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 +1219 -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 sha256:8fe48edcdde23a5588a8549e95d5fb0486a24896dd13293ae133da43c434319b
|
| 3 |
+
size 13613718
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf9bc74b2bd104548cd8d02ca84bc5ebc48d655bdc6178305d1bda78a31a5204
|
| 3 |
+
size 11406574787
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46c7db0971706b9b41b656bca5de0bf4e3415d9d07ca30ff7e56b27de4b1c9a7
|
| 3 |
+
size 14503
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fec7052ce05353952c02ae680c11e93e7b4882635632849448bfcb6a1a554f2
|
| 3 |
+
size 14503
|
rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:acd7598c1bcabb0da9e5c29ca62e28a9152e30b0adba51a0f8c008df3b6d00db
|
| 3 |
+
size 14503
|
rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6f716e16e4b6f6636e37e3b264a835604632c793457ab2b71e515dc8e019891
|
| 3 |
+
size 14503
|
rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fc534771cbd511dce1ca527c835875ebd4e9163a210e159a450dfa82c4aa96c
|
| 3 |
+
size 14503
|
rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad195f13d8edcfe4858c44b3efce017d83e50a69f321706095f823906c2ee56e
|
| 3 |
+
size 14503
|
rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ab2d037db58e19f2f19b4fc839a3e6d3dd2636e70d755dd4bb8e61cdf218c5b
|
| 3 |
+
size 14503
|
rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf1ddef438519730ed04a34dee735ef88cc53c7bf11fea71ab591e651a830ab6
|
| 3 |
+
size 14503
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3317509e5c26afaecf7a0c073b5425c1bd0d79d65aff9354b8a1c0dd28253e19
|
| 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 +1,1219 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6317539484621779,
|
| 3 |
+
"best_model_checkpoint": "./experiment/train_0503_sparc_no_coref_only_dependency/checkpoint-1344",
|
| 4 |
+
"epoch": 149.3221476510067,
|
| 5 |
+
"global_step": 1344,
|
| 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": 3.6153,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.86,
|
| 18 |
+
"learning_rate": 0.0001,
|
| 19 |
+
"loss": 1.5839,
|
| 20 |
+
"step": 8
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.75,
|
| 24 |
+
"learning_rate": 0.0001,
|
| 25 |
+
"loss": 0.5896,
|
| 26 |
+
"step": 16
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 2.64,
|
| 30 |
+
"learning_rate": 0.0001,
|
| 31 |
+
"loss": 0.352,
|
| 32 |
+
"step": 24
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 3.54,
|
| 36 |
+
"learning_rate": 0.0001,
|
| 37 |
+
"loss": 0.2808,
|
| 38 |
+
"step": 32
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 4.43,
|
| 42 |
+
"learning_rate": 0.0001,
|
| 43 |
+
"loss": 0.2175,
|
| 44 |
+
"step": 40
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 5.32,
|
| 48 |
+
"learning_rate": 0.0001,
|
| 49 |
+
"loss": 0.1583,
|
| 50 |
+
"step": 48
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 6.21,
|
| 54 |
+
"learning_rate": 0.0001,
|
| 55 |
+
"loss": 0.13,
|
| 56 |
+
"step": 56
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 7.11,
|
| 60 |
+
"learning_rate": 0.0001,
|
| 61 |
+
"loss": 0.1486,
|
| 62 |
+
"step": 64
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 7.11,
|
| 66 |
+
"eval_exact_match": 0.48960931005818786,
|
| 67 |
+
"eval_exec": 0.542809642560266,
|
| 68 |
+
"eval_loss": 0.17051339149475098,
|
| 69 |
+
"eval_runtime": 473.2311,
|
| 70 |
+
"eval_samples_per_second": 3.434,
|
| 71 |
+
"step": 64
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 7.97,
|
| 75 |
+
"learning_rate": 0.0001,
|
| 76 |
+
"loss": 0.1015,
|
| 77 |
+
"step": 72
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 8.86,
|
| 81 |
+
"learning_rate": 0.0001,
|
| 82 |
+
"loss": 0.0976,
|
| 83 |
+
"step": 80
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 9.75,
|
| 87 |
+
"learning_rate": 0.0001,
|
| 88 |
+
"loss": 0.0801,
|
| 89 |
+
"step": 88
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 10.64,
|
| 93 |
+
"learning_rate": 0.0001,
|
| 94 |
+
"loss": 0.0797,
|
| 95 |
+
"step": 96
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 11.54,
|
| 99 |
+
"learning_rate": 0.0001,
|
| 100 |
+
"loss": 0.0718,
|
| 101 |
+
"step": 104
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 12.43,
|
| 105 |
+
"learning_rate": 0.0001,
|
| 106 |
+
"loss": 0.061,
|
| 107 |
+
"step": 112
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 13.32,
|
| 111 |
+
"learning_rate": 0.0001,
|
| 112 |
+
"loss": 0.0583,
|
| 113 |
+
"step": 120
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 14.21,
|
| 117 |
+
"learning_rate": 0.0001,
|
| 118 |
+
"loss": 0.0491,
|
| 119 |
+
"step": 128
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 14.21,
|
| 123 |
+
"eval_exact_match": 0.5403158769742311,
|
| 124 |
+
"eval_exec": 0.6201163757273483,
|
| 125 |
+
"eval_loss": 0.17214366793632507,
|
| 126 |
+
"eval_runtime": 803.5727,
|
| 127 |
+
"eval_samples_per_second": 2.022,
|
| 128 |
+
"step": 128
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 15.11,
|
| 132 |
+
"learning_rate": 0.0001,
|
| 133 |
+
"loss": 0.048,
|
| 134 |
+
"step": 136
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 15.97,
|
| 138 |
+
"learning_rate": 0.0001,
|
| 139 |
+
"loss": 0.039,
|
| 140 |
+
"step": 144
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 16.86,
|
| 144 |
+
"learning_rate": 0.0001,
|
| 145 |
+
"loss": 0.0393,
|
| 146 |
+
"step": 152
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 17.75,
|
| 150 |
+
"learning_rate": 0.0001,
|
| 151 |
+
"loss": 0.0423,
|
| 152 |
+
"step": 160
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 18.64,
|
| 156 |
+
"learning_rate": 0.0001,
|
| 157 |
+
"loss": 0.0375,
|
| 158 |
+
"step": 168
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 19.54,
|
| 162 |
+
"learning_rate": 0.0001,
|
| 163 |
+
"loss": 0.0439,
|
| 164 |
+
"step": 176
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 20.43,
|
| 168 |
+
"learning_rate": 0.0001,
|
| 169 |
+
"loss": 0.026,
|
| 170 |
+
"step": 184
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 21.32,
|
| 174 |
+
"learning_rate": 0.0001,
|
| 175 |
+
"loss": 0.024,
|
| 176 |
+
"step": 192
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 21.32,
|
| 180 |
+
"eval_exact_match": 0.5502909393183707,
|
| 181 |
+
"eval_exec": 0.6084788029925187,
|
| 182 |
+
"eval_loss": 0.19952385127544403,
|
| 183 |
+
"eval_runtime": 654.4546,
|
| 184 |
+
"eval_samples_per_second": 2.483,
|
| 185 |
+
"step": 192
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 22.21,
|
| 189 |
+
"learning_rate": 0.0001,
|
| 190 |
+
"loss": 0.0227,
|
| 191 |
+
"step": 200
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 23.11,
|
| 195 |
+
"learning_rate": 0.0001,
|
| 196 |
+
"loss": 0.02,
|
| 197 |
+
"step": 208
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 23.97,
|
| 201 |
+
"learning_rate": 0.0001,
|
| 202 |
+
"loss": 0.018,
|
| 203 |
+
"step": 216
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 24.86,
|
| 207 |
+
"learning_rate": 0.0001,
|
| 208 |
+
"loss": 0.0175,
|
| 209 |
+
"step": 224
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 25.75,
|
| 213 |
+
"learning_rate": 0.0001,
|
| 214 |
+
"loss": 0.0161,
|
| 215 |
+
"step": 232
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 26.64,
|
| 219 |
+
"learning_rate": 0.0001,
|
| 220 |
+
"loss": 0.0136,
|
| 221 |
+
"step": 240
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 27.54,
|
| 225 |
+
"learning_rate": 0.0001,
|
| 226 |
+
"loss": 0.0135,
|
| 227 |
+
"step": 248
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 28.43,
|
| 231 |
+
"learning_rate": 0.0001,
|
| 232 |
+
"loss": 0.013,
|
| 233 |
+
"step": 256
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 28.43,
|
| 237 |
+
"eval_exact_match": 0.5694098088113051,
|
| 238 |
+
"eval_exec": 0.6325852036575229,
|
| 239 |
+
"eval_loss": 0.23655764758586884,
|
| 240 |
+
"eval_runtime": 762.1152,
|
| 241 |
+
"eval_samples_per_second": 2.132,
|
| 242 |
+
"step": 256
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 29.32,
|
| 246 |
+
"learning_rate": 0.0001,
|
| 247 |
+
"loss": 0.0123,
|
| 248 |
+
"step": 264
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 30.21,
|
| 252 |
+
"learning_rate": 0.0001,
|
| 253 |
+
"loss": 0.012,
|
| 254 |
+
"step": 272
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 31.11,
|
| 258 |
+
"learning_rate": 0.0001,
|
| 259 |
+
"loss": 0.0133,
|
| 260 |
+
"step": 280
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 31.97,
|
| 264 |
+
"learning_rate": 0.0001,
|
| 265 |
+
"loss": 0.0094,
|
| 266 |
+
"step": 288
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 32.86,
|
| 270 |
+
"learning_rate": 0.0001,
|
| 271 |
+
"loss": 0.0166,
|
| 272 |
+
"step": 296
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 33.75,
|
| 276 |
+
"learning_rate": 0.0001,
|
| 277 |
+
"loss": 0.0154,
|
| 278 |
+
"step": 304
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 34.64,
|
| 282 |
+
"learning_rate": 0.0001,
|
| 283 |
+
"loss": 0.0109,
|
| 284 |
+
"step": 312
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 35.54,
|
| 288 |
+
"learning_rate": 0.0001,
|
| 289 |
+
"loss": 0.0077,
|
| 290 |
+
"step": 320
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 35.54,
|
| 294 |
+
"eval_exact_match": 0.5901911886949294,
|
| 295 |
+
"eval_exec": 0.6408977556109726,
|
| 296 |
+
"eval_loss": 0.259878933429718,
|
| 297 |
+
"eval_runtime": 661.2927,
|
| 298 |
+
"eval_samples_per_second": 2.457,
|
| 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": 0.0066,
|
| 311 |
+
"step": 336
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 38.21,
|
| 315 |
+
"learning_rate": 0.0001,
|
| 316 |
+
"loss": 0.0064,
|
| 317 |
+
"step": 344
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 39.11,
|
| 321 |
+
"learning_rate": 0.0001,
|
| 322 |
+
"loss": 0.007,
|
| 323 |
+
"step": 352
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 39.97,
|
| 327 |
+
"learning_rate": 0.0001,
|
| 328 |
+
"loss": 0.0165,
|
| 329 |
+
"step": 360
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 40.86,
|
| 333 |
+
"learning_rate": 0.0001,
|
| 334 |
+
"loss": 0.0063,
|
| 335 |
+
"step": 368
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 41.75,
|
| 339 |
+
"learning_rate": 0.0001,
|
| 340 |
+
"loss": 0.0052,
|
| 341 |
+
"step": 376
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 42.64,
|
| 345 |
+
"learning_rate": 0.0001,
|
| 346 |
+
"loss": 0.0047,
|
| 347 |
+
"step": 384
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 42.64,
|
| 351 |
+
"eval_exact_match": 0.5926849542809642,
|
| 352 |
+
"eval_exec": 0.6525353283458022,
|
| 353 |
+
"eval_loss": 0.2874293625354767,
|
| 354 |
+
"eval_runtime": 686.186,
|
| 355 |
+
"eval_samples_per_second": 2.368,
|
| 356 |
+
"step": 384
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 43.54,
|
| 360 |
+
"learning_rate": 0.0001,
|
| 361 |
+
"loss": 0.006,
|
| 362 |
+
"step": 392
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 44.43,
|
| 366 |
+
"learning_rate": 0.0001,
|
| 367 |
+
"loss": 0.0055,
|
| 368 |
+
"step": 400
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 45.32,
|
| 372 |
+
"learning_rate": 0.0001,
|
| 373 |
+
"loss": 0.0047,
|
| 374 |
+
"step": 408
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 46.21,
|
| 378 |
+
"learning_rate": 0.0001,
|
| 379 |
+
"loss": 0.0041,
|
| 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": 0.0035,
|
| 392 |
+
"step": 432
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 48.86,
|
| 396 |
+
"learning_rate": 0.0001,
|
| 397 |
+
"loss": 0.0039,
|
| 398 |
+
"step": 440
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 49.75,
|
| 402 |
+
"learning_rate": 0.0001,
|
| 403 |
+
"loss": 0.0036,
|
| 404 |
+
"step": 448
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 49.75,
|
| 408 |
+
"eval_exact_match": 0.6026600166251039,
|
| 409 |
+
"eval_exec": 0.657522859517872,
|
| 410 |
+
"eval_loss": 0.2975001633167267,
|
| 411 |
+
"eval_runtime": 636.4635,
|
| 412 |
+
"eval_samples_per_second": 2.553,
|
| 413 |
+
"step": 448
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 50.64,
|
| 417 |
+
"learning_rate": 0.0001,
|
| 418 |
+
"loss": 0.0034,
|
| 419 |
+
"step": 456
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 51.54,
|
| 423 |
+
"learning_rate": 0.0001,
|
| 424 |
+
"loss": 0.0035,
|
| 425 |
+
"step": 464
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 52.43,
|
| 429 |
+
"learning_rate": 0.0001,
|
| 430 |
+
"loss": 0.0032,
|
| 431 |
+
"step": 472
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 53.32,
|
| 435 |
+
"learning_rate": 0.0001,
|
| 436 |
+
"loss": 0.0034,
|
| 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": 0.0034,
|
| 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": 0.0029,
|
| 461 |
+
"step": 512
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 56.86,
|
| 465 |
+
"eval_exact_match": 0.6109725685785536,
|
| 466 |
+
"eval_exec": 0.6583541147132169,
|
| 467 |
+
"eval_loss": 0.32981422543525696,
|
| 468 |
+
"eval_runtime": 627.5266,
|
| 469 |
+
"eval_samples_per_second": 2.59,
|
| 470 |
+
"step": 512
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 57.75,
|
| 474 |
+
"learning_rate": 0.0001,
|
| 475 |
+
"loss": 0.0027,
|
| 476 |
+
"step": 520
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 58.64,
|
| 480 |
+
"learning_rate": 0.0001,
|
| 481 |
+
"loss": 0.005,
|
| 482 |
+
"step": 528
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 59.54,
|
| 486 |
+
"learning_rate": 0.0001,
|
| 487 |
+
"loss": 0.0204,
|
| 488 |
+
"step": 536
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 60.43,
|
| 492 |
+
"learning_rate": 0.0001,
|
| 493 |
+
"loss": 0.0037,
|
| 494 |
+
"step": 544
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 61.32,
|
| 498 |
+
"learning_rate": 0.0001,
|
| 499 |
+
"loss": 0.0037,
|
| 500 |
+
"step": 552
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 62.21,
|
| 504 |
+
"learning_rate": 0.0001,
|
| 505 |
+
"loss": 0.0028,
|
| 506 |
+
"step": 560
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 63.11,
|
| 510 |
+
"learning_rate": 0.0001,
|
| 511 |
+
"loss": 0.0025,
|
| 512 |
+
"step": 568
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 63.97,
|
| 516 |
+
"learning_rate": 0.0001,
|
| 517 |
+
"loss": 0.0027,
|
| 518 |
+
"step": 576
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 63.97,
|
| 522 |
+
"eval_exact_match": 0.6134663341645885,
|
| 523 |
+
"eval_exec": 0.6658354114713217,
|
| 524 |
+
"eval_loss": 0.3227553963661194,
|
| 525 |
+
"eval_runtime": 689.9491,
|
| 526 |
+
"eval_samples_per_second": 2.355,
|
| 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": 0.0028,
|
| 539 |
+
"step": 592
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 66.64,
|
| 543 |
+
"learning_rate": 0.0001,
|
| 544 |
+
"loss": 0.0028,
|
| 545 |
+
"step": 600
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 67.54,
|
| 549 |
+
"learning_rate": 0.0001,
|
| 550 |
+
"loss": 0.0024,
|
| 551 |
+
"step": 608
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 68.43,
|
| 555 |
+
"learning_rate": 0.0001,
|
| 556 |
+
"loss": 0.0024,
|
| 557 |
+
"step": 616
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 69.32,
|
| 561 |
+
"learning_rate": 0.0001,
|
| 562 |
+
"loss": 0.0021,
|
| 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": 0.0021,
|
| 575 |
+
"step": 640
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 71.11,
|
| 579 |
+
"eval_exact_match": 0.600166251039069,
|
| 580 |
+
"eval_exec": 0.6583541147132169,
|
| 581 |
+
"eval_loss": 0.3371490240097046,
|
| 582 |
+
"eval_runtime": 633.7926,
|
| 583 |
+
"eval_samples_per_second": 2.564,
|
| 584 |
+
"step": 640
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 71.97,
|
| 588 |
+
"learning_rate": 0.0001,
|
| 589 |
+
"loss": 0.0019,
|
| 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": 0.0082,
|
| 608 |
+
"step": 672
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 75.54,
|
| 612 |
+
"learning_rate": 0.0001,
|
| 613 |
+
"loss": 0.0029,
|
| 614 |
+
"step": 680
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 76.43,
|
| 618 |
+
"learning_rate": 0.0001,
|
| 619 |
+
"loss": 0.0027,
|
| 620 |
+
"step": 688
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 77.32,
|
| 624 |
+
"learning_rate": 0.0001,
|
| 625 |
+
"loss": 0.002,
|
| 626 |
+
"step": 696
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 78.21,
|
| 630 |
+
"learning_rate": 0.0001,
|
| 631 |
+
"loss": 0.0019,
|
| 632 |
+
"step": 704
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 78.21,
|
| 636 |
+
"eval_exact_match": 0.6034912718204489,
|
| 637 |
+
"eval_exec": 0.6533665835411472,
|
| 638 |
+
"eval_loss": 0.33176735043525696,
|
| 639 |
+
"eval_runtime": 625.8717,
|
| 640 |
+
"eval_samples_per_second": 2.596,
|
| 641 |
+
"step": 704
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 79.11,
|
| 645 |
+
"learning_rate": 0.0001,
|
| 646 |
+
"loss": 0.0018,
|
| 647 |
+
"step": 712
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 79.97,
|
| 651 |
+
"learning_rate": 0.0001,
|
| 652 |
+
"loss": 0.0018,
|
| 653 |
+
"step": 720
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 80.86,
|
| 657 |
+
"learning_rate": 0.0001,
|
| 658 |
+
"loss": 0.002,
|
| 659 |
+
"step": 728
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 81.75,
|
| 663 |
+
"learning_rate": 0.0001,
|
| 664 |
+
"loss": 0.0018,
|
| 665 |
+
"step": 736
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 82.64,
|
| 669 |
+
"learning_rate": 0.0001,
|
| 670 |
+
"loss": 0.0019,
|
| 671 |
+
"step": 744
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 83.54,
|
| 675 |
+
"learning_rate": 0.0001,
|
| 676 |
+
"loss": 0.0018,
|
| 677 |
+
"step": 752
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 84.43,
|
| 681 |
+
"learning_rate": 0.0001,
|
| 682 |
+
"loss": 0.0019,
|
| 683 |
+
"step": 760
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 85.32,
|
| 687 |
+
"learning_rate": 0.0001,
|
| 688 |
+
"loss": 0.0029,
|
| 689 |
+
"step": 768
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 85.32,
|
| 693 |
+
"eval_exact_match": 0.6234413965087282,
|
| 694 |
+
"eval_exec": 0.6716541978387365,
|
| 695 |
+
"eval_loss": 0.285192608833313,
|
| 696 |
+
"eval_runtime": 642.1565,
|
| 697 |
+
"eval_samples_per_second": 2.531,
|
| 698 |
+
"step": 768
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 86.21,
|
| 702 |
+
"learning_rate": 0.0001,
|
| 703 |
+
"loss": 0.0017,
|
| 704 |
+
"step": 776
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 87.11,
|
| 708 |
+
"learning_rate": 0.0001,
|
| 709 |
+
"loss": 0.0023,
|
| 710 |
+
"step": 784
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 87.97,
|
| 714 |
+
"learning_rate": 0.0001,
|
| 715 |
+
"loss": 0.0017,
|
| 716 |
+
"step": 792
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 88.86,
|
| 720 |
+
"learning_rate": 0.0001,
|
| 721 |
+
"loss": 0.0018,
|
| 722 |
+
"step": 800
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 89.75,
|
| 726 |
+
"learning_rate": 0.0001,
|
| 727 |
+
"loss": 0.0046,
|
| 728 |
+
"step": 808
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 90.64,
|
| 732 |
+
"learning_rate": 0.0001,
|
| 733 |
+
"loss": 0.0022,
|
| 734 |
+
"step": 816
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 91.54,
|
| 738 |
+
"learning_rate": 0.0001,
|
| 739 |
+
"loss": 0.0015,
|
| 740 |
+
"step": 824
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 92.43,
|
| 744 |
+
"learning_rate": 0.0001,
|
| 745 |
+
"loss": 0.002,
|
| 746 |
+
"step": 832
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 92.43,
|
| 750 |
+
"eval_exact_match": 0.5344970906068163,
|
| 751 |
+
"eval_exec": 0.5802161263507897,
|
| 752 |
+
"eval_loss": 0.37689846754074097,
|
| 753 |
+
"eval_runtime": 614.899,
|
| 754 |
+
"eval_samples_per_second": 2.643,
|
| 755 |
+
"step": 832
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 93.32,
|
| 759 |
+
"learning_rate": 0.0001,
|
| 760 |
+
"loss": 0.0083,
|
| 761 |
+
"step": 840
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 94.21,
|
| 765 |
+
"learning_rate": 0.0001,
|
| 766 |
+
"loss": 0.0015,
|
| 767 |
+
"step": 848
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 95.11,
|
| 771 |
+
"learning_rate": 0.0001,
|
| 772 |
+
"loss": 0.0015,
|
| 773 |
+
"step": 856
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 95.97,
|
| 777 |
+
"learning_rate": 0.0001,
|
| 778 |
+
"loss": 0.0014,
|
| 779 |
+
"step": 864
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 96.86,
|
| 783 |
+
"learning_rate": 0.0001,
|
| 784 |
+
"loss": 0.0015,
|
| 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": 0.0132,
|
| 797 |
+
"step": 888
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 99.54,
|
| 801 |
+
"learning_rate": 0.0001,
|
| 802 |
+
"loss": 0.0032,
|
| 803 |
+
"step": 896
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 99.54,
|
| 807 |
+
"eval_exact_match": 0.6126350789692435,
|
| 808 |
+
"eval_exec": 0.6724854530340815,
|
| 809 |
+
"eval_loss": 0.3111036419868469,
|
| 810 |
+
"eval_runtime": 624.8082,
|
| 811 |
+
"eval_samples_per_second": 2.601,
|
| 812 |
+
"step": 896
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 100.43,
|
| 816 |
+
"learning_rate": 0.0001,
|
| 817 |
+
"loss": 0.0014,
|
| 818 |
+
"step": 904
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 101.32,
|
| 822 |
+
"learning_rate": 0.0001,
|
| 823 |
+
"loss": 0.0013,
|
| 824 |
+
"step": 912
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 102.21,
|
| 828 |
+
"learning_rate": 0.0001,
|
| 829 |
+
"loss": 0.0017,
|
| 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": 0.0012,
|
| 842 |
+
"step": 936
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 104.86,
|
| 846 |
+
"learning_rate": 0.0001,
|
| 847 |
+
"loss": 0.0013,
|
| 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": 0.0114,
|
| 860 |
+
"step": 960
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 106.64,
|
| 864 |
+
"eval_exact_match": 0.6151288445552785,
|
| 865 |
+
"eval_exec": 0.6774729842061513,
|
| 866 |
+
"eval_loss": 0.3059256076812744,
|
| 867 |
+
"eval_runtime": 709.1272,
|
| 868 |
+
"eval_samples_per_second": 2.292,
|
| 869 |
+
"step": 960
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 107.54,
|
| 873 |
+
"learning_rate": 0.0001,
|
| 874 |
+
"loss": 0.0015,
|
| 875 |
+
"step": 968
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 108.43,
|
| 879 |
+
"learning_rate": 0.0001,
|
| 880 |
+
"loss": 0.0015,
|
| 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": 0.0016,
|
| 893 |
+
"step": 992
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 111.11,
|
| 897 |
+
"learning_rate": 0.0001,
|
| 898 |
+
"loss": 0.0011,
|
| 899 |
+
"step": 1000
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 111.97,
|
| 903 |
+
"learning_rate": 0.0001,
|
| 904 |
+
"loss": 0.0011,
|
| 905 |
+
"step": 1008
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 112.86,
|
| 909 |
+
"learning_rate": 0.0001,
|
| 910 |
+
"loss": 0.0012,
|
| 911 |
+
"step": 1016
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 113.75,
|
| 915 |
+
"learning_rate": 0.0001,
|
| 916 |
+
"loss": 0.0012,
|
| 917 |
+
"step": 1024
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 113.75,
|
| 921 |
+
"eval_exact_match": 0.6176226101413134,
|
| 922 |
+
"eval_exec": 0.6724854530340815,
|
| 923 |
+
"eval_loss": 0.35855236649513245,
|
| 924 |
+
"eval_runtime": 647.1974,
|
| 925 |
+
"eval_samples_per_second": 2.511,
|
| 926 |
+
"step": 1024
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 114.64,
|
| 930 |
+
"learning_rate": 0.0001,
|
| 931 |
+
"loss": 0.0011,
|
| 932 |
+
"step": 1032
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 115.54,
|
| 936 |
+
"learning_rate": 0.0001,
|
| 937 |
+
"loss": 0.0013,
|
| 938 |
+
"step": 1040
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 116.43,
|
| 942 |
+
"learning_rate": 0.0001,
|
| 943 |
+
"loss": 0.0011,
|
| 944 |
+
"step": 1048
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 117.32,
|
| 948 |
+
"learning_rate": 0.0001,
|
| 949 |
+
"loss": 0.0011,
|
| 950 |
+
"step": 1056
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 118.21,
|
| 954 |
+
"learning_rate": 0.0001,
|
| 955 |
+
"loss": 0.0013,
|
| 956 |
+
"step": 1064
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 119.11,
|
| 960 |
+
"learning_rate": 0.0001,
|
| 961 |
+
"loss": 0.0012,
|
| 962 |
+
"step": 1072
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 119.97,
|
| 966 |
+
"learning_rate": 0.0001,
|
| 967 |
+
"loss": 0.0012,
|
| 968 |
+
"step": 1080
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 120.86,
|
| 972 |
+
"learning_rate": 0.0001,
|
| 973 |
+
"loss": 0.0025,
|
| 974 |
+
"step": 1088
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 120.86,
|
| 978 |
+
"eval_exact_match": 0.6118038237738986,
|
| 979 |
+
"eval_exec": 0.6766417290108063,
|
| 980 |
+
"eval_loss": 0.34494832158088684,
|
| 981 |
+
"eval_runtime": 1089.7361,
|
| 982 |
+
"eval_samples_per_second": 1.491,
|
| 983 |
+
"step": 1088
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 121.75,
|
| 987 |
+
"learning_rate": 0.0001,
|
| 988 |
+
"loss": 0.0028,
|
| 989 |
+
"step": 1096
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 122.64,
|
| 993 |
+
"learning_rate": 0.0001,
|
| 994 |
+
"loss": 0.0011,
|
| 995 |
+
"step": 1104
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 123.54,
|
| 999 |
+
"learning_rate": 0.0001,
|
| 1000 |
+
"loss": 0.001,
|
| 1001 |
+
"step": 1112
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 124.43,
|
| 1005 |
+
"learning_rate": 0.0001,
|
| 1006 |
+
"loss": 0.0011,
|
| 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": 0.0013,
|
| 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": 0.0011,
|
| 1031 |
+
"step": 1152
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 127.97,
|
| 1035 |
+
"eval_exact_match": 0.6234413965087282,
|
| 1036 |
+
"eval_exec": 0.6724854530340815,
|
| 1037 |
+
"eval_loss": 0.352324515581131,
|
| 1038 |
+
"eval_runtime": 627.1111,
|
| 1039 |
+
"eval_samples_per_second": 2.591,
|
| 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": 0.0012,
|
| 1052 |
+
"step": 1168
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 130.64,
|
| 1056 |
+
"learning_rate": 0.0001,
|
| 1057 |
+
"loss": 0.0009,
|
| 1058 |
+
"step": 1176
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 131.54,
|
| 1062 |
+
"learning_rate": 0.0001,
|
| 1063 |
+
"loss": 0.001,
|
| 1064 |
+
"step": 1184
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 132.43,
|
| 1068 |
+
"learning_rate": 0.0001,
|
| 1069 |
+
"loss": 0.0009,
|
| 1070 |
+
"step": 1192
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 133.32,
|
| 1074 |
+
"learning_rate": 0.0001,
|
| 1075 |
+
"loss": 0.0025,
|
| 1076 |
+
"step": 1200
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 134.21,
|
| 1080 |
+
"learning_rate": 0.0001,
|
| 1081 |
+
"loss": 0.0052,
|
| 1082 |
+
"step": 1208
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 135.11,
|
| 1086 |
+
"learning_rate": 0.0001,
|
| 1087 |
+
"loss": 0.0016,
|
| 1088 |
+
"step": 1216
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 135.11,
|
| 1092 |
+
"eval_exact_match": 0.6101413133832086,
|
| 1093 |
+
"eval_exec": 0.6608478802992519,
|
| 1094 |
+
"eval_loss": 0.34119850397109985,
|
| 1095 |
+
"eval_runtime": 683.7196,
|
| 1096 |
+
"eval_samples_per_second": 2.377,
|
| 1097 |
+
"step": 1216
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 135.97,
|
| 1101 |
+
"learning_rate": 0.0001,
|
| 1102 |
+
"loss": 0.0011,
|
| 1103 |
+
"step": 1224
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 136.86,
|
| 1107 |
+
"learning_rate": 0.0001,
|
| 1108 |
+
"loss": 0.0012,
|
| 1109 |
+
"step": 1232
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 137.75,
|
| 1113 |
+
"learning_rate": 0.0001,
|
| 1114 |
+
"loss": 0.0012,
|
| 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": 0.0018,
|
| 1127 |
+
"step": 1256
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 140.43,
|
| 1131 |
+
"learning_rate": 0.0001,
|
| 1132 |
+
"loss": 0.0012,
|
| 1133 |
+
"step": 1264
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 141.32,
|
| 1137 |
+
"learning_rate": 0.0001,
|
| 1138 |
+
"loss": 0.0012,
|
| 1139 |
+
"step": 1272
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 142.21,
|
| 1143 |
+
"learning_rate": 0.0001,
|
| 1144 |
+
"loss": 0.0011,
|
| 1145 |
+
"step": 1280
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 142.21,
|
| 1149 |
+
"eval_exact_match": 0.6300914380714879,
|
| 1150 |
+
"eval_exec": 0.6658354114713217,
|
| 1151 |
+
"eval_loss": 0.36506175994873047,
|
| 1152 |
+
"eval_runtime": 628.8834,
|
| 1153 |
+
"eval_samples_per_second": 2.584,
|
| 1154 |
+
"step": 1280
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 143.11,
|
| 1158 |
+
"learning_rate": 0.0001,
|
| 1159 |
+
"loss": 0.001,
|
| 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": 0.0029,
|
| 1172 |
+
"step": 1304
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 145.75,
|
| 1176 |
+
"learning_rate": 0.0001,
|
| 1177 |
+
"loss": 0.0015,
|
| 1178 |
+
"step": 1312
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 146.64,
|
| 1182 |
+
"learning_rate": 0.0001,
|
| 1183 |
+
"loss": 0.0014,
|
| 1184 |
+
"step": 1320
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 147.54,
|
| 1188 |
+
"learning_rate": 0.0001,
|
| 1189 |
+
"loss": 0.0011,
|
| 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": 0.0009,
|
| 1202 |
+
"step": 1344
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 149.32,
|
| 1206 |
+
"eval_exact_match": 0.6317539484621779,
|
| 1207 |
+
"eval_exec": 0.6874480465502909,
|
| 1208 |
+
"eval_loss": 0.37579649686813354,
|
| 1209 |
+
"eval_runtime": 605.7302,
|
| 1210 |
+
"eval_samples_per_second": 2.683,
|
| 1211 |
+
"step": 1344
|
| 1212 |
+
}
|
| 1213 |
+
],
|
| 1214 |
+
"max_steps": 27648,
|
| 1215 |
+
"num_train_epochs": 3072,
|
| 1216 |
+
"total_flos": 1.0258011267411214e+19,
|
| 1217 |
+
"trial_name": null,
|
| 1218 |
+
"trial_params": null
|
| 1219 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5936c0ccf4b48fe3e5ac24530dd7c42653e2d091d0dd7019529bd35e823a4235
|
| 3 |
+
size 3247
|