Upload 12 files
Browse files- all_results.json +16 -0
- config.json +62 -0
- eval_results.json +9 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- special_tokens_map.json +125 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +938 -0
- train_results.json +11 -0
- trainer_state.json +1024 -0
- training_args.bin +3 -0
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 0.13376566767692566,
|
| 4 |
+
"eval_runtime": 45.0014,
|
| 5 |
+
"eval_samples": 2500,
|
| 6 |
+
"eval_samples_per_second": 55.554,
|
| 7 |
+
"eval_steps_per_second": 6.955,
|
| 8 |
+
"num_input_tokens_seen": 56941616,
|
| 9 |
+
"total_flos": 2.067540416810189e+16,
|
| 10 |
+
"train_loss": 0.19179043090820314,
|
| 11 |
+
"train_runtime": 4730.669,
|
| 12 |
+
"train_samples": 100000,
|
| 13 |
+
"train_samples_per_second": 21.139,
|
| 14 |
+
"train_steps_per_second": 10.569,
|
| 15 |
+
"train_tokens_per_second": 12036.694
|
| 16 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/flan-t5-small",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 1024,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 512,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "gelu_new",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "gated-gelu",
|
| 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 |
+
"n_positions": 512,
|
| 21 |
+
"num_decoder_layers": 8,
|
| 22 |
+
"num_heads": 6,
|
| 23 |
+
"num_layers": 8,
|
| 24 |
+
"output_past": true,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"relative_attention_max_distance": 128,
|
| 27 |
+
"relative_attention_num_buckets": 32,
|
| 28 |
+
"task_specific_params": {
|
| 29 |
+
"summarization": {
|
| 30 |
+
"early_stopping": true,
|
| 31 |
+
"length_penalty": 2.0,
|
| 32 |
+
"max_length": 200,
|
| 33 |
+
"min_length": 30,
|
| 34 |
+
"no_repeat_ngram_size": 3,
|
| 35 |
+
"num_beams": 4,
|
| 36 |
+
"prefix": "summarize: "
|
| 37 |
+
},
|
| 38 |
+
"translation_en_to_de": {
|
| 39 |
+
"early_stopping": true,
|
| 40 |
+
"max_length": 300,
|
| 41 |
+
"num_beams": 4,
|
| 42 |
+
"prefix": "translate English to German: "
|
| 43 |
+
},
|
| 44 |
+
"translation_en_to_fr": {
|
| 45 |
+
"early_stopping": true,
|
| 46 |
+
"max_length": 300,
|
| 47 |
+
"num_beams": 4,
|
| 48 |
+
"prefix": "translate English to French: "
|
| 49 |
+
},
|
| 50 |
+
"translation_en_to_ro": {
|
| 51 |
+
"early_stopping": true,
|
| 52 |
+
"max_length": 300,
|
| 53 |
+
"num_beams": 4,
|
| 54 |
+
"prefix": "translate English to Romanian: "
|
| 55 |
+
}
|
| 56 |
+
},
|
| 57 |
+
"tie_word_embeddings": false,
|
| 58 |
+
"torch_dtype": "float32",
|
| 59 |
+
"transformers_version": "4.43.3",
|
| 60 |
+
"use_cache": true,
|
| 61 |
+
"vocab_size": 32128
|
| 62 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 0.13376566767692566,
|
| 4 |
+
"eval_runtime": 45.0014,
|
| 5 |
+
"eval_samples": 2500,
|
| 6 |
+
"eval_samples_per_second": 55.554,
|
| 7 |
+
"eval_steps_per_second": 6.955,
|
| 8 |
+
"num_input_tokens_seen": 56941616
|
| 9 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.43.3"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e6a9b467e2e38a28544787bee94673aef3672a31c04f1f1004cbca64e1eb848
|
| 3 |
+
size 307867048
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"eos_token": {
|
| 105 |
+
"content": "</s>",
|
| 106 |
+
"lstrip": false,
|
| 107 |
+
"normalized": false,
|
| 108 |
+
"rstrip": false,
|
| 109 |
+
"single_word": false
|
| 110 |
+
},
|
| 111 |
+
"pad_token": {
|
| 112 |
+
"content": "<pad>",
|
| 113 |
+
"lstrip": false,
|
| 114 |
+
"normalized": false,
|
| 115 |
+
"rstrip": false,
|
| 116 |
+
"single_word": false
|
| 117 |
+
},
|
| 118 |
+
"unk_token": {
|
| 119 |
+
"content": "<unk>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false
|
| 124 |
+
}
|
| 125 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
| 3 |
+
size 791656
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,938 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "</s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<unk>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"32000": {
|
| 28 |
+
"content": "<extra_id_99>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"32001": {
|
| 36 |
+
"content": "<extra_id_98>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"32002": {
|
| 44 |
+
"content": "<extra_id_97>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"32003": {
|
| 52 |
+
"content": "<extra_id_96>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"32004": {
|
| 60 |
+
"content": "<extra_id_95>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"32005": {
|
| 68 |
+
"content": "<extra_id_94>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"32006": {
|
| 76 |
+
"content": "<extra_id_93>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"32007": {
|
| 84 |
+
"content": "<extra_id_92>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"32008": {
|
| 92 |
+
"content": "<extra_id_91>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"32009": {
|
| 100 |
+
"content": "<extra_id_90>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"32010": {
|
| 108 |
+
"content": "<extra_id_89>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"32011": {
|
| 116 |
+
"content": "<extra_id_88>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"32012": {
|
| 124 |
+
"content": "<extra_id_87>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"32013": {
|
| 132 |
+
"content": "<extra_id_86>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"32014": {
|
| 140 |
+
"content": "<extra_id_85>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"32015": {
|
| 148 |
+
"content": "<extra_id_84>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"32016": {
|
| 156 |
+
"content": "<extra_id_83>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"32017": {
|
| 164 |
+
"content": "<extra_id_82>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"32018": {
|
| 172 |
+
"content": "<extra_id_81>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"32019": {
|
| 180 |
+
"content": "<extra_id_80>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"32020": {
|
| 188 |
+
"content": "<extra_id_79>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"32021": {
|
| 196 |
+
"content": "<extra_id_78>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"32022": {
|
| 204 |
+
"content": "<extra_id_77>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"32023": {
|
| 212 |
+
"content": "<extra_id_76>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"32024": {
|
| 220 |
+
"content": "<extra_id_75>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"32025": {
|
| 228 |
+
"content": "<extra_id_74>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"32026": {
|
| 236 |
+
"content": "<extra_id_73>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"32027": {
|
| 244 |
+
"content": "<extra_id_72>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"32028": {
|
| 252 |
+
"content": "<extra_id_71>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"32029": {
|
| 260 |
+
"content": "<extra_id_70>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"32030": {
|
| 268 |
+
"content": "<extra_id_69>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"32031": {
|
| 276 |
+
"content": "<extra_id_68>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"32032": {
|
| 284 |
+
"content": "<extra_id_67>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"32033": {
|
| 292 |
+
"content": "<extra_id_66>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"32034": {
|
| 300 |
+
"content": "<extra_id_65>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"32035": {
|
| 308 |
+
"content": "<extra_id_64>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"32036": {
|
| 316 |
+
"content": "<extra_id_63>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"32037": {
|
| 324 |
+
"content": "<extra_id_62>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"32038": {
|
| 332 |
+
"content": "<extra_id_61>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"32039": {
|
| 340 |
+
"content": "<extra_id_60>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"32040": {
|
| 348 |
+
"content": "<extra_id_59>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"32041": {
|
| 356 |
+
"content": "<extra_id_58>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"32042": {
|
| 364 |
+
"content": "<extra_id_57>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"32043": {
|
| 372 |
+
"content": "<extra_id_56>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"32044": {
|
| 380 |
+
"content": "<extra_id_55>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"32045": {
|
| 388 |
+
"content": "<extra_id_54>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"32046": {
|
| 396 |
+
"content": "<extra_id_53>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"32047": {
|
| 404 |
+
"content": "<extra_id_52>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"32048": {
|
| 412 |
+
"content": "<extra_id_51>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"32049": {
|
| 420 |
+
"content": "<extra_id_50>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"32050": {
|
| 428 |
+
"content": "<extra_id_49>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"32051": {
|
| 436 |
+
"content": "<extra_id_48>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"32052": {
|
| 444 |
+
"content": "<extra_id_47>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"32053": {
|
| 452 |
+
"content": "<extra_id_46>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"32054": {
|
| 460 |
+
"content": "<extra_id_45>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"32055": {
|
| 468 |
+
"content": "<extra_id_44>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"32056": {
|
| 476 |
+
"content": "<extra_id_43>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"32057": {
|
| 484 |
+
"content": "<extra_id_42>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"32058": {
|
| 492 |
+
"content": "<extra_id_41>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"32059": {
|
| 500 |
+
"content": "<extra_id_40>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"32060": {
|
| 508 |
+
"content": "<extra_id_39>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"32061": {
|
| 516 |
+
"content": "<extra_id_38>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"32062": {
|
| 524 |
+
"content": "<extra_id_37>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"32063": {
|
| 532 |
+
"content": "<extra_id_36>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"32064": {
|
| 540 |
+
"content": "<extra_id_35>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"32065": {
|
| 548 |
+
"content": "<extra_id_34>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"32066": {
|
| 556 |
+
"content": "<extra_id_33>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"32067": {
|
| 564 |
+
"content": "<extra_id_32>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"32068": {
|
| 572 |
+
"content": "<extra_id_31>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"32069": {
|
| 580 |
+
"content": "<extra_id_30>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"32070": {
|
| 588 |
+
"content": "<extra_id_29>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"32071": {
|
| 596 |
+
"content": "<extra_id_28>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"32072": {
|
| 604 |
+
"content": "<extra_id_27>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"32073": {
|
| 612 |
+
"content": "<extra_id_26>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"32074": {
|
| 620 |
+
"content": "<extra_id_25>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"32075": {
|
| 628 |
+
"content": "<extra_id_24>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"32076": {
|
| 636 |
+
"content": "<extra_id_23>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"32077": {
|
| 644 |
+
"content": "<extra_id_22>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"32078": {
|
| 652 |
+
"content": "<extra_id_21>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"32079": {
|
| 660 |
+
"content": "<extra_id_20>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"32080": {
|
| 668 |
+
"content": "<extra_id_19>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"32081": {
|
| 676 |
+
"content": "<extra_id_18>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"32082": {
|
| 684 |
+
"content": "<extra_id_17>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"32083": {
|
| 692 |
+
"content": "<extra_id_16>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"32084": {
|
| 700 |
+
"content": "<extra_id_15>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"32085": {
|
| 708 |
+
"content": "<extra_id_14>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"32086": {
|
| 716 |
+
"content": "<extra_id_13>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"32087": {
|
| 724 |
+
"content": "<extra_id_12>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"32088": {
|
| 732 |
+
"content": "<extra_id_11>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"32089": {
|
| 740 |
+
"content": "<extra_id_10>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"32090": {
|
| 748 |
+
"content": "<extra_id_9>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"32091": {
|
| 756 |
+
"content": "<extra_id_8>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"32092": {
|
| 764 |
+
"content": "<extra_id_7>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"32093": {
|
| 772 |
+
"content": "<extra_id_6>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"32094": {
|
| 780 |
+
"content": "<extra_id_5>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"32095": {
|
| 788 |
+
"content": "<extra_id_4>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"32096": {
|
| 796 |
+
"content": "<extra_id_3>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"32097": {
|
| 804 |
+
"content": "<extra_id_2>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"32098": {
|
| 812 |
+
"content": "<extra_id_1>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"32099": {
|
| 820 |
+
"content": "<extra_id_0>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
}
|
| 827 |
+
},
|
| 828 |
+
"additional_special_tokens": [
|
| 829 |
+
"<extra_id_0>",
|
| 830 |
+
"<extra_id_1>",
|
| 831 |
+
"<extra_id_2>",
|
| 832 |
+
"<extra_id_3>",
|
| 833 |
+
"<extra_id_4>",
|
| 834 |
+
"<extra_id_5>",
|
| 835 |
+
"<extra_id_6>",
|
| 836 |
+
"<extra_id_7>",
|
| 837 |
+
"<extra_id_8>",
|
| 838 |
+
"<extra_id_9>",
|
| 839 |
+
"<extra_id_10>",
|
| 840 |
+
"<extra_id_11>",
|
| 841 |
+
"<extra_id_12>",
|
| 842 |
+
"<extra_id_13>",
|
| 843 |
+
"<extra_id_14>",
|
| 844 |
+
"<extra_id_15>",
|
| 845 |
+
"<extra_id_16>",
|
| 846 |
+
"<extra_id_17>",
|
| 847 |
+
"<extra_id_18>",
|
| 848 |
+
"<extra_id_19>",
|
| 849 |
+
"<extra_id_20>",
|
| 850 |
+
"<extra_id_21>",
|
| 851 |
+
"<extra_id_22>",
|
| 852 |
+
"<extra_id_23>",
|
| 853 |
+
"<extra_id_24>",
|
| 854 |
+
"<extra_id_25>",
|
| 855 |
+
"<extra_id_26>",
|
| 856 |
+
"<extra_id_27>",
|
| 857 |
+
"<extra_id_28>",
|
| 858 |
+
"<extra_id_29>",
|
| 859 |
+
"<extra_id_30>",
|
| 860 |
+
"<extra_id_31>",
|
| 861 |
+
"<extra_id_32>",
|
| 862 |
+
"<extra_id_33>",
|
| 863 |
+
"<extra_id_34>",
|
| 864 |
+
"<extra_id_35>",
|
| 865 |
+
"<extra_id_36>",
|
| 866 |
+
"<extra_id_37>",
|
| 867 |
+
"<extra_id_38>",
|
| 868 |
+
"<extra_id_39>",
|
| 869 |
+
"<extra_id_40>",
|
| 870 |
+
"<extra_id_41>",
|
| 871 |
+
"<extra_id_42>",
|
| 872 |
+
"<extra_id_43>",
|
| 873 |
+
"<extra_id_44>",
|
| 874 |
+
"<extra_id_45>",
|
| 875 |
+
"<extra_id_46>",
|
| 876 |
+
"<extra_id_47>",
|
| 877 |
+
"<extra_id_48>",
|
| 878 |
+
"<extra_id_49>",
|
| 879 |
+
"<extra_id_50>",
|
| 880 |
+
"<extra_id_51>",
|
| 881 |
+
"<extra_id_52>",
|
| 882 |
+
"<extra_id_53>",
|
| 883 |
+
"<extra_id_54>",
|
| 884 |
+
"<extra_id_55>",
|
| 885 |
+
"<extra_id_56>",
|
| 886 |
+
"<extra_id_57>",
|
| 887 |
+
"<extra_id_58>",
|
| 888 |
+
"<extra_id_59>",
|
| 889 |
+
"<extra_id_60>",
|
| 890 |
+
"<extra_id_61>",
|
| 891 |
+
"<extra_id_62>",
|
| 892 |
+
"<extra_id_63>",
|
| 893 |
+
"<extra_id_64>",
|
| 894 |
+
"<extra_id_65>",
|
| 895 |
+
"<extra_id_66>",
|
| 896 |
+
"<extra_id_67>",
|
| 897 |
+
"<extra_id_68>",
|
| 898 |
+
"<extra_id_69>",
|
| 899 |
+
"<extra_id_70>",
|
| 900 |
+
"<extra_id_71>",
|
| 901 |
+
"<extra_id_72>",
|
| 902 |
+
"<extra_id_73>",
|
| 903 |
+
"<extra_id_74>",
|
| 904 |
+
"<extra_id_75>",
|
| 905 |
+
"<extra_id_76>",
|
| 906 |
+
"<extra_id_77>",
|
| 907 |
+
"<extra_id_78>",
|
| 908 |
+
"<extra_id_79>",
|
| 909 |
+
"<extra_id_80>",
|
| 910 |
+
"<extra_id_81>",
|
| 911 |
+
"<extra_id_82>",
|
| 912 |
+
"<extra_id_83>",
|
| 913 |
+
"<extra_id_84>",
|
| 914 |
+
"<extra_id_85>",
|
| 915 |
+
"<extra_id_86>",
|
| 916 |
+
"<extra_id_87>",
|
| 917 |
+
"<extra_id_88>",
|
| 918 |
+
"<extra_id_89>",
|
| 919 |
+
"<extra_id_90>",
|
| 920 |
+
"<extra_id_91>",
|
| 921 |
+
"<extra_id_92>",
|
| 922 |
+
"<extra_id_93>",
|
| 923 |
+
"<extra_id_94>",
|
| 924 |
+
"<extra_id_95>",
|
| 925 |
+
"<extra_id_96>",
|
| 926 |
+
"<extra_id_97>",
|
| 927 |
+
"<extra_id_98>",
|
| 928 |
+
"<extra_id_99>"
|
| 929 |
+
],
|
| 930 |
+
"clean_up_tokenization_spaces": true,
|
| 931 |
+
"eos_token": "</s>",
|
| 932 |
+
"extra_ids": 100,
|
| 933 |
+
"model_max_length": 512,
|
| 934 |
+
"pad_token": "<pad>",
|
| 935 |
+
"sp_model_kwargs": {},
|
| 936 |
+
"tokenizer_class": "T5Tokenizer",
|
| 937 |
+
"unk_token": "<unk>"
|
| 938 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"num_input_tokens_seen": 56941616,
|
| 4 |
+
"total_flos": 2.067540416810189e+16,
|
| 5 |
+
"train_loss": 0.19179043090820314,
|
| 6 |
+
"train_runtime": 4730.669,
|
| 7 |
+
"train_samples": 100000,
|
| 8 |
+
"train_samples_per_second": 21.139,
|
| 9 |
+
"train_steps_per_second": 10.569,
|
| 10 |
+
"train_tokens_per_second": 12036.694
|
| 11 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1024 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.13376566767692566,
|
| 3 |
+
"best_model_checkpoint": "/media/user/Expansion/flan-t5-small-capitalizer/checkpoint-50000",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 2500,
|
| 6 |
+
"global_step": 50000,
|
| 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 |
+
"grad_norm": 1.4570035934448242,
|
| 14 |
+
"learning_rate": 4.9500000000000004e-05,
|
| 15 |
+
"loss": 0.3309,
|
| 16 |
+
"num_input_tokens_seen": 570534,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.02,
|
| 21 |
+
"grad_norm": 1.5052685737609863,
|
| 22 |
+
"learning_rate": 4.9e-05,
|
| 23 |
+
"loss": 0.2655,
|
| 24 |
+
"num_input_tokens_seen": 1140292,
|
| 25 |
+
"step": 1000
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.03,
|
| 29 |
+
"grad_norm": 1.3262746334075928,
|
| 30 |
+
"learning_rate": 4.85e-05,
|
| 31 |
+
"loss": 0.2673,
|
| 32 |
+
"num_input_tokens_seen": 1697650,
|
| 33 |
+
"step": 1500
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.04,
|
| 37 |
+
"grad_norm": 1.0782378911972046,
|
| 38 |
+
"learning_rate": 4.8e-05,
|
| 39 |
+
"loss": 0.2606,
|
| 40 |
+
"num_input_tokens_seen": 2254526,
|
| 41 |
+
"step": 2000
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.05,
|
| 45 |
+
"grad_norm": 1.1907426118850708,
|
| 46 |
+
"learning_rate": 4.75e-05,
|
| 47 |
+
"loss": 0.2532,
|
| 48 |
+
"num_input_tokens_seen": 2824810,
|
| 49 |
+
"step": 2500
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.05,
|
| 53 |
+
"eval_loss": 0.1738843023777008,
|
| 54 |
+
"eval_runtime": 44.8865,
|
| 55 |
+
"eval_samples_per_second": 55.696,
|
| 56 |
+
"eval_steps_per_second": 6.973,
|
| 57 |
+
"num_input_tokens_seen": 2824810,
|
| 58 |
+
"step": 2500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.06,
|
| 62 |
+
"grad_norm": 2.4040281772613525,
|
| 63 |
+
"learning_rate": 4.7e-05,
|
| 64 |
+
"loss": 0.2395,
|
| 65 |
+
"num_input_tokens_seen": 3398362,
|
| 66 |
+
"step": 3000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.07,
|
| 70 |
+
"grad_norm": 1.624157428741455,
|
| 71 |
+
"learning_rate": 4.6500000000000005e-05,
|
| 72 |
+
"loss": 0.2372,
|
| 73 |
+
"num_input_tokens_seen": 3976908,
|
| 74 |
+
"step": 3500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.08,
|
| 78 |
+
"grad_norm": 1.1766471862792969,
|
| 79 |
+
"learning_rate": 4.600000000000001e-05,
|
| 80 |
+
"loss": 0.2333,
|
| 81 |
+
"num_input_tokens_seen": 4534622,
|
| 82 |
+
"step": 4000
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.09,
|
| 86 |
+
"grad_norm": 1.0758516788482666,
|
| 87 |
+
"learning_rate": 4.55e-05,
|
| 88 |
+
"loss": 0.2244,
|
| 89 |
+
"num_input_tokens_seen": 5111014,
|
| 90 |
+
"step": 4500
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.1,
|
| 94 |
+
"grad_norm": 2.210937261581421,
|
| 95 |
+
"learning_rate": 4.5e-05,
|
| 96 |
+
"loss": 0.231,
|
| 97 |
+
"num_input_tokens_seen": 5702148,
|
| 98 |
+
"step": 5000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.1,
|
| 102 |
+
"eval_loss": 0.16534267365932465,
|
| 103 |
+
"eval_runtime": 44.9542,
|
| 104 |
+
"eval_samples_per_second": 55.612,
|
| 105 |
+
"eval_steps_per_second": 6.963,
|
| 106 |
+
"num_input_tokens_seen": 5702148,
|
| 107 |
+
"step": 5000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.11,
|
| 111 |
+
"grad_norm": 1.975110411643982,
|
| 112 |
+
"learning_rate": 4.4500000000000004e-05,
|
| 113 |
+
"loss": 0.2232,
|
| 114 |
+
"num_input_tokens_seen": 6276610,
|
| 115 |
+
"step": 5500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.12,
|
| 119 |
+
"grad_norm": 2.1255569458007812,
|
| 120 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 121 |
+
"loss": 0.2184,
|
| 122 |
+
"num_input_tokens_seen": 6847280,
|
| 123 |
+
"step": 6000
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.13,
|
| 127 |
+
"grad_norm": 1.8061076402664185,
|
| 128 |
+
"learning_rate": 4.35e-05,
|
| 129 |
+
"loss": 0.216,
|
| 130 |
+
"num_input_tokens_seen": 7406418,
|
| 131 |
+
"step": 6500
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.14,
|
| 135 |
+
"grad_norm": 1.6190805435180664,
|
| 136 |
+
"learning_rate": 4.3e-05,
|
| 137 |
+
"loss": 0.2346,
|
| 138 |
+
"num_input_tokens_seen": 7976560,
|
| 139 |
+
"step": 7000
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 0.15,
|
| 143 |
+
"grad_norm": 0.7121838331222534,
|
| 144 |
+
"learning_rate": 4.25e-05,
|
| 145 |
+
"loss": 0.2163,
|
| 146 |
+
"num_input_tokens_seen": 8531178,
|
| 147 |
+
"step": 7500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.15,
|
| 151 |
+
"eval_loss": 0.15705962479114532,
|
| 152 |
+
"eval_runtime": 45.3915,
|
| 153 |
+
"eval_samples_per_second": 55.076,
|
| 154 |
+
"eval_steps_per_second": 6.896,
|
| 155 |
+
"num_input_tokens_seen": 8531178,
|
| 156 |
+
"step": 7500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.16,
|
| 160 |
+
"grad_norm": 1.3726420402526855,
|
| 161 |
+
"learning_rate": 4.2e-05,
|
| 162 |
+
"loss": 0.213,
|
| 163 |
+
"num_input_tokens_seen": 9096822,
|
| 164 |
+
"step": 8000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.17,
|
| 168 |
+
"grad_norm": 1.3163851499557495,
|
| 169 |
+
"learning_rate": 4.15e-05,
|
| 170 |
+
"loss": 0.2152,
|
| 171 |
+
"num_input_tokens_seen": 9655322,
|
| 172 |
+
"step": 8500
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.18,
|
| 176 |
+
"grad_norm": 0.5095873475074768,
|
| 177 |
+
"learning_rate": 4.1e-05,
|
| 178 |
+
"loss": 0.2151,
|
| 179 |
+
"num_input_tokens_seen": 10222666,
|
| 180 |
+
"step": 9000
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.19,
|
| 184 |
+
"grad_norm": 1.6344404220581055,
|
| 185 |
+
"learning_rate": 4.05e-05,
|
| 186 |
+
"loss": 0.2097,
|
| 187 |
+
"num_input_tokens_seen": 10783398,
|
| 188 |
+
"step": 9500
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.2,
|
| 192 |
+
"grad_norm": 0.9461726546287537,
|
| 193 |
+
"learning_rate": 4e-05,
|
| 194 |
+
"loss": 0.1966,
|
| 195 |
+
"num_input_tokens_seen": 11350902,
|
| 196 |
+
"step": 10000
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.2,
|
| 200 |
+
"eval_loss": 0.1528666764497757,
|
| 201 |
+
"eval_runtime": 45.1903,
|
| 202 |
+
"eval_samples_per_second": 55.322,
|
| 203 |
+
"eval_steps_per_second": 6.926,
|
| 204 |
+
"num_input_tokens_seen": 11350902,
|
| 205 |
+
"step": 10000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.21,
|
| 209 |
+
"grad_norm": 0.5499858260154724,
|
| 210 |
+
"learning_rate": 3.9500000000000005e-05,
|
| 211 |
+
"loss": 0.202,
|
| 212 |
+
"num_input_tokens_seen": 11937536,
|
| 213 |
+
"step": 10500
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.22,
|
| 217 |
+
"grad_norm": 0.9817250967025757,
|
| 218 |
+
"learning_rate": 3.9000000000000006e-05,
|
| 219 |
+
"loss": 0.2055,
|
| 220 |
+
"num_input_tokens_seen": 12530266,
|
| 221 |
+
"step": 11000
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.23,
|
| 225 |
+
"grad_norm": 1.1686115264892578,
|
| 226 |
+
"learning_rate": 3.85e-05,
|
| 227 |
+
"loss": 0.2045,
|
| 228 |
+
"num_input_tokens_seen": 13084430,
|
| 229 |
+
"step": 11500
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.24,
|
| 233 |
+
"grad_norm": 0.8986425399780273,
|
| 234 |
+
"learning_rate": 3.8e-05,
|
| 235 |
+
"loss": 0.2005,
|
| 236 |
+
"num_input_tokens_seen": 13645732,
|
| 237 |
+
"step": 12000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.25,
|
| 241 |
+
"grad_norm": 1.1480282545089722,
|
| 242 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 243 |
+
"loss": 0.2013,
|
| 244 |
+
"num_input_tokens_seen": 14191502,
|
| 245 |
+
"step": 12500
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.25,
|
| 249 |
+
"eval_loss": 0.14906854927539825,
|
| 250 |
+
"eval_runtime": 47.8025,
|
| 251 |
+
"eval_samples_per_second": 52.299,
|
| 252 |
+
"eval_steps_per_second": 6.548,
|
| 253 |
+
"num_input_tokens_seen": 14191502,
|
| 254 |
+
"step": 12500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.26,
|
| 258 |
+
"grad_norm": 0.8384343981742859,
|
| 259 |
+
"learning_rate": 3.7e-05,
|
| 260 |
+
"loss": 0.2027,
|
| 261 |
+
"num_input_tokens_seen": 14784072,
|
| 262 |
+
"step": 13000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.27,
|
| 266 |
+
"grad_norm": 1.3071606159210205,
|
| 267 |
+
"learning_rate": 3.65e-05,
|
| 268 |
+
"loss": 0.2068,
|
| 269 |
+
"num_input_tokens_seen": 15336696,
|
| 270 |
+
"step": 13500
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.28,
|
| 274 |
+
"grad_norm": 0.5159173011779785,
|
| 275 |
+
"learning_rate": 3.6e-05,
|
| 276 |
+
"loss": 0.2093,
|
| 277 |
+
"num_input_tokens_seen": 15914526,
|
| 278 |
+
"step": 14000
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.29,
|
| 282 |
+
"grad_norm": 1.51547110080719,
|
| 283 |
+
"learning_rate": 3.55e-05,
|
| 284 |
+
"loss": 0.1908,
|
| 285 |
+
"num_input_tokens_seen": 16486110,
|
| 286 |
+
"step": 14500
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.3,
|
| 290 |
+
"grad_norm": 0.7921791076660156,
|
| 291 |
+
"learning_rate": 3.5e-05,
|
| 292 |
+
"loss": 0.1971,
|
| 293 |
+
"num_input_tokens_seen": 17050704,
|
| 294 |
+
"step": 15000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.3,
|
| 298 |
+
"eval_loss": 0.14638836681842804,
|
| 299 |
+
"eval_runtime": 46.342,
|
| 300 |
+
"eval_samples_per_second": 53.947,
|
| 301 |
+
"eval_steps_per_second": 6.754,
|
| 302 |
+
"num_input_tokens_seen": 17050704,
|
| 303 |
+
"step": 15000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.31,
|
| 307 |
+
"grad_norm": 0.5466729402542114,
|
| 308 |
+
"learning_rate": 3.45e-05,
|
| 309 |
+
"loss": 0.1948,
|
| 310 |
+
"num_input_tokens_seen": 17650510,
|
| 311 |
+
"step": 15500
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.32,
|
| 315 |
+
"grad_norm": 0.6244600415229797,
|
| 316 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 317 |
+
"loss": 0.1863,
|
| 318 |
+
"num_input_tokens_seen": 18201474,
|
| 319 |
+
"step": 16000
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 0.33,
|
| 323 |
+
"grad_norm": 1.0302484035491943,
|
| 324 |
+
"learning_rate": 3.35e-05,
|
| 325 |
+
"loss": 0.185,
|
| 326 |
+
"num_input_tokens_seen": 18734382,
|
| 327 |
+
"step": 16500
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.34,
|
| 331 |
+
"grad_norm": 0.45665842294692993,
|
| 332 |
+
"learning_rate": 3.3e-05,
|
| 333 |
+
"loss": 0.1883,
|
| 334 |
+
"num_input_tokens_seen": 19293596,
|
| 335 |
+
"step": 17000
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.35,
|
| 339 |
+
"grad_norm": 0.8066365122795105,
|
| 340 |
+
"learning_rate": 3.2500000000000004e-05,
|
| 341 |
+
"loss": 0.1791,
|
| 342 |
+
"num_input_tokens_seen": 19857804,
|
| 343 |
+
"step": 17500
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 0.35,
|
| 347 |
+
"eval_loss": 0.14467556774616241,
|
| 348 |
+
"eval_runtime": 45.168,
|
| 349 |
+
"eval_samples_per_second": 55.349,
|
| 350 |
+
"eval_steps_per_second": 6.93,
|
| 351 |
+
"num_input_tokens_seen": 19857804,
|
| 352 |
+
"step": 17500
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.36,
|
| 356 |
+
"grad_norm": 6.650664329528809,
|
| 357 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 358 |
+
"loss": 0.1929,
|
| 359 |
+
"num_input_tokens_seen": 20418316,
|
| 360 |
+
"step": 18000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.37,
|
| 364 |
+
"grad_norm": 0.9265847206115723,
|
| 365 |
+
"learning_rate": 3.15e-05,
|
| 366 |
+
"loss": 0.1864,
|
| 367 |
+
"num_input_tokens_seen": 20975738,
|
| 368 |
+
"step": 18500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.38,
|
| 372 |
+
"grad_norm": 0.9065707921981812,
|
| 373 |
+
"learning_rate": 3.1e-05,
|
| 374 |
+
"loss": 0.1783,
|
| 375 |
+
"num_input_tokens_seen": 21552842,
|
| 376 |
+
"step": 19000
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.39,
|
| 380 |
+
"grad_norm": 1.3064478635787964,
|
| 381 |
+
"learning_rate": 3.05e-05,
|
| 382 |
+
"loss": 0.1849,
|
| 383 |
+
"num_input_tokens_seen": 22115314,
|
| 384 |
+
"step": 19500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.4,
|
| 388 |
+
"grad_norm": 0.7317535281181335,
|
| 389 |
+
"learning_rate": 3e-05,
|
| 390 |
+
"loss": 0.193,
|
| 391 |
+
"num_input_tokens_seen": 22687180,
|
| 392 |
+
"step": 20000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.4,
|
| 396 |
+
"eval_loss": 0.14237256348133087,
|
| 397 |
+
"eval_runtime": 46.1002,
|
| 398 |
+
"eval_samples_per_second": 54.23,
|
| 399 |
+
"eval_steps_per_second": 6.79,
|
| 400 |
+
"num_input_tokens_seen": 22687180,
|
| 401 |
+
"step": 20000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.41,
|
| 405 |
+
"grad_norm": 1.0536916255950928,
|
| 406 |
+
"learning_rate": 2.95e-05,
|
| 407 |
+
"loss": 0.1875,
|
| 408 |
+
"num_input_tokens_seen": 23265246,
|
| 409 |
+
"step": 20500
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.42,
|
| 413 |
+
"grad_norm": 0.7591565847396851,
|
| 414 |
+
"learning_rate": 2.9e-05,
|
| 415 |
+
"loss": 0.1775,
|
| 416 |
+
"num_input_tokens_seen": 23837722,
|
| 417 |
+
"step": 21000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.43,
|
| 421 |
+
"grad_norm": 0.7889916300773621,
|
| 422 |
+
"learning_rate": 2.8499999999999998e-05,
|
| 423 |
+
"loss": 0.1833,
|
| 424 |
+
"num_input_tokens_seen": 24407840,
|
| 425 |
+
"step": 21500
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.44,
|
| 429 |
+
"grad_norm": 2.9207775592803955,
|
| 430 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 431 |
+
"loss": 0.1901,
|
| 432 |
+
"num_input_tokens_seen": 24987106,
|
| 433 |
+
"step": 22000
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 0.45,
|
| 437 |
+
"grad_norm": 0.3993462026119232,
|
| 438 |
+
"learning_rate": 2.7500000000000004e-05,
|
| 439 |
+
"loss": 0.1821,
|
| 440 |
+
"num_input_tokens_seen": 25532518,
|
| 441 |
+
"step": 22500
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.45,
|
| 445 |
+
"eval_loss": 0.14162951707839966,
|
| 446 |
+
"eval_runtime": 45.1335,
|
| 447 |
+
"eval_samples_per_second": 55.391,
|
| 448 |
+
"eval_steps_per_second": 6.935,
|
| 449 |
+
"num_input_tokens_seen": 25532518,
|
| 450 |
+
"step": 22500
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.46,
|
| 454 |
+
"grad_norm": 1.0471628904342651,
|
| 455 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 456 |
+
"loss": 0.1898,
|
| 457 |
+
"num_input_tokens_seen": 26101602,
|
| 458 |
+
"step": 23000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.47,
|
| 462 |
+
"grad_norm": 0.4212801158428192,
|
| 463 |
+
"learning_rate": 2.6500000000000004e-05,
|
| 464 |
+
"loss": 0.177,
|
| 465 |
+
"num_input_tokens_seen": 26700486,
|
| 466 |
+
"step": 23500
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.48,
|
| 470 |
+
"grad_norm": 1.0187805891036987,
|
| 471 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 472 |
+
"loss": 0.1932,
|
| 473 |
+
"num_input_tokens_seen": 27290876,
|
| 474 |
+
"step": 24000
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.49,
|
| 478 |
+
"grad_norm": 0.48242756724357605,
|
| 479 |
+
"learning_rate": 2.5500000000000003e-05,
|
| 480 |
+
"loss": 0.1797,
|
| 481 |
+
"num_input_tokens_seen": 27851074,
|
| 482 |
+
"step": 24500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.5,
|
| 486 |
+
"grad_norm": 0.9889593720436096,
|
| 487 |
+
"learning_rate": 2.5e-05,
|
| 488 |
+
"loss": 0.19,
|
| 489 |
+
"num_input_tokens_seen": 28423408,
|
| 490 |
+
"step": 25000
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.5,
|
| 494 |
+
"eval_loss": 0.13971897959709167,
|
| 495 |
+
"eval_runtime": 45.1742,
|
| 496 |
+
"eval_samples_per_second": 55.341,
|
| 497 |
+
"eval_steps_per_second": 6.929,
|
| 498 |
+
"num_input_tokens_seen": 28423408,
|
| 499 |
+
"step": 25000
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.51,
|
| 503 |
+
"grad_norm": 0.6578853726387024,
|
| 504 |
+
"learning_rate": 2.45e-05,
|
| 505 |
+
"loss": 0.191,
|
| 506 |
+
"num_input_tokens_seen": 28986964,
|
| 507 |
+
"step": 25500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.52,
|
| 511 |
+
"grad_norm": 1.1678123474121094,
|
| 512 |
+
"learning_rate": 2.4e-05,
|
| 513 |
+
"loss": 0.1807,
|
| 514 |
+
"num_input_tokens_seen": 29555682,
|
| 515 |
+
"step": 26000
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.53,
|
| 519 |
+
"grad_norm": 0.3844729959964752,
|
| 520 |
+
"learning_rate": 2.35e-05,
|
| 521 |
+
"loss": 0.174,
|
| 522 |
+
"num_input_tokens_seen": 30106292,
|
| 523 |
+
"step": 26500
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 0.54,
|
| 527 |
+
"grad_norm": 1.3147269487380981,
|
| 528 |
+
"learning_rate": 2.3000000000000003e-05,
|
| 529 |
+
"loss": 0.184,
|
| 530 |
+
"num_input_tokens_seen": 30669702,
|
| 531 |
+
"step": 27000
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.55,
|
| 535 |
+
"grad_norm": 1.0336247682571411,
|
| 536 |
+
"learning_rate": 2.25e-05,
|
| 537 |
+
"loss": 0.1753,
|
| 538 |
+
"num_input_tokens_seen": 31248170,
|
| 539 |
+
"step": 27500
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.55,
|
| 543 |
+
"eval_loss": 0.13881850242614746,
|
| 544 |
+
"eval_runtime": 45.1907,
|
| 545 |
+
"eval_samples_per_second": 55.321,
|
| 546 |
+
"eval_steps_per_second": 6.926,
|
| 547 |
+
"num_input_tokens_seen": 31248170,
|
| 548 |
+
"step": 27500
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.56,
|
| 552 |
+
"grad_norm": 1.407716989517212,
|
| 553 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 554 |
+
"loss": 0.1725,
|
| 555 |
+
"num_input_tokens_seen": 31809958,
|
| 556 |
+
"step": 28000
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.57,
|
| 560 |
+
"grad_norm": 1.2787240743637085,
|
| 561 |
+
"learning_rate": 2.15e-05,
|
| 562 |
+
"loss": 0.1811,
|
| 563 |
+
"num_input_tokens_seen": 32366844,
|
| 564 |
+
"step": 28500
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.58,
|
| 568 |
+
"grad_norm": 0.9074501395225525,
|
| 569 |
+
"learning_rate": 2.1e-05,
|
| 570 |
+
"loss": 0.184,
|
| 571 |
+
"num_input_tokens_seen": 32913758,
|
| 572 |
+
"step": 29000
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.59,
|
| 576 |
+
"grad_norm": 0.5810595154762268,
|
| 577 |
+
"learning_rate": 2.05e-05,
|
| 578 |
+
"loss": 0.1754,
|
| 579 |
+
"num_input_tokens_seen": 33479540,
|
| 580 |
+
"step": 29500
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 0.6,
|
| 584 |
+
"grad_norm": 1.109554648399353,
|
| 585 |
+
"learning_rate": 2e-05,
|
| 586 |
+
"loss": 0.184,
|
| 587 |
+
"num_input_tokens_seen": 34048604,
|
| 588 |
+
"step": 30000
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 0.6,
|
| 592 |
+
"eval_loss": 0.13782289624214172,
|
| 593 |
+
"eval_runtime": 45.1441,
|
| 594 |
+
"eval_samples_per_second": 55.378,
|
| 595 |
+
"eval_steps_per_second": 6.933,
|
| 596 |
+
"num_input_tokens_seen": 34048604,
|
| 597 |
+
"step": 30000
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.61,
|
| 601 |
+
"grad_norm": 1.1160213947296143,
|
| 602 |
+
"learning_rate": 1.9500000000000003e-05,
|
| 603 |
+
"loss": 0.1674,
|
| 604 |
+
"num_input_tokens_seen": 34606292,
|
| 605 |
+
"step": 30500
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.62,
|
| 609 |
+
"grad_norm": 1.3033101558685303,
|
| 610 |
+
"learning_rate": 1.9e-05,
|
| 611 |
+
"loss": 0.1817,
|
| 612 |
+
"num_input_tokens_seen": 35171758,
|
| 613 |
+
"step": 31000
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.63,
|
| 617 |
+
"grad_norm": 0.44109177589416504,
|
| 618 |
+
"learning_rate": 1.85e-05,
|
| 619 |
+
"loss": 0.1854,
|
| 620 |
+
"num_input_tokens_seen": 35716556,
|
| 621 |
+
"step": 31500
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.64,
|
| 625 |
+
"grad_norm": 0.6188114285469055,
|
| 626 |
+
"learning_rate": 1.8e-05,
|
| 627 |
+
"loss": 0.1793,
|
| 628 |
+
"num_input_tokens_seen": 36298888,
|
| 629 |
+
"step": 32000
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 0.65,
|
| 633 |
+
"grad_norm": 0.612743079662323,
|
| 634 |
+
"learning_rate": 1.75e-05,
|
| 635 |
+
"loss": 0.1717,
|
| 636 |
+
"num_input_tokens_seen": 36903282,
|
| 637 |
+
"step": 32500
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 0.65,
|
| 641 |
+
"eval_loss": 0.13706056773662567,
|
| 642 |
+
"eval_runtime": 45.1443,
|
| 643 |
+
"eval_samples_per_second": 55.378,
|
| 644 |
+
"eval_steps_per_second": 6.933,
|
| 645 |
+
"num_input_tokens_seen": 36903282,
|
| 646 |
+
"step": 32500
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.66,
|
| 650 |
+
"grad_norm": 1.1475753784179688,
|
| 651 |
+
"learning_rate": 1.7000000000000003e-05,
|
| 652 |
+
"loss": 0.1814,
|
| 653 |
+
"num_input_tokens_seen": 37471044,
|
| 654 |
+
"step": 33000
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.67,
|
| 658 |
+
"grad_norm": 0.7694216966629028,
|
| 659 |
+
"learning_rate": 1.65e-05,
|
| 660 |
+
"loss": 0.1813,
|
| 661 |
+
"num_input_tokens_seen": 38025842,
|
| 662 |
+
"step": 33500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.68,
|
| 666 |
+
"grad_norm": 0.7751884460449219,
|
| 667 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 668 |
+
"loss": 0.1753,
|
| 669 |
+
"num_input_tokens_seen": 38565964,
|
| 670 |
+
"step": 34000
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 0.69,
|
| 674 |
+
"grad_norm": 1.2093932628631592,
|
| 675 |
+
"learning_rate": 1.55e-05,
|
| 676 |
+
"loss": 0.1752,
|
| 677 |
+
"num_input_tokens_seen": 39144446,
|
| 678 |
+
"step": 34500
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 0.7,
|
| 682 |
+
"grad_norm": 0.6265527009963989,
|
| 683 |
+
"learning_rate": 1.5e-05,
|
| 684 |
+
"loss": 0.1693,
|
| 685 |
+
"num_input_tokens_seen": 39709784,
|
| 686 |
+
"step": 35000
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.7,
|
| 690 |
+
"eval_loss": 0.1358744204044342,
|
| 691 |
+
"eval_runtime": 45.1674,
|
| 692 |
+
"eval_samples_per_second": 55.35,
|
| 693 |
+
"eval_steps_per_second": 6.93,
|
| 694 |
+
"num_input_tokens_seen": 39709784,
|
| 695 |
+
"step": 35000
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.71,
|
| 699 |
+
"grad_norm": 0.8478279709815979,
|
| 700 |
+
"learning_rate": 1.45e-05,
|
| 701 |
+
"loss": 0.1765,
|
| 702 |
+
"num_input_tokens_seen": 40271324,
|
| 703 |
+
"step": 35500
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.72,
|
| 707 |
+
"grad_norm": 1.2263400554656982,
|
| 708 |
+
"learning_rate": 1.4000000000000001e-05,
|
| 709 |
+
"loss": 0.1813,
|
| 710 |
+
"num_input_tokens_seen": 40869346,
|
| 711 |
+
"step": 36000
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.73,
|
| 715 |
+
"grad_norm": 1.0012421607971191,
|
| 716 |
+
"learning_rate": 1.3500000000000001e-05,
|
| 717 |
+
"loss": 0.1843,
|
| 718 |
+
"num_input_tokens_seen": 41439134,
|
| 719 |
+
"step": 36500
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.74,
|
| 723 |
+
"grad_norm": 3.3730311393737793,
|
| 724 |
+
"learning_rate": 1.3000000000000001e-05,
|
| 725 |
+
"loss": 0.1788,
|
| 726 |
+
"num_input_tokens_seen": 42021868,
|
| 727 |
+
"step": 37000
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.75,
|
| 731 |
+
"grad_norm": 0.48923859000205994,
|
| 732 |
+
"learning_rate": 1.25e-05,
|
| 733 |
+
"loss": 0.1729,
|
| 734 |
+
"num_input_tokens_seen": 42614112,
|
| 735 |
+
"step": 37500
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.75,
|
| 739 |
+
"eval_loss": 0.13453309237957,
|
| 740 |
+
"eval_runtime": 45.1646,
|
| 741 |
+
"eval_samples_per_second": 55.353,
|
| 742 |
+
"eval_steps_per_second": 6.93,
|
| 743 |
+
"num_input_tokens_seen": 42614112,
|
| 744 |
+
"step": 37500
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.76,
|
| 748 |
+
"grad_norm": 0.5432136654853821,
|
| 749 |
+
"learning_rate": 1.2e-05,
|
| 750 |
+
"loss": 0.1763,
|
| 751 |
+
"num_input_tokens_seen": 43221016,
|
| 752 |
+
"step": 38000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.77,
|
| 756 |
+
"grad_norm": 1.0637930631637573,
|
| 757 |
+
"learning_rate": 1.1500000000000002e-05,
|
| 758 |
+
"loss": 0.1718,
|
| 759 |
+
"num_input_tokens_seen": 43792306,
|
| 760 |
+
"step": 38500
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.78,
|
| 764 |
+
"grad_norm": 1.766243577003479,
|
| 765 |
+
"learning_rate": 1.1000000000000001e-05,
|
| 766 |
+
"loss": 0.1639,
|
| 767 |
+
"num_input_tokens_seen": 44358230,
|
| 768 |
+
"step": 39000
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.79,
|
| 772 |
+
"grad_norm": 0.6301211714744568,
|
| 773 |
+
"learning_rate": 1.05e-05,
|
| 774 |
+
"loss": 0.1782,
|
| 775 |
+
"num_input_tokens_seen": 44912720,
|
| 776 |
+
"step": 39500
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.8,
|
| 780 |
+
"grad_norm": 3.600902557373047,
|
| 781 |
+
"learning_rate": 1e-05,
|
| 782 |
+
"loss": 0.1711,
|
| 783 |
+
"num_input_tokens_seen": 45471178,
|
| 784 |
+
"step": 40000
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 0.8,
|
| 788 |
+
"eval_loss": 0.1343887597322464,
|
| 789 |
+
"eval_runtime": 45.1761,
|
| 790 |
+
"eval_samples_per_second": 55.339,
|
| 791 |
+
"eval_steps_per_second": 6.928,
|
| 792 |
+
"num_input_tokens_seen": 45471178,
|
| 793 |
+
"step": 40000
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.81,
|
| 797 |
+
"grad_norm": 0.8937748670578003,
|
| 798 |
+
"learning_rate": 9.5e-06,
|
| 799 |
+
"loss": 0.1775,
|
| 800 |
+
"num_input_tokens_seen": 46048204,
|
| 801 |
+
"step": 40500
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.82,
|
| 805 |
+
"grad_norm": 0.3030432462692261,
|
| 806 |
+
"learning_rate": 9e-06,
|
| 807 |
+
"loss": 0.1681,
|
| 808 |
+
"num_input_tokens_seen": 46617836,
|
| 809 |
+
"step": 41000
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.83,
|
| 813 |
+
"grad_norm": 0.7168088555335999,
|
| 814 |
+
"learning_rate": 8.500000000000002e-06,
|
| 815 |
+
"loss": 0.1649,
|
| 816 |
+
"num_input_tokens_seen": 47193690,
|
| 817 |
+
"step": 41500
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.84,
|
| 821 |
+
"grad_norm": 1.0438125133514404,
|
| 822 |
+
"learning_rate": 8.000000000000001e-06,
|
| 823 |
+
"loss": 0.1745,
|
| 824 |
+
"num_input_tokens_seen": 47771028,
|
| 825 |
+
"step": 42000
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.85,
|
| 829 |
+
"grad_norm": 1.256290078163147,
|
| 830 |
+
"learning_rate": 7.5e-06,
|
| 831 |
+
"loss": 0.1735,
|
| 832 |
+
"num_input_tokens_seen": 48355942,
|
| 833 |
+
"step": 42500
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.85,
|
| 837 |
+
"eval_loss": 0.13401633501052856,
|
| 838 |
+
"eval_runtime": 45.2261,
|
| 839 |
+
"eval_samples_per_second": 55.278,
|
| 840 |
+
"eval_steps_per_second": 6.921,
|
| 841 |
+
"num_input_tokens_seen": 48355942,
|
| 842 |
+
"step": 42500
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.86,
|
| 846 |
+
"grad_norm": 0.8616393804550171,
|
| 847 |
+
"learning_rate": 7.000000000000001e-06,
|
| 848 |
+
"loss": 0.1721,
|
| 849 |
+
"num_input_tokens_seen": 48935198,
|
| 850 |
+
"step": 43000
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.87,
|
| 854 |
+
"grad_norm": 1.0820131301879883,
|
| 855 |
+
"learning_rate": 6.5000000000000004e-06,
|
| 856 |
+
"loss": 0.1729,
|
| 857 |
+
"num_input_tokens_seen": 49486184,
|
| 858 |
+
"step": 43500
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.88,
|
| 862 |
+
"grad_norm": 1.0676862001419067,
|
| 863 |
+
"learning_rate": 6e-06,
|
| 864 |
+
"loss": 0.174,
|
| 865 |
+
"num_input_tokens_seen": 50057436,
|
| 866 |
+
"step": 44000
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.89,
|
| 870 |
+
"grad_norm": 0.8204198479652405,
|
| 871 |
+
"learning_rate": 5.500000000000001e-06,
|
| 872 |
+
"loss": 0.1741,
|
| 873 |
+
"num_input_tokens_seen": 50627550,
|
| 874 |
+
"step": 44500
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 0.9,
|
| 878 |
+
"grad_norm": 0.747173011302948,
|
| 879 |
+
"learning_rate": 5e-06,
|
| 880 |
+
"loss": 0.1797,
|
| 881 |
+
"num_input_tokens_seen": 51187066,
|
| 882 |
+
"step": 45000
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.9,
|
| 886 |
+
"eval_loss": 0.13398794829845428,
|
| 887 |
+
"eval_runtime": 45.1424,
|
| 888 |
+
"eval_samples_per_second": 55.38,
|
| 889 |
+
"eval_steps_per_second": 6.934,
|
| 890 |
+
"num_input_tokens_seen": 51187066,
|
| 891 |
+
"step": 45000
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.91,
|
| 895 |
+
"grad_norm": 1.2061275243759155,
|
| 896 |
+
"learning_rate": 4.5e-06,
|
| 897 |
+
"loss": 0.1744,
|
| 898 |
+
"num_input_tokens_seen": 51768826,
|
| 899 |
+
"step": 45500
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.92,
|
| 903 |
+
"grad_norm": 0.8262666463851929,
|
| 904 |
+
"learning_rate": 4.000000000000001e-06,
|
| 905 |
+
"loss": 0.1681,
|
| 906 |
+
"num_input_tokens_seen": 52332322,
|
| 907 |
+
"step": 46000
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 0.93,
|
| 911 |
+
"grad_norm": 0.3594360649585724,
|
| 912 |
+
"learning_rate": 3.5000000000000004e-06,
|
| 913 |
+
"loss": 0.1653,
|
| 914 |
+
"num_input_tokens_seen": 52916462,
|
| 915 |
+
"step": 46500
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.94,
|
| 919 |
+
"grad_norm": 0.3951094448566437,
|
| 920 |
+
"learning_rate": 3e-06,
|
| 921 |
+
"loss": 0.1584,
|
| 922 |
+
"num_input_tokens_seen": 53487326,
|
| 923 |
+
"step": 47000
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 0.95,
|
| 927 |
+
"grad_norm": 1.0189286470413208,
|
| 928 |
+
"learning_rate": 2.5e-06,
|
| 929 |
+
"loss": 0.1659,
|
| 930 |
+
"num_input_tokens_seen": 54074434,
|
| 931 |
+
"step": 47500
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 0.95,
|
| 935 |
+
"eval_loss": 0.13384351134300232,
|
| 936 |
+
"eval_runtime": 45.2087,
|
| 937 |
+
"eval_samples_per_second": 55.299,
|
| 938 |
+
"eval_steps_per_second": 6.923,
|
| 939 |
+
"num_input_tokens_seen": 54074434,
|
| 940 |
+
"step": 47500
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.96,
|
| 944 |
+
"grad_norm": 1.1751518249511719,
|
| 945 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 946 |
+
"loss": 0.1664,
|
| 947 |
+
"num_input_tokens_seen": 54651492,
|
| 948 |
+
"step": 48000
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.97,
|
| 952 |
+
"grad_norm": 0.47343894839286804,
|
| 953 |
+
"learning_rate": 1.5e-06,
|
| 954 |
+
"loss": 0.172,
|
| 955 |
+
"num_input_tokens_seen": 55223994,
|
| 956 |
+
"step": 48500
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 0.98,
|
| 960 |
+
"grad_norm": 0.70182865858078,
|
| 961 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 962 |
+
"loss": 0.175,
|
| 963 |
+
"num_input_tokens_seen": 55785026,
|
| 964 |
+
"step": 49000
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.99,
|
| 968 |
+
"grad_norm": 0.8210330605506897,
|
| 969 |
+
"learning_rate": 5.000000000000001e-07,
|
| 970 |
+
"loss": 0.1706,
|
| 971 |
+
"num_input_tokens_seen": 56363982,
|
| 972 |
+
"step": 49500
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 1.0,
|
| 976 |
+
"grad_norm": 0.5335518717765808,
|
| 977 |
+
"learning_rate": 0.0,
|
| 978 |
+
"loss": 0.1658,
|
| 979 |
+
"num_input_tokens_seen": 56941616,
|
| 980 |
+
"step": 50000
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 1.0,
|
| 984 |
+
"eval_loss": 0.13376566767692566,
|
| 985 |
+
"eval_runtime": 45.1906,
|
| 986 |
+
"eval_samples_per_second": 55.321,
|
| 987 |
+
"eval_steps_per_second": 6.926,
|
| 988 |
+
"num_input_tokens_seen": 56941616,
|
| 989 |
+
"step": 50000
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 1.0,
|
| 993 |
+
"num_input_tokens_seen": 56941616,
|
| 994 |
+
"step": 50000,
|
| 995 |
+
"total_flos": 2.067540416810189e+16,
|
| 996 |
+
"train_loss": 0.19179043090820314,
|
| 997 |
+
"train_runtime": 4730.669,
|
| 998 |
+
"train_samples_per_second": 21.139,
|
| 999 |
+
"train_steps_per_second": 10.569,
|
| 1000 |
+
"train_tokens_per_second": 12036.694
|
| 1001 |
+
}
|
| 1002 |
+
],
|
| 1003 |
+
"logging_steps": 500,
|
| 1004 |
+
"max_steps": 50000,
|
| 1005 |
+
"num_input_tokens_seen": 56941616,
|
| 1006 |
+
"num_train_epochs": 1,
|
| 1007 |
+
"save_steps": 2500,
|
| 1008 |
+
"stateful_callbacks": {
|
| 1009 |
+
"TrainerControl": {
|
| 1010 |
+
"args": {
|
| 1011 |
+
"should_epoch_stop": false,
|
| 1012 |
+
"should_evaluate": false,
|
| 1013 |
+
"should_log": false,
|
| 1014 |
+
"should_save": true,
|
| 1015 |
+
"should_training_stop": true
|
| 1016 |
+
},
|
| 1017 |
+
"attributes": {}
|
| 1018 |
+
}
|
| 1019 |
+
},
|
| 1020 |
+
"total_flos": 2.067540416810189e+16,
|
| 1021 |
+
"train_batch_size": 2,
|
| 1022 |
+
"trial_name": null,
|
| 1023 |
+
"trial_params": null
|
| 1024 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49389af45f75ca8c3177e9b0d50aa3b6ff26ba74e80e559bd1a0acee39ce53b3
|
| 3 |
+
size 5368
|