init
Browse files- config.json +33 -0
- generation_config.json +9 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +125 -0
- tokenizer.json +0 -0
- tokenizer_config.json +938 -0
- trainer_state.json +1015 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"T5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.3,
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 2048,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 768,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "gelu_new",
|
| 12 |
+
"dropout": 0.3,
|
| 13 |
+
"dropout_rate": 0.1,
|
| 14 |
+
"dtype": "float32",
|
| 15 |
+
"eos_token_id": 1,
|
| 16 |
+
"feed_forward_proj": "gated-gelu",
|
| 17 |
+
"initializer_factor": 1.0,
|
| 18 |
+
"is_encoder_decoder": true,
|
| 19 |
+
"is_gated_act": true,
|
| 20 |
+
"layer_norm_epsilon": 1e-06,
|
| 21 |
+
"model_type": "t5",
|
| 22 |
+
"num_decoder_layers": 12,
|
| 23 |
+
"num_heads": 12,
|
| 24 |
+
"num_layers": 12,
|
| 25 |
+
"output_past": true,
|
| 26 |
+
"pad_token_id": 0,
|
| 27 |
+
"relative_attention_max_distance": 128,
|
| 28 |
+
"relative_attention_num_buckets": 32,
|
| 29 |
+
"tie_word_embeddings": false,
|
| 30 |
+
"transformers_version": "4.56.1",
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 50258
|
| 33 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
1
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 0,
|
| 8 |
+
"transformers_version": "4.56.1"
|
| 9 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8196db40919f81f9584f7bd3a7a5bdb0eb43afb83c92b086eba3b9fefaf8abf6
|
| 3 |
+
size 1101735784
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f26558831d657b51c1d590e95a5fe58736b9cad706580d8710374c43e9d00b65
|
| 3 |
+
size 2203642315
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc28dd3621119535bc6b515c38b28bc5d53971bdac84661515f94f4128da99aa
|
| 3 |
+
size 14645
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0e5ec702865236df4b9bd60d220b419b8d23de87018250b30e7b6e27536cb4a
|
| 3 |
+
size 1383
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16153222a02e0834661fd7661f2a8049d0715d9228a56f2f82ea287f8f6371f4
|
| 3 |
+
size 1465
|
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": "<pad>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false
|
| 124 |
+
}
|
| 125 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,938 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": null,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<pad>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "</s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"50258": {
|
| 21 |
+
"content": "<extra_id_0>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"50259": {
|
| 29 |
+
"content": "<extra_id_1>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50260": {
|
| 37 |
+
"content": "<extra_id_2>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"50261": {
|
| 45 |
+
"content": "<extra_id_3>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"50262": {
|
| 53 |
+
"content": "<extra_id_4>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"50263": {
|
| 61 |
+
"content": "<extra_id_5>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"50264": {
|
| 69 |
+
"content": "<extra_id_6>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"50265": {
|
| 77 |
+
"content": "<extra_id_7>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"50266": {
|
| 85 |
+
"content": "<extra_id_8>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"50267": {
|
| 93 |
+
"content": "<extra_id_9>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"50268": {
|
| 101 |
+
"content": "<extra_id_10>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"50269": {
|
| 109 |
+
"content": "<extra_id_11>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"50270": {
|
| 117 |
+
"content": "<extra_id_12>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"50271": {
|
| 125 |
+
"content": "<extra_id_13>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"50272": {
|
| 133 |
+
"content": "<extra_id_14>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
},
|
| 140 |
+
"50273": {
|
| 141 |
+
"content": "<extra_id_15>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
"50274": {
|
| 149 |
+
"content": "<extra_id_16>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": true
|
| 155 |
+
},
|
| 156 |
+
"50275": {
|
| 157 |
+
"content": "<extra_id_17>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": true
|
| 163 |
+
},
|
| 164 |
+
"50276": {
|
| 165 |
+
"content": "<extra_id_18>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"50277": {
|
| 173 |
+
"content": "<extra_id_19>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
+
},
|
| 180 |
+
"50278": {
|
| 181 |
+
"content": "<extra_id_20>",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": true
|
| 187 |
+
},
|
| 188 |
+
"50279": {
|
| 189 |
+
"content": "<extra_id_21>",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": true
|
| 195 |
+
},
|
| 196 |
+
"50280": {
|
| 197 |
+
"content": "<extra_id_22>",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": true
|
| 203 |
+
},
|
| 204 |
+
"50281": {
|
| 205 |
+
"content": "<extra_id_23>",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": true
|
| 211 |
+
},
|
| 212 |
+
"50282": {
|
| 213 |
+
"content": "<extra_id_24>",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": true
|
| 219 |
+
},
|
| 220 |
+
"50283": {
|
| 221 |
+
"content": "<extra_id_25>",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": true
|
| 227 |
+
},
|
| 228 |
+
"50284": {
|
| 229 |
+
"content": "<extra_id_26>",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": true
|
| 235 |
+
},
|
| 236 |
+
"50285": {
|
| 237 |
+
"content": "<extra_id_27>",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": false,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": true
|
| 243 |
+
},
|
| 244 |
+
"50286": {
|
| 245 |
+
"content": "<extra_id_28>",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": false,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": true
|
| 251 |
+
},
|
| 252 |
+
"50287": {
|
| 253 |
+
"content": "<extra_id_29>",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": true
|
| 259 |
+
},
|
| 260 |
+
"50288": {
|
| 261 |
+
"content": "<extra_id_30>",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": false,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": true
|
| 267 |
+
},
|
| 268 |
+
"50289": {
|
| 269 |
+
"content": "<extra_id_31>",
|
| 270 |
+
"lstrip": false,
|
| 271 |
+
"normalized": false,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": true
|
| 275 |
+
},
|
| 276 |
+
"50290": {
|
| 277 |
+
"content": "<extra_id_32>",
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"normalized": false,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": true
|
| 283 |
+
},
|
| 284 |
+
"50291": {
|
| 285 |
+
"content": "<extra_id_33>",
|
| 286 |
+
"lstrip": false,
|
| 287 |
+
"normalized": false,
|
| 288 |
+
"rstrip": false,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": true
|
| 291 |
+
},
|
| 292 |
+
"50292": {
|
| 293 |
+
"content": "<extra_id_34>",
|
| 294 |
+
"lstrip": false,
|
| 295 |
+
"normalized": false,
|
| 296 |
+
"rstrip": false,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": true
|
| 299 |
+
},
|
| 300 |
+
"50293": {
|
| 301 |
+
"content": "<extra_id_35>",
|
| 302 |
+
"lstrip": false,
|
| 303 |
+
"normalized": false,
|
| 304 |
+
"rstrip": false,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": true
|
| 307 |
+
},
|
| 308 |
+
"50294": {
|
| 309 |
+
"content": "<extra_id_36>",
|
| 310 |
+
"lstrip": false,
|
| 311 |
+
"normalized": false,
|
| 312 |
+
"rstrip": false,
|
| 313 |
+
"single_word": false,
|
| 314 |
+
"special": true
|
| 315 |
+
},
|
| 316 |
+
"50295": {
|
| 317 |
+
"content": "<extra_id_37>",
|
| 318 |
+
"lstrip": false,
|
| 319 |
+
"normalized": false,
|
| 320 |
+
"rstrip": false,
|
| 321 |
+
"single_word": false,
|
| 322 |
+
"special": true
|
| 323 |
+
},
|
| 324 |
+
"50296": {
|
| 325 |
+
"content": "<extra_id_38>",
|
| 326 |
+
"lstrip": false,
|
| 327 |
+
"normalized": false,
|
| 328 |
+
"rstrip": false,
|
| 329 |
+
"single_word": false,
|
| 330 |
+
"special": true
|
| 331 |
+
},
|
| 332 |
+
"50297": {
|
| 333 |
+
"content": "<extra_id_39>",
|
| 334 |
+
"lstrip": false,
|
| 335 |
+
"normalized": false,
|
| 336 |
+
"rstrip": false,
|
| 337 |
+
"single_word": false,
|
| 338 |
+
"special": true
|
| 339 |
+
},
|
| 340 |
+
"50298": {
|
| 341 |
+
"content": "<extra_id_40>",
|
| 342 |
+
"lstrip": false,
|
| 343 |
+
"normalized": false,
|
| 344 |
+
"rstrip": false,
|
| 345 |
+
"single_word": false,
|
| 346 |
+
"special": true
|
| 347 |
+
},
|
| 348 |
+
"50299": {
|
| 349 |
+
"content": "<extra_id_41>",
|
| 350 |
+
"lstrip": false,
|
| 351 |
+
"normalized": false,
|
| 352 |
+
"rstrip": false,
|
| 353 |
+
"single_word": false,
|
| 354 |
+
"special": true
|
| 355 |
+
},
|
| 356 |
+
"50300": {
|
| 357 |
+
"content": "<extra_id_42>",
|
| 358 |
+
"lstrip": false,
|
| 359 |
+
"normalized": false,
|
| 360 |
+
"rstrip": false,
|
| 361 |
+
"single_word": false,
|
| 362 |
+
"special": true
|
| 363 |
+
},
|
| 364 |
+
"50301": {
|
| 365 |
+
"content": "<extra_id_43>",
|
| 366 |
+
"lstrip": false,
|
| 367 |
+
"normalized": false,
|
| 368 |
+
"rstrip": false,
|
| 369 |
+
"single_word": false,
|
| 370 |
+
"special": true
|
| 371 |
+
},
|
| 372 |
+
"50302": {
|
| 373 |
+
"content": "<extra_id_44>",
|
| 374 |
+
"lstrip": false,
|
| 375 |
+
"normalized": false,
|
| 376 |
+
"rstrip": false,
|
| 377 |
+
"single_word": false,
|
| 378 |
+
"special": true
|
| 379 |
+
},
|
| 380 |
+
"50303": {
|
| 381 |
+
"content": "<extra_id_45>",
|
| 382 |
+
"lstrip": false,
|
| 383 |
+
"normalized": false,
|
| 384 |
+
"rstrip": false,
|
| 385 |
+
"single_word": false,
|
| 386 |
+
"special": true
|
| 387 |
+
},
|
| 388 |
+
"50304": {
|
| 389 |
+
"content": "<extra_id_46>",
|
| 390 |
+
"lstrip": false,
|
| 391 |
+
"normalized": false,
|
| 392 |
+
"rstrip": false,
|
| 393 |
+
"single_word": false,
|
| 394 |
+
"special": true
|
| 395 |
+
},
|
| 396 |
+
"50305": {
|
| 397 |
+
"content": "<extra_id_47>",
|
| 398 |
+
"lstrip": false,
|
| 399 |
+
"normalized": false,
|
| 400 |
+
"rstrip": false,
|
| 401 |
+
"single_word": false,
|
| 402 |
+
"special": true
|
| 403 |
+
},
|
| 404 |
+
"50306": {
|
| 405 |
+
"content": "<extra_id_48>",
|
| 406 |
+
"lstrip": false,
|
| 407 |
+
"normalized": false,
|
| 408 |
+
"rstrip": false,
|
| 409 |
+
"single_word": false,
|
| 410 |
+
"special": true
|
| 411 |
+
},
|
| 412 |
+
"50307": {
|
| 413 |
+
"content": "<extra_id_49>",
|
| 414 |
+
"lstrip": false,
|
| 415 |
+
"normalized": false,
|
| 416 |
+
"rstrip": false,
|
| 417 |
+
"single_word": false,
|
| 418 |
+
"special": true
|
| 419 |
+
},
|
| 420 |
+
"50308": {
|
| 421 |
+
"content": "<extra_id_50>",
|
| 422 |
+
"lstrip": false,
|
| 423 |
+
"normalized": false,
|
| 424 |
+
"rstrip": false,
|
| 425 |
+
"single_word": false,
|
| 426 |
+
"special": true
|
| 427 |
+
},
|
| 428 |
+
"50309": {
|
| 429 |
+
"content": "<extra_id_51>",
|
| 430 |
+
"lstrip": false,
|
| 431 |
+
"normalized": false,
|
| 432 |
+
"rstrip": false,
|
| 433 |
+
"single_word": false,
|
| 434 |
+
"special": true
|
| 435 |
+
},
|
| 436 |
+
"50310": {
|
| 437 |
+
"content": "<extra_id_52>",
|
| 438 |
+
"lstrip": false,
|
| 439 |
+
"normalized": false,
|
| 440 |
+
"rstrip": false,
|
| 441 |
+
"single_word": false,
|
| 442 |
+
"special": true
|
| 443 |
+
},
|
| 444 |
+
"50311": {
|
| 445 |
+
"content": "<extra_id_53>",
|
| 446 |
+
"lstrip": false,
|
| 447 |
+
"normalized": false,
|
| 448 |
+
"rstrip": false,
|
| 449 |
+
"single_word": false,
|
| 450 |
+
"special": true
|
| 451 |
+
},
|
| 452 |
+
"50312": {
|
| 453 |
+
"content": "<extra_id_54>",
|
| 454 |
+
"lstrip": false,
|
| 455 |
+
"normalized": false,
|
| 456 |
+
"rstrip": false,
|
| 457 |
+
"single_word": false,
|
| 458 |
+
"special": true
|
| 459 |
+
},
|
| 460 |
+
"50313": {
|
| 461 |
+
"content": "<extra_id_55>",
|
| 462 |
+
"lstrip": false,
|
| 463 |
+
"normalized": false,
|
| 464 |
+
"rstrip": false,
|
| 465 |
+
"single_word": false,
|
| 466 |
+
"special": true
|
| 467 |
+
},
|
| 468 |
+
"50314": {
|
| 469 |
+
"content": "<extra_id_56>",
|
| 470 |
+
"lstrip": false,
|
| 471 |
+
"normalized": false,
|
| 472 |
+
"rstrip": false,
|
| 473 |
+
"single_word": false,
|
| 474 |
+
"special": true
|
| 475 |
+
},
|
| 476 |
+
"50315": {
|
| 477 |
+
"content": "<extra_id_57>",
|
| 478 |
+
"lstrip": false,
|
| 479 |
+
"normalized": false,
|
| 480 |
+
"rstrip": false,
|
| 481 |
+
"single_word": false,
|
| 482 |
+
"special": true
|
| 483 |
+
},
|
| 484 |
+
"50316": {
|
| 485 |
+
"content": "<extra_id_58>",
|
| 486 |
+
"lstrip": false,
|
| 487 |
+
"normalized": false,
|
| 488 |
+
"rstrip": false,
|
| 489 |
+
"single_word": false,
|
| 490 |
+
"special": true
|
| 491 |
+
},
|
| 492 |
+
"50317": {
|
| 493 |
+
"content": "<extra_id_59>",
|
| 494 |
+
"lstrip": false,
|
| 495 |
+
"normalized": false,
|
| 496 |
+
"rstrip": false,
|
| 497 |
+
"single_word": false,
|
| 498 |
+
"special": true
|
| 499 |
+
},
|
| 500 |
+
"50318": {
|
| 501 |
+
"content": "<extra_id_60>",
|
| 502 |
+
"lstrip": false,
|
| 503 |
+
"normalized": false,
|
| 504 |
+
"rstrip": false,
|
| 505 |
+
"single_word": false,
|
| 506 |
+
"special": true
|
| 507 |
+
},
|
| 508 |
+
"50319": {
|
| 509 |
+
"content": "<extra_id_61>",
|
| 510 |
+
"lstrip": false,
|
| 511 |
+
"normalized": false,
|
| 512 |
+
"rstrip": false,
|
| 513 |
+
"single_word": false,
|
| 514 |
+
"special": true
|
| 515 |
+
},
|
| 516 |
+
"50320": {
|
| 517 |
+
"content": "<extra_id_62>",
|
| 518 |
+
"lstrip": false,
|
| 519 |
+
"normalized": false,
|
| 520 |
+
"rstrip": false,
|
| 521 |
+
"single_word": false,
|
| 522 |
+
"special": true
|
| 523 |
+
},
|
| 524 |
+
"50321": {
|
| 525 |
+
"content": "<extra_id_63>",
|
| 526 |
+
"lstrip": false,
|
| 527 |
+
"normalized": false,
|
| 528 |
+
"rstrip": false,
|
| 529 |
+
"single_word": false,
|
| 530 |
+
"special": true
|
| 531 |
+
},
|
| 532 |
+
"50322": {
|
| 533 |
+
"content": "<extra_id_64>",
|
| 534 |
+
"lstrip": false,
|
| 535 |
+
"normalized": false,
|
| 536 |
+
"rstrip": false,
|
| 537 |
+
"single_word": false,
|
| 538 |
+
"special": true
|
| 539 |
+
},
|
| 540 |
+
"50323": {
|
| 541 |
+
"content": "<extra_id_65>",
|
| 542 |
+
"lstrip": false,
|
| 543 |
+
"normalized": false,
|
| 544 |
+
"rstrip": false,
|
| 545 |
+
"single_word": false,
|
| 546 |
+
"special": true
|
| 547 |
+
},
|
| 548 |
+
"50324": {
|
| 549 |
+
"content": "<extra_id_66>",
|
| 550 |
+
"lstrip": false,
|
| 551 |
+
"normalized": false,
|
| 552 |
+
"rstrip": false,
|
| 553 |
+
"single_word": false,
|
| 554 |
+
"special": true
|
| 555 |
+
},
|
| 556 |
+
"50325": {
|
| 557 |
+
"content": "<extra_id_67>",
|
| 558 |
+
"lstrip": false,
|
| 559 |
+
"normalized": false,
|
| 560 |
+
"rstrip": false,
|
| 561 |
+
"single_word": false,
|
| 562 |
+
"special": true
|
| 563 |
+
},
|
| 564 |
+
"50326": {
|
| 565 |
+
"content": "<extra_id_68>",
|
| 566 |
+
"lstrip": false,
|
| 567 |
+
"normalized": false,
|
| 568 |
+
"rstrip": false,
|
| 569 |
+
"single_word": false,
|
| 570 |
+
"special": true
|
| 571 |
+
},
|
| 572 |
+
"50327": {
|
| 573 |
+
"content": "<extra_id_69>",
|
| 574 |
+
"lstrip": false,
|
| 575 |
+
"normalized": false,
|
| 576 |
+
"rstrip": false,
|
| 577 |
+
"single_word": false,
|
| 578 |
+
"special": true
|
| 579 |
+
},
|
| 580 |
+
"50328": {
|
| 581 |
+
"content": "<extra_id_70>",
|
| 582 |
+
"lstrip": false,
|
| 583 |
+
"normalized": false,
|
| 584 |
+
"rstrip": false,
|
| 585 |
+
"single_word": false,
|
| 586 |
+
"special": true
|
| 587 |
+
},
|
| 588 |
+
"50329": {
|
| 589 |
+
"content": "<extra_id_71>",
|
| 590 |
+
"lstrip": false,
|
| 591 |
+
"normalized": false,
|
| 592 |
+
"rstrip": false,
|
| 593 |
+
"single_word": false,
|
| 594 |
+
"special": true
|
| 595 |
+
},
|
| 596 |
+
"50330": {
|
| 597 |
+
"content": "<extra_id_72>",
|
| 598 |
+
"lstrip": false,
|
| 599 |
+
"normalized": false,
|
| 600 |
+
"rstrip": false,
|
| 601 |
+
"single_word": false,
|
| 602 |
+
"special": true
|
| 603 |
+
},
|
| 604 |
+
"50331": {
|
| 605 |
+
"content": "<extra_id_73>",
|
| 606 |
+
"lstrip": false,
|
| 607 |
+
"normalized": false,
|
| 608 |
+
"rstrip": false,
|
| 609 |
+
"single_word": false,
|
| 610 |
+
"special": true
|
| 611 |
+
},
|
| 612 |
+
"50332": {
|
| 613 |
+
"content": "<extra_id_74>",
|
| 614 |
+
"lstrip": false,
|
| 615 |
+
"normalized": false,
|
| 616 |
+
"rstrip": false,
|
| 617 |
+
"single_word": false,
|
| 618 |
+
"special": true
|
| 619 |
+
},
|
| 620 |
+
"50333": {
|
| 621 |
+
"content": "<extra_id_75>",
|
| 622 |
+
"lstrip": false,
|
| 623 |
+
"normalized": false,
|
| 624 |
+
"rstrip": false,
|
| 625 |
+
"single_word": false,
|
| 626 |
+
"special": true
|
| 627 |
+
},
|
| 628 |
+
"50334": {
|
| 629 |
+
"content": "<extra_id_76>",
|
| 630 |
+
"lstrip": false,
|
| 631 |
+
"normalized": false,
|
| 632 |
+
"rstrip": false,
|
| 633 |
+
"single_word": false,
|
| 634 |
+
"special": true
|
| 635 |
+
},
|
| 636 |
+
"50335": {
|
| 637 |
+
"content": "<extra_id_77>",
|
| 638 |
+
"lstrip": false,
|
| 639 |
+
"normalized": false,
|
| 640 |
+
"rstrip": false,
|
| 641 |
+
"single_word": false,
|
| 642 |
+
"special": true
|
| 643 |
+
},
|
| 644 |
+
"50336": {
|
| 645 |
+
"content": "<extra_id_78>",
|
| 646 |
+
"lstrip": false,
|
| 647 |
+
"normalized": false,
|
| 648 |
+
"rstrip": false,
|
| 649 |
+
"single_word": false,
|
| 650 |
+
"special": true
|
| 651 |
+
},
|
| 652 |
+
"50337": {
|
| 653 |
+
"content": "<extra_id_79>",
|
| 654 |
+
"lstrip": false,
|
| 655 |
+
"normalized": false,
|
| 656 |
+
"rstrip": false,
|
| 657 |
+
"single_word": false,
|
| 658 |
+
"special": true
|
| 659 |
+
},
|
| 660 |
+
"50338": {
|
| 661 |
+
"content": "<extra_id_80>",
|
| 662 |
+
"lstrip": false,
|
| 663 |
+
"normalized": false,
|
| 664 |
+
"rstrip": false,
|
| 665 |
+
"single_word": false,
|
| 666 |
+
"special": true
|
| 667 |
+
},
|
| 668 |
+
"50339": {
|
| 669 |
+
"content": "<extra_id_81>",
|
| 670 |
+
"lstrip": false,
|
| 671 |
+
"normalized": false,
|
| 672 |
+
"rstrip": false,
|
| 673 |
+
"single_word": false,
|
| 674 |
+
"special": true
|
| 675 |
+
},
|
| 676 |
+
"50340": {
|
| 677 |
+
"content": "<extra_id_82>",
|
| 678 |
+
"lstrip": false,
|
| 679 |
+
"normalized": false,
|
| 680 |
+
"rstrip": false,
|
| 681 |
+
"single_word": false,
|
| 682 |
+
"special": true
|
| 683 |
+
},
|
| 684 |
+
"50341": {
|
| 685 |
+
"content": "<extra_id_83>",
|
| 686 |
+
"lstrip": false,
|
| 687 |
+
"normalized": false,
|
| 688 |
+
"rstrip": false,
|
| 689 |
+
"single_word": false,
|
| 690 |
+
"special": true
|
| 691 |
+
},
|
| 692 |
+
"50342": {
|
| 693 |
+
"content": "<extra_id_84>",
|
| 694 |
+
"lstrip": false,
|
| 695 |
+
"normalized": false,
|
| 696 |
+
"rstrip": false,
|
| 697 |
+
"single_word": false,
|
| 698 |
+
"special": true
|
| 699 |
+
},
|
| 700 |
+
"50343": {
|
| 701 |
+
"content": "<extra_id_85>",
|
| 702 |
+
"lstrip": false,
|
| 703 |
+
"normalized": false,
|
| 704 |
+
"rstrip": false,
|
| 705 |
+
"single_word": false,
|
| 706 |
+
"special": true
|
| 707 |
+
},
|
| 708 |
+
"50344": {
|
| 709 |
+
"content": "<extra_id_86>",
|
| 710 |
+
"lstrip": false,
|
| 711 |
+
"normalized": false,
|
| 712 |
+
"rstrip": false,
|
| 713 |
+
"single_word": false,
|
| 714 |
+
"special": true
|
| 715 |
+
},
|
| 716 |
+
"50345": {
|
| 717 |
+
"content": "<extra_id_87>",
|
| 718 |
+
"lstrip": false,
|
| 719 |
+
"normalized": false,
|
| 720 |
+
"rstrip": false,
|
| 721 |
+
"single_word": false,
|
| 722 |
+
"special": true
|
| 723 |
+
},
|
| 724 |
+
"50346": {
|
| 725 |
+
"content": "<extra_id_88>",
|
| 726 |
+
"lstrip": false,
|
| 727 |
+
"normalized": false,
|
| 728 |
+
"rstrip": false,
|
| 729 |
+
"single_word": false,
|
| 730 |
+
"special": true
|
| 731 |
+
},
|
| 732 |
+
"50347": {
|
| 733 |
+
"content": "<extra_id_89>",
|
| 734 |
+
"lstrip": false,
|
| 735 |
+
"normalized": false,
|
| 736 |
+
"rstrip": false,
|
| 737 |
+
"single_word": false,
|
| 738 |
+
"special": true
|
| 739 |
+
},
|
| 740 |
+
"50348": {
|
| 741 |
+
"content": "<extra_id_90>",
|
| 742 |
+
"lstrip": false,
|
| 743 |
+
"normalized": false,
|
| 744 |
+
"rstrip": false,
|
| 745 |
+
"single_word": false,
|
| 746 |
+
"special": true
|
| 747 |
+
},
|
| 748 |
+
"50349": {
|
| 749 |
+
"content": "<extra_id_91>",
|
| 750 |
+
"lstrip": false,
|
| 751 |
+
"normalized": false,
|
| 752 |
+
"rstrip": false,
|
| 753 |
+
"single_word": false,
|
| 754 |
+
"special": true
|
| 755 |
+
},
|
| 756 |
+
"50350": {
|
| 757 |
+
"content": "<extra_id_92>",
|
| 758 |
+
"lstrip": false,
|
| 759 |
+
"normalized": false,
|
| 760 |
+
"rstrip": false,
|
| 761 |
+
"single_word": false,
|
| 762 |
+
"special": true
|
| 763 |
+
},
|
| 764 |
+
"50351": {
|
| 765 |
+
"content": "<extra_id_93>",
|
| 766 |
+
"lstrip": false,
|
| 767 |
+
"normalized": false,
|
| 768 |
+
"rstrip": false,
|
| 769 |
+
"single_word": false,
|
| 770 |
+
"special": true
|
| 771 |
+
},
|
| 772 |
+
"50352": {
|
| 773 |
+
"content": "<extra_id_94>",
|
| 774 |
+
"lstrip": false,
|
| 775 |
+
"normalized": false,
|
| 776 |
+
"rstrip": false,
|
| 777 |
+
"single_word": false,
|
| 778 |
+
"special": true
|
| 779 |
+
},
|
| 780 |
+
"50353": {
|
| 781 |
+
"content": "<extra_id_95>",
|
| 782 |
+
"lstrip": false,
|
| 783 |
+
"normalized": false,
|
| 784 |
+
"rstrip": false,
|
| 785 |
+
"single_word": false,
|
| 786 |
+
"special": true
|
| 787 |
+
},
|
| 788 |
+
"50354": {
|
| 789 |
+
"content": "<extra_id_96>",
|
| 790 |
+
"lstrip": false,
|
| 791 |
+
"normalized": false,
|
| 792 |
+
"rstrip": false,
|
| 793 |
+
"single_word": false,
|
| 794 |
+
"special": true
|
| 795 |
+
},
|
| 796 |
+
"50355": {
|
| 797 |
+
"content": "<extra_id_97>",
|
| 798 |
+
"lstrip": false,
|
| 799 |
+
"normalized": false,
|
| 800 |
+
"rstrip": false,
|
| 801 |
+
"single_word": false,
|
| 802 |
+
"special": true
|
| 803 |
+
},
|
| 804 |
+
"50356": {
|
| 805 |
+
"content": "<extra_id_98>",
|
| 806 |
+
"lstrip": false,
|
| 807 |
+
"normalized": false,
|
| 808 |
+
"rstrip": false,
|
| 809 |
+
"single_word": false,
|
| 810 |
+
"special": true
|
| 811 |
+
},
|
| 812 |
+
"50357": {
|
| 813 |
+
"content": "<extra_id_99>",
|
| 814 |
+
"lstrip": false,
|
| 815 |
+
"normalized": false,
|
| 816 |
+
"rstrip": false,
|
| 817 |
+
"single_word": false,
|
| 818 |
+
"special": true
|
| 819 |
+
}
|
| 820 |
+
},
|
| 821 |
+
"additional_special_tokens": [
|
| 822 |
+
"<extra_id_0>",
|
| 823 |
+
"<extra_id_1>",
|
| 824 |
+
"<extra_id_2>",
|
| 825 |
+
"<extra_id_3>",
|
| 826 |
+
"<extra_id_4>",
|
| 827 |
+
"<extra_id_5>",
|
| 828 |
+
"<extra_id_6>",
|
| 829 |
+
"<extra_id_7>",
|
| 830 |
+
"<extra_id_8>",
|
| 831 |
+
"<extra_id_9>",
|
| 832 |
+
"<extra_id_10>",
|
| 833 |
+
"<extra_id_11>",
|
| 834 |
+
"<extra_id_12>",
|
| 835 |
+
"<extra_id_13>",
|
| 836 |
+
"<extra_id_14>",
|
| 837 |
+
"<extra_id_15>",
|
| 838 |
+
"<extra_id_16>",
|
| 839 |
+
"<extra_id_17>",
|
| 840 |
+
"<extra_id_18>",
|
| 841 |
+
"<extra_id_19>",
|
| 842 |
+
"<extra_id_20>",
|
| 843 |
+
"<extra_id_21>",
|
| 844 |
+
"<extra_id_22>",
|
| 845 |
+
"<extra_id_23>",
|
| 846 |
+
"<extra_id_24>",
|
| 847 |
+
"<extra_id_25>",
|
| 848 |
+
"<extra_id_26>",
|
| 849 |
+
"<extra_id_27>",
|
| 850 |
+
"<extra_id_28>",
|
| 851 |
+
"<extra_id_29>",
|
| 852 |
+
"<extra_id_30>",
|
| 853 |
+
"<extra_id_31>",
|
| 854 |
+
"<extra_id_32>",
|
| 855 |
+
"<extra_id_33>",
|
| 856 |
+
"<extra_id_34>",
|
| 857 |
+
"<extra_id_35>",
|
| 858 |
+
"<extra_id_36>",
|
| 859 |
+
"<extra_id_37>",
|
| 860 |
+
"<extra_id_38>",
|
| 861 |
+
"<extra_id_39>",
|
| 862 |
+
"<extra_id_40>",
|
| 863 |
+
"<extra_id_41>",
|
| 864 |
+
"<extra_id_42>",
|
| 865 |
+
"<extra_id_43>",
|
| 866 |
+
"<extra_id_44>",
|
| 867 |
+
"<extra_id_45>",
|
| 868 |
+
"<extra_id_46>",
|
| 869 |
+
"<extra_id_47>",
|
| 870 |
+
"<extra_id_48>",
|
| 871 |
+
"<extra_id_49>",
|
| 872 |
+
"<extra_id_50>",
|
| 873 |
+
"<extra_id_51>",
|
| 874 |
+
"<extra_id_52>",
|
| 875 |
+
"<extra_id_53>",
|
| 876 |
+
"<extra_id_54>",
|
| 877 |
+
"<extra_id_55>",
|
| 878 |
+
"<extra_id_56>",
|
| 879 |
+
"<extra_id_57>",
|
| 880 |
+
"<extra_id_58>",
|
| 881 |
+
"<extra_id_59>",
|
| 882 |
+
"<extra_id_60>",
|
| 883 |
+
"<extra_id_61>",
|
| 884 |
+
"<extra_id_62>",
|
| 885 |
+
"<extra_id_63>",
|
| 886 |
+
"<extra_id_64>",
|
| 887 |
+
"<extra_id_65>",
|
| 888 |
+
"<extra_id_66>",
|
| 889 |
+
"<extra_id_67>",
|
| 890 |
+
"<extra_id_68>",
|
| 891 |
+
"<extra_id_69>",
|
| 892 |
+
"<extra_id_70>",
|
| 893 |
+
"<extra_id_71>",
|
| 894 |
+
"<extra_id_72>",
|
| 895 |
+
"<extra_id_73>",
|
| 896 |
+
"<extra_id_74>",
|
| 897 |
+
"<extra_id_75>",
|
| 898 |
+
"<extra_id_76>",
|
| 899 |
+
"<extra_id_77>",
|
| 900 |
+
"<extra_id_78>",
|
| 901 |
+
"<extra_id_79>",
|
| 902 |
+
"<extra_id_80>",
|
| 903 |
+
"<extra_id_81>",
|
| 904 |
+
"<extra_id_82>",
|
| 905 |
+
"<extra_id_83>",
|
| 906 |
+
"<extra_id_84>",
|
| 907 |
+
"<extra_id_85>",
|
| 908 |
+
"<extra_id_86>",
|
| 909 |
+
"<extra_id_87>",
|
| 910 |
+
"<extra_id_88>",
|
| 911 |
+
"<extra_id_89>",
|
| 912 |
+
"<extra_id_90>",
|
| 913 |
+
"<extra_id_91>",
|
| 914 |
+
"<extra_id_92>",
|
| 915 |
+
"<extra_id_93>",
|
| 916 |
+
"<extra_id_94>",
|
| 917 |
+
"<extra_id_95>",
|
| 918 |
+
"<extra_id_96>",
|
| 919 |
+
"<extra_id_97>",
|
| 920 |
+
"<extra_id_98>",
|
| 921 |
+
"<extra_id_99>"
|
| 922 |
+
],
|
| 923 |
+
"clean_up_tokenization_spaces": false,
|
| 924 |
+
"eos_token": "</s>",
|
| 925 |
+
"extra_ids": 100,
|
| 926 |
+
"extra_special_tokens": {},
|
| 927 |
+
"max_length": null,
|
| 928 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 929 |
+
"pad_to_multiple_of": null,
|
| 930 |
+
"pad_token": "<pad>",
|
| 931 |
+
"pad_token_type_id": 0,
|
| 932 |
+
"padding_side": "right",
|
| 933 |
+
"stride": 0,
|
| 934 |
+
"tokenizer_class": "T5TokenizerFast",
|
| 935 |
+
"truncation_side": "right",
|
| 936 |
+
"truncation_strategy": "longest_first",
|
| 937 |
+
"unk_token": "<pad>"
|
| 938 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1015 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 1650,
|
| 3 |
+
"best_metric": 0.006614842917770147,
|
| 4 |
+
"best_model_checkpoint": "/content/NH-SQL-finetuned/checkpoint-1650",
|
| 5 |
+
"epoch": 50.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1650,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.030303030303030304,
|
| 14 |
+
"grad_norm": 6.595283031463623,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 1.9666,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.6060606060606061,
|
| 21 |
+
"grad_norm": 6.3463263511657715,
|
| 22 |
+
"learning_rate": 5.757575757575758e-07,
|
| 23 |
+
"loss": 1.8746,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.0,
|
| 28 |
+
"eval_loss": 1.7834347486495972,
|
| 29 |
+
"eval_runtime": 0.9389,
|
| 30 |
+
"eval_samples_per_second": 140.592,
|
| 31 |
+
"eval_steps_per_second": 18.107,
|
| 32 |
+
"step": 33
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.2121212121212122,
|
| 36 |
+
"grad_norm": 4.871561050415039,
|
| 37 |
+
"learning_rate": 1.181818181818182e-06,
|
| 38 |
+
"loss": 1.7412,
|
| 39 |
+
"step": 40
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.8181818181818183,
|
| 43 |
+
"grad_norm": 3.2557735443115234,
|
| 44 |
+
"learning_rate": 1.787878787878788e-06,
|
| 45 |
+
"loss": 1.5522,
|
| 46 |
+
"step": 60
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 2.0,
|
| 50 |
+
"eval_loss": 1.2882661819458008,
|
| 51 |
+
"eval_runtime": 0.9475,
|
| 52 |
+
"eval_samples_per_second": 139.315,
|
| 53 |
+
"eval_steps_per_second": 17.942,
|
| 54 |
+
"step": 66
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 2.4242424242424243,
|
| 58 |
+
"grad_norm": 1.9632468223571777,
|
| 59 |
+
"learning_rate": 2.393939393939394e-06,
|
| 60 |
+
"loss": 1.2669,
|
| 61 |
+
"step": 80
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 3.0,
|
| 65 |
+
"eval_loss": 0.8929286003112793,
|
| 66 |
+
"eval_runtime": 0.9528,
|
| 67 |
+
"eval_samples_per_second": 138.545,
|
| 68 |
+
"eval_steps_per_second": 17.843,
|
| 69 |
+
"step": 99
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 3.0303030303030303,
|
| 73 |
+
"grad_norm": 1.6738139390945435,
|
| 74 |
+
"learning_rate": 3e-06,
|
| 75 |
+
"loss": 1.0527,
|
| 76 |
+
"step": 100
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 3.6363636363636362,
|
| 80 |
+
"grad_norm": 1.4490736722946167,
|
| 81 |
+
"learning_rate": 3.606060606060606e-06,
|
| 82 |
+
"loss": 0.8491,
|
| 83 |
+
"step": 120
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 4.0,
|
| 87 |
+
"eval_loss": 0.5932092070579529,
|
| 88 |
+
"eval_runtime": 0.9509,
|
| 89 |
+
"eval_samples_per_second": 138.815,
|
| 90 |
+
"eval_steps_per_second": 17.878,
|
| 91 |
+
"step": 132
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 4.242424242424242,
|
| 95 |
+
"grad_norm": 1.0791282653808594,
|
| 96 |
+
"learning_rate": 4.212121212121212e-06,
|
| 97 |
+
"loss": 0.6586,
|
| 98 |
+
"step": 140
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 4.848484848484849,
|
| 102 |
+
"grad_norm": 0.8789141178131104,
|
| 103 |
+
"learning_rate": 4.818181818181819e-06,
|
| 104 |
+
"loss": 0.4801,
|
| 105 |
+
"step": 160
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 5.0,
|
| 109 |
+
"eval_loss": 0.42336800694465637,
|
| 110 |
+
"eval_runtime": 0.9459,
|
| 111 |
+
"eval_samples_per_second": 139.555,
|
| 112 |
+
"eval_steps_per_second": 17.973,
|
| 113 |
+
"step": 165
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 5.454545454545454,
|
| 117 |
+
"grad_norm": 0.8390600085258484,
|
| 118 |
+
"learning_rate": 4.9989035693310165e-06,
|
| 119 |
+
"loss": 0.4134,
|
| 120 |
+
"step": 180
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 6.0,
|
| 124 |
+
"eval_loss": 0.3166239559650421,
|
| 125 |
+
"eval_runtime": 0.9402,
|
| 126 |
+
"eval_samples_per_second": 140.394,
|
| 127 |
+
"eval_steps_per_second": 18.081,
|
| 128 |
+
"step": 198
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 6.0606060606060606,
|
| 132 |
+
"grad_norm": 0.908724308013916,
|
| 133 |
+
"learning_rate": 4.993535611735464e-06,
|
| 134 |
+
"loss": 0.33,
|
| 135 |
+
"step": 200
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 6.666666666666667,
|
| 139 |
+
"grad_norm": 0.8689959645271301,
|
| 140 |
+
"learning_rate": 4.983704338371375e-06,
|
| 141 |
+
"loss": 0.2941,
|
| 142 |
+
"step": 220
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 7.0,
|
| 146 |
+
"eval_loss": 0.246794193983078,
|
| 147 |
+
"eval_runtime": 0.9539,
|
| 148 |
+
"eval_samples_per_second": 138.381,
|
| 149 |
+
"eval_steps_per_second": 17.822,
|
| 150 |
+
"step": 231
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 7.2727272727272725,
|
| 154 |
+
"grad_norm": 0.806349515914917,
|
| 155 |
+
"learning_rate": 4.969427346772643e-06,
|
| 156 |
+
"loss": 0.2513,
|
| 157 |
+
"step": 240
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 7.878787878787879,
|
| 161 |
+
"grad_norm": 0.8216381072998047,
|
| 162 |
+
"learning_rate": 4.950730192107368e-06,
|
| 163 |
+
"loss": 0.2244,
|
| 164 |
+
"step": 260
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 8.0,
|
| 168 |
+
"eval_loss": 0.19389495253562927,
|
| 169 |
+
"eval_runtime": 0.9398,
|
| 170 |
+
"eval_samples_per_second": 140.46,
|
| 171 |
+
"eval_steps_per_second": 18.09,
|
| 172 |
+
"step": 264
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 8.484848484848484,
|
| 176 |
+
"grad_norm": 0.8309475183486938,
|
| 177 |
+
"learning_rate": 4.927646341435276e-06,
|
| 178 |
+
"loss": 0.1756,
|
| 179 |
+
"step": 280
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 9.0,
|
| 183 |
+
"eval_loss": 0.1608426719903946,
|
| 184 |
+
"eval_runtime": 0.9567,
|
| 185 |
+
"eval_samples_per_second": 137.969,
|
| 186 |
+
"eval_steps_per_second": 17.769,
|
| 187 |
+
"step": 297
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 9.090909090909092,
|
| 191 |
+
"grad_norm": 0.807766854763031,
|
| 192 |
+
"learning_rate": 4.900217113803193e-06,
|
| 193 |
+
"loss": 0.1666,
|
| 194 |
+
"step": 300
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 9.696969696969697,
|
| 198 |
+
"grad_norm": 0.638713538646698,
|
| 199 |
+
"learning_rate": 4.868491606285823e-06,
|
| 200 |
+
"loss": 0.1756,
|
| 201 |
+
"step": 320
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 10.0,
|
| 205 |
+
"eval_loss": 0.13285745680332184,
|
| 206 |
+
"eval_runtime": 0.9431,
|
| 207 |
+
"eval_samples_per_second": 139.968,
|
| 208 |
+
"eval_steps_per_second": 18.026,
|
| 209 |
+
"step": 330
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 10.303030303030303,
|
| 213 |
+
"grad_norm": 0.6577040553092957,
|
| 214 |
+
"learning_rate": 4.832526606104213e-06,
|
| 215 |
+
"loss": 0.1407,
|
| 216 |
+
"step": 340
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 10.909090909090908,
|
| 220 |
+
"grad_norm": 0.7107315063476562,
|
| 221 |
+
"learning_rate": 4.792386488979193e-06,
|
| 222 |
+
"loss": 0.1218,
|
| 223 |
+
"step": 360
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 11.0,
|
| 227 |
+
"eval_loss": 0.1115950271487236,
|
| 228 |
+
"eval_runtime": 0.9468,
|
| 229 |
+
"eval_samples_per_second": 139.417,
|
| 230 |
+
"eval_steps_per_second": 17.955,
|
| 231 |
+
"step": 363
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 11.515151515151516,
|
| 235 |
+
"grad_norm": 0.7401019334793091,
|
| 236 |
+
"learning_rate": 4.74814310390176e-06,
|
| 237 |
+
"loss": 0.1362,
|
| 238 |
+
"step": 380
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 12.0,
|
| 242 |
+
"eval_loss": 0.09207186847925186,
|
| 243 |
+
"eval_runtime": 0.9332,
|
| 244 |
+
"eval_samples_per_second": 141.446,
|
| 245 |
+
"eval_steps_per_second": 18.216,
|
| 246 |
+
"step": 396
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 12.121212121212121,
|
| 250 |
+
"grad_norm": 0.68468177318573,
|
| 251 |
+
"learning_rate": 4.699875644526633e-06,
|
| 252 |
+
"loss": 0.0987,
|
| 253 |
+
"step": 400
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 12.727272727272727,
|
| 257 |
+
"grad_norm": 0.7722787857055664,
|
| 258 |
+
"learning_rate": 4.647670507419206e-06,
|
| 259 |
+
"loss": 0.0989,
|
| 260 |
+
"step": 420
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 13.0,
|
| 264 |
+
"eval_loss": 0.0792744979262352,
|
| 265 |
+
"eval_runtime": 0.935,
|
| 266 |
+
"eval_samples_per_second": 141.172,
|
| 267 |
+
"eval_steps_per_second": 18.181,
|
| 268 |
+
"step": 429
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 13.333333333333334,
|
| 272 |
+
"grad_norm": 0.48431074619293213,
|
| 273 |
+
"learning_rate": 4.591621137409602e-06,
|
| 274 |
+
"loss": 0.0936,
|
| 275 |
+
"step": 440
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 13.93939393939394,
|
| 279 |
+
"grad_norm": 0.555296778678894,
|
| 280 |
+
"learning_rate": 4.53182786033067e-06,
|
| 281 |
+
"loss": 0.0945,
|
| 282 |
+
"step": 460
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 14.0,
|
| 286 |
+
"eval_loss": 0.07043830305337906,
|
| 287 |
+
"eval_runtime": 0.9312,
|
| 288 |
+
"eval_samples_per_second": 141.753,
|
| 289 |
+
"eval_steps_per_second": 18.256,
|
| 290 |
+
"step": 462
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 14.545454545454545,
|
| 294 |
+
"grad_norm": 0.5280194878578186,
|
| 295 |
+
"learning_rate": 4.468397703439282e-06,
|
| 296 |
+
"loss": 0.0811,
|
| 297 |
+
"step": 480
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 15.0,
|
| 301 |
+
"eval_loss": 0.06017066538333893,
|
| 302 |
+
"eval_runtime": 0.9305,
|
| 303 |
+
"eval_samples_per_second": 141.866,
|
| 304 |
+
"eval_steps_per_second": 18.271,
|
| 305 |
+
"step": 495
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 15.151515151515152,
|
| 309 |
+
"grad_norm": 0.5912495851516724,
|
| 310 |
+
"learning_rate": 4.401444203842396e-06,
|
| 311 |
+
"loss": 0.0742,
|
| 312 |
+
"step": 500
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 15.757575757575758,
|
| 316 |
+
"grad_norm": 1.0043439865112305,
|
| 317 |
+
"learning_rate": 4.331087205270778e-06,
|
| 318 |
+
"loss": 0.0778,
|
| 319 |
+
"step": 520
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 16.0,
|
| 323 |
+
"eval_loss": 0.052856337279081345,
|
| 324 |
+
"eval_runtime": 0.9363,
|
| 325 |
+
"eval_samples_per_second": 140.988,
|
| 326 |
+
"eval_steps_per_second": 18.158,
|
| 327 |
+
"step": 528
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 16.363636363636363,
|
| 331 |
+
"grad_norm": 0.37315091490745544,
|
| 332 |
+
"learning_rate": 4.257452643564155e-06,
|
| 333 |
+
"loss": 0.0746,
|
| 334 |
+
"step": 540
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 16.96969696969697,
|
| 338 |
+
"grad_norm": 0.5725280046463013,
|
| 339 |
+
"learning_rate": 4.180672321251766e-06,
|
| 340 |
+
"loss": 0.0651,
|
| 341 |
+
"step": 560
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 17.0,
|
| 345 |
+
"eval_loss": 0.04653371125459671,
|
| 346 |
+
"eval_runtime": 0.9263,
|
| 347 |
+
"eval_samples_per_second": 142.504,
|
| 348 |
+
"eval_steps_per_second": 18.353,
|
| 349 |
+
"step": 561
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 17.575757575757574,
|
| 353 |
+
"grad_norm": 0.6575049161911011,
|
| 354 |
+
"learning_rate": 4.100883671631806e-06,
|
| 355 |
+
"loss": 0.0529,
|
| 356 |
+
"step": 580
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 18.0,
|
| 360 |
+
"eval_loss": 0.04210372641682625,
|
| 361 |
+
"eval_runtime": 0.9448,
|
| 362 |
+
"eval_samples_per_second": 139.719,
|
| 363 |
+
"eval_steps_per_second": 17.994,
|
| 364 |
+
"step": 594
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 18.181818181818183,
|
| 368 |
+
"grad_norm": 0.7622207999229431,
|
| 369 |
+
"learning_rate": 4.018229512772053e-06,
|
| 370 |
+
"loss": 0.0644,
|
| 371 |
+
"step": 600
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 18.78787878787879,
|
| 375 |
+
"grad_norm": 0.5367633700370789,
|
| 376 |
+
"learning_rate": 3.9328577918719916e-06,
|
| 377 |
+
"loss": 0.0551,
|
| 378 |
+
"step": 620
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 19.0,
|
| 382 |
+
"eval_loss": 0.03950377553701401,
|
| 383 |
+
"eval_runtime": 0.9419,
|
| 384 |
+
"eval_samples_per_second": 140.144,
|
| 385 |
+
"eval_steps_per_second": 18.049,
|
| 386 |
+
"step": 627
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 19.393939393939394,
|
| 390 |
+
"grad_norm": 0.581658661365509,
|
| 391 |
+
"learning_rate": 3.844921320444031e-06,
|
| 392 |
+
"loss": 0.0566,
|
| 393 |
+
"step": 640
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 20.0,
|
| 397 |
+
"grad_norm": 0.7774003148078918,
|
| 398 |
+
"learning_rate": 3.754577500787828e-06,
|
| 399 |
+
"loss": 0.0532,
|
| 400 |
+
"step": 660
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 20.0,
|
| 404 |
+
"eval_loss": 0.0353802889585495,
|
| 405 |
+
"eval_runtime": 0.9534,
|
| 406 |
+
"eval_samples_per_second": 138.453,
|
| 407 |
+
"eval_steps_per_second": 17.831,
|
| 408 |
+
"step": 660
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 20.606060606060606,
|
| 412 |
+
"grad_norm": 0.6069843769073486,
|
| 413 |
+
"learning_rate": 3.66198804424729e-06,
|
| 414 |
+
"loss": 0.0436,
|
| 415 |
+
"step": 680
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 21.0,
|
| 419 |
+
"eval_loss": 0.031004376709461212,
|
| 420 |
+
"eval_runtime": 0.9391,
|
| 421 |
+
"eval_samples_per_second": 140.556,
|
| 422 |
+
"eval_steps_per_second": 18.102,
|
| 423 |
+
"step": 693
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 21.21212121212121,
|
| 427 |
+
"grad_norm": 0.5869702696800232,
|
| 428 |
+
"learning_rate": 3.5673186817546047e-06,
|
| 429 |
+
"loss": 0.0487,
|
| 430 |
+
"step": 700
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 21.818181818181817,
|
| 434 |
+
"grad_norm": 0.39276406168937683,
|
| 435 |
+
"learning_rate": 3.4707388671793814e-06,
|
| 436 |
+
"loss": 0.0459,
|
| 437 |
+
"step": 720
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 22.0,
|
| 441 |
+
"eval_loss": 0.027377676218748093,
|
| 442 |
+
"eval_runtime": 0.9405,
|
| 443 |
+
"eval_samples_per_second": 140.352,
|
| 444 |
+
"eval_steps_per_second": 18.076,
|
| 445 |
+
"step": 726
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 22.424242424242426,
|
| 449 |
+
"grad_norm": 0.5247741937637329,
|
| 450 |
+
"learning_rate": 3.3724214740138933e-06,
|
| 451 |
+
"loss": 0.0461,
|
| 452 |
+
"step": 740
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 23.0,
|
| 456 |
+
"eval_loss": 0.02525358274579048,
|
| 457 |
+
"eval_runtime": 0.9593,
|
| 458 |
+
"eval_samples_per_second": 137.596,
|
| 459 |
+
"eval_steps_per_second": 17.721,
|
| 460 |
+
"step": 759
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 23.03030303030303,
|
| 464 |
+
"grad_norm": 0.4420148730278015,
|
| 465 |
+
"learning_rate": 3.272542485937369e-06,
|
| 466 |
+
"loss": 0.0424,
|
| 467 |
+
"step": 760
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 23.636363636363637,
|
| 471 |
+
"grad_norm": 0.4988000690937042,
|
| 472 |
+
"learning_rate": 3.171280681813174e-06,
|
| 473 |
+
"loss": 0.0443,
|
| 474 |
+
"step": 780
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 24.0,
|
| 478 |
+
"eval_loss": 0.02300359681248665,
|
| 479 |
+
"eval_runtime": 0.9498,
|
| 480 |
+
"eval_samples_per_second": 138.973,
|
| 481 |
+
"eval_steps_per_second": 17.898,
|
| 482 |
+
"step": 792
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 24.242424242424242,
|
| 486 |
+
"grad_norm": 0.6696539521217346,
|
| 487 |
+
"learning_rate": 3.0688173156827454e-06,
|
| 488 |
+
"loss": 0.0346,
|
| 489 |
+
"step": 800
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 24.848484848484848,
|
| 493 |
+
"grad_norm": 0.6659572720527649,
|
| 494 |
+
"learning_rate": 2.9653357923290753e-06,
|
| 495 |
+
"loss": 0.0394,
|
| 496 |
+
"step": 820
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 25.0,
|
| 500 |
+
"eval_loss": 0.02064535580575466,
|
| 501 |
+
"eval_runtime": 0.9419,
|
| 502 |
+
"eval_samples_per_second": 140.14,
|
| 503 |
+
"eval_steps_per_second": 18.048,
|
| 504 |
+
"step": 825
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 25.454545454545453,
|
| 508 |
+
"grad_norm": 0.477318674325943,
|
| 509 |
+
"learning_rate": 2.86102133899045e-06,
|
| 510 |
+
"loss": 0.0354,
|
| 511 |
+
"step": 840
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 26.0,
|
| 515 |
+
"eval_loss": 0.017997996881604195,
|
| 516 |
+
"eval_runtime": 0.9337,
|
| 517 |
+
"eval_samples_per_second": 141.375,
|
| 518 |
+
"eval_steps_per_second": 18.207,
|
| 519 |
+
"step": 858
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 26.060606060606062,
|
| 523 |
+
"grad_norm": 0.4188827574253082,
|
| 524 |
+
"learning_rate": 2.7560606738120947e-06,
|
| 525 |
+
"loss": 0.0379,
|
| 526 |
+
"step": 860
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 26.666666666666668,
|
| 530 |
+
"grad_norm": 0.37732234597206116,
|
| 531 |
+
"learning_rate": 2.6506416716291466e-06,
|
| 532 |
+
"loss": 0.0369,
|
| 533 |
+
"step": 880
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 27.0,
|
| 537 |
+
"eval_loss": 0.01666710339486599,
|
| 538 |
+
"eval_runtime": 0.9423,
|
| 539 |
+
"eval_samples_per_second": 140.084,
|
| 540 |
+
"eval_steps_per_second": 18.041,
|
| 541 |
+
"step": 891
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 27.272727272727273,
|
| 545 |
+
"grad_norm": 0.5058871507644653,
|
| 546 |
+
"learning_rate": 2.544953027679216e-06,
|
| 547 |
+
"loss": 0.0327,
|
| 548 |
+
"step": 900
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 27.87878787878788,
|
| 552 |
+
"grad_norm": 0.5595805644989014,
|
| 553 |
+
"learning_rate": 2.4391839198464613e-06,
|
| 554 |
+
"loss": 0.0338,
|
| 555 |
+
"step": 920
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 28.0,
|
| 559 |
+
"eval_loss": 0.015013493597507477,
|
| 560 |
+
"eval_runtime": 0.93,
|
| 561 |
+
"eval_samples_per_second": 141.934,
|
| 562 |
+
"eval_steps_per_second": 18.279,
|
| 563 |
+
"step": 924
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 28.484848484848484,
|
| 567 |
+
"grad_norm": 0.4609270393848419,
|
| 568 |
+
"learning_rate": 2.3335236700417404e-06,
|
| 569 |
+
"loss": 0.0306,
|
| 570 |
+
"step": 940
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 29.0,
|
| 574 |
+
"eval_loss": 0.014108900912106037,
|
| 575 |
+
"eval_runtime": 0.9248,
|
| 576 |
+
"eval_samples_per_second": 142.737,
|
| 577 |
+
"eval_steps_per_second": 18.383,
|
| 578 |
+
"step": 957
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 29.09090909090909,
|
| 582 |
+
"grad_norm": 0.3746008276939392,
|
| 583 |
+
"learning_rate": 2.2281614053249796e-06,
|
| 584 |
+
"loss": 0.0307,
|
| 585 |
+
"step": 960
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 29.696969696969695,
|
| 589 |
+
"grad_norm": 0.5330935716629028,
|
| 590 |
+
"learning_rate": 2.1232857193762923e-06,
|
| 591 |
+
"loss": 0.0298,
|
| 592 |
+
"step": 980
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 30.0,
|
| 596 |
+
"eval_loss": 0.013387720100581646,
|
| 597 |
+
"eval_runtime": 0.9587,
|
| 598 |
+
"eval_samples_per_second": 137.688,
|
| 599 |
+
"eval_steps_per_second": 17.733,
|
| 600 |
+
"step": 990
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 30.303030303030305,
|
| 604 |
+
"grad_norm": 0.31854015588760376,
|
| 605 |
+
"learning_rate": 2.019084334921849e-06,
|
| 606 |
+
"loss": 0.028,
|
| 607 |
+
"step": 1000
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 30.90909090909091,
|
| 611 |
+
"grad_norm": 0.38515424728393555,
|
| 612 |
+
"learning_rate": 1.9157437677186903e-06,
|
| 613 |
+
"loss": 0.031,
|
| 614 |
+
"step": 1020
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 31.0,
|
| 618 |
+
"eval_loss": 0.012279902584850788,
|
| 619 |
+
"eval_runtime": 0.9342,
|
| 620 |
+
"eval_samples_per_second": 141.305,
|
| 621 |
+
"eval_steps_per_second": 18.198,
|
| 622 |
+
"step": 1023
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 31.515151515151516,
|
| 626 |
+
"grad_norm": 0.45346567034721375,
|
| 627 |
+
"learning_rate": 1.8134489926999837e-06,
|
| 628 |
+
"loss": 0.033,
|
| 629 |
+
"step": 1040
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 32.0,
|
| 633 |
+
"eval_loss": 0.011261457577347755,
|
| 634 |
+
"eval_runtime": 0.9421,
|
| 635 |
+
"eval_samples_per_second": 140.119,
|
| 636 |
+
"eval_steps_per_second": 18.046,
|
| 637 |
+
"step": 1056
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 32.121212121212125,
|
| 641 |
+
"grad_norm": 0.44893690943717957,
|
| 642 |
+
"learning_rate": 1.7123831128782686e-06,
|
| 643 |
+
"loss": 0.0246,
|
| 644 |
+
"step": 1060
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 32.72727272727273,
|
| 648 |
+
"grad_norm": 0.4021283984184265,
|
| 649 |
+
"learning_rate": 1.612727031599356e-06,
|
| 650 |
+
"loss": 0.03,
|
| 651 |
+
"step": 1080
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 33.0,
|
| 655 |
+
"eval_loss": 0.010378457605838776,
|
| 656 |
+
"eval_runtime": 0.9543,
|
| 657 |
+
"eval_samples_per_second": 138.318,
|
| 658 |
+
"eval_steps_per_second": 17.814,
|
| 659 |
+
"step": 1089
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 33.333333333333336,
|
| 663 |
+
"grad_norm": 0.6586357951164246,
|
| 664 |
+
"learning_rate": 1.5146591287335452e-06,
|
| 665 |
+
"loss": 0.0266,
|
| 666 |
+
"step": 1100
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 33.93939393939394,
|
| 670 |
+
"grad_norm": 0.4133249521255493,
|
| 671 |
+
"learning_rate": 1.4183549413837288e-06,
|
| 672 |
+
"loss": 0.026,
|
| 673 |
+
"step": 1120
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 34.0,
|
| 677 |
+
"eval_loss": 0.009874224662780762,
|
| 678 |
+
"eval_runtime": 0.9426,
|
| 679 |
+
"eval_samples_per_second": 140.041,
|
| 680 |
+
"eval_steps_per_second": 18.036,
|
| 681 |
+
"step": 1122
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 34.54545454545455,
|
| 685 |
+
"grad_norm": 0.4618055522441864,
|
| 686 |
+
"learning_rate": 1.3239868496819407e-06,
|
| 687 |
+
"loss": 0.0278,
|
| 688 |
+
"step": 1140
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 35.0,
|
| 692 |
+
"eval_loss": 0.009275372140109539,
|
| 693 |
+
"eval_runtime": 0.9399,
|
| 694 |
+
"eval_samples_per_second": 140.441,
|
| 695 |
+
"eval_steps_per_second": 18.087,
|
| 696 |
+
"step": 1155
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 35.15151515151515,
|
| 700 |
+
"grad_norm": 0.3481239676475525,
|
| 701 |
+
"learning_rate": 1.2317237682367178e-06,
|
| 702 |
+
"loss": 0.0253,
|
| 703 |
+
"step": 1160
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 35.75757575757576,
|
| 707 |
+
"grad_norm": 0.42644399404525757,
|
| 708 |
+
"learning_rate": 1.1417308437836181e-06,
|
| 709 |
+
"loss": 0.0269,
|
| 710 |
+
"step": 1180
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 36.0,
|
| 714 |
+
"eval_loss": 0.008818729780614376,
|
| 715 |
+
"eval_runtime": 0.9417,
|
| 716 |
+
"eval_samples_per_second": 140.172,
|
| 717 |
+
"eval_steps_per_second": 18.052,
|
| 718 |
+
"step": 1188
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 36.36363636363637,
|
| 722 |
+
"grad_norm": 0.5186192393302917,
|
| 723 |
+
"learning_rate": 1.0541691595800338e-06,
|
| 724 |
+
"loss": 0.0231,
|
| 725 |
+
"step": 1200
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 36.96969696969697,
|
| 729 |
+
"grad_norm": 0.3892291784286499,
|
| 730 |
+
"learning_rate": 9.691954470734692e-07,
|
| 731 |
+
"loss": 0.0273,
|
| 732 |
+
"step": 1220
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 37.0,
|
| 736 |
+
"eval_loss": 0.008245617151260376,
|
| 737 |
+
"eval_runtime": 0.9541,
|
| 738 |
+
"eval_samples_per_second": 138.353,
|
| 739 |
+
"eval_steps_per_second": 17.818,
|
| 740 |
+
"step": 1221
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 37.57575757575758,
|
| 744 |
+
"grad_norm": 0.5318649411201477,
|
| 745 |
+
"learning_rate": 8.869618053593429e-07,
|
| 746 |
+
"loss": 0.0251,
|
| 747 |
+
"step": 1240
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 38.0,
|
| 751 |
+
"eval_loss": 0.007936290465295315,
|
| 752 |
+
"eval_runtime": 0.9281,
|
| 753 |
+
"eval_samples_per_second": 142.225,
|
| 754 |
+
"eval_steps_per_second": 18.317,
|
| 755 |
+
"step": 1254
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 38.18181818181818,
|
| 759 |
+
"grad_norm": 0.37824392318725586,
|
| 760 |
+
"learning_rate": 8.076154289305019e-07,
|
| 761 |
+
"loss": 0.0258,
|
| 762 |
+
"step": 1260
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 38.78787878787879,
|
| 766 |
+
"grad_norm": 0.402786523103714,
|
| 767 |
+
"learning_rate": 7.312983442057497e-07,
|
| 768 |
+
"loss": 0.0263,
|
| 769 |
+
"step": 1280
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 39.0,
|
| 773 |
+
"eval_loss": 0.007719958666712046,
|
| 774 |
+
"eval_runtime": 0.9423,
|
| 775 |
+
"eval_samples_per_second": 140.079,
|
| 776 |
+
"eval_steps_per_second": 18.041,
|
| 777 |
+
"step": 1287
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 39.39393939393939,
|
| 781 |
+
"grad_norm": 0.41106194257736206,
|
| 782 |
+
"learning_rate": 6.581471553089874e-07,
|
| 783 |
+
"loss": 0.0243,
|
| 784 |
+
"step": 1300
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 40.0,
|
| 788 |
+
"grad_norm": 0.5733346939086914,
|
| 789 |
+
"learning_rate": 5.882927995540266e-07,
|
| 790 |
+
"loss": 0.0247,
|
| 791 |
+
"step": 1320
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 40.0,
|
| 795 |
+
"eval_loss": 0.00738176517188549,
|
| 796 |
+
"eval_runtime": 0.9247,
|
| 797 |
+
"eval_samples_per_second": 142.756,
|
| 798 |
+
"eval_steps_per_second": 18.385,
|
| 799 |
+
"step": 1320
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 40.60606060606061,
|
| 803 |
+
"grad_norm": 0.3024619221687317,
|
| 804 |
+
"learning_rate": 5.218603130727243e-07,
|
| 805 |
+
"loss": 0.0243,
|
| 806 |
+
"step": 1340
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 41.0,
|
| 810 |
+
"eval_loss": 0.007284797262400389,
|
| 811 |
+
"eval_runtime": 0.9333,
|
| 812 |
+
"eval_samples_per_second": 141.426,
|
| 813 |
+
"eval_steps_per_second": 18.214,
|
| 814 |
+
"step": 1353
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 41.21212121212121,
|
| 818 |
+
"grad_norm": 0.48434221744537354,
|
| 819 |
+
"learning_rate": 4.589686070059762e-07,
|
| 820 |
+
"loss": 0.0245,
|
| 821 |
+
"step": 1360
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 41.81818181818182,
|
| 825 |
+
"grad_norm": 0.4191039204597473,
|
| 826 |
+
"learning_rate": 3.997302546581597e-07,
|
| 827 |
+
"loss": 0.0259,
|
| 828 |
+
"step": 1380
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 42.0,
|
| 832 |
+
"eval_loss": 0.007058488205075264,
|
| 833 |
+
"eval_runtime": 0.9549,
|
| 834 |
+
"eval_samples_per_second": 138.232,
|
| 835 |
+
"eval_steps_per_second": 17.803,
|
| 836 |
+
"step": 1386
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 42.42424242424242,
|
| 840 |
+
"grad_norm": 0.3011131286621094,
|
| 841 |
+
"learning_rate": 3.4425128999602265e-07,
|
| 842 |
+
"loss": 0.0234,
|
| 843 |
+
"step": 1400
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 43.0,
|
| 847 |
+
"eval_loss": 0.006919534411281347,
|
| 848 |
+
"eval_runtime": 0.9466,
|
| 849 |
+
"eval_samples_per_second": 139.447,
|
| 850 |
+
"eval_steps_per_second": 17.959,
|
| 851 |
+
"step": 1419
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 43.03030303030303,
|
| 855 |
+
"grad_norm": 0.49921727180480957,
|
| 856 |
+
"learning_rate": 2.9263101785268253e-07,
|
| 857 |
+
"loss": 0.0268,
|
| 858 |
+
"step": 1420
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 43.63636363636363,
|
| 862 |
+
"grad_norm": 0.41327381134033203,
|
| 863 |
+
"learning_rate": 2.449618361764788e-07,
|
| 864 |
+
"loss": 0.0232,
|
| 865 |
+
"step": 1440
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 44.0,
|
| 869 |
+
"eval_loss": 0.0067825643345713615,
|
| 870 |
+
"eval_runtime": 0.9457,
|
| 871 |
+
"eval_samples_per_second": 139.574,
|
| 872 |
+
"eval_steps_per_second": 17.975,
|
| 873 |
+
"step": 1452
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 44.24242424242424,
|
| 877 |
+
"grad_norm": 0.42085084319114685,
|
| 878 |
+
"learning_rate": 2.0132907064282837e-07,
|
| 879 |
+
"loss": 0.0222,
|
| 880 |
+
"step": 1460
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 44.84848484848485,
|
| 884 |
+
"grad_norm": 0.4812968075275421,
|
| 885 |
+
"learning_rate": 1.6181082192513352e-07,
|
| 886 |
+
"loss": 0.0245,
|
| 887 |
+
"step": 1480
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 45.0,
|
| 891 |
+
"eval_loss": 0.006708750035613775,
|
| 892 |
+
"eval_runtime": 0.944,
|
| 893 |
+
"eval_samples_per_second": 139.826,
|
| 894 |
+
"eval_steps_per_second": 18.008,
|
| 895 |
+
"step": 1485
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 45.45454545454545,
|
| 899 |
+
"grad_norm": 0.41410696506500244,
|
| 900 |
+
"learning_rate": 1.264778258981178e-07,
|
| 901 |
+
"loss": 0.0234,
|
| 902 |
+
"step": 1500
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 46.0,
|
| 906 |
+
"eval_loss": 0.006636774633079767,
|
| 907 |
+
"eval_runtime": 0.9246,
|
| 908 |
+
"eval_samples_per_second": 142.77,
|
| 909 |
+
"eval_steps_per_second": 18.387,
|
| 910 |
+
"step": 1518
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 46.06060606060606,
|
| 914 |
+
"grad_norm": 0.36860212683677673,
|
| 915 |
+
"learning_rate": 9.539332702381026e-08,
|
| 916 |
+
"loss": 0.0264,
|
| 917 |
+
"step": 1520
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 46.666666666666664,
|
| 921 |
+
"grad_norm": 0.3396029770374298,
|
| 922 |
+
"learning_rate": 6.86129651468273e-08,
|
| 923 |
+
"loss": 0.0229,
|
| 924 |
+
"step": 1540
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 47.0,
|
| 928 |
+
"eval_loss": 0.00661947438493371,
|
| 929 |
+
"eval_runtime": 0.9503,
|
| 930 |
+
"eval_samples_per_second": 138.905,
|
| 931 |
+
"eval_steps_per_second": 17.889,
|
| 932 |
+
"step": 1551
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 47.27272727272727,
|
| 936 |
+
"grad_norm": 0.4342035949230194,
|
| 937 |
+
"learning_rate": 4.618467590157133e-08,
|
| 938 |
+
"loss": 0.0233,
|
| 939 |
+
"step": 1560
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 47.878787878787875,
|
| 943 |
+
"grad_norm": 0.4722955822944641,
|
| 944 |
+
"learning_rate": 2.814860490961607e-08,
|
| 945 |
+
"loss": 0.0248,
|
| 946 |
+
"step": 1580
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 48.0,
|
| 950 |
+
"eval_loss": 0.006618270184844732,
|
| 951 |
+
"eval_runtime": 0.9496,
|
| 952 |
+
"eval_samples_per_second": 139.011,
|
| 953 |
+
"eval_steps_per_second": 17.903,
|
| 954 |
+
"step": 1584
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 48.484848484848484,
|
| 958 |
+
"grad_norm": 0.22162474691867828,
|
| 959 |
+
"learning_rate": 1.453703592086353e-08,
|
| 960 |
+
"loss": 0.0239,
|
| 961 |
+
"step": 1600
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 49.0,
|
| 965 |
+
"eval_loss": 0.006619932595640421,
|
| 966 |
+
"eval_runtime": 0.947,
|
| 967 |
+
"eval_samples_per_second": 139.389,
|
| 968 |
+
"eval_steps_per_second": 17.952,
|
| 969 |
+
"step": 1617
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 49.09090909090909,
|
| 973 |
+
"grad_norm": 0.4756720960140228,
|
| 974 |
+
"learning_rate": 5.374333027093892e-09,
|
| 975 |
+
"loss": 0.0236,
|
| 976 |
+
"step": 1620
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 49.696969696969695,
|
| 980 |
+
"grad_norm": 0.42004162073135376,
|
| 981 |
+
"learning_rate": 6.768970513457151e-10,
|
| 982 |
+
"loss": 0.0228,
|
| 983 |
+
"step": 1640
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 50.0,
|
| 987 |
+
"eval_loss": 0.006614842917770147,
|
| 988 |
+
"eval_runtime": 0.9549,
|
| 989 |
+
"eval_samples_per_second": 138.227,
|
| 990 |
+
"eval_steps_per_second": 17.802,
|
| 991 |
+
"step": 1650
|
| 992 |
+
}
|
| 993 |
+
],
|
| 994 |
+
"logging_steps": 20,
|
| 995 |
+
"max_steps": 1650,
|
| 996 |
+
"num_input_tokens_seen": 0,
|
| 997 |
+
"num_train_epochs": 50,
|
| 998 |
+
"save_steps": 500,
|
| 999 |
+
"stateful_callbacks": {
|
| 1000 |
+
"TrainerControl": {
|
| 1001 |
+
"args": {
|
| 1002 |
+
"should_epoch_stop": false,
|
| 1003 |
+
"should_evaluate": false,
|
| 1004 |
+
"should_log": false,
|
| 1005 |
+
"should_save": true,
|
| 1006 |
+
"should_training_stop": true
|
| 1007 |
+
},
|
| 1008 |
+
"attributes": {}
|
| 1009 |
+
}
|
| 1010 |
+
},
|
| 1011 |
+
"total_flos": 1.91340755288064e+16,
|
| 1012 |
+
"train_batch_size": 8,
|
| 1013 |
+
"trial_name": null,
|
| 1014 |
+
"trial_params": null
|
| 1015 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d6a9f13510ad980c3b2e8f4d2236425a0cc234fc6417db395095f1d6539b81c
|
| 3 |
+
size 5969
|