
|
1733 |
+
"epoch": 215.11,
|
1734 |
+
"learning_rate": 0.0001,
|
1735 |
+
"loss": 0.0007,
|
1736 |
+
"step": 1936
|
1737 |
+
},
|
1738 |
+
{
|
1739 |
+
"epoch": 215.97,
|
1740 |
+
"learning_rate": 0.0001,
|
1741 |
+
"loss": 0.0008,
|
1742 |
+
"step": 1944
|
1743 |
+
},
|
1744 |
+
{
|
1745 |
+
"epoch": 216.86,
|
1746 |
+
"learning_rate": 0.0001,
|
1747 |
+
"loss": 0.0007,
|
1748 |
+
"step": 1952
|
1749 |
+
},
|
1750 |
+
{
|
1751 |
+
"epoch": 217.75,
|
1752 |
+
"learning_rate": 0.0001,
|
1753 |
+
"loss": 0.0007,
|
1754 |
+
"step": 1960
|
1755 |
+
},
|
1756 |
+
{
|
1757 |
+
"epoch": 218.64,
|
1758 |
+
"learning_rate": 0.0001,
|
1759 |
+
"loss": 0.0007,
|
1760 |
+
"step": 1968
|
1761 |
+
},
|
1762 |
+
{
|
1763 |
+
"epoch": 219.54,
|
1764 |
+
"learning_rate": 0.0001,
|
1765 |
+
"loss": 0.0008,
|
1766 |
+
"step": 1976
|
1767 |
+
},
|
1768 |
+
{
|
1769 |
+
"epoch": 220.43,
|
1770 |
+
"learning_rate": 0.0001,
|
1771 |
+
"loss": 0.0007,
|
1772 |
+
"step": 1984
|
1773 |
+
},
|
1774 |
+
{
|
1775 |
+
"epoch": 220.43,
|
1776 |
+
"eval_exact_match": 0.6275976724854531,
|
1777 |
+
"eval_exec": 0.6758104738154613,
|
1778 |
+
"eval_loss": 0.3946389853954315,
|
1779 |
+
"eval_runtime": 614.3111,
|
1780 |
+
"eval_samples_per_second": 2.645,
|
1781 |
+
"step": 1984
|
1782 |
+
},
|
1783 |
+
{
|
1784 |
+
"epoch": 221.32,
|
1785 |
+
"learning_rate": 0.0001,
|
1786 |
+
"loss": 0.0007,
|
1787 |
+
"step": 1992
|
1788 |
+
},
|
1789 |
+
{
|
1790 |
+
"epoch": 222.21,
|
1791 |
+
"learning_rate": 0.0001,
|
1792 |
+
"loss": 0.0007,
|
1793 |
+
"step": 2000
|
1794 |
+
},
|
1795 |
+
{
|
1796 |
+
"epoch": 223.11,
|
1797 |
+
"learning_rate": 0.0001,
|
1798 |
+
"loss": 0.0006,
|
1799 |
+
"step": 2008
|
1800 |
+
},
|
1801 |
+
{
|
1802 |
+
"epoch": 223.97,
|
1803 |
+
"learning_rate": 0.0001,
|
1804 |
+
"loss": 0.0007,
|
1805 |
+
"step": 2016
|
1806 |
+
},
|
1807 |
+
{
|
1808 |
+
"epoch": 224.86,
|
1809 |
+
"learning_rate": 0.0001,
|
1810 |
+
"loss": 0.0006,
|
1811 |
+
"step": 2024
|
1812 |
+
},
|
1813 |
+
{
|
1814 |
+
"epoch": 225.75,
|
1815 |
+
"learning_rate": 0.0001,
|
1816 |
+
"loss": 0.0085,
|
1817 |
+
"step": 2032
|
1818 |
+
},
|
1819 |
+
{
|
1820 |
+
"epoch": 226.64,
|
1821 |
+
"learning_rate": 0.0001,
|
1822 |
+
"loss": 0.0028,
|
1823 |
+
"step": 2040
|
1824 |
+
},
|
1825 |
+
{
|
1826 |
+
"epoch": 227.54,
|
1827 |
+
"learning_rate": 0.0001,
|
1828 |
+
"loss": 0.0007,
|
1829 |
+
"step": 2048
|
1830 |
+
},
|
1831 |
+
{
|
1832 |
+
"epoch": 227.54,
|
1833 |
+
"eval_exact_match": 0.6334164588528678,
|
1834 |
+
"eval_exec": 0.6749792186201163,
|
1835 |
+
"eval_loss": 0.3720964789390564,
|
1836 |
+
"eval_runtime": 625.9541,
|
1837 |
+
"eval_samples_per_second": 2.596,
|
1838 |
+
"step": 2048
|
1839 |
+
},
|
1840 |
+
{
|
1841 |
+
"epoch": 228.43,
|
1842 |
+
"learning_rate": 0.0001,
|
1843 |
+
"loss": 0.0007,
|
1844 |
+
"step": 2056
|
1845 |
+
},
|
1846 |
+
{
|
1847 |
+
"epoch": 229.32,
|
1848 |
+
"learning_rate": 0.0001,
|
1849 |
+
"loss": 0.0006,
|
1850 |
+
"step": 2064
|
1851 |
+
},
|
1852 |
+
{
|
1853 |
+
"epoch": 230.21,
|
1854 |
+
"learning_rate": 0.0001,
|
1855 |
+
"loss": 0.0006,
|
1856 |
+
"step": 2072
|
1857 |
+
},
|
1858 |
+
{
|
1859 |
+
"epoch": 231.11,
|
1860 |
+
"learning_rate": 0.0001,
|
1861 |
+
"loss": 0.0007,
|
1862 |
+
"step": 2080
|
1863 |
+
},
|
1864 |
+
{
|
1865 |
+
"epoch": 231.97,
|
1866 |
+
"learning_rate": 0.0001,
|
1867 |
+
"loss": 0.0005,
|
1868 |
+
"step": 2088
|
1869 |
+
},
|
1870 |
+
{
|
1871 |
+
"epoch": 232.86,
|
1872 |
+
"learning_rate": 0.0001,
|
1873 |
+
"loss": 0.0006,
|
1874 |
+
"step": 2096
|
1875 |
+
},
|
1876 |
+
{
|
1877 |
+
"epoch": 233.75,
|
1878 |
+
"learning_rate": 0.0001,
|
1879 |
+
"loss": 0.0006,
|
1880 |
+
"step": 2104
|
1881 |
+
},
|
1882 |
+
{
|
1883 |
+
"epoch": 234.64,
|
1884 |
+
"learning_rate": 0.0001,
|
1885 |
+
"loss": 0.0008,
|
1886 |
+
"step": 2112
|
1887 |
+
},
|
1888 |
+
{
|
1889 |
+
"epoch": 234.64,
|
1890 |
+
"eval_exact_match": 0.6226101413133832,
|
1891 |
+
"eval_exec": 0.6766417290108063,
|
1892 |
+
"eval_loss": 0.3971711993217468,
|
1893 |
+
"eval_runtime": 618.6026,
|
1894 |
+
"eval_samples_per_second": 2.627,
|
1895 |
+
"step": 2112
|
1896 |
+
},
|
1897 |
+
{
|
1898 |
+
"epoch": 235.54,
|
1899 |
+
"learning_rate": 0.0001,
|
1900 |
+
"loss": 0.0009,
|
1901 |
+
"step": 2120
|
1902 |
+
},
|
1903 |
+
{
|
1904 |
+
"epoch": 236.43,
|
1905 |
+
"learning_rate": 0.0001,
|
1906 |
+
"loss": 0.0006,
|
1907 |
+
"step": 2128
|
1908 |
+
},
|
1909 |
+
{
|
1910 |
+
"epoch": 237.32,
|
1911 |
+
"learning_rate": 0.0001,
|
1912 |
+
"loss": 0.0008,
|
1913 |
+
"step": 2136
|
1914 |
+
},
|
1915 |
+
{
|
1916 |
+
"epoch": 238.21,
|
1917 |
+
"learning_rate": 0.0001,
|
1918 |
+
"loss": 0.0006,
|
1919 |
+
"step": 2144
|
1920 |
+
},
|
1921 |
+
{
|
1922 |
+
"epoch": 239.11,
|
1923 |
+
"learning_rate": 0.0001,
|
1924 |
+
"loss": 0.0006,
|
1925 |
+
"step": 2152
|
1926 |
+
},
|
1927 |
+
{
|
1928 |
+
"epoch": 239.97,
|
1929 |
+
"learning_rate": 0.0001,
|
1930 |
+
"loss": 0.0007,
|
1931 |
+
"step": 2160
|
1932 |
+
},
|
1933 |
+
{
|
1934 |
+
"epoch": 240.86,
|
1935 |
+
"learning_rate": 0.0001,
|
1936 |
+
"loss": 0.0007,
|
1937 |
+
"step": 2168
|
1938 |
+
},
|
1939 |
+
{
|
1940 |
+
"epoch": 241.75,
|
1941 |
+
"learning_rate": 0.0001,
|
1942 |
+
"loss": 0.0021,
|
1943 |
+
"step": 2176
|
1944 |
+
},
|
1945 |
+
{
|
1946 |
+
"epoch": 241.75,
|
1947 |
+
"eval_exact_match": 0.6292601828761429,
|
1948 |
+
"eval_exec": 0.6783042394014963,
|
1949 |
+
"eval_loss": 0.3668304681777954,
|
1950 |
+
"eval_runtime": 553.3572,
|
1951 |
+
"eval_samples_per_second": 2.937,
|
1952 |
+
"step": 2176
|
1953 |
+
},
|
1954 |
+
{
|
1955 |
+
"epoch": 242.64,
|
1956 |
+
"learning_rate": 0.0001,
|
1957 |
+
"loss": 0.0006,
|
1958 |
+
"step": 2184
|
1959 |
+
},
|
1960 |
+
{
|
1961 |
+
"epoch": 243.54,
|
1962 |
+
"learning_rate": 0.0001,
|
1963 |
+
"loss": 0.0017,
|
1964 |
+
"step": 2192
|
1965 |
+
},
|
1966 |
+
{
|
1967 |
+
"epoch": 244.43,
|
1968 |
+
"learning_rate": 0.0001,
|
1969 |
+
"loss": 0.0007,
|
1970 |
+
"step": 2200
|
1971 |
+
},
|
1972 |
+
{
|
1973 |
+
"epoch": 245.32,
|
1974 |
+
"learning_rate": 0.0001,
|
1975 |
+
"loss": 0.0008,
|
1976 |
+
"step": 2208
|
1977 |
+
},
|
1978 |
+
{
|
1979 |
+
"epoch": 246.21,
|
1980 |
+
"learning_rate": 0.0001,
|
1981 |
+
"loss": 0.0008,
|
1982 |
+
"step": 2216
|
1983 |
+
},
|
1984 |
+
{
|
1985 |
+
"epoch": 247.11,
|
1986 |
+
"learning_rate": 0.0001,
|
1987 |
+
"loss": 0.0006,
|
1988 |
+
"step": 2224
|
1989 |
+
},
|
1990 |
+
{
|
1991 |
+
"epoch": 247.97,
|
1992 |
+
"learning_rate": 0.0001,
|
1993 |
+
"loss": 0.0006,
|
1994 |
+
"step": 2232
|
1995 |
+
},
|
1996 |
+
{
|
1997 |
+
"epoch": 248.86,
|
1998 |
+
"learning_rate": 0.0001,
|
1999 |
+
"loss": 0.0007,
|
2000 |
+
"step": 2240
|
2001 |
+
},
|
2002 |
+
{
|
2003 |
+
"epoch": 248.86,
|
2004 |
+
"eval_exact_match": 0.6217788861180382,
|
2005 |
+
"eval_exec": 0.6741479634247715,
|
2006 |
+
"eval_loss": 0.3940756320953369,
|
2007 |
+
"eval_runtime": 599.5801,
|
2008 |
+
"eval_samples_per_second": 2.71,
|
2009 |
+
"step": 2240
|
2010 |
+
},
|
2011 |
+
{
|
2012 |
+
"epoch": 249.75,
|
2013 |
+
"learning_rate": 0.0001,
|
2014 |
+
"loss": 0.0007,
|
2015 |
+
"step": 2248
|
2016 |
+
},
|
2017 |
+
{
|
2018 |
+
"epoch": 250.64,
|
2019 |
+
"learning_rate": 0.0001,
|
2020 |
+
"loss": 0.0007,
|
2021 |
+
"step": 2256
|
2022 |
+
},
|
2023 |
+
{
|
2024 |
+
"epoch": 251.54,
|
2025 |
+
"learning_rate": 0.0001,
|
2026 |
+
"loss": 0.0007,
|
2027 |
+
"step": 2264
|
2028 |
+
},
|
2029 |
+
{
|
2030 |
+
"epoch": 252.43,
|
2031 |
+
"learning_rate": 0.0001,
|
2032 |
+
"loss": 0.0007,
|
2033 |
+
"step": 2272
|
2034 |
+
},
|
2035 |
+
{
|
2036 |
+
"epoch": 253.32,
|
2037 |
+
"learning_rate": 0.0001,
|
2038 |
+
"loss": 0.0007,
|
2039 |
+
"step": 2280
|
2040 |
+
},
|
2041 |
+
{
|
2042 |
+
"epoch": 254.21,
|
2043 |
+
"learning_rate": 0.0001,
|
2044 |
+
"loss": 0.0006,
|
2045 |
+
"step": 2288
|
2046 |
+
},
|
2047 |
+
{
|
2048 |
+
"epoch": 255.11,
|
2049 |
+
"learning_rate": 0.0001,
|
2050 |
+
"loss": 0.0006,
|
2051 |
+
"step": 2296
|
2052 |
+
},
|
2053 |
+
{
|
2054 |
+
"epoch": 255.97,
|
2055 |
+
"learning_rate": 0.0001,
|
2056 |
+
"loss": 0.0006,
|
2057 |
+
"step": 2304
|
2058 |
+
},
|
2059 |
+
{
|
2060 |
+
"epoch": 255.97,
|
2061 |
+
"eval_exact_match": 0.6359102244389028,
|
2062 |
+
"eval_exec": 0.686616791354946,
|
2063 |
+
"eval_loss": 0.39379316568374634,
|
2064 |
+
"eval_runtime": 602.7618,
|
2065 |
+
"eval_samples_per_second": 2.696,
|
2066 |
+
"step": 2304
|
2067 |
+
}
|
2068 |
+
],
|
2069 |
+
"max_steps": 27648,
|
2070 |
+
"num_train_epochs": 3072,
|
2071 |
+
"total_flos": 1.7577156158550966e+19,
|
2072 |
+
"trial_name": null,
|
2073 |
+
"trial_params": null
|
2074 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e93f286a6e00a4925bce29e7e7d788007d56bf677afec65728af3c30fd4a1b7c
|
3 |
+
size 3247
|