This model allows to generate multiple words aligned to a beat
Browse files- config.json +33 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +150 -0
- test_results.json +9 -0
- tokenizer_config.json +157 -0
- trainer_state.json +845 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/byt5-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 3968,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 1536,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "gelu_new",
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"eos_token_id": 1,
|
| 13 |
+
"feed_forward_proj": "gated-gelu",
|
| 14 |
+
"gradient_checkpointing": false,
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": true,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "t5",
|
| 20 |
+
"num_decoder_layers": 6,
|
| 21 |
+
"num_heads": 12,
|
| 22 |
+
"num_layers": 18,
|
| 23 |
+
"output_past": true,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"relative_attention_max_distance": 128,
|
| 26 |
+
"relative_attention_num_buckets": 32,
|
| 27 |
+
"tie_word_embeddings": false,
|
| 28 |
+
"tokenizer_class": "ByT5Tokenizer",
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.20.0",
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 384
|
| 33 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d73c84ee09215b1e246ee9dde8ee41ea9490778459dab099428755c4d12ee88f
|
| 3 |
+
size 2326700029
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,150 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"<extra_id_100>",
|
| 104 |
+
"<extra_id_101>",
|
| 105 |
+
"<extra_id_102>",
|
| 106 |
+
"<extra_id_103>",
|
| 107 |
+
"<extra_id_104>",
|
| 108 |
+
"<extra_id_105>",
|
| 109 |
+
"<extra_id_106>",
|
| 110 |
+
"<extra_id_107>",
|
| 111 |
+
"<extra_id_108>",
|
| 112 |
+
"<extra_id_109>",
|
| 113 |
+
"<extra_id_110>",
|
| 114 |
+
"<extra_id_111>",
|
| 115 |
+
"<extra_id_112>",
|
| 116 |
+
"<extra_id_113>",
|
| 117 |
+
"<extra_id_114>",
|
| 118 |
+
"<extra_id_115>",
|
| 119 |
+
"<extra_id_116>",
|
| 120 |
+
"<extra_id_117>",
|
| 121 |
+
"<extra_id_118>",
|
| 122 |
+
"<extra_id_119>",
|
| 123 |
+
"<extra_id_120>",
|
| 124 |
+
"<extra_id_121>",
|
| 125 |
+
"<extra_id_122>",
|
| 126 |
+
"<extra_id_123>",
|
| 127 |
+
"<extra_id_124>"
|
| 128 |
+
],
|
| 129 |
+
"eos_token": {
|
| 130 |
+
"content": "</s>",
|
| 131 |
+
"lstrip": false,
|
| 132 |
+
"normalized": true,
|
| 133 |
+
"rstrip": false,
|
| 134 |
+
"single_word": false
|
| 135 |
+
},
|
| 136 |
+
"pad_token": {
|
| 137 |
+
"content": "<pad>",
|
| 138 |
+
"lstrip": false,
|
| 139 |
+
"normalized": true,
|
| 140 |
+
"rstrip": false,
|
| 141 |
+
"single_word": false
|
| 142 |
+
},
|
| 143 |
+
"unk_token": {
|
| 144 |
+
"content": "<unk>",
|
| 145 |
+
"lstrip": false,
|
| 146 |
+
"normalized": true,
|
| 147 |
+
"rstrip": false,
|
| 148 |
+
"single_word": false
|
| 149 |
+
}
|
| 150 |
+
}
|
test_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"test_corv_score": 0.9817096649980747,
|
| 4 |
+
"test_lev_score": 0.9965901585851572,
|
| 5 |
+
"test_runtime": 114.9349,
|
| 6 |
+
"test_samples_per_second": 45.191,
|
| 7 |
+
"test_steps_per_second": 2.828,
|
| 8 |
+
"test_t5-prp-fluency": 7.498412014887883
|
| 9 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,157 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"<extra_id_100>",
|
| 104 |
+
"<extra_id_101>",
|
| 105 |
+
"<extra_id_102>",
|
| 106 |
+
"<extra_id_103>",
|
| 107 |
+
"<extra_id_104>",
|
| 108 |
+
"<extra_id_105>",
|
| 109 |
+
"<extra_id_106>",
|
| 110 |
+
"<extra_id_107>",
|
| 111 |
+
"<extra_id_108>",
|
| 112 |
+
"<extra_id_109>",
|
| 113 |
+
"<extra_id_110>",
|
| 114 |
+
"<extra_id_111>",
|
| 115 |
+
"<extra_id_112>",
|
| 116 |
+
"<extra_id_113>",
|
| 117 |
+
"<extra_id_114>",
|
| 118 |
+
"<extra_id_115>",
|
| 119 |
+
"<extra_id_116>",
|
| 120 |
+
"<extra_id_117>",
|
| 121 |
+
"<extra_id_118>",
|
| 122 |
+
"<extra_id_119>",
|
| 123 |
+
"<extra_id_120>",
|
| 124 |
+
"<extra_id_121>",
|
| 125 |
+
"<extra_id_122>",
|
| 126 |
+
"<extra_id_123>",
|
| 127 |
+
"<extra_id_124>"
|
| 128 |
+
],
|
| 129 |
+
"eos_token": {
|
| 130 |
+
"__type": "AddedToken",
|
| 131 |
+
"content": "</s>",
|
| 132 |
+
"lstrip": false,
|
| 133 |
+
"normalized": true,
|
| 134 |
+
"rstrip": false,
|
| 135 |
+
"single_word": false
|
| 136 |
+
},
|
| 137 |
+
"extra_ids": 125,
|
| 138 |
+
"name_or_path": "google/byt5-base",
|
| 139 |
+
"pad_token": {
|
| 140 |
+
"__type": "AddedToken",
|
| 141 |
+
"content": "<pad>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": true,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false
|
| 146 |
+
},
|
| 147 |
+
"special_tokens_map_file": "/home/melzohbi/.cache/huggingface/transformers/f22e687c418a9ed3e651ca340d6a5880bbb312bc24bbe893f5cd47288891b89d.063895353d5ef9e19a25220cb616c43abc5e84a2f11b1ffb71c29e097572a109",
|
| 148 |
+
"tokenizer_class": "ByT5Tokenizer",
|
| 149 |
+
"unk_token": {
|
| 150 |
+
"__type": "AddedToken",
|
| 151 |
+
"content": "<unk>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false
|
| 156 |
+
}
|
| 157 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,845 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.9999225970246295,
|
| 5 |
+
"global_step": 32296,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.0,
|
| 12 |
+
"learning_rate": 9.287925696594427e-07,
|
| 13 |
+
"loss": 7.2762,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.03,
|
| 18 |
+
"learning_rate": 0.00023219814241486067,
|
| 19 |
+
"loss": 3.2842,
|
| 20 |
+
"step": 250
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.06,
|
| 24 |
+
"learning_rate": 0.0002999773154682302,
|
| 25 |
+
"loss": 1.4905,
|
| 26 |
+
"step": 500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.09,
|
| 30 |
+
"learning_rate": 0.0002998679962481985,
|
| 31 |
+
"loss": 1.2796,
|
| 32 |
+
"step": 750
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.12,
|
| 36 |
+
"learning_rate": 0.0002996682496269463,
|
| 37 |
+
"loss": 1.1723,
|
| 38 |
+
"step": 1000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.15,
|
| 42 |
+
"learning_rate": 0.00029937819612765605,
|
| 43 |
+
"loss": 1.1113,
|
| 44 |
+
"step": 1250
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.19,
|
| 48 |
+
"learning_rate": 0.0002989980107629042,
|
| 49 |
+
"loss": 1.0653,
|
| 50 |
+
"step": 1500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.22,
|
| 54 |
+
"learning_rate": 0.00029852792292906226,
|
| 55 |
+
"loss": 1.0398,
|
| 56 |
+
"step": 1750
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.25,
|
| 60 |
+
"learning_rate": 0.0002979682162678829,
|
| 61 |
+
"loss": 1.0151,
|
| 62 |
+
"step": 2000
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.28,
|
| 66 |
+
"learning_rate": 0.0002973192284953569,
|
| 67 |
+
"loss": 1.0004,
|
| 68 |
+
"step": 2250
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.31,
|
| 72 |
+
"learning_rate": 0.00029658135119794136,
|
| 73 |
+
"loss": 0.9809,
|
| 74 |
+
"step": 2500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.34,
|
| 78 |
+
"learning_rate": 0.00029575502959628444,
|
| 79 |
+
"loss": 0.9701,
|
| 80 |
+
"step": 2750
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.37,
|
| 84 |
+
"learning_rate": 0.00029484076227658787,
|
| 85 |
+
"loss": 0.9533,
|
| 86 |
+
"step": 3000
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.4,
|
| 90 |
+
"learning_rate": 0.00029383910088976985,
|
| 91 |
+
"loss": 0.9449,
|
| 92 |
+
"step": 3250
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.43,
|
| 96 |
+
"learning_rate": 0.00029275064981860977,
|
| 97 |
+
"loss": 0.9328,
|
| 98 |
+
"step": 3500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.46,
|
| 102 |
+
"learning_rate": 0.0002915760658130755,
|
| 103 |
+
"loss": 0.9233,
|
| 104 |
+
"step": 3750
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.5,
|
| 108 |
+
"learning_rate": 0.0002903160575940534,
|
| 109 |
+
"loss": 0.9198,
|
| 110 |
+
"step": 4000
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.53,
|
| 114 |
+
"learning_rate": 0.00028897138542572,
|
| 115 |
+
"loss": 0.9065,
|
| 116 |
+
"step": 4250
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.56,
|
| 120 |
+
"learning_rate": 0.00028754286065681367,
|
| 121 |
+
"loss": 0.9031,
|
| 122 |
+
"step": 4500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.59,
|
| 126 |
+
"learning_rate": 0.0002860313452310827,
|
| 127 |
+
"loss": 0.8971,
|
| 128 |
+
"step": 4750
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.62,
|
| 132 |
+
"learning_rate": 0.0002844377511672054,
|
| 133 |
+
"loss": 0.8871,
|
| 134 |
+
"step": 5000
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.65,
|
| 138 |
+
"learning_rate": 0.0002827630400084958,
|
| 139 |
+
"loss": 0.8796,
|
| 140 |
+
"step": 5250
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.68,
|
| 144 |
+
"learning_rate": 0.00028100822224272776,
|
| 145 |
+
"loss": 0.8793,
|
| 146 |
+
"step": 5500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.71,
|
| 150 |
+
"learning_rate": 0.0002791743566924259,
|
| 151 |
+
"loss": 0.8675,
|
| 152 |
+
"step": 5750
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.74,
|
| 156 |
+
"learning_rate": 0.0002772625498759935,
|
| 157 |
+
"loss": 0.8755,
|
| 158 |
+
"step": 6000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.77,
|
| 162 |
+
"learning_rate": 0.00027527395534006084,
|
| 163 |
+
"loss": 0.8654,
|
| 164 |
+
"step": 6250
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.8,
|
| 168 |
+
"learning_rate": 0.0002732097729634576,
|
| 169 |
+
"loss": 0.8639,
|
| 170 |
+
"step": 6500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.84,
|
| 174 |
+
"learning_rate": 0.0002710712482332301,
|
| 175 |
+
"loss": 0.8581,
|
| 176 |
+
"step": 6750
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.87,
|
| 180 |
+
"learning_rate": 0.0002688596714931383,
|
| 181 |
+
"loss": 0.8543,
|
| 182 |
+
"step": 7000
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.9,
|
| 186 |
+
"learning_rate": 0.0002665763771650883,
|
| 187 |
+
"loss": 0.849,
|
| 188 |
+
"step": 7250
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.93,
|
| 192 |
+
"learning_rate": 0.00026422274294396817,
|
| 193 |
+
"loss": 0.8407,
|
| 194 |
+
"step": 7500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.96,
|
| 198 |
+
"learning_rate": 0.0002618001889663738,
|
| 199 |
+
"loss": 0.842,
|
| 200 |
+
"step": 7750
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.99,
|
| 204 |
+
"learning_rate": 0.0002593101769537267,
|
| 205 |
+
"loss": 0.8345,
|
| 206 |
+
"step": 8000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.0,
|
| 210 |
+
"eval_corv_score": 0.9549480169426261,
|
| 211 |
+
"eval_lev_score": 0.9913295381925039,
|
| 212 |
+
"eval_runtime": 119.8225,
|
| 213 |
+
"eval_samples_per_second": 43.347,
|
| 214 |
+
"eval_steps_per_second": 2.712,
|
| 215 |
+
"eval_t5-prp-fluency": 7.594483043964092,
|
| 216 |
+
"step": 8074
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.02,
|
| 220 |
+
"learning_rate": 0.0002567542093302999,
|
| 221 |
+
"loss": 0.8192,
|
| 222 |
+
"step": 8250
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 1.05,
|
| 226 |
+
"learning_rate": 0.00025413382831668464,
|
| 227 |
+
"loss": 0.7998,
|
| 228 |
+
"step": 8500
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.08,
|
| 232 |
+
"learning_rate": 0.000251450614999245,
|
| 233 |
+
"loss": 0.7973,
|
| 234 |
+
"step": 8750
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.11,
|
| 238 |
+
"learning_rate": 0.0002487061883761213,
|
| 239 |
+
"loss": 0.7956,
|
| 240 |
+
"step": 9000
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.15,
|
| 244 |
+
"learning_rate": 0.0002459022043803584,
|
| 245 |
+
"loss": 0.7908,
|
| 246 |
+
"step": 9250
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.18,
|
| 250 |
+
"learning_rate": 0.00024304035488074857,
|
| 251 |
+
"loss": 0.791,
|
| 252 |
+
"step": 9500
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.21,
|
| 256 |
+
"learning_rate": 0.0002401223666609909,
|
| 257 |
+
"loss": 0.7884,
|
| 258 |
+
"step": 9750
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.24,
|
| 262 |
+
"learning_rate": 0.00023715000037778392,
|
| 263 |
+
"loss": 0.7937,
|
| 264 |
+
"step": 10000
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.27,
|
| 268 |
+
"learning_rate": 0.00023412504949848025,
|
| 269 |
+
"loss": 0.7863,
|
| 270 |
+
"step": 10250
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.3,
|
| 274 |
+
"learning_rate": 0.0002310493392189435,
|
| 275 |
+
"loss": 0.7907,
|
| 276 |
+
"step": 10500
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.33,
|
| 280 |
+
"learning_rate": 0.000227924725362261,
|
| 281 |
+
"loss": 0.7781,
|
| 282 |
+
"step": 10750
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.36,
|
| 286 |
+
"learning_rate": 0.0002247530932589765,
|
| 287 |
+
"loss": 0.7778,
|
| 288 |
+
"step": 11000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.39,
|
| 292 |
+
"learning_rate": 0.00022153635660951925,
|
| 293 |
+
"loss": 0.7752,
|
| 294 |
+
"step": 11250
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.42,
|
| 298 |
+
"learning_rate": 0.00021827645632951426,
|
| 299 |
+
"loss": 0.7694,
|
| 300 |
+
"step": 11500
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.46,
|
| 304 |
+
"learning_rate": 0.00021497535937867236,
|
| 305 |
+
"loss": 0.771,
|
| 306 |
+
"step": 11750
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.49,
|
| 310 |
+
"learning_rate": 0.0002116350575739653,
|
| 311 |
+
"loss": 0.7709,
|
| 312 |
+
"step": 12000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 1.52,
|
| 316 |
+
"learning_rate": 0.0002082575663878024,
|
| 317 |
+
"loss": 0.768,
|
| 318 |
+
"step": 12250
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.55,
|
| 322 |
+
"learning_rate": 0.00020484492373193437,
|
| 323 |
+
"loss": 0.7678,
|
| 324 |
+
"step": 12500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.58,
|
| 328 |
+
"learning_rate": 0.00020139918872781742,
|
| 329 |
+
"loss": 0.7605,
|
| 330 |
+
"step": 12750
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 1.61,
|
| 334 |
+
"learning_rate": 0.00019792244046417973,
|
| 335 |
+
"loss": 0.7641,
|
| 336 |
+
"step": 13000
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.64,
|
| 340 |
+
"learning_rate": 0.0001944167767425403,
|
| 341 |
+
"loss": 0.7559,
|
| 342 |
+
"step": 13250
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 1.67,
|
| 346 |
+
"learning_rate": 0.00019088431281143674,
|
| 347 |
+
"loss": 0.7604,
|
| 348 |
+
"step": 13500
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 1.7,
|
| 352 |
+
"learning_rate": 0.00018732718009012596,
|
| 353 |
+
"loss": 0.7573,
|
| 354 |
+
"step": 13750
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.73,
|
| 358 |
+
"learning_rate": 0.0001837475248825276,
|
| 359 |
+
"loss": 0.7552,
|
| 360 |
+
"step": 14000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.76,
|
| 364 |
+
"learning_rate": 0.00018014750708218673,
|
| 365 |
+
"loss": 0.7494,
|
| 366 |
+
"step": 14250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.8,
|
| 370 |
+
"learning_rate": 0.00017652929886903608,
|
| 371 |
+
"loss": 0.7521,
|
| 372 |
+
"step": 14500
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.83,
|
| 376 |
+
"learning_rate": 0.00017289508339874587,
|
| 377 |
+
"loss": 0.7454,
|
| 378 |
+
"step": 14750
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.86,
|
| 382 |
+
"learning_rate": 0.00016924705348545055,
|
| 383 |
+
"loss": 0.7496,
|
| 384 |
+
"step": 15000
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.89,
|
| 388 |
+
"learning_rate": 0.00016558741027864748,
|
| 389 |
+
"loss": 0.7424,
|
| 390 |
+
"step": 15250
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.92,
|
| 394 |
+
"learning_rate": 0.00016191836193506709,
|
| 395 |
+
"loss": 0.7434,
|
| 396 |
+
"step": 15500
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.95,
|
| 400 |
+
"learning_rate": 0.0001582421222863143,
|
| 401 |
+
"loss": 0.7399,
|
| 402 |
+
"step": 15750
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.98,
|
| 406 |
+
"learning_rate": 0.00015456090950308622,
|
| 407 |
+
"loss": 0.7354,
|
| 408 |
+
"step": 16000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.0,
|
| 412 |
+
"eval_corv_score": 0.9751636503658067,
|
| 413 |
+
"eval_lev_score": 0.9953171820578365,
|
| 414 |
+
"eval_runtime": 115.5905,
|
| 415 |
+
"eval_samples_per_second": 44.935,
|
| 416 |
+
"eval_steps_per_second": 2.812,
|
| 417 |
+
"eval_t5-prp-fluency": 7.509893327859732,
|
| 418 |
+
"step": 16148
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 2.01,
|
| 422 |
+
"learning_rate": 0.0001508769447567713,
|
| 423 |
+
"loss": 0.7177,
|
| 424 |
+
"step": 16250
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 2.04,
|
| 428 |
+
"learning_rate": 0.00014719245087923855,
|
| 429 |
+
"loss": 0.6866,
|
| 430 |
+
"step": 16500
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 2.07,
|
| 434 |
+
"learning_rate": 0.0001435096510216243,
|
| 435 |
+
"loss": 0.6838,
|
| 436 |
+
"step": 16750
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 2.11,
|
| 440 |
+
"learning_rate": 0.0001398307673129266,
|
| 441 |
+
"loss": 0.6827,
|
| 442 |
+
"step": 17000
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 2.14,
|
| 446 |
+
"learning_rate": 0.0001361580195192162,
|
| 447 |
+
"loss": 0.6826,
|
| 448 |
+
"step": 17250
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 2.17,
|
| 452 |
+
"learning_rate": 0.0001324936237042735,
|
| 453 |
+
"loss": 0.6816,
|
| 454 |
+
"step": 17500
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 2.2,
|
| 458 |
+
"learning_rate": 0.00012883979089245917,
|
| 459 |
+
"loss": 0.6859,
|
| 460 |
+
"step": 17750
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 2.23,
|
| 464 |
+
"learning_rate": 0.00012519872573462553,
|
| 465 |
+
"loss": 0.6783,
|
| 466 |
+
"step": 18000
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 2.26,
|
| 470 |
+
"learning_rate": 0.00012157262517787366,
|
| 471 |
+
"loss": 0.6826,
|
| 472 |
+
"step": 18250
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 2.29,
|
| 476 |
+
"learning_rate": 0.0001179636771399586,
|
| 477 |
+
"loss": 0.6756,
|
| 478 |
+
"step": 18500
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 2.32,
|
| 482 |
+
"learning_rate": 0.00011437405918914297,
|
| 483 |
+
"loss": 0.6782,
|
| 484 |
+
"step": 18750
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 2.35,
|
| 488 |
+
"learning_rate": 0.00011080593723029505,
|
| 489 |
+
"loss": 0.6762,
|
| 490 |
+
"step": 19000
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 2.38,
|
| 494 |
+
"learning_rate": 0.00010726146419802426,
|
| 495 |
+
"loss": 0.6736,
|
| 496 |
+
"step": 19250
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 2.42,
|
| 500 |
+
"learning_rate": 0.00010374277875764294,
|
| 501 |
+
"loss": 0.6716,
|
| 502 |
+
"step": 19500
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 2.45,
|
| 506 |
+
"learning_rate": 0.0001002520040147377,
|
| 507 |
+
"loss": 0.6695,
|
| 508 |
+
"step": 19750
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 2.48,
|
| 512 |
+
"learning_rate": 9.679124623412919e-05,
|
| 513 |
+
"loss": 0.6705,
|
| 514 |
+
"step": 20000
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 2.51,
|
| 518 |
+
"learning_rate": 9.336259356899358e-05,
|
| 519 |
+
"loss": 0.6656,
|
| 520 |
+
"step": 20250
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 2.54,
|
| 524 |
+
"learning_rate": 8.99681148009116e-05,
|
| 525 |
+
"loss": 0.6703,
|
| 526 |
+
"step": 20500
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 2.57,
|
| 530 |
+
"learning_rate": 8.660985809160688e-05,
|
| 531 |
+
"loss": 0.6694,
|
| 532 |
+
"step": 20750
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 2.6,
|
| 536 |
+
"learning_rate": 8.328984974712501e-05,
|
| 537 |
+
"loss": 0.661,
|
| 538 |
+
"step": 21000
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 2.63,
|
| 542 |
+
"learning_rate": 8.001009299520067e-05,
|
| 543 |
+
"loss": 0.6628,
|
| 544 |
+
"step": 21250
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 2.66,
|
| 548 |
+
"learning_rate": 7.677256677654927e-05,
|
| 549 |
+
"loss": 0.6637,
|
| 550 |
+
"step": 21500
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 2.69,
|
| 554 |
+
"learning_rate": 7.35792245508131e-05,
|
| 555 |
+
"loss": 0.6618,
|
| 556 |
+
"step": 21750
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 2.72,
|
| 560 |
+
"learning_rate": 7.043199311788208e-05,
|
| 561 |
+
"loss": 0.6656,
|
| 562 |
+
"step": 22000
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 2.76,
|
| 566 |
+
"learning_rate": 6.733277145530084e-05,
|
| 567 |
+
"loss": 0.6639,
|
| 568 |
+
"step": 22250
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 2.79,
|
| 572 |
+
"learning_rate": 6.428342957246265e-05,
|
| 573 |
+
"loss": 0.6534,
|
| 574 |
+
"step": 22500
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 2.82,
|
| 578 |
+
"learning_rate": 6.128580738228292e-05,
|
| 579 |
+
"loss": 0.6596,
|
| 580 |
+
"step": 22750
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 2.85,
|
| 584 |
+
"learning_rate": 5.8341713591031753e-05,
|
| 585 |
+
"loss": 0.6578,
|
| 586 |
+
"step": 23000
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 2.88,
|
| 590 |
+
"learning_rate": 5.545292460699615e-05,
|
| 591 |
+
"loss": 0.6567,
|
| 592 |
+
"step": 23250
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.91,
|
| 596 |
+
"learning_rate": 5.2621183468630204e-05,
|
| 597 |
+
"loss": 0.6557,
|
| 598 |
+
"step": 23500
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 2.94,
|
| 602 |
+
"learning_rate": 4.9848198792840026e-05,
|
| 603 |
+
"loss": 0.6566,
|
| 604 |
+
"step": 23750
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 2.97,
|
| 608 |
+
"learning_rate": 4.713564374403786e-05,
|
| 609 |
+
"loss": 0.6569,
|
| 610 |
+
"step": 24000
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 3.0,
|
| 614 |
+
"eval_corv_score": 0.9797843665768194,
|
| 615 |
+
"eval_lev_score": 0.99618999924753,
|
| 616 |
+
"eval_runtime": 155.6188,
|
| 617 |
+
"eval_samples_per_second": 33.376,
|
| 618 |
+
"eval_steps_per_second": 2.088,
|
| 619 |
+
"eval_t5-prp-fluency": 7.498019453195425,
|
| 620 |
+
"step": 24222
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 3.0,
|
| 624 |
+
"learning_rate": 4.448515502458757e-05,
|
| 625 |
+
"loss": 0.6509,
|
| 626 |
+
"step": 24250
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 3.03,
|
| 630 |
+
"learning_rate": 4.189833188725071e-05,
|
| 631 |
+
"loss": 0.6021,
|
| 632 |
+
"step": 24500
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 3.07,
|
| 636 |
+
"learning_rate": 3.9376735170228755e-05,
|
| 637 |
+
"loss": 0.5938,
|
| 638 |
+
"step": 24750
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 3.1,
|
| 642 |
+
"learning_rate": 3.6921886355384136e-05,
|
| 643 |
+
"loss": 0.594,
|
| 644 |
+
"step": 25000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 3.13,
|
| 648 |
+
"learning_rate": 3.45352666502079e-05,
|
| 649 |
+
"loss": 0.5941,
|
| 650 |
+
"step": 25250
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 3.16,
|
| 654 |
+
"learning_rate": 3.221831609408837e-05,
|
| 655 |
+
"loss": 0.5967,
|
| 656 |
+
"step": 25500
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 3.19,
|
| 660 |
+
"learning_rate": 2.9972432689419552e-05,
|
| 661 |
+
"loss": 0.5897,
|
| 662 |
+
"step": 25750
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 3.22,
|
| 666 |
+
"learning_rate": 2.779897155807418e-05,
|
| 667 |
+
"loss": 0.5969,
|
| 668 |
+
"step": 26000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 3.25,
|
| 672 |
+
"learning_rate": 2.569924412374956e-05,
|
| 673 |
+
"loss": 0.5944,
|
| 674 |
+
"step": 26250
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 3.28,
|
| 678 |
+
"learning_rate": 2.367451732068059e-05,
|
| 679 |
+
"loss": 0.598,
|
| 680 |
+
"step": 26500
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 3.31,
|
| 684 |
+
"learning_rate": 2.1726012829196434e-05,
|
| 685 |
+
"loss": 0.592,
|
| 686 |
+
"step": 26750
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 3.34,
|
| 690 |
+
"learning_rate": 1.9854906338582588e-05,
|
| 691 |
+
"loss": 0.5907,
|
| 692 |
+
"step": 27000
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 3.38,
|
| 696 |
+
"learning_rate": 1.8062326837693165e-05,
|
| 697 |
+
"loss": 0.5923,
|
| 698 |
+
"step": 27250
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 3.41,
|
| 702 |
+
"learning_rate": 1.6349355933741237e-05,
|
| 703 |
+
"loss": 0.5915,
|
| 704 |
+
"step": 27500
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 3.44,
|
| 708 |
+
"learning_rate": 1.4717027199678216e-05,
|
| 709 |
+
"loss": 0.5901,
|
| 710 |
+
"step": 27750
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 3.47,
|
| 714 |
+
"learning_rate": 1.3166325550556416e-05,
|
| 715 |
+
"loss": 0.5891,
|
| 716 |
+
"step": 28000
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 3.5,
|
| 720 |
+
"learning_rate": 1.1698186649250535e-05,
|
| 721 |
+
"loss": 0.5903,
|
| 722 |
+
"step": 28250
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 3.53,
|
| 726 |
+
"learning_rate": 1.0313496341897181e-05,
|
| 727 |
+
"loss": 0.587,
|
| 728 |
+
"step": 28500
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 3.56,
|
| 732 |
+
"learning_rate": 9.013090123392674e-06,
|
| 733 |
+
"loss": 0.5943,
|
| 734 |
+
"step": 28750
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 3.59,
|
| 738 |
+
"learning_rate": 7.797752633271908e-06,
|
| 739 |
+
"loss": 0.5919,
|
| 740 |
+
"step": 29000
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 3.62,
|
| 744 |
+
"learning_rate": 6.6682171822722675e-06,
|
| 745 |
+
"loss": 0.589,
|
| 746 |
+
"step": 29250
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 3.65,
|
| 750 |
+
"learning_rate": 5.625165309868323e-06,
|
| 751 |
+
"loss": 0.5911,
|
| 752 |
+
"step": 29500
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 3.68,
|
| 756 |
+
"learning_rate": 4.669226373044388e-06,
|
| 757 |
+
"loss": 0.5929,
|
| 758 |
+
"step": 29750
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 3.72,
|
| 762 |
+
"learning_rate": 3.8009771665527712e-06,
|
| 763 |
+
"loss": 0.5899,
|
| 764 |
+
"step": 30000
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 3.75,
|
| 768 |
+
"learning_rate": 3.0209415748873254e-06,
|
| 769 |
+
"loss": 0.592,
|
| 770 |
+
"step": 30250
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 3.78,
|
| 774 |
+
"learning_rate": 2.3295902561817516e-06,
|
| 775 |
+
"loss": 0.5888,
|
| 776 |
+
"step": 30500
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 3.81,
|
| 780 |
+
"learning_rate": 1.7273403582237277e-06,
|
| 781 |
+
"loss": 0.5904,
|
| 782 |
+
"step": 30750
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 3.84,
|
| 786 |
+
"learning_rate": 1.2145552667561676e-06,
|
| 787 |
+
"loss": 0.5886,
|
| 788 |
+
"step": 31000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 3.87,
|
| 792 |
+
"learning_rate": 7.915443862174409e-07,
|
| 793 |
+
"loss": 0.5904,
|
| 794 |
+
"step": 31250
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 3.9,
|
| 798 |
+
"learning_rate": 4.585629530527768e-07,
|
| 799 |
+
"loss": 0.5841,
|
| 800 |
+
"step": 31500
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 3.93,
|
| 804 |
+
"learning_rate": 2.1581188170960438e-07,
|
| 805 |
+
"loss": 0.5886,
|
| 806 |
+
"step": 31750
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 3.96,
|
| 810 |
+
"learning_rate": 6.343764340977497e-08,
|
| 811 |
+
"loss": 0.5857,
|
| 812 |
+
"step": 32000
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 3.99,
|
| 816 |
+
"learning_rate": 1.5321777716570394e-09,
|
| 817 |
+
"loss": 0.5867,
|
| 818 |
+
"step": 32250
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 4.0,
|
| 822 |
+
"eval_corv_score": 0.9830573738929534,
|
| 823 |
+
"eval_lev_score": 0.9963118068762173,
|
| 824 |
+
"eval_runtime": 116.0292,
|
| 825 |
+
"eval_samples_per_second": 44.765,
|
| 826 |
+
"eval_steps_per_second": 2.801,
|
| 827 |
+
"eval_t5-prp-fluency": 7.493759269714356,
|
| 828 |
+
"step": 32296
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 4.0,
|
| 832 |
+
"step": 32296,
|
| 833 |
+
"total_flos": 7.67688706167423e+17,
|
| 834 |
+
"train_loss": 0.7648685576303306,
|
| 835 |
+
"train_runtime": 24220.9861,
|
| 836 |
+
"train_samples_per_second": 170.687,
|
| 837 |
+
"train_steps_per_second": 1.333
|
| 838 |
+
}
|
| 839 |
+
],
|
| 840 |
+
"max_steps": 32296,
|
| 841 |
+
"num_train_epochs": 4,
|
| 842 |
+
"total_flos": 7.67688706167423e+17,
|
| 843 |
+
"trial_name": null,
|
| 844 |
+
"trial_params": null
|
| 845 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35d8401529627986916928e07fef2ac496ca8ae1c88d0bd8a470f2223ca1d5cc
|
| 3 |
+
size 3515
|