Upload 9 files
Browse files- config.json +38 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +13 -0
- tokenizer.json +0 -0
- tokenizer_config.json +112 -0
- trainer_state.json +1384 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/flan-t5-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 2816,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 1024,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "gelu_new",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"early_stopping": true,
|
| 14 |
+
"eos_token_id": 1,
|
| 15 |
+
"feed_forward_proj": "gated-gelu",
|
| 16 |
+
"initializer_factor": 1.0,
|
| 17 |
+
"is_encoder_decoder": true,
|
| 18 |
+
"is_gated_act": true,
|
| 19 |
+
"layer_norm_epsilon": 1e-06,
|
| 20 |
+
"length_penalty": 2.0,
|
| 21 |
+
"max_length": 4,
|
| 22 |
+
"min_length": 100,
|
| 23 |
+
"model_type": "t5",
|
| 24 |
+
"n_positions": 512,
|
| 25 |
+
"no_repeat_ngram_size": 3,
|
| 26 |
+
"num_decoder_layers": 24,
|
| 27 |
+
"num_heads": 16,
|
| 28 |
+
"num_layers": 24,
|
| 29 |
+
"output_past": true,
|
| 30 |
+
"pad_token_id": 0,
|
| 31 |
+
"relative_attention_max_distance": 128,
|
| 32 |
+
"relative_attention_num_buckets": 32,
|
| 33 |
+
"tie_word_embeddings": false,
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.33.3",
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 32100
|
| 38 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1185b6b3382ee0685b966a56ad35dbe66376972d14f588b5080580884cc5db4
|
| 3 |
+
size 3132564293
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23d730ea44512112f685e80528ea985b41bcdbdf666a6443cc77304b5703f68a
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:decbfe5fd0162b6fb6b19bf5944473086405894ca05cd6af72523918c25dd77e
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_1>",
|
| 4 |
+
"<extra_id_2>",
|
| 5 |
+
"<extra_id_3>",
|
| 6 |
+
"<extra_id_4>",
|
| 7 |
+
"<extra_id_5>",
|
| 8 |
+
"<extra_id_6>"
|
| 9 |
+
],
|
| 10 |
+
"eos_token": "</s>",
|
| 11 |
+
"pad_token": "<pad>",
|
| 12 |
+
"unk_token": "<unk>"
|
| 13 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"clean_up_tokenization_spaces": true,
|
| 105 |
+
"eos_token": "</s>",
|
| 106 |
+
"extra_ids": 100,
|
| 107 |
+
"model_max_length": 512,
|
| 108 |
+
"pad_token": "<pad>",
|
| 109 |
+
"sp_model_kwargs": {},
|
| 110 |
+
"tokenizer_class": "T5Tokenizer",
|
| 111 |
+
"unk_token": "<unk>"
|
| 112 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1384 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 83.6764,
|
| 3 |
+
"best_model_checkpoint": "models/one_alignment_vs_summary/flan-t5-large/flan_t5_large_alignment_first/checkpoint-6500",
|
| 4 |
+
"epoch": 0.9742206235011991,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 6500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 4.992505995203837e-05,
|
| 14 |
+
"loss": 0.5753,
|
| 15 |
+
"step": 100
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"eval_F1": 46.8005,
|
| 20 |
+
"eval_Precision": 65.9011,
|
| 21 |
+
"eval_Recall": 36.284,
|
| 22 |
+
"eval_accuracy": 58.536,
|
| 23 |
+
"eval_accuracy_negative": 80.7879,
|
| 24 |
+
"eval_accuracy_positive": 36.284,
|
| 25 |
+
"eval_gen_len": 3.0,
|
| 26 |
+
"eval_loss": 0.3608146607875824,
|
| 27 |
+
"eval_runtime": 77.8641,
|
| 28 |
+
"eval_samples_per_second": 52.81,
|
| 29 |
+
"eval_steps_per_second": 3.301,
|
| 30 |
+
"step": 100
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.03,
|
| 34 |
+
"learning_rate": 4.9850119904076745e-05,
|
| 35 |
+
"loss": 0.3529,
|
| 36 |
+
"step": 200
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.03,
|
| 40 |
+
"eval_F1": 75.56,
|
| 41 |
+
"eval_Precision": 63.7671,
|
| 42 |
+
"eval_Recall": 92.7043,
|
| 43 |
+
"eval_accuracy": 69.9903,
|
| 44 |
+
"eval_accuracy_negative": 47.2763,
|
| 45 |
+
"eval_accuracy_positive": 92.7043,
|
| 46 |
+
"eval_gen_len": 3.0,
|
| 47 |
+
"eval_loss": 0.3245851397514343,
|
| 48 |
+
"eval_runtime": 78.1082,
|
| 49 |
+
"eval_samples_per_second": 52.645,
|
| 50 |
+
"eval_steps_per_second": 3.29,
|
| 51 |
+
"step": 200
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.04,
|
| 55 |
+
"learning_rate": 4.977517985611511e-05,
|
| 56 |
+
"loss": 0.2974,
|
| 57 |
+
"step": 300
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.04,
|
| 61 |
+
"eval_F1": 78.279,
|
| 62 |
+
"eval_Precision": 68.5944,
|
| 63 |
+
"eval_Recall": 91.1479,
|
| 64 |
+
"eval_accuracy": 74.392,
|
| 65 |
+
"eval_accuracy_negative": 57.6362,
|
| 66 |
+
"eval_accuracy_positive": 91.1479,
|
| 67 |
+
"eval_gen_len": 3.0,
|
| 68 |
+
"eval_loss": 0.41329512000083923,
|
| 69 |
+
"eval_runtime": 78.0252,
|
| 70 |
+
"eval_samples_per_second": 52.701,
|
| 71 |
+
"eval_steps_per_second": 3.294,
|
| 72 |
+
"step": 300
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.06,
|
| 76 |
+
"learning_rate": 4.970023980815348e-05,
|
| 77 |
+
"loss": 0.2854,
|
| 78 |
+
"step": 400
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.06,
|
| 82 |
+
"eval_F1": 79.6539,
|
| 83 |
+
"eval_Precision": 73.2354,
|
| 84 |
+
"eval_Recall": 87.3054,
|
| 85 |
+
"eval_accuracy": 77.3346,
|
| 86 |
+
"eval_accuracy_negative": 67.3638,
|
| 87 |
+
"eval_accuracy_positive": 87.3054,
|
| 88 |
+
"eval_gen_len": 3.0,
|
| 89 |
+
"eval_loss": 0.2850329875946045,
|
| 90 |
+
"eval_runtime": 77.9552,
|
| 91 |
+
"eval_samples_per_second": 52.748,
|
| 92 |
+
"eval_steps_per_second": 3.297,
|
| 93 |
+
"step": 400
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.07,
|
| 97 |
+
"learning_rate": 4.9625299760191855e-05,
|
| 98 |
+
"loss": 0.2569,
|
| 99 |
+
"step": 500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.07,
|
| 103 |
+
"eval_F1": 79.9727,
|
| 104 |
+
"eval_Precision": 75.225,
|
| 105 |
+
"eval_Recall": 85.3599,
|
| 106 |
+
"eval_accuracy": 78.2588,
|
| 107 |
+
"eval_accuracy_negative": 71.1576,
|
| 108 |
+
"eval_accuracy_positive": 85.3599,
|
| 109 |
+
"eval_gen_len": 3.0,
|
| 110 |
+
"eval_loss": 0.31440889835357666,
|
| 111 |
+
"eval_runtime": 77.9127,
|
| 112 |
+
"eval_samples_per_second": 52.777,
|
| 113 |
+
"eval_steps_per_second": 3.299,
|
| 114 |
+
"step": 500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.09,
|
| 118 |
+
"learning_rate": 4.9550359712230215e-05,
|
| 119 |
+
"loss": 0.273,
|
| 120 |
+
"step": 600
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.09,
|
| 124 |
+
"eval_F1": 80.6036,
|
| 125 |
+
"eval_Precision": 74.1224,
|
| 126 |
+
"eval_Recall": 88.3268,
|
| 127 |
+
"eval_accuracy": 78.6722,
|
| 128 |
+
"eval_accuracy_negative": 69.0175,
|
| 129 |
+
"eval_accuracy_positive": 88.3268,
|
| 130 |
+
"eval_gen_len": 3.0,
|
| 131 |
+
"eval_loss": 0.2862711548805237,
|
| 132 |
+
"eval_runtime": 77.9247,
|
| 133 |
+
"eval_samples_per_second": 52.769,
|
| 134 |
+
"eval_steps_per_second": 3.298,
|
| 135 |
+
"step": 600
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.1,
|
| 139 |
+
"learning_rate": 4.947541966426858e-05,
|
| 140 |
+
"loss": 0.2769,
|
| 141 |
+
"step": 700
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.1,
|
| 145 |
+
"eval_F1": 79.2214,
|
| 146 |
+
"eval_Precision": 79.26,
|
| 147 |
+
"eval_Recall": 79.1829,
|
| 148 |
+
"eval_accuracy": 78.4776,
|
| 149 |
+
"eval_accuracy_negative": 77.7724,
|
| 150 |
+
"eval_accuracy_positive": 79.1829,
|
| 151 |
+
"eval_gen_len": 3.0,
|
| 152 |
+
"eval_loss": 0.26657262444496155,
|
| 153 |
+
"eval_runtime": 77.9599,
|
| 154 |
+
"eval_samples_per_second": 52.745,
|
| 155 |
+
"eval_steps_per_second": 3.297,
|
| 156 |
+
"step": 700
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.12,
|
| 160 |
+
"learning_rate": 4.940047961630696e-05,
|
| 161 |
+
"loss": 0.288,
|
| 162 |
+
"step": 800
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.12,
|
| 166 |
+
"eval_F1": 80.125,
|
| 167 |
+
"eval_Precision": 79.1924,
|
| 168 |
+
"eval_Recall": 81.0798,
|
| 169 |
+
"eval_accuracy": 79.7909,
|
| 170 |
+
"eval_accuracy_negative": 78.5019,
|
| 171 |
+
"eval_accuracy_positive": 81.0798,
|
| 172 |
+
"eval_gen_len": 3.0,
|
| 173 |
+
"eval_loss": 0.23273229598999023,
|
| 174 |
+
"eval_runtime": 77.9321,
|
| 175 |
+
"eval_samples_per_second": 52.764,
|
| 176 |
+
"eval_steps_per_second": 3.298,
|
| 177 |
+
"step": 800
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.13,
|
| 181 |
+
"learning_rate": 4.9325539568345325e-05,
|
| 182 |
+
"loss": 0.2597,
|
| 183 |
+
"step": 900
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.13,
|
| 187 |
+
"eval_F1": 79.5494,
|
| 188 |
+
"eval_Precision": 80.1184,
|
| 189 |
+
"eval_Recall": 78.9883,
|
| 190 |
+
"eval_accuracy": 78.7451,
|
| 191 |
+
"eval_accuracy_negative": 78.5019,
|
| 192 |
+
"eval_accuracy_positive": 78.9883,
|
| 193 |
+
"eval_gen_len": 3.0,
|
| 194 |
+
"eval_loss": 0.22254109382629395,
|
| 195 |
+
"eval_runtime": 77.9631,
|
| 196 |
+
"eval_samples_per_second": 52.743,
|
| 197 |
+
"eval_steps_per_second": 3.296,
|
| 198 |
+
"step": 900
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.15,
|
| 202 |
+
"learning_rate": 4.925059952038369e-05,
|
| 203 |
+
"loss": 0.2735,
|
| 204 |
+
"step": 1000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.15,
|
| 208 |
+
"eval_F1": 81.095,
|
| 209 |
+
"eval_Precision": 78.1335,
|
| 210 |
+
"eval_Recall": 84.2899,
|
| 211 |
+
"eval_accuracy": 79.9368,
|
| 212 |
+
"eval_accuracy_negative": 75.5837,
|
| 213 |
+
"eval_accuracy_positive": 84.2899,
|
| 214 |
+
"eval_gen_len": 3.0,
|
| 215 |
+
"eval_loss": 0.23284350335597992,
|
| 216 |
+
"eval_runtime": 77.9328,
|
| 217 |
+
"eval_samples_per_second": 52.763,
|
| 218 |
+
"eval_steps_per_second": 3.298,
|
| 219 |
+
"step": 1000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.16,
|
| 223 |
+
"learning_rate": 4.917565947242207e-05,
|
| 224 |
+
"loss": 0.2591,
|
| 225 |
+
"step": 1100
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.16,
|
| 229 |
+
"eval_F1": 81.521,
|
| 230 |
+
"eval_Precision": 77.891,
|
| 231 |
+
"eval_Recall": 85.5058,
|
| 232 |
+
"eval_accuracy": 80.5934,
|
| 233 |
+
"eval_accuracy_negative": 75.6809,
|
| 234 |
+
"eval_accuracy_positive": 85.5058,
|
| 235 |
+
"eval_gen_len": 3.0,
|
| 236 |
+
"eval_loss": 0.26482418179512024,
|
| 237 |
+
"eval_runtime": 78.0339,
|
| 238 |
+
"eval_samples_per_second": 52.695,
|
| 239 |
+
"eval_steps_per_second": 3.293,
|
| 240 |
+
"step": 1100
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.18,
|
| 244 |
+
"learning_rate": 4.9100719424460435e-05,
|
| 245 |
+
"loss": 0.2675,
|
| 246 |
+
"step": 1200
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.18,
|
| 250 |
+
"eval_F1": 80.1508,
|
| 251 |
+
"eval_Precision": 82.9002,
|
| 252 |
+
"eval_Recall": 77.5778,
|
| 253 |
+
"eval_accuracy": 80.7879,
|
| 254 |
+
"eval_accuracy_negative": 83.9981,
|
| 255 |
+
"eval_accuracy_positive": 77.5778,
|
| 256 |
+
"eval_gen_len": 3.0,
|
| 257 |
+
"eval_loss": 0.23910629749298096,
|
| 258 |
+
"eval_runtime": 78.0093,
|
| 259 |
+
"eval_samples_per_second": 52.712,
|
| 260 |
+
"eval_steps_per_second": 3.294,
|
| 261 |
+
"step": 1200
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.19,
|
| 265 |
+
"learning_rate": 4.90257793764988e-05,
|
| 266 |
+
"loss": 0.2549,
|
| 267 |
+
"step": 1300
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.19,
|
| 271 |
+
"eval_F1": 81.6754,
|
| 272 |
+
"eval_Precision": 79.9627,
|
| 273 |
+
"eval_Recall": 83.463,
|
| 274 |
+
"eval_accuracy": 81.1041,
|
| 275 |
+
"eval_accuracy_negative": 78.7451,
|
| 276 |
+
"eval_accuracy_positive": 83.463,
|
| 277 |
+
"eval_gen_len": 3.0,
|
| 278 |
+
"eval_loss": 0.22716127336025238,
|
| 279 |
+
"eval_runtime": 78.0476,
|
| 280 |
+
"eval_samples_per_second": 52.686,
|
| 281 |
+
"eval_steps_per_second": 3.293,
|
| 282 |
+
"step": 1300
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.21,
|
| 286 |
+
"learning_rate": 4.895083932853717e-05,
|
| 287 |
+
"loss": 0.2338,
|
| 288 |
+
"step": 1400
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.21,
|
| 292 |
+
"eval_F1": 80.1995,
|
| 293 |
+
"eval_Precision": 82.2927,
|
| 294 |
+
"eval_Recall": 78.2101,
|
| 295 |
+
"eval_accuracy": 80.4475,
|
| 296 |
+
"eval_accuracy_negative": 82.6848,
|
| 297 |
+
"eval_accuracy_positive": 78.2101,
|
| 298 |
+
"eval_gen_len": 3.0,
|
| 299 |
+
"eval_loss": 0.24518640339374542,
|
| 300 |
+
"eval_runtime": 77.9981,
|
| 301 |
+
"eval_samples_per_second": 52.719,
|
| 302 |
+
"eval_steps_per_second": 3.295,
|
| 303 |
+
"step": 1400
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.22,
|
| 307 |
+
"learning_rate": 4.8875899280575545e-05,
|
| 308 |
+
"loss": 0.2747,
|
| 309 |
+
"step": 1500
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.22,
|
| 313 |
+
"eval_F1": 81.9309,
|
| 314 |
+
"eval_Precision": 75.2033,
|
| 315 |
+
"eval_Recall": 89.9805,
|
| 316 |
+
"eval_accuracy": 79.4504,
|
| 317 |
+
"eval_accuracy_negative": 68.9202,
|
| 318 |
+
"eval_accuracy_positive": 89.9805,
|
| 319 |
+
"eval_gen_len": 3.0,
|
| 320 |
+
"eval_loss": 0.2351878583431244,
|
| 321 |
+
"eval_runtime": 77.8581,
|
| 322 |
+
"eval_samples_per_second": 52.814,
|
| 323 |
+
"eval_steps_per_second": 3.301,
|
| 324 |
+
"step": 1500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.24,
|
| 328 |
+
"learning_rate": 4.880095923261391e-05,
|
| 329 |
+
"loss": 0.2389,
|
| 330 |
+
"step": 1600
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.24,
|
| 334 |
+
"eval_F1": 77.4047,
|
| 335 |
+
"eval_Precision": 80.4724,
|
| 336 |
+
"eval_Recall": 74.5623,
|
| 337 |
+
"eval_accuracy": 76.143,
|
| 338 |
+
"eval_accuracy_negative": 77.7237,
|
| 339 |
+
"eval_accuracy_positive": 74.5623,
|
| 340 |
+
"eval_gen_len": 3.0,
|
| 341 |
+
"eval_loss": 0.240137979388237,
|
| 342 |
+
"eval_runtime": 77.9704,
|
| 343 |
+
"eval_samples_per_second": 52.738,
|
| 344 |
+
"eval_steps_per_second": 3.296,
|
| 345 |
+
"step": 1600
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.25,
|
| 349 |
+
"learning_rate": 4.872601918465228e-05,
|
| 350 |
+
"loss": 0.2486,
|
| 351 |
+
"step": 1700
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.25,
|
| 355 |
+
"eval_F1": 74.3833,
|
| 356 |
+
"eval_Precision": 84.0171,
|
| 357 |
+
"eval_Recall": 66.7315,
|
| 358 |
+
"eval_accuracy": 73.5165,
|
| 359 |
+
"eval_accuracy_negative": 80.3016,
|
| 360 |
+
"eval_accuracy_positive": 66.7315,
|
| 361 |
+
"eval_gen_len": 3.0,
|
| 362 |
+
"eval_loss": 0.23113004863262177,
|
| 363 |
+
"eval_runtime": 77.9471,
|
| 364 |
+
"eval_samples_per_second": 52.754,
|
| 365 |
+
"eval_steps_per_second": 3.297,
|
| 366 |
+
"step": 1700
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.27,
|
| 370 |
+
"learning_rate": 4.865107913669065e-05,
|
| 371 |
+
"loss": 0.2558,
|
| 372 |
+
"step": 1800
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 0.27,
|
| 376 |
+
"eval_F1": 75.5311,
|
| 377 |
+
"eval_Precision": 81.9579,
|
| 378 |
+
"eval_Recall": 70.0389,
|
| 379 |
+
"eval_accuracy": 71.644,
|
| 380 |
+
"eval_accuracy_negative": 73.249,
|
| 381 |
+
"eval_accuracy_positive": 70.0389,
|
| 382 |
+
"eval_gen_len": 3.0,
|
| 383 |
+
"eval_loss": 0.2416938990354538,
|
| 384 |
+
"eval_runtime": 77.8981,
|
| 385 |
+
"eval_samples_per_second": 52.787,
|
| 386 |
+
"eval_steps_per_second": 3.299,
|
| 387 |
+
"step": 1800
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.28,
|
| 391 |
+
"learning_rate": 4.8576139088729016e-05,
|
| 392 |
+
"loss": 0.2521,
|
| 393 |
+
"step": 1900
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.28,
|
| 397 |
+
"eval_F1": 75.8988,
|
| 398 |
+
"eval_Precision": 83.8729,
|
| 399 |
+
"eval_Recall": 69.3093,
|
| 400 |
+
"eval_accuracy": 72.0574,
|
| 401 |
+
"eval_accuracy_negative": 74.8054,
|
| 402 |
+
"eval_accuracy_positive": 69.3093,
|
| 403 |
+
"eval_gen_len": 3.0,
|
| 404 |
+
"eval_loss": 0.2378227710723877,
|
| 405 |
+
"eval_runtime": 78.1302,
|
| 406 |
+
"eval_samples_per_second": 52.63,
|
| 407 |
+
"eval_steps_per_second": 3.289,
|
| 408 |
+
"step": 1900
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.3,
|
| 412 |
+
"learning_rate": 4.8501199040767384e-05,
|
| 413 |
+
"loss": 0.2487,
|
| 414 |
+
"step": 2000
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.3,
|
| 418 |
+
"eval_F1": 82.5998,
|
| 419 |
+
"eval_Precision": 77.7587,
|
| 420 |
+
"eval_Recall": 88.0837,
|
| 421 |
+
"eval_accuracy": 72.5438,
|
| 422 |
+
"eval_accuracy_negative": 57.0039,
|
| 423 |
+
"eval_accuracy_positive": 88.0837,
|
| 424 |
+
"eval_gen_len": 3.0,
|
| 425 |
+
"eval_loss": 0.31695932149887085,
|
| 426 |
+
"eval_runtime": 78.0522,
|
| 427 |
+
"eval_samples_per_second": 52.683,
|
| 428 |
+
"eval_steps_per_second": 3.293,
|
| 429 |
+
"step": 2000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.31,
|
| 433 |
+
"learning_rate": 4.842625899280576e-05,
|
| 434 |
+
"loss": 0.246,
|
| 435 |
+
"step": 2100
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.31,
|
| 439 |
+
"eval_F1": 81.1168,
|
| 440 |
+
"eval_Precision": 81.6971,
|
| 441 |
+
"eval_Recall": 80.5447,
|
| 442 |
+
"eval_accuracy": 66.3911,
|
| 443 |
+
"eval_accuracy_negative": 52.2374,
|
| 444 |
+
"eval_accuracy_positive": 80.5447,
|
| 445 |
+
"eval_gen_len": 3.0,
|
| 446 |
+
"eval_loss": 0.25484344363212585,
|
| 447 |
+
"eval_runtime": 78.0548,
|
| 448 |
+
"eval_samples_per_second": 52.681,
|
| 449 |
+
"eval_steps_per_second": 3.293,
|
| 450 |
+
"step": 2100
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.33,
|
| 454 |
+
"learning_rate": 4.8351318944844126e-05,
|
| 455 |
+
"loss": 0.2407,
|
| 456 |
+
"step": 2200
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.33,
|
| 460 |
+
"eval_F1": 74.0905,
|
| 461 |
+
"eval_Precision": 86.343,
|
| 462 |
+
"eval_Recall": 64.8833,
|
| 463 |
+
"eval_accuracy": 71.7656,
|
| 464 |
+
"eval_accuracy_negative": 78.6479,
|
| 465 |
+
"eval_accuracy_positive": 64.8833,
|
| 466 |
+
"eval_gen_len": 3.0,
|
| 467 |
+
"eval_loss": 0.26473525166511536,
|
| 468 |
+
"eval_runtime": 77.9999,
|
| 469 |
+
"eval_samples_per_second": 52.718,
|
| 470 |
+
"eval_steps_per_second": 3.295,
|
| 471 |
+
"step": 2200
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.34,
|
| 475 |
+
"learning_rate": 4.8276378896882494e-05,
|
| 476 |
+
"loss": 0.2293,
|
| 477 |
+
"step": 2300
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.34,
|
| 481 |
+
"eval_F1": 76.173,
|
| 482 |
+
"eval_Precision": 82.6038,
|
| 483 |
+
"eval_Recall": 70.6712,
|
| 484 |
+
"eval_accuracy": 72.7383,
|
| 485 |
+
"eval_accuracy_negative": 74.8054,
|
| 486 |
+
"eval_accuracy_positive": 70.6712,
|
| 487 |
+
"eval_gen_len": 3.0,
|
| 488 |
+
"eval_loss": 0.23481938242912292,
|
| 489 |
+
"eval_runtime": 78.0051,
|
| 490 |
+
"eval_samples_per_second": 52.714,
|
| 491 |
+
"eval_steps_per_second": 3.295,
|
| 492 |
+
"step": 2300
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.36,
|
| 496 |
+
"learning_rate": 4.820143884892087e-05,
|
| 497 |
+
"loss": 0.199,
|
| 498 |
+
"step": 2400
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.36,
|
| 502 |
+
"eval_F1": 81.2854,
|
| 503 |
+
"eval_Precision": 79.0441,
|
| 504 |
+
"eval_Recall": 83.6576,
|
| 505 |
+
"eval_accuracy": 77.8453,
|
| 506 |
+
"eval_accuracy_negative": 72.0331,
|
| 507 |
+
"eval_accuracy_positive": 83.6576,
|
| 508 |
+
"eval_gen_len": 3.0,
|
| 509 |
+
"eval_loss": 0.29514577984809875,
|
| 510 |
+
"eval_runtime": 77.9919,
|
| 511 |
+
"eval_samples_per_second": 52.723,
|
| 512 |
+
"eval_steps_per_second": 3.295,
|
| 513 |
+
"step": 2400
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.37,
|
| 517 |
+
"learning_rate": 4.8126498800959236e-05,
|
| 518 |
+
"loss": 0.247,
|
| 519 |
+
"step": 2500
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.37,
|
| 523 |
+
"eval_F1": 67.5548,
|
| 524 |
+
"eval_Precision": 86.3086,
|
| 525 |
+
"eval_Recall": 55.4961,
|
| 526 |
+
"eval_accuracy": 70.3551,
|
| 527 |
+
"eval_accuracy_negative": 85.214,
|
| 528 |
+
"eval_accuracy_positive": 55.4961,
|
| 529 |
+
"eval_gen_len": 3.0,
|
| 530 |
+
"eval_loss": 0.23327696323394775,
|
| 531 |
+
"eval_runtime": 78.0614,
|
| 532 |
+
"eval_samples_per_second": 52.677,
|
| 533 |
+
"eval_steps_per_second": 3.292,
|
| 534 |
+
"step": 2500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.39,
|
| 538 |
+
"learning_rate": 4.8051558752997604e-05,
|
| 539 |
+
"loss": 0.2659,
|
| 540 |
+
"step": 2600
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 0.39,
|
| 544 |
+
"eval_F1": 77.5335,
|
| 545 |
+
"eval_Precision": 80.6944,
|
| 546 |
+
"eval_Recall": 74.6109,
|
| 547 |
+
"eval_accuracy": 68.6284,
|
| 548 |
+
"eval_accuracy_negative": 62.6459,
|
| 549 |
+
"eval_accuracy_positive": 74.6109,
|
| 550 |
+
"eval_gen_len": 3.0,
|
| 551 |
+
"eval_loss": 0.26498734951019287,
|
| 552 |
+
"eval_runtime": 77.9945,
|
| 553 |
+
"eval_samples_per_second": 52.722,
|
| 554 |
+
"eval_steps_per_second": 3.295,
|
| 555 |
+
"step": 2600
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.4,
|
| 559 |
+
"learning_rate": 4.797661870503598e-05,
|
| 560 |
+
"loss": 0.2445,
|
| 561 |
+
"step": 2700
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.4,
|
| 565 |
+
"eval_F1": 81.6411,
|
| 566 |
+
"eval_Precision": 77.1998,
|
| 567 |
+
"eval_Recall": 86.6245,
|
| 568 |
+
"eval_accuracy": 78.0156,
|
| 569 |
+
"eval_accuracy_negative": 69.4066,
|
| 570 |
+
"eval_accuracy_positive": 86.6245,
|
| 571 |
+
"eval_gen_len": 3.0,
|
| 572 |
+
"eval_loss": 0.25022661685943604,
|
| 573 |
+
"eval_runtime": 78.0413,
|
| 574 |
+
"eval_samples_per_second": 52.69,
|
| 575 |
+
"eval_steps_per_second": 3.293,
|
| 576 |
+
"step": 2700
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.42,
|
| 580 |
+
"learning_rate": 4.7901678657074346e-05,
|
| 581 |
+
"loss": 0.2397,
|
| 582 |
+
"step": 2800
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 0.42,
|
| 586 |
+
"eval_F1": 81.1614,
|
| 587 |
+
"eval_Precision": 77.679,
|
| 588 |
+
"eval_Recall": 84.9708,
|
| 589 |
+
"eval_accuracy": 75.9241,
|
| 590 |
+
"eval_accuracy_negative": 66.8774,
|
| 591 |
+
"eval_accuracy_positive": 84.9708,
|
| 592 |
+
"eval_gen_len": 3.0,
|
| 593 |
+
"eval_loss": 0.2765290439128876,
|
| 594 |
+
"eval_runtime": 77.9454,
|
| 595 |
+
"eval_samples_per_second": 52.755,
|
| 596 |
+
"eval_steps_per_second": 3.297,
|
| 597 |
+
"step": 2800
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.43,
|
| 601 |
+
"learning_rate": 4.7826738609112713e-05,
|
| 602 |
+
"loss": 0.2134,
|
| 603 |
+
"step": 2900
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.43,
|
| 607 |
+
"eval_F1": 81.6516,
|
| 608 |
+
"eval_Precision": 78.0488,
|
| 609 |
+
"eval_Recall": 85.6031,
|
| 610 |
+
"eval_accuracy": 77.9426,
|
| 611 |
+
"eval_accuracy_negative": 70.2821,
|
| 612 |
+
"eval_accuracy_positive": 85.6031,
|
| 613 |
+
"eval_gen_len": 3.0,
|
| 614 |
+
"eval_loss": 0.2863008975982666,
|
| 615 |
+
"eval_runtime": 78.0388,
|
| 616 |
+
"eval_samples_per_second": 52.692,
|
| 617 |
+
"eval_steps_per_second": 3.293,
|
| 618 |
+
"step": 2900
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.45,
|
| 622 |
+
"learning_rate": 4.775179856115108e-05,
|
| 623 |
+
"loss": 0.2349,
|
| 624 |
+
"step": 3000
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.45,
|
| 628 |
+
"eval_F1": 81.0536,
|
| 629 |
+
"eval_Precision": 80.5476,
|
| 630 |
+
"eval_Recall": 81.5661,
|
| 631 |
+
"eval_accuracy": 77.8696,
|
| 632 |
+
"eval_accuracy_negative": 74.1732,
|
| 633 |
+
"eval_accuracy_positive": 81.5661,
|
| 634 |
+
"eval_gen_len": 3.0,
|
| 635 |
+
"eval_loss": 0.23327529430389404,
|
| 636 |
+
"eval_runtime": 77.998,
|
| 637 |
+
"eval_samples_per_second": 52.719,
|
| 638 |
+
"eval_steps_per_second": 3.295,
|
| 639 |
+
"step": 3000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.46,
|
| 643 |
+
"learning_rate": 4.767685851318945e-05,
|
| 644 |
+
"loss": 0.2031,
|
| 645 |
+
"step": 3100
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.46,
|
| 649 |
+
"eval_F1": 80.2638,
|
| 650 |
+
"eval_Precision": 83.8812,
|
| 651 |
+
"eval_Recall": 76.9455,
|
| 652 |
+
"eval_accuracy": 78.429,
|
| 653 |
+
"eval_accuracy_negative": 79.9125,
|
| 654 |
+
"eval_accuracy_positive": 76.9455,
|
| 655 |
+
"eval_gen_len": 3.0,
|
| 656 |
+
"eval_loss": 0.2780900001525879,
|
| 657 |
+
"eval_runtime": 78.0382,
|
| 658 |
+
"eval_samples_per_second": 52.692,
|
| 659 |
+
"eval_steps_per_second": 3.293,
|
| 660 |
+
"step": 3100
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.48,
|
| 664 |
+
"learning_rate": 4.7601918465227817e-05,
|
| 665 |
+
"loss": 0.2704,
|
| 666 |
+
"step": 3200
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 0.48,
|
| 670 |
+
"eval_F1": 80.8479,
|
| 671 |
+
"eval_Precision": 82.958,
|
| 672 |
+
"eval_Recall": 78.8424,
|
| 673 |
+
"eval_accuracy": 79.8881,
|
| 674 |
+
"eval_accuracy_negative": 80.9339,
|
| 675 |
+
"eval_accuracy_positive": 78.8424,
|
| 676 |
+
"eval_gen_len": 3.0,
|
| 677 |
+
"eval_loss": 0.22213193774223328,
|
| 678 |
+
"eval_runtime": 77.9705,
|
| 679 |
+
"eval_samples_per_second": 52.738,
|
| 680 |
+
"eval_steps_per_second": 3.296,
|
| 681 |
+
"step": 3200
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.49,
|
| 685 |
+
"learning_rate": 4.752697841726619e-05,
|
| 686 |
+
"loss": 0.2413,
|
| 687 |
+
"step": 3300
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.49,
|
| 691 |
+
"eval_F1": 82.2274,
|
| 692 |
+
"eval_Precision": 78.6158,
|
| 693 |
+
"eval_Recall": 86.1868,
|
| 694 |
+
"eval_accuracy": 79.3045,
|
| 695 |
+
"eval_accuracy_negative": 72.4222,
|
| 696 |
+
"eval_accuracy_positive": 86.1868,
|
| 697 |
+
"eval_gen_len": 3.0,
|
| 698 |
+
"eval_loss": 0.21565163135528564,
|
| 699 |
+
"eval_runtime": 77.9735,
|
| 700 |
+
"eval_samples_per_second": 52.736,
|
| 701 |
+
"eval_steps_per_second": 3.296,
|
| 702 |
+
"step": 3300
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.51,
|
| 706 |
+
"learning_rate": 4.745203836930456e-05,
|
| 707 |
+
"loss": 0.2549,
|
| 708 |
+
"step": 3400
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 0.51,
|
| 712 |
+
"eval_F1": 80.991,
|
| 713 |
+
"eval_Precision": 70.8045,
|
| 714 |
+
"eval_Recall": 94.6012,
|
| 715 |
+
"eval_accuracy": 75.5107,
|
| 716 |
+
"eval_accuracy_negative": 56.4202,
|
| 717 |
+
"eval_accuracy_positive": 94.6012,
|
| 718 |
+
"eval_gen_len": 3.0,
|
| 719 |
+
"eval_loss": 0.3653569221496582,
|
| 720 |
+
"eval_runtime": 77.9428,
|
| 721 |
+
"eval_samples_per_second": 52.757,
|
| 722 |
+
"eval_steps_per_second": 3.297,
|
| 723 |
+
"step": 3400
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.52,
|
| 727 |
+
"learning_rate": 4.7377098321342926e-05,
|
| 728 |
+
"loss": 0.2327,
|
| 729 |
+
"step": 3500
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.52,
|
| 733 |
+
"eval_F1": 80.6348,
|
| 734 |
+
"eval_Precision": 82.2458,
|
| 735 |
+
"eval_Recall": 79.0856,
|
| 736 |
+
"eval_accuracy": 78.7938,
|
| 737 |
+
"eval_accuracy_negative": 78.5019,
|
| 738 |
+
"eval_accuracy_positive": 79.0856,
|
| 739 |
+
"eval_gen_len": 3.0,
|
| 740 |
+
"eval_loss": 0.22318707406520844,
|
| 741 |
+
"eval_runtime": 77.9908,
|
| 742 |
+
"eval_samples_per_second": 52.724,
|
| 743 |
+
"eval_steps_per_second": 3.295,
|
| 744 |
+
"step": 3500
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.54,
|
| 748 |
+
"learning_rate": 4.7302158273381294e-05,
|
| 749 |
+
"loss": 0.234,
|
| 750 |
+
"step": 3600
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 0.54,
|
| 754 |
+
"eval_F1": 82.8591,
|
| 755 |
+
"eval_Precision": 76.8176,
|
| 756 |
+
"eval_Recall": 89.9319,
|
| 757 |
+
"eval_accuracy": 77.5535,
|
| 758 |
+
"eval_accuracy_negative": 65.1751,
|
| 759 |
+
"eval_accuracy_positive": 89.9319,
|
| 760 |
+
"eval_gen_len": 3.0,
|
| 761 |
+
"eval_loss": 0.28604593873023987,
|
| 762 |
+
"eval_runtime": 77.9808,
|
| 763 |
+
"eval_samples_per_second": 52.731,
|
| 764 |
+
"eval_steps_per_second": 3.296,
|
| 765 |
+
"step": 3600
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.55,
|
| 769 |
+
"learning_rate": 4.722721822541967e-05,
|
| 770 |
+
"loss": 0.258,
|
| 771 |
+
"step": 3700
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.55,
|
| 775 |
+
"eval_F1": 74.4311,
|
| 776 |
+
"eval_Precision": 82.7874,
|
| 777 |
+
"eval_Recall": 67.607,
|
| 778 |
+
"eval_accuracy": 67.9718,
|
| 779 |
+
"eval_accuracy_negative": 68.3366,
|
| 780 |
+
"eval_accuracy_positive": 67.607,
|
| 781 |
+
"eval_gen_len": 3.0,
|
| 782 |
+
"eval_loss": 0.2335677146911621,
|
| 783 |
+
"eval_runtime": 78.0681,
|
| 784 |
+
"eval_samples_per_second": 52.672,
|
| 785 |
+
"eval_steps_per_second": 3.292,
|
| 786 |
+
"step": 3700
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.57,
|
| 790 |
+
"learning_rate": 4.7152278177458036e-05,
|
| 791 |
+
"loss": 0.2367,
|
| 792 |
+
"step": 3800
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 0.57,
|
| 796 |
+
"eval_F1": 69.2561,
|
| 797 |
+
"eval_Precision": 89.7754,
|
| 798 |
+
"eval_Recall": 56.3716,
|
| 799 |
+
"eval_accuracy": 67.4368,
|
| 800 |
+
"eval_accuracy_negative": 78.5019,
|
| 801 |
+
"eval_accuracy_positive": 56.3716,
|
| 802 |
+
"eval_gen_len": 3.0,
|
| 803 |
+
"eval_loss": 0.2100234031677246,
|
| 804 |
+
"eval_runtime": 77.9683,
|
| 805 |
+
"eval_samples_per_second": 52.739,
|
| 806 |
+
"eval_steps_per_second": 3.296,
|
| 807 |
+
"step": 3800
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.58,
|
| 811 |
+
"learning_rate": 4.7077338129496404e-05,
|
| 812 |
+
"loss": 0.2157,
|
| 813 |
+
"step": 3900
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.58,
|
| 817 |
+
"eval_F1": 79.2374,
|
| 818 |
+
"eval_Precision": 85.5612,
|
| 819 |
+
"eval_Recall": 73.784,
|
| 820 |
+
"eval_accuracy": 76.8482,
|
| 821 |
+
"eval_accuracy_negative": 79.9125,
|
| 822 |
+
"eval_accuracy_positive": 73.784,
|
| 823 |
+
"eval_gen_len": 3.0,
|
| 824 |
+
"eval_loss": 0.23944681882858276,
|
| 825 |
+
"eval_runtime": 77.9314,
|
| 826 |
+
"eval_samples_per_second": 52.764,
|
| 827 |
+
"eval_steps_per_second": 3.298,
|
| 828 |
+
"step": 3900
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.6,
|
| 832 |
+
"learning_rate": 4.700239808153478e-05,
|
| 833 |
+
"loss": 0.2431,
|
| 834 |
+
"step": 4000
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.6,
|
| 838 |
+
"eval_F1": 72.7115,
|
| 839 |
+
"eval_Precision": 89.4812,
|
| 840 |
+
"eval_Recall": 61.2354,
|
| 841 |
+
"eval_accuracy": 74.0272,
|
| 842 |
+
"eval_accuracy_negative": 86.8191,
|
| 843 |
+
"eval_accuracy_positive": 61.2354,
|
| 844 |
+
"eval_gen_len": 3.0,
|
| 845 |
+
"eval_loss": 0.2376098483800888,
|
| 846 |
+
"eval_runtime": 78.0857,
|
| 847 |
+
"eval_samples_per_second": 52.66,
|
| 848 |
+
"eval_steps_per_second": 3.291,
|
| 849 |
+
"step": 4000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.61,
|
| 853 |
+
"learning_rate": 4.6927458033573146e-05,
|
| 854 |
+
"loss": 0.2442,
|
| 855 |
+
"step": 4100
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.61,
|
| 859 |
+
"eval_F1": 82.3446,
|
| 860 |
+
"eval_Precision": 79.7901,
|
| 861 |
+
"eval_Recall": 85.0681,
|
| 862 |
+
"eval_accuracy": 78.4047,
|
| 863 |
+
"eval_accuracy_negative": 71.7412,
|
| 864 |
+
"eval_accuracy_positive": 85.0681,
|
| 865 |
+
"eval_gen_len": 3.0,
|
| 866 |
+
"eval_loss": 0.2564048767089844,
|
| 867 |
+
"eval_runtime": 78.0736,
|
| 868 |
+
"eval_samples_per_second": 52.668,
|
| 869 |
+
"eval_steps_per_second": 3.292,
|
| 870 |
+
"step": 4100
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.63,
|
| 874 |
+
"learning_rate": 4.685251798561151e-05,
|
| 875 |
+
"loss": 0.2125,
|
| 876 |
+
"step": 4200
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 0.63,
|
| 880 |
+
"eval_F1": 81.7357,
|
| 881 |
+
"eval_Precision": 82.4024,
|
| 882 |
+
"eval_Recall": 81.0798,
|
| 883 |
+
"eval_accuracy": 77.4562,
|
| 884 |
+
"eval_accuracy_negative": 73.8327,
|
| 885 |
+
"eval_accuracy_positive": 81.0798,
|
| 886 |
+
"eval_gen_len": 3.0,
|
| 887 |
+
"eval_loss": 0.26422980427742004,
|
| 888 |
+
"eval_runtime": 77.9729,
|
| 889 |
+
"eval_samples_per_second": 52.736,
|
| 890 |
+
"eval_steps_per_second": 3.296,
|
| 891 |
+
"step": 4200
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.64,
|
| 895 |
+
"learning_rate": 4.677757793764988e-05,
|
| 896 |
+
"loss": 0.2213,
|
| 897 |
+
"step": 4300
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.64,
|
| 901 |
+
"eval_F1": 61.6757,
|
| 902 |
+
"eval_Precision": 89.3813,
|
| 903 |
+
"eval_Recall": 47.0817,
|
| 904 |
+
"eval_accuracy": 66.5856,
|
| 905 |
+
"eval_accuracy_negative": 86.0895,
|
| 906 |
+
"eval_accuracy_positive": 47.0817,
|
| 907 |
+
"eval_gen_len": 3.0,
|
| 908 |
+
"eval_loss": 0.2372213900089264,
|
| 909 |
+
"eval_runtime": 78.0051,
|
| 910 |
+
"eval_samples_per_second": 52.714,
|
| 911 |
+
"eval_steps_per_second": 3.295,
|
| 912 |
+
"step": 4300
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.66,
|
| 916 |
+
"learning_rate": 4.670263788968825e-05,
|
| 917 |
+
"loss": 0.2277,
|
| 918 |
+
"step": 4400
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 0.66,
|
| 922 |
+
"eval_F1": 65.461,
|
| 923 |
+
"eval_Precision": 83.8269,
|
| 924 |
+
"eval_Recall": 53.6965,
|
| 925 |
+
"eval_accuracy": 63.2539,
|
| 926 |
+
"eval_accuracy_negative": 72.8113,
|
| 927 |
+
"eval_accuracy_positive": 53.6965,
|
| 928 |
+
"eval_gen_len": 3.0,
|
| 929 |
+
"eval_loss": 0.21777845919132233,
|
| 930 |
+
"eval_runtime": 78.04,
|
| 931 |
+
"eval_samples_per_second": 52.691,
|
| 932 |
+
"eval_steps_per_second": 3.293,
|
| 933 |
+
"step": 4400
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.67,
|
| 937 |
+
"learning_rate": 4.662769784172662e-05,
|
| 938 |
+
"loss": 0.1893,
|
| 939 |
+
"step": 4500
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.67,
|
| 943 |
+
"eval_F1": 61.2192,
|
| 944 |
+
"eval_Precision": 91.8288,
|
| 945 |
+
"eval_Recall": 45.9144,
|
| 946 |
+
"eval_accuracy": 62.1839,
|
| 947 |
+
"eval_accuracy_negative": 78.4533,
|
| 948 |
+
"eval_accuracy_positive": 45.9144,
|
| 949 |
+
"eval_gen_len": 3.0,
|
| 950 |
+
"eval_loss": 0.25438836216926575,
|
| 951 |
+
"eval_runtime": 77.9949,
|
| 952 |
+
"eval_samples_per_second": 52.721,
|
| 953 |
+
"eval_steps_per_second": 3.295,
|
| 954 |
+
"step": 4500
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.69,
|
| 958 |
+
"learning_rate": 4.655275779376499e-05,
|
| 959 |
+
"loss": 0.2577,
|
| 960 |
+
"step": 4600
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.69,
|
| 964 |
+
"eval_F1": 48.5335,
|
| 965 |
+
"eval_Precision": 86.0149,
|
| 966 |
+
"eval_Recall": 33.8035,
|
| 967 |
+
"eval_accuracy": 56.9309,
|
| 968 |
+
"eval_accuracy_negative": 80.0584,
|
| 969 |
+
"eval_accuracy_positive": 33.8035,
|
| 970 |
+
"eval_gen_len": 3.0,
|
| 971 |
+
"eval_loss": 0.20975889265537262,
|
| 972 |
+
"eval_runtime": 77.9509,
|
| 973 |
+
"eval_samples_per_second": 52.751,
|
| 974 |
+
"eval_steps_per_second": 3.297,
|
| 975 |
+
"step": 4600
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.7,
|
| 979 |
+
"learning_rate": 4.647781774580336e-05,
|
| 980 |
+
"loss": 0.2255,
|
| 981 |
+
"step": 4700
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.7,
|
| 985 |
+
"eval_F1": 48.856,
|
| 986 |
+
"eval_Precision": 88.4076,
|
| 987 |
+
"eval_Recall": 33.7549,
|
| 988 |
+
"eval_accuracy": 59.3872,
|
| 989 |
+
"eval_accuracy_negative": 85.0195,
|
| 990 |
+
"eval_accuracy_positive": 33.7549,
|
| 991 |
+
"eval_gen_len": 3.0,
|
| 992 |
+
"eval_loss": 0.2087894082069397,
|
| 993 |
+
"eval_runtime": 78.0665,
|
| 994 |
+
"eval_samples_per_second": 52.673,
|
| 995 |
+
"eval_steps_per_second": 3.292,
|
| 996 |
+
"step": 4700
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.72,
|
| 1000 |
+
"learning_rate": 4.640287769784173e-05,
|
| 1001 |
+
"loss": 0.2052,
|
| 1002 |
+
"step": 4800
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 0.72,
|
| 1006 |
+
"eval_F1": 62.0057,
|
| 1007 |
+
"eval_Precision": 88.6878,
|
| 1008 |
+
"eval_Recall": 47.6654,
|
| 1009 |
+
"eval_accuracy": 64.6887,
|
| 1010 |
+
"eval_accuracy_negative": 81.7121,
|
| 1011 |
+
"eval_accuracy_positive": 47.6654,
|
| 1012 |
+
"eval_gen_len": 3.0,
|
| 1013 |
+
"eval_loss": 0.2096925675868988,
|
| 1014 |
+
"eval_runtime": 78.1278,
|
| 1015 |
+
"eval_samples_per_second": 52.632,
|
| 1016 |
+
"eval_steps_per_second": 3.289,
|
| 1017 |
+
"step": 4800
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.73,
|
| 1021 |
+
"learning_rate": 4.63279376498801e-05,
|
| 1022 |
+
"loss": 0.1803,
|
| 1023 |
+
"step": 4900
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.73,
|
| 1027 |
+
"eval_F1": 76.7251,
|
| 1028 |
+
"eval_Precision": 87.782,
|
| 1029 |
+
"eval_Recall": 68.142,
|
| 1030 |
+
"eval_accuracy": 75.8025,
|
| 1031 |
+
"eval_accuracy_negative": 83.463,
|
| 1032 |
+
"eval_accuracy_positive": 68.142,
|
| 1033 |
+
"eval_gen_len": 3.0,
|
| 1034 |
+
"eval_loss": 0.23566679656505585,
|
| 1035 |
+
"eval_runtime": 78.1099,
|
| 1036 |
+
"eval_samples_per_second": 52.644,
|
| 1037 |
+
"eval_steps_per_second": 3.29,
|
| 1038 |
+
"step": 4900
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.75,
|
| 1042 |
+
"learning_rate": 4.625299760191847e-05,
|
| 1043 |
+
"loss": 0.2405,
|
| 1044 |
+
"step": 5000
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 0.75,
|
| 1048 |
+
"eval_F1": 79.0246,
|
| 1049 |
+
"eval_Precision": 85.7224,
|
| 1050 |
+
"eval_Recall": 73.2977,
|
| 1051 |
+
"eval_accuracy": 75.8998,
|
| 1052 |
+
"eval_accuracy_negative": 78.5019,
|
| 1053 |
+
"eval_accuracy_positive": 73.2977,
|
| 1054 |
+
"eval_gen_len": 3.0,
|
| 1055 |
+
"eval_loss": 0.22571609914302826,
|
| 1056 |
+
"eval_runtime": 77.9758,
|
| 1057 |
+
"eval_samples_per_second": 52.734,
|
| 1058 |
+
"eval_steps_per_second": 3.296,
|
| 1059 |
+
"step": 5000
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.76,
|
| 1063 |
+
"learning_rate": 4.617805755395684e-05,
|
| 1064 |
+
"loss": 0.195,
|
| 1065 |
+
"step": 5100
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.76,
|
| 1069 |
+
"eval_F1": 38.7195,
|
| 1070 |
+
"eval_Precision": 89.4366,
|
| 1071 |
+
"eval_Recall": 24.7082,
|
| 1072 |
+
"eval_accuracy": 55.0097,
|
| 1073 |
+
"eval_accuracy_negative": 85.3113,
|
| 1074 |
+
"eval_accuracy_positive": 24.7082,
|
| 1075 |
+
"eval_gen_len": 3.0,
|
| 1076 |
+
"eval_loss": 0.25449925661087036,
|
| 1077 |
+
"eval_runtime": 78.1451,
|
| 1078 |
+
"eval_samples_per_second": 52.62,
|
| 1079 |
+
"eval_steps_per_second": 3.289,
|
| 1080 |
+
"step": 5100
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.78,
|
| 1084 |
+
"learning_rate": 4.610311750599521e-05,
|
| 1085 |
+
"loss": 0.2136,
|
| 1086 |
+
"step": 5200
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 0.78,
|
| 1090 |
+
"eval_F1": 72.9004,
|
| 1091 |
+
"eval_Precision": 89.638,
|
| 1092 |
+
"eval_Recall": 61.43,
|
| 1093 |
+
"eval_accuracy": 70.1605,
|
| 1094 |
+
"eval_accuracy_negative": 78.8911,
|
| 1095 |
+
"eval_accuracy_positive": 61.43,
|
| 1096 |
+
"eval_gen_len": 3.0,
|
| 1097 |
+
"eval_loss": 0.23430722951889038,
|
| 1098 |
+
"eval_runtime": 78.0577,
|
| 1099 |
+
"eval_samples_per_second": 52.679,
|
| 1100 |
+
"eval_steps_per_second": 3.292,
|
| 1101 |
+
"step": 5200
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.79,
|
| 1105 |
+
"learning_rate": 4.602817745803358e-05,
|
| 1106 |
+
"loss": 0.205,
|
| 1107 |
+
"step": 5300
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 0.79,
|
| 1111 |
+
"eval_F1": 61.5385,
|
| 1112 |
+
"eval_Precision": 88.8073,
|
| 1113 |
+
"eval_Recall": 47.0817,
|
| 1114 |
+
"eval_accuracy": 63.6916,
|
| 1115 |
+
"eval_accuracy_negative": 80.3016,
|
| 1116 |
+
"eval_accuracy_positive": 47.0817,
|
| 1117 |
+
"eval_gen_len": 3.0,
|
| 1118 |
+
"eval_loss": 0.20516321063041687,
|
| 1119 |
+
"eval_runtime": 78.06,
|
| 1120 |
+
"eval_samples_per_second": 52.677,
|
| 1121 |
+
"eval_steps_per_second": 3.292,
|
| 1122 |
+
"step": 5300
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.81,
|
| 1126 |
+
"learning_rate": 4.595323741007194e-05,
|
| 1127 |
+
"loss": 0.227,
|
| 1128 |
+
"step": 5400
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 0.81,
|
| 1132 |
+
"eval_F1": 71.5575,
|
| 1133 |
+
"eval_Precision": 89.1226,
|
| 1134 |
+
"eval_Recall": 59.7763,
|
| 1135 |
+
"eval_accuracy": 70.1119,
|
| 1136 |
+
"eval_accuracy_negative": 80.4475,
|
| 1137 |
+
"eval_accuracy_positive": 59.7763,
|
| 1138 |
+
"eval_gen_len": 3.0,
|
| 1139 |
+
"eval_loss": 0.20273716747760773,
|
| 1140 |
+
"eval_runtime": 78.0817,
|
| 1141 |
+
"eval_samples_per_second": 52.663,
|
| 1142 |
+
"eval_steps_per_second": 3.291,
|
| 1143 |
+
"step": 5400
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.82,
|
| 1147 |
+
"learning_rate": 4.5878297362110315e-05,
|
| 1148 |
+
"loss": 0.221,
|
| 1149 |
+
"step": 5500
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 0.82,
|
| 1153 |
+
"eval_F1": 70.1068,
|
| 1154 |
+
"eval_Precision": 89.8176,
|
| 1155 |
+
"eval_Recall": 57.4903,
|
| 1156 |
+
"eval_accuracy": 68.3123,
|
| 1157 |
+
"eval_accuracy_negative": 79.1342,
|
| 1158 |
+
"eval_accuracy_positive": 57.4903,
|
| 1159 |
+
"eval_gen_len": 3.0,
|
| 1160 |
+
"eval_loss": 0.20614123344421387,
|
| 1161 |
+
"eval_runtime": 78.0595,
|
| 1162 |
+
"eval_samples_per_second": 52.678,
|
| 1163 |
+
"eval_steps_per_second": 3.292,
|
| 1164 |
+
"step": 5500
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.84,
|
| 1168 |
+
"learning_rate": 4.580335731414868e-05,
|
| 1169 |
+
"loss": 0.2148,
|
| 1170 |
+
"step": 5600
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 0.84,
|
| 1174 |
+
"eval_F1": 78.0293,
|
| 1175 |
+
"eval_Precision": 86.2272,
|
| 1176 |
+
"eval_Recall": 71.2549,
|
| 1177 |
+
"eval_accuracy": 71.6683,
|
| 1178 |
+
"eval_accuracy_negative": 72.0817,
|
| 1179 |
+
"eval_accuracy_positive": 71.2549,
|
| 1180 |
+
"eval_gen_len": 3.0,
|
| 1181 |
+
"eval_loss": 0.23381440341472626,
|
| 1182 |
+
"eval_runtime": 78.0578,
|
| 1183 |
+
"eval_samples_per_second": 52.679,
|
| 1184 |
+
"eval_steps_per_second": 3.292,
|
| 1185 |
+
"step": 5600
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.85,
|
| 1189 |
+
"learning_rate": 4.572841726618705e-05,
|
| 1190 |
+
"loss": 0.203,
|
| 1191 |
+
"step": 5700
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 0.85,
|
| 1195 |
+
"eval_F1": 58.205,
|
| 1196 |
+
"eval_Precision": 93.4409,
|
| 1197 |
+
"eval_Recall": 42.2665,
|
| 1198 |
+
"eval_accuracy": 60.4572,
|
| 1199 |
+
"eval_accuracy_negative": 78.6479,
|
| 1200 |
+
"eval_accuracy_positive": 42.2665,
|
| 1201 |
+
"eval_gen_len": 3.0,
|
| 1202 |
+
"eval_loss": 0.2337663322687149,
|
| 1203 |
+
"eval_runtime": 78.2027,
|
| 1204 |
+
"eval_samples_per_second": 52.581,
|
| 1205 |
+
"eval_steps_per_second": 3.286,
|
| 1206 |
+
"step": 5700
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.87,
|
| 1210 |
+
"learning_rate": 4.5653477218225424e-05,
|
| 1211 |
+
"loss": 0.1912,
|
| 1212 |
+
"step": 5800
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 0.87,
|
| 1216 |
+
"eval_F1": 82.295,
|
| 1217 |
+
"eval_Precision": 83.3416,
|
| 1218 |
+
"eval_Recall": 81.2743,
|
| 1219 |
+
"eval_accuracy": 78.6722,
|
| 1220 |
+
"eval_accuracy_negative": 76.07,
|
| 1221 |
+
"eval_accuracy_positive": 81.2743,
|
| 1222 |
+
"eval_gen_len": 3.0,
|
| 1223 |
+
"eval_loss": 0.23967531323432922,
|
| 1224 |
+
"eval_runtime": 78.2026,
|
| 1225 |
+
"eval_samples_per_second": 52.581,
|
| 1226 |
+
"eval_steps_per_second": 3.286,
|
| 1227 |
+
"step": 5800
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.88,
|
| 1231 |
+
"learning_rate": 4.557853717026379e-05,
|
| 1232 |
+
"loss": 0.2292,
|
| 1233 |
+
"step": 5900
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 0.88,
|
| 1237 |
+
"eval_F1": 77.3544,
|
| 1238 |
+
"eval_Precision": 87.8245,
|
| 1239 |
+
"eval_Recall": 69.1148,
|
| 1240 |
+
"eval_accuracy": 71.8142,
|
| 1241 |
+
"eval_accuracy_negative": 74.5136,
|
| 1242 |
+
"eval_accuracy_positive": 69.1148,
|
| 1243 |
+
"eval_gen_len": 3.0,
|
| 1244 |
+
"eval_loss": 0.21783529222011566,
|
| 1245 |
+
"eval_runtime": 78.0505,
|
| 1246 |
+
"eval_samples_per_second": 52.684,
|
| 1247 |
+
"eval_steps_per_second": 3.293,
|
| 1248 |
+
"step": 5900
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.9,
|
| 1252 |
+
"learning_rate": 4.550359712230216e-05,
|
| 1253 |
+
"loss": 0.2366,
|
| 1254 |
+
"step": 6000
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 0.9,
|
| 1258 |
+
"eval_F1": 73.1382,
|
| 1259 |
+
"eval_Precision": 90.4659,
|
| 1260 |
+
"eval_Recall": 61.3813,
|
| 1261 |
+
"eval_accuracy": 69.3337,
|
| 1262 |
+
"eval_accuracy_negative": 77.286,
|
| 1263 |
+
"eval_accuracy_positive": 61.3813,
|
| 1264 |
+
"eval_gen_len": 3.0,
|
| 1265 |
+
"eval_loss": 0.21324363350868225,
|
| 1266 |
+
"eval_runtime": 78.0489,
|
| 1267 |
+
"eval_samples_per_second": 52.685,
|
| 1268 |
+
"eval_steps_per_second": 3.293,
|
| 1269 |
+
"step": 6000
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.91,
|
| 1273 |
+
"learning_rate": 4.542865707434053e-05,
|
| 1274 |
+
"loss": 0.2172,
|
| 1275 |
+
"step": 6100
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 0.91,
|
| 1279 |
+
"eval_F1": 82.6628,
|
| 1280 |
+
"eval_Precision": 81.4151,
|
| 1281 |
+
"eval_Recall": 83.9494,
|
| 1282 |
+
"eval_accuracy": 80.0584,
|
| 1283 |
+
"eval_accuracy_negative": 76.1673,
|
| 1284 |
+
"eval_accuracy_positive": 83.9494,
|
| 1285 |
+
"eval_gen_len": 3.0,
|
| 1286 |
+
"eval_loss": 0.21681031584739685,
|
| 1287 |
+
"eval_runtime": 77.9889,
|
| 1288 |
+
"eval_samples_per_second": 52.725,
|
| 1289 |
+
"eval_steps_per_second": 3.295,
|
| 1290 |
+
"step": 6100
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.93,
|
| 1294 |
+
"learning_rate": 4.53537170263789e-05,
|
| 1295 |
+
"loss": 0.2176,
|
| 1296 |
+
"step": 6200
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 0.93,
|
| 1300 |
+
"eval_F1": 81.7284,
|
| 1301 |
+
"eval_Precision": 82.999,
|
| 1302 |
+
"eval_Recall": 80.4961,
|
| 1303 |
+
"eval_accuracy": 79.2802,
|
| 1304 |
+
"eval_accuracy_negative": 78.0642,
|
| 1305 |
+
"eval_accuracy_positive": 80.4961,
|
| 1306 |
+
"eval_gen_len": 3.0,
|
| 1307 |
+
"eval_loss": 0.19668923318386078,
|
| 1308 |
+
"eval_runtime": 78.1339,
|
| 1309 |
+
"eval_samples_per_second": 52.628,
|
| 1310 |
+
"eval_steps_per_second": 3.289,
|
| 1311 |
+
"step": 6200
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.94,
|
| 1315 |
+
"learning_rate": 4.527877697841727e-05,
|
| 1316 |
+
"loss": 0.1703,
|
| 1317 |
+
"step": 6300
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 0.94,
|
| 1321 |
+
"eval_F1": 82.7941,
|
| 1322 |
+
"eval_Precision": 83.4486,
|
| 1323 |
+
"eval_Recall": 82.1498,
|
| 1324 |
+
"eval_accuracy": 79.9125,
|
| 1325 |
+
"eval_accuracy_negative": 77.6751,
|
| 1326 |
+
"eval_accuracy_positive": 82.1498,
|
| 1327 |
+
"eval_gen_len": 3.0,
|
| 1328 |
+
"eval_loss": 0.23434630036354065,
|
| 1329 |
+
"eval_runtime": 77.9722,
|
| 1330 |
+
"eval_samples_per_second": 52.737,
|
| 1331 |
+
"eval_steps_per_second": 3.296,
|
| 1332 |
+
"step": 6300
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.96,
|
| 1336 |
+
"learning_rate": 4.520383693045564e-05,
|
| 1337 |
+
"loss": 0.2234,
|
| 1338 |
+
"step": 6400
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 0.96,
|
| 1342 |
+
"eval_F1": 83.6217,
|
| 1343 |
+
"eval_Precision": 81.5534,
|
| 1344 |
+
"eval_Recall": 85.7977,
|
| 1345 |
+
"eval_accuracy": 80.2529,
|
| 1346 |
+
"eval_accuracy_negative": 74.7082,
|
| 1347 |
+
"eval_accuracy_positive": 85.7977,
|
| 1348 |
+
"eval_gen_len": 3.0,
|
| 1349 |
+
"eval_loss": 0.22015611827373505,
|
| 1350 |
+
"eval_runtime": 78.0553,
|
| 1351 |
+
"eval_samples_per_second": 52.681,
|
| 1352 |
+
"eval_steps_per_second": 3.293,
|
| 1353 |
+
"step": 6400
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.97,
|
| 1357 |
+
"learning_rate": 4.512889688249401e-05,
|
| 1358 |
+
"loss": 0.2047,
|
| 1359 |
+
"step": 6500
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 0.97,
|
| 1363 |
+
"eval_F1": 83.6764,
|
| 1364 |
+
"eval_Precision": 82.3751,
|
| 1365 |
+
"eval_Recall": 85.0195,
|
| 1366 |
+
"eval_accuracy": 79.1586,
|
| 1367 |
+
"eval_accuracy_negative": 73.2977,
|
| 1368 |
+
"eval_accuracy_positive": 85.0195,
|
| 1369 |
+
"eval_gen_len": 3.0,
|
| 1370 |
+
"eval_loss": 0.20958371460437775,
|
| 1371 |
+
"eval_runtime": 77.9877,
|
| 1372 |
+
"eval_samples_per_second": 52.726,
|
| 1373 |
+
"eval_steps_per_second": 3.295,
|
| 1374 |
+
"step": 6500
|
| 1375 |
+
}
|
| 1376 |
+
],
|
| 1377 |
+
"logging_steps": 100,
|
| 1378 |
+
"max_steps": 66720,
|
| 1379 |
+
"num_train_epochs": 10,
|
| 1380 |
+
"save_steps": 100,
|
| 1381 |
+
"total_flos": 1.83775713030144e+16,
|
| 1382 |
+
"trial_name": null,
|
| 1383 |
+
"trial_params": null
|
| 1384 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc06968df6ffa080e66881d54e5b42b706b771520ad1bde5994d5f71263e9760
|
| 3 |
+
size 4411
|