Upload 10 files
Browse files- config.json +32 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +125 -0
- tokenizer.json +0 -0
- tokenizer_config.json +940 -0
- trainer_state.json +1434 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"T5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"classifier_dropout": 0.0,
|
| 6 |
+
"d_ff": 2816,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 1024,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "gelu_new",
|
| 11 |
+
"dropout_rate": 0.0,
|
| 12 |
+
"eos_token_id": 1,
|
| 13 |
+
"feed_forward_proj": "gated-gelu",
|
| 14 |
+
"initializer_factor": 1.0,
|
| 15 |
+
"is_bf16": false,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": true,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "t5",
|
| 20 |
+
"num_decoder_layers": 24,
|
| 21 |
+
"num_heads": 16,
|
| 22 |
+
"num_layers": 24,
|
| 23 |
+
"output_past": true,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"relative_attention_max_distance": 128,
|
| 26 |
+
"relative_attention_num_buckets": 32,
|
| 27 |
+
"tie_word_embeddings": false,
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.52.3",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 32128
|
| 32 |
+
}
|
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": "4.52.3"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7983d95cae2c5866b730a4504709e6c7438eea3a925783c54fa373644fabf42
|
| 3 |
+
size 3132668808
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0c0cf0766bb765def9f860cce2b0fc099f350972839f5b9f0a4fe7e76ccea2e
|
| 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 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,940 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_eos_token": true,
|
| 3 |
+
"add_prefix_space": null,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<pad>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "</s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "<unk>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"3": {
|
| 30 |
+
"content": "<extra_id_0>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"4": {
|
| 38 |
+
"content": "<extra_id_1>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"5": {
|
| 46 |
+
"content": "<extra_id_2>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"6": {
|
| 54 |
+
"content": "<extra_id_3>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"7": {
|
| 62 |
+
"content": "<extra_id_4>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"8": {
|
| 70 |
+
"content": "<extra_id_5>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"9": {
|
| 78 |
+
"content": "<extra_id_6>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"10": {
|
| 86 |
+
"content": "<extra_id_7>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"11": {
|
| 94 |
+
"content": "<extra_id_8>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"12": {
|
| 102 |
+
"content": "<extra_id_9>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"13": {
|
| 110 |
+
"content": "<extra_id_10>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"14": {
|
| 118 |
+
"content": "<extra_id_11>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": true
|
| 124 |
+
},
|
| 125 |
+
"15": {
|
| 126 |
+
"content": "<extra_id_12>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": true
|
| 132 |
+
},
|
| 133 |
+
"16": {
|
| 134 |
+
"content": "<extra_id_13>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": true
|
| 140 |
+
},
|
| 141 |
+
"17": {
|
| 142 |
+
"content": "<extra_id_14>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": true
|
| 148 |
+
},
|
| 149 |
+
"18": {
|
| 150 |
+
"content": "<extra_id_15>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": true
|
| 156 |
+
},
|
| 157 |
+
"19": {
|
| 158 |
+
"content": "<extra_id_16>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": true
|
| 164 |
+
},
|
| 165 |
+
"20": {
|
| 166 |
+
"content": "<extra_id_17>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": true
|
| 172 |
+
},
|
| 173 |
+
"21": {
|
| 174 |
+
"content": "<extra_id_18>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": true
|
| 180 |
+
},
|
| 181 |
+
"22": {
|
| 182 |
+
"content": "<extra_id_19>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": true
|
| 188 |
+
},
|
| 189 |
+
"23": {
|
| 190 |
+
"content": "<extra_id_20>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": true
|
| 196 |
+
},
|
| 197 |
+
"24": {
|
| 198 |
+
"content": "<extra_id_21>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": true
|
| 204 |
+
},
|
| 205 |
+
"25": {
|
| 206 |
+
"content": "<extra_id_22>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": true
|
| 212 |
+
},
|
| 213 |
+
"26": {
|
| 214 |
+
"content": "<extra_id_23>",
|
| 215 |
+
"lstrip": false,
|
| 216 |
+
"normalized": false,
|
| 217 |
+
"rstrip": false,
|
| 218 |
+
"single_word": false,
|
| 219 |
+
"special": true
|
| 220 |
+
},
|
| 221 |
+
"27": {
|
| 222 |
+
"content": "<extra_id_24>",
|
| 223 |
+
"lstrip": false,
|
| 224 |
+
"normalized": false,
|
| 225 |
+
"rstrip": false,
|
| 226 |
+
"single_word": false,
|
| 227 |
+
"special": true
|
| 228 |
+
},
|
| 229 |
+
"28": {
|
| 230 |
+
"content": "<extra_id_25>",
|
| 231 |
+
"lstrip": false,
|
| 232 |
+
"normalized": false,
|
| 233 |
+
"rstrip": false,
|
| 234 |
+
"single_word": false,
|
| 235 |
+
"special": true
|
| 236 |
+
},
|
| 237 |
+
"29": {
|
| 238 |
+
"content": "<extra_id_26>",
|
| 239 |
+
"lstrip": false,
|
| 240 |
+
"normalized": false,
|
| 241 |
+
"rstrip": false,
|
| 242 |
+
"single_word": false,
|
| 243 |
+
"special": true
|
| 244 |
+
},
|
| 245 |
+
"30": {
|
| 246 |
+
"content": "<extra_id_27>",
|
| 247 |
+
"lstrip": false,
|
| 248 |
+
"normalized": false,
|
| 249 |
+
"rstrip": false,
|
| 250 |
+
"single_word": false,
|
| 251 |
+
"special": true
|
| 252 |
+
},
|
| 253 |
+
"31": {
|
| 254 |
+
"content": "<extra_id_28>",
|
| 255 |
+
"lstrip": false,
|
| 256 |
+
"normalized": false,
|
| 257 |
+
"rstrip": false,
|
| 258 |
+
"single_word": false,
|
| 259 |
+
"special": true
|
| 260 |
+
},
|
| 261 |
+
"32": {
|
| 262 |
+
"content": "<extra_id_29>",
|
| 263 |
+
"lstrip": false,
|
| 264 |
+
"normalized": false,
|
| 265 |
+
"rstrip": false,
|
| 266 |
+
"single_word": false,
|
| 267 |
+
"special": true
|
| 268 |
+
},
|
| 269 |
+
"33": {
|
| 270 |
+
"content": "<extra_id_30>",
|
| 271 |
+
"lstrip": false,
|
| 272 |
+
"normalized": false,
|
| 273 |
+
"rstrip": false,
|
| 274 |
+
"single_word": false,
|
| 275 |
+
"special": true
|
| 276 |
+
},
|
| 277 |
+
"34": {
|
| 278 |
+
"content": "<extra_id_31>",
|
| 279 |
+
"lstrip": false,
|
| 280 |
+
"normalized": false,
|
| 281 |
+
"rstrip": false,
|
| 282 |
+
"single_word": false,
|
| 283 |
+
"special": true
|
| 284 |
+
},
|
| 285 |
+
"35": {
|
| 286 |
+
"content": "<extra_id_32>",
|
| 287 |
+
"lstrip": false,
|
| 288 |
+
"normalized": false,
|
| 289 |
+
"rstrip": false,
|
| 290 |
+
"single_word": false,
|
| 291 |
+
"special": true
|
| 292 |
+
},
|
| 293 |
+
"36": {
|
| 294 |
+
"content": "<extra_id_33>",
|
| 295 |
+
"lstrip": false,
|
| 296 |
+
"normalized": false,
|
| 297 |
+
"rstrip": false,
|
| 298 |
+
"single_word": false,
|
| 299 |
+
"special": true
|
| 300 |
+
},
|
| 301 |
+
"37": {
|
| 302 |
+
"content": "<extra_id_34>",
|
| 303 |
+
"lstrip": false,
|
| 304 |
+
"normalized": false,
|
| 305 |
+
"rstrip": false,
|
| 306 |
+
"single_word": false,
|
| 307 |
+
"special": true
|
| 308 |
+
},
|
| 309 |
+
"38": {
|
| 310 |
+
"content": "<extra_id_35>",
|
| 311 |
+
"lstrip": false,
|
| 312 |
+
"normalized": false,
|
| 313 |
+
"rstrip": false,
|
| 314 |
+
"single_word": false,
|
| 315 |
+
"special": true
|
| 316 |
+
},
|
| 317 |
+
"39": {
|
| 318 |
+
"content": "<extra_id_36>",
|
| 319 |
+
"lstrip": false,
|
| 320 |
+
"normalized": false,
|
| 321 |
+
"rstrip": false,
|
| 322 |
+
"single_word": false,
|
| 323 |
+
"special": true
|
| 324 |
+
},
|
| 325 |
+
"40": {
|
| 326 |
+
"content": "<extra_id_37>",
|
| 327 |
+
"lstrip": false,
|
| 328 |
+
"normalized": false,
|
| 329 |
+
"rstrip": false,
|
| 330 |
+
"single_word": false,
|
| 331 |
+
"special": true
|
| 332 |
+
},
|
| 333 |
+
"41": {
|
| 334 |
+
"content": "<extra_id_38>",
|
| 335 |
+
"lstrip": false,
|
| 336 |
+
"normalized": false,
|
| 337 |
+
"rstrip": false,
|
| 338 |
+
"single_word": false,
|
| 339 |
+
"special": true
|
| 340 |
+
},
|
| 341 |
+
"42": {
|
| 342 |
+
"content": "<extra_id_39>",
|
| 343 |
+
"lstrip": false,
|
| 344 |
+
"normalized": false,
|
| 345 |
+
"rstrip": false,
|
| 346 |
+
"single_word": false,
|
| 347 |
+
"special": true
|
| 348 |
+
},
|
| 349 |
+
"43": {
|
| 350 |
+
"content": "<extra_id_40>",
|
| 351 |
+
"lstrip": false,
|
| 352 |
+
"normalized": false,
|
| 353 |
+
"rstrip": false,
|
| 354 |
+
"single_word": false,
|
| 355 |
+
"special": true
|
| 356 |
+
},
|
| 357 |
+
"44": {
|
| 358 |
+
"content": "<extra_id_41>",
|
| 359 |
+
"lstrip": false,
|
| 360 |
+
"normalized": false,
|
| 361 |
+
"rstrip": false,
|
| 362 |
+
"single_word": false,
|
| 363 |
+
"special": true
|
| 364 |
+
},
|
| 365 |
+
"45": {
|
| 366 |
+
"content": "<extra_id_42>",
|
| 367 |
+
"lstrip": false,
|
| 368 |
+
"normalized": false,
|
| 369 |
+
"rstrip": false,
|
| 370 |
+
"single_word": false,
|
| 371 |
+
"special": true
|
| 372 |
+
},
|
| 373 |
+
"46": {
|
| 374 |
+
"content": "<extra_id_43>",
|
| 375 |
+
"lstrip": false,
|
| 376 |
+
"normalized": false,
|
| 377 |
+
"rstrip": false,
|
| 378 |
+
"single_word": false,
|
| 379 |
+
"special": true
|
| 380 |
+
},
|
| 381 |
+
"47": {
|
| 382 |
+
"content": "<extra_id_44>",
|
| 383 |
+
"lstrip": false,
|
| 384 |
+
"normalized": false,
|
| 385 |
+
"rstrip": false,
|
| 386 |
+
"single_word": false,
|
| 387 |
+
"special": true
|
| 388 |
+
},
|
| 389 |
+
"48": {
|
| 390 |
+
"content": "<extra_id_45>",
|
| 391 |
+
"lstrip": false,
|
| 392 |
+
"normalized": false,
|
| 393 |
+
"rstrip": false,
|
| 394 |
+
"single_word": false,
|
| 395 |
+
"special": true
|
| 396 |
+
},
|
| 397 |
+
"49": {
|
| 398 |
+
"content": "<extra_id_46>",
|
| 399 |
+
"lstrip": false,
|
| 400 |
+
"normalized": false,
|
| 401 |
+
"rstrip": false,
|
| 402 |
+
"single_word": false,
|
| 403 |
+
"special": true
|
| 404 |
+
},
|
| 405 |
+
"50": {
|
| 406 |
+
"content": "<extra_id_47>",
|
| 407 |
+
"lstrip": false,
|
| 408 |
+
"normalized": false,
|
| 409 |
+
"rstrip": false,
|
| 410 |
+
"single_word": false,
|
| 411 |
+
"special": true
|
| 412 |
+
},
|
| 413 |
+
"51": {
|
| 414 |
+
"content": "<extra_id_48>",
|
| 415 |
+
"lstrip": false,
|
| 416 |
+
"normalized": false,
|
| 417 |
+
"rstrip": false,
|
| 418 |
+
"single_word": false,
|
| 419 |
+
"special": true
|
| 420 |
+
},
|
| 421 |
+
"52": {
|
| 422 |
+
"content": "<extra_id_49>",
|
| 423 |
+
"lstrip": false,
|
| 424 |
+
"normalized": false,
|
| 425 |
+
"rstrip": false,
|
| 426 |
+
"single_word": false,
|
| 427 |
+
"special": true
|
| 428 |
+
},
|
| 429 |
+
"53": {
|
| 430 |
+
"content": "<extra_id_50>",
|
| 431 |
+
"lstrip": false,
|
| 432 |
+
"normalized": false,
|
| 433 |
+
"rstrip": false,
|
| 434 |
+
"single_word": false,
|
| 435 |
+
"special": true
|
| 436 |
+
},
|
| 437 |
+
"54": {
|
| 438 |
+
"content": "<extra_id_51>",
|
| 439 |
+
"lstrip": false,
|
| 440 |
+
"normalized": false,
|
| 441 |
+
"rstrip": false,
|
| 442 |
+
"single_word": false,
|
| 443 |
+
"special": true
|
| 444 |
+
},
|
| 445 |
+
"55": {
|
| 446 |
+
"content": "<extra_id_52>",
|
| 447 |
+
"lstrip": false,
|
| 448 |
+
"normalized": false,
|
| 449 |
+
"rstrip": false,
|
| 450 |
+
"single_word": false,
|
| 451 |
+
"special": true
|
| 452 |
+
},
|
| 453 |
+
"56": {
|
| 454 |
+
"content": "<extra_id_53>",
|
| 455 |
+
"lstrip": false,
|
| 456 |
+
"normalized": false,
|
| 457 |
+
"rstrip": false,
|
| 458 |
+
"single_word": false,
|
| 459 |
+
"special": true
|
| 460 |
+
},
|
| 461 |
+
"57": {
|
| 462 |
+
"content": "<extra_id_54>",
|
| 463 |
+
"lstrip": false,
|
| 464 |
+
"normalized": false,
|
| 465 |
+
"rstrip": false,
|
| 466 |
+
"single_word": false,
|
| 467 |
+
"special": true
|
| 468 |
+
},
|
| 469 |
+
"58": {
|
| 470 |
+
"content": "<extra_id_55>",
|
| 471 |
+
"lstrip": false,
|
| 472 |
+
"normalized": false,
|
| 473 |
+
"rstrip": false,
|
| 474 |
+
"single_word": false,
|
| 475 |
+
"special": true
|
| 476 |
+
},
|
| 477 |
+
"59": {
|
| 478 |
+
"content": "<extra_id_56>",
|
| 479 |
+
"lstrip": false,
|
| 480 |
+
"normalized": false,
|
| 481 |
+
"rstrip": false,
|
| 482 |
+
"single_word": false,
|
| 483 |
+
"special": true
|
| 484 |
+
},
|
| 485 |
+
"60": {
|
| 486 |
+
"content": "<extra_id_57>",
|
| 487 |
+
"lstrip": false,
|
| 488 |
+
"normalized": false,
|
| 489 |
+
"rstrip": false,
|
| 490 |
+
"single_word": false,
|
| 491 |
+
"special": true
|
| 492 |
+
},
|
| 493 |
+
"61": {
|
| 494 |
+
"content": "<extra_id_58>",
|
| 495 |
+
"lstrip": false,
|
| 496 |
+
"normalized": false,
|
| 497 |
+
"rstrip": false,
|
| 498 |
+
"single_word": false,
|
| 499 |
+
"special": true
|
| 500 |
+
},
|
| 501 |
+
"62": {
|
| 502 |
+
"content": "<extra_id_59>",
|
| 503 |
+
"lstrip": false,
|
| 504 |
+
"normalized": false,
|
| 505 |
+
"rstrip": false,
|
| 506 |
+
"single_word": false,
|
| 507 |
+
"special": true
|
| 508 |
+
},
|
| 509 |
+
"63": {
|
| 510 |
+
"content": "<extra_id_60>",
|
| 511 |
+
"lstrip": false,
|
| 512 |
+
"normalized": false,
|
| 513 |
+
"rstrip": false,
|
| 514 |
+
"single_word": false,
|
| 515 |
+
"special": true
|
| 516 |
+
},
|
| 517 |
+
"64": {
|
| 518 |
+
"content": "<extra_id_61>",
|
| 519 |
+
"lstrip": false,
|
| 520 |
+
"normalized": false,
|
| 521 |
+
"rstrip": false,
|
| 522 |
+
"single_word": false,
|
| 523 |
+
"special": true
|
| 524 |
+
},
|
| 525 |
+
"65": {
|
| 526 |
+
"content": "<extra_id_62>",
|
| 527 |
+
"lstrip": false,
|
| 528 |
+
"normalized": false,
|
| 529 |
+
"rstrip": false,
|
| 530 |
+
"single_word": false,
|
| 531 |
+
"special": true
|
| 532 |
+
},
|
| 533 |
+
"66": {
|
| 534 |
+
"content": "<extra_id_63>",
|
| 535 |
+
"lstrip": false,
|
| 536 |
+
"normalized": false,
|
| 537 |
+
"rstrip": false,
|
| 538 |
+
"single_word": false,
|
| 539 |
+
"special": true
|
| 540 |
+
},
|
| 541 |
+
"67": {
|
| 542 |
+
"content": "<extra_id_64>",
|
| 543 |
+
"lstrip": false,
|
| 544 |
+
"normalized": false,
|
| 545 |
+
"rstrip": false,
|
| 546 |
+
"single_word": false,
|
| 547 |
+
"special": true
|
| 548 |
+
},
|
| 549 |
+
"68": {
|
| 550 |
+
"content": "<extra_id_65>",
|
| 551 |
+
"lstrip": false,
|
| 552 |
+
"normalized": false,
|
| 553 |
+
"rstrip": false,
|
| 554 |
+
"single_word": false,
|
| 555 |
+
"special": true
|
| 556 |
+
},
|
| 557 |
+
"69": {
|
| 558 |
+
"content": "<extra_id_66>",
|
| 559 |
+
"lstrip": false,
|
| 560 |
+
"normalized": false,
|
| 561 |
+
"rstrip": false,
|
| 562 |
+
"single_word": false,
|
| 563 |
+
"special": true
|
| 564 |
+
},
|
| 565 |
+
"70": {
|
| 566 |
+
"content": "<extra_id_67>",
|
| 567 |
+
"lstrip": false,
|
| 568 |
+
"normalized": false,
|
| 569 |
+
"rstrip": false,
|
| 570 |
+
"single_word": false,
|
| 571 |
+
"special": true
|
| 572 |
+
},
|
| 573 |
+
"71": {
|
| 574 |
+
"content": "<extra_id_68>",
|
| 575 |
+
"lstrip": false,
|
| 576 |
+
"normalized": false,
|
| 577 |
+
"rstrip": false,
|
| 578 |
+
"single_word": false,
|
| 579 |
+
"special": true
|
| 580 |
+
},
|
| 581 |
+
"72": {
|
| 582 |
+
"content": "<extra_id_69>",
|
| 583 |
+
"lstrip": false,
|
| 584 |
+
"normalized": false,
|
| 585 |
+
"rstrip": false,
|
| 586 |
+
"single_word": false,
|
| 587 |
+
"special": true
|
| 588 |
+
},
|
| 589 |
+
"73": {
|
| 590 |
+
"content": "<extra_id_70>",
|
| 591 |
+
"lstrip": false,
|
| 592 |
+
"normalized": false,
|
| 593 |
+
"rstrip": false,
|
| 594 |
+
"single_word": false,
|
| 595 |
+
"special": true
|
| 596 |
+
},
|
| 597 |
+
"74": {
|
| 598 |
+
"content": "<extra_id_71>",
|
| 599 |
+
"lstrip": false,
|
| 600 |
+
"normalized": false,
|
| 601 |
+
"rstrip": false,
|
| 602 |
+
"single_word": false,
|
| 603 |
+
"special": true
|
| 604 |
+
},
|
| 605 |
+
"75": {
|
| 606 |
+
"content": "<extra_id_72>",
|
| 607 |
+
"lstrip": false,
|
| 608 |
+
"normalized": false,
|
| 609 |
+
"rstrip": false,
|
| 610 |
+
"single_word": false,
|
| 611 |
+
"special": true
|
| 612 |
+
},
|
| 613 |
+
"76": {
|
| 614 |
+
"content": "<extra_id_73>",
|
| 615 |
+
"lstrip": false,
|
| 616 |
+
"normalized": false,
|
| 617 |
+
"rstrip": false,
|
| 618 |
+
"single_word": false,
|
| 619 |
+
"special": true
|
| 620 |
+
},
|
| 621 |
+
"77": {
|
| 622 |
+
"content": "<extra_id_74>",
|
| 623 |
+
"lstrip": false,
|
| 624 |
+
"normalized": false,
|
| 625 |
+
"rstrip": false,
|
| 626 |
+
"single_word": false,
|
| 627 |
+
"special": true
|
| 628 |
+
},
|
| 629 |
+
"78": {
|
| 630 |
+
"content": "<extra_id_75>",
|
| 631 |
+
"lstrip": false,
|
| 632 |
+
"normalized": false,
|
| 633 |
+
"rstrip": false,
|
| 634 |
+
"single_word": false,
|
| 635 |
+
"special": true
|
| 636 |
+
},
|
| 637 |
+
"79": {
|
| 638 |
+
"content": "<extra_id_76>",
|
| 639 |
+
"lstrip": false,
|
| 640 |
+
"normalized": false,
|
| 641 |
+
"rstrip": false,
|
| 642 |
+
"single_word": false,
|
| 643 |
+
"special": true
|
| 644 |
+
},
|
| 645 |
+
"80": {
|
| 646 |
+
"content": "<extra_id_77>",
|
| 647 |
+
"lstrip": false,
|
| 648 |
+
"normalized": false,
|
| 649 |
+
"rstrip": false,
|
| 650 |
+
"single_word": false,
|
| 651 |
+
"special": true
|
| 652 |
+
},
|
| 653 |
+
"81": {
|
| 654 |
+
"content": "<extra_id_78>",
|
| 655 |
+
"lstrip": false,
|
| 656 |
+
"normalized": false,
|
| 657 |
+
"rstrip": false,
|
| 658 |
+
"single_word": false,
|
| 659 |
+
"special": true
|
| 660 |
+
},
|
| 661 |
+
"82": {
|
| 662 |
+
"content": "<extra_id_79>",
|
| 663 |
+
"lstrip": false,
|
| 664 |
+
"normalized": false,
|
| 665 |
+
"rstrip": false,
|
| 666 |
+
"single_word": false,
|
| 667 |
+
"special": true
|
| 668 |
+
},
|
| 669 |
+
"83": {
|
| 670 |
+
"content": "<extra_id_80>",
|
| 671 |
+
"lstrip": false,
|
| 672 |
+
"normalized": false,
|
| 673 |
+
"rstrip": false,
|
| 674 |
+
"single_word": false,
|
| 675 |
+
"special": true
|
| 676 |
+
},
|
| 677 |
+
"84": {
|
| 678 |
+
"content": "<extra_id_81>",
|
| 679 |
+
"lstrip": false,
|
| 680 |
+
"normalized": false,
|
| 681 |
+
"rstrip": false,
|
| 682 |
+
"single_word": false,
|
| 683 |
+
"special": true
|
| 684 |
+
},
|
| 685 |
+
"85": {
|
| 686 |
+
"content": "<extra_id_82>",
|
| 687 |
+
"lstrip": false,
|
| 688 |
+
"normalized": false,
|
| 689 |
+
"rstrip": false,
|
| 690 |
+
"single_word": false,
|
| 691 |
+
"special": true
|
| 692 |
+
},
|
| 693 |
+
"86": {
|
| 694 |
+
"content": "<extra_id_83>",
|
| 695 |
+
"lstrip": false,
|
| 696 |
+
"normalized": false,
|
| 697 |
+
"rstrip": false,
|
| 698 |
+
"single_word": false,
|
| 699 |
+
"special": true
|
| 700 |
+
},
|
| 701 |
+
"87": {
|
| 702 |
+
"content": "<extra_id_84>",
|
| 703 |
+
"lstrip": false,
|
| 704 |
+
"normalized": false,
|
| 705 |
+
"rstrip": false,
|
| 706 |
+
"single_word": false,
|
| 707 |
+
"special": true
|
| 708 |
+
},
|
| 709 |
+
"88": {
|
| 710 |
+
"content": "<extra_id_85>",
|
| 711 |
+
"lstrip": false,
|
| 712 |
+
"normalized": false,
|
| 713 |
+
"rstrip": false,
|
| 714 |
+
"single_word": false,
|
| 715 |
+
"special": true
|
| 716 |
+
},
|
| 717 |
+
"89": {
|
| 718 |
+
"content": "<extra_id_86>",
|
| 719 |
+
"lstrip": false,
|
| 720 |
+
"normalized": false,
|
| 721 |
+
"rstrip": false,
|
| 722 |
+
"single_word": false,
|
| 723 |
+
"special": true
|
| 724 |
+
},
|
| 725 |
+
"90": {
|
| 726 |
+
"content": "<extra_id_87>",
|
| 727 |
+
"lstrip": false,
|
| 728 |
+
"normalized": false,
|
| 729 |
+
"rstrip": false,
|
| 730 |
+
"single_word": false,
|
| 731 |
+
"special": true
|
| 732 |
+
},
|
| 733 |
+
"91": {
|
| 734 |
+
"content": "<extra_id_88>",
|
| 735 |
+
"lstrip": false,
|
| 736 |
+
"normalized": false,
|
| 737 |
+
"rstrip": false,
|
| 738 |
+
"single_word": false,
|
| 739 |
+
"special": true
|
| 740 |
+
},
|
| 741 |
+
"92": {
|
| 742 |
+
"content": "<extra_id_89>",
|
| 743 |
+
"lstrip": false,
|
| 744 |
+
"normalized": false,
|
| 745 |
+
"rstrip": false,
|
| 746 |
+
"single_word": false,
|
| 747 |
+
"special": true
|
| 748 |
+
},
|
| 749 |
+
"93": {
|
| 750 |
+
"content": "<extra_id_90>",
|
| 751 |
+
"lstrip": false,
|
| 752 |
+
"normalized": false,
|
| 753 |
+
"rstrip": false,
|
| 754 |
+
"single_word": false,
|
| 755 |
+
"special": true
|
| 756 |
+
},
|
| 757 |
+
"94": {
|
| 758 |
+
"content": "<extra_id_91>",
|
| 759 |
+
"lstrip": false,
|
| 760 |
+
"normalized": false,
|
| 761 |
+
"rstrip": false,
|
| 762 |
+
"single_word": false,
|
| 763 |
+
"special": true
|
| 764 |
+
},
|
| 765 |
+
"95": {
|
| 766 |
+
"content": "<extra_id_92>",
|
| 767 |
+
"lstrip": false,
|
| 768 |
+
"normalized": false,
|
| 769 |
+
"rstrip": false,
|
| 770 |
+
"single_word": false,
|
| 771 |
+
"special": true
|
| 772 |
+
},
|
| 773 |
+
"96": {
|
| 774 |
+
"content": "<extra_id_93>",
|
| 775 |
+
"lstrip": false,
|
| 776 |
+
"normalized": false,
|
| 777 |
+
"rstrip": false,
|
| 778 |
+
"single_word": false,
|
| 779 |
+
"special": true
|
| 780 |
+
},
|
| 781 |
+
"97": {
|
| 782 |
+
"content": "<extra_id_94>",
|
| 783 |
+
"lstrip": false,
|
| 784 |
+
"normalized": false,
|
| 785 |
+
"rstrip": false,
|
| 786 |
+
"single_word": false,
|
| 787 |
+
"special": true
|
| 788 |
+
},
|
| 789 |
+
"98": {
|
| 790 |
+
"content": "<extra_id_95>",
|
| 791 |
+
"lstrip": false,
|
| 792 |
+
"normalized": false,
|
| 793 |
+
"rstrip": false,
|
| 794 |
+
"single_word": false,
|
| 795 |
+
"special": true
|
| 796 |
+
},
|
| 797 |
+
"99": {
|
| 798 |
+
"content": "<extra_id_96>",
|
| 799 |
+
"lstrip": false,
|
| 800 |
+
"normalized": false,
|
| 801 |
+
"rstrip": false,
|
| 802 |
+
"single_word": false,
|
| 803 |
+
"special": true
|
| 804 |
+
},
|
| 805 |
+
"100": {
|
| 806 |
+
"content": "<extra_id_97>",
|
| 807 |
+
"lstrip": false,
|
| 808 |
+
"normalized": false,
|
| 809 |
+
"rstrip": false,
|
| 810 |
+
"single_word": false,
|
| 811 |
+
"special": true
|
| 812 |
+
},
|
| 813 |
+
"101": {
|
| 814 |
+
"content": "<extra_id_98>",
|
| 815 |
+
"lstrip": false,
|
| 816 |
+
"normalized": false,
|
| 817 |
+
"rstrip": false,
|
| 818 |
+
"single_word": false,
|
| 819 |
+
"special": true
|
| 820 |
+
},
|
| 821 |
+
"102": {
|
| 822 |
+
"content": "<extra_id_99>",
|
| 823 |
+
"lstrip": false,
|
| 824 |
+
"normalized": false,
|
| 825 |
+
"rstrip": false,
|
| 826 |
+
"single_word": false,
|
| 827 |
+
"special": true
|
| 828 |
+
}
|
| 829 |
+
},
|
| 830 |
+
"additional_special_tokens": [
|
| 831 |
+
"<extra_id_0>",
|
| 832 |
+
"<extra_id_1>",
|
| 833 |
+
"<extra_id_2>",
|
| 834 |
+
"<extra_id_3>",
|
| 835 |
+
"<extra_id_4>",
|
| 836 |
+
"<extra_id_5>",
|
| 837 |
+
"<extra_id_6>",
|
| 838 |
+
"<extra_id_7>",
|
| 839 |
+
"<extra_id_8>",
|
| 840 |
+
"<extra_id_9>",
|
| 841 |
+
"<extra_id_10>",
|
| 842 |
+
"<extra_id_11>",
|
| 843 |
+
"<extra_id_12>",
|
| 844 |
+
"<extra_id_13>",
|
| 845 |
+
"<extra_id_14>",
|
| 846 |
+
"<extra_id_15>",
|
| 847 |
+
"<extra_id_16>",
|
| 848 |
+
"<extra_id_17>",
|
| 849 |
+
"<extra_id_18>",
|
| 850 |
+
"<extra_id_19>",
|
| 851 |
+
"<extra_id_20>",
|
| 852 |
+
"<extra_id_21>",
|
| 853 |
+
"<extra_id_22>",
|
| 854 |
+
"<extra_id_23>",
|
| 855 |
+
"<extra_id_24>",
|
| 856 |
+
"<extra_id_25>",
|
| 857 |
+
"<extra_id_26>",
|
| 858 |
+
"<extra_id_27>",
|
| 859 |
+
"<extra_id_28>",
|
| 860 |
+
"<extra_id_29>",
|
| 861 |
+
"<extra_id_30>",
|
| 862 |
+
"<extra_id_31>",
|
| 863 |
+
"<extra_id_32>",
|
| 864 |
+
"<extra_id_33>",
|
| 865 |
+
"<extra_id_34>",
|
| 866 |
+
"<extra_id_35>",
|
| 867 |
+
"<extra_id_36>",
|
| 868 |
+
"<extra_id_37>",
|
| 869 |
+
"<extra_id_38>",
|
| 870 |
+
"<extra_id_39>",
|
| 871 |
+
"<extra_id_40>",
|
| 872 |
+
"<extra_id_41>",
|
| 873 |
+
"<extra_id_42>",
|
| 874 |
+
"<extra_id_43>",
|
| 875 |
+
"<extra_id_44>",
|
| 876 |
+
"<extra_id_45>",
|
| 877 |
+
"<extra_id_46>",
|
| 878 |
+
"<extra_id_47>",
|
| 879 |
+
"<extra_id_48>",
|
| 880 |
+
"<extra_id_49>",
|
| 881 |
+
"<extra_id_50>",
|
| 882 |
+
"<extra_id_51>",
|
| 883 |
+
"<extra_id_52>",
|
| 884 |
+
"<extra_id_53>",
|
| 885 |
+
"<extra_id_54>",
|
| 886 |
+
"<extra_id_55>",
|
| 887 |
+
"<extra_id_56>",
|
| 888 |
+
"<extra_id_57>",
|
| 889 |
+
"<extra_id_58>",
|
| 890 |
+
"<extra_id_59>",
|
| 891 |
+
"<extra_id_60>",
|
| 892 |
+
"<extra_id_61>",
|
| 893 |
+
"<extra_id_62>",
|
| 894 |
+
"<extra_id_63>",
|
| 895 |
+
"<extra_id_64>",
|
| 896 |
+
"<extra_id_65>",
|
| 897 |
+
"<extra_id_66>",
|
| 898 |
+
"<extra_id_67>",
|
| 899 |
+
"<extra_id_68>",
|
| 900 |
+
"<extra_id_69>",
|
| 901 |
+
"<extra_id_70>",
|
| 902 |
+
"<extra_id_71>",
|
| 903 |
+
"<extra_id_72>",
|
| 904 |
+
"<extra_id_73>",
|
| 905 |
+
"<extra_id_74>",
|
| 906 |
+
"<extra_id_75>",
|
| 907 |
+
"<extra_id_76>",
|
| 908 |
+
"<extra_id_77>",
|
| 909 |
+
"<extra_id_78>",
|
| 910 |
+
"<extra_id_79>",
|
| 911 |
+
"<extra_id_80>",
|
| 912 |
+
"<extra_id_81>",
|
| 913 |
+
"<extra_id_82>",
|
| 914 |
+
"<extra_id_83>",
|
| 915 |
+
"<extra_id_84>",
|
| 916 |
+
"<extra_id_85>",
|
| 917 |
+
"<extra_id_86>",
|
| 918 |
+
"<extra_id_87>",
|
| 919 |
+
"<extra_id_88>",
|
| 920 |
+
"<extra_id_89>",
|
| 921 |
+
"<extra_id_90>",
|
| 922 |
+
"<extra_id_91>",
|
| 923 |
+
"<extra_id_92>",
|
| 924 |
+
"<extra_id_93>",
|
| 925 |
+
"<extra_id_94>",
|
| 926 |
+
"<extra_id_95>",
|
| 927 |
+
"<extra_id_96>",
|
| 928 |
+
"<extra_id_97>",
|
| 929 |
+
"<extra_id_98>",
|
| 930 |
+
"<extra_id_99>"
|
| 931 |
+
],
|
| 932 |
+
"clean_up_tokenization_spaces": false,
|
| 933 |
+
"eos_token": "</s>",
|
| 934 |
+
"extra_ids": 100,
|
| 935 |
+
"extra_special_tokens": {},
|
| 936 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 937 |
+
"pad_token": "<pad>",
|
| 938 |
+
"tokenizer_class": "T5TokenizerFast",
|
| 939 |
+
"unk_token": "<unk>"
|
| 940 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1434 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.0046453183320519995,
|
| 6 |
+
"eval_steps": 2000,
|
| 7 |
+
"global_step": 2000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 2.3226591660259998e-05,
|
| 14 |
+
"grad_norm": 0.43654176592826843,
|
| 15 |
+
"learning_rate": 0.0009999930320225019,
|
| 16 |
+
"loss": 1.0703,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 4.6453183320519996e-05,
|
| 21 |
+
"grad_norm": 0.29478368163108826,
|
| 22 |
+
"learning_rate": 0.0009999852898252817,
|
| 23 |
+
"loss": 1.1726,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 6.967977498078e-05,
|
| 28 |
+
"grad_norm": 0.30410653352737427,
|
| 29 |
+
"learning_rate": 0.0009999775476280618,
|
| 30 |
+
"loss": 1.106,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 9.290636664103999e-05,
|
| 35 |
+
"grad_norm": 0.3648824989795685,
|
| 36 |
+
"learning_rate": 0.0009999698054308417,
|
| 37 |
+
"loss": 1.1939,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.00011613295830129999,
|
| 42 |
+
"grad_norm": 0.430895060300827,
|
| 43 |
+
"learning_rate": 0.0009999620632336215,
|
| 44 |
+
"loss": 1.2002,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.00013935954996156,
|
| 49 |
+
"grad_norm": 0.3720713257789612,
|
| 50 |
+
"learning_rate": 0.0009999543210364014,
|
| 51 |
+
"loss": 1.0248,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.00016258614162182,
|
| 56 |
+
"grad_norm": 0.354899138212204,
|
| 57 |
+
"learning_rate": 0.0009999465788391815,
|
| 58 |
+
"loss": 1.1271,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.00018581273328207998,
|
| 63 |
+
"grad_norm": 0.35504820942878723,
|
| 64 |
+
"learning_rate": 0.0009999388366419614,
|
| 65 |
+
"loss": 1.1396,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.00020903932494234,
|
| 70 |
+
"grad_norm": 0.4521724581718445,
|
| 71 |
+
"learning_rate": 0.0009999310944447412,
|
| 72 |
+
"loss": 1.1032,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.00023226591660259997,
|
| 77 |
+
"grad_norm": 0.2742864787578583,
|
| 78 |
+
"learning_rate": 0.000999923352247521,
|
| 79 |
+
"loss": 1.1479,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.00025549250826286,
|
| 84 |
+
"grad_norm": 0.41575589776039124,
|
| 85 |
+
"learning_rate": 0.0009999156100503012,
|
| 86 |
+
"loss": 1.1837,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.00027871909992312,
|
| 91 |
+
"grad_norm": 0.27715566754341125,
|
| 92 |
+
"learning_rate": 0.000999907867853081,
|
| 93 |
+
"loss": 1.1597,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.00030194569158338,
|
| 98 |
+
"grad_norm": 0.4537408649921417,
|
| 99 |
+
"learning_rate": 0.000999900125655861,
|
| 100 |
+
"loss": 1.1183,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.00032517228324364,
|
| 105 |
+
"grad_norm": 0.2952319383621216,
|
| 106 |
+
"learning_rate": 0.0009998923834586408,
|
| 107 |
+
"loss": 1.1501,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.00034839887490389996,
|
| 112 |
+
"grad_norm": 0.38295623660087585,
|
| 113 |
+
"learning_rate": 0.0009998846412614208,
|
| 114 |
+
"loss": 1.1381,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.00037162546656415997,
|
| 119 |
+
"grad_norm": 0.3845287561416626,
|
| 120 |
+
"learning_rate": 0.0009998768990642007,
|
| 121 |
+
"loss": 1.0968,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.00039485205822442,
|
| 126 |
+
"grad_norm": 0.25896570086479187,
|
| 127 |
+
"learning_rate": 0.0009998691568669806,
|
| 128 |
+
"loss": 1.0684,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.00041807864988468,
|
| 133 |
+
"grad_norm": 0.2440153807401657,
|
| 134 |
+
"learning_rate": 0.0009998614146697604,
|
| 135 |
+
"loss": 1.1281,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.00044130524154494,
|
| 140 |
+
"grad_norm": 0.3060740530490875,
|
| 141 |
+
"learning_rate": 0.0009998536724725403,
|
| 142 |
+
"loss": 1.1285,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.00046453183320519995,
|
| 147 |
+
"grad_norm": 0.2703372538089752,
|
| 148 |
+
"learning_rate": 0.0009998459302753204,
|
| 149 |
+
"loss": 1.2085,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.00048775842486545995,
|
| 154 |
+
"grad_norm": 0.3993639647960663,
|
| 155 |
+
"learning_rate": 0.0009998381880781003,
|
| 156 |
+
"loss": 1.2365,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.00051098501652572,
|
| 161 |
+
"grad_norm": 0.41694164276123047,
|
| 162 |
+
"learning_rate": 0.0009998304458808801,
|
| 163 |
+
"loss": 1.161,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.0005342116081859799,
|
| 168 |
+
"grad_norm": 0.2720717191696167,
|
| 169 |
+
"learning_rate": 0.00099982270368366,
|
| 170 |
+
"loss": 1.0553,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.00055743819984624,
|
| 175 |
+
"grad_norm": 0.3238905072212219,
|
| 176 |
+
"learning_rate": 0.0009998149614864399,
|
| 177 |
+
"loss": 1.0825,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.0005806647915064999,
|
| 182 |
+
"grad_norm": 0.39301878213882446,
|
| 183 |
+
"learning_rate": 0.00099980721928922,
|
| 184 |
+
"loss": 1.1421,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.00060389138316676,
|
| 189 |
+
"grad_norm": 0.25302958488464355,
|
| 190 |
+
"learning_rate": 0.0009997994770919998,
|
| 191 |
+
"loss": 1.0533,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.00062711797482702,
|
| 196 |
+
"grad_norm": 0.29384830594062805,
|
| 197 |
+
"learning_rate": 0.0009997917348947797,
|
| 198 |
+
"loss": 1.1011,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.00065034456648728,
|
| 203 |
+
"grad_norm": 0.35217076539993286,
|
| 204 |
+
"learning_rate": 0.0009997839926975595,
|
| 205 |
+
"loss": 1.0289,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.00067357115814754,
|
| 210 |
+
"grad_norm": 0.3412124216556549,
|
| 211 |
+
"learning_rate": 0.0009997762505003394,
|
| 212 |
+
"loss": 1.0974,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.0006967977498077999,
|
| 217 |
+
"grad_norm": 0.2988780736923218,
|
| 218 |
+
"learning_rate": 0.0009997685083031195,
|
| 219 |
+
"loss": 1.1618,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.00072002434146806,
|
| 224 |
+
"grad_norm": 0.43221724033355713,
|
| 225 |
+
"learning_rate": 0.0009997607661058994,
|
| 226 |
+
"loss": 1.1023,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.0007432509331283199,
|
| 231 |
+
"grad_norm": 0.2644006013870239,
|
| 232 |
+
"learning_rate": 0.0009997530239086792,
|
| 233 |
+
"loss": 1.1548,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.00076647752478858,
|
| 238 |
+
"grad_norm": 0.2950528860092163,
|
| 239 |
+
"learning_rate": 0.000999745281711459,
|
| 240 |
+
"loss": 1.1203,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.00078970411644884,
|
| 245 |
+
"grad_norm": 0.20538517832756042,
|
| 246 |
+
"learning_rate": 0.0009997375395142392,
|
| 247 |
+
"loss": 1.0904,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.0008129307081090999,
|
| 252 |
+
"grad_norm": 0.3531719446182251,
|
| 253 |
+
"learning_rate": 0.000999729797317019,
|
| 254 |
+
"loss": 1.0951,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.00083615729976936,
|
| 259 |
+
"grad_norm": 0.3661258816719055,
|
| 260 |
+
"learning_rate": 0.000999722055119799,
|
| 261 |
+
"loss": 1.0885,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.0008593838914296199,
|
| 266 |
+
"grad_norm": 0.4355231523513794,
|
| 267 |
+
"learning_rate": 0.0009997143129225788,
|
| 268 |
+
"loss": 1.1301,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.00088261048308988,
|
| 273 |
+
"grad_norm": 0.3286990225315094,
|
| 274 |
+
"learning_rate": 0.0009997065707253588,
|
| 275 |
+
"loss": 1.0705,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.0009058370747501399,
|
| 280 |
+
"grad_norm": 0.31140822172164917,
|
| 281 |
+
"learning_rate": 0.0009996988285281387,
|
| 282 |
+
"loss": 1.1873,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.0009290636664103999,
|
| 287 |
+
"grad_norm": 0.2582302689552307,
|
| 288 |
+
"learning_rate": 0.0009996910863309186,
|
| 289 |
+
"loss": 1.1567,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.00095229025807066,
|
| 294 |
+
"grad_norm": 0.36799147725105286,
|
| 295 |
+
"learning_rate": 0.0009996833441336984,
|
| 296 |
+
"loss": 1.2273,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.0009755168497309199,
|
| 301 |
+
"grad_norm": 0.28618550300598145,
|
| 302 |
+
"learning_rate": 0.0009996756019364785,
|
| 303 |
+
"loss": 1.0851,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.00099874344139118,
|
| 308 |
+
"grad_norm": 0.3006650507450104,
|
| 309 |
+
"learning_rate": 0.0009996678597392584,
|
| 310 |
+
"loss": 1.0341,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.00102197003305144,
|
| 315 |
+
"grad_norm": 0.3651888072490692,
|
| 316 |
+
"learning_rate": 0.0009996601175420383,
|
| 317 |
+
"loss": 1.0212,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.0010451966247116999,
|
| 322 |
+
"grad_norm": 0.32596904039382935,
|
| 323 |
+
"learning_rate": 0.0009996523753448181,
|
| 324 |
+
"loss": 1.0919,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.0010684232163719598,
|
| 329 |
+
"grad_norm": 0.30658453702926636,
|
| 330 |
+
"learning_rate": 0.000999644633147598,
|
| 331 |
+
"loss": 1.0934,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.00109164980803222,
|
| 336 |
+
"grad_norm": 0.49543142318725586,
|
| 337 |
+
"learning_rate": 0.0009996368909503779,
|
| 338 |
+
"loss": 1.1603,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.00111487639969248,
|
| 343 |
+
"grad_norm": 0.24394716322422028,
|
| 344 |
+
"learning_rate": 0.000999629148753158,
|
| 345 |
+
"loss": 1.1455,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.00113810299135274,
|
| 350 |
+
"grad_norm": 0.38373667001724243,
|
| 351 |
+
"learning_rate": 0.0009996214065559378,
|
| 352 |
+
"loss": 1.1498,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.0011613295830129999,
|
| 357 |
+
"grad_norm": 0.5020566582679749,
|
| 358 |
+
"learning_rate": 0.0009996136643587177,
|
| 359 |
+
"loss": 1.076,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.0011845561746732598,
|
| 364 |
+
"grad_norm": 0.3413016200065613,
|
| 365 |
+
"learning_rate": 0.0009996059221614975,
|
| 366 |
+
"loss": 1.1747,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.00120778276633352,
|
| 371 |
+
"grad_norm": 0.3450530171394348,
|
| 372 |
+
"learning_rate": 0.0009995981799642774,
|
| 373 |
+
"loss": 1.1441,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.00123100935799378,
|
| 378 |
+
"grad_norm": 0.3582036793231964,
|
| 379 |
+
"learning_rate": 0.0009995904377670575,
|
| 380 |
+
"loss": 1.1679,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.00125423594965404,
|
| 385 |
+
"grad_norm": 0.30296868085861206,
|
| 386 |
+
"learning_rate": 0.0009995826955698373,
|
| 387 |
+
"loss": 1.0446,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.0012774625413142999,
|
| 392 |
+
"grad_norm": 0.3772015869617462,
|
| 393 |
+
"learning_rate": 0.0009995749533726172,
|
| 394 |
+
"loss": 1.1239,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.00130068913297456,
|
| 399 |
+
"grad_norm": 0.3441556692123413,
|
| 400 |
+
"learning_rate": 0.000999567211175397,
|
| 401 |
+
"loss": 1.112,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.00132391572463482,
|
| 406 |
+
"grad_norm": 0.3211918771266937,
|
| 407 |
+
"learning_rate": 0.0009995594689781772,
|
| 408 |
+
"loss": 1.1344,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.00134714231629508,
|
| 413 |
+
"grad_norm": 0.2808244824409485,
|
| 414 |
+
"learning_rate": 0.000999551726780957,
|
| 415 |
+
"loss": 1.1398,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.0013703689079553399,
|
| 420 |
+
"grad_norm": 0.32571667432785034,
|
| 421 |
+
"learning_rate": 0.000999543984583737,
|
| 422 |
+
"loss": 1.1455,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.0013935954996155998,
|
| 427 |
+
"grad_norm": 0.3554767668247223,
|
| 428 |
+
"learning_rate": 0.0009995362423865168,
|
| 429 |
+
"loss": 0.991,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.00141682209127586,
|
| 434 |
+
"grad_norm": 0.253456711769104,
|
| 435 |
+
"learning_rate": 0.0009995285001892968,
|
| 436 |
+
"loss": 1.1686,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.00144004868293612,
|
| 441 |
+
"grad_norm": 0.31393057107925415,
|
| 442 |
+
"learning_rate": 0.0009995207579920767,
|
| 443 |
+
"loss": 1.1034,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.00146327527459638,
|
| 448 |
+
"grad_norm": 0.3797680735588074,
|
| 449 |
+
"learning_rate": 0.0009995130157948566,
|
| 450 |
+
"loss": 1.1224,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.0014865018662566399,
|
| 455 |
+
"grad_norm": 0.3667146563529968,
|
| 456 |
+
"learning_rate": 0.0009995052735976364,
|
| 457 |
+
"loss": 1.1484,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.0015097284579168998,
|
| 462 |
+
"grad_norm": 0.28348517417907715,
|
| 463 |
+
"learning_rate": 0.0009994975314004165,
|
| 464 |
+
"loss": 1.2004,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.00153295504957716,
|
| 469 |
+
"grad_norm": 0.4176248610019684,
|
| 470 |
+
"learning_rate": 0.0009994897892031964,
|
| 471 |
+
"loss": 1.1415,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.00155618164123742,
|
| 476 |
+
"grad_norm": 0.3170236647129059,
|
| 477 |
+
"learning_rate": 0.0009994820470059763,
|
| 478 |
+
"loss": 1.0853,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.00157940823289768,
|
| 483 |
+
"grad_norm": 0.31185317039489746,
|
| 484 |
+
"learning_rate": 0.0009994743048087561,
|
| 485 |
+
"loss": 1.1353,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.0016026348245579399,
|
| 490 |
+
"grad_norm": 0.33214762806892395,
|
| 491 |
+
"learning_rate": 0.000999466562611536,
|
| 492 |
+
"loss": 1.1504,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.0016258614162181998,
|
| 497 |
+
"grad_norm": 0.3761586844921112,
|
| 498 |
+
"learning_rate": 0.000999458820414316,
|
| 499 |
+
"loss": 1.0549,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.00164908800787846,
|
| 504 |
+
"grad_norm": 0.2806662619113922,
|
| 505 |
+
"learning_rate": 0.000999451078217096,
|
| 506 |
+
"loss": 1.1859,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.00167231459953872,
|
| 511 |
+
"grad_norm": 0.39696329832077026,
|
| 512 |
+
"learning_rate": 0.0009994433360198758,
|
| 513 |
+
"loss": 1.1716,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.0016955411911989799,
|
| 518 |
+
"grad_norm": 0.28009161353111267,
|
| 519 |
+
"learning_rate": 0.0009994355938226557,
|
| 520 |
+
"loss": 1.1932,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.0017187677828592398,
|
| 525 |
+
"grad_norm": 0.2747149169445038,
|
| 526 |
+
"learning_rate": 0.0009994278516254355,
|
| 527 |
+
"loss": 1.0847,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.0017419943745194998,
|
| 532 |
+
"grad_norm": 0.30023542046546936,
|
| 533 |
+
"learning_rate": 0.0009994201094282154,
|
| 534 |
+
"loss": 1.0696,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.00176522096617976,
|
| 539 |
+
"grad_norm": 0.3453909158706665,
|
| 540 |
+
"learning_rate": 0.0009994123672309955,
|
| 541 |
+
"loss": 1.0967,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.00178844755784002,
|
| 546 |
+
"grad_norm": 0.49272191524505615,
|
| 547 |
+
"learning_rate": 0.0009994046250337753,
|
| 548 |
+
"loss": 1.0573,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.0018116741495002799,
|
| 553 |
+
"grad_norm": 0.2652382254600525,
|
| 554 |
+
"learning_rate": 0.0009993968828365552,
|
| 555 |
+
"loss": 1.1404,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.0018349007411605398,
|
| 560 |
+
"grad_norm": 0.25675663352012634,
|
| 561 |
+
"learning_rate": 0.000999389140639335,
|
| 562 |
+
"loss": 1.0459,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.0018581273328207998,
|
| 567 |
+
"grad_norm": 0.3685920834541321,
|
| 568 |
+
"learning_rate": 0.0009993813984421152,
|
| 569 |
+
"loss": 1.0117,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.00188135392448106,
|
| 574 |
+
"grad_norm": 0.3216955363750458,
|
| 575 |
+
"learning_rate": 0.000999373656244895,
|
| 576 |
+
"loss": 1.1672,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.00190458051614132,
|
| 581 |
+
"grad_norm": 0.4081834852695465,
|
| 582 |
+
"learning_rate": 0.000999365914047675,
|
| 583 |
+
"loss": 1.1555,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.0019278071078015799,
|
| 588 |
+
"grad_norm": 0.3144775927066803,
|
| 589 |
+
"learning_rate": 0.0009993581718504548,
|
| 590 |
+
"loss": 1.2002,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.0019510336994618398,
|
| 595 |
+
"grad_norm": 0.3642594814300537,
|
| 596 |
+
"learning_rate": 0.0009993504296532348,
|
| 597 |
+
"loss": 1.0547,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.0019742602911220998,
|
| 602 |
+
"grad_norm": 0.3856127858161926,
|
| 603 |
+
"learning_rate": 0.0009993426874560147,
|
| 604 |
+
"loss": 1.2028,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.00199748688278236,
|
| 609 |
+
"grad_norm": 0.41429170966148376,
|
| 610 |
+
"learning_rate": 0.0009993349452587946,
|
| 611 |
+
"loss": 1.0857,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.0020207134744426197,
|
| 616 |
+
"grad_norm": 0.4278993606567383,
|
| 617 |
+
"learning_rate": 0.0009993272030615744,
|
| 618 |
+
"loss": 1.0574,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.00204394006610288,
|
| 623 |
+
"grad_norm": 0.26868101954460144,
|
| 624 |
+
"learning_rate": 0.0009993194608643545,
|
| 625 |
+
"loss": 1.0538,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.00206716665776314,
|
| 630 |
+
"grad_norm": 0.8726014494895935,
|
| 631 |
+
"learning_rate": 0.0009993117186671344,
|
| 632 |
+
"loss": 1.2263,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.0020903932494233998,
|
| 637 |
+
"grad_norm": 0.39568719267845154,
|
| 638 |
+
"learning_rate": 0.0009993039764699143,
|
| 639 |
+
"loss": 1.1606,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.00211361984108366,
|
| 644 |
+
"grad_norm": 0.3933831751346588,
|
| 645 |
+
"learning_rate": 0.0009992962342726941,
|
| 646 |
+
"loss": 1.1263,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.0021368464327439197,
|
| 651 |
+
"grad_norm": 0.4326261579990387,
|
| 652 |
+
"learning_rate": 0.000999288492075474,
|
| 653 |
+
"loss": 1.0729,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.00216007302440418,
|
| 658 |
+
"grad_norm": 0.3416406810283661,
|
| 659 |
+
"learning_rate": 0.000999280749878254,
|
| 660 |
+
"loss": 1.1538,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.00218329961606444,
|
| 665 |
+
"grad_norm": 0.338379830121994,
|
| 666 |
+
"learning_rate": 0.000999273007681034,
|
| 667 |
+
"loss": 1.0347,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.0022065262077246997,
|
| 672 |
+
"grad_norm": 0.34776318073272705,
|
| 673 |
+
"learning_rate": 0.0009992652654838138,
|
| 674 |
+
"loss": 1.1322,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.00222975279938496,
|
| 679 |
+
"grad_norm": 0.23187178373336792,
|
| 680 |
+
"learning_rate": 0.0009992575232865937,
|
| 681 |
+
"loss": 1.0574,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.0022529793910452196,
|
| 686 |
+
"grad_norm": 0.3015563189983368,
|
| 687 |
+
"learning_rate": 0.0009992497810893735,
|
| 688 |
+
"loss": 1.0911,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.00227620598270548,
|
| 693 |
+
"grad_norm": 0.31411874294281006,
|
| 694 |
+
"learning_rate": 0.0009992420388921534,
|
| 695 |
+
"loss": 1.1008,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.00229943257436574,
|
| 700 |
+
"grad_norm": 0.4988269805908203,
|
| 701 |
+
"learning_rate": 0.0009992342966949335,
|
| 702 |
+
"loss": 1.1292,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.0023226591660259997,
|
| 707 |
+
"grad_norm": 0.3398004472255707,
|
| 708 |
+
"learning_rate": 0.0009992265544977133,
|
| 709 |
+
"loss": 1.1665,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.00234588575768626,
|
| 714 |
+
"grad_norm": 0.32879185676574707,
|
| 715 |
+
"learning_rate": 0.0009992188123004932,
|
| 716 |
+
"loss": 1.1131,
|
| 717 |
+
"step": 1010
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.0023691123493465196,
|
| 721 |
+
"grad_norm": 0.40583041310310364,
|
| 722 |
+
"learning_rate": 0.000999211070103273,
|
| 723 |
+
"loss": 1.0571,
|
| 724 |
+
"step": 1020
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.00239233894100678,
|
| 728 |
+
"grad_norm": 0.3514922559261322,
|
| 729 |
+
"learning_rate": 0.0009992033279060532,
|
| 730 |
+
"loss": 1.1166,
|
| 731 |
+
"step": 1030
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.00241556553266704,
|
| 735 |
+
"grad_norm": 1.3851335048675537,
|
| 736 |
+
"learning_rate": 0.000999195585708833,
|
| 737 |
+
"loss": 1.0532,
|
| 738 |
+
"step": 1040
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.0024387921243272997,
|
| 742 |
+
"grad_norm": 0.5054768919944763,
|
| 743 |
+
"learning_rate": 0.000999187843511613,
|
| 744 |
+
"loss": 1.16,
|
| 745 |
+
"step": 1050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.00246201871598756,
|
| 749 |
+
"grad_norm": 0.37074124813079834,
|
| 750 |
+
"learning_rate": 0.0009991801013143928,
|
| 751 |
+
"loss": 1.2028,
|
| 752 |
+
"step": 1060
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.0024852453076478196,
|
| 756 |
+
"grad_norm": 0.3337225615978241,
|
| 757 |
+
"learning_rate": 0.0009991723591171728,
|
| 758 |
+
"loss": 1.1109,
|
| 759 |
+
"step": 1070
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.00250847189930808,
|
| 763 |
+
"grad_norm": 0.283372163772583,
|
| 764 |
+
"learning_rate": 0.0009991646169199527,
|
| 765 |
+
"loss": 1.063,
|
| 766 |
+
"step": 1080
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.00253169849096834,
|
| 770 |
+
"grad_norm": 0.3113659620285034,
|
| 771 |
+
"learning_rate": 0.0009991568747227326,
|
| 772 |
+
"loss": 1.1027,
|
| 773 |
+
"step": 1090
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.0025549250826285997,
|
| 777 |
+
"grad_norm": 0.43556565046310425,
|
| 778 |
+
"learning_rate": 0.0009991491325255124,
|
| 779 |
+
"loss": 1.1181,
|
| 780 |
+
"step": 1100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.00257815167428886,
|
| 784 |
+
"grad_norm": 0.3736826479434967,
|
| 785 |
+
"learning_rate": 0.0009991413903282925,
|
| 786 |
+
"loss": 1.1035,
|
| 787 |
+
"step": 1110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.00260137826594912,
|
| 791 |
+
"grad_norm": 0.3376559913158417,
|
| 792 |
+
"learning_rate": 0.0009991336481310724,
|
| 793 |
+
"loss": 1.0149,
|
| 794 |
+
"step": 1120
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.0026246048576093798,
|
| 798 |
+
"grad_norm": 0.3545368015766144,
|
| 799 |
+
"learning_rate": 0.0009991259059338523,
|
| 800 |
+
"loss": 1.1472,
|
| 801 |
+
"step": 1130
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.00264783144926964,
|
| 805 |
+
"grad_norm": 0.2400045394897461,
|
| 806 |
+
"learning_rate": 0.0009991181637366321,
|
| 807 |
+
"loss": 1.1423,
|
| 808 |
+
"step": 1140
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.0026710580409298997,
|
| 812 |
+
"grad_norm": 0.37132346630096436,
|
| 813 |
+
"learning_rate": 0.0009991104215394122,
|
| 814 |
+
"loss": 1.1802,
|
| 815 |
+
"step": 1150
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.00269428463259016,
|
| 819 |
+
"grad_norm": 0.26770955324172974,
|
| 820 |
+
"learning_rate": 0.000999102679342192,
|
| 821 |
+
"loss": 1.0859,
|
| 822 |
+
"step": 1160
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.00271751122425042,
|
| 826 |
+
"grad_norm": 0.3567134439945221,
|
| 827 |
+
"learning_rate": 0.000999094937144972,
|
| 828 |
+
"loss": 1.1699,
|
| 829 |
+
"step": 1170
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.0027407378159106798,
|
| 833 |
+
"grad_norm": 0.3370940387248993,
|
| 834 |
+
"learning_rate": 0.0009990871949477518,
|
| 835 |
+
"loss": 1.2679,
|
| 836 |
+
"step": 1180
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.00276396440757094,
|
| 840 |
+
"grad_norm": 0.3533010184764862,
|
| 841 |
+
"learning_rate": 0.0009990794527505317,
|
| 842 |
+
"loss": 1.1444,
|
| 843 |
+
"step": 1190
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.0027871909992311997,
|
| 847 |
+
"grad_norm": 0.227728933095932,
|
| 848 |
+
"learning_rate": 0.0009990717105533115,
|
| 849 |
+
"loss": 1.1105,
|
| 850 |
+
"step": 1200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.00281041759089146,
|
| 854 |
+
"grad_norm": 0.39945659041404724,
|
| 855 |
+
"learning_rate": 0.0009990639683560916,
|
| 856 |
+
"loss": 1.0122,
|
| 857 |
+
"step": 1210
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.00283364418255172,
|
| 861 |
+
"grad_norm": 0.38961905241012573,
|
| 862 |
+
"learning_rate": 0.0009990562261588715,
|
| 863 |
+
"loss": 1.1677,
|
| 864 |
+
"step": 1220
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.0028568707742119798,
|
| 868 |
+
"grad_norm": 0.35965076088905334,
|
| 869 |
+
"learning_rate": 0.0009990484839616513,
|
| 870 |
+
"loss": 1.2045,
|
| 871 |
+
"step": 1230
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.00288009736587224,
|
| 875 |
+
"grad_norm": 0.3876691460609436,
|
| 876 |
+
"learning_rate": 0.0009990407417644312,
|
| 877 |
+
"loss": 1.1577,
|
| 878 |
+
"step": 1240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.0029033239575324997,
|
| 882 |
+
"grad_norm": 0.3059842586517334,
|
| 883 |
+
"learning_rate": 0.000999032999567211,
|
| 884 |
+
"loss": 1.1294,
|
| 885 |
+
"step": 1250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.00292655054919276,
|
| 889 |
+
"grad_norm": 0.31481969356536865,
|
| 890 |
+
"learning_rate": 0.0009990252573699912,
|
| 891 |
+
"loss": 1.1202,
|
| 892 |
+
"step": 1260
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.00294977714085302,
|
| 896 |
+
"grad_norm": 0.3077446222305298,
|
| 897 |
+
"learning_rate": 0.000999017515172771,
|
| 898 |
+
"loss": 1.0893,
|
| 899 |
+
"step": 1270
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.0029730037325132797,
|
| 903 |
+
"grad_norm": 0.30285683274269104,
|
| 904 |
+
"learning_rate": 0.000999009772975551,
|
| 905 |
+
"loss": 1.0844,
|
| 906 |
+
"step": 1280
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.00299623032417354,
|
| 910 |
+
"grad_norm": 0.32145956158638,
|
| 911 |
+
"learning_rate": 0.0009990020307783308,
|
| 912 |
+
"loss": 1.1524,
|
| 913 |
+
"step": 1290
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.0030194569158337996,
|
| 917 |
+
"grad_norm": 0.3908081352710724,
|
| 918 |
+
"learning_rate": 0.0009989942885811108,
|
| 919 |
+
"loss": 1.104,
|
| 920 |
+
"step": 1300
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.00304268350749406,
|
| 924 |
+
"grad_norm": 0.32902881503105164,
|
| 925 |
+
"learning_rate": 0.0009989865463838907,
|
| 926 |
+
"loss": 1.1161,
|
| 927 |
+
"step": 1310
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.00306591009915432,
|
| 931 |
+
"grad_norm": 0.3777260184288025,
|
| 932 |
+
"learning_rate": 0.0009989788041866706,
|
| 933 |
+
"loss": 1.1623,
|
| 934 |
+
"step": 1320
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.0030891366908145797,
|
| 938 |
+
"grad_norm": 0.4204845130443573,
|
| 939 |
+
"learning_rate": 0.0009989710619894504,
|
| 940 |
+
"loss": 1.1284,
|
| 941 |
+
"step": 1330
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.00311236328247484,
|
| 945 |
+
"grad_norm": 0.3189554810523987,
|
| 946 |
+
"learning_rate": 0.0009989633197922305,
|
| 947 |
+
"loss": 1.104,
|
| 948 |
+
"step": 1340
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.0031355898741350996,
|
| 952 |
+
"grad_norm": 0.30896514654159546,
|
| 953 |
+
"learning_rate": 0.0009989555775950104,
|
| 954 |
+
"loss": 1.1221,
|
| 955 |
+
"step": 1350
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.00315881646579536,
|
| 959 |
+
"grad_norm": 1.2486257553100586,
|
| 960 |
+
"learning_rate": 0.0009989478353977903,
|
| 961 |
+
"loss": 1.2578,
|
| 962 |
+
"step": 1360
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.00318204305745562,
|
| 966 |
+
"grad_norm": 0.433830201625824,
|
| 967 |
+
"learning_rate": 0.0009989400932005701,
|
| 968 |
+
"loss": 1.101,
|
| 969 |
+
"step": 1370
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.0032052696491158797,
|
| 973 |
+
"grad_norm": 0.3873724341392517,
|
| 974 |
+
"learning_rate": 0.0009989323510033502,
|
| 975 |
+
"loss": 1.1509,
|
| 976 |
+
"step": 1380
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.00322849624077614,
|
| 980 |
+
"grad_norm": 0.238771453499794,
|
| 981 |
+
"learning_rate": 0.00099892460880613,
|
| 982 |
+
"loss": 1.171,
|
| 983 |
+
"step": 1390
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.0032517228324363996,
|
| 987 |
+
"grad_norm": 0.3480624258518219,
|
| 988 |
+
"learning_rate": 0.00099891686660891,
|
| 989 |
+
"loss": 1.2122,
|
| 990 |
+
"step": 1400
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.00327494942409666,
|
| 994 |
+
"grad_norm": 0.35760608315467834,
|
| 995 |
+
"learning_rate": 0.0009989091244116898,
|
| 996 |
+
"loss": 1.0479,
|
| 997 |
+
"step": 1410
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.00329817601575692,
|
| 1001 |
+
"grad_norm": 0.3133438527584076,
|
| 1002 |
+
"learning_rate": 0.0009989013822144697,
|
| 1003 |
+
"loss": 1.1176,
|
| 1004 |
+
"step": 1420
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.0033214026074171797,
|
| 1008 |
+
"grad_norm": 0.2956129014492035,
|
| 1009 |
+
"learning_rate": 0.0009988936400172495,
|
| 1010 |
+
"loss": 1.12,
|
| 1011 |
+
"step": 1430
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.00334462919907744,
|
| 1015 |
+
"grad_norm": 0.2697290778160095,
|
| 1016 |
+
"learning_rate": 0.0009988858978200296,
|
| 1017 |
+
"loss": 1.0247,
|
| 1018 |
+
"step": 1440
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.0033678557907376996,
|
| 1022 |
+
"grad_norm": 0.34495481848716736,
|
| 1023 |
+
"learning_rate": 0.0009988781556228095,
|
| 1024 |
+
"loss": 1.0775,
|
| 1025 |
+
"step": 1450
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.0033910823823979598,
|
| 1029 |
+
"grad_norm": 0.29800111055374146,
|
| 1030 |
+
"learning_rate": 0.0009988704134255893,
|
| 1031 |
+
"loss": 1.1489,
|
| 1032 |
+
"step": 1460
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.00341430897405822,
|
| 1036 |
+
"grad_norm": 0.29650014638900757,
|
| 1037 |
+
"learning_rate": 0.0009988626712283692,
|
| 1038 |
+
"loss": 1.0565,
|
| 1039 |
+
"step": 1470
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.0034375355657184797,
|
| 1043 |
+
"grad_norm": 0.35248780250549316,
|
| 1044 |
+
"learning_rate": 0.000998854929031149,
|
| 1045 |
+
"loss": 1.1121,
|
| 1046 |
+
"step": 1480
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.00346076215737874,
|
| 1050 |
+
"grad_norm": 0.2716731131076813,
|
| 1051 |
+
"learning_rate": 0.0009988471868339292,
|
| 1052 |
+
"loss": 1.0923,
|
| 1053 |
+
"step": 1490
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.0034839887490389996,
|
| 1057 |
+
"grad_norm": 0.4371800422668457,
|
| 1058 |
+
"learning_rate": 0.000998839444636709,
|
| 1059 |
+
"loss": 1.0155,
|
| 1060 |
+
"step": 1500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.0035072153406992598,
|
| 1064 |
+
"grad_norm": 0.2633199691772461,
|
| 1065 |
+
"learning_rate": 0.0009988317024394889,
|
| 1066 |
+
"loss": 1.1037,
|
| 1067 |
+
"step": 1510
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.00353044193235952,
|
| 1071 |
+
"grad_norm": 0.2944166362285614,
|
| 1072 |
+
"learning_rate": 0.0009988239602422688,
|
| 1073 |
+
"loss": 1.0995,
|
| 1074 |
+
"step": 1520
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.0035536685240197797,
|
| 1078 |
+
"grad_norm": 0.2786024212837219,
|
| 1079 |
+
"learning_rate": 0.0009988162180450488,
|
| 1080 |
+
"loss": 1.0641,
|
| 1081 |
+
"step": 1530
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.00357689511568004,
|
| 1085 |
+
"grad_norm": 0.31116756796836853,
|
| 1086 |
+
"learning_rate": 0.0009988084758478287,
|
| 1087 |
+
"loss": 1.1015,
|
| 1088 |
+
"step": 1540
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.0036001217073402996,
|
| 1092 |
+
"grad_norm": 0.31829699873924255,
|
| 1093 |
+
"learning_rate": 0.0009988007336506086,
|
| 1094 |
+
"loss": 1.0519,
|
| 1095 |
+
"step": 1550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.0036233482990005597,
|
| 1099 |
+
"grad_norm": 0.4150811433792114,
|
| 1100 |
+
"learning_rate": 0.0009987929914533884,
|
| 1101 |
+
"loss": 1.1509,
|
| 1102 |
+
"step": 1560
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.00364657489066082,
|
| 1106 |
+
"grad_norm": 0.2690746784210205,
|
| 1107 |
+
"learning_rate": 0.0009987852492561685,
|
| 1108 |
+
"loss": 1.0517,
|
| 1109 |
+
"step": 1570
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.0036698014823210797,
|
| 1113 |
+
"grad_norm": 0.3126815855503082,
|
| 1114 |
+
"learning_rate": 0.0009987775070589484,
|
| 1115 |
+
"loss": 1.1398,
|
| 1116 |
+
"step": 1580
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.00369302807398134,
|
| 1120 |
+
"grad_norm": 0.34572452306747437,
|
| 1121 |
+
"learning_rate": 0.0009987697648617283,
|
| 1122 |
+
"loss": 1.0342,
|
| 1123 |
+
"step": 1590
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.0037162546656415996,
|
| 1127 |
+
"grad_norm": 0.30171483755111694,
|
| 1128 |
+
"learning_rate": 0.0009987620226645081,
|
| 1129 |
+
"loss": 1.0517,
|
| 1130 |
+
"step": 1600
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.0037394812573018597,
|
| 1134 |
+
"grad_norm": 0.2483634054660797,
|
| 1135 |
+
"learning_rate": 0.0009987542804672882,
|
| 1136 |
+
"loss": 1.1146,
|
| 1137 |
+
"step": 1610
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.00376270784896212,
|
| 1141 |
+
"grad_norm": 0.41606566309928894,
|
| 1142 |
+
"learning_rate": 0.000998746538270068,
|
| 1143 |
+
"loss": 1.0997,
|
| 1144 |
+
"step": 1620
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.0037859344406223796,
|
| 1148 |
+
"grad_norm": 0.3014843761920929,
|
| 1149 |
+
"learning_rate": 0.000998738796072848,
|
| 1150 |
+
"loss": 1.0975,
|
| 1151 |
+
"step": 1630
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.00380916103228264,
|
| 1155 |
+
"grad_norm": 0.31974515318870544,
|
| 1156 |
+
"learning_rate": 0.0009987310538756278,
|
| 1157 |
+
"loss": 1.0963,
|
| 1158 |
+
"step": 1640
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.0038323876239428996,
|
| 1162 |
+
"grad_norm": 0.3185972273349762,
|
| 1163 |
+
"learning_rate": 0.0009987233116784077,
|
| 1164 |
+
"loss": 1.1598,
|
| 1165 |
+
"step": 1650
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.0038556142156031597,
|
| 1169 |
+
"grad_norm": 0.3430216908454895,
|
| 1170 |
+
"learning_rate": 0.0009987155694811877,
|
| 1171 |
+
"loss": 0.9476,
|
| 1172 |
+
"step": 1660
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.00387884080726342,
|
| 1176 |
+
"grad_norm": 0.4456688165664673,
|
| 1177 |
+
"learning_rate": 0.0009987078272839676,
|
| 1178 |
+
"loss": 1.1319,
|
| 1179 |
+
"step": 1670
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.0039020673989236796,
|
| 1183 |
+
"grad_norm": 0.4243941605091095,
|
| 1184 |
+
"learning_rate": 0.0009987000850867475,
|
| 1185 |
+
"loss": 1.1765,
|
| 1186 |
+
"step": 1680
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.003925293990583939,
|
| 1190 |
+
"grad_norm": 0.22148986160755157,
|
| 1191 |
+
"learning_rate": 0.0009986923428895273,
|
| 1192 |
+
"loss": 1.1305,
|
| 1193 |
+
"step": 1690
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.0039485205822441995,
|
| 1197 |
+
"grad_norm": 0.44649383425712585,
|
| 1198 |
+
"learning_rate": 0.0009986846006923072,
|
| 1199 |
+
"loss": 1.1282,
|
| 1200 |
+
"step": 1700
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.00397174717390446,
|
| 1204 |
+
"grad_norm": 0.35965171456336975,
|
| 1205 |
+
"learning_rate": 0.000998676858495087,
|
| 1206 |
+
"loss": 1.0997,
|
| 1207 |
+
"step": 1710
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.00399497376556472,
|
| 1211 |
+
"grad_norm": 0.4147953987121582,
|
| 1212 |
+
"learning_rate": 0.0009986691162978672,
|
| 1213 |
+
"loss": 1.0682,
|
| 1214 |
+
"step": 1720
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.00401820035722498,
|
| 1218 |
+
"grad_norm": 0.47538864612579346,
|
| 1219 |
+
"learning_rate": 0.000998661374100647,
|
| 1220 |
+
"loss": 1.1625,
|
| 1221 |
+
"step": 1730
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.004041426948885239,
|
| 1225 |
+
"grad_norm": 0.3181823194026947,
|
| 1226 |
+
"learning_rate": 0.0009986536319034269,
|
| 1227 |
+
"loss": 1.1683,
|
| 1228 |
+
"step": 1740
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.0040646535405454995,
|
| 1232 |
+
"grad_norm": 0.32929712533950806,
|
| 1233 |
+
"learning_rate": 0.0009986458897062068,
|
| 1234 |
+
"loss": 1.1306,
|
| 1235 |
+
"step": 1750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.00408788013220576,
|
| 1239 |
+
"grad_norm": 0.34377196431159973,
|
| 1240 |
+
"learning_rate": 0.0009986381475089868,
|
| 1241 |
+
"loss": 1.1267,
|
| 1242 |
+
"step": 1760
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.00411110672386602,
|
| 1246 |
+
"grad_norm": 0.3156042695045471,
|
| 1247 |
+
"learning_rate": 0.0009986304053117667,
|
| 1248 |
+
"loss": 1.0523,
|
| 1249 |
+
"step": 1770
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.00413433331552628,
|
| 1253 |
+
"grad_norm": 0.35088011622428894,
|
| 1254 |
+
"learning_rate": 0.0009986226631145466,
|
| 1255 |
+
"loss": 1.0075,
|
| 1256 |
+
"step": 1780
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.004157559907186539,
|
| 1260 |
+
"grad_norm": 0.3740438222885132,
|
| 1261 |
+
"learning_rate": 0.0009986149209173264,
|
| 1262 |
+
"loss": 1.1788,
|
| 1263 |
+
"step": 1790
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.0041807864988467995,
|
| 1267 |
+
"grad_norm": 0.28393882513046265,
|
| 1268 |
+
"learning_rate": 0.0009986071787201065,
|
| 1269 |
+
"loss": 1.0374,
|
| 1270 |
+
"step": 1800
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.00420401309050706,
|
| 1274 |
+
"grad_norm": 0.2916342318058014,
|
| 1275 |
+
"learning_rate": 0.0009985994365228864,
|
| 1276 |
+
"loss": 1.0783,
|
| 1277 |
+
"step": 1810
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.00422723968216732,
|
| 1281 |
+
"grad_norm": 0.3398910462856293,
|
| 1282 |
+
"learning_rate": 0.0009985916943256663,
|
| 1283 |
+
"loss": 1.129,
|
| 1284 |
+
"step": 1820
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.00425046627382758,
|
| 1288 |
+
"grad_norm": 0.3244156837463379,
|
| 1289 |
+
"learning_rate": 0.0009985839521284461,
|
| 1290 |
+
"loss": 1.1812,
|
| 1291 |
+
"step": 1830
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.004273692865487839,
|
| 1295 |
+
"grad_norm": 0.5498040318489075,
|
| 1296 |
+
"learning_rate": 0.0009985762099312262,
|
| 1297 |
+
"loss": 1.1812,
|
| 1298 |
+
"step": 1840
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.0042969194571480995,
|
| 1302 |
+
"grad_norm": 0.27574270963668823,
|
| 1303 |
+
"learning_rate": 0.000998568467734006,
|
| 1304 |
+
"loss": 1.1414,
|
| 1305 |
+
"step": 1850
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.00432014604880836,
|
| 1309 |
+
"grad_norm": 0.3610564172267914,
|
| 1310 |
+
"learning_rate": 0.000998560725536786,
|
| 1311 |
+
"loss": 1.0763,
|
| 1312 |
+
"step": 1860
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.00434337264046862,
|
| 1316 |
+
"grad_norm": 0.33828043937683105,
|
| 1317 |
+
"learning_rate": 0.0009985529833395658,
|
| 1318 |
+
"loss": 1.0169,
|
| 1319 |
+
"step": 1870
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.00436659923212888,
|
| 1323 |
+
"grad_norm": 0.22078180313110352,
|
| 1324 |
+
"learning_rate": 0.0009985452411423457,
|
| 1325 |
+
"loss": 1.0513,
|
| 1326 |
+
"step": 1880
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.004389825823789139,
|
| 1330 |
+
"grad_norm": 0.4355666935443878,
|
| 1331 |
+
"learning_rate": 0.0009985374989451257,
|
| 1332 |
+
"loss": 1.1245,
|
| 1333 |
+
"step": 1890
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.0044130524154493995,
|
| 1337 |
+
"grad_norm": 0.3071712851524353,
|
| 1338 |
+
"learning_rate": 0.0009985297567479056,
|
| 1339 |
+
"loss": 1.1669,
|
| 1340 |
+
"step": 1900
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.00443627900710966,
|
| 1344 |
+
"grad_norm": 0.3043074905872345,
|
| 1345 |
+
"learning_rate": 0.0009985220145506855,
|
| 1346 |
+
"loss": 1.1917,
|
| 1347 |
+
"step": 1910
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.00445950559876992,
|
| 1351 |
+
"grad_norm": 0.33084383606910706,
|
| 1352 |
+
"learning_rate": 0.0009985142723534653,
|
| 1353 |
+
"loss": 1.0819,
|
| 1354 |
+
"step": 1920
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.00448273219043018,
|
| 1358 |
+
"grad_norm": 0.32064658403396606,
|
| 1359 |
+
"learning_rate": 0.0009985065301562452,
|
| 1360 |
+
"loss": 1.1362,
|
| 1361 |
+
"step": 1930
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.004505958782090439,
|
| 1365 |
+
"grad_norm": 0.34291279315948486,
|
| 1366 |
+
"learning_rate": 0.0009984987879590253,
|
| 1367 |
+
"loss": 1.0888,
|
| 1368 |
+
"step": 1940
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.0045291853737506995,
|
| 1372 |
+
"grad_norm": 0.4338567852973938,
|
| 1373 |
+
"learning_rate": 0.0009984910457618052,
|
| 1374 |
+
"loss": 1.0783,
|
| 1375 |
+
"step": 1950
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.00455241196541096,
|
| 1379 |
+
"grad_norm": 0.33047792315483093,
|
| 1380 |
+
"learning_rate": 0.000998483303564585,
|
| 1381 |
+
"loss": 1.0977,
|
| 1382 |
+
"step": 1960
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.00457563855707122,
|
| 1386 |
+
"grad_norm": 0.33728134632110596,
|
| 1387 |
+
"learning_rate": 0.0009984755613673649,
|
| 1388 |
+
"loss": 1.137,
|
| 1389 |
+
"step": 1970
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.00459886514873148,
|
| 1393 |
+
"grad_norm": 0.27301332354545593,
|
| 1394 |
+
"learning_rate": 0.0009984678191701448,
|
| 1395 |
+
"loss": 1.1413,
|
| 1396 |
+
"step": 1980
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.004622091740391739,
|
| 1400 |
+
"grad_norm": 0.2804515063762665,
|
| 1401 |
+
"learning_rate": 0.0009984600769729248,
|
| 1402 |
+
"loss": 1.0865,
|
| 1403 |
+
"step": 1990
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.0046453183320519995,
|
| 1407 |
+
"grad_norm": 0.33448469638824463,
|
| 1408 |
+
"learning_rate": 0.0009984523347757047,
|
| 1409 |
+
"loss": 1.1526,
|
| 1410 |
+
"step": 2000
|
| 1411 |
+
}
|
| 1412 |
+
],
|
| 1413 |
+
"logging_steps": 10,
|
| 1414 |
+
"max_steps": 1291623,
|
| 1415 |
+
"num_input_tokens_seen": 0,
|
| 1416 |
+
"num_train_epochs": 3,
|
| 1417 |
+
"save_steps": 1000,
|
| 1418 |
+
"stateful_callbacks": {
|
| 1419 |
+
"TrainerControl": {
|
| 1420 |
+
"args": {
|
| 1421 |
+
"should_epoch_stop": false,
|
| 1422 |
+
"should_evaluate": false,
|
| 1423 |
+
"should_log": false,
|
| 1424 |
+
"should_save": true,
|
| 1425 |
+
"should_training_stop": false
|
| 1426 |
+
},
|
| 1427 |
+
"attributes": {}
|
| 1428 |
+
}
|
| 1429 |
+
},
|
| 1430 |
+
"total_flos": 2.5412177861554176e+16,
|
| 1431 |
+
"train_batch_size": 7,
|
| 1432 |
+
"trial_name": null,
|
| 1433 |
+
"trial_params": null
|
| 1434 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c18823066aa92f35bdecf34f9b9ab3f8984a7bdc26ffda5a2c298da54cde28e
|
| 3 |
+
size 5496
|