Upload full training checkpoint (including optimizer state)
Browse files- added_tokens.json +104 -0
- config.json +32 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +127 -0
- spiece.model +3 -0
- tokenizer_config.json +959 -0
- trainer_state.json +3013 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<BN>": 32100,
|
| 3 |
+
"<SY>": 32101,
|
| 4 |
+
"<extra_id_0>": 32099,
|
| 5 |
+
"<extra_id_10>": 32089,
|
| 6 |
+
"<extra_id_11>": 32088,
|
| 7 |
+
"<extra_id_12>": 32087,
|
| 8 |
+
"<extra_id_13>": 32086,
|
| 9 |
+
"<extra_id_14>": 32085,
|
| 10 |
+
"<extra_id_15>": 32084,
|
| 11 |
+
"<extra_id_16>": 32083,
|
| 12 |
+
"<extra_id_17>": 32082,
|
| 13 |
+
"<extra_id_18>": 32081,
|
| 14 |
+
"<extra_id_19>": 32080,
|
| 15 |
+
"<extra_id_1>": 32098,
|
| 16 |
+
"<extra_id_20>": 32079,
|
| 17 |
+
"<extra_id_21>": 32078,
|
| 18 |
+
"<extra_id_22>": 32077,
|
| 19 |
+
"<extra_id_23>": 32076,
|
| 20 |
+
"<extra_id_24>": 32075,
|
| 21 |
+
"<extra_id_25>": 32074,
|
| 22 |
+
"<extra_id_26>": 32073,
|
| 23 |
+
"<extra_id_27>": 32072,
|
| 24 |
+
"<extra_id_28>": 32071,
|
| 25 |
+
"<extra_id_29>": 32070,
|
| 26 |
+
"<extra_id_2>": 32097,
|
| 27 |
+
"<extra_id_30>": 32069,
|
| 28 |
+
"<extra_id_31>": 32068,
|
| 29 |
+
"<extra_id_32>": 32067,
|
| 30 |
+
"<extra_id_33>": 32066,
|
| 31 |
+
"<extra_id_34>": 32065,
|
| 32 |
+
"<extra_id_35>": 32064,
|
| 33 |
+
"<extra_id_36>": 32063,
|
| 34 |
+
"<extra_id_37>": 32062,
|
| 35 |
+
"<extra_id_38>": 32061,
|
| 36 |
+
"<extra_id_39>": 32060,
|
| 37 |
+
"<extra_id_3>": 32096,
|
| 38 |
+
"<extra_id_40>": 32059,
|
| 39 |
+
"<extra_id_41>": 32058,
|
| 40 |
+
"<extra_id_42>": 32057,
|
| 41 |
+
"<extra_id_43>": 32056,
|
| 42 |
+
"<extra_id_44>": 32055,
|
| 43 |
+
"<extra_id_45>": 32054,
|
| 44 |
+
"<extra_id_46>": 32053,
|
| 45 |
+
"<extra_id_47>": 32052,
|
| 46 |
+
"<extra_id_48>": 32051,
|
| 47 |
+
"<extra_id_49>": 32050,
|
| 48 |
+
"<extra_id_4>": 32095,
|
| 49 |
+
"<extra_id_50>": 32049,
|
| 50 |
+
"<extra_id_51>": 32048,
|
| 51 |
+
"<extra_id_52>": 32047,
|
| 52 |
+
"<extra_id_53>": 32046,
|
| 53 |
+
"<extra_id_54>": 32045,
|
| 54 |
+
"<extra_id_55>": 32044,
|
| 55 |
+
"<extra_id_56>": 32043,
|
| 56 |
+
"<extra_id_57>": 32042,
|
| 57 |
+
"<extra_id_58>": 32041,
|
| 58 |
+
"<extra_id_59>": 32040,
|
| 59 |
+
"<extra_id_5>": 32094,
|
| 60 |
+
"<extra_id_60>": 32039,
|
| 61 |
+
"<extra_id_61>": 32038,
|
| 62 |
+
"<extra_id_62>": 32037,
|
| 63 |
+
"<extra_id_63>": 32036,
|
| 64 |
+
"<extra_id_64>": 32035,
|
| 65 |
+
"<extra_id_65>": 32034,
|
| 66 |
+
"<extra_id_66>": 32033,
|
| 67 |
+
"<extra_id_67>": 32032,
|
| 68 |
+
"<extra_id_68>": 32031,
|
| 69 |
+
"<extra_id_69>": 32030,
|
| 70 |
+
"<extra_id_6>": 32093,
|
| 71 |
+
"<extra_id_70>": 32029,
|
| 72 |
+
"<extra_id_71>": 32028,
|
| 73 |
+
"<extra_id_72>": 32027,
|
| 74 |
+
"<extra_id_73>": 32026,
|
| 75 |
+
"<extra_id_74>": 32025,
|
| 76 |
+
"<extra_id_75>": 32024,
|
| 77 |
+
"<extra_id_76>": 32023,
|
| 78 |
+
"<extra_id_77>": 32022,
|
| 79 |
+
"<extra_id_78>": 32021,
|
| 80 |
+
"<extra_id_79>": 32020,
|
| 81 |
+
"<extra_id_7>": 32092,
|
| 82 |
+
"<extra_id_80>": 32019,
|
| 83 |
+
"<extra_id_81>": 32018,
|
| 84 |
+
"<extra_id_82>": 32017,
|
| 85 |
+
"<extra_id_83>": 32016,
|
| 86 |
+
"<extra_id_84>": 32015,
|
| 87 |
+
"<extra_id_85>": 32014,
|
| 88 |
+
"<extra_id_86>": 32013,
|
| 89 |
+
"<extra_id_87>": 32012,
|
| 90 |
+
"<extra_id_88>": 32011,
|
| 91 |
+
"<extra_id_89>": 32010,
|
| 92 |
+
"<extra_id_8>": 32091,
|
| 93 |
+
"<extra_id_90>": 32009,
|
| 94 |
+
"<extra_id_91>": 32008,
|
| 95 |
+
"<extra_id_92>": 32007,
|
| 96 |
+
"<extra_id_93>": 32006,
|
| 97 |
+
"<extra_id_94>": 32005,
|
| 98 |
+
"<extra_id_95>": 32004,
|
| 99 |
+
"<extra_id_96>": 32003,
|
| 100 |
+
"<extra_id_97>": 32002,
|
| 101 |
+
"<extra_id_98>": 32001,
|
| 102 |
+
"<extra_id_99>": 32000,
|
| 103 |
+
"<extra_id_9>": 32090
|
| 104 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"T5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"classifier_dropout": 0.0,
|
| 6 |
+
"d_ff": 2048,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 768,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "gelu_new",
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"eos_token_id": 1,
|
| 13 |
+
"feed_forward_proj": "gated-gelu",
|
| 14 |
+
"gradient_checkpointing": false,
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": true,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "t5",
|
| 20 |
+
"num_decoder_layers": 12,
|
| 21 |
+
"num_heads": 12,
|
| 22 |
+
"num_layers": 12,
|
| 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": "4.54.1",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 32102
|
| 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": "4.54.1"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a362ad74ecdd3d29a102c8117642174c93ee465df5da1b4595fa94a234de7234
|
| 3 |
+
size 990185320
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b82db22b6891448c5c31d179151f5cbd660554523ea3ec6c76f2eb97b1de18ef
|
| 3 |
+
size 1980540922
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f78a674aa2b4fdd82caff54d14a91a9039ca5220c343c30e97377494701aa69a
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8ed5b5855a820a266d1940d2bebfabd66ce7527bdfc2ac754460ff7467631d4
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,127 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<BN>",
|
| 4 |
+
"<SY>",
|
| 5 |
+
"<extra_id_0>",
|
| 6 |
+
"<extra_id_1>",
|
| 7 |
+
"<extra_id_2>",
|
| 8 |
+
"<extra_id_3>",
|
| 9 |
+
"<extra_id_4>",
|
| 10 |
+
"<extra_id_5>",
|
| 11 |
+
"<extra_id_6>",
|
| 12 |
+
"<extra_id_7>",
|
| 13 |
+
"<extra_id_8>",
|
| 14 |
+
"<extra_id_9>",
|
| 15 |
+
"<extra_id_10>",
|
| 16 |
+
"<extra_id_11>",
|
| 17 |
+
"<extra_id_12>",
|
| 18 |
+
"<extra_id_13>",
|
| 19 |
+
"<extra_id_14>",
|
| 20 |
+
"<extra_id_15>",
|
| 21 |
+
"<extra_id_16>",
|
| 22 |
+
"<extra_id_17>",
|
| 23 |
+
"<extra_id_18>",
|
| 24 |
+
"<extra_id_19>",
|
| 25 |
+
"<extra_id_20>",
|
| 26 |
+
"<extra_id_21>",
|
| 27 |
+
"<extra_id_22>",
|
| 28 |
+
"<extra_id_23>",
|
| 29 |
+
"<extra_id_24>",
|
| 30 |
+
"<extra_id_25>",
|
| 31 |
+
"<extra_id_26>",
|
| 32 |
+
"<extra_id_27>",
|
| 33 |
+
"<extra_id_28>",
|
| 34 |
+
"<extra_id_29>",
|
| 35 |
+
"<extra_id_30>",
|
| 36 |
+
"<extra_id_31>",
|
| 37 |
+
"<extra_id_32>",
|
| 38 |
+
"<extra_id_33>",
|
| 39 |
+
"<extra_id_34>",
|
| 40 |
+
"<extra_id_35>",
|
| 41 |
+
"<extra_id_36>",
|
| 42 |
+
"<extra_id_37>",
|
| 43 |
+
"<extra_id_38>",
|
| 44 |
+
"<extra_id_39>",
|
| 45 |
+
"<extra_id_40>",
|
| 46 |
+
"<extra_id_41>",
|
| 47 |
+
"<extra_id_42>",
|
| 48 |
+
"<extra_id_43>",
|
| 49 |
+
"<extra_id_44>",
|
| 50 |
+
"<extra_id_45>",
|
| 51 |
+
"<extra_id_46>",
|
| 52 |
+
"<extra_id_47>",
|
| 53 |
+
"<extra_id_48>",
|
| 54 |
+
"<extra_id_49>",
|
| 55 |
+
"<extra_id_50>",
|
| 56 |
+
"<extra_id_51>",
|
| 57 |
+
"<extra_id_52>",
|
| 58 |
+
"<extra_id_53>",
|
| 59 |
+
"<extra_id_54>",
|
| 60 |
+
"<extra_id_55>",
|
| 61 |
+
"<extra_id_56>",
|
| 62 |
+
"<extra_id_57>",
|
| 63 |
+
"<extra_id_58>",
|
| 64 |
+
"<extra_id_59>",
|
| 65 |
+
"<extra_id_60>",
|
| 66 |
+
"<extra_id_61>",
|
| 67 |
+
"<extra_id_62>",
|
| 68 |
+
"<extra_id_63>",
|
| 69 |
+
"<extra_id_64>",
|
| 70 |
+
"<extra_id_65>",
|
| 71 |
+
"<extra_id_66>",
|
| 72 |
+
"<extra_id_67>",
|
| 73 |
+
"<extra_id_68>",
|
| 74 |
+
"<extra_id_69>",
|
| 75 |
+
"<extra_id_70>",
|
| 76 |
+
"<extra_id_71>",
|
| 77 |
+
"<extra_id_72>",
|
| 78 |
+
"<extra_id_73>",
|
| 79 |
+
"<extra_id_74>",
|
| 80 |
+
"<extra_id_75>",
|
| 81 |
+
"<extra_id_76>",
|
| 82 |
+
"<extra_id_77>",
|
| 83 |
+
"<extra_id_78>",
|
| 84 |
+
"<extra_id_79>",
|
| 85 |
+
"<extra_id_80>",
|
| 86 |
+
"<extra_id_81>",
|
| 87 |
+
"<extra_id_82>",
|
| 88 |
+
"<extra_id_83>",
|
| 89 |
+
"<extra_id_84>",
|
| 90 |
+
"<extra_id_85>",
|
| 91 |
+
"<extra_id_86>",
|
| 92 |
+
"<extra_id_87>",
|
| 93 |
+
"<extra_id_88>",
|
| 94 |
+
"<extra_id_89>",
|
| 95 |
+
"<extra_id_90>",
|
| 96 |
+
"<extra_id_91>",
|
| 97 |
+
"<extra_id_92>",
|
| 98 |
+
"<extra_id_93>",
|
| 99 |
+
"<extra_id_94>",
|
| 100 |
+
"<extra_id_95>",
|
| 101 |
+
"<extra_id_96>",
|
| 102 |
+
"<extra_id_97>",
|
| 103 |
+
"<extra_id_98>",
|
| 104 |
+
"<extra_id_99>"
|
| 105 |
+
],
|
| 106 |
+
"eos_token": {
|
| 107 |
+
"content": "</s>",
|
| 108 |
+
"lstrip": false,
|
| 109 |
+
"normalized": false,
|
| 110 |
+
"rstrip": false,
|
| 111 |
+
"single_word": false
|
| 112 |
+
},
|
| 113 |
+
"pad_token": {
|
| 114 |
+
"content": "<pad>",
|
| 115 |
+
"lstrip": false,
|
| 116 |
+
"normalized": false,
|
| 117 |
+
"rstrip": false,
|
| 118 |
+
"single_word": false
|
| 119 |
+
},
|
| 120 |
+
"unk_token": {
|
| 121 |
+
"content": "<unk>",
|
| 122 |
+
"lstrip": false,
|
| 123 |
+
"normalized": false,
|
| 124 |
+
"rstrip": false,
|
| 125 |
+
"single_word": false
|
| 126 |
+
}
|
| 127 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7dcab96935a2a51b1461c84e44c952ea8a3640c8bc3e2c6ae7a21d855454ae27
|
| 3 |
+
size 1111492
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,959 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<pad>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "</s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "<unk>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"32000": {
|
| 29 |
+
"content": "<extra_id_99>",
|
| 30 |
+
"lstrip": true,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": true,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"32001": {
|
| 37 |
+
"content": "<extra_id_98>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": true,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"32002": {
|
| 45 |
+
"content": "<extra_id_97>",
|
| 46 |
+
"lstrip": true,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": true,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"32003": {
|
| 53 |
+
"content": "<extra_id_96>",
|
| 54 |
+
"lstrip": true,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": true,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"32004": {
|
| 61 |
+
"content": "<extra_id_95>",
|
| 62 |
+
"lstrip": true,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": true,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"32005": {
|
| 69 |
+
"content": "<extra_id_94>",
|
| 70 |
+
"lstrip": true,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": true,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"32006": {
|
| 77 |
+
"content": "<extra_id_93>",
|
| 78 |
+
"lstrip": true,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": true,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"32007": {
|
| 85 |
+
"content": "<extra_id_92>",
|
| 86 |
+
"lstrip": true,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": true,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"32008": {
|
| 93 |
+
"content": "<extra_id_91>",
|
| 94 |
+
"lstrip": true,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": true,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"32009": {
|
| 101 |
+
"content": "<extra_id_90>",
|
| 102 |
+
"lstrip": true,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": true,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"32010": {
|
| 109 |
+
"content": "<extra_id_89>",
|
| 110 |
+
"lstrip": true,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": true,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"32011": {
|
| 117 |
+
"content": "<extra_id_88>",
|
| 118 |
+
"lstrip": true,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": true,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"32012": {
|
| 125 |
+
"content": "<extra_id_87>",
|
| 126 |
+
"lstrip": true,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": true,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"32013": {
|
| 133 |
+
"content": "<extra_id_86>",
|
| 134 |
+
"lstrip": true,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": true,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
},
|
| 140 |
+
"32014": {
|
| 141 |
+
"content": "<extra_id_85>",
|
| 142 |
+
"lstrip": true,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": true,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
"32015": {
|
| 149 |
+
"content": "<extra_id_84>",
|
| 150 |
+
"lstrip": true,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": true,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": true
|
| 155 |
+
},
|
| 156 |
+
"32016": {
|
| 157 |
+
"content": "<extra_id_83>",
|
| 158 |
+
"lstrip": true,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": true,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": true
|
| 163 |
+
},
|
| 164 |
+
"32017": {
|
| 165 |
+
"content": "<extra_id_82>",
|
| 166 |
+
"lstrip": true,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": true,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"32018": {
|
| 173 |
+
"content": "<extra_id_81>",
|
| 174 |
+
"lstrip": true,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": true,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
+
},
|
| 180 |
+
"32019": {
|
| 181 |
+
"content": "<extra_id_80>",
|
| 182 |
+
"lstrip": true,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": true,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": true
|
| 187 |
+
},
|
| 188 |
+
"32020": {
|
| 189 |
+
"content": "<extra_id_79>",
|
| 190 |
+
"lstrip": true,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": true,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": true
|
| 195 |
+
},
|
| 196 |
+
"32021": {
|
| 197 |
+
"content": "<extra_id_78>",
|
| 198 |
+
"lstrip": true,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": true,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": true
|
| 203 |
+
},
|
| 204 |
+
"32022": {
|
| 205 |
+
"content": "<extra_id_77>",
|
| 206 |
+
"lstrip": true,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": true,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": true
|
| 211 |
+
},
|
| 212 |
+
"32023": {
|
| 213 |
+
"content": "<extra_id_76>",
|
| 214 |
+
"lstrip": true,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"rstrip": true,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": true
|
| 219 |
+
},
|
| 220 |
+
"32024": {
|
| 221 |
+
"content": "<extra_id_75>",
|
| 222 |
+
"lstrip": true,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"rstrip": true,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": true
|
| 227 |
+
},
|
| 228 |
+
"32025": {
|
| 229 |
+
"content": "<extra_id_74>",
|
| 230 |
+
"lstrip": true,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"rstrip": true,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": true
|
| 235 |
+
},
|
| 236 |
+
"32026": {
|
| 237 |
+
"content": "<extra_id_73>",
|
| 238 |
+
"lstrip": true,
|
| 239 |
+
"normalized": false,
|
| 240 |
+
"rstrip": true,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": true
|
| 243 |
+
},
|
| 244 |
+
"32027": {
|
| 245 |
+
"content": "<extra_id_72>",
|
| 246 |
+
"lstrip": true,
|
| 247 |
+
"normalized": false,
|
| 248 |
+
"rstrip": true,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": true
|
| 251 |
+
},
|
| 252 |
+
"32028": {
|
| 253 |
+
"content": "<extra_id_71>",
|
| 254 |
+
"lstrip": true,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"rstrip": true,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": true
|
| 259 |
+
},
|
| 260 |
+
"32029": {
|
| 261 |
+
"content": "<extra_id_70>",
|
| 262 |
+
"lstrip": true,
|
| 263 |
+
"normalized": false,
|
| 264 |
+
"rstrip": true,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": true
|
| 267 |
+
},
|
| 268 |
+
"32030": {
|
| 269 |
+
"content": "<extra_id_69>",
|
| 270 |
+
"lstrip": true,
|
| 271 |
+
"normalized": false,
|
| 272 |
+
"rstrip": true,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": true
|
| 275 |
+
},
|
| 276 |
+
"32031": {
|
| 277 |
+
"content": "<extra_id_68>",
|
| 278 |
+
"lstrip": true,
|
| 279 |
+
"normalized": false,
|
| 280 |
+
"rstrip": true,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": true
|
| 283 |
+
},
|
| 284 |
+
"32032": {
|
| 285 |
+
"content": "<extra_id_67>",
|
| 286 |
+
"lstrip": true,
|
| 287 |
+
"normalized": false,
|
| 288 |
+
"rstrip": true,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": true
|
| 291 |
+
},
|
| 292 |
+
"32033": {
|
| 293 |
+
"content": "<extra_id_66>",
|
| 294 |
+
"lstrip": true,
|
| 295 |
+
"normalized": false,
|
| 296 |
+
"rstrip": true,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": true
|
| 299 |
+
},
|
| 300 |
+
"32034": {
|
| 301 |
+
"content": "<extra_id_65>",
|
| 302 |
+
"lstrip": true,
|
| 303 |
+
"normalized": false,
|
| 304 |
+
"rstrip": true,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": true
|
| 307 |
+
},
|
| 308 |
+
"32035": {
|
| 309 |
+
"content": "<extra_id_64>",
|
| 310 |
+
"lstrip": true,
|
| 311 |
+
"normalized": false,
|
| 312 |
+
"rstrip": true,
|
| 313 |
+
"single_word": false,
|
| 314 |
+
"special": true
|
| 315 |
+
},
|
| 316 |
+
"32036": {
|
| 317 |
+
"content": "<extra_id_63>",
|
| 318 |
+
"lstrip": true,
|
| 319 |
+
"normalized": false,
|
| 320 |
+
"rstrip": true,
|
| 321 |
+
"single_word": false,
|
| 322 |
+
"special": true
|
| 323 |
+
},
|
| 324 |
+
"32037": {
|
| 325 |
+
"content": "<extra_id_62>",
|
| 326 |
+
"lstrip": true,
|
| 327 |
+
"normalized": false,
|
| 328 |
+
"rstrip": true,
|
| 329 |
+
"single_word": false,
|
| 330 |
+
"special": true
|
| 331 |
+
},
|
| 332 |
+
"32038": {
|
| 333 |
+
"content": "<extra_id_61>",
|
| 334 |
+
"lstrip": true,
|
| 335 |
+
"normalized": false,
|
| 336 |
+
"rstrip": true,
|
| 337 |
+
"single_word": false,
|
| 338 |
+
"special": true
|
| 339 |
+
},
|
| 340 |
+
"32039": {
|
| 341 |
+
"content": "<extra_id_60>",
|
| 342 |
+
"lstrip": true,
|
| 343 |
+
"normalized": false,
|
| 344 |
+
"rstrip": true,
|
| 345 |
+
"single_word": false,
|
| 346 |
+
"special": true
|
| 347 |
+
},
|
| 348 |
+
"32040": {
|
| 349 |
+
"content": "<extra_id_59>",
|
| 350 |
+
"lstrip": true,
|
| 351 |
+
"normalized": false,
|
| 352 |
+
"rstrip": true,
|
| 353 |
+
"single_word": false,
|
| 354 |
+
"special": true
|
| 355 |
+
},
|
| 356 |
+
"32041": {
|
| 357 |
+
"content": "<extra_id_58>",
|
| 358 |
+
"lstrip": true,
|
| 359 |
+
"normalized": false,
|
| 360 |
+
"rstrip": true,
|
| 361 |
+
"single_word": false,
|
| 362 |
+
"special": true
|
| 363 |
+
},
|
| 364 |
+
"32042": {
|
| 365 |
+
"content": "<extra_id_57>",
|
| 366 |
+
"lstrip": true,
|
| 367 |
+
"normalized": false,
|
| 368 |
+
"rstrip": true,
|
| 369 |
+
"single_word": false,
|
| 370 |
+
"special": true
|
| 371 |
+
},
|
| 372 |
+
"32043": {
|
| 373 |
+
"content": "<extra_id_56>",
|
| 374 |
+
"lstrip": true,
|
| 375 |
+
"normalized": false,
|
| 376 |
+
"rstrip": true,
|
| 377 |
+
"single_word": false,
|
| 378 |
+
"special": true
|
| 379 |
+
},
|
| 380 |
+
"32044": {
|
| 381 |
+
"content": "<extra_id_55>",
|
| 382 |
+
"lstrip": true,
|
| 383 |
+
"normalized": false,
|
| 384 |
+
"rstrip": true,
|
| 385 |
+
"single_word": false,
|
| 386 |
+
"special": true
|
| 387 |
+
},
|
| 388 |
+
"32045": {
|
| 389 |
+
"content": "<extra_id_54>",
|
| 390 |
+
"lstrip": true,
|
| 391 |
+
"normalized": false,
|
| 392 |
+
"rstrip": true,
|
| 393 |
+
"single_word": false,
|
| 394 |
+
"special": true
|
| 395 |
+
},
|
| 396 |
+
"32046": {
|
| 397 |
+
"content": "<extra_id_53>",
|
| 398 |
+
"lstrip": true,
|
| 399 |
+
"normalized": false,
|
| 400 |
+
"rstrip": true,
|
| 401 |
+
"single_word": false,
|
| 402 |
+
"special": true
|
| 403 |
+
},
|
| 404 |
+
"32047": {
|
| 405 |
+
"content": "<extra_id_52>",
|
| 406 |
+
"lstrip": true,
|
| 407 |
+
"normalized": false,
|
| 408 |
+
"rstrip": true,
|
| 409 |
+
"single_word": false,
|
| 410 |
+
"special": true
|
| 411 |
+
},
|
| 412 |
+
"32048": {
|
| 413 |
+
"content": "<extra_id_51>",
|
| 414 |
+
"lstrip": true,
|
| 415 |
+
"normalized": false,
|
| 416 |
+
"rstrip": true,
|
| 417 |
+
"single_word": false,
|
| 418 |
+
"special": true
|
| 419 |
+
},
|
| 420 |
+
"32049": {
|
| 421 |
+
"content": "<extra_id_50>",
|
| 422 |
+
"lstrip": true,
|
| 423 |
+
"normalized": false,
|
| 424 |
+
"rstrip": true,
|
| 425 |
+
"single_word": false,
|
| 426 |
+
"special": true
|
| 427 |
+
},
|
| 428 |
+
"32050": {
|
| 429 |
+
"content": "<extra_id_49>",
|
| 430 |
+
"lstrip": true,
|
| 431 |
+
"normalized": false,
|
| 432 |
+
"rstrip": true,
|
| 433 |
+
"single_word": false,
|
| 434 |
+
"special": true
|
| 435 |
+
},
|
| 436 |
+
"32051": {
|
| 437 |
+
"content": "<extra_id_48>",
|
| 438 |
+
"lstrip": true,
|
| 439 |
+
"normalized": false,
|
| 440 |
+
"rstrip": true,
|
| 441 |
+
"single_word": false,
|
| 442 |
+
"special": true
|
| 443 |
+
},
|
| 444 |
+
"32052": {
|
| 445 |
+
"content": "<extra_id_47>",
|
| 446 |
+
"lstrip": true,
|
| 447 |
+
"normalized": false,
|
| 448 |
+
"rstrip": true,
|
| 449 |
+
"single_word": false,
|
| 450 |
+
"special": true
|
| 451 |
+
},
|
| 452 |
+
"32053": {
|
| 453 |
+
"content": "<extra_id_46>",
|
| 454 |
+
"lstrip": true,
|
| 455 |
+
"normalized": false,
|
| 456 |
+
"rstrip": true,
|
| 457 |
+
"single_word": false,
|
| 458 |
+
"special": true
|
| 459 |
+
},
|
| 460 |
+
"32054": {
|
| 461 |
+
"content": "<extra_id_45>",
|
| 462 |
+
"lstrip": true,
|
| 463 |
+
"normalized": false,
|
| 464 |
+
"rstrip": true,
|
| 465 |
+
"single_word": false,
|
| 466 |
+
"special": true
|
| 467 |
+
},
|
| 468 |
+
"32055": {
|
| 469 |
+
"content": "<extra_id_44>",
|
| 470 |
+
"lstrip": true,
|
| 471 |
+
"normalized": false,
|
| 472 |
+
"rstrip": true,
|
| 473 |
+
"single_word": false,
|
| 474 |
+
"special": true
|
| 475 |
+
},
|
| 476 |
+
"32056": {
|
| 477 |
+
"content": "<extra_id_43>",
|
| 478 |
+
"lstrip": true,
|
| 479 |
+
"normalized": false,
|
| 480 |
+
"rstrip": true,
|
| 481 |
+
"single_word": false,
|
| 482 |
+
"special": true
|
| 483 |
+
},
|
| 484 |
+
"32057": {
|
| 485 |
+
"content": "<extra_id_42>",
|
| 486 |
+
"lstrip": true,
|
| 487 |
+
"normalized": false,
|
| 488 |
+
"rstrip": true,
|
| 489 |
+
"single_word": false,
|
| 490 |
+
"special": true
|
| 491 |
+
},
|
| 492 |
+
"32058": {
|
| 493 |
+
"content": "<extra_id_41>",
|
| 494 |
+
"lstrip": true,
|
| 495 |
+
"normalized": false,
|
| 496 |
+
"rstrip": true,
|
| 497 |
+
"single_word": false,
|
| 498 |
+
"special": true
|
| 499 |
+
},
|
| 500 |
+
"32059": {
|
| 501 |
+
"content": "<extra_id_40>",
|
| 502 |
+
"lstrip": true,
|
| 503 |
+
"normalized": false,
|
| 504 |
+
"rstrip": true,
|
| 505 |
+
"single_word": false,
|
| 506 |
+
"special": true
|
| 507 |
+
},
|
| 508 |
+
"32060": {
|
| 509 |
+
"content": "<extra_id_39>",
|
| 510 |
+
"lstrip": true,
|
| 511 |
+
"normalized": false,
|
| 512 |
+
"rstrip": true,
|
| 513 |
+
"single_word": false,
|
| 514 |
+
"special": true
|
| 515 |
+
},
|
| 516 |
+
"32061": {
|
| 517 |
+
"content": "<extra_id_38>",
|
| 518 |
+
"lstrip": true,
|
| 519 |
+
"normalized": false,
|
| 520 |
+
"rstrip": true,
|
| 521 |
+
"single_word": false,
|
| 522 |
+
"special": true
|
| 523 |
+
},
|
| 524 |
+
"32062": {
|
| 525 |
+
"content": "<extra_id_37>",
|
| 526 |
+
"lstrip": true,
|
| 527 |
+
"normalized": false,
|
| 528 |
+
"rstrip": true,
|
| 529 |
+
"single_word": false,
|
| 530 |
+
"special": true
|
| 531 |
+
},
|
| 532 |
+
"32063": {
|
| 533 |
+
"content": "<extra_id_36>",
|
| 534 |
+
"lstrip": true,
|
| 535 |
+
"normalized": false,
|
| 536 |
+
"rstrip": true,
|
| 537 |
+
"single_word": false,
|
| 538 |
+
"special": true
|
| 539 |
+
},
|
| 540 |
+
"32064": {
|
| 541 |
+
"content": "<extra_id_35>",
|
| 542 |
+
"lstrip": true,
|
| 543 |
+
"normalized": false,
|
| 544 |
+
"rstrip": true,
|
| 545 |
+
"single_word": false,
|
| 546 |
+
"special": true
|
| 547 |
+
},
|
| 548 |
+
"32065": {
|
| 549 |
+
"content": "<extra_id_34>",
|
| 550 |
+
"lstrip": true,
|
| 551 |
+
"normalized": false,
|
| 552 |
+
"rstrip": true,
|
| 553 |
+
"single_word": false,
|
| 554 |
+
"special": true
|
| 555 |
+
},
|
| 556 |
+
"32066": {
|
| 557 |
+
"content": "<extra_id_33>",
|
| 558 |
+
"lstrip": true,
|
| 559 |
+
"normalized": false,
|
| 560 |
+
"rstrip": true,
|
| 561 |
+
"single_word": false,
|
| 562 |
+
"special": true
|
| 563 |
+
},
|
| 564 |
+
"32067": {
|
| 565 |
+
"content": "<extra_id_32>",
|
| 566 |
+
"lstrip": true,
|
| 567 |
+
"normalized": false,
|
| 568 |
+
"rstrip": true,
|
| 569 |
+
"single_word": false,
|
| 570 |
+
"special": true
|
| 571 |
+
},
|
| 572 |
+
"32068": {
|
| 573 |
+
"content": "<extra_id_31>",
|
| 574 |
+
"lstrip": true,
|
| 575 |
+
"normalized": false,
|
| 576 |
+
"rstrip": true,
|
| 577 |
+
"single_word": false,
|
| 578 |
+
"special": true
|
| 579 |
+
},
|
| 580 |
+
"32069": {
|
| 581 |
+
"content": "<extra_id_30>",
|
| 582 |
+
"lstrip": true,
|
| 583 |
+
"normalized": false,
|
| 584 |
+
"rstrip": true,
|
| 585 |
+
"single_word": false,
|
| 586 |
+
"special": true
|
| 587 |
+
},
|
| 588 |
+
"32070": {
|
| 589 |
+
"content": "<extra_id_29>",
|
| 590 |
+
"lstrip": true,
|
| 591 |
+
"normalized": false,
|
| 592 |
+
"rstrip": true,
|
| 593 |
+
"single_word": false,
|
| 594 |
+
"special": true
|
| 595 |
+
},
|
| 596 |
+
"32071": {
|
| 597 |
+
"content": "<extra_id_28>",
|
| 598 |
+
"lstrip": true,
|
| 599 |
+
"normalized": false,
|
| 600 |
+
"rstrip": true,
|
| 601 |
+
"single_word": false,
|
| 602 |
+
"special": true
|
| 603 |
+
},
|
| 604 |
+
"32072": {
|
| 605 |
+
"content": "<extra_id_27>",
|
| 606 |
+
"lstrip": true,
|
| 607 |
+
"normalized": false,
|
| 608 |
+
"rstrip": true,
|
| 609 |
+
"single_word": false,
|
| 610 |
+
"special": true
|
| 611 |
+
},
|
| 612 |
+
"32073": {
|
| 613 |
+
"content": "<extra_id_26>",
|
| 614 |
+
"lstrip": true,
|
| 615 |
+
"normalized": false,
|
| 616 |
+
"rstrip": true,
|
| 617 |
+
"single_word": false,
|
| 618 |
+
"special": true
|
| 619 |
+
},
|
| 620 |
+
"32074": {
|
| 621 |
+
"content": "<extra_id_25>",
|
| 622 |
+
"lstrip": true,
|
| 623 |
+
"normalized": false,
|
| 624 |
+
"rstrip": true,
|
| 625 |
+
"single_word": false,
|
| 626 |
+
"special": true
|
| 627 |
+
},
|
| 628 |
+
"32075": {
|
| 629 |
+
"content": "<extra_id_24>",
|
| 630 |
+
"lstrip": true,
|
| 631 |
+
"normalized": false,
|
| 632 |
+
"rstrip": true,
|
| 633 |
+
"single_word": false,
|
| 634 |
+
"special": true
|
| 635 |
+
},
|
| 636 |
+
"32076": {
|
| 637 |
+
"content": "<extra_id_23>",
|
| 638 |
+
"lstrip": true,
|
| 639 |
+
"normalized": false,
|
| 640 |
+
"rstrip": true,
|
| 641 |
+
"single_word": false,
|
| 642 |
+
"special": true
|
| 643 |
+
},
|
| 644 |
+
"32077": {
|
| 645 |
+
"content": "<extra_id_22>",
|
| 646 |
+
"lstrip": true,
|
| 647 |
+
"normalized": false,
|
| 648 |
+
"rstrip": true,
|
| 649 |
+
"single_word": false,
|
| 650 |
+
"special": true
|
| 651 |
+
},
|
| 652 |
+
"32078": {
|
| 653 |
+
"content": "<extra_id_21>",
|
| 654 |
+
"lstrip": true,
|
| 655 |
+
"normalized": false,
|
| 656 |
+
"rstrip": true,
|
| 657 |
+
"single_word": false,
|
| 658 |
+
"special": true
|
| 659 |
+
},
|
| 660 |
+
"32079": {
|
| 661 |
+
"content": "<extra_id_20>",
|
| 662 |
+
"lstrip": true,
|
| 663 |
+
"normalized": false,
|
| 664 |
+
"rstrip": true,
|
| 665 |
+
"single_word": false,
|
| 666 |
+
"special": true
|
| 667 |
+
},
|
| 668 |
+
"32080": {
|
| 669 |
+
"content": "<extra_id_19>",
|
| 670 |
+
"lstrip": true,
|
| 671 |
+
"normalized": false,
|
| 672 |
+
"rstrip": true,
|
| 673 |
+
"single_word": false,
|
| 674 |
+
"special": true
|
| 675 |
+
},
|
| 676 |
+
"32081": {
|
| 677 |
+
"content": "<extra_id_18>",
|
| 678 |
+
"lstrip": true,
|
| 679 |
+
"normalized": false,
|
| 680 |
+
"rstrip": true,
|
| 681 |
+
"single_word": false,
|
| 682 |
+
"special": true
|
| 683 |
+
},
|
| 684 |
+
"32082": {
|
| 685 |
+
"content": "<extra_id_17>",
|
| 686 |
+
"lstrip": true,
|
| 687 |
+
"normalized": false,
|
| 688 |
+
"rstrip": true,
|
| 689 |
+
"single_word": false,
|
| 690 |
+
"special": true
|
| 691 |
+
},
|
| 692 |
+
"32083": {
|
| 693 |
+
"content": "<extra_id_16>",
|
| 694 |
+
"lstrip": true,
|
| 695 |
+
"normalized": false,
|
| 696 |
+
"rstrip": true,
|
| 697 |
+
"single_word": false,
|
| 698 |
+
"special": true
|
| 699 |
+
},
|
| 700 |
+
"32084": {
|
| 701 |
+
"content": "<extra_id_15>",
|
| 702 |
+
"lstrip": true,
|
| 703 |
+
"normalized": false,
|
| 704 |
+
"rstrip": true,
|
| 705 |
+
"single_word": false,
|
| 706 |
+
"special": true
|
| 707 |
+
},
|
| 708 |
+
"32085": {
|
| 709 |
+
"content": "<extra_id_14>",
|
| 710 |
+
"lstrip": true,
|
| 711 |
+
"normalized": false,
|
| 712 |
+
"rstrip": true,
|
| 713 |
+
"single_word": false,
|
| 714 |
+
"special": true
|
| 715 |
+
},
|
| 716 |
+
"32086": {
|
| 717 |
+
"content": "<extra_id_13>",
|
| 718 |
+
"lstrip": true,
|
| 719 |
+
"normalized": false,
|
| 720 |
+
"rstrip": true,
|
| 721 |
+
"single_word": false,
|
| 722 |
+
"special": true
|
| 723 |
+
},
|
| 724 |
+
"32087": {
|
| 725 |
+
"content": "<extra_id_12>",
|
| 726 |
+
"lstrip": true,
|
| 727 |
+
"normalized": false,
|
| 728 |
+
"rstrip": true,
|
| 729 |
+
"single_word": false,
|
| 730 |
+
"special": true
|
| 731 |
+
},
|
| 732 |
+
"32088": {
|
| 733 |
+
"content": "<extra_id_11>",
|
| 734 |
+
"lstrip": true,
|
| 735 |
+
"normalized": false,
|
| 736 |
+
"rstrip": true,
|
| 737 |
+
"single_word": false,
|
| 738 |
+
"special": true
|
| 739 |
+
},
|
| 740 |
+
"32089": {
|
| 741 |
+
"content": "<extra_id_10>",
|
| 742 |
+
"lstrip": true,
|
| 743 |
+
"normalized": false,
|
| 744 |
+
"rstrip": true,
|
| 745 |
+
"single_word": false,
|
| 746 |
+
"special": true
|
| 747 |
+
},
|
| 748 |
+
"32090": {
|
| 749 |
+
"content": "<extra_id_9>",
|
| 750 |
+
"lstrip": true,
|
| 751 |
+
"normalized": false,
|
| 752 |
+
"rstrip": true,
|
| 753 |
+
"single_word": false,
|
| 754 |
+
"special": true
|
| 755 |
+
},
|
| 756 |
+
"32091": {
|
| 757 |
+
"content": "<extra_id_8>",
|
| 758 |
+
"lstrip": true,
|
| 759 |
+
"normalized": false,
|
| 760 |
+
"rstrip": true,
|
| 761 |
+
"single_word": false,
|
| 762 |
+
"special": true
|
| 763 |
+
},
|
| 764 |
+
"32092": {
|
| 765 |
+
"content": "<extra_id_7>",
|
| 766 |
+
"lstrip": true,
|
| 767 |
+
"normalized": false,
|
| 768 |
+
"rstrip": true,
|
| 769 |
+
"single_word": false,
|
| 770 |
+
"special": true
|
| 771 |
+
},
|
| 772 |
+
"32093": {
|
| 773 |
+
"content": "<extra_id_6>",
|
| 774 |
+
"lstrip": true,
|
| 775 |
+
"normalized": false,
|
| 776 |
+
"rstrip": true,
|
| 777 |
+
"single_word": false,
|
| 778 |
+
"special": true
|
| 779 |
+
},
|
| 780 |
+
"32094": {
|
| 781 |
+
"content": "<extra_id_5>",
|
| 782 |
+
"lstrip": true,
|
| 783 |
+
"normalized": false,
|
| 784 |
+
"rstrip": true,
|
| 785 |
+
"single_word": false,
|
| 786 |
+
"special": true
|
| 787 |
+
},
|
| 788 |
+
"32095": {
|
| 789 |
+
"content": "<extra_id_4>",
|
| 790 |
+
"lstrip": true,
|
| 791 |
+
"normalized": false,
|
| 792 |
+
"rstrip": true,
|
| 793 |
+
"single_word": false,
|
| 794 |
+
"special": true
|
| 795 |
+
},
|
| 796 |
+
"32096": {
|
| 797 |
+
"content": "<extra_id_3>",
|
| 798 |
+
"lstrip": true,
|
| 799 |
+
"normalized": false,
|
| 800 |
+
"rstrip": true,
|
| 801 |
+
"single_word": false,
|
| 802 |
+
"special": true
|
| 803 |
+
},
|
| 804 |
+
"32097": {
|
| 805 |
+
"content": "<extra_id_2>",
|
| 806 |
+
"lstrip": true,
|
| 807 |
+
"normalized": false,
|
| 808 |
+
"rstrip": true,
|
| 809 |
+
"single_word": false,
|
| 810 |
+
"special": true
|
| 811 |
+
},
|
| 812 |
+
"32098": {
|
| 813 |
+
"content": "<extra_id_1>",
|
| 814 |
+
"lstrip": true,
|
| 815 |
+
"normalized": false,
|
| 816 |
+
"rstrip": true,
|
| 817 |
+
"single_word": false,
|
| 818 |
+
"special": true
|
| 819 |
+
},
|
| 820 |
+
"32099": {
|
| 821 |
+
"content": "<extra_id_0>",
|
| 822 |
+
"lstrip": true,
|
| 823 |
+
"normalized": false,
|
| 824 |
+
"rstrip": true,
|
| 825 |
+
"single_word": false,
|
| 826 |
+
"special": true
|
| 827 |
+
},
|
| 828 |
+
"32100": {
|
| 829 |
+
"content": "<BN>",
|
| 830 |
+
"lstrip": false,
|
| 831 |
+
"normalized": false,
|
| 832 |
+
"rstrip": false,
|
| 833 |
+
"single_word": false,
|
| 834 |
+
"special": true
|
| 835 |
+
},
|
| 836 |
+
"32101": {
|
| 837 |
+
"content": "<SY>",
|
| 838 |
+
"lstrip": false,
|
| 839 |
+
"normalized": false,
|
| 840 |
+
"rstrip": false,
|
| 841 |
+
"single_word": false,
|
| 842 |
+
"special": true
|
| 843 |
+
}
|
| 844 |
+
},
|
| 845 |
+
"additional_special_tokens": [
|
| 846 |
+
"<BN>",
|
| 847 |
+
"<SY>",
|
| 848 |
+
"<extra_id_0>",
|
| 849 |
+
"<extra_id_1>",
|
| 850 |
+
"<extra_id_2>",
|
| 851 |
+
"<extra_id_3>",
|
| 852 |
+
"<extra_id_4>",
|
| 853 |
+
"<extra_id_5>",
|
| 854 |
+
"<extra_id_6>",
|
| 855 |
+
"<extra_id_7>",
|
| 856 |
+
"<extra_id_8>",
|
| 857 |
+
"<extra_id_9>",
|
| 858 |
+
"<extra_id_10>",
|
| 859 |
+
"<extra_id_11>",
|
| 860 |
+
"<extra_id_12>",
|
| 861 |
+
"<extra_id_13>",
|
| 862 |
+
"<extra_id_14>",
|
| 863 |
+
"<extra_id_15>",
|
| 864 |
+
"<extra_id_16>",
|
| 865 |
+
"<extra_id_17>",
|
| 866 |
+
"<extra_id_18>",
|
| 867 |
+
"<extra_id_19>",
|
| 868 |
+
"<extra_id_20>",
|
| 869 |
+
"<extra_id_21>",
|
| 870 |
+
"<extra_id_22>",
|
| 871 |
+
"<extra_id_23>",
|
| 872 |
+
"<extra_id_24>",
|
| 873 |
+
"<extra_id_25>",
|
| 874 |
+
"<extra_id_26>",
|
| 875 |
+
"<extra_id_27>",
|
| 876 |
+
"<extra_id_28>",
|
| 877 |
+
"<extra_id_29>",
|
| 878 |
+
"<extra_id_30>",
|
| 879 |
+
"<extra_id_31>",
|
| 880 |
+
"<extra_id_32>",
|
| 881 |
+
"<extra_id_33>",
|
| 882 |
+
"<extra_id_34>",
|
| 883 |
+
"<extra_id_35>",
|
| 884 |
+
"<extra_id_36>",
|
| 885 |
+
"<extra_id_37>",
|
| 886 |
+
"<extra_id_38>",
|
| 887 |
+
"<extra_id_39>",
|
| 888 |
+
"<extra_id_40>",
|
| 889 |
+
"<extra_id_41>",
|
| 890 |
+
"<extra_id_42>",
|
| 891 |
+
"<extra_id_43>",
|
| 892 |
+
"<extra_id_44>",
|
| 893 |
+
"<extra_id_45>",
|
| 894 |
+
"<extra_id_46>",
|
| 895 |
+
"<extra_id_47>",
|
| 896 |
+
"<extra_id_48>",
|
| 897 |
+
"<extra_id_49>",
|
| 898 |
+
"<extra_id_50>",
|
| 899 |
+
"<extra_id_51>",
|
| 900 |
+
"<extra_id_52>",
|
| 901 |
+
"<extra_id_53>",
|
| 902 |
+
"<extra_id_54>",
|
| 903 |
+
"<extra_id_55>",
|
| 904 |
+
"<extra_id_56>",
|
| 905 |
+
"<extra_id_57>",
|
| 906 |
+
"<extra_id_58>",
|
| 907 |
+
"<extra_id_59>",
|
| 908 |
+
"<extra_id_60>",
|
| 909 |
+
"<extra_id_61>",
|
| 910 |
+
"<extra_id_62>",
|
| 911 |
+
"<extra_id_63>",
|
| 912 |
+
"<extra_id_64>",
|
| 913 |
+
"<extra_id_65>",
|
| 914 |
+
"<extra_id_66>",
|
| 915 |
+
"<extra_id_67>",
|
| 916 |
+
"<extra_id_68>",
|
| 917 |
+
"<extra_id_69>",
|
| 918 |
+
"<extra_id_70>",
|
| 919 |
+
"<extra_id_71>",
|
| 920 |
+
"<extra_id_72>",
|
| 921 |
+
"<extra_id_73>",
|
| 922 |
+
"<extra_id_74>",
|
| 923 |
+
"<extra_id_75>",
|
| 924 |
+
"<extra_id_76>",
|
| 925 |
+
"<extra_id_77>",
|
| 926 |
+
"<extra_id_78>",
|
| 927 |
+
"<extra_id_79>",
|
| 928 |
+
"<extra_id_80>",
|
| 929 |
+
"<extra_id_81>",
|
| 930 |
+
"<extra_id_82>",
|
| 931 |
+
"<extra_id_83>",
|
| 932 |
+
"<extra_id_84>",
|
| 933 |
+
"<extra_id_85>",
|
| 934 |
+
"<extra_id_86>",
|
| 935 |
+
"<extra_id_87>",
|
| 936 |
+
"<extra_id_88>",
|
| 937 |
+
"<extra_id_89>",
|
| 938 |
+
"<extra_id_90>",
|
| 939 |
+
"<extra_id_91>",
|
| 940 |
+
"<extra_id_92>",
|
| 941 |
+
"<extra_id_93>",
|
| 942 |
+
"<extra_id_94>",
|
| 943 |
+
"<extra_id_95>",
|
| 944 |
+
"<extra_id_96>",
|
| 945 |
+
"<extra_id_97>",
|
| 946 |
+
"<extra_id_98>",
|
| 947 |
+
"<extra_id_99>"
|
| 948 |
+
],
|
| 949 |
+
"clean_up_tokenization_spaces": false,
|
| 950 |
+
"eos_token": "</s>",
|
| 951 |
+
"extra_ids": 100,
|
| 952 |
+
"extra_special_tokens": {},
|
| 953 |
+
"legacy": true,
|
| 954 |
+
"model_max_length": 512,
|
| 955 |
+
"pad_token": "<pad>",
|
| 956 |
+
"sp_model_kwargs": {},
|
| 957 |
+
"tokenizer_class": "T5Tokenizer",
|
| 958 |
+
"unk_token": "<unk>"
|
| 959 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3013 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 25.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 39775,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.06285355122564425,
|
| 14 |
+
"grad_norm": 608.9674682617188,
|
| 15 |
+
"learning_rate": 4.844437460716531e-05,
|
| 16 |
+
"loss": 14.2524,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.1257071024512885,
|
| 21 |
+
"grad_norm": 34.65327453613281,
|
| 22 |
+
"learning_rate": 4.6873035826524205e-05,
|
| 23 |
+
"loss": 10.3562,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.18856065367693275,
|
| 28 |
+
"grad_norm": 21.24808120727539,
|
| 29 |
+
"learning_rate": 4.5301697045883096e-05,
|
| 30 |
+
"loss": 7.8551,
|
| 31 |
+
"step": 300
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.251414204902577,
|
| 35 |
+
"grad_norm": 17.404918670654297,
|
| 36 |
+
"learning_rate": 4.373035826524199e-05,
|
| 37 |
+
"loss": 6.6346,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.3142677561282212,
|
| 42 |
+
"grad_norm": 12.713433265686035,
|
| 43 |
+
"learning_rate": 4.2159019484600884e-05,
|
| 44 |
+
"loss": 5.9755,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.3771213073538655,
|
| 49 |
+
"grad_norm": 10.050477981567383,
|
| 50 |
+
"learning_rate": 4.0587680703959775e-05,
|
| 51 |
+
"loss": 5.5595,
|
| 52 |
+
"step": 600
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.43997485857950974,
|
| 56 |
+
"grad_norm": 13.709216117858887,
|
| 57 |
+
"learning_rate": 3.9016341923318666e-05,
|
| 58 |
+
"loss": 5.2853,
|
| 59 |
+
"step": 700
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.502828409805154,
|
| 63 |
+
"grad_norm": 9.112940788269043,
|
| 64 |
+
"learning_rate": 3.744500314267756e-05,
|
| 65 |
+
"loss": 5.1417,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.5656819610307983,
|
| 70 |
+
"grad_norm": 8.267425537109375,
|
| 71 |
+
"learning_rate": 3.587366436203646e-05,
|
| 72 |
+
"loss": 4.9615,
|
| 73 |
+
"step": 900
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.6285355122564424,
|
| 77 |
+
"grad_norm": 9.709076881408691,
|
| 78 |
+
"learning_rate": 3.430232558139535e-05,
|
| 79 |
+
"loss": 4.6907,
|
| 80 |
+
"step": 1000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.6913890634820867,
|
| 84 |
+
"grad_norm": 845.80859375,
|
| 85 |
+
"learning_rate": 3.273098680075424e-05,
|
| 86 |
+
"loss": 4.5456,
|
| 87 |
+
"step": 1100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.754242614707731,
|
| 91 |
+
"grad_norm": 5.943735599517822,
|
| 92 |
+
"learning_rate": 3.115964802011313e-05,
|
| 93 |
+
"loss": 4.4291,
|
| 94 |
+
"step": 1200
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.8170961659333752,
|
| 98 |
+
"grad_norm": 5.8759989738464355,
|
| 99 |
+
"learning_rate": 2.9588309239472034e-05,
|
| 100 |
+
"loss": 4.3252,
|
| 101 |
+
"step": 1300
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.8799497171590195,
|
| 105 |
+
"grad_norm": 14.995753288269043,
|
| 106 |
+
"learning_rate": 2.8016970458830928e-05,
|
| 107 |
+
"loss": 4.2586,
|
| 108 |
+
"step": 1400
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.9428032683846638,
|
| 112 |
+
"grad_norm": 23.3351993560791,
|
| 113 |
+
"learning_rate": 2.644563167818982e-05,
|
| 114 |
+
"loss": 4.1372,
|
| 115 |
+
"step": 1500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 1.0,
|
| 119 |
+
"eval_loss": 3.215750217437744,
|
| 120 |
+
"eval_runtime": 19.7611,
|
| 121 |
+
"eval_samples_per_second": 48.479,
|
| 122 |
+
"eval_steps_per_second": 6.073,
|
| 123 |
+
"step": 1591
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.005656819610308,
|
| 127 |
+
"grad_norm": 8.584565162658691,
|
| 128 |
+
"learning_rate": 2.4874292897548713e-05,
|
| 129 |
+
"loss": 4.0272,
|
| 130 |
+
"step": 1600
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.0685103708359522,
|
| 134 |
+
"grad_norm": 6.45043420791626,
|
| 135 |
+
"learning_rate": 2.3302954116907607e-05,
|
| 136 |
+
"loss": 3.9602,
|
| 137 |
+
"step": 1700
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.1313639220615965,
|
| 141 |
+
"grad_norm": 6.03476095199585,
|
| 142 |
+
"learning_rate": 2.17316153362665e-05,
|
| 143 |
+
"loss": 3.9052,
|
| 144 |
+
"step": 1800
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.1942174732872408,
|
| 148 |
+
"grad_norm": 5.746309280395508,
|
| 149 |
+
"learning_rate": 2.0160276555625392e-05,
|
| 150 |
+
"loss": 3.9282,
|
| 151 |
+
"step": 1900
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.2570710245128849,
|
| 155 |
+
"grad_norm": 8.062549591064453,
|
| 156 |
+
"learning_rate": 1.858893777498429e-05,
|
| 157 |
+
"loss": 3.8096,
|
| 158 |
+
"step": 2000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.3199245757385292,
|
| 162 |
+
"grad_norm": 8.58310317993164,
|
| 163 |
+
"learning_rate": 1.701759899434318e-05,
|
| 164 |
+
"loss": 3.803,
|
| 165 |
+
"step": 2100
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.3827781269641735,
|
| 169 |
+
"grad_norm": 7.599905490875244,
|
| 170 |
+
"learning_rate": 1.5446260213702074e-05,
|
| 171 |
+
"loss": 3.8381,
|
| 172 |
+
"step": 2200
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.4456316781898177,
|
| 176 |
+
"grad_norm": 22.772512435913086,
|
| 177 |
+
"learning_rate": 1.3874921433060969e-05,
|
| 178 |
+
"loss": 3.6456,
|
| 179 |
+
"step": 2300
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.508485229415462,
|
| 183 |
+
"grad_norm": 6.949570178985596,
|
| 184 |
+
"learning_rate": 1.2303582652419863e-05,
|
| 185 |
+
"loss": 3.7442,
|
| 186 |
+
"step": 2400
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.5713387806411063,
|
| 190 |
+
"grad_norm": 5.7536821365356445,
|
| 191 |
+
"learning_rate": 1.0732243871778757e-05,
|
| 192 |
+
"loss": 3.691,
|
| 193 |
+
"step": 2500
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.6341923318667506,
|
| 197 |
+
"grad_norm": 55.64060974121094,
|
| 198 |
+
"learning_rate": 9.160905091137651e-06,
|
| 199 |
+
"loss": 3.7461,
|
| 200 |
+
"step": 2600
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.6970458830923947,
|
| 204 |
+
"grad_norm": 6.573077201843262,
|
| 205 |
+
"learning_rate": 7.589566310496543e-06,
|
| 206 |
+
"loss": 3.6186,
|
| 207 |
+
"step": 2700
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.759899434318039,
|
| 211 |
+
"grad_norm": 8.615326881408691,
|
| 212 |
+
"learning_rate": 6.018227529855437e-06,
|
| 213 |
+
"loss": 3.6546,
|
| 214 |
+
"step": 2800
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.8227529855436833,
|
| 218 |
+
"grad_norm": 6.359428405761719,
|
| 219 |
+
"learning_rate": 4.446888749214331e-06,
|
| 220 |
+
"loss": 3.5724,
|
| 221 |
+
"step": 2900
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.8856065367693273,
|
| 225 |
+
"grad_norm": 5.5190582275390625,
|
| 226 |
+
"learning_rate": 2.8755499685732243e-06,
|
| 227 |
+
"loss": 3.6164,
|
| 228 |
+
"step": 3000
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.9484600879949716,
|
| 232 |
+
"grad_norm": 5.9382004737854,
|
| 233 |
+
"learning_rate": 1.3042111879321182e-06,
|
| 234 |
+
"loss": 3.52,
|
| 235 |
+
"step": 3100
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 2.0,
|
| 239 |
+
"eval_loss": 2.803544521331787,
|
| 240 |
+
"eval_runtime": 19.8643,
|
| 241 |
+
"eval_samples_per_second": 48.227,
|
| 242 |
+
"eval_steps_per_second": 6.041,
|
| 243 |
+
"step": 3182
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 2.011313639220616,
|
| 247 |
+
"grad_norm": 10.074417114257812,
|
| 248 |
+
"learning_rate": 3.9946574481458206e-05,
|
| 249 |
+
"loss": 3.5087,
|
| 250 |
+
"step": 3200
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 2.07416719044626,
|
| 254 |
+
"grad_norm": 6.9990434646606445,
|
| 255 |
+
"learning_rate": 3.963230672532998e-05,
|
| 256 |
+
"loss": 3.5746,
|
| 257 |
+
"step": 3300
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 2.1370207416719045,
|
| 261 |
+
"grad_norm": 6.968172073364258,
|
| 262 |
+
"learning_rate": 3.931803896920176e-05,
|
| 263 |
+
"loss": 3.6324,
|
| 264 |
+
"step": 3400
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 2.1998742928975488,
|
| 268 |
+
"grad_norm": 179.99803161621094,
|
| 269 |
+
"learning_rate": 3.9003771213073545e-05,
|
| 270 |
+
"loss": 3.4072,
|
| 271 |
+
"step": 3500
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 2.262727844123193,
|
| 275 |
+
"grad_norm": 59.86805725097656,
|
| 276 |
+
"learning_rate": 3.868950345694532e-05,
|
| 277 |
+
"loss": 3.391,
|
| 278 |
+
"step": 3600
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.3255813953488373,
|
| 282 |
+
"grad_norm": 7.445355415344238,
|
| 283 |
+
"learning_rate": 3.83752357008171e-05,
|
| 284 |
+
"loss": 3.2032,
|
| 285 |
+
"step": 3700
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.3884349465744816,
|
| 289 |
+
"grad_norm": 5.553746700286865,
|
| 290 |
+
"learning_rate": 3.806096794468888e-05,
|
| 291 |
+
"loss": 3.3644,
|
| 292 |
+
"step": 3800
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 2.4512884978001255,
|
| 296 |
+
"grad_norm": 6.544325351715088,
|
| 297 |
+
"learning_rate": 3.7746700188560656e-05,
|
| 298 |
+
"loss": 3.1666,
|
| 299 |
+
"step": 3900
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 2.5141420490257698,
|
| 303 |
+
"grad_norm": 7.863962650299072,
|
| 304 |
+
"learning_rate": 3.7432432432432436e-05,
|
| 305 |
+
"loss": 3.1982,
|
| 306 |
+
"step": 4000
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 2.576995600251414,
|
| 310 |
+
"grad_norm": 10.573624610900879,
|
| 311 |
+
"learning_rate": 3.7118164676304215e-05,
|
| 312 |
+
"loss": 3.1336,
|
| 313 |
+
"step": 4100
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 2.6398491514770583,
|
| 317 |
+
"grad_norm": 8.506134986877441,
|
| 318 |
+
"learning_rate": 3.680389692017599e-05,
|
| 319 |
+
"loss": 3.0191,
|
| 320 |
+
"step": 4200
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.7027027027027026,
|
| 324 |
+
"grad_norm": 7.1274518966674805,
|
| 325 |
+
"learning_rate": 3.6489629164047774e-05,
|
| 326 |
+
"loss": 3.003,
|
| 327 |
+
"step": 4300
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 2.765556253928347,
|
| 331 |
+
"grad_norm": 5.121671199798584,
|
| 332 |
+
"learning_rate": 3.617536140791955e-05,
|
| 333 |
+
"loss": 3.085,
|
| 334 |
+
"step": 4400
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 2.828409805153991,
|
| 338 |
+
"grad_norm": 6.66685152053833,
|
| 339 |
+
"learning_rate": 3.5861093651791327e-05,
|
| 340 |
+
"loss": 3.0205,
|
| 341 |
+
"step": 4500
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 2.8912633563796355,
|
| 345 |
+
"grad_norm": 8.410430908203125,
|
| 346 |
+
"learning_rate": 3.5546825895663106e-05,
|
| 347 |
+
"loss": 2.9611,
|
| 348 |
+
"step": 4600
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 2.95411690760528,
|
| 352 |
+
"grad_norm": 6.266846179962158,
|
| 353 |
+
"learning_rate": 3.5232558139534886e-05,
|
| 354 |
+
"loss": 2.9299,
|
| 355 |
+
"step": 4700
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 3.0,
|
| 359 |
+
"eval_loss": 2.3084471225738525,
|
| 360 |
+
"eval_runtime": 20.0337,
|
| 361 |
+
"eval_samples_per_second": 47.819,
|
| 362 |
+
"eval_steps_per_second": 5.99,
|
| 363 |
+
"step": 4773
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 3.016970458830924,
|
| 367 |
+
"grad_norm": 6.011202335357666,
|
| 368 |
+
"learning_rate": 3.4918290383406665e-05,
|
| 369 |
+
"loss": 2.886,
|
| 370 |
+
"step": 4800
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 3.0798240100565684,
|
| 374 |
+
"grad_norm": 7.204225063323975,
|
| 375 |
+
"learning_rate": 3.4604022627278445e-05,
|
| 376 |
+
"loss": 2.8579,
|
| 377 |
+
"step": 4900
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 3.1426775612822127,
|
| 381 |
+
"grad_norm": 10.316048622131348,
|
| 382 |
+
"learning_rate": 3.428975487115022e-05,
|
| 383 |
+
"loss": 2.8155,
|
| 384 |
+
"step": 5000
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 3.2055311125078565,
|
| 388 |
+
"grad_norm": 6.55385684967041,
|
| 389 |
+
"learning_rate": 3.3975487115022e-05,
|
| 390 |
+
"loss": 2.8938,
|
| 391 |
+
"step": 5100
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 3.268384663733501,
|
| 395 |
+
"grad_norm": 6.081694602966309,
|
| 396 |
+
"learning_rate": 3.366121935889378e-05,
|
| 397 |
+
"loss": 2.7344,
|
| 398 |
+
"step": 5200
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 3.331238214959145,
|
| 402 |
+
"grad_norm": 8.186753273010254,
|
| 403 |
+
"learning_rate": 3.3346951602765556e-05,
|
| 404 |
+
"loss": 2.7899,
|
| 405 |
+
"step": 5300
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 3.3940917661847894,
|
| 409 |
+
"grad_norm": 7.425989627838135,
|
| 410 |
+
"learning_rate": 3.3032683846637335e-05,
|
| 411 |
+
"loss": 2.7317,
|
| 412 |
+
"step": 5400
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 3.4569453174104336,
|
| 416 |
+
"grad_norm": 5.459439277648926,
|
| 417 |
+
"learning_rate": 3.2718416090509115e-05,
|
| 418 |
+
"loss": 2.6456,
|
| 419 |
+
"step": 5500
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 3.519798868636078,
|
| 423 |
+
"grad_norm": 5.077919006347656,
|
| 424 |
+
"learning_rate": 3.2404148334380894e-05,
|
| 425 |
+
"loss": 2.6816,
|
| 426 |
+
"step": 5600
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 3.5826524198617222,
|
| 430 |
+
"grad_norm": 5.81939172744751,
|
| 431 |
+
"learning_rate": 3.2089880578252674e-05,
|
| 432 |
+
"loss": 2.64,
|
| 433 |
+
"step": 5700
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 3.6455059710873665,
|
| 437 |
+
"grad_norm": 39.74727249145508,
|
| 438 |
+
"learning_rate": 3.177561282212445e-05,
|
| 439 |
+
"loss": 2.6725,
|
| 440 |
+
"step": 5800
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 3.708359522313011,
|
| 444 |
+
"grad_norm": 5.927642345428467,
|
| 445 |
+
"learning_rate": 3.1461345065996226e-05,
|
| 446 |
+
"loss": 2.5395,
|
| 447 |
+
"step": 5900
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 3.771213073538655,
|
| 451 |
+
"grad_norm": 5.984442710876465,
|
| 452 |
+
"learning_rate": 3.114707730986801e-05,
|
| 453 |
+
"loss": 2.6297,
|
| 454 |
+
"step": 6000
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 3.834066624764299,
|
| 458 |
+
"grad_norm": 5.258358478546143,
|
| 459 |
+
"learning_rate": 3.083280955373979e-05,
|
| 460 |
+
"loss": 2.6291,
|
| 461 |
+
"step": 6100
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 3.8969201759899432,
|
| 465 |
+
"grad_norm": 5.7379937171936035,
|
| 466 |
+
"learning_rate": 3.0518541797611565e-05,
|
| 467 |
+
"loss": 2.6116,
|
| 468 |
+
"step": 6200
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 3.9597737272155875,
|
| 472 |
+
"grad_norm": 5.038835048675537,
|
| 473 |
+
"learning_rate": 3.0204274041483344e-05,
|
| 474 |
+
"loss": 2.6695,
|
| 475 |
+
"step": 6300
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 4.0,
|
| 479 |
+
"eval_loss": 2.0932769775390625,
|
| 480 |
+
"eval_runtime": 20.0417,
|
| 481 |
+
"eval_samples_per_second": 47.8,
|
| 482 |
+
"eval_steps_per_second": 5.988,
|
| 483 |
+
"step": 6364
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 4.022627278441232,
|
| 487 |
+
"grad_norm": 7.459395885467529,
|
| 488 |
+
"learning_rate": 2.9890006285355127e-05,
|
| 489 |
+
"loss": 2.6404,
|
| 490 |
+
"step": 6400
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 4.085480829666876,
|
| 494 |
+
"grad_norm": 6.721461296081543,
|
| 495 |
+
"learning_rate": 2.9575738529226903e-05,
|
| 496 |
+
"loss": 2.4614,
|
| 497 |
+
"step": 6500
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 4.14833438089252,
|
| 501 |
+
"grad_norm": 6.69769287109375,
|
| 502 |
+
"learning_rate": 2.9261470773098683e-05,
|
| 503 |
+
"loss": 2.457,
|
| 504 |
+
"step": 6600
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 4.211187932118165,
|
| 508 |
+
"grad_norm": 5.306356906890869,
|
| 509 |
+
"learning_rate": 2.894720301697046e-05,
|
| 510 |
+
"loss": 2.513,
|
| 511 |
+
"step": 6700
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 4.274041483343809,
|
| 515 |
+
"grad_norm": 5.425265312194824,
|
| 516 |
+
"learning_rate": 2.8632935260842235e-05,
|
| 517 |
+
"loss": 2.5467,
|
| 518 |
+
"step": 6800
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 4.336895034569453,
|
| 522 |
+
"grad_norm": 4.722207546234131,
|
| 523 |
+
"learning_rate": 2.8318667504714018e-05,
|
| 524 |
+
"loss": 2.3467,
|
| 525 |
+
"step": 6900
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 4.3997485857950975,
|
| 529 |
+
"grad_norm": 4.346086502075195,
|
| 530 |
+
"learning_rate": 2.8004399748585797e-05,
|
| 531 |
+
"loss": 2.5098,
|
| 532 |
+
"step": 7000
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 4.462602137020742,
|
| 536 |
+
"grad_norm": 7.4684319496154785,
|
| 537 |
+
"learning_rate": 2.7690131992457573e-05,
|
| 538 |
+
"loss": 2.4396,
|
| 539 |
+
"step": 7100
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 4.525455688246386,
|
| 543 |
+
"grad_norm": 5.709039688110352,
|
| 544 |
+
"learning_rate": 2.7375864236329353e-05,
|
| 545 |
+
"loss": 2.4688,
|
| 546 |
+
"step": 7200
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 4.58830923947203,
|
| 550 |
+
"grad_norm": 4.952858924865723,
|
| 551 |
+
"learning_rate": 2.7061596480201136e-05,
|
| 552 |
+
"loss": 2.3643,
|
| 553 |
+
"step": 7300
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 4.651162790697675,
|
| 557 |
+
"grad_norm": 6.68017578125,
|
| 558 |
+
"learning_rate": 2.6747328724072912e-05,
|
| 559 |
+
"loss": 2.4242,
|
| 560 |
+
"step": 7400
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 4.714016341923319,
|
| 564 |
+
"grad_norm": 3.584669828414917,
|
| 565 |
+
"learning_rate": 2.6433060967944688e-05,
|
| 566 |
+
"loss": 2.4552,
|
| 567 |
+
"step": 7500
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 4.776869893148963,
|
| 571 |
+
"grad_norm": 5.264488220214844,
|
| 572 |
+
"learning_rate": 2.6118793211816468e-05,
|
| 573 |
+
"loss": 2.4232,
|
| 574 |
+
"step": 7600
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 4.8397234443746076,
|
| 578 |
+
"grad_norm": 4.609414100646973,
|
| 579 |
+
"learning_rate": 2.580452545568825e-05,
|
| 580 |
+
"loss": 2.4418,
|
| 581 |
+
"step": 7700
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 4.902576995600251,
|
| 585 |
+
"grad_norm": 4.986881256103516,
|
| 586 |
+
"learning_rate": 2.5490257699560027e-05,
|
| 587 |
+
"loss": 2.4065,
|
| 588 |
+
"step": 7800
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 4.965430546825896,
|
| 592 |
+
"grad_norm": 4.9718098640441895,
|
| 593 |
+
"learning_rate": 2.5175989943431806e-05,
|
| 594 |
+
"loss": 2.4589,
|
| 595 |
+
"step": 7900
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 5.0,
|
| 599 |
+
"eval_loss": 1.984979271888733,
|
| 600 |
+
"eval_runtime": 20.0353,
|
| 601 |
+
"eval_samples_per_second": 47.816,
|
| 602 |
+
"eval_steps_per_second": 5.989,
|
| 603 |
+
"step": 7955
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 5.0282840980515395,
|
| 607 |
+
"grad_norm": 5.2526750564575195,
|
| 608 |
+
"learning_rate": 2.4861722187303586e-05,
|
| 609 |
+
"loss": 2.2708,
|
| 610 |
+
"step": 8000
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 5.091137649277184,
|
| 614 |
+
"grad_norm": 5.312747001647949,
|
| 615 |
+
"learning_rate": 2.454745443117536e-05,
|
| 616 |
+
"loss": 2.3068,
|
| 617 |
+
"step": 8100
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 5.153991200502828,
|
| 621 |
+
"grad_norm": 7.204046726226807,
|
| 622 |
+
"learning_rate": 2.423318667504714e-05,
|
| 623 |
+
"loss": 2.3729,
|
| 624 |
+
"step": 8200
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 5.216844751728472,
|
| 628 |
+
"grad_norm": 4.8044753074646,
|
| 629 |
+
"learning_rate": 2.391891891891892e-05,
|
| 630 |
+
"loss": 2.3501,
|
| 631 |
+
"step": 8300
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 5.279698302954117,
|
| 635 |
+
"grad_norm": 6.9473185539245605,
|
| 636 |
+
"learning_rate": 2.3604651162790697e-05,
|
| 637 |
+
"loss": 2.3398,
|
| 638 |
+
"step": 8400
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 5.342551854179761,
|
| 642 |
+
"grad_norm": 4.014726161956787,
|
| 643 |
+
"learning_rate": 2.3290383406662476e-05,
|
| 644 |
+
"loss": 2.2938,
|
| 645 |
+
"step": 8500
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 5.405405405405405,
|
| 649 |
+
"grad_norm": 6.722488880157471,
|
| 650 |
+
"learning_rate": 2.2976115650534256e-05,
|
| 651 |
+
"loss": 2.2354,
|
| 652 |
+
"step": 8600
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 5.4682589566310495,
|
| 656 |
+
"grad_norm": 5.856524467468262,
|
| 657 |
+
"learning_rate": 2.2661847894406035e-05,
|
| 658 |
+
"loss": 2.2757,
|
| 659 |
+
"step": 8700
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 5.531112507856694,
|
| 663 |
+
"grad_norm": 4.9930644035339355,
|
| 664 |
+
"learning_rate": 2.234758013827781e-05,
|
| 665 |
+
"loss": 2.2586,
|
| 666 |
+
"step": 8800
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 5.593966059082338,
|
| 670 |
+
"grad_norm": 5.49005126953125,
|
| 671 |
+
"learning_rate": 2.2033312382149594e-05,
|
| 672 |
+
"loss": 2.3155,
|
| 673 |
+
"step": 8900
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 5.656819610307982,
|
| 677 |
+
"grad_norm": 8.850517272949219,
|
| 678 |
+
"learning_rate": 2.171904462602137e-05,
|
| 679 |
+
"loss": 2.2841,
|
| 680 |
+
"step": 9000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 5.719673161533627,
|
| 684 |
+
"grad_norm": 5.094405651092529,
|
| 685 |
+
"learning_rate": 2.140477686989315e-05,
|
| 686 |
+
"loss": 2.3147,
|
| 687 |
+
"step": 9100
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 5.782526712759271,
|
| 691 |
+
"grad_norm": 4.709909439086914,
|
| 692 |
+
"learning_rate": 2.109050911376493e-05,
|
| 693 |
+
"loss": 2.1584,
|
| 694 |
+
"step": 9200
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 5.845380263984915,
|
| 698 |
+
"grad_norm": 4.1693525314331055,
|
| 699 |
+
"learning_rate": 2.077624135763671e-05,
|
| 700 |
+
"loss": 2.2396,
|
| 701 |
+
"step": 9300
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 5.90823381521056,
|
| 705 |
+
"grad_norm": 6.800940036773682,
|
| 706 |
+
"learning_rate": 2.0461973601508485e-05,
|
| 707 |
+
"loss": 2.301,
|
| 708 |
+
"step": 9400
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 5.971087366436204,
|
| 712 |
+
"grad_norm": 7.419278144836426,
|
| 713 |
+
"learning_rate": 2.0147705845380265e-05,
|
| 714 |
+
"loss": 2.3142,
|
| 715 |
+
"step": 9500
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 6.0,
|
| 719 |
+
"eval_loss": 1.905881643295288,
|
| 720 |
+
"eval_runtime": 20.0332,
|
| 721 |
+
"eval_samples_per_second": 47.821,
|
| 722 |
+
"eval_steps_per_second": 5.99,
|
| 723 |
+
"step": 9546
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 6.033940917661848,
|
| 727 |
+
"grad_norm": 4.217894077301025,
|
| 728 |
+
"learning_rate": 1.9833438089252044e-05,
|
| 729 |
+
"loss": 2.1013,
|
| 730 |
+
"step": 9600
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 6.096794468887492,
|
| 734 |
+
"grad_norm": 5.345584869384766,
|
| 735 |
+
"learning_rate": 1.9519170333123824e-05,
|
| 736 |
+
"loss": 2.2714,
|
| 737 |
+
"step": 9700
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 6.159648020113137,
|
| 741 |
+
"grad_norm": 5.364700794219971,
|
| 742 |
+
"learning_rate": 1.92049025769956e-05,
|
| 743 |
+
"loss": 2.2381,
|
| 744 |
+
"step": 9800
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 6.222501571338781,
|
| 748 |
+
"grad_norm": 4.380568504333496,
|
| 749 |
+
"learning_rate": 1.8890634820867383e-05,
|
| 750 |
+
"loss": 2.1527,
|
| 751 |
+
"step": 9900
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 6.285355122564425,
|
| 755 |
+
"grad_norm": 6.300790309906006,
|
| 756 |
+
"learning_rate": 1.857636706473916e-05,
|
| 757 |
+
"loss": 2.1771,
|
| 758 |
+
"step": 10000
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 6.348208673790069,
|
| 762 |
+
"grad_norm": 5.757110118865967,
|
| 763 |
+
"learning_rate": 1.8262099308610938e-05,
|
| 764 |
+
"loss": 2.1695,
|
| 765 |
+
"step": 10100
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 6.411062225015713,
|
| 769 |
+
"grad_norm": 4.908361434936523,
|
| 770 |
+
"learning_rate": 1.7947831552482718e-05,
|
| 771 |
+
"loss": 2.1056,
|
| 772 |
+
"step": 10200
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 6.473915776241357,
|
| 776 |
+
"grad_norm": 5.048102378845215,
|
| 777 |
+
"learning_rate": 1.7633563796354494e-05,
|
| 778 |
+
"loss": 2.2112,
|
| 779 |
+
"step": 10300
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 6.536769327467002,
|
| 783 |
+
"grad_norm": 8.040143013000488,
|
| 784 |
+
"learning_rate": 1.7319296040226273e-05,
|
| 785 |
+
"loss": 2.0298,
|
| 786 |
+
"step": 10400
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 6.599622878692646,
|
| 790 |
+
"grad_norm": 5.15581750869751,
|
| 791 |
+
"learning_rate": 1.7005028284098053e-05,
|
| 792 |
+
"loss": 2.1224,
|
| 793 |
+
"step": 10500
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 6.66247642991829,
|
| 797 |
+
"grad_norm": 4.935842514038086,
|
| 798 |
+
"learning_rate": 1.6690760527969832e-05,
|
| 799 |
+
"loss": 2.0772,
|
| 800 |
+
"step": 10600
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 6.725329981143934,
|
| 804 |
+
"grad_norm": 5.487718105316162,
|
| 805 |
+
"learning_rate": 1.637649277184161e-05,
|
| 806 |
+
"loss": 2.2552,
|
| 807 |
+
"step": 10700
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 6.788183532369579,
|
| 811 |
+
"grad_norm": 5.713748455047607,
|
| 812 |
+
"learning_rate": 1.6062225015713388e-05,
|
| 813 |
+
"loss": 2.1358,
|
| 814 |
+
"step": 10800
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 6.851037083595223,
|
| 818 |
+
"grad_norm": 4.882757186889648,
|
| 819 |
+
"learning_rate": 1.5747957259585168e-05,
|
| 820 |
+
"loss": 2.1613,
|
| 821 |
+
"step": 10900
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 6.913890634820867,
|
| 825 |
+
"grad_norm": 5.634950637817383,
|
| 826 |
+
"learning_rate": 1.5433689503456947e-05,
|
| 827 |
+
"loss": 2.2567,
|
| 828 |
+
"step": 11000
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 6.976744186046512,
|
| 832 |
+
"grad_norm": 5.634829044342041,
|
| 833 |
+
"learning_rate": 1.5119421747328725e-05,
|
| 834 |
+
"loss": 2.1283,
|
| 835 |
+
"step": 11100
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 7.0,
|
| 839 |
+
"eval_loss": 1.84635591506958,
|
| 840 |
+
"eval_runtime": 20.0367,
|
| 841 |
+
"eval_samples_per_second": 47.812,
|
| 842 |
+
"eval_steps_per_second": 5.989,
|
| 843 |
+
"step": 11137
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 7.039597737272156,
|
| 847 |
+
"grad_norm": 5.635861873626709,
|
| 848 |
+
"learning_rate": 1.4805153991200504e-05,
|
| 849 |
+
"loss": 2.0938,
|
| 850 |
+
"step": 11200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 7.1024512884978,
|
| 854 |
+
"grad_norm": 5.214977741241455,
|
| 855 |
+
"learning_rate": 1.4490886235072282e-05,
|
| 856 |
+
"loss": 2.062,
|
| 857 |
+
"step": 11300
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 7.1653048397234445,
|
| 861 |
+
"grad_norm": 7.498839855194092,
|
| 862 |
+
"learning_rate": 1.4176618478944062e-05,
|
| 863 |
+
"loss": 2.1292,
|
| 864 |
+
"step": 11400
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 7.228158390949089,
|
| 868 |
+
"grad_norm": 5.83459997177124,
|
| 869 |
+
"learning_rate": 1.386235072281584e-05,
|
| 870 |
+
"loss": 2.0796,
|
| 871 |
+
"step": 11500
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 7.291011942174733,
|
| 875 |
+
"grad_norm": 3.8935282230377197,
|
| 876 |
+
"learning_rate": 1.3548082966687619e-05,
|
| 877 |
+
"loss": 2.1414,
|
| 878 |
+
"step": 11600
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 7.353865493400377,
|
| 882 |
+
"grad_norm": 5.774020671844482,
|
| 883 |
+
"learning_rate": 1.3233815210559397e-05,
|
| 884 |
+
"loss": 2.145,
|
| 885 |
+
"step": 11700
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 7.416719044626022,
|
| 889 |
+
"grad_norm": 128.24192810058594,
|
| 890 |
+
"learning_rate": 1.2919547454431178e-05,
|
| 891 |
+
"loss": 2.0242,
|
| 892 |
+
"step": 11800
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 7.479572595851666,
|
| 896 |
+
"grad_norm": 4.4846367835998535,
|
| 897 |
+
"learning_rate": 1.2605279698302954e-05,
|
| 898 |
+
"loss": 2.0936,
|
| 899 |
+
"step": 11900
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 7.54242614707731,
|
| 903 |
+
"grad_norm": 5.091222763061523,
|
| 904 |
+
"learning_rate": 1.2291011942174734e-05,
|
| 905 |
+
"loss": 2.1988,
|
| 906 |
+
"step": 12000
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 7.6052796983029545,
|
| 910 |
+
"grad_norm": 3.3482093811035156,
|
| 911 |
+
"learning_rate": 1.1976744186046513e-05,
|
| 912 |
+
"loss": 2.1323,
|
| 913 |
+
"step": 12100
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 7.668133249528598,
|
| 917 |
+
"grad_norm": 5.329409599304199,
|
| 918 |
+
"learning_rate": 1.1662476429918291e-05,
|
| 919 |
+
"loss": 2.0587,
|
| 920 |
+
"step": 12200
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 7.730986800754243,
|
| 924 |
+
"grad_norm": 7.584386348724365,
|
| 925 |
+
"learning_rate": 1.134820867379007e-05,
|
| 926 |
+
"loss": 2.1341,
|
| 927 |
+
"step": 12300
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 7.7938403519798864,
|
| 931 |
+
"grad_norm": 5.996345520019531,
|
| 932 |
+
"learning_rate": 1.1033940917661848e-05,
|
| 933 |
+
"loss": 2.1108,
|
| 934 |
+
"step": 12400
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 7.856693903205531,
|
| 938 |
+
"grad_norm": 6.1731648445129395,
|
| 939 |
+
"learning_rate": 1.0719673161533628e-05,
|
| 940 |
+
"loss": 2.1218,
|
| 941 |
+
"step": 12500
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 7.919547454431175,
|
| 945 |
+
"grad_norm": 5.414481163024902,
|
| 946 |
+
"learning_rate": 1.0405405405405407e-05,
|
| 947 |
+
"loss": 2.028,
|
| 948 |
+
"step": 12600
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 7.982401005656819,
|
| 952 |
+
"grad_norm": 7.198294639587402,
|
| 953 |
+
"learning_rate": 1.0091137649277185e-05,
|
| 954 |
+
"loss": 2.0489,
|
| 955 |
+
"step": 12700
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 8.0,
|
| 959 |
+
"eval_loss": 1.8111430406570435,
|
| 960 |
+
"eval_runtime": 20.0666,
|
| 961 |
+
"eval_samples_per_second": 47.741,
|
| 962 |
+
"eval_steps_per_second": 5.98,
|
| 963 |
+
"step": 12728
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 8.045254556882464,
|
| 967 |
+
"grad_norm": 6.677022933959961,
|
| 968 |
+
"learning_rate": 9.776869893148963e-06,
|
| 969 |
+
"loss": 2.0814,
|
| 970 |
+
"step": 12800
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 8.108108108108109,
|
| 974 |
+
"grad_norm": 5.1916728019714355,
|
| 975 |
+
"learning_rate": 9.46260213702074e-06,
|
| 976 |
+
"loss": 2.119,
|
| 977 |
+
"step": 12900
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 8.170961659333752,
|
| 981 |
+
"grad_norm": 6.04162073135376,
|
| 982 |
+
"learning_rate": 9.14833438089252e-06,
|
| 983 |
+
"loss": 2.0058,
|
| 984 |
+
"step": 13000
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 8.233815210559397,
|
| 988 |
+
"grad_norm": 4.764267444610596,
|
| 989 |
+
"learning_rate": 8.8340666247643e-06,
|
| 990 |
+
"loss": 2.0113,
|
| 991 |
+
"step": 13100
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 8.29666876178504,
|
| 995 |
+
"grad_norm": 5.77971887588501,
|
| 996 |
+
"learning_rate": 8.519798868636078e-06,
|
| 997 |
+
"loss": 2.0392,
|
| 998 |
+
"step": 13200
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 8.359522313010686,
|
| 1002 |
+
"grad_norm": 5.698218822479248,
|
| 1003 |
+
"learning_rate": 8.205531112507857e-06,
|
| 1004 |
+
"loss": 2.107,
|
| 1005 |
+
"step": 13300
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 8.42237586423633,
|
| 1009 |
+
"grad_norm": 5.236012935638428,
|
| 1010 |
+
"learning_rate": 7.891263356379635e-06,
|
| 1011 |
+
"loss": 2.0829,
|
| 1012 |
+
"step": 13400
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 8.485229415461973,
|
| 1016 |
+
"grad_norm": 4.379955291748047,
|
| 1017 |
+
"learning_rate": 7.576995600251414e-06,
|
| 1018 |
+
"loss": 1.9321,
|
| 1019 |
+
"step": 13500
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 8.548082966687618,
|
| 1023 |
+
"grad_norm": 6.034859657287598,
|
| 1024 |
+
"learning_rate": 7.262727844123193e-06,
|
| 1025 |
+
"loss": 2.1013,
|
| 1026 |
+
"step": 13600
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 8.610936517913261,
|
| 1030 |
+
"grad_norm": 5.320705413818359,
|
| 1031 |
+
"learning_rate": 6.948460087994972e-06,
|
| 1032 |
+
"loss": 2.0543,
|
| 1033 |
+
"step": 13700
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 8.673790069138906,
|
| 1037 |
+
"grad_norm": 5.735895156860352,
|
| 1038 |
+
"learning_rate": 6.634192331866751e-06,
|
| 1039 |
+
"loss": 2.0594,
|
| 1040 |
+
"step": 13800
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 8.73664362036455,
|
| 1044 |
+
"grad_norm": 4.845800876617432,
|
| 1045 |
+
"learning_rate": 6.31992457573853e-06,
|
| 1046 |
+
"loss": 1.9402,
|
| 1047 |
+
"step": 13900
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 8.799497171590195,
|
| 1051 |
+
"grad_norm": 4.628382682800293,
|
| 1052 |
+
"learning_rate": 6.0056568196103085e-06,
|
| 1053 |
+
"loss": 1.9937,
|
| 1054 |
+
"step": 14000
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 8.862350722815838,
|
| 1058 |
+
"grad_norm": 4.747410774230957,
|
| 1059 |
+
"learning_rate": 5.691389063482086e-06,
|
| 1060 |
+
"loss": 2.0654,
|
| 1061 |
+
"step": 14100
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 8.925204274041484,
|
| 1065 |
+
"grad_norm": 4.694166660308838,
|
| 1066 |
+
"learning_rate": 5.377121307353866e-06,
|
| 1067 |
+
"loss": 2.0523,
|
| 1068 |
+
"step": 14200
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 8.988057825267127,
|
| 1072 |
+
"grad_norm": 6.711084365844727,
|
| 1073 |
+
"learning_rate": 5.0628535512256445e-06,
|
| 1074 |
+
"loss": 1.9856,
|
| 1075 |
+
"step": 14300
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 9.0,
|
| 1079 |
+
"eval_loss": 1.7920939922332764,
|
| 1080 |
+
"eval_runtime": 20.0378,
|
| 1081 |
+
"eval_samples_per_second": 47.81,
|
| 1082 |
+
"eval_steps_per_second": 5.989,
|
| 1083 |
+
"step": 14319
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 9.050911376492772,
|
| 1087 |
+
"grad_norm": 6.053162097930908,
|
| 1088 |
+
"learning_rate": 4.748585795097423e-06,
|
| 1089 |
+
"loss": 2.0392,
|
| 1090 |
+
"step": 14400
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 9.113764927718416,
|
| 1094 |
+
"grad_norm": 4.806529521942139,
|
| 1095 |
+
"learning_rate": 4.434318038969202e-06,
|
| 1096 |
+
"loss": 2.0308,
|
| 1097 |
+
"step": 14500
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 9.17661847894406,
|
| 1101 |
+
"grad_norm": 4.725819110870361,
|
| 1102 |
+
"learning_rate": 4.1200502828409805e-06,
|
| 1103 |
+
"loss": 2.0441,
|
| 1104 |
+
"step": 14600
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 9.239472030169704,
|
| 1108 |
+
"grad_norm": 4.637420177459717,
|
| 1109 |
+
"learning_rate": 3.8057825267127596e-06,
|
| 1110 |
+
"loss": 2.0061,
|
| 1111 |
+
"step": 14700
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 9.30232558139535,
|
| 1115 |
+
"grad_norm": 6.441665172576904,
|
| 1116 |
+
"learning_rate": 3.4915147705845382e-06,
|
| 1117 |
+
"loss": 2.1299,
|
| 1118 |
+
"step": 14800
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 9.365179132620993,
|
| 1122 |
+
"grad_norm": 3.506943941116333,
|
| 1123 |
+
"learning_rate": 3.1772470144563173e-06,
|
| 1124 |
+
"loss": 1.9443,
|
| 1125 |
+
"step": 14900
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 9.428032683846638,
|
| 1129 |
+
"grad_norm": 8.454822540283203,
|
| 1130 |
+
"learning_rate": 2.8629792583280956e-06,
|
| 1131 |
+
"loss": 2.0327,
|
| 1132 |
+
"step": 15000
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 9.490886235072281,
|
| 1136 |
+
"grad_norm": 5.021187782287598,
|
| 1137 |
+
"learning_rate": 2.5487115021998746e-06,
|
| 1138 |
+
"loss": 1.9839,
|
| 1139 |
+
"step": 15100
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 9.553739786297927,
|
| 1143 |
+
"grad_norm": 6.3962016105651855,
|
| 1144 |
+
"learning_rate": 2.234443746071653e-06,
|
| 1145 |
+
"loss": 2.0604,
|
| 1146 |
+
"step": 15200
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 9.61659333752357,
|
| 1150 |
+
"grad_norm": 5.531436443328857,
|
| 1151 |
+
"learning_rate": 1.920175989943432e-06,
|
| 1152 |
+
"loss": 2.0168,
|
| 1153 |
+
"step": 15300
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 9.679446888749215,
|
| 1157 |
+
"grad_norm": 4.300695896148682,
|
| 1158 |
+
"learning_rate": 1.6059082338152106e-06,
|
| 1159 |
+
"loss": 1.9994,
|
| 1160 |
+
"step": 15400
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 9.742300439974859,
|
| 1164 |
+
"grad_norm": 3.102018356323242,
|
| 1165 |
+
"learning_rate": 1.2916404776869893e-06,
|
| 1166 |
+
"loss": 2.0441,
|
| 1167 |
+
"step": 15500
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 9.805153991200502,
|
| 1171 |
+
"grad_norm": 4.91919469833374,
|
| 1172 |
+
"learning_rate": 9.773727215587681e-07,
|
| 1173 |
+
"loss": 1.9584,
|
| 1174 |
+
"step": 15600
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 9.868007542426147,
|
| 1178 |
+
"grad_norm": 4.21737813949585,
|
| 1179 |
+
"learning_rate": 6.631049654305469e-07,
|
| 1180 |
+
"loss": 2.0019,
|
| 1181 |
+
"step": 15700
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 9.930861093651792,
|
| 1185 |
+
"grad_norm": 4.098769187927246,
|
| 1186 |
+
"learning_rate": 3.4883720930232557e-07,
|
| 1187 |
+
"loss": 2.0121,
|
| 1188 |
+
"step": 15800
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 9.993714644877436,
|
| 1192 |
+
"grad_norm": 4.722096920013428,
|
| 1193 |
+
"learning_rate": 3.456945317410434e-08,
|
| 1194 |
+
"loss": 2.0196,
|
| 1195 |
+
"step": 15900
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 10.0,
|
| 1199 |
+
"eval_loss": 1.787421464920044,
|
| 1200 |
+
"eval_runtime": 20.0243,
|
| 1201 |
+
"eval_samples_per_second": 47.842,
|
| 1202 |
+
"eval_steps_per_second": 5.993,
|
| 1203 |
+
"step": 15910
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 10.056568196103079,
|
| 1207 |
+
"grad_norm": 3.8331987857818604,
|
| 1208 |
+
"learning_rate": 2.4860150848522942e-05,
|
| 1209 |
+
"loss": 2.0388,
|
| 1210 |
+
"step": 16000
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 10.119421747328724,
|
| 1214 |
+
"grad_norm": 3.9292027950286865,
|
| 1215 |
+
"learning_rate": 2.4703016970458832e-05,
|
| 1216 |
+
"loss": 2.0913,
|
| 1217 |
+
"step": 16100
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 10.182275298554368,
|
| 1221 |
+
"grad_norm": 5.124855995178223,
|
| 1222 |
+
"learning_rate": 2.454588309239472e-05,
|
| 1223 |
+
"loss": 2.0452,
|
| 1224 |
+
"step": 16200
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 10.245128849780013,
|
| 1228 |
+
"grad_norm": 5.743933200836182,
|
| 1229 |
+
"learning_rate": 2.438874921433061e-05,
|
| 1230 |
+
"loss": 2.016,
|
| 1231 |
+
"step": 16300
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 10.307982401005656,
|
| 1235 |
+
"grad_norm": 6.4510931968688965,
|
| 1236 |
+
"learning_rate": 2.42316153362665e-05,
|
| 1237 |
+
"loss": 1.9785,
|
| 1238 |
+
"step": 16400
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 10.370835952231301,
|
| 1242 |
+
"grad_norm": 6.550465106964111,
|
| 1243 |
+
"learning_rate": 2.4074481458202387e-05,
|
| 1244 |
+
"loss": 1.9912,
|
| 1245 |
+
"step": 16500
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 10.433689503456945,
|
| 1249 |
+
"grad_norm": 5.37285852432251,
|
| 1250 |
+
"learning_rate": 2.391734758013828e-05,
|
| 1251 |
+
"loss": 2.0549,
|
| 1252 |
+
"step": 16600
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 10.49654305468259,
|
| 1256 |
+
"grad_norm": 5.4893412590026855,
|
| 1257 |
+
"learning_rate": 2.376021370207417e-05,
|
| 1258 |
+
"loss": 1.9434,
|
| 1259 |
+
"step": 16700
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 10.559396605908233,
|
| 1263 |
+
"grad_norm": 4.316259384155273,
|
| 1264 |
+
"learning_rate": 2.3603079824010057e-05,
|
| 1265 |
+
"loss": 1.8413,
|
| 1266 |
+
"step": 16800
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 10.622250157133879,
|
| 1270 |
+
"grad_norm": 3.4342756271362305,
|
| 1271 |
+
"learning_rate": 2.3445945945945946e-05,
|
| 1272 |
+
"loss": 1.9312,
|
| 1273 |
+
"step": 16900
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 10.685103708359522,
|
| 1277 |
+
"grad_norm": 5.680815696716309,
|
| 1278 |
+
"learning_rate": 2.3288812067881836e-05,
|
| 1279 |
+
"loss": 1.9678,
|
| 1280 |
+
"step": 17000
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 10.747957259585167,
|
| 1284 |
+
"grad_norm": 6.04569149017334,
|
| 1285 |
+
"learning_rate": 2.3131678189817726e-05,
|
| 1286 |
+
"loss": 2.0329,
|
| 1287 |
+
"step": 17100
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 10.81081081081081,
|
| 1291 |
+
"grad_norm": 9.336991310119629,
|
| 1292 |
+
"learning_rate": 2.2974544311753616e-05,
|
| 1293 |
+
"loss": 1.9575,
|
| 1294 |
+
"step": 17200
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 10.873664362036456,
|
| 1298 |
+
"grad_norm": 3.826447010040283,
|
| 1299 |
+
"learning_rate": 2.2817410433689505e-05,
|
| 1300 |
+
"loss": 1.9692,
|
| 1301 |
+
"step": 17300
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 10.936517913262099,
|
| 1305 |
+
"grad_norm": 4.134801387786865,
|
| 1306 |
+
"learning_rate": 2.2660276555625392e-05,
|
| 1307 |
+
"loss": 2.0406,
|
| 1308 |
+
"step": 17400
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 10.999371464487744,
|
| 1312 |
+
"grad_norm": 5.291431903839111,
|
| 1313 |
+
"learning_rate": 2.2503142677561285e-05,
|
| 1314 |
+
"loss": 1.9631,
|
| 1315 |
+
"step": 17500
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 11.0,
|
| 1319 |
+
"eval_loss": 1.7517410516738892,
|
| 1320 |
+
"eval_runtime": 21.6572,
|
| 1321 |
+
"eval_samples_per_second": 44.235,
|
| 1322 |
+
"eval_steps_per_second": 5.541,
|
| 1323 |
+
"step": 17501
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 11.062225015713388,
|
| 1327 |
+
"grad_norm": 4.9575066566467285,
|
| 1328 |
+
"learning_rate": 2.234600879949717e-05,
|
| 1329 |
+
"loss": 1.9381,
|
| 1330 |
+
"step": 17600
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 11.125078566939033,
|
| 1334 |
+
"grad_norm": 12.871175765991211,
|
| 1335 |
+
"learning_rate": 2.218887492143306e-05,
|
| 1336 |
+
"loss": 1.8867,
|
| 1337 |
+
"step": 17700
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 11.187932118164676,
|
| 1341 |
+
"grad_norm": 4.3662519454956055,
|
| 1342 |
+
"learning_rate": 2.203174104336895e-05,
|
| 1343 |
+
"loss": 1.9713,
|
| 1344 |
+
"step": 17800
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 11.250785669390321,
|
| 1348 |
+
"grad_norm": 5.662289619445801,
|
| 1349 |
+
"learning_rate": 2.187460716530484e-05,
|
| 1350 |
+
"loss": 1.9188,
|
| 1351 |
+
"step": 17900
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 11.313639220615965,
|
| 1355 |
+
"grad_norm": 7.633818626403809,
|
| 1356 |
+
"learning_rate": 2.171747328724073e-05,
|
| 1357 |
+
"loss": 1.9142,
|
| 1358 |
+
"step": 18000
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 11.376492771841608,
|
| 1362 |
+
"grad_norm": 4.940028667449951,
|
| 1363 |
+
"learning_rate": 2.156033940917662e-05,
|
| 1364 |
+
"loss": 1.8697,
|
| 1365 |
+
"step": 18100
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 11.439346323067253,
|
| 1369 |
+
"grad_norm": 5.070211410522461,
|
| 1370 |
+
"learning_rate": 2.1403205531112506e-05,
|
| 1371 |
+
"loss": 1.9624,
|
| 1372 |
+
"step": 18200
|
| 1373 |
+
},
|
| 1374 |
+
{
|
| 1375 |
+
"epoch": 11.502199874292897,
|
| 1376 |
+
"grad_norm": 7.409548282623291,
|
| 1377 |
+
"learning_rate": 2.12460716530484e-05,
|
| 1378 |
+
"loss": 1.9283,
|
| 1379 |
+
"step": 18300
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 11.565053425518542,
|
| 1383 |
+
"grad_norm": 6.541192531585693,
|
| 1384 |
+
"learning_rate": 2.108893777498429e-05,
|
| 1385 |
+
"loss": 1.9357,
|
| 1386 |
+
"step": 18400
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 11.627906976744185,
|
| 1390 |
+
"grad_norm": 5.941864967346191,
|
| 1391 |
+
"learning_rate": 2.0931803896920176e-05,
|
| 1392 |
+
"loss": 1.869,
|
| 1393 |
+
"step": 18500
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"epoch": 11.69076052796983,
|
| 1397 |
+
"grad_norm": 9.418646812438965,
|
| 1398 |
+
"learning_rate": 2.0774670018856065e-05,
|
| 1399 |
+
"loss": 1.8518,
|
| 1400 |
+
"step": 18600
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 11.753614079195474,
|
| 1404 |
+
"grad_norm": 5.367152690887451,
|
| 1405 |
+
"learning_rate": 2.061753614079196e-05,
|
| 1406 |
+
"loss": 1.8945,
|
| 1407 |
+
"step": 18700
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 11.81646763042112,
|
| 1411 |
+
"grad_norm": 5.896432399749756,
|
| 1412 |
+
"learning_rate": 2.0460402262727845e-05,
|
| 1413 |
+
"loss": 1.8569,
|
| 1414 |
+
"step": 18800
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 11.879321181646763,
|
| 1418 |
+
"grad_norm": 6.137564182281494,
|
| 1419 |
+
"learning_rate": 2.0303268384663735e-05,
|
| 1420 |
+
"loss": 1.9179,
|
| 1421 |
+
"step": 18900
|
| 1422 |
+
},
|
| 1423 |
+
{
|
| 1424 |
+
"epoch": 11.942174732872408,
|
| 1425 |
+
"grad_norm": 4.5933918952941895,
|
| 1426 |
+
"learning_rate": 2.0146134506599625e-05,
|
| 1427 |
+
"loss": 1.8941,
|
| 1428 |
+
"step": 19000
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 12.0,
|
| 1432 |
+
"eval_loss": 1.7062737941741943,
|
| 1433 |
+
"eval_runtime": 21.7167,
|
| 1434 |
+
"eval_samples_per_second": 44.114,
|
| 1435 |
+
"eval_steps_per_second": 5.526,
|
| 1436 |
+
"step": 19092
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 12.005028284098051,
|
| 1440 |
+
"grad_norm": 5.298050880432129,
|
| 1441 |
+
"learning_rate": 1.998900062853551e-05,
|
| 1442 |
+
"loss": 1.8681,
|
| 1443 |
+
"step": 19100
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 12.067881835323696,
|
| 1447 |
+
"grad_norm": 7.001854419708252,
|
| 1448 |
+
"learning_rate": 1.9831866750471404e-05,
|
| 1449 |
+
"loss": 1.8377,
|
| 1450 |
+
"step": 19200
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 12.13073538654934,
|
| 1454 |
+
"grad_norm": 4.692386150360107,
|
| 1455 |
+
"learning_rate": 1.9674732872407294e-05,
|
| 1456 |
+
"loss": 1.8279,
|
| 1457 |
+
"step": 19300
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 12.193588937774985,
|
| 1461 |
+
"grad_norm": 6.864208221435547,
|
| 1462 |
+
"learning_rate": 1.951759899434318e-05,
|
| 1463 |
+
"loss": 1.8855,
|
| 1464 |
+
"step": 19400
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 12.256442489000628,
|
| 1468 |
+
"grad_norm": 3.883880853652954,
|
| 1469 |
+
"learning_rate": 1.936046511627907e-05,
|
| 1470 |
+
"loss": 1.84,
|
| 1471 |
+
"step": 19500
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 12.319296040226273,
|
| 1475 |
+
"grad_norm": 5.302524566650391,
|
| 1476 |
+
"learning_rate": 1.920333123821496e-05,
|
| 1477 |
+
"loss": 1.8791,
|
| 1478 |
+
"step": 19600
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 12.382149591451917,
|
| 1482 |
+
"grad_norm": 6.854051113128662,
|
| 1483 |
+
"learning_rate": 1.904619736015085e-05,
|
| 1484 |
+
"loss": 1.9189,
|
| 1485 |
+
"step": 19700
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 12.445003142677562,
|
| 1489 |
+
"grad_norm": 4.728283405303955,
|
| 1490 |
+
"learning_rate": 1.888906348208674e-05,
|
| 1491 |
+
"loss": 1.8903,
|
| 1492 |
+
"step": 19800
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 12.507856693903205,
|
| 1496 |
+
"grad_norm": 4.314347267150879,
|
| 1497 |
+
"learning_rate": 1.8731929604022626e-05,
|
| 1498 |
+
"loss": 1.8615,
|
| 1499 |
+
"step": 19900
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 12.57071024512885,
|
| 1503 |
+
"grad_norm": 3.873619318008423,
|
| 1504 |
+
"learning_rate": 1.857479572595852e-05,
|
| 1505 |
+
"loss": 1.8232,
|
| 1506 |
+
"step": 20000
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 12.633563796354494,
|
| 1510 |
+
"grad_norm": 6.445096969604492,
|
| 1511 |
+
"learning_rate": 1.841766184789441e-05,
|
| 1512 |
+
"loss": 1.7764,
|
| 1513 |
+
"step": 20100
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 12.696417347580137,
|
| 1517 |
+
"grad_norm": 4.258322715759277,
|
| 1518 |
+
"learning_rate": 1.8260527969830295e-05,
|
| 1519 |
+
"loss": 1.869,
|
| 1520 |
+
"step": 20200
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 12.759270898805783,
|
| 1524 |
+
"grad_norm": 7.782538414001465,
|
| 1525 |
+
"learning_rate": 1.8103394091766185e-05,
|
| 1526 |
+
"loss": 1.7986,
|
| 1527 |
+
"step": 20300
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 12.822124450031426,
|
| 1531 |
+
"grad_norm": 7.189488887786865,
|
| 1532 |
+
"learning_rate": 1.7946260213702078e-05,
|
| 1533 |
+
"loss": 1.8448,
|
| 1534 |
+
"step": 20400
|
| 1535 |
+
},
|
| 1536 |
+
{
|
| 1537 |
+
"epoch": 12.884978001257071,
|
| 1538 |
+
"grad_norm": 5.59601354598999,
|
| 1539 |
+
"learning_rate": 1.7789126335637964e-05,
|
| 1540 |
+
"loss": 1.7924,
|
| 1541 |
+
"step": 20500
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 12.947831552482715,
|
| 1545 |
+
"grad_norm": 4.675200939178467,
|
| 1546 |
+
"learning_rate": 1.7631992457573854e-05,
|
| 1547 |
+
"loss": 1.8212,
|
| 1548 |
+
"step": 20600
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 13.0,
|
| 1552 |
+
"eval_loss": 1.6696668863296509,
|
| 1553 |
+
"eval_runtime": 21.645,
|
| 1554 |
+
"eval_samples_per_second": 44.26,
|
| 1555 |
+
"eval_steps_per_second": 5.544,
|
| 1556 |
+
"step": 20683
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 13.01068510370836,
|
| 1560 |
+
"grad_norm": 3.3650217056274414,
|
| 1561 |
+
"learning_rate": 1.7474858579509744e-05,
|
| 1562 |
+
"loss": 1.6872,
|
| 1563 |
+
"step": 20700
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 13.073538654934003,
|
| 1567 |
+
"grad_norm": 6.4758219718933105,
|
| 1568 |
+
"learning_rate": 1.731772470144563e-05,
|
| 1569 |
+
"loss": 1.8029,
|
| 1570 |
+
"step": 20800
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 13.136392206159648,
|
| 1574 |
+
"grad_norm": 4.500367641448975,
|
| 1575 |
+
"learning_rate": 1.7160590823381523e-05,
|
| 1576 |
+
"loss": 1.8655,
|
| 1577 |
+
"step": 20900
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 13.199245757385292,
|
| 1581 |
+
"grad_norm": 5.369949817657471,
|
| 1582 |
+
"learning_rate": 1.7003456945317413e-05,
|
| 1583 |
+
"loss": 1.821,
|
| 1584 |
+
"step": 21000
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 13.262099308610937,
|
| 1588 |
+
"grad_norm": 4.84245491027832,
|
| 1589 |
+
"learning_rate": 1.68463230672533e-05,
|
| 1590 |
+
"loss": 1.7454,
|
| 1591 |
+
"step": 21100
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 13.32495285983658,
|
| 1595 |
+
"grad_norm": 4.510051727294922,
|
| 1596 |
+
"learning_rate": 1.668918918918919e-05,
|
| 1597 |
+
"loss": 1.8378,
|
| 1598 |
+
"step": 21200
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 13.387806411062225,
|
| 1602 |
+
"grad_norm": 5.163560390472412,
|
| 1603 |
+
"learning_rate": 1.653205531112508e-05,
|
| 1604 |
+
"loss": 1.7985,
|
| 1605 |
+
"step": 21300
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 13.450659962287869,
|
| 1609 |
+
"grad_norm": 4.454617023468018,
|
| 1610 |
+
"learning_rate": 1.637492143306097e-05,
|
| 1611 |
+
"loss": 1.8177,
|
| 1612 |
+
"step": 21400
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 13.513513513513514,
|
| 1616 |
+
"grad_norm": 3.672908067703247,
|
| 1617 |
+
"learning_rate": 1.6217787554996858e-05,
|
| 1618 |
+
"loss": 1.6908,
|
| 1619 |
+
"step": 21500
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 13.576367064739157,
|
| 1623 |
+
"grad_norm": 4.549923419952393,
|
| 1624 |
+
"learning_rate": 1.6060653676932748e-05,
|
| 1625 |
+
"loss": 1.7603,
|
| 1626 |
+
"step": 21600
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 13.639220615964803,
|
| 1630 |
+
"grad_norm": 5.733989715576172,
|
| 1631 |
+
"learning_rate": 1.5903519798868638e-05,
|
| 1632 |
+
"loss": 1.7689,
|
| 1633 |
+
"step": 21700
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 13.702074167190446,
|
| 1637 |
+
"grad_norm": 4.507519245147705,
|
| 1638 |
+
"learning_rate": 1.5746385920804527e-05,
|
| 1639 |
+
"loss": 1.7984,
|
| 1640 |
+
"step": 21800
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 13.764927718416091,
|
| 1644 |
+
"grad_norm": 4.713226795196533,
|
| 1645 |
+
"learning_rate": 1.5589252042740414e-05,
|
| 1646 |
+
"loss": 1.8011,
|
| 1647 |
+
"step": 21900
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 13.827781269641735,
|
| 1651 |
+
"grad_norm": 4.300686359405518,
|
| 1652 |
+
"learning_rate": 1.5432118164676304e-05,
|
| 1653 |
+
"loss": 1.7743,
|
| 1654 |
+
"step": 22000
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 13.89063482086738,
|
| 1658 |
+
"grad_norm": 4.702789306640625,
|
| 1659 |
+
"learning_rate": 1.5274984286612197e-05,
|
| 1660 |
+
"loss": 1.6903,
|
| 1661 |
+
"step": 22100
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 13.953488372093023,
|
| 1665 |
+
"grad_norm": 6.481640815734863,
|
| 1666 |
+
"learning_rate": 1.5117850408548085e-05,
|
| 1667 |
+
"loss": 1.822,
|
| 1668 |
+
"step": 22200
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 14.0,
|
| 1672 |
+
"eval_loss": 1.648952603340149,
|
| 1673 |
+
"eval_runtime": 21.6512,
|
| 1674 |
+
"eval_samples_per_second": 44.247,
|
| 1675 |
+
"eval_steps_per_second": 5.542,
|
| 1676 |
+
"step": 22274
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 14.016341923318668,
|
| 1680 |
+
"grad_norm": 4.320845127105713,
|
| 1681 |
+
"learning_rate": 2.1968573224387177e-05,
|
| 1682 |
+
"loss": 1.7866,
|
| 1683 |
+
"step": 22300
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 14.079195474544312,
|
| 1687 |
+
"grad_norm": 5.575278282165527,
|
| 1688 |
+
"learning_rate": 2.184286612193589e-05,
|
| 1689 |
+
"loss": 1.7572,
|
| 1690 |
+
"step": 22400
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 14.142049025769955,
|
| 1694 |
+
"grad_norm": 5.764155387878418,
|
| 1695 |
+
"learning_rate": 2.17171590194846e-05,
|
| 1696 |
+
"loss": 1.7566,
|
| 1697 |
+
"step": 22500
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 14.2049025769956,
|
| 1701 |
+
"grad_norm": 4.854477882385254,
|
| 1702 |
+
"learning_rate": 2.1591451917033316e-05,
|
| 1703 |
+
"loss": 1.7517,
|
| 1704 |
+
"step": 22600
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 14.267756128221244,
|
| 1708 |
+
"grad_norm": 4.7141618728637695,
|
| 1709 |
+
"learning_rate": 2.1465744814582025e-05,
|
| 1710 |
+
"loss": 1.713,
|
| 1711 |
+
"step": 22700
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 14.330609679446889,
|
| 1715 |
+
"grad_norm": 4.3324785232543945,
|
| 1716 |
+
"learning_rate": 2.1340037712130736e-05,
|
| 1717 |
+
"loss": 1.7511,
|
| 1718 |
+
"step": 22800
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 14.393463230672532,
|
| 1722 |
+
"grad_norm": 3.4204530715942383,
|
| 1723 |
+
"learning_rate": 2.1214330609679448e-05,
|
| 1724 |
+
"loss": 1.7451,
|
| 1725 |
+
"step": 22900
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 14.456316781898177,
|
| 1729 |
+
"grad_norm": 4.925296783447266,
|
| 1730 |
+
"learning_rate": 2.108862350722816e-05,
|
| 1731 |
+
"loss": 1.6868,
|
| 1732 |
+
"step": 23000
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 14.51917033312382,
|
| 1736 |
+
"grad_norm": 4.997200965881348,
|
| 1737 |
+
"learning_rate": 2.0962916404776872e-05,
|
| 1738 |
+
"loss": 1.7259,
|
| 1739 |
+
"step": 23100
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 14.582023884349466,
|
| 1743 |
+
"grad_norm": 4.816483497619629,
|
| 1744 |
+
"learning_rate": 2.0837209302325584e-05,
|
| 1745 |
+
"loss": 1.7716,
|
| 1746 |
+
"step": 23200
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 14.64487743557511,
|
| 1750 |
+
"grad_norm": 5.224360466003418,
|
| 1751 |
+
"learning_rate": 2.0711502199874295e-05,
|
| 1752 |
+
"loss": 1.7039,
|
| 1753 |
+
"step": 23300
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 14.707730986800755,
|
| 1757 |
+
"grad_norm": 7.450541019439697,
|
| 1758 |
+
"learning_rate": 2.0585795097423004e-05,
|
| 1759 |
+
"loss": 1.6634,
|
| 1760 |
+
"step": 23400
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 14.770584538026398,
|
| 1764 |
+
"grad_norm": 5.811767101287842,
|
| 1765 |
+
"learning_rate": 2.0460087994971716e-05,
|
| 1766 |
+
"loss": 1.7526,
|
| 1767 |
+
"step": 23500
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 14.833438089252043,
|
| 1771 |
+
"grad_norm": 4.1061272621154785,
|
| 1772 |
+
"learning_rate": 2.0334380892520427e-05,
|
| 1773 |
+
"loss": 1.7612,
|
| 1774 |
+
"step": 23600
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 14.896291640477687,
|
| 1778 |
+
"grad_norm": 4.599556922912598,
|
| 1779 |
+
"learning_rate": 2.020867379006914e-05,
|
| 1780 |
+
"loss": 1.776,
|
| 1781 |
+
"step": 23700
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 14.959145191703332,
|
| 1785 |
+
"grad_norm": 4.085700988769531,
|
| 1786 |
+
"learning_rate": 2.008296668761785e-05,
|
| 1787 |
+
"loss": 1.7143,
|
| 1788 |
+
"step": 23800
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 15.0,
|
| 1792 |
+
"eval_loss": 1.6270309686660767,
|
| 1793 |
+
"eval_runtime": 20.346,
|
| 1794 |
+
"eval_samples_per_second": 47.085,
|
| 1795 |
+
"eval_steps_per_second": 5.898,
|
| 1796 |
+
"step": 23865
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 15.021998742928975,
|
| 1800 |
+
"grad_norm": 8.476902961730957,
|
| 1801 |
+
"learning_rate": 1.9957259585166563e-05,
|
| 1802 |
+
"loss": 1.6504,
|
| 1803 |
+
"step": 23900
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 15.08485229415462,
|
| 1807 |
+
"grad_norm": 4.84979772567749,
|
| 1808 |
+
"learning_rate": 1.9831552482715275e-05,
|
| 1809 |
+
"loss": 1.7259,
|
| 1810 |
+
"step": 24000
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 15.147705845380264,
|
| 1814 |
+
"grad_norm": 4.314637184143066,
|
| 1815 |
+
"learning_rate": 1.9705845380263983e-05,
|
| 1816 |
+
"loss": 1.6254,
|
| 1817 |
+
"step": 24100
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 15.210559396605909,
|
| 1821 |
+
"grad_norm": 4.656597137451172,
|
| 1822 |
+
"learning_rate": 1.9580138277812698e-05,
|
| 1823 |
+
"loss": 1.7493,
|
| 1824 |
+
"step": 24200
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 15.273412947831552,
|
| 1828 |
+
"grad_norm": 4.276788711547852,
|
| 1829 |
+
"learning_rate": 1.945443117536141e-05,
|
| 1830 |
+
"loss": 1.6797,
|
| 1831 |
+
"step": 24300
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 15.336266499057198,
|
| 1835 |
+
"grad_norm": 3.9574031829833984,
|
| 1836 |
+
"learning_rate": 1.9328724072910122e-05,
|
| 1837 |
+
"loss": 1.716,
|
| 1838 |
+
"step": 24400
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 15.399120050282841,
|
| 1842 |
+
"grad_norm": 8.148831367492676,
|
| 1843 |
+
"learning_rate": 1.920301697045883e-05,
|
| 1844 |
+
"loss": 1.6737,
|
| 1845 |
+
"step": 24500
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 15.461973601508486,
|
| 1849 |
+
"grad_norm": 3.8734018802642822,
|
| 1850 |
+
"learning_rate": 1.9077309868007542e-05,
|
| 1851 |
+
"loss": 1.6452,
|
| 1852 |
+
"step": 24600
|
| 1853 |
+
},
|
| 1854 |
+
{
|
| 1855 |
+
"epoch": 15.52482715273413,
|
| 1856 |
+
"grad_norm": 4.928835391998291,
|
| 1857 |
+
"learning_rate": 1.8951602765556257e-05,
|
| 1858 |
+
"loss": 1.7134,
|
| 1859 |
+
"step": 24700
|
| 1860 |
+
},
|
| 1861 |
+
{
|
| 1862 |
+
"epoch": 15.587680703959773,
|
| 1863 |
+
"grad_norm": 4.991033554077148,
|
| 1864 |
+
"learning_rate": 1.8825895663104966e-05,
|
| 1865 |
+
"loss": 1.7327,
|
| 1866 |
+
"step": 24800
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 15.650534255185418,
|
| 1870 |
+
"grad_norm": 4.160732269287109,
|
| 1871 |
+
"learning_rate": 1.8700188560653677e-05,
|
| 1872 |
+
"loss": 1.6678,
|
| 1873 |
+
"step": 24900
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"epoch": 15.713387806411061,
|
| 1877 |
+
"grad_norm": 6.523078441619873,
|
| 1878 |
+
"learning_rate": 1.857448145820239e-05,
|
| 1879 |
+
"loss": 1.6856,
|
| 1880 |
+
"step": 25000
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 15.776241357636707,
|
| 1884 |
+
"grad_norm": 6.306403636932373,
|
| 1885 |
+
"learning_rate": 1.84487743557511e-05,
|
| 1886 |
+
"loss": 1.6699,
|
| 1887 |
+
"step": 25100
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 15.83909490886235,
|
| 1891 |
+
"grad_norm": 4.479640483856201,
|
| 1892 |
+
"learning_rate": 1.832306725329981e-05,
|
| 1893 |
+
"loss": 1.676,
|
| 1894 |
+
"step": 25200
|
| 1895 |
+
},
|
| 1896 |
+
{
|
| 1897 |
+
"epoch": 15.901948460087995,
|
| 1898 |
+
"grad_norm": 4.6891279220581055,
|
| 1899 |
+
"learning_rate": 1.8197360150848525e-05,
|
| 1900 |
+
"loss": 1.667,
|
| 1901 |
+
"step": 25300
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 15.964802011313639,
|
| 1905 |
+
"grad_norm": 5.908668518066406,
|
| 1906 |
+
"learning_rate": 1.8071653048397236e-05,
|
| 1907 |
+
"loss": 1.6267,
|
| 1908 |
+
"step": 25400
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 16.0,
|
| 1912 |
+
"eval_loss": 1.608726143836975,
|
| 1913 |
+
"eval_runtime": 20.3571,
|
| 1914 |
+
"eval_samples_per_second": 47.06,
|
| 1915 |
+
"eval_steps_per_second": 5.895,
|
| 1916 |
+
"step": 25456
|
| 1917 |
+
},
|
| 1918 |
+
{
|
| 1919 |
+
"epoch": 16.027655562539284,
|
| 1920 |
+
"grad_norm": 4.081086158752441,
|
| 1921 |
+
"learning_rate": 1.7945945945945948e-05,
|
| 1922 |
+
"loss": 1.5625,
|
| 1923 |
+
"step": 25500
|
| 1924 |
+
},
|
| 1925 |
+
{
|
| 1926 |
+
"epoch": 16.090509113764927,
|
| 1927 |
+
"grad_norm": 3.7648415565490723,
|
| 1928 |
+
"learning_rate": 1.7820238843494657e-05,
|
| 1929 |
+
"loss": 1.6818,
|
| 1930 |
+
"step": 25600
|
| 1931 |
+
},
|
| 1932 |
+
{
|
| 1933 |
+
"epoch": 16.15336266499057,
|
| 1934 |
+
"grad_norm": 5.430357456207275,
|
| 1935 |
+
"learning_rate": 1.769453174104337e-05,
|
| 1936 |
+
"loss": 1.6125,
|
| 1937 |
+
"step": 25700
|
| 1938 |
+
},
|
| 1939 |
+
{
|
| 1940 |
+
"epoch": 16.216216216216218,
|
| 1941 |
+
"grad_norm": 5.235119819641113,
|
| 1942 |
+
"learning_rate": 1.7568824638592084e-05,
|
| 1943 |
+
"loss": 1.6985,
|
| 1944 |
+
"step": 25800
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 16.27906976744186,
|
| 1948 |
+
"grad_norm": 5.521476745605469,
|
| 1949 |
+
"learning_rate": 1.7443117536140792e-05,
|
| 1950 |
+
"loss": 1.6291,
|
| 1951 |
+
"step": 25900
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 16.341923318667504,
|
| 1955 |
+
"grad_norm": 5.7086873054504395,
|
| 1956 |
+
"learning_rate": 1.7317410433689504e-05,
|
| 1957 |
+
"loss": 1.6523,
|
| 1958 |
+
"step": 26000
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 16.404776869893148,
|
| 1962 |
+
"grad_norm": 5.697257041931152,
|
| 1963 |
+
"learning_rate": 1.7191703331238216e-05,
|
| 1964 |
+
"loss": 1.6518,
|
| 1965 |
+
"step": 26100
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 16.467630421118795,
|
| 1969 |
+
"grad_norm": 8.258442878723145,
|
| 1970 |
+
"learning_rate": 1.7065996228786928e-05,
|
| 1971 |
+
"loss": 1.6314,
|
| 1972 |
+
"step": 26200
|
| 1973 |
+
},
|
| 1974 |
+
{
|
| 1975 |
+
"epoch": 16.530483972344438,
|
| 1976 |
+
"grad_norm": 4.087442874908447,
|
| 1977 |
+
"learning_rate": 1.694028912633564e-05,
|
| 1978 |
+
"loss": 1.7048,
|
| 1979 |
+
"step": 26300
|
| 1980 |
+
},
|
| 1981 |
+
{
|
| 1982 |
+
"epoch": 16.59333752357008,
|
| 1983 |
+
"grad_norm": 4.184548377990723,
|
| 1984 |
+
"learning_rate": 1.681458202388435e-05,
|
| 1985 |
+
"loss": 1.6062,
|
| 1986 |
+
"step": 26400
|
| 1987 |
+
},
|
| 1988 |
+
{
|
| 1989 |
+
"epoch": 16.656191074795725,
|
| 1990 |
+
"grad_norm": 5.8042707443237305,
|
| 1991 |
+
"learning_rate": 1.6688874921433063e-05,
|
| 1992 |
+
"loss": 1.6239,
|
| 1993 |
+
"step": 26500
|
| 1994 |
+
},
|
| 1995 |
+
{
|
| 1996 |
+
"epoch": 16.719044626021372,
|
| 1997 |
+
"grad_norm": 4.104475498199463,
|
| 1998 |
+
"learning_rate": 1.656316781898177e-05,
|
| 1999 |
+
"loss": 1.5742,
|
| 2000 |
+
"step": 26600
|
| 2001 |
+
},
|
| 2002 |
+
{
|
| 2003 |
+
"epoch": 16.781898177247015,
|
| 2004 |
+
"grad_norm": 4.2934722900390625,
|
| 2005 |
+
"learning_rate": 1.6437460716530483e-05,
|
| 2006 |
+
"loss": 1.6069,
|
| 2007 |
+
"step": 26700
|
| 2008 |
+
},
|
| 2009 |
+
{
|
| 2010 |
+
"epoch": 16.84475172847266,
|
| 2011 |
+
"grad_norm": 4.601330757141113,
|
| 2012 |
+
"learning_rate": 1.6311753614079195e-05,
|
| 2013 |
+
"loss": 1.5827,
|
| 2014 |
+
"step": 26800
|
| 2015 |
+
},
|
| 2016 |
+
{
|
| 2017 |
+
"epoch": 16.907605279698302,
|
| 2018 |
+
"grad_norm": 4.304816246032715,
|
| 2019 |
+
"learning_rate": 1.618604651162791e-05,
|
| 2020 |
+
"loss": 1.6461,
|
| 2021 |
+
"step": 26900
|
| 2022 |
+
},
|
| 2023 |
+
{
|
| 2024 |
+
"epoch": 16.970458830923945,
|
| 2025 |
+
"grad_norm": 6.80120325088501,
|
| 2026 |
+
"learning_rate": 1.606033940917662e-05,
|
| 2027 |
+
"loss": 1.6143,
|
| 2028 |
+
"step": 27000
|
| 2029 |
+
},
|
| 2030 |
+
{
|
| 2031 |
+
"epoch": 17.0,
|
| 2032 |
+
"eval_loss": 1.5869935750961304,
|
| 2033 |
+
"eval_runtime": 20.3162,
|
| 2034 |
+
"eval_samples_per_second": 47.154,
|
| 2035 |
+
"eval_steps_per_second": 5.907,
|
| 2036 |
+
"step": 27047
|
| 2037 |
+
},
|
| 2038 |
+
{
|
| 2039 |
+
"epoch": 17.033312382149592,
|
| 2040 |
+
"grad_norm": 4.368440628051758,
|
| 2041 |
+
"learning_rate": 1.593463230672533e-05,
|
| 2042 |
+
"loss": 1.6352,
|
| 2043 |
+
"step": 27100
|
| 2044 |
+
},
|
| 2045 |
+
{
|
| 2046 |
+
"epoch": 17.096165933375236,
|
| 2047 |
+
"grad_norm": 4.066120624542236,
|
| 2048 |
+
"learning_rate": 1.5808925204274042e-05,
|
| 2049 |
+
"loss": 1.5052,
|
| 2050 |
+
"step": 27200
|
| 2051 |
+
},
|
| 2052 |
+
{
|
| 2053 |
+
"epoch": 17.15901948460088,
|
| 2054 |
+
"grad_norm": 6.150811672210693,
|
| 2055 |
+
"learning_rate": 1.5683218101822754e-05,
|
| 2056 |
+
"loss": 1.5449,
|
| 2057 |
+
"step": 27300
|
| 2058 |
+
},
|
| 2059 |
+
{
|
| 2060 |
+
"epoch": 17.221873035826523,
|
| 2061 |
+
"grad_norm": 7.994663715362549,
|
| 2062 |
+
"learning_rate": 1.5557510999371466e-05,
|
| 2063 |
+
"loss": 1.7157,
|
| 2064 |
+
"step": 27400
|
| 2065 |
+
},
|
| 2066 |
+
{
|
| 2067 |
+
"epoch": 17.28472658705217,
|
| 2068 |
+
"grad_norm": 3.554856061935425,
|
| 2069 |
+
"learning_rate": 1.5431803896920178e-05,
|
| 2070 |
+
"loss": 1.5878,
|
| 2071 |
+
"step": 27500
|
| 2072 |
+
},
|
| 2073 |
+
{
|
| 2074 |
+
"epoch": 17.347580138277813,
|
| 2075 |
+
"grad_norm": 4.025883674621582,
|
| 2076 |
+
"learning_rate": 1.530609679446889e-05,
|
| 2077 |
+
"loss": 1.6454,
|
| 2078 |
+
"step": 27600
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 17.410433689503456,
|
| 2082 |
+
"grad_norm": 2.9825448989868164,
|
| 2083 |
+
"learning_rate": 1.51803896920176e-05,
|
| 2084 |
+
"loss": 1.5605,
|
| 2085 |
+
"step": 27700
|
| 2086 |
+
},
|
| 2087 |
+
{
|
| 2088 |
+
"epoch": 17.4732872407291,
|
| 2089 |
+
"grad_norm": 4.528345584869385,
|
| 2090 |
+
"learning_rate": 1.505468258956631e-05,
|
| 2091 |
+
"loss": 1.626,
|
| 2092 |
+
"step": 27800
|
| 2093 |
+
},
|
| 2094 |
+
{
|
| 2095 |
+
"epoch": 17.536140791954747,
|
| 2096 |
+
"grad_norm": 4.549004554748535,
|
| 2097 |
+
"learning_rate": 1.4928975487115023e-05,
|
| 2098 |
+
"loss": 1.5508,
|
| 2099 |
+
"step": 27900
|
| 2100 |
+
},
|
| 2101 |
+
{
|
| 2102 |
+
"epoch": 17.59899434318039,
|
| 2103 |
+
"grad_norm": 4.830588340759277,
|
| 2104 |
+
"learning_rate": 1.4803268384663735e-05,
|
| 2105 |
+
"loss": 1.5394,
|
| 2106 |
+
"step": 28000
|
| 2107 |
+
},
|
| 2108 |
+
{
|
| 2109 |
+
"epoch": 17.661847894406034,
|
| 2110 |
+
"grad_norm": 4.127079486846924,
|
| 2111 |
+
"learning_rate": 1.4677561282212447e-05,
|
| 2112 |
+
"loss": 1.5548,
|
| 2113 |
+
"step": 28100
|
| 2114 |
+
},
|
| 2115 |
+
{
|
| 2116 |
+
"epoch": 17.724701445631677,
|
| 2117 |
+
"grad_norm": 3.208592414855957,
|
| 2118 |
+
"learning_rate": 1.4551854179761157e-05,
|
| 2119 |
+
"loss": 1.5595,
|
| 2120 |
+
"step": 28200
|
| 2121 |
+
},
|
| 2122 |
+
{
|
| 2123 |
+
"epoch": 17.787554996857324,
|
| 2124 |
+
"grad_norm": 4.784154891967773,
|
| 2125 |
+
"learning_rate": 1.4426147077309869e-05,
|
| 2126 |
+
"loss": 1.6029,
|
| 2127 |
+
"step": 28300
|
| 2128 |
+
},
|
| 2129 |
+
{
|
| 2130 |
+
"epoch": 17.850408548082967,
|
| 2131 |
+
"grad_norm": 5.0941481590271,
|
| 2132 |
+
"learning_rate": 1.4300439974858582e-05,
|
| 2133 |
+
"loss": 1.634,
|
| 2134 |
+
"step": 28400
|
| 2135 |
+
},
|
| 2136 |
+
{
|
| 2137 |
+
"epoch": 17.91326209930861,
|
| 2138 |
+
"grad_norm": 6.4498982429504395,
|
| 2139 |
+
"learning_rate": 1.4174732872407292e-05,
|
| 2140 |
+
"loss": 1.6685,
|
| 2141 |
+
"step": 28500
|
| 2142 |
+
},
|
| 2143 |
+
{
|
| 2144 |
+
"epoch": 17.976115650534254,
|
| 2145 |
+
"grad_norm": 5.136322021484375,
|
| 2146 |
+
"learning_rate": 1.4049025769956004e-05,
|
| 2147 |
+
"loss": 1.5587,
|
| 2148 |
+
"step": 28600
|
| 2149 |
+
},
|
| 2150 |
+
{
|
| 2151 |
+
"epoch": 18.0,
|
| 2152 |
+
"eval_loss": 1.565408706665039,
|
| 2153 |
+
"eval_runtime": 20.3165,
|
| 2154 |
+
"eval_samples_per_second": 47.154,
|
| 2155 |
+
"eval_steps_per_second": 5.907,
|
| 2156 |
+
"step": 28638
|
| 2157 |
+
},
|
| 2158 |
+
{
|
| 2159 |
+
"epoch": 18.0389692017599,
|
| 2160 |
+
"grad_norm": 7.265219211578369,
|
| 2161 |
+
"learning_rate": 1.3923318667504714e-05,
|
| 2162 |
+
"loss": 1.534,
|
| 2163 |
+
"step": 28700
|
| 2164 |
+
},
|
| 2165 |
+
{
|
| 2166 |
+
"epoch": 18.101822752985544,
|
| 2167 |
+
"grad_norm": 5.552704334259033,
|
| 2168 |
+
"learning_rate": 1.3797611565053426e-05,
|
| 2169 |
+
"loss": 1.5396,
|
| 2170 |
+
"step": 28800
|
| 2171 |
+
},
|
| 2172 |
+
{
|
| 2173 |
+
"epoch": 18.164676304211188,
|
| 2174 |
+
"grad_norm": 7.356419086456299,
|
| 2175 |
+
"learning_rate": 1.3671904462602136e-05,
|
| 2176 |
+
"loss": 1.5851,
|
| 2177 |
+
"step": 28900
|
| 2178 |
+
},
|
| 2179 |
+
{
|
| 2180 |
+
"epoch": 18.22752985543683,
|
| 2181 |
+
"grad_norm": 5.519120693206787,
|
| 2182 |
+
"learning_rate": 1.354619736015085e-05,
|
| 2183 |
+
"loss": 1.6331,
|
| 2184 |
+
"step": 29000
|
| 2185 |
+
},
|
| 2186 |
+
{
|
| 2187 |
+
"epoch": 18.290383406662478,
|
| 2188 |
+
"grad_norm": 4.4178242683410645,
|
| 2189 |
+
"learning_rate": 1.3420490257699561e-05,
|
| 2190 |
+
"loss": 1.508,
|
| 2191 |
+
"step": 29100
|
| 2192 |
+
},
|
| 2193 |
+
{
|
| 2194 |
+
"epoch": 18.35323695788812,
|
| 2195 |
+
"grad_norm": 4.479162216186523,
|
| 2196 |
+
"learning_rate": 1.3294783155248271e-05,
|
| 2197 |
+
"loss": 1.5201,
|
| 2198 |
+
"step": 29200
|
| 2199 |
+
},
|
| 2200 |
+
{
|
| 2201 |
+
"epoch": 18.416090509113765,
|
| 2202 |
+
"grad_norm": 4.4193806648254395,
|
| 2203 |
+
"learning_rate": 1.3169076052796983e-05,
|
| 2204 |
+
"loss": 1.5393,
|
| 2205 |
+
"step": 29300
|
| 2206 |
+
},
|
| 2207 |
+
{
|
| 2208 |
+
"epoch": 18.47894406033941,
|
| 2209 |
+
"grad_norm": 6.695824146270752,
|
| 2210 |
+
"learning_rate": 1.3043368950345693e-05,
|
| 2211 |
+
"loss": 1.6264,
|
| 2212 |
+
"step": 29400
|
| 2213 |
+
},
|
| 2214 |
+
{
|
| 2215 |
+
"epoch": 18.541797611565052,
|
| 2216 |
+
"grad_norm": 4.760421276092529,
|
| 2217 |
+
"learning_rate": 1.2917661847894409e-05,
|
| 2218 |
+
"loss": 1.5465,
|
| 2219 |
+
"step": 29500
|
| 2220 |
+
},
|
| 2221 |
+
{
|
| 2222 |
+
"epoch": 18.6046511627907,
|
| 2223 |
+
"grad_norm": 4.158078193664551,
|
| 2224 |
+
"learning_rate": 1.2791954745443119e-05,
|
| 2225 |
+
"loss": 1.5533,
|
| 2226 |
+
"step": 29600
|
| 2227 |
+
},
|
| 2228 |
+
{
|
| 2229 |
+
"epoch": 18.667504714016342,
|
| 2230 |
+
"grad_norm": 6.8502092361450195,
|
| 2231 |
+
"learning_rate": 1.266624764299183e-05,
|
| 2232 |
+
"loss": 1.6525,
|
| 2233 |
+
"step": 29700
|
| 2234 |
+
},
|
| 2235 |
+
{
|
| 2236 |
+
"epoch": 18.730358265241986,
|
| 2237 |
+
"grad_norm": 4.013594150543213,
|
| 2238 |
+
"learning_rate": 1.254054054054054e-05,
|
| 2239 |
+
"loss": 1.5357,
|
| 2240 |
+
"step": 29800
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"epoch": 18.79321181646763,
|
| 2244 |
+
"grad_norm": 6.064908981323242,
|
| 2245 |
+
"learning_rate": 1.2414833438089252e-05,
|
| 2246 |
+
"loss": 1.5659,
|
| 2247 |
+
"step": 29900
|
| 2248 |
+
},
|
| 2249 |
+
{
|
| 2250 |
+
"epoch": 18.856065367693276,
|
| 2251 |
+
"grad_norm": 5.281710624694824,
|
| 2252 |
+
"learning_rate": 1.2289126335637964e-05,
|
| 2253 |
+
"loss": 1.4692,
|
| 2254 |
+
"step": 30000
|
| 2255 |
+
},
|
| 2256 |
+
{
|
| 2257 |
+
"epoch": 18.91891891891892,
|
| 2258 |
+
"grad_norm": 4.661835193634033,
|
| 2259 |
+
"learning_rate": 1.2163419233186674e-05,
|
| 2260 |
+
"loss": 1.5126,
|
| 2261 |
+
"step": 30100
|
| 2262 |
+
},
|
| 2263 |
+
{
|
| 2264 |
+
"epoch": 18.981772470144563,
|
| 2265 |
+
"grad_norm": 3.9490227699279785,
|
| 2266 |
+
"learning_rate": 1.2037712130735388e-05,
|
| 2267 |
+
"loss": 1.5389,
|
| 2268 |
+
"step": 30200
|
| 2269 |
+
},
|
| 2270 |
+
{
|
| 2271 |
+
"epoch": 19.0,
|
| 2272 |
+
"eval_loss": 1.5563335418701172,
|
| 2273 |
+
"eval_runtime": 20.3631,
|
| 2274 |
+
"eval_samples_per_second": 47.046,
|
| 2275 |
+
"eval_steps_per_second": 5.893,
|
| 2276 |
+
"step": 30229
|
| 2277 |
+
},
|
| 2278 |
+
{
|
| 2279 |
+
"epoch": 19.044626021370206,
|
| 2280 |
+
"grad_norm": 4.6667866706848145,
|
| 2281 |
+
"learning_rate": 1.1912005028284098e-05,
|
| 2282 |
+
"loss": 1.5508,
|
| 2283 |
+
"step": 30300
|
| 2284 |
+
},
|
| 2285 |
+
{
|
| 2286 |
+
"epoch": 19.107479572595853,
|
| 2287 |
+
"grad_norm": 4.471792697906494,
|
| 2288 |
+
"learning_rate": 1.1786297925832811e-05,
|
| 2289 |
+
"loss": 1.5253,
|
| 2290 |
+
"step": 30400
|
| 2291 |
+
},
|
| 2292 |
+
{
|
| 2293 |
+
"epoch": 19.170333123821496,
|
| 2294 |
+
"grad_norm": 4.01970100402832,
|
| 2295 |
+
"learning_rate": 1.1660590823381521e-05,
|
| 2296 |
+
"loss": 1.5047,
|
| 2297 |
+
"step": 30500
|
| 2298 |
+
},
|
| 2299 |
+
{
|
| 2300 |
+
"epoch": 19.23318667504714,
|
| 2301 |
+
"grad_norm": 5.021801471710205,
|
| 2302 |
+
"learning_rate": 1.1534883720930233e-05,
|
| 2303 |
+
"loss": 1.5459,
|
| 2304 |
+
"step": 30600
|
| 2305 |
+
},
|
| 2306 |
+
{
|
| 2307 |
+
"epoch": 19.296040226272783,
|
| 2308 |
+
"grad_norm": 4.681889533996582,
|
| 2309 |
+
"learning_rate": 1.1409176618478945e-05,
|
| 2310 |
+
"loss": 1.561,
|
| 2311 |
+
"step": 30700
|
| 2312 |
+
},
|
| 2313 |
+
{
|
| 2314 |
+
"epoch": 19.35889377749843,
|
| 2315 |
+
"grad_norm": 4.114772319793701,
|
| 2316 |
+
"learning_rate": 1.1283469516027655e-05,
|
| 2317 |
+
"loss": 1.532,
|
| 2318 |
+
"step": 30800
|
| 2319 |
+
},
|
| 2320 |
+
{
|
| 2321 |
+
"epoch": 19.421747328724074,
|
| 2322 |
+
"grad_norm": 3.9337844848632812,
|
| 2323 |
+
"learning_rate": 1.1157762413576367e-05,
|
| 2324 |
+
"loss": 1.5512,
|
| 2325 |
+
"step": 30900
|
| 2326 |
+
},
|
| 2327 |
+
{
|
| 2328 |
+
"epoch": 19.484600879949717,
|
| 2329 |
+
"grad_norm": 4.935436725616455,
|
| 2330 |
+
"learning_rate": 1.1032055311125079e-05,
|
| 2331 |
+
"loss": 1.5328,
|
| 2332 |
+
"step": 31000
|
| 2333 |
+
},
|
| 2334 |
+
{
|
| 2335 |
+
"epoch": 19.54745443117536,
|
| 2336 |
+
"grad_norm": 5.703494071960449,
|
| 2337 |
+
"learning_rate": 1.090634820867379e-05,
|
| 2338 |
+
"loss": 1.5889,
|
| 2339 |
+
"step": 31100
|
| 2340 |
+
},
|
| 2341 |
+
{
|
| 2342 |
+
"epoch": 19.610307982401007,
|
| 2343 |
+
"grad_norm": 6.010659217834473,
|
| 2344 |
+
"learning_rate": 1.0780641106222502e-05,
|
| 2345 |
+
"loss": 1.5166,
|
| 2346 |
+
"step": 31200
|
| 2347 |
+
},
|
| 2348 |
+
{
|
| 2349 |
+
"epoch": 19.67316153362665,
|
| 2350 |
+
"grad_norm": 5.14444637298584,
|
| 2351 |
+
"learning_rate": 1.0654934003771214e-05,
|
| 2352 |
+
"loss": 1.5096,
|
| 2353 |
+
"step": 31300
|
| 2354 |
+
},
|
| 2355 |
+
{
|
| 2356 |
+
"epoch": 19.736015084852294,
|
| 2357 |
+
"grad_norm": 7.321188449859619,
|
| 2358 |
+
"learning_rate": 1.0529226901319924e-05,
|
| 2359 |
+
"loss": 1.4865,
|
| 2360 |
+
"step": 31400
|
| 2361 |
+
},
|
| 2362 |
+
{
|
| 2363 |
+
"epoch": 19.798868636077938,
|
| 2364 |
+
"grad_norm": 3.7702994346618652,
|
| 2365 |
+
"learning_rate": 1.0403519798868636e-05,
|
| 2366 |
+
"loss": 1.5122,
|
| 2367 |
+
"step": 31500
|
| 2368 |
+
},
|
| 2369 |
+
{
|
| 2370 |
+
"epoch": 19.86172218730358,
|
| 2371 |
+
"grad_norm": 5.493444442749023,
|
| 2372 |
+
"learning_rate": 1.0277812696417348e-05,
|
| 2373 |
+
"loss": 1.4974,
|
| 2374 |
+
"step": 31600
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"epoch": 19.924575738529228,
|
| 2378 |
+
"grad_norm": 5.273486137390137,
|
| 2379 |
+
"learning_rate": 1.015210559396606e-05,
|
| 2380 |
+
"loss": 1.5619,
|
| 2381 |
+
"step": 31700
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"epoch": 19.98742928975487,
|
| 2385 |
+
"grad_norm": 4.340183734893799,
|
| 2386 |
+
"learning_rate": 1.0026398491514772e-05,
|
| 2387 |
+
"loss": 1.4476,
|
| 2388 |
+
"step": 31800
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 20.0,
|
| 2392 |
+
"eval_loss": 1.5459223985671997,
|
| 2393 |
+
"eval_runtime": 20.3264,
|
| 2394 |
+
"eval_samples_per_second": 47.131,
|
| 2395 |
+
"eval_steps_per_second": 5.904,
|
| 2396 |
+
"step": 31820
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 20.050282840980515,
|
| 2400 |
+
"grad_norm": 3.8120639324188232,
|
| 2401 |
+
"learning_rate": 9.900691389063482e-06,
|
| 2402 |
+
"loss": 1.4837,
|
| 2403 |
+
"step": 31900
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 20.113136392206158,
|
| 2407 |
+
"grad_norm": 4.154244899749756,
|
| 2408 |
+
"learning_rate": 9.774984286612195e-06,
|
| 2409 |
+
"loss": 1.4684,
|
| 2410 |
+
"step": 32000
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 20.175989943431805,
|
| 2414 |
+
"grad_norm": 3.925746202468872,
|
| 2415 |
+
"learning_rate": 9.649277184160905e-06,
|
| 2416 |
+
"loss": 1.4685,
|
| 2417 |
+
"step": 32100
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 20.23884349465745,
|
| 2421 |
+
"grad_norm": 5.944131374359131,
|
| 2422 |
+
"learning_rate": 9.523570081709617e-06,
|
| 2423 |
+
"loss": 1.5097,
|
| 2424 |
+
"step": 32200
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 20.301697045883092,
|
| 2428 |
+
"grad_norm": 4.755185127258301,
|
| 2429 |
+
"learning_rate": 9.397862979258329e-06,
|
| 2430 |
+
"loss": 1.4334,
|
| 2431 |
+
"step": 32300
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 20.364550597108735,
|
| 2435 |
+
"grad_norm": 4.627038478851318,
|
| 2436 |
+
"learning_rate": 9.27215587680704e-06,
|
| 2437 |
+
"loss": 1.503,
|
| 2438 |
+
"step": 32400
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 20.427404148334382,
|
| 2442 |
+
"grad_norm": 9.863165855407715,
|
| 2443 |
+
"learning_rate": 9.14644877435575e-06,
|
| 2444 |
+
"loss": 1.4607,
|
| 2445 |
+
"step": 32500
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 20.490257699560026,
|
| 2449 |
+
"grad_norm": 4.401854991912842,
|
| 2450 |
+
"learning_rate": 9.020741671904463e-06,
|
| 2451 |
+
"loss": 1.4653,
|
| 2452 |
+
"step": 32600
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 20.55311125078567,
|
| 2456 |
+
"grad_norm": 6.041737079620361,
|
| 2457 |
+
"learning_rate": 8.895034569453174e-06,
|
| 2458 |
+
"loss": 1.504,
|
| 2459 |
+
"step": 32700
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 20.615964802011312,
|
| 2463 |
+
"grad_norm": 6.523427963256836,
|
| 2464 |
+
"learning_rate": 8.769327467001886e-06,
|
| 2465 |
+
"loss": 1.6205,
|
| 2466 |
+
"step": 32800
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 20.67881835323696,
|
| 2470 |
+
"grad_norm": 5.47548246383667,
|
| 2471 |
+
"learning_rate": 8.643620364550598e-06,
|
| 2472 |
+
"loss": 1.4491,
|
| 2473 |
+
"step": 32900
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 20.741671904462603,
|
| 2477 |
+
"grad_norm": 5.3726959228515625,
|
| 2478 |
+
"learning_rate": 8.517913262099308e-06,
|
| 2479 |
+
"loss": 1.5817,
|
| 2480 |
+
"step": 33000
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 20.804525455688246,
|
| 2484 |
+
"grad_norm": 3.872283935546875,
|
| 2485 |
+
"learning_rate": 8.392206159648022e-06,
|
| 2486 |
+
"loss": 1.5482,
|
| 2487 |
+
"step": 33100
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 20.86737900691389,
|
| 2491 |
+
"grad_norm": 4.935946464538574,
|
| 2492 |
+
"learning_rate": 8.266499057196732e-06,
|
| 2493 |
+
"loss": 1.5006,
|
| 2494 |
+
"step": 33200
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 20.930232558139537,
|
| 2498 |
+
"grad_norm": 6.805904388427734,
|
| 2499 |
+
"learning_rate": 8.140791954745444e-06,
|
| 2500 |
+
"loss": 1.5314,
|
| 2501 |
+
"step": 33300
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 20.99308610936518,
|
| 2505 |
+
"grad_norm": 4.420083522796631,
|
| 2506 |
+
"learning_rate": 8.015084852294155e-06,
|
| 2507 |
+
"loss": 1.5417,
|
| 2508 |
+
"step": 33400
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 21.0,
|
| 2512 |
+
"eval_loss": 1.5356966257095337,
|
| 2513 |
+
"eval_runtime": 20.4137,
|
| 2514 |
+
"eval_samples_per_second": 46.929,
|
| 2515 |
+
"eval_steps_per_second": 5.878,
|
| 2516 |
+
"step": 33411
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 21.055939660590823,
|
| 2520 |
+
"grad_norm": 3.697171688079834,
|
| 2521 |
+
"learning_rate": 7.889377749842865e-06,
|
| 2522 |
+
"loss": 1.4994,
|
| 2523 |
+
"step": 33500
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 21.118793211816467,
|
| 2527 |
+
"grad_norm": 5.232399940490723,
|
| 2528 |
+
"learning_rate": 7.763670647391579e-06,
|
| 2529 |
+
"loss": 1.5351,
|
| 2530 |
+
"step": 33600
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 21.18164676304211,
|
| 2534 |
+
"grad_norm": 4.508577823638916,
|
| 2535 |
+
"learning_rate": 7.637963544940289e-06,
|
| 2536 |
+
"loss": 1.4301,
|
| 2537 |
+
"step": 33700
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 21.244500314267757,
|
| 2541 |
+
"grad_norm": 5.425107479095459,
|
| 2542 |
+
"learning_rate": 7.512256442489001e-06,
|
| 2543 |
+
"loss": 1.4739,
|
| 2544 |
+
"step": 33800
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 21.3073538654934,
|
| 2548 |
+
"grad_norm": 6.195432186126709,
|
| 2549 |
+
"learning_rate": 7.386549340037713e-06,
|
| 2550 |
+
"loss": 1.5458,
|
| 2551 |
+
"step": 33900
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 21.370207416719044,
|
| 2555 |
+
"grad_norm": 5.850045204162598,
|
| 2556 |
+
"learning_rate": 7.260842237586424e-06,
|
| 2557 |
+
"loss": 1.5189,
|
| 2558 |
+
"step": 34000
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 21.433060967944687,
|
| 2562 |
+
"grad_norm": 7.121579170227051,
|
| 2563 |
+
"learning_rate": 7.135135135135136e-06,
|
| 2564 |
+
"loss": 1.5273,
|
| 2565 |
+
"step": 34100
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 21.495914519170334,
|
| 2569 |
+
"grad_norm": 4.316208362579346,
|
| 2570 |
+
"learning_rate": 7.009428032683847e-06,
|
| 2571 |
+
"loss": 1.4437,
|
| 2572 |
+
"step": 34200
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 21.558768070395978,
|
| 2576 |
+
"grad_norm": 4.3052873611450195,
|
| 2577 |
+
"learning_rate": 6.883720930232558e-06,
|
| 2578 |
+
"loss": 1.4266,
|
| 2579 |
+
"step": 34300
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 21.62162162162162,
|
| 2583 |
+
"grad_norm": 4.691330432891846,
|
| 2584 |
+
"learning_rate": 6.758013827781271e-06,
|
| 2585 |
+
"loss": 1.422,
|
| 2586 |
+
"step": 34400
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 21.684475172847264,
|
| 2590 |
+
"grad_norm": 4.346444129943848,
|
| 2591 |
+
"learning_rate": 6.632306725329982e-06,
|
| 2592 |
+
"loss": 1.5511,
|
| 2593 |
+
"step": 34500
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 21.74732872407291,
|
| 2597 |
+
"grad_norm": 5.304843902587891,
|
| 2598 |
+
"learning_rate": 6.506599622878693e-06,
|
| 2599 |
+
"loss": 1.4961,
|
| 2600 |
+
"step": 34600
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 21.810182275298555,
|
| 2604 |
+
"grad_norm": 4.877419948577881,
|
| 2605 |
+
"learning_rate": 6.3808925204274045e-06,
|
| 2606 |
+
"loss": 1.4837,
|
| 2607 |
+
"step": 34700
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 21.873035826524198,
|
| 2611 |
+
"grad_norm": 4.086881637573242,
|
| 2612 |
+
"learning_rate": 6.2551854179761155e-06,
|
| 2613 |
+
"loss": 1.5164,
|
| 2614 |
+
"step": 34800
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 21.93588937774984,
|
| 2618 |
+
"grad_norm": 4.570976734161377,
|
| 2619 |
+
"learning_rate": 6.129478315524827e-06,
|
| 2620 |
+
"loss": 1.4681,
|
| 2621 |
+
"step": 34900
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 21.99874292897549,
|
| 2625 |
+
"grad_norm": 25.407676696777344,
|
| 2626 |
+
"learning_rate": 6.003771213073539e-06,
|
| 2627 |
+
"loss": 1.4062,
|
| 2628 |
+
"step": 35000
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 22.0,
|
| 2632 |
+
"eval_loss": 1.5373815298080444,
|
| 2633 |
+
"eval_runtime": 20.3495,
|
| 2634 |
+
"eval_samples_per_second": 47.077,
|
| 2635 |
+
"eval_steps_per_second": 5.897,
|
| 2636 |
+
"step": 35002
|
| 2637 |
+
},
|
| 2638 |
+
{
|
| 2639 |
+
"epoch": 22.061596480201132,
|
| 2640 |
+
"grad_norm": 4.965208053588867,
|
| 2641 |
+
"learning_rate": 5.878064110622251e-06,
|
| 2642 |
+
"loss": 1.446,
|
| 2643 |
+
"step": 35100
|
| 2644 |
+
},
|
| 2645 |
+
{
|
| 2646 |
+
"epoch": 22.124450031426775,
|
| 2647 |
+
"grad_norm": 5.620969772338867,
|
| 2648 |
+
"learning_rate": 5.752357008170962e-06,
|
| 2649 |
+
"loss": 1.475,
|
| 2650 |
+
"step": 35200
|
| 2651 |
+
},
|
| 2652 |
+
{
|
| 2653 |
+
"epoch": 22.18730358265242,
|
| 2654 |
+
"grad_norm": 4.315845489501953,
|
| 2655 |
+
"learning_rate": 5.626649905719674e-06,
|
| 2656 |
+
"loss": 1.4866,
|
| 2657 |
+
"step": 35300
|
| 2658 |
+
},
|
| 2659 |
+
{
|
| 2660 |
+
"epoch": 22.250157133878066,
|
| 2661 |
+
"grad_norm": 4.076879501342773,
|
| 2662 |
+
"learning_rate": 5.5009428032683854e-06,
|
| 2663 |
+
"loss": 1.5079,
|
| 2664 |
+
"step": 35400
|
| 2665 |
+
},
|
| 2666 |
+
{
|
| 2667 |
+
"epoch": 22.31301068510371,
|
| 2668 |
+
"grad_norm": 9.52351188659668,
|
| 2669 |
+
"learning_rate": 5.375235700817096e-06,
|
| 2670 |
+
"loss": 1.5637,
|
| 2671 |
+
"step": 35500
|
| 2672 |
+
},
|
| 2673 |
+
{
|
| 2674 |
+
"epoch": 22.375864236329353,
|
| 2675 |
+
"grad_norm": 5.529058933258057,
|
| 2676 |
+
"learning_rate": 5.249528598365807e-06,
|
| 2677 |
+
"loss": 1.4702,
|
| 2678 |
+
"step": 35600
|
| 2679 |
+
},
|
| 2680 |
+
{
|
| 2681 |
+
"epoch": 22.438717787554996,
|
| 2682 |
+
"grad_norm": 4.761877536773682,
|
| 2683 |
+
"learning_rate": 5.123821495914519e-06,
|
| 2684 |
+
"loss": 1.4367,
|
| 2685 |
+
"step": 35700
|
| 2686 |
+
},
|
| 2687 |
+
{
|
| 2688 |
+
"epoch": 22.501571338780643,
|
| 2689 |
+
"grad_norm": 6.587429046630859,
|
| 2690 |
+
"learning_rate": 4.998114393463231e-06,
|
| 2691 |
+
"loss": 1.4052,
|
| 2692 |
+
"step": 35800
|
| 2693 |
+
},
|
| 2694 |
+
{
|
| 2695 |
+
"epoch": 22.564424890006286,
|
| 2696 |
+
"grad_norm": 5.834304332733154,
|
| 2697 |
+
"learning_rate": 4.872407291011943e-06,
|
| 2698 |
+
"loss": 1.4186,
|
| 2699 |
+
"step": 35900
|
| 2700 |
+
},
|
| 2701 |
+
{
|
| 2702 |
+
"epoch": 22.62727844123193,
|
| 2703 |
+
"grad_norm": 3.871225595474243,
|
| 2704 |
+
"learning_rate": 4.746700188560654e-06,
|
| 2705 |
+
"loss": 1.51,
|
| 2706 |
+
"step": 36000
|
| 2707 |
+
},
|
| 2708 |
+
{
|
| 2709 |
+
"epoch": 22.690131992457573,
|
| 2710 |
+
"grad_norm": 3.876692771911621,
|
| 2711 |
+
"learning_rate": 4.6209930861093655e-06,
|
| 2712 |
+
"loss": 1.5022,
|
| 2713 |
+
"step": 36100
|
| 2714 |
+
},
|
| 2715 |
+
{
|
| 2716 |
+
"epoch": 22.752985543683216,
|
| 2717 |
+
"grad_norm": 4.569952964782715,
|
| 2718 |
+
"learning_rate": 4.495285983658077e-06,
|
| 2719 |
+
"loss": 1.454,
|
| 2720 |
+
"step": 36200
|
| 2721 |
+
},
|
| 2722 |
+
{
|
| 2723 |
+
"epoch": 22.815839094908863,
|
| 2724 |
+
"grad_norm": 5.837776184082031,
|
| 2725 |
+
"learning_rate": 4.369578881206788e-06,
|
| 2726 |
+
"loss": 1.4472,
|
| 2727 |
+
"step": 36300
|
| 2728 |
+
},
|
| 2729 |
+
{
|
| 2730 |
+
"epoch": 22.878692646134507,
|
| 2731 |
+
"grad_norm": 5.9942426681518555,
|
| 2732 |
+
"learning_rate": 4.243871778755499e-06,
|
| 2733 |
+
"loss": 1.4198,
|
| 2734 |
+
"step": 36400
|
| 2735 |
+
},
|
| 2736 |
+
{
|
| 2737 |
+
"epoch": 22.94154619736015,
|
| 2738 |
+
"grad_norm": 4.1033220291137695,
|
| 2739 |
+
"learning_rate": 4.118164676304211e-06,
|
| 2740 |
+
"loss": 1.4658,
|
| 2741 |
+
"step": 36500
|
| 2742 |
+
},
|
| 2743 |
+
{
|
| 2744 |
+
"epoch": 23.0,
|
| 2745 |
+
"eval_loss": 1.5307875871658325,
|
| 2746 |
+
"eval_runtime": 20.3299,
|
| 2747 |
+
"eval_samples_per_second": 47.123,
|
| 2748 |
+
"eval_steps_per_second": 5.903,
|
| 2749 |
+
"step": 36593
|
| 2750 |
+
},
|
| 2751 |
+
{
|
| 2752 |
+
"epoch": 23.004399748585794,
|
| 2753 |
+
"grad_norm": 4.649007320404053,
|
| 2754 |
+
"learning_rate": 3.992457573852923e-06,
|
| 2755 |
+
"loss": 1.4064,
|
| 2756 |
+
"step": 36600
|
| 2757 |
+
},
|
| 2758 |
+
{
|
| 2759 |
+
"epoch": 23.06725329981144,
|
| 2760 |
+
"grad_norm": 4.318711757659912,
|
| 2761 |
+
"learning_rate": 3.866750471401635e-06,
|
| 2762 |
+
"loss": 1.4249,
|
| 2763 |
+
"step": 36700
|
| 2764 |
+
},
|
| 2765 |
+
{
|
| 2766 |
+
"epoch": 23.130106851037084,
|
| 2767 |
+
"grad_norm": 6.213062286376953,
|
| 2768 |
+
"learning_rate": 3.7410433689503456e-06,
|
| 2769 |
+
"loss": 1.4317,
|
| 2770 |
+
"step": 36800
|
| 2771 |
+
},
|
| 2772 |
+
{
|
| 2773 |
+
"epoch": 23.192960402262727,
|
| 2774 |
+
"grad_norm": 4.529442310333252,
|
| 2775 |
+
"learning_rate": 3.6153362664990574e-06,
|
| 2776 |
+
"loss": 1.5102,
|
| 2777 |
+
"step": 36900
|
| 2778 |
+
},
|
| 2779 |
+
{
|
| 2780 |
+
"epoch": 23.25581395348837,
|
| 2781 |
+
"grad_norm": 4.912539005279541,
|
| 2782 |
+
"learning_rate": 3.4896291640477688e-06,
|
| 2783 |
+
"loss": 1.4684,
|
| 2784 |
+
"step": 37000
|
| 2785 |
+
},
|
| 2786 |
+
{
|
| 2787 |
+
"epoch": 23.318667504714018,
|
| 2788 |
+
"grad_norm": 4.593921661376953,
|
| 2789 |
+
"learning_rate": 3.3639220615964806e-06,
|
| 2790 |
+
"loss": 1.4181,
|
| 2791 |
+
"step": 37100
|
| 2792 |
+
},
|
| 2793 |
+
{
|
| 2794 |
+
"epoch": 23.38152105593966,
|
| 2795 |
+
"grad_norm": 5.35049295425415,
|
| 2796 |
+
"learning_rate": 3.2382149591451915e-06,
|
| 2797 |
+
"loss": 1.4813,
|
| 2798 |
+
"step": 37200
|
| 2799 |
+
},
|
| 2800 |
+
{
|
| 2801 |
+
"epoch": 23.444374607165305,
|
| 2802 |
+
"grad_norm": 4.00051212310791,
|
| 2803 |
+
"learning_rate": 3.1125078566939033e-06,
|
| 2804 |
+
"loss": 1.4392,
|
| 2805 |
+
"step": 37300
|
| 2806 |
+
},
|
| 2807 |
+
{
|
| 2808 |
+
"epoch": 23.507228158390948,
|
| 2809 |
+
"grad_norm": 5.91484260559082,
|
| 2810 |
+
"learning_rate": 2.9868007542426147e-06,
|
| 2811 |
+
"loss": 1.4386,
|
| 2812 |
+
"step": 37400
|
| 2813 |
+
},
|
| 2814 |
+
{
|
| 2815 |
+
"epoch": 23.570081709616595,
|
| 2816 |
+
"grad_norm": 7.114585876464844,
|
| 2817 |
+
"learning_rate": 2.861093651791326e-06,
|
| 2818 |
+
"loss": 1.4115,
|
| 2819 |
+
"step": 37500
|
| 2820 |
+
},
|
| 2821 |
+
{
|
| 2822 |
+
"epoch": 23.63293526084224,
|
| 2823 |
+
"grad_norm": 2.977877378463745,
|
| 2824 |
+
"learning_rate": 2.735386549340038e-06,
|
| 2825 |
+
"loss": 1.4211,
|
| 2826 |
+
"step": 37600
|
| 2827 |
+
},
|
| 2828 |
+
{
|
| 2829 |
+
"epoch": 23.69578881206788,
|
| 2830 |
+
"grad_norm": 3.83953857421875,
|
| 2831 |
+
"learning_rate": 2.6096794468887493e-06,
|
| 2832 |
+
"loss": 1.4601,
|
| 2833 |
+
"step": 37700
|
| 2834 |
+
},
|
| 2835 |
+
{
|
| 2836 |
+
"epoch": 23.758642363293525,
|
| 2837 |
+
"grad_norm": 4.377187728881836,
|
| 2838 |
+
"learning_rate": 2.483972344437461e-06,
|
| 2839 |
+
"loss": 1.4281,
|
| 2840 |
+
"step": 37800
|
| 2841 |
+
},
|
| 2842 |
+
{
|
| 2843 |
+
"epoch": 23.821495914519172,
|
| 2844 |
+
"grad_norm": 3.9868085384368896,
|
| 2845 |
+
"learning_rate": 2.358265241986172e-06,
|
| 2846 |
+
"loss": 1.4585,
|
| 2847 |
+
"step": 37900
|
| 2848 |
+
},
|
| 2849 |
+
{
|
| 2850 |
+
"epoch": 23.884349465744815,
|
| 2851 |
+
"grad_norm": 3.989767551422119,
|
| 2852 |
+
"learning_rate": 2.232558139534884e-06,
|
| 2853 |
+
"loss": 1.5302,
|
| 2854 |
+
"step": 38000
|
| 2855 |
+
},
|
| 2856 |
+
{
|
| 2857 |
+
"epoch": 23.94720301697046,
|
| 2858 |
+
"grad_norm": 4.481296062469482,
|
| 2859 |
+
"learning_rate": 2.1068510370835952e-06,
|
| 2860 |
+
"loss": 1.4366,
|
| 2861 |
+
"step": 38100
|
| 2862 |
+
},
|
| 2863 |
+
{
|
| 2864 |
+
"epoch": 24.0,
|
| 2865 |
+
"eval_loss": 1.5289642810821533,
|
| 2866 |
+
"eval_runtime": 20.3269,
|
| 2867 |
+
"eval_samples_per_second": 47.13,
|
| 2868 |
+
"eval_steps_per_second": 5.904,
|
| 2869 |
+
"step": 38184
|
| 2870 |
+
},
|
| 2871 |
+
{
|
| 2872 |
+
"epoch": 24.010056568196102,
|
| 2873 |
+
"grad_norm": 4.909224033355713,
|
| 2874 |
+
"learning_rate": 1.981143934632307e-06,
|
| 2875 |
+
"loss": 1.4956,
|
| 2876 |
+
"step": 38200
|
| 2877 |
+
},
|
| 2878 |
+
{
|
| 2879 |
+
"epoch": 24.072910119421746,
|
| 2880 |
+
"grad_norm": 4.9214372634887695,
|
| 2881 |
+
"learning_rate": 1.8554368321810182e-06,
|
| 2882 |
+
"loss": 1.4725,
|
| 2883 |
+
"step": 38300
|
| 2884 |
+
},
|
| 2885 |
+
{
|
| 2886 |
+
"epoch": 24.135763670647393,
|
| 2887 |
+
"grad_norm": 4.345515251159668,
|
| 2888 |
+
"learning_rate": 1.7297297297297298e-06,
|
| 2889 |
+
"loss": 1.4407,
|
| 2890 |
+
"step": 38400
|
| 2891 |
+
},
|
| 2892 |
+
{
|
| 2893 |
+
"epoch": 24.198617221873036,
|
| 2894 |
+
"grad_norm": 4.926340579986572,
|
| 2895 |
+
"learning_rate": 1.6040226272784412e-06,
|
| 2896 |
+
"loss": 1.5008,
|
| 2897 |
+
"step": 38500
|
| 2898 |
+
},
|
| 2899 |
+
{
|
| 2900 |
+
"epoch": 24.26147077309868,
|
| 2901 |
+
"grad_norm": 4.5064263343811035,
|
| 2902 |
+
"learning_rate": 1.4783155248271527e-06,
|
| 2903 |
+
"loss": 1.4868,
|
| 2904 |
+
"step": 38600
|
| 2905 |
+
},
|
| 2906 |
+
{
|
| 2907 |
+
"epoch": 24.324324324324323,
|
| 2908 |
+
"grad_norm": 5.347716808319092,
|
| 2909 |
+
"learning_rate": 1.3526084223758643e-06,
|
| 2910 |
+
"loss": 1.45,
|
| 2911 |
+
"step": 38700
|
| 2912 |
+
},
|
| 2913 |
+
{
|
| 2914 |
+
"epoch": 24.38717787554997,
|
| 2915 |
+
"grad_norm": 5.024169921875,
|
| 2916 |
+
"learning_rate": 1.2269013199245757e-06,
|
| 2917 |
+
"loss": 1.3905,
|
| 2918 |
+
"step": 38800
|
| 2919 |
+
},
|
| 2920 |
+
{
|
| 2921 |
+
"epoch": 24.450031426775613,
|
| 2922 |
+
"grad_norm": 4.319692611694336,
|
| 2923 |
+
"learning_rate": 1.1011942174732873e-06,
|
| 2924 |
+
"loss": 1.4671,
|
| 2925 |
+
"step": 38900
|
| 2926 |
+
},
|
| 2927 |
+
{
|
| 2928 |
+
"epoch": 24.512884978001257,
|
| 2929 |
+
"grad_norm": 2.880321979522705,
|
| 2930 |
+
"learning_rate": 9.75487115021999e-07,
|
| 2931 |
+
"loss": 1.4211,
|
| 2932 |
+
"step": 39000
|
| 2933 |
+
},
|
| 2934 |
+
{
|
| 2935 |
+
"epoch": 24.5757385292269,
|
| 2936 |
+
"grad_norm": 4.416039943695068,
|
| 2937 |
+
"learning_rate": 8.497800125707103e-07,
|
| 2938 |
+
"loss": 1.4176,
|
| 2939 |
+
"step": 39100
|
| 2940 |
+
},
|
| 2941 |
+
{
|
| 2942 |
+
"epoch": 24.638592080452547,
|
| 2943 |
+
"grad_norm": 4.598896503448486,
|
| 2944 |
+
"learning_rate": 7.240729101194218e-07,
|
| 2945 |
+
"loss": 1.4194,
|
| 2946 |
+
"step": 39200
|
| 2947 |
+
},
|
| 2948 |
+
{
|
| 2949 |
+
"epoch": 24.70144563167819,
|
| 2950 |
+
"grad_norm": 4.256235599517822,
|
| 2951 |
+
"learning_rate": 5.983658076681333e-07,
|
| 2952 |
+
"loss": 1.4331,
|
| 2953 |
+
"step": 39300
|
| 2954 |
+
},
|
| 2955 |
+
{
|
| 2956 |
+
"epoch": 24.764299182903834,
|
| 2957 |
+
"grad_norm": 4.7764811515808105,
|
| 2958 |
+
"learning_rate": 4.726587052168448e-07,
|
| 2959 |
+
"loss": 1.4491,
|
| 2960 |
+
"step": 39400
|
| 2961 |
+
},
|
| 2962 |
+
{
|
| 2963 |
+
"epoch": 24.827152734129477,
|
| 2964 |
+
"grad_norm": 4.296844005584717,
|
| 2965 |
+
"learning_rate": 3.4695160276555627e-07,
|
| 2966 |
+
"loss": 1.4443,
|
| 2967 |
+
"step": 39500
|
| 2968 |
+
},
|
| 2969 |
+
{
|
| 2970 |
+
"epoch": 24.890006285355124,
|
| 2971 |
+
"grad_norm": 3.9589693546295166,
|
| 2972 |
+
"learning_rate": 2.2124450031426776e-07,
|
| 2973 |
+
"loss": 1.4612,
|
| 2974 |
+
"step": 39600
|
| 2975 |
+
},
|
| 2976 |
+
{
|
| 2977 |
+
"epoch": 24.952859836580767,
|
| 2978 |
+
"grad_norm": 4.165828227996826,
|
| 2979 |
+
"learning_rate": 9.553739786297926e-08,
|
| 2980 |
+
"loss": 1.48,
|
| 2981 |
+
"step": 39700
|
| 2982 |
+
},
|
| 2983 |
+
{
|
| 2984 |
+
"epoch": 25.0,
|
| 2985 |
+
"eval_loss": 1.528791069984436,
|
| 2986 |
+
"eval_runtime": 20.2887,
|
| 2987 |
+
"eval_samples_per_second": 47.218,
|
| 2988 |
+
"eval_steps_per_second": 5.915,
|
| 2989 |
+
"step": 39775
|
| 2990 |
+
}
|
| 2991 |
+
],
|
| 2992 |
+
"logging_steps": 100,
|
| 2993 |
+
"max_steps": 39775,
|
| 2994 |
+
"num_input_tokens_seen": 0,
|
| 2995 |
+
"num_train_epochs": 25,
|
| 2996 |
+
"save_steps": 500,
|
| 2997 |
+
"stateful_callbacks": {
|
| 2998 |
+
"TrainerControl": {
|
| 2999 |
+
"args": {
|
| 3000 |
+
"should_epoch_stop": false,
|
| 3001 |
+
"should_evaluate": false,
|
| 3002 |
+
"should_log": false,
|
| 3003 |
+
"should_save": true,
|
| 3004 |
+
"should_training_stop": true
|
| 3005 |
+
},
|
| 3006 |
+
"attributes": {}
|
| 3007 |
+
}
|
| 3008 |
+
},
|
| 3009 |
+
"total_flos": 5.44418915549184e+16,
|
| 3010 |
+
"train_batch_size": 8,
|
| 3011 |
+
"trial_name": null,
|
| 3012 |
+
"trial_params": null
|
| 3013 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1eb33c931180dbe9257345f90d386a1a68acae0c56733e81b74d0f9751ab8173
|
| 3 |
+
size 5496
|