personal-info-redaction
Browse files- config.json +61 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +125 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +941 -0
- trainer_state.json +1623 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/content/drive/MyDrive/MODEL_CUSTOM",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 3072,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 768,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "relu",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "relu",
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": false,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "t5",
|
| 20 |
+
"n_positions": 512,
|
| 21 |
+
"num_decoder_layers": 12,
|
| 22 |
+
"num_heads": 12,
|
| 23 |
+
"num_layers": 12,
|
| 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 |
+
"torch_dtype": "float32",
|
| 58 |
+
"transformers_version": "4.41.2",
|
| 59 |
+
"use_cache": true,
|
| 60 |
+
"vocab_size": 32128
|
| 61 |
+
}
|
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": "4.41.2"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5afcfbae2cb5cf3182bb88f8dc8e3594e9d5c8f44a1fd3bbd60b9301f8bf01f4
|
| 3 |
+
size 891644712
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dabb61dda448eedbf5836bd58b09f23e78d5cce12b461637526f72db2ac82519
|
| 3 |
+
size 1783444794
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de3f37dce0da17968fb3a00416110763470946455b488bf1dcd630ad0c37ecb2
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb4d22a760904b590f9392ca147847ab7aae2768b6cb6b31adf29bc3631c0e87
|
| 3 |
+
size 1064
|
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 +1,941 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"max_length": 64,
|
| 934 |
+
"model_max_length": 1512,
|
| 935 |
+
"pad_token": "<pad>",
|
| 936 |
+
"stride": 0,
|
| 937 |
+
"tokenizer_class": "T5Tokenizer",
|
| 938 |
+
"truncation_side": "right",
|
| 939 |
+
"truncation_strategy": "longest_first",
|
| 940 |
+
"unk_token": "<unk>"
|
| 941 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1623 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.9801934740826255e-06,
|
| 3 |
+
"best_model_checkpoint": "Models/t5-base-class-gen/checkpoint-10400",
|
| 4 |
+
"epoch": 4.9440298507462686,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 10600,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04664179104477612,
|
| 13 |
+
"grad_norm": 1.2865939140319824,
|
| 14 |
+
"learning_rate": 3.9630597014925376e-05,
|
| 15 |
+
"loss": 0.437,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.04664179104477612,
|
| 20 |
+
"eval_loss": 0.020251411944627762,
|
| 21 |
+
"eval_runtime": 0.1587,
|
| 22 |
+
"eval_samples_per_second": 189.027,
|
| 23 |
+
"eval_steps_per_second": 25.204,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.09328358208955224,
|
| 28 |
+
"grad_norm": 0.69548100233078,
|
| 29 |
+
"learning_rate": 3.925746268656717e-05,
|
| 30 |
+
"loss": 0.0333,
|
| 31 |
+
"step": 200
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.09328358208955224,
|
| 35 |
+
"eval_loss": 0.0021759807132184505,
|
| 36 |
+
"eval_runtime": 0.1592,
|
| 37 |
+
"eval_samples_per_second": 188.446,
|
| 38 |
+
"eval_steps_per_second": 25.126,
|
| 39 |
+
"step": 200
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.13992537313432835,
|
| 43 |
+
"grad_norm": 0.07560934871435165,
|
| 44 |
+
"learning_rate": 3.888432835820896e-05,
|
| 45 |
+
"loss": 0.0203,
|
| 46 |
+
"step": 300
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.13992537313432835,
|
| 50 |
+
"eval_loss": 0.004563063848763704,
|
| 51 |
+
"eval_runtime": 0.1618,
|
| 52 |
+
"eval_samples_per_second": 185.371,
|
| 53 |
+
"eval_steps_per_second": 24.716,
|
| 54 |
+
"step": 300
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.1865671641791045,
|
| 58 |
+
"grad_norm": 0.646364688873291,
|
| 59 |
+
"learning_rate": 3.851119402985075e-05,
|
| 60 |
+
"loss": 0.0144,
|
| 61 |
+
"step": 400
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.1865671641791045,
|
| 65 |
+
"eval_loss": 0.00161658669821918,
|
| 66 |
+
"eval_runtime": 0.1567,
|
| 67 |
+
"eval_samples_per_second": 191.49,
|
| 68 |
+
"eval_steps_per_second": 25.532,
|
| 69 |
+
"step": 400
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.2332089552238806,
|
| 73 |
+
"grad_norm": 0.30101820826530457,
|
| 74 |
+
"learning_rate": 3.813805970149254e-05,
|
| 75 |
+
"loss": 0.0079,
|
| 76 |
+
"step": 500
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.2332089552238806,
|
| 80 |
+
"eval_loss": 0.0010551114100962877,
|
| 81 |
+
"eval_runtime": 0.1559,
|
| 82 |
+
"eval_samples_per_second": 192.377,
|
| 83 |
+
"eval_steps_per_second": 25.65,
|
| 84 |
+
"step": 500
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.2798507462686567,
|
| 88 |
+
"grad_norm": 0.5621537566184998,
|
| 89 |
+
"learning_rate": 3.7764925373134334e-05,
|
| 90 |
+
"loss": 0.0076,
|
| 91 |
+
"step": 600
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.2798507462686567,
|
| 95 |
+
"eval_loss": 0.0002234852290712297,
|
| 96 |
+
"eval_runtime": 0.1571,
|
| 97 |
+
"eval_samples_per_second": 191.018,
|
| 98 |
+
"eval_steps_per_second": 25.469,
|
| 99 |
+
"step": 600
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.32649253731343286,
|
| 103 |
+
"grad_norm": 0.10140960663557053,
|
| 104 |
+
"learning_rate": 3.7391791044776125e-05,
|
| 105 |
+
"loss": 0.0092,
|
| 106 |
+
"step": 700
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.32649253731343286,
|
| 110 |
+
"eval_loss": 0.00010653692879714072,
|
| 111 |
+
"eval_runtime": 0.1572,
|
| 112 |
+
"eval_samples_per_second": 190.855,
|
| 113 |
+
"eval_steps_per_second": 25.447,
|
| 114 |
+
"step": 700
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.373134328358209,
|
| 118 |
+
"grad_norm": 0.02672586776316166,
|
| 119 |
+
"learning_rate": 3.701865671641792e-05,
|
| 120 |
+
"loss": 0.0053,
|
| 121 |
+
"step": 800
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.373134328358209,
|
| 125 |
+
"eval_loss": 0.00011367371189408004,
|
| 126 |
+
"eval_runtime": 0.1569,
|
| 127 |
+
"eval_samples_per_second": 191.155,
|
| 128 |
+
"eval_steps_per_second": 25.487,
|
| 129 |
+
"step": 800
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.4197761194029851,
|
| 133 |
+
"grad_norm": 0.09280095249414444,
|
| 134 |
+
"learning_rate": 3.66455223880597e-05,
|
| 135 |
+
"loss": 0.0054,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.4197761194029851,
|
| 140 |
+
"eval_loss": 0.00013640630641020834,
|
| 141 |
+
"eval_runtime": 0.1588,
|
| 142 |
+
"eval_samples_per_second": 188.886,
|
| 143 |
+
"eval_steps_per_second": 25.185,
|
| 144 |
+
"step": 900
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.4664179104477612,
|
| 148 |
+
"grad_norm": 0.034318458288908005,
|
| 149 |
+
"learning_rate": 3.62723880597015e-05,
|
| 150 |
+
"loss": 0.0067,
|
| 151 |
+
"step": 1000
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.4664179104477612,
|
| 155 |
+
"eval_loss": 7.585491403006017e-05,
|
| 156 |
+
"eval_runtime": 0.1557,
|
| 157 |
+
"eval_samples_per_second": 192.664,
|
| 158 |
+
"eval_steps_per_second": 25.689,
|
| 159 |
+
"step": 1000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.5130597014925373,
|
| 163 |
+
"grad_norm": 0.018935877829790115,
|
| 164 |
+
"learning_rate": 3.5899253731343285e-05,
|
| 165 |
+
"loss": 0.0035,
|
| 166 |
+
"step": 1100
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.5130597014925373,
|
| 170 |
+
"eval_loss": 4.489553612074815e-05,
|
| 171 |
+
"eval_runtime": 0.1574,
|
| 172 |
+
"eval_samples_per_second": 190.631,
|
| 173 |
+
"eval_steps_per_second": 25.418,
|
| 174 |
+
"step": 1100
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.5597014925373134,
|
| 178 |
+
"grad_norm": 0.8913596868515015,
|
| 179 |
+
"learning_rate": 3.5526119402985077e-05,
|
| 180 |
+
"loss": 0.0056,
|
| 181 |
+
"step": 1200
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.5597014925373134,
|
| 185 |
+
"eval_loss": 4.118124343222007e-05,
|
| 186 |
+
"eval_runtime": 0.1589,
|
| 187 |
+
"eval_samples_per_second": 188.831,
|
| 188 |
+
"eval_steps_per_second": 25.177,
|
| 189 |
+
"step": 1200
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.6063432835820896,
|
| 193 |
+
"grad_norm": 0.017305633053183556,
|
| 194 |
+
"learning_rate": 3.515298507462687e-05,
|
| 195 |
+
"loss": 0.0041,
|
| 196 |
+
"step": 1300
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.6063432835820896,
|
| 200 |
+
"eval_loss": 4.481070573092438e-05,
|
| 201 |
+
"eval_runtime": 0.1552,
|
| 202 |
+
"eval_samples_per_second": 193.329,
|
| 203 |
+
"eval_steps_per_second": 25.777,
|
| 204 |
+
"step": 1300
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.6529850746268657,
|
| 208 |
+
"grad_norm": 0.009413465857505798,
|
| 209 |
+
"learning_rate": 3.477985074626866e-05,
|
| 210 |
+
"loss": 0.0029,
|
| 211 |
+
"step": 1400
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.6529850746268657,
|
| 215 |
+
"eval_loss": 2.9594228180940263e-05,
|
| 216 |
+
"eval_runtime": 0.1654,
|
| 217 |
+
"eval_samples_per_second": 181.422,
|
| 218 |
+
"eval_steps_per_second": 24.19,
|
| 219 |
+
"step": 1400
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.6996268656716418,
|
| 223 |
+
"grad_norm": 0.004255557898432016,
|
| 224 |
+
"learning_rate": 3.440671641791045e-05,
|
| 225 |
+
"loss": 0.0028,
|
| 226 |
+
"step": 1500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.6996268656716418,
|
| 230 |
+
"eval_loss": 3.3944801543839276e-05,
|
| 231 |
+
"eval_runtime": 0.1543,
|
| 232 |
+
"eval_samples_per_second": 194.435,
|
| 233 |
+
"eval_steps_per_second": 25.925,
|
| 234 |
+
"step": 1500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.746268656716418,
|
| 238 |
+
"grad_norm": 0.6249216198921204,
|
| 239 |
+
"learning_rate": 3.403358208955224e-05,
|
| 240 |
+
"loss": 0.003,
|
| 241 |
+
"step": 1600
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.746268656716418,
|
| 245 |
+
"eval_loss": 3.595968155423179e-05,
|
| 246 |
+
"eval_runtime": 0.1621,
|
| 247 |
+
"eval_samples_per_second": 185.072,
|
| 248 |
+
"eval_steps_per_second": 24.676,
|
| 249 |
+
"step": 1600
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.792910447761194,
|
| 253 |
+
"grad_norm": 0.014389215037226677,
|
| 254 |
+
"learning_rate": 3.3660447761194034e-05,
|
| 255 |
+
"loss": 0.002,
|
| 256 |
+
"step": 1700
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.792910447761194,
|
| 260 |
+
"eval_loss": 3.822403959929943e-05,
|
| 261 |
+
"eval_runtime": 0.1593,
|
| 262 |
+
"eval_samples_per_second": 188.284,
|
| 263 |
+
"eval_steps_per_second": 25.105,
|
| 264 |
+
"step": 1700
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.8395522388059702,
|
| 268 |
+
"grad_norm": 0.1081342026591301,
|
| 269 |
+
"learning_rate": 3.328731343283582e-05,
|
| 270 |
+
"loss": 0.0039,
|
| 271 |
+
"step": 1800
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.8395522388059702,
|
| 275 |
+
"eval_loss": 3.7738984246971086e-05,
|
| 276 |
+
"eval_runtime": 0.1558,
|
| 277 |
+
"eval_samples_per_second": 192.583,
|
| 278 |
+
"eval_steps_per_second": 25.678,
|
| 279 |
+
"step": 1800
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.8861940298507462,
|
| 283 |
+
"grad_norm": 1.123632550239563,
|
| 284 |
+
"learning_rate": 3.291417910447762e-05,
|
| 285 |
+
"loss": 0.0035,
|
| 286 |
+
"step": 1900
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.8861940298507462,
|
| 290 |
+
"eval_loss": 2.4694763851584867e-05,
|
| 291 |
+
"eval_runtime": 0.157,
|
| 292 |
+
"eval_samples_per_second": 191.065,
|
| 293 |
+
"eval_steps_per_second": 25.475,
|
| 294 |
+
"step": 1900
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.9328358208955224,
|
| 298 |
+
"grad_norm": 0.00756313418969512,
|
| 299 |
+
"learning_rate": 3.25410447761194e-05,
|
| 300 |
+
"loss": 0.0027,
|
| 301 |
+
"step": 2000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.9328358208955224,
|
| 305 |
+
"eval_loss": 5.045727448305115e-05,
|
| 306 |
+
"eval_runtime": 0.1664,
|
| 307 |
+
"eval_samples_per_second": 180.272,
|
| 308 |
+
"eval_steps_per_second": 24.036,
|
| 309 |
+
"step": 2000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.9794776119402985,
|
| 313 |
+
"grad_norm": 0.0035852426663041115,
|
| 314 |
+
"learning_rate": 3.2167910447761194e-05,
|
| 315 |
+
"loss": 0.0026,
|
| 316 |
+
"step": 2100
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.9794776119402985,
|
| 320 |
+
"eval_loss": 2.137782212230377e-05,
|
| 321 |
+
"eval_runtime": 0.1552,
|
| 322 |
+
"eval_samples_per_second": 193.332,
|
| 323 |
+
"eval_steps_per_second": 25.778,
|
| 324 |
+
"step": 2100
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.0261194029850746,
|
| 328 |
+
"grad_norm": 0.01669035293161869,
|
| 329 |
+
"learning_rate": 3.1794776119402986e-05,
|
| 330 |
+
"loss": 0.0008,
|
| 331 |
+
"step": 2200
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.0261194029850746,
|
| 335 |
+
"eval_loss": 2.3261545720743015e-05,
|
| 336 |
+
"eval_runtime": 0.1554,
|
| 337 |
+
"eval_samples_per_second": 193.073,
|
| 338 |
+
"eval_steps_per_second": 25.743,
|
| 339 |
+
"step": 2200
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.0727611940298507,
|
| 343 |
+
"grad_norm": 0.002784071722999215,
|
| 344 |
+
"learning_rate": 3.142164179104478e-05,
|
| 345 |
+
"loss": 0.0016,
|
| 346 |
+
"step": 2300
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.0727611940298507,
|
| 350 |
+
"eval_loss": 1.877884460554924e-05,
|
| 351 |
+
"eval_runtime": 0.1597,
|
| 352 |
+
"eval_samples_per_second": 187.795,
|
| 353 |
+
"eval_steps_per_second": 25.039,
|
| 354 |
+
"step": 2300
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.1194029850746268,
|
| 358 |
+
"grad_norm": 0.010812056250870228,
|
| 359 |
+
"learning_rate": 3.104850746268657e-05,
|
| 360 |
+
"loss": 0.0013,
|
| 361 |
+
"step": 2400
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.1194029850746268,
|
| 365 |
+
"eval_loss": 2.032700831477996e-05,
|
| 366 |
+
"eval_runtime": 0.157,
|
| 367 |
+
"eval_samples_per_second": 191.1,
|
| 368 |
+
"eval_steps_per_second": 25.48,
|
| 369 |
+
"step": 2400
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.166044776119403,
|
| 373 |
+
"grad_norm": 0.08882497251033783,
|
| 374 |
+
"learning_rate": 3.067537313432836e-05,
|
| 375 |
+
"loss": 0.0023,
|
| 376 |
+
"step": 2500
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 1.166044776119403,
|
| 380 |
+
"eval_loss": 2.7997491997666657e-05,
|
| 381 |
+
"eval_runtime": 0.1583,
|
| 382 |
+
"eval_samples_per_second": 189.547,
|
| 383 |
+
"eval_steps_per_second": 25.273,
|
| 384 |
+
"step": 2500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.212686567164179,
|
| 388 |
+
"grad_norm": 0.5638116002082825,
|
| 389 |
+
"learning_rate": 3.030223880597015e-05,
|
| 390 |
+
"loss": 0.0014,
|
| 391 |
+
"step": 2600
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.212686567164179,
|
| 395 |
+
"eval_loss": 1.3365392987907398e-05,
|
| 396 |
+
"eval_runtime": 0.1568,
|
| 397 |
+
"eval_samples_per_second": 191.368,
|
| 398 |
+
"eval_steps_per_second": 25.516,
|
| 399 |
+
"step": 2600
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.2593283582089552,
|
| 403 |
+
"grad_norm": 0.6982096433639526,
|
| 404 |
+
"learning_rate": 2.9929104477611944e-05,
|
| 405 |
+
"loss": 0.0009,
|
| 406 |
+
"step": 2700
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.2593283582089552,
|
| 410 |
+
"eval_loss": 1.1131261089758482e-05,
|
| 411 |
+
"eval_runtime": 0.1571,
|
| 412 |
+
"eval_samples_per_second": 191.001,
|
| 413 |
+
"eval_steps_per_second": 25.467,
|
| 414 |
+
"step": 2700
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.3059701492537314,
|
| 418 |
+
"grad_norm": 0.2126922756433487,
|
| 419 |
+
"learning_rate": 2.9555970149253732e-05,
|
| 420 |
+
"loss": 0.0007,
|
| 421 |
+
"step": 2800
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 1.3059701492537314,
|
| 425 |
+
"eval_loss": 1.0051960998680443e-05,
|
| 426 |
+
"eval_runtime": 0.1557,
|
| 427 |
+
"eval_samples_per_second": 192.64,
|
| 428 |
+
"eval_steps_per_second": 25.685,
|
| 429 |
+
"step": 2800
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.3526119402985075,
|
| 433 |
+
"grad_norm": 0.07693888247013092,
|
| 434 |
+
"learning_rate": 2.9182835820895527e-05,
|
| 435 |
+
"loss": 0.0011,
|
| 436 |
+
"step": 2900
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.3526119402985075,
|
| 440 |
+
"eval_loss": 8.506859558110591e-06,
|
| 441 |
+
"eval_runtime": 0.1606,
|
| 442 |
+
"eval_samples_per_second": 186.795,
|
| 443 |
+
"eval_steps_per_second": 24.906,
|
| 444 |
+
"step": 2900
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.3992537313432836,
|
| 448 |
+
"grad_norm": 0.005555067211389542,
|
| 449 |
+
"learning_rate": 2.8809701492537315e-05,
|
| 450 |
+
"loss": 0.0012,
|
| 451 |
+
"step": 3000
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.3992537313432836,
|
| 455 |
+
"eval_loss": 1.0461569218023214e-05,
|
| 456 |
+
"eval_runtime": 0.1562,
|
| 457 |
+
"eval_samples_per_second": 192.09,
|
| 458 |
+
"eval_steps_per_second": 25.612,
|
| 459 |
+
"step": 3000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.4458955223880596,
|
| 463 |
+
"grad_norm": 0.15883490443229675,
|
| 464 |
+
"learning_rate": 2.8436567164179106e-05,
|
| 465 |
+
"loss": 0.0015,
|
| 466 |
+
"step": 3100
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.4458955223880596,
|
| 470 |
+
"eval_loss": 9.19290141609963e-06,
|
| 471 |
+
"eval_runtime": 0.1574,
|
| 472 |
+
"eval_samples_per_second": 190.61,
|
| 473 |
+
"eval_steps_per_second": 25.415,
|
| 474 |
+
"step": 3100
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.4925373134328357,
|
| 478 |
+
"grad_norm": 0.0036452861968427896,
|
| 479 |
+
"learning_rate": 2.806716417910448e-05,
|
| 480 |
+
"loss": 0.0017,
|
| 481 |
+
"step": 3200
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 1.4925373134328357,
|
| 485 |
+
"eval_loss": 7.644109246029984e-06,
|
| 486 |
+
"eval_runtime": 0.1573,
|
| 487 |
+
"eval_samples_per_second": 190.724,
|
| 488 |
+
"eval_steps_per_second": 25.43,
|
| 489 |
+
"step": 3200
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.539179104477612,
|
| 493 |
+
"grad_norm": 0.1588873416185379,
|
| 494 |
+
"learning_rate": 2.769402985074627e-05,
|
| 495 |
+
"loss": 0.0009,
|
| 496 |
+
"step": 3300
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 1.539179104477612,
|
| 500 |
+
"eval_loss": 9.155748557532206e-06,
|
| 501 |
+
"eval_runtime": 0.1602,
|
| 502 |
+
"eval_samples_per_second": 187.322,
|
| 503 |
+
"eval_steps_per_second": 24.976,
|
| 504 |
+
"step": 3300
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.585820895522388,
|
| 508 |
+
"grad_norm": 0.004792116116732359,
|
| 509 |
+
"learning_rate": 2.7320895522388062e-05,
|
| 510 |
+
"loss": 0.0018,
|
| 511 |
+
"step": 3400
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 1.585820895522388,
|
| 515 |
+
"eval_loss": 8.091868039628025e-06,
|
| 516 |
+
"eval_runtime": 0.1578,
|
| 517 |
+
"eval_samples_per_second": 190.11,
|
| 518 |
+
"eval_steps_per_second": 25.348,
|
| 519 |
+
"step": 3400
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.6324626865671643,
|
| 523 |
+
"grad_norm": 2.761561870574951,
|
| 524 |
+
"learning_rate": 2.694776119402985e-05,
|
| 525 |
+
"loss": 0.0011,
|
| 526 |
+
"step": 3500
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 1.6324626865671643,
|
| 530 |
+
"eval_loss": 8.603728929301724e-06,
|
| 531 |
+
"eval_runtime": 0.1552,
|
| 532 |
+
"eval_samples_per_second": 193.265,
|
| 533 |
+
"eval_steps_per_second": 25.769,
|
| 534 |
+
"step": 3500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.6791044776119404,
|
| 538 |
+
"grad_norm": 0.001969451317563653,
|
| 539 |
+
"learning_rate": 2.6574626865671645e-05,
|
| 540 |
+
"loss": 0.0012,
|
| 541 |
+
"step": 3600
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.6791044776119404,
|
| 545 |
+
"eval_loss": 8.435232302872464e-06,
|
| 546 |
+
"eval_runtime": 0.1553,
|
| 547 |
+
"eval_samples_per_second": 193.184,
|
| 548 |
+
"eval_steps_per_second": 25.758,
|
| 549 |
+
"step": 3600
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.7257462686567164,
|
| 553 |
+
"grad_norm": 0.005350825376808643,
|
| 554 |
+
"learning_rate": 2.6201492537313434e-05,
|
| 555 |
+
"loss": 0.0008,
|
| 556 |
+
"step": 3700
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.7257462686567164,
|
| 560 |
+
"eval_loss": 7.432493021042319e-06,
|
| 561 |
+
"eval_runtime": 0.1563,
|
| 562 |
+
"eval_samples_per_second": 191.964,
|
| 563 |
+
"eval_steps_per_second": 25.595,
|
| 564 |
+
"step": 3700
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 1.7723880597014925,
|
| 568 |
+
"grad_norm": 0.004110433626919985,
|
| 569 |
+
"learning_rate": 2.5828358208955225e-05,
|
| 570 |
+
"loss": 0.0014,
|
| 571 |
+
"step": 3800
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 1.7723880597014925,
|
| 575 |
+
"eval_loss": 7.303169240913121e-06,
|
| 576 |
+
"eval_runtime": 0.1569,
|
| 577 |
+
"eval_samples_per_second": 191.177,
|
| 578 |
+
"eval_steps_per_second": 25.49,
|
| 579 |
+
"step": 3800
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 1.8190298507462686,
|
| 583 |
+
"grad_norm": 0.0039463951252400875,
|
| 584 |
+
"learning_rate": 2.5455223880597017e-05,
|
| 585 |
+
"loss": 0.0015,
|
| 586 |
+
"step": 3900
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 1.8190298507462686,
|
| 590 |
+
"eval_loss": 9.76303817878943e-06,
|
| 591 |
+
"eval_runtime": 0.1571,
|
| 592 |
+
"eval_samples_per_second": 190.973,
|
| 593 |
+
"eval_steps_per_second": 25.463,
|
| 594 |
+
"step": 3900
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.8656716417910446,
|
| 598 |
+
"grad_norm": 0.004805909004062414,
|
| 599 |
+
"learning_rate": 2.508208955223881e-05,
|
| 600 |
+
"loss": 0.0012,
|
| 601 |
+
"step": 4000
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 1.8656716417910446,
|
| 605 |
+
"eval_loss": 8.14036320662126e-06,
|
| 606 |
+
"eval_runtime": 0.157,
|
| 607 |
+
"eval_samples_per_second": 191.027,
|
| 608 |
+
"eval_steps_per_second": 25.47,
|
| 609 |
+
"step": 4000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.912313432835821,
|
| 613 |
+
"grad_norm": 0.0031389566138386726,
|
| 614 |
+
"learning_rate": 2.4708955223880597e-05,
|
| 615 |
+
"loss": 0.0004,
|
| 616 |
+
"step": 4100
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 1.912313432835821,
|
| 620 |
+
"eval_loss": 6.821030183346011e-06,
|
| 621 |
+
"eval_runtime": 0.1614,
|
| 622 |
+
"eval_samples_per_second": 185.9,
|
| 623 |
+
"eval_steps_per_second": 24.787,
|
| 624 |
+
"step": 4100
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 1.9589552238805972,
|
| 628 |
+
"grad_norm": 0.0017104181461036205,
|
| 629 |
+
"learning_rate": 2.433582089552239e-05,
|
| 630 |
+
"loss": 0.0008,
|
| 631 |
+
"step": 4200
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 1.9589552238805972,
|
| 635 |
+
"eval_loss": 7.834916686988436e-06,
|
| 636 |
+
"eval_runtime": 0.1615,
|
| 637 |
+
"eval_samples_per_second": 185.757,
|
| 638 |
+
"eval_steps_per_second": 24.768,
|
| 639 |
+
"step": 4200
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 2.0055970149253732,
|
| 643 |
+
"grad_norm": 0.013449718244373798,
|
| 644 |
+
"learning_rate": 2.396268656716418e-05,
|
| 645 |
+
"loss": 0.001,
|
| 646 |
+
"step": 4300
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 2.0055970149253732,
|
| 650 |
+
"eval_loss": 7.582441867270973e-06,
|
| 651 |
+
"eval_runtime": 0.1686,
|
| 652 |
+
"eval_samples_per_second": 177.913,
|
| 653 |
+
"eval_steps_per_second": 23.722,
|
| 654 |
+
"step": 4300
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 2.0522388059701493,
|
| 658 |
+
"grad_norm": 0.0017907052533701062,
|
| 659 |
+
"learning_rate": 2.358955223880597e-05,
|
| 660 |
+
"loss": 0.0007,
|
| 661 |
+
"step": 4400
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 2.0522388059701493,
|
| 665 |
+
"eval_loss": 6.949214366613887e-06,
|
| 666 |
+
"eval_runtime": 0.1537,
|
| 667 |
+
"eval_samples_per_second": 195.234,
|
| 668 |
+
"eval_steps_per_second": 26.031,
|
| 669 |
+
"step": 4400
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.0988805970149254,
|
| 673 |
+
"grad_norm": 0.001830141874961555,
|
| 674 |
+
"learning_rate": 2.3216417910447763e-05,
|
| 675 |
+
"loss": 0.0004,
|
| 676 |
+
"step": 4500
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.0988805970149254,
|
| 680 |
+
"eval_loss": 7.074564564391039e-06,
|
| 681 |
+
"eval_runtime": 0.1577,
|
| 682 |
+
"eval_samples_per_second": 190.227,
|
| 683 |
+
"eval_steps_per_second": 25.364,
|
| 684 |
+
"step": 4500
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 2.1455223880597014,
|
| 688 |
+
"grad_norm": 0.0030846677254885435,
|
| 689 |
+
"learning_rate": 2.2843283582089555e-05,
|
| 690 |
+
"loss": 0.0006,
|
| 691 |
+
"step": 4600
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 2.1455223880597014,
|
| 695 |
+
"eval_loss": 6.291250883805333e-06,
|
| 696 |
+
"eval_runtime": 0.1566,
|
| 697 |
+
"eval_samples_per_second": 191.563,
|
| 698 |
+
"eval_steps_per_second": 25.542,
|
| 699 |
+
"step": 4600
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 2.1921641791044775,
|
| 703 |
+
"grad_norm": 0.24780245125293732,
|
| 704 |
+
"learning_rate": 2.2470149253731343e-05,
|
| 705 |
+
"loss": 0.0003,
|
| 706 |
+
"step": 4700
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 2.1921641791044775,
|
| 710 |
+
"eval_loss": 6.1347077462414745e-06,
|
| 711 |
+
"eval_runtime": 0.1575,
|
| 712 |
+
"eval_samples_per_second": 190.525,
|
| 713 |
+
"eval_steps_per_second": 25.403,
|
| 714 |
+
"step": 4700
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 2.2388059701492535,
|
| 718 |
+
"grad_norm": 0.006296923384070396,
|
| 719 |
+
"learning_rate": 2.2097014925373138e-05,
|
| 720 |
+
"loss": 0.0003,
|
| 721 |
+
"step": 4800
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 2.2388059701492535,
|
| 725 |
+
"eval_loss": 5.517637873708736e-06,
|
| 726 |
+
"eval_runtime": 0.1579,
|
| 727 |
+
"eval_samples_per_second": 189.97,
|
| 728 |
+
"eval_steps_per_second": 25.329,
|
| 729 |
+
"step": 4800
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 2.28544776119403,
|
| 733 |
+
"grad_norm": 0.0017776070162653923,
|
| 734 |
+
"learning_rate": 2.1723880597014926e-05,
|
| 735 |
+
"loss": 0.0007,
|
| 736 |
+
"step": 4900
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 2.28544776119403,
|
| 740 |
+
"eval_loss": 5.534998763323529e-06,
|
| 741 |
+
"eval_runtime": 0.158,
|
| 742 |
+
"eval_samples_per_second": 189.867,
|
| 743 |
+
"eval_steps_per_second": 25.316,
|
| 744 |
+
"step": 4900
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 2.332089552238806,
|
| 748 |
+
"grad_norm": 0.0026376782916486263,
|
| 749 |
+
"learning_rate": 2.1350746268656717e-05,
|
| 750 |
+
"loss": 0.0004,
|
| 751 |
+
"step": 5000
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 2.332089552238806,
|
| 755 |
+
"eval_loss": 5.3646053856937215e-06,
|
| 756 |
+
"eval_runtime": 0.158,
|
| 757 |
+
"eval_samples_per_second": 189.825,
|
| 758 |
+
"eval_steps_per_second": 25.31,
|
| 759 |
+
"step": 5000
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 2.378731343283582,
|
| 763 |
+
"grad_norm": 0.008729691617190838,
|
| 764 |
+
"learning_rate": 2.097761194029851e-05,
|
| 765 |
+
"loss": 0.0009,
|
| 766 |
+
"step": 5100
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 2.378731343283582,
|
| 770 |
+
"eval_loss": 5.699926987290382e-06,
|
| 771 |
+
"eval_runtime": 0.1586,
|
| 772 |
+
"eval_samples_per_second": 189.183,
|
| 773 |
+
"eval_steps_per_second": 25.224,
|
| 774 |
+
"step": 5100
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 2.425373134328358,
|
| 778 |
+
"grad_norm": 0.0009663441451266408,
|
| 779 |
+
"learning_rate": 2.06044776119403e-05,
|
| 780 |
+
"loss": 0.0002,
|
| 781 |
+
"step": 5200
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 2.425373134328358,
|
| 785 |
+
"eval_loss": 5.018339379603276e-06,
|
| 786 |
+
"eval_runtime": 0.1609,
|
| 787 |
+
"eval_samples_per_second": 186.434,
|
| 788 |
+
"eval_steps_per_second": 24.858,
|
| 789 |
+
"step": 5200
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 2.4720149253731343,
|
| 793 |
+
"grad_norm": 0.0009370720363222063,
|
| 794 |
+
"learning_rate": 2.023134328358209e-05,
|
| 795 |
+
"loss": 0.0003,
|
| 796 |
+
"step": 5300
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 2.4720149253731343,
|
| 800 |
+
"eval_loss": 4.319118488638196e-06,
|
| 801 |
+
"eval_runtime": 0.1594,
|
| 802 |
+
"eval_samples_per_second": 188.258,
|
| 803 |
+
"eval_steps_per_second": 25.101,
|
| 804 |
+
"step": 5300
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 2.5186567164179103,
|
| 808 |
+
"grad_norm": 0.00313656241632998,
|
| 809 |
+
"learning_rate": 1.9858208955223884e-05,
|
| 810 |
+
"loss": 0.0008,
|
| 811 |
+
"step": 5400
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 2.5186567164179103,
|
| 815 |
+
"eval_loss": 4.456574970390648e-06,
|
| 816 |
+
"eval_runtime": 0.1551,
|
| 817 |
+
"eval_samples_per_second": 193.476,
|
| 818 |
+
"eval_steps_per_second": 25.797,
|
| 819 |
+
"step": 5400
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 2.5652985074626864,
|
| 823 |
+
"grad_norm": 0.0011074623325839639,
|
| 824 |
+
"learning_rate": 1.9485074626865675e-05,
|
| 825 |
+
"loss": 0.001,
|
| 826 |
+
"step": 5500
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 2.5652985074626864,
|
| 830 |
+
"eval_loss": 3.924767952412367e-06,
|
| 831 |
+
"eval_runtime": 0.1544,
|
| 832 |
+
"eval_samples_per_second": 194.285,
|
| 833 |
+
"eval_steps_per_second": 25.905,
|
| 834 |
+
"step": 5500
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 2.611940298507463,
|
| 838 |
+
"grad_norm": 0.02510717324912548,
|
| 839 |
+
"learning_rate": 1.9111940298507467e-05,
|
| 840 |
+
"loss": 0.0003,
|
| 841 |
+
"step": 5600
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 2.611940298507463,
|
| 845 |
+
"eval_loss": 4.046037247462664e-06,
|
| 846 |
+
"eval_runtime": 0.1553,
|
| 847 |
+
"eval_samples_per_second": 193.136,
|
| 848 |
+
"eval_steps_per_second": 25.752,
|
| 849 |
+
"step": 5600
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 2.658582089552239,
|
| 853 |
+
"grad_norm": 0.023706955835223198,
|
| 854 |
+
"learning_rate": 1.8738805970149255e-05,
|
| 855 |
+
"loss": 0.0003,
|
| 856 |
+
"step": 5700
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 2.658582089552239,
|
| 860 |
+
"eval_loss": 4.111709131393582e-06,
|
| 861 |
+
"eval_runtime": 0.1558,
|
| 862 |
+
"eval_samples_per_second": 192.543,
|
| 863 |
+
"eval_steps_per_second": 25.672,
|
| 864 |
+
"step": 5700
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 2.705223880597015,
|
| 868 |
+
"grad_norm": 0.004163182340562344,
|
| 869 |
+
"learning_rate": 1.8365671641791047e-05,
|
| 870 |
+
"loss": 0.0006,
|
| 871 |
+
"step": 5800
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 2.705223880597015,
|
| 875 |
+
"eval_loss": 4.339735369285336e-06,
|
| 876 |
+
"eval_runtime": 0.1607,
|
| 877 |
+
"eval_samples_per_second": 186.695,
|
| 878 |
+
"eval_steps_per_second": 24.893,
|
| 879 |
+
"step": 5800
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 2.751865671641791,
|
| 883 |
+
"grad_norm": 0.002963052364066243,
|
| 884 |
+
"learning_rate": 1.7992537313432835e-05,
|
| 885 |
+
"loss": 0.0005,
|
| 886 |
+
"step": 5900
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 2.751865671641791,
|
| 890 |
+
"eval_loss": 3.9786968955013435e-06,
|
| 891 |
+
"eval_runtime": 0.1575,
|
| 892 |
+
"eval_samples_per_second": 190.477,
|
| 893 |
+
"eval_steps_per_second": 25.397,
|
| 894 |
+
"step": 5900
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 2.798507462686567,
|
| 898 |
+
"grad_norm": 0.045626550912857056,
|
| 899 |
+
"learning_rate": 1.7619402985074627e-05,
|
| 900 |
+
"loss": 0.0008,
|
| 901 |
+
"step": 6000
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 2.798507462686567,
|
| 905 |
+
"eval_loss": 4.052158146805596e-06,
|
| 906 |
+
"eval_runtime": 0.1579,
|
| 907 |
+
"eval_samples_per_second": 189.965,
|
| 908 |
+
"eval_steps_per_second": 25.329,
|
| 909 |
+
"step": 6000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 2.845149253731343,
|
| 913 |
+
"grad_norm": 0.008129669353365898,
|
| 914 |
+
"learning_rate": 1.7246268656716418e-05,
|
| 915 |
+
"loss": 0.0004,
|
| 916 |
+
"step": 6100
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 2.845149253731343,
|
| 920 |
+
"eval_loss": 4.024254849355202e-06,
|
| 921 |
+
"eval_runtime": 0.158,
|
| 922 |
+
"eval_samples_per_second": 189.912,
|
| 923 |
+
"eval_steps_per_second": 25.322,
|
| 924 |
+
"step": 6100
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 2.8917910447761193,
|
| 928 |
+
"grad_norm": 0.002264247043058276,
|
| 929 |
+
"learning_rate": 1.687313432835821e-05,
|
| 930 |
+
"loss": 0.0007,
|
| 931 |
+
"step": 6200
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 2.8917910447761193,
|
| 935 |
+
"eval_loss": 3.7680488276237156e-06,
|
| 936 |
+
"eval_runtime": 0.1559,
|
| 937 |
+
"eval_samples_per_second": 192.455,
|
| 938 |
+
"eval_steps_per_second": 25.661,
|
| 939 |
+
"step": 6200
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 2.9384328358208958,
|
| 943 |
+
"grad_norm": 0.013498159125447273,
|
| 944 |
+
"learning_rate": 1.65e-05,
|
| 945 |
+
"loss": 0.0002,
|
| 946 |
+
"step": 6300
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 2.9384328358208958,
|
| 950 |
+
"eval_loss": 3.534241386660142e-06,
|
| 951 |
+
"eval_runtime": 0.1562,
|
| 952 |
+
"eval_samples_per_second": 192.066,
|
| 953 |
+
"eval_steps_per_second": 25.609,
|
| 954 |
+
"step": 6300
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 2.9850746268656714,
|
| 958 |
+
"grad_norm": 0.000992327812127769,
|
| 959 |
+
"learning_rate": 1.6126865671641793e-05,
|
| 960 |
+
"loss": 0.0009,
|
| 961 |
+
"step": 6400
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 2.9850746268656714,
|
| 965 |
+
"eval_loss": 3.539219051162945e-06,
|
| 966 |
+
"eval_runtime": 0.1581,
|
| 967 |
+
"eval_samples_per_second": 189.704,
|
| 968 |
+
"eval_steps_per_second": 25.294,
|
| 969 |
+
"step": 6400
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 3.031716417910448,
|
| 973 |
+
"grad_norm": 0.002681414596736431,
|
| 974 |
+
"learning_rate": 1.575373134328358e-05,
|
| 975 |
+
"loss": 0.0003,
|
| 976 |
+
"step": 6500
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 3.031716417910448,
|
| 980 |
+
"eval_loss": 3.239377292629797e-06,
|
| 981 |
+
"eval_runtime": 0.1572,
|
| 982 |
+
"eval_samples_per_second": 190.818,
|
| 983 |
+
"eval_steps_per_second": 25.442,
|
| 984 |
+
"step": 6500
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 3.078358208955224,
|
| 988 |
+
"grad_norm": 0.06693683564662933,
|
| 989 |
+
"learning_rate": 1.5380597014925373e-05,
|
| 990 |
+
"loss": 0.0003,
|
| 991 |
+
"step": 6600
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 3.078358208955224,
|
| 995 |
+
"eval_loss": 3.1195118026516866e-06,
|
| 996 |
+
"eval_runtime": 0.1554,
|
| 997 |
+
"eval_samples_per_second": 192.996,
|
| 998 |
+
"eval_steps_per_second": 25.733,
|
| 999 |
+
"step": 6600
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 3.125,
|
| 1003 |
+
"grad_norm": 0.007976911030709743,
|
| 1004 |
+
"learning_rate": 1.5007462686567164e-05,
|
| 1005 |
+
"loss": 0.0002,
|
| 1006 |
+
"step": 6700
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 3.125,
|
| 1010 |
+
"eval_loss": 3.158217623422388e-06,
|
| 1011 |
+
"eval_runtime": 0.1613,
|
| 1012 |
+
"eval_samples_per_second": 186.004,
|
| 1013 |
+
"eval_steps_per_second": 24.801,
|
| 1014 |
+
"step": 6700
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 3.171641791044776,
|
| 1018 |
+
"grad_norm": 0.0018902523443102837,
|
| 1019 |
+
"learning_rate": 1.4634328358208956e-05,
|
| 1020 |
+
"loss": 0.0002,
|
| 1021 |
+
"step": 6800
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 3.171641791044776,
|
| 1025 |
+
"eval_loss": 3.020254553121049e-06,
|
| 1026 |
+
"eval_runtime": 0.1619,
|
| 1027 |
+
"eval_samples_per_second": 185.322,
|
| 1028 |
+
"eval_steps_per_second": 24.71,
|
| 1029 |
+
"step": 6800
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 3.218283582089552,
|
| 1033 |
+
"grad_norm": 0.0031356920953840017,
|
| 1034 |
+
"learning_rate": 1.4261194029850747e-05,
|
| 1035 |
+
"loss": 0.0002,
|
| 1036 |
+
"step": 6900
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 3.218283582089552,
|
| 1040 |
+
"eval_loss": 2.9624054604937555e-06,
|
| 1041 |
+
"eval_runtime": 0.1556,
|
| 1042 |
+
"eval_samples_per_second": 192.812,
|
| 1043 |
+
"eval_steps_per_second": 25.708,
|
| 1044 |
+
"step": 6900
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 3.264925373134328,
|
| 1048 |
+
"grad_norm": 0.005576052237302065,
|
| 1049 |
+
"learning_rate": 1.3888059701492537e-05,
|
| 1050 |
+
"loss": 0.0005,
|
| 1051 |
+
"step": 7000
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 3.264925373134328,
|
| 1055 |
+
"eval_loss": 2.9549014470831025e-06,
|
| 1056 |
+
"eval_runtime": 0.1578,
|
| 1057 |
+
"eval_samples_per_second": 190.15,
|
| 1058 |
+
"eval_steps_per_second": 25.353,
|
| 1059 |
+
"step": 7000
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 3.3115671641791042,
|
| 1063 |
+
"grad_norm": 0.0018602815689519048,
|
| 1064 |
+
"learning_rate": 1.3514925373134329e-05,
|
| 1065 |
+
"loss": 0.0002,
|
| 1066 |
+
"step": 7100
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 3.3115671641791042,
|
| 1070 |
+
"eval_loss": 2.8336680770735256e-06,
|
| 1071 |
+
"eval_runtime": 0.1552,
|
| 1072 |
+
"eval_samples_per_second": 193.246,
|
| 1073 |
+
"eval_steps_per_second": 25.766,
|
| 1074 |
+
"step": 7100
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 3.3582089552238807,
|
| 1078 |
+
"grad_norm": 0.002030579838901758,
|
| 1079 |
+
"learning_rate": 1.314179104477612e-05,
|
| 1080 |
+
"loss": 0.0003,
|
| 1081 |
+
"step": 7200
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 3.3582089552238807,
|
| 1085 |
+
"eval_loss": 2.7239029805059545e-06,
|
| 1086 |
+
"eval_runtime": 0.1624,
|
| 1087 |
+
"eval_samples_per_second": 184.688,
|
| 1088 |
+
"eval_steps_per_second": 24.625,
|
| 1089 |
+
"step": 7200
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 3.404850746268657,
|
| 1093 |
+
"grad_norm": 0.027261830866336823,
|
| 1094 |
+
"learning_rate": 1.276865671641791e-05,
|
| 1095 |
+
"loss": 0.0003,
|
| 1096 |
+
"step": 7300
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 3.404850746268657,
|
| 1100 |
+
"eval_loss": 2.706149643927347e-06,
|
| 1101 |
+
"eval_runtime": 0.1586,
|
| 1102 |
+
"eval_samples_per_second": 189.213,
|
| 1103 |
+
"eval_steps_per_second": 25.228,
|
| 1104 |
+
"step": 7300
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 3.451492537313433,
|
| 1108 |
+
"grad_norm": 0.005287382751703262,
|
| 1109 |
+
"learning_rate": 1.2395522388059702e-05,
|
| 1110 |
+
"loss": 0.0002,
|
| 1111 |
+
"step": 7400
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 3.451492537313433,
|
| 1115 |
+
"eval_loss": 2.5531167011649814e-06,
|
| 1116 |
+
"eval_runtime": 0.1543,
|
| 1117 |
+
"eval_samples_per_second": 194.469,
|
| 1118 |
+
"eval_steps_per_second": 25.929,
|
| 1119 |
+
"step": 7400
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 3.498134328358209,
|
| 1123 |
+
"grad_norm": 0.0021771446336060762,
|
| 1124 |
+
"learning_rate": 1.2022388059701493e-05,
|
| 1125 |
+
"loss": 0.0003,
|
| 1126 |
+
"step": 7500
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 3.498134328358209,
|
| 1130 |
+
"eval_loss": 2.8221681986906333e-06,
|
| 1131 |
+
"eval_runtime": 0.1601,
|
| 1132 |
+
"eval_samples_per_second": 187.36,
|
| 1133 |
+
"eval_steps_per_second": 24.981,
|
| 1134 |
+
"step": 7500
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 3.544776119402985,
|
| 1138 |
+
"grad_norm": 0.0027294817846268415,
|
| 1139 |
+
"learning_rate": 1.1649253731343283e-05,
|
| 1140 |
+
"loss": 0.0003,
|
| 1141 |
+
"step": 7600
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 3.544776119402985,
|
| 1145 |
+
"eval_loss": 2.784717707982054e-06,
|
| 1146 |
+
"eval_runtime": 0.1555,
|
| 1147 |
+
"eval_samples_per_second": 192.876,
|
| 1148 |
+
"eval_steps_per_second": 25.717,
|
| 1149 |
+
"step": 7600
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 3.591417910447761,
|
| 1153 |
+
"grad_norm": 0.0013641875702887774,
|
| 1154 |
+
"learning_rate": 1.1276119402985075e-05,
|
| 1155 |
+
"loss": 0.0003,
|
| 1156 |
+
"step": 7700
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 3.591417910447761,
|
| 1160 |
+
"eval_loss": 2.9222812827356393e-06,
|
| 1161 |
+
"eval_runtime": 0.1639,
|
| 1162 |
+
"eval_samples_per_second": 183.034,
|
| 1163 |
+
"eval_steps_per_second": 24.405,
|
| 1164 |
+
"step": 7700
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 3.638059701492537,
|
| 1168 |
+
"grad_norm": 0.08378789573907852,
|
| 1169 |
+
"learning_rate": 1.0902985074626867e-05,
|
| 1170 |
+
"loss": 0.0002,
|
| 1171 |
+
"step": 7800
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 3.638059701492537,
|
| 1175 |
+
"eval_loss": 2.9144475774955936e-06,
|
| 1176 |
+
"eval_runtime": 0.1585,
|
| 1177 |
+
"eval_samples_per_second": 189.266,
|
| 1178 |
+
"eval_steps_per_second": 25.235,
|
| 1179 |
+
"step": 7800
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 3.6847014925373136,
|
| 1183 |
+
"grad_norm": 0.004190696403384209,
|
| 1184 |
+
"learning_rate": 1.0529850746268656e-05,
|
| 1185 |
+
"loss": 0.0002,
|
| 1186 |
+
"step": 7900
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 3.6847014925373136,
|
| 1190 |
+
"eval_loss": 2.752276259343489e-06,
|
| 1191 |
+
"eval_runtime": 0.1641,
|
| 1192 |
+
"eval_samples_per_second": 182.838,
|
| 1193 |
+
"eval_steps_per_second": 24.378,
|
| 1194 |
+
"step": 7900
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 3.7313432835820897,
|
| 1198 |
+
"grad_norm": 0.0028494582511484623,
|
| 1199 |
+
"learning_rate": 1.0156716417910448e-05,
|
| 1200 |
+
"loss": 0.0005,
|
| 1201 |
+
"step": 8000
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 3.7313432835820897,
|
| 1205 |
+
"eval_loss": 2.7154821964359144e-06,
|
| 1206 |
+
"eval_runtime": 0.1578,
|
| 1207 |
+
"eval_samples_per_second": 190.11,
|
| 1208 |
+
"eval_steps_per_second": 25.348,
|
| 1209 |
+
"step": 8000
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 3.7779850746268657,
|
| 1213 |
+
"grad_norm": 0.03807828575372696,
|
| 1214 |
+
"learning_rate": 9.787313432835822e-06,
|
| 1215 |
+
"loss": 0.0006,
|
| 1216 |
+
"step": 8100
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 3.7779850746268657,
|
| 1220 |
+
"eval_loss": 2.827802290994441e-06,
|
| 1221 |
+
"eval_runtime": 0.1552,
|
| 1222 |
+
"eval_samples_per_second": 193.25,
|
| 1223 |
+
"eval_steps_per_second": 25.767,
|
| 1224 |
+
"step": 8100
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 3.824626865671642,
|
| 1228 |
+
"grad_norm": 0.5222908854484558,
|
| 1229 |
+
"learning_rate": 9.414179104477614e-06,
|
| 1230 |
+
"loss": 0.0002,
|
| 1231 |
+
"step": 8200
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 3.824626865671642,
|
| 1235 |
+
"eval_loss": 2.7299265639157966e-06,
|
| 1236 |
+
"eval_runtime": 0.156,
|
| 1237 |
+
"eval_samples_per_second": 192.29,
|
| 1238 |
+
"eval_steps_per_second": 25.639,
|
| 1239 |
+
"step": 8200
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 3.871268656716418,
|
| 1243 |
+
"grad_norm": 0.0023298938758671284,
|
| 1244 |
+
"learning_rate": 9.041044776119404e-06,
|
| 1245 |
+
"loss": 0.0002,
|
| 1246 |
+
"step": 8300
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 3.871268656716418,
|
| 1250 |
+
"eval_loss": 2.6636719212547177e-06,
|
| 1251 |
+
"eval_runtime": 0.1552,
|
| 1252 |
+
"eval_samples_per_second": 193.302,
|
| 1253 |
+
"eval_steps_per_second": 25.774,
|
| 1254 |
+
"step": 8300
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 3.917910447761194,
|
| 1258 |
+
"grad_norm": 0.05465957522392273,
|
| 1259 |
+
"learning_rate": 8.667910447761195e-06,
|
| 1260 |
+
"loss": 0.0005,
|
| 1261 |
+
"step": 8400
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 3.917910447761194,
|
| 1265 |
+
"eval_loss": 2.582373781478964e-06,
|
| 1266 |
+
"eval_runtime": 0.1571,
|
| 1267 |
+
"eval_samples_per_second": 190.991,
|
| 1268 |
+
"eval_steps_per_second": 25.465,
|
| 1269 |
+
"step": 8400
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 3.96455223880597,
|
| 1273 |
+
"grad_norm": 0.048116568475961685,
|
| 1274 |
+
"learning_rate": 8.294776119402985e-06,
|
| 1275 |
+
"loss": 0.0002,
|
| 1276 |
+
"step": 8500
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 3.96455223880597,
|
| 1280 |
+
"eval_loss": 2.487162873876514e-06,
|
| 1281 |
+
"eval_runtime": 0.1645,
|
| 1282 |
+
"eval_samples_per_second": 182.375,
|
| 1283 |
+
"eval_steps_per_second": 24.317,
|
| 1284 |
+
"step": 8500
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 4.0111940298507465,
|
| 1288 |
+
"grad_norm": 0.0024153583217412233,
|
| 1289 |
+
"learning_rate": 7.921641791044777e-06,
|
| 1290 |
+
"loss": 0.0001,
|
| 1291 |
+
"step": 8600
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 4.0111940298507465,
|
| 1295 |
+
"eval_loss": 2.429806954751257e-06,
|
| 1296 |
+
"eval_runtime": 0.182,
|
| 1297 |
+
"eval_samples_per_second": 164.853,
|
| 1298 |
+
"eval_steps_per_second": 21.98,
|
| 1299 |
+
"step": 8600
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 4.057835820895522,
|
| 1303 |
+
"grad_norm": 0.002540579764172435,
|
| 1304 |
+
"learning_rate": 7.548507462686568e-06,
|
| 1305 |
+
"loss": 0.0001,
|
| 1306 |
+
"step": 8700
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 4.057835820895522,
|
| 1310 |
+
"eval_loss": 2.3769621293467935e-06,
|
| 1311 |
+
"eval_runtime": 0.1595,
|
| 1312 |
+
"eval_samples_per_second": 188.114,
|
| 1313 |
+
"eval_steps_per_second": 25.082,
|
| 1314 |
+
"step": 8700
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 4.104477611940299,
|
| 1318 |
+
"grad_norm": 0.0042966934852302074,
|
| 1319 |
+
"learning_rate": 7.175373134328358e-06,
|
| 1320 |
+
"loss": 0.0002,
|
| 1321 |
+
"step": 8800
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 4.104477611940299,
|
| 1325 |
+
"eval_loss": 2.33703940466512e-06,
|
| 1326 |
+
"eval_runtime": 0.1575,
|
| 1327 |
+
"eval_samples_per_second": 190.469,
|
| 1328 |
+
"eval_steps_per_second": 25.396,
|
| 1329 |
+
"step": 8800
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 4.151119402985074,
|
| 1333 |
+
"grad_norm": 0.0006062475731596351,
|
| 1334 |
+
"learning_rate": 6.802238805970149e-06,
|
| 1335 |
+
"loss": 0.0004,
|
| 1336 |
+
"step": 8900
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 4.151119402985074,
|
| 1340 |
+
"eval_loss": 2.3632851480215322e-06,
|
| 1341 |
+
"eval_runtime": 0.1561,
|
| 1342 |
+
"eval_samples_per_second": 192.228,
|
| 1343 |
+
"eval_steps_per_second": 25.63,
|
| 1344 |
+
"step": 8900
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 4.197761194029851,
|
| 1348 |
+
"grad_norm": 0.009168209508061409,
|
| 1349 |
+
"learning_rate": 6.429104477611941e-06,
|
| 1350 |
+
"loss": 0.0002,
|
| 1351 |
+
"step": 9000
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 4.197761194029851,
|
| 1355 |
+
"eval_loss": 2.2578756215807516e-06,
|
| 1356 |
+
"eval_runtime": 0.1552,
|
| 1357 |
+
"eval_samples_per_second": 193.262,
|
| 1358 |
+
"eval_steps_per_second": 25.768,
|
| 1359 |
+
"step": 9000
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 4.244402985074627,
|
| 1363 |
+
"grad_norm": 0.002683964092284441,
|
| 1364 |
+
"learning_rate": 6.055970149253731e-06,
|
| 1365 |
+
"loss": 0.0001,
|
| 1366 |
+
"step": 9100
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 4.244402985074627,
|
| 1370 |
+
"eval_loss": 2.2409305984183447e-06,
|
| 1371 |
+
"eval_runtime": 0.1564,
|
| 1372 |
+
"eval_samples_per_second": 191.8,
|
| 1373 |
+
"eval_steps_per_second": 25.573,
|
| 1374 |
+
"step": 9100
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 4.291044776119403,
|
| 1378 |
+
"grad_norm": 0.0012024191673845053,
|
| 1379 |
+
"learning_rate": 5.682835820895522e-06,
|
| 1380 |
+
"loss": 0.0002,
|
| 1381 |
+
"step": 9200
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 4.291044776119403,
|
| 1385 |
+
"eval_loss": 2.202784344262909e-06,
|
| 1386 |
+
"eval_runtime": 0.1563,
|
| 1387 |
+
"eval_samples_per_second": 191.927,
|
| 1388 |
+
"eval_steps_per_second": 25.59,
|
| 1389 |
+
"step": 9200
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 4.337686567164179,
|
| 1393 |
+
"grad_norm": 0.003109121695160866,
|
| 1394 |
+
"learning_rate": 5.309701492537314e-06,
|
| 1395 |
+
"loss": 0.0002,
|
| 1396 |
+
"step": 9300
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 4.337686567164179,
|
| 1400 |
+
"eval_loss": 2.2312042347039096e-06,
|
| 1401 |
+
"eval_runtime": 0.1563,
|
| 1402 |
+
"eval_samples_per_second": 191.941,
|
| 1403 |
+
"eval_steps_per_second": 25.592,
|
| 1404 |
+
"step": 9300
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 4.384328358208955,
|
| 1408 |
+
"grad_norm": 0.0009185061790049076,
|
| 1409 |
+
"learning_rate": 4.9365671641791045e-06,
|
| 1410 |
+
"loss": 0.0002,
|
| 1411 |
+
"step": 9400
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 4.384328358208955,
|
| 1415 |
+
"eval_loss": 2.1759601622761693e-06,
|
| 1416 |
+
"eval_runtime": 0.159,
|
| 1417 |
+
"eval_samples_per_second": 188.695,
|
| 1418 |
+
"eval_steps_per_second": 25.159,
|
| 1419 |
+
"step": 9400
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 4.4309701492537314,
|
| 1423 |
+
"grad_norm": 0.0008011642494238913,
|
| 1424 |
+
"learning_rate": 4.563432835820896e-06,
|
| 1425 |
+
"loss": 0.0004,
|
| 1426 |
+
"step": 9500
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 4.4309701492537314,
|
| 1430 |
+
"eval_loss": 2.2056660782254767e-06,
|
| 1431 |
+
"eval_runtime": 0.1567,
|
| 1432 |
+
"eval_samples_per_second": 191.395,
|
| 1433 |
+
"eval_steps_per_second": 25.519,
|
| 1434 |
+
"step": 9500
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 4.477611940298507,
|
| 1438 |
+
"grad_norm": 0.001676097046583891,
|
| 1439 |
+
"learning_rate": 4.190298507462687e-06,
|
| 1440 |
+
"loss": 0.0001,
|
| 1441 |
+
"step": 9600
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 4.477611940298507,
|
| 1445 |
+
"eval_loss": 2.196997229475528e-06,
|
| 1446 |
+
"eval_runtime": 0.1554,
|
| 1447 |
+
"eval_samples_per_second": 193.034,
|
| 1448 |
+
"eval_steps_per_second": 25.738,
|
| 1449 |
+
"step": 9600
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 4.524253731343284,
|
| 1453 |
+
"grad_norm": 0.001348722493276,
|
| 1454 |
+
"learning_rate": 3.8171641791044775e-06,
|
| 1455 |
+
"loss": 0.0002,
|
| 1456 |
+
"step": 9700
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 4.524253731343284,
|
| 1460 |
+
"eval_loss": 2.159943960577948e-06,
|
| 1461 |
+
"eval_runtime": 0.1588,
|
| 1462 |
+
"eval_samples_per_second": 188.88,
|
| 1463 |
+
"eval_steps_per_second": 25.184,
|
| 1464 |
+
"step": 9700
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 4.57089552238806,
|
| 1468 |
+
"grad_norm": 0.002949994755908847,
|
| 1469 |
+
"learning_rate": 3.4440298507462687e-06,
|
| 1470 |
+
"loss": 0.0001,
|
| 1471 |
+
"step": 9800
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 4.57089552238806,
|
| 1475 |
+
"eval_loss": 2.117126769007882e-06,
|
| 1476 |
+
"eval_runtime": 0.1558,
|
| 1477 |
+
"eval_samples_per_second": 192.602,
|
| 1478 |
+
"eval_steps_per_second": 25.68,
|
| 1479 |
+
"step": 9800
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 4.617537313432836,
|
| 1483 |
+
"grad_norm": 0.005024689715355635,
|
| 1484 |
+
"learning_rate": 3.07089552238806e-06,
|
| 1485 |
+
"loss": 0.0001,
|
| 1486 |
+
"step": 9900
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 4.617537313432836,
|
| 1490 |
+
"eval_loss": 2.069621814371203e-06,
|
| 1491 |
+
"eval_runtime": 0.1558,
|
| 1492 |
+
"eval_samples_per_second": 192.576,
|
| 1493 |
+
"eval_steps_per_second": 25.677,
|
| 1494 |
+
"step": 9900
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 4.664179104477612,
|
| 1498 |
+
"grad_norm": 0.0006656211335211992,
|
| 1499 |
+
"learning_rate": 2.697761194029851e-06,
|
| 1500 |
+
"loss": 0.0004,
|
| 1501 |
+
"step": 10000
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 4.664179104477612,
|
| 1505 |
+
"eval_loss": 2.0410807337611914e-06,
|
| 1506 |
+
"eval_runtime": 0.1585,
|
| 1507 |
+
"eval_samples_per_second": 189.231,
|
| 1508 |
+
"eval_steps_per_second": 25.231,
|
| 1509 |
+
"step": 10000
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 4.710820895522388,
|
| 1513 |
+
"grad_norm": 0.0003097167646046728,
|
| 1514 |
+
"learning_rate": 2.324626865671642e-06,
|
| 1515 |
+
"loss": 0.0001,
|
| 1516 |
+
"step": 10100
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 4.710820895522388,
|
| 1520 |
+
"eval_loss": 2.0217082692397526e-06,
|
| 1521 |
+
"eval_runtime": 0.1557,
|
| 1522 |
+
"eval_samples_per_second": 192.62,
|
| 1523 |
+
"eval_steps_per_second": 25.683,
|
| 1524 |
+
"step": 10100
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 4.757462686567164,
|
| 1528 |
+
"grad_norm": 0.0007842735503800213,
|
| 1529 |
+
"learning_rate": 1.951492537313433e-06,
|
| 1530 |
+
"loss": 0.0001,
|
| 1531 |
+
"step": 10200
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 4.757462686567164,
|
| 1535 |
+
"eval_loss": 2.0089323697902728e-06,
|
| 1536 |
+
"eval_runtime": 0.174,
|
| 1537 |
+
"eval_samples_per_second": 172.426,
|
| 1538 |
+
"eval_steps_per_second": 22.99,
|
| 1539 |
+
"step": 10200
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 4.80410447761194,
|
| 1543 |
+
"grad_norm": 0.004456710536032915,
|
| 1544 |
+
"learning_rate": 1.578358208955224e-06,
|
| 1545 |
+
"loss": 0.0001,
|
| 1546 |
+
"step": 10300
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 4.80410447761194,
|
| 1550 |
+
"eval_loss": 2.0024342575197807e-06,
|
| 1551 |
+
"eval_runtime": 0.1647,
|
| 1552 |
+
"eval_samples_per_second": 182.154,
|
| 1553 |
+
"eval_steps_per_second": 24.287,
|
| 1554 |
+
"step": 10300
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 4.850746268656716,
|
| 1558 |
+
"grad_norm": 0.0003174096636939794,
|
| 1559 |
+
"learning_rate": 1.205223880597015e-06,
|
| 1560 |
+
"loss": 0.0001,
|
| 1561 |
+
"step": 10400
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 4.850746268656716,
|
| 1565 |
+
"eval_loss": 1.9801934740826255e-06,
|
| 1566 |
+
"eval_runtime": 0.1571,
|
| 1567 |
+
"eval_samples_per_second": 190.953,
|
| 1568 |
+
"eval_steps_per_second": 25.46,
|
| 1569 |
+
"step": 10400
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 4.897388059701493,
|
| 1573 |
+
"grad_norm": 0.013769041746854782,
|
| 1574 |
+
"learning_rate": 8.320895522388061e-07,
|
| 1575 |
+
"loss": 0.0001,
|
| 1576 |
+
"step": 10500
|
| 1577 |
+
},
|
| 1578 |
+
{
|
| 1579 |
+
"epoch": 4.897388059701493,
|
| 1580 |
+
"eval_loss": 1.9813883227470797e-06,
|
| 1581 |
+
"eval_runtime": 0.1598,
|
| 1582 |
+
"eval_samples_per_second": 187.736,
|
| 1583 |
+
"eval_steps_per_second": 25.031,
|
| 1584 |
+
"step": 10500
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 4.9440298507462686,
|
| 1588 |
+
"grad_norm": 0.0012828693725168705,
|
| 1589 |
+
"learning_rate": 4.5895522388059706e-07,
|
| 1590 |
+
"loss": 0.0002,
|
| 1591 |
+
"step": 10600
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 4.9440298507462686,
|
| 1595 |
+
"eval_loss": 1.981977902687504e-06,
|
| 1596 |
+
"eval_runtime": 0.1586,
|
| 1597 |
+
"eval_samples_per_second": 189.182,
|
| 1598 |
+
"eval_steps_per_second": 25.224,
|
| 1599 |
+
"step": 10600
|
| 1600 |
+
}
|
| 1601 |
+
],
|
| 1602 |
+
"logging_steps": 100,
|
| 1603 |
+
"max_steps": 10720,
|
| 1604 |
+
"num_input_tokens_seen": 0,
|
| 1605 |
+
"num_train_epochs": 5,
|
| 1606 |
+
"save_steps": 200,
|
| 1607 |
+
"stateful_callbacks": {
|
| 1608 |
+
"TrainerControl": {
|
| 1609 |
+
"args": {
|
| 1610 |
+
"should_epoch_stop": false,
|
| 1611 |
+
"should_evaluate": false,
|
| 1612 |
+
"should_log": false,
|
| 1613 |
+
"should_save": true,
|
| 1614 |
+
"should_training_stop": false
|
| 1615 |
+
},
|
| 1616 |
+
"attributes": {}
|
| 1617 |
+
}
|
| 1618 |
+
},
|
| 1619 |
+
"total_flos": 4161551619317760.0,
|
| 1620 |
+
"train_batch_size": 8,
|
| 1621 |
+
"trial_name": null,
|
| 1622 |
+
"trial_params": null
|
| 1623 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:522e1d1c64170c5a8e8052a1ee3925b8e6a8bc3d5f20f0b716a52785290af1c9
|
| 3 |
+
size 5240
|