Upload 13 files
Browse files- added_tokens.json +102 -0
- config.json +61 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +125 -0
- spiece.model +3 -0
- tokenizer_config.json +941 -0
- trainer_state.json +2448 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<extra_id_0>": 32099,
|
| 3 |
+
"<extra_id_10>": 32089,
|
| 4 |
+
"<extra_id_11>": 32088,
|
| 5 |
+
"<extra_id_12>": 32087,
|
| 6 |
+
"<extra_id_13>": 32086,
|
| 7 |
+
"<extra_id_14>": 32085,
|
| 8 |
+
"<extra_id_15>": 32084,
|
| 9 |
+
"<extra_id_16>": 32083,
|
| 10 |
+
"<extra_id_17>": 32082,
|
| 11 |
+
"<extra_id_18>": 32081,
|
| 12 |
+
"<extra_id_19>": 32080,
|
| 13 |
+
"<extra_id_1>": 32098,
|
| 14 |
+
"<extra_id_20>": 32079,
|
| 15 |
+
"<extra_id_21>": 32078,
|
| 16 |
+
"<extra_id_22>": 32077,
|
| 17 |
+
"<extra_id_23>": 32076,
|
| 18 |
+
"<extra_id_24>": 32075,
|
| 19 |
+
"<extra_id_25>": 32074,
|
| 20 |
+
"<extra_id_26>": 32073,
|
| 21 |
+
"<extra_id_27>": 32072,
|
| 22 |
+
"<extra_id_28>": 32071,
|
| 23 |
+
"<extra_id_29>": 32070,
|
| 24 |
+
"<extra_id_2>": 32097,
|
| 25 |
+
"<extra_id_30>": 32069,
|
| 26 |
+
"<extra_id_31>": 32068,
|
| 27 |
+
"<extra_id_32>": 32067,
|
| 28 |
+
"<extra_id_33>": 32066,
|
| 29 |
+
"<extra_id_34>": 32065,
|
| 30 |
+
"<extra_id_35>": 32064,
|
| 31 |
+
"<extra_id_36>": 32063,
|
| 32 |
+
"<extra_id_37>": 32062,
|
| 33 |
+
"<extra_id_38>": 32061,
|
| 34 |
+
"<extra_id_39>": 32060,
|
| 35 |
+
"<extra_id_3>": 32096,
|
| 36 |
+
"<extra_id_40>": 32059,
|
| 37 |
+
"<extra_id_41>": 32058,
|
| 38 |
+
"<extra_id_42>": 32057,
|
| 39 |
+
"<extra_id_43>": 32056,
|
| 40 |
+
"<extra_id_44>": 32055,
|
| 41 |
+
"<extra_id_45>": 32054,
|
| 42 |
+
"<extra_id_46>": 32053,
|
| 43 |
+
"<extra_id_47>": 32052,
|
| 44 |
+
"<extra_id_48>": 32051,
|
| 45 |
+
"<extra_id_49>": 32050,
|
| 46 |
+
"<extra_id_4>": 32095,
|
| 47 |
+
"<extra_id_50>": 32049,
|
| 48 |
+
"<extra_id_51>": 32048,
|
| 49 |
+
"<extra_id_52>": 32047,
|
| 50 |
+
"<extra_id_53>": 32046,
|
| 51 |
+
"<extra_id_54>": 32045,
|
| 52 |
+
"<extra_id_55>": 32044,
|
| 53 |
+
"<extra_id_56>": 32043,
|
| 54 |
+
"<extra_id_57>": 32042,
|
| 55 |
+
"<extra_id_58>": 32041,
|
| 56 |
+
"<extra_id_59>": 32040,
|
| 57 |
+
"<extra_id_5>": 32094,
|
| 58 |
+
"<extra_id_60>": 32039,
|
| 59 |
+
"<extra_id_61>": 32038,
|
| 60 |
+
"<extra_id_62>": 32037,
|
| 61 |
+
"<extra_id_63>": 32036,
|
| 62 |
+
"<extra_id_64>": 32035,
|
| 63 |
+
"<extra_id_65>": 32034,
|
| 64 |
+
"<extra_id_66>": 32033,
|
| 65 |
+
"<extra_id_67>": 32032,
|
| 66 |
+
"<extra_id_68>": 32031,
|
| 67 |
+
"<extra_id_69>": 32030,
|
| 68 |
+
"<extra_id_6>": 32093,
|
| 69 |
+
"<extra_id_70>": 32029,
|
| 70 |
+
"<extra_id_71>": 32028,
|
| 71 |
+
"<extra_id_72>": 32027,
|
| 72 |
+
"<extra_id_73>": 32026,
|
| 73 |
+
"<extra_id_74>": 32025,
|
| 74 |
+
"<extra_id_75>": 32024,
|
| 75 |
+
"<extra_id_76>": 32023,
|
| 76 |
+
"<extra_id_77>": 32022,
|
| 77 |
+
"<extra_id_78>": 32021,
|
| 78 |
+
"<extra_id_79>": 32020,
|
| 79 |
+
"<extra_id_7>": 32092,
|
| 80 |
+
"<extra_id_80>": 32019,
|
| 81 |
+
"<extra_id_81>": 32018,
|
| 82 |
+
"<extra_id_82>": 32017,
|
| 83 |
+
"<extra_id_83>": 32016,
|
| 84 |
+
"<extra_id_84>": 32015,
|
| 85 |
+
"<extra_id_85>": 32014,
|
| 86 |
+
"<extra_id_86>": 32013,
|
| 87 |
+
"<extra_id_87>": 32012,
|
| 88 |
+
"<extra_id_88>": 32011,
|
| 89 |
+
"<extra_id_89>": 32010,
|
| 90 |
+
"<extra_id_8>": 32091,
|
| 91 |
+
"<extra_id_90>": 32009,
|
| 92 |
+
"<extra_id_91>": 32008,
|
| 93 |
+
"<extra_id_92>": 32007,
|
| 94 |
+
"<extra_id_93>": 32006,
|
| 95 |
+
"<extra_id_94>": 32005,
|
| 96 |
+
"<extra_id_95>": 32004,
|
| 97 |
+
"<extra_id_96>": 32003,
|
| 98 |
+
"<extra_id_97>": 32002,
|
| 99 |
+
"<extra_id_98>": 32001,
|
| 100 |
+
"<extra_id_99>": 32000,
|
| 101 |
+
"<extra_id_9>": 32090
|
| 102 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_num_labels": 2,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 3072,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 768,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "relu",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 2,
|
| 14 |
+
"feed_forward_proj": "relu",
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": false,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "t5",
|
| 20 |
+
"n_positions": 512,
|
| 21 |
+
"num_decoder_layers": 12,
|
| 22 |
+
"num_heads": 12,
|
| 23 |
+
"num_layers": 12,
|
| 24 |
+
"output_past": true,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"relative_attention_max_distance": 128,
|
| 27 |
+
"relative_attention_num_buckets": 32,
|
| 28 |
+
"task_specific_params": {
|
| 29 |
+
"summarization": {
|
| 30 |
+
"early_stopping": true,
|
| 31 |
+
"length_penalty": 2.0,
|
| 32 |
+
"max_length": 200,
|
| 33 |
+
"min_length": 30,
|
| 34 |
+
"no_repeat_ngram_size": 3,
|
| 35 |
+
"num_beams": 4,
|
| 36 |
+
"prefix": "summarize: "
|
| 37 |
+
},
|
| 38 |
+
"translation_en_to_de": {
|
| 39 |
+
"early_stopping": true,
|
| 40 |
+
"max_length": 300,
|
| 41 |
+
"num_beams": 4,
|
| 42 |
+
"prefix": "translate English to German: "
|
| 43 |
+
},
|
| 44 |
+
"translation_en_to_fr": {
|
| 45 |
+
"early_stopping": true,
|
| 46 |
+
"max_length": 300,
|
| 47 |
+
"num_beams": 4,
|
| 48 |
+
"prefix": "translate English to French: "
|
| 49 |
+
},
|
| 50 |
+
"translation_en_to_ro": {
|
| 51 |
+
"early_stopping": true,
|
| 52 |
+
"max_length": 300,
|
| 53 |
+
"num_beams": 4,
|
| 54 |
+
"prefix": "translate English to Romanian: "
|
| 55 |
+
}
|
| 56 |
+
},
|
| 57 |
+
"torch_dtype": "float32",
|
| 58 |
+
"transformers_version": "4.51.3",
|
| 59 |
+
"use_cache": true,
|
| 60 |
+
"vocab_size": 32128
|
| 61 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.51.3"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6282d81308a4c20f381a6c67b6fbbe1ae4af5e5ecbb68e502ead3c0e2ffaa30
|
| 3 |
+
size 891644712
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74bea9a94b6f03823c7da7d884048e24f54f99c71b6ad4185af42c96c3eb0f24
|
| 3 |
+
size 1783445259
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49a85e4ea0dabf583c084cfb7053d3b461fd5a45bc525dffc02a2ebaa8d96f97
|
| 3 |
+
size 14645
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:104398ff0996f21172574347c3f37cabce8d2845ea276c31d216e4233b8835e6
|
| 3 |
+
size 1383
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47ac71d6a40c55dd69ede47858c8d98a3b6ecca3725727071949ec3bc2b94e14
|
| 3 |
+
size 1465
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"eos_token": {
|
| 105 |
+
"content": "</s>",
|
| 106 |
+
"lstrip": false,
|
| 107 |
+
"normalized": false,
|
| 108 |
+
"rstrip": false,
|
| 109 |
+
"single_word": false
|
| 110 |
+
},
|
| 111 |
+
"pad_token": {
|
| 112 |
+
"content": "<pad>",
|
| 113 |
+
"lstrip": false,
|
| 114 |
+
"normalized": false,
|
| 115 |
+
"rstrip": false,
|
| 116 |
+
"single_word": false
|
| 117 |
+
},
|
| 118 |
+
"unk_token": {
|
| 119 |
+
"content": "<unk>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false
|
| 124 |
+
}
|
| 125 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a4eb87011448a4564a3144979384da51eee1da95e554feb22ccc85529535dd5
|
| 3 |
+
size 1003118
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,941 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "<unk>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 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": true,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"32001": {
|
| 37 |
+
"content": "<extra_id_98>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": true,
|
| 41 |
+
"single_word": true,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"32002": {
|
| 45 |
+
"content": "<extra_id_97>",
|
| 46 |
+
"lstrip": true,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": true,
|
| 49 |
+
"single_word": true,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"32003": {
|
| 53 |
+
"content": "<extra_id_96>",
|
| 54 |
+
"lstrip": true,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": true,
|
| 57 |
+
"single_word": true,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"32004": {
|
| 61 |
+
"content": "<extra_id_95>",
|
| 62 |
+
"lstrip": true,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": true,
|
| 65 |
+
"single_word": true,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"32005": {
|
| 69 |
+
"content": "<extra_id_94>",
|
| 70 |
+
"lstrip": true,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": true,
|
| 73 |
+
"single_word": true,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"32006": {
|
| 77 |
+
"content": "<extra_id_93>",
|
| 78 |
+
"lstrip": true,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": true,
|
| 81 |
+
"single_word": true,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"32007": {
|
| 85 |
+
"content": "<extra_id_92>",
|
| 86 |
+
"lstrip": true,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": true,
|
| 89 |
+
"single_word": true,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"32008": {
|
| 93 |
+
"content": "<extra_id_91>",
|
| 94 |
+
"lstrip": true,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": true,
|
| 97 |
+
"single_word": true,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"32009": {
|
| 101 |
+
"content": "<extra_id_90>",
|
| 102 |
+
"lstrip": true,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": true,
|
| 105 |
+
"single_word": true,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"32010": {
|
| 109 |
+
"content": "<extra_id_89>",
|
| 110 |
+
"lstrip": true,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": true,
|
| 113 |
+
"single_word": true,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"32011": {
|
| 117 |
+
"content": "<extra_id_88>",
|
| 118 |
+
"lstrip": true,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": true,
|
| 121 |
+
"single_word": true,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"32012": {
|
| 125 |
+
"content": "<extra_id_87>",
|
| 126 |
+
"lstrip": true,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": true,
|
| 129 |
+
"single_word": true,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"32013": {
|
| 133 |
+
"content": "<extra_id_86>",
|
| 134 |
+
"lstrip": true,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": true,
|
| 137 |
+
"single_word": true,
|
| 138 |
+
"special": true
|
| 139 |
+
},
|
| 140 |
+
"32014": {
|
| 141 |
+
"content": "<extra_id_85>",
|
| 142 |
+
"lstrip": true,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": true,
|
| 145 |
+
"single_word": true,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
"32015": {
|
| 149 |
+
"content": "<extra_id_84>",
|
| 150 |
+
"lstrip": true,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": true,
|
| 153 |
+
"single_word": true,
|
| 154 |
+
"special": true
|
| 155 |
+
},
|
| 156 |
+
"32016": {
|
| 157 |
+
"content": "<extra_id_83>",
|
| 158 |
+
"lstrip": true,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": true,
|
| 161 |
+
"single_word": true,
|
| 162 |
+
"special": true
|
| 163 |
+
},
|
| 164 |
+
"32017": {
|
| 165 |
+
"content": "<extra_id_82>",
|
| 166 |
+
"lstrip": true,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": true,
|
| 169 |
+
"single_word": true,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"32018": {
|
| 173 |
+
"content": "<extra_id_81>",
|
| 174 |
+
"lstrip": true,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": true,
|
| 177 |
+
"single_word": true,
|
| 178 |
+
"special": true
|
| 179 |
+
},
|
| 180 |
+
"32019": {
|
| 181 |
+
"content": "<extra_id_80>",
|
| 182 |
+
"lstrip": true,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": true,
|
| 185 |
+
"single_word": true,
|
| 186 |
+
"special": true
|
| 187 |
+
},
|
| 188 |
+
"32020": {
|
| 189 |
+
"content": "<extra_id_79>",
|
| 190 |
+
"lstrip": true,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": true,
|
| 193 |
+
"single_word": true,
|
| 194 |
+
"special": true
|
| 195 |
+
},
|
| 196 |
+
"32021": {
|
| 197 |
+
"content": "<extra_id_78>",
|
| 198 |
+
"lstrip": true,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": true,
|
| 201 |
+
"single_word": true,
|
| 202 |
+
"special": true
|
| 203 |
+
},
|
| 204 |
+
"32022": {
|
| 205 |
+
"content": "<extra_id_77>",
|
| 206 |
+
"lstrip": true,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": true,
|
| 209 |
+
"single_word": true,
|
| 210 |
+
"special": true
|
| 211 |
+
},
|
| 212 |
+
"32023": {
|
| 213 |
+
"content": "<extra_id_76>",
|
| 214 |
+
"lstrip": true,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"rstrip": true,
|
| 217 |
+
"single_word": true,
|
| 218 |
+
"special": true
|
| 219 |
+
},
|
| 220 |
+
"32024": {
|
| 221 |
+
"content": "<extra_id_75>",
|
| 222 |
+
"lstrip": true,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"rstrip": true,
|
| 225 |
+
"single_word": true,
|
| 226 |
+
"special": true
|
| 227 |
+
},
|
| 228 |
+
"32025": {
|
| 229 |
+
"content": "<extra_id_74>",
|
| 230 |
+
"lstrip": true,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"rstrip": true,
|
| 233 |
+
"single_word": true,
|
| 234 |
+
"special": true
|
| 235 |
+
},
|
| 236 |
+
"32026": {
|
| 237 |
+
"content": "<extra_id_73>",
|
| 238 |
+
"lstrip": true,
|
| 239 |
+
"normalized": false,
|
| 240 |
+
"rstrip": true,
|
| 241 |
+
"single_word": true,
|
| 242 |
+
"special": true
|
| 243 |
+
},
|
| 244 |
+
"32027": {
|
| 245 |
+
"content": "<extra_id_72>",
|
| 246 |
+
"lstrip": true,
|
| 247 |
+
"normalized": false,
|
| 248 |
+
"rstrip": true,
|
| 249 |
+
"single_word": true,
|
| 250 |
+
"special": true
|
| 251 |
+
},
|
| 252 |
+
"32028": {
|
| 253 |
+
"content": "<extra_id_71>",
|
| 254 |
+
"lstrip": true,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"rstrip": true,
|
| 257 |
+
"single_word": true,
|
| 258 |
+
"special": true
|
| 259 |
+
},
|
| 260 |
+
"32029": {
|
| 261 |
+
"content": "<extra_id_70>",
|
| 262 |
+
"lstrip": true,
|
| 263 |
+
"normalized": false,
|
| 264 |
+
"rstrip": true,
|
| 265 |
+
"single_word": true,
|
| 266 |
+
"special": true
|
| 267 |
+
},
|
| 268 |
+
"32030": {
|
| 269 |
+
"content": "<extra_id_69>",
|
| 270 |
+
"lstrip": true,
|
| 271 |
+
"normalized": false,
|
| 272 |
+
"rstrip": true,
|
| 273 |
+
"single_word": true,
|
| 274 |
+
"special": true
|
| 275 |
+
},
|
| 276 |
+
"32031": {
|
| 277 |
+
"content": "<extra_id_68>",
|
| 278 |
+
"lstrip": true,
|
| 279 |
+
"normalized": false,
|
| 280 |
+
"rstrip": true,
|
| 281 |
+
"single_word": true,
|
| 282 |
+
"special": true
|
| 283 |
+
},
|
| 284 |
+
"32032": {
|
| 285 |
+
"content": "<extra_id_67>",
|
| 286 |
+
"lstrip": true,
|
| 287 |
+
"normalized": false,
|
| 288 |
+
"rstrip": true,
|
| 289 |
+
"single_word": true,
|
| 290 |
+
"special": true
|
| 291 |
+
},
|
| 292 |
+
"32033": {
|
| 293 |
+
"content": "<extra_id_66>",
|
| 294 |
+
"lstrip": true,
|
| 295 |
+
"normalized": false,
|
| 296 |
+
"rstrip": true,
|
| 297 |
+
"single_word": true,
|
| 298 |
+
"special": true
|
| 299 |
+
},
|
| 300 |
+
"32034": {
|
| 301 |
+
"content": "<extra_id_65>",
|
| 302 |
+
"lstrip": true,
|
| 303 |
+
"normalized": false,
|
| 304 |
+
"rstrip": true,
|
| 305 |
+
"single_word": true,
|
| 306 |
+
"special": true
|
| 307 |
+
},
|
| 308 |
+
"32035": {
|
| 309 |
+
"content": "<extra_id_64>",
|
| 310 |
+
"lstrip": true,
|
| 311 |
+
"normalized": false,
|
| 312 |
+
"rstrip": true,
|
| 313 |
+
"single_word": true,
|
| 314 |
+
"special": true
|
| 315 |
+
},
|
| 316 |
+
"32036": {
|
| 317 |
+
"content": "<extra_id_63>",
|
| 318 |
+
"lstrip": true,
|
| 319 |
+
"normalized": false,
|
| 320 |
+
"rstrip": true,
|
| 321 |
+
"single_word": true,
|
| 322 |
+
"special": true
|
| 323 |
+
},
|
| 324 |
+
"32037": {
|
| 325 |
+
"content": "<extra_id_62>",
|
| 326 |
+
"lstrip": true,
|
| 327 |
+
"normalized": false,
|
| 328 |
+
"rstrip": true,
|
| 329 |
+
"single_word": true,
|
| 330 |
+
"special": true
|
| 331 |
+
},
|
| 332 |
+
"32038": {
|
| 333 |
+
"content": "<extra_id_61>",
|
| 334 |
+
"lstrip": true,
|
| 335 |
+
"normalized": false,
|
| 336 |
+
"rstrip": true,
|
| 337 |
+
"single_word": true,
|
| 338 |
+
"special": true
|
| 339 |
+
},
|
| 340 |
+
"32039": {
|
| 341 |
+
"content": "<extra_id_60>",
|
| 342 |
+
"lstrip": true,
|
| 343 |
+
"normalized": false,
|
| 344 |
+
"rstrip": true,
|
| 345 |
+
"single_word": true,
|
| 346 |
+
"special": true
|
| 347 |
+
},
|
| 348 |
+
"32040": {
|
| 349 |
+
"content": "<extra_id_59>",
|
| 350 |
+
"lstrip": true,
|
| 351 |
+
"normalized": false,
|
| 352 |
+
"rstrip": true,
|
| 353 |
+
"single_word": true,
|
| 354 |
+
"special": true
|
| 355 |
+
},
|
| 356 |
+
"32041": {
|
| 357 |
+
"content": "<extra_id_58>",
|
| 358 |
+
"lstrip": true,
|
| 359 |
+
"normalized": false,
|
| 360 |
+
"rstrip": true,
|
| 361 |
+
"single_word": true,
|
| 362 |
+
"special": true
|
| 363 |
+
},
|
| 364 |
+
"32042": {
|
| 365 |
+
"content": "<extra_id_57>",
|
| 366 |
+
"lstrip": true,
|
| 367 |
+
"normalized": false,
|
| 368 |
+
"rstrip": true,
|
| 369 |
+
"single_word": true,
|
| 370 |
+
"special": true
|
| 371 |
+
},
|
| 372 |
+
"32043": {
|
| 373 |
+
"content": "<extra_id_56>",
|
| 374 |
+
"lstrip": true,
|
| 375 |
+
"normalized": false,
|
| 376 |
+
"rstrip": true,
|
| 377 |
+
"single_word": true,
|
| 378 |
+
"special": true
|
| 379 |
+
},
|
| 380 |
+
"32044": {
|
| 381 |
+
"content": "<extra_id_55>",
|
| 382 |
+
"lstrip": true,
|
| 383 |
+
"normalized": false,
|
| 384 |
+
"rstrip": true,
|
| 385 |
+
"single_word": true,
|
| 386 |
+
"special": true
|
| 387 |
+
},
|
| 388 |
+
"32045": {
|
| 389 |
+
"content": "<extra_id_54>",
|
| 390 |
+
"lstrip": true,
|
| 391 |
+
"normalized": false,
|
| 392 |
+
"rstrip": true,
|
| 393 |
+
"single_word": true,
|
| 394 |
+
"special": true
|
| 395 |
+
},
|
| 396 |
+
"32046": {
|
| 397 |
+
"content": "<extra_id_53>",
|
| 398 |
+
"lstrip": true,
|
| 399 |
+
"normalized": false,
|
| 400 |
+
"rstrip": true,
|
| 401 |
+
"single_word": true,
|
| 402 |
+
"special": true
|
| 403 |
+
},
|
| 404 |
+
"32047": {
|
| 405 |
+
"content": "<extra_id_52>",
|
| 406 |
+
"lstrip": true,
|
| 407 |
+
"normalized": false,
|
| 408 |
+
"rstrip": true,
|
| 409 |
+
"single_word": true,
|
| 410 |
+
"special": true
|
| 411 |
+
},
|
| 412 |
+
"32048": {
|
| 413 |
+
"content": "<extra_id_51>",
|
| 414 |
+
"lstrip": true,
|
| 415 |
+
"normalized": false,
|
| 416 |
+
"rstrip": true,
|
| 417 |
+
"single_word": true,
|
| 418 |
+
"special": true
|
| 419 |
+
},
|
| 420 |
+
"32049": {
|
| 421 |
+
"content": "<extra_id_50>",
|
| 422 |
+
"lstrip": true,
|
| 423 |
+
"normalized": false,
|
| 424 |
+
"rstrip": true,
|
| 425 |
+
"single_word": true,
|
| 426 |
+
"special": true
|
| 427 |
+
},
|
| 428 |
+
"32050": {
|
| 429 |
+
"content": "<extra_id_49>",
|
| 430 |
+
"lstrip": true,
|
| 431 |
+
"normalized": false,
|
| 432 |
+
"rstrip": true,
|
| 433 |
+
"single_word": true,
|
| 434 |
+
"special": true
|
| 435 |
+
},
|
| 436 |
+
"32051": {
|
| 437 |
+
"content": "<extra_id_48>",
|
| 438 |
+
"lstrip": true,
|
| 439 |
+
"normalized": false,
|
| 440 |
+
"rstrip": true,
|
| 441 |
+
"single_word": true,
|
| 442 |
+
"special": true
|
| 443 |
+
},
|
| 444 |
+
"32052": {
|
| 445 |
+
"content": "<extra_id_47>",
|
| 446 |
+
"lstrip": true,
|
| 447 |
+
"normalized": false,
|
| 448 |
+
"rstrip": true,
|
| 449 |
+
"single_word": true,
|
| 450 |
+
"special": true
|
| 451 |
+
},
|
| 452 |
+
"32053": {
|
| 453 |
+
"content": "<extra_id_46>",
|
| 454 |
+
"lstrip": true,
|
| 455 |
+
"normalized": false,
|
| 456 |
+
"rstrip": true,
|
| 457 |
+
"single_word": true,
|
| 458 |
+
"special": true
|
| 459 |
+
},
|
| 460 |
+
"32054": {
|
| 461 |
+
"content": "<extra_id_45>",
|
| 462 |
+
"lstrip": true,
|
| 463 |
+
"normalized": false,
|
| 464 |
+
"rstrip": true,
|
| 465 |
+
"single_word": true,
|
| 466 |
+
"special": true
|
| 467 |
+
},
|
| 468 |
+
"32055": {
|
| 469 |
+
"content": "<extra_id_44>",
|
| 470 |
+
"lstrip": true,
|
| 471 |
+
"normalized": false,
|
| 472 |
+
"rstrip": true,
|
| 473 |
+
"single_word": true,
|
| 474 |
+
"special": true
|
| 475 |
+
},
|
| 476 |
+
"32056": {
|
| 477 |
+
"content": "<extra_id_43>",
|
| 478 |
+
"lstrip": true,
|
| 479 |
+
"normalized": false,
|
| 480 |
+
"rstrip": true,
|
| 481 |
+
"single_word": true,
|
| 482 |
+
"special": true
|
| 483 |
+
},
|
| 484 |
+
"32057": {
|
| 485 |
+
"content": "<extra_id_42>",
|
| 486 |
+
"lstrip": true,
|
| 487 |
+
"normalized": false,
|
| 488 |
+
"rstrip": true,
|
| 489 |
+
"single_word": true,
|
| 490 |
+
"special": true
|
| 491 |
+
},
|
| 492 |
+
"32058": {
|
| 493 |
+
"content": "<extra_id_41>",
|
| 494 |
+
"lstrip": true,
|
| 495 |
+
"normalized": false,
|
| 496 |
+
"rstrip": true,
|
| 497 |
+
"single_word": true,
|
| 498 |
+
"special": true
|
| 499 |
+
},
|
| 500 |
+
"32059": {
|
| 501 |
+
"content": "<extra_id_40>",
|
| 502 |
+
"lstrip": true,
|
| 503 |
+
"normalized": false,
|
| 504 |
+
"rstrip": true,
|
| 505 |
+
"single_word": true,
|
| 506 |
+
"special": true
|
| 507 |
+
},
|
| 508 |
+
"32060": {
|
| 509 |
+
"content": "<extra_id_39>",
|
| 510 |
+
"lstrip": true,
|
| 511 |
+
"normalized": false,
|
| 512 |
+
"rstrip": true,
|
| 513 |
+
"single_word": true,
|
| 514 |
+
"special": true
|
| 515 |
+
},
|
| 516 |
+
"32061": {
|
| 517 |
+
"content": "<extra_id_38>",
|
| 518 |
+
"lstrip": true,
|
| 519 |
+
"normalized": false,
|
| 520 |
+
"rstrip": true,
|
| 521 |
+
"single_word": true,
|
| 522 |
+
"special": true
|
| 523 |
+
},
|
| 524 |
+
"32062": {
|
| 525 |
+
"content": "<extra_id_37>",
|
| 526 |
+
"lstrip": true,
|
| 527 |
+
"normalized": false,
|
| 528 |
+
"rstrip": true,
|
| 529 |
+
"single_word": true,
|
| 530 |
+
"special": true
|
| 531 |
+
},
|
| 532 |
+
"32063": {
|
| 533 |
+
"content": "<extra_id_36>",
|
| 534 |
+
"lstrip": true,
|
| 535 |
+
"normalized": false,
|
| 536 |
+
"rstrip": true,
|
| 537 |
+
"single_word": true,
|
| 538 |
+
"special": true
|
| 539 |
+
},
|
| 540 |
+
"32064": {
|
| 541 |
+
"content": "<extra_id_35>",
|
| 542 |
+
"lstrip": true,
|
| 543 |
+
"normalized": false,
|
| 544 |
+
"rstrip": true,
|
| 545 |
+
"single_word": true,
|
| 546 |
+
"special": true
|
| 547 |
+
},
|
| 548 |
+
"32065": {
|
| 549 |
+
"content": "<extra_id_34>",
|
| 550 |
+
"lstrip": true,
|
| 551 |
+
"normalized": false,
|
| 552 |
+
"rstrip": true,
|
| 553 |
+
"single_word": true,
|
| 554 |
+
"special": true
|
| 555 |
+
},
|
| 556 |
+
"32066": {
|
| 557 |
+
"content": "<extra_id_33>",
|
| 558 |
+
"lstrip": true,
|
| 559 |
+
"normalized": false,
|
| 560 |
+
"rstrip": true,
|
| 561 |
+
"single_word": true,
|
| 562 |
+
"special": true
|
| 563 |
+
},
|
| 564 |
+
"32067": {
|
| 565 |
+
"content": "<extra_id_32>",
|
| 566 |
+
"lstrip": true,
|
| 567 |
+
"normalized": false,
|
| 568 |
+
"rstrip": true,
|
| 569 |
+
"single_word": true,
|
| 570 |
+
"special": true
|
| 571 |
+
},
|
| 572 |
+
"32068": {
|
| 573 |
+
"content": "<extra_id_31>",
|
| 574 |
+
"lstrip": true,
|
| 575 |
+
"normalized": false,
|
| 576 |
+
"rstrip": true,
|
| 577 |
+
"single_word": true,
|
| 578 |
+
"special": true
|
| 579 |
+
},
|
| 580 |
+
"32069": {
|
| 581 |
+
"content": "<extra_id_30>",
|
| 582 |
+
"lstrip": true,
|
| 583 |
+
"normalized": false,
|
| 584 |
+
"rstrip": true,
|
| 585 |
+
"single_word": true,
|
| 586 |
+
"special": true
|
| 587 |
+
},
|
| 588 |
+
"32070": {
|
| 589 |
+
"content": "<extra_id_29>",
|
| 590 |
+
"lstrip": true,
|
| 591 |
+
"normalized": false,
|
| 592 |
+
"rstrip": true,
|
| 593 |
+
"single_word": true,
|
| 594 |
+
"special": true
|
| 595 |
+
},
|
| 596 |
+
"32071": {
|
| 597 |
+
"content": "<extra_id_28>",
|
| 598 |
+
"lstrip": true,
|
| 599 |
+
"normalized": false,
|
| 600 |
+
"rstrip": true,
|
| 601 |
+
"single_word": true,
|
| 602 |
+
"special": true
|
| 603 |
+
},
|
| 604 |
+
"32072": {
|
| 605 |
+
"content": "<extra_id_27>",
|
| 606 |
+
"lstrip": true,
|
| 607 |
+
"normalized": false,
|
| 608 |
+
"rstrip": true,
|
| 609 |
+
"single_word": true,
|
| 610 |
+
"special": true
|
| 611 |
+
},
|
| 612 |
+
"32073": {
|
| 613 |
+
"content": "<extra_id_26>",
|
| 614 |
+
"lstrip": true,
|
| 615 |
+
"normalized": false,
|
| 616 |
+
"rstrip": true,
|
| 617 |
+
"single_word": true,
|
| 618 |
+
"special": true
|
| 619 |
+
},
|
| 620 |
+
"32074": {
|
| 621 |
+
"content": "<extra_id_25>",
|
| 622 |
+
"lstrip": true,
|
| 623 |
+
"normalized": false,
|
| 624 |
+
"rstrip": true,
|
| 625 |
+
"single_word": true,
|
| 626 |
+
"special": true
|
| 627 |
+
},
|
| 628 |
+
"32075": {
|
| 629 |
+
"content": "<extra_id_24>",
|
| 630 |
+
"lstrip": true,
|
| 631 |
+
"normalized": false,
|
| 632 |
+
"rstrip": true,
|
| 633 |
+
"single_word": true,
|
| 634 |
+
"special": true
|
| 635 |
+
},
|
| 636 |
+
"32076": {
|
| 637 |
+
"content": "<extra_id_23>",
|
| 638 |
+
"lstrip": true,
|
| 639 |
+
"normalized": false,
|
| 640 |
+
"rstrip": true,
|
| 641 |
+
"single_word": true,
|
| 642 |
+
"special": true
|
| 643 |
+
},
|
| 644 |
+
"32077": {
|
| 645 |
+
"content": "<extra_id_22>",
|
| 646 |
+
"lstrip": true,
|
| 647 |
+
"normalized": false,
|
| 648 |
+
"rstrip": true,
|
| 649 |
+
"single_word": true,
|
| 650 |
+
"special": true
|
| 651 |
+
},
|
| 652 |
+
"32078": {
|
| 653 |
+
"content": "<extra_id_21>",
|
| 654 |
+
"lstrip": true,
|
| 655 |
+
"normalized": false,
|
| 656 |
+
"rstrip": true,
|
| 657 |
+
"single_word": true,
|
| 658 |
+
"special": true
|
| 659 |
+
},
|
| 660 |
+
"32079": {
|
| 661 |
+
"content": "<extra_id_20>",
|
| 662 |
+
"lstrip": true,
|
| 663 |
+
"normalized": false,
|
| 664 |
+
"rstrip": true,
|
| 665 |
+
"single_word": true,
|
| 666 |
+
"special": true
|
| 667 |
+
},
|
| 668 |
+
"32080": {
|
| 669 |
+
"content": "<extra_id_19>",
|
| 670 |
+
"lstrip": true,
|
| 671 |
+
"normalized": false,
|
| 672 |
+
"rstrip": true,
|
| 673 |
+
"single_word": true,
|
| 674 |
+
"special": true
|
| 675 |
+
},
|
| 676 |
+
"32081": {
|
| 677 |
+
"content": "<extra_id_18>",
|
| 678 |
+
"lstrip": true,
|
| 679 |
+
"normalized": false,
|
| 680 |
+
"rstrip": true,
|
| 681 |
+
"single_word": true,
|
| 682 |
+
"special": true
|
| 683 |
+
},
|
| 684 |
+
"32082": {
|
| 685 |
+
"content": "<extra_id_17>",
|
| 686 |
+
"lstrip": true,
|
| 687 |
+
"normalized": false,
|
| 688 |
+
"rstrip": true,
|
| 689 |
+
"single_word": true,
|
| 690 |
+
"special": true
|
| 691 |
+
},
|
| 692 |
+
"32083": {
|
| 693 |
+
"content": "<extra_id_16>",
|
| 694 |
+
"lstrip": true,
|
| 695 |
+
"normalized": false,
|
| 696 |
+
"rstrip": true,
|
| 697 |
+
"single_word": true,
|
| 698 |
+
"special": true
|
| 699 |
+
},
|
| 700 |
+
"32084": {
|
| 701 |
+
"content": "<extra_id_15>",
|
| 702 |
+
"lstrip": true,
|
| 703 |
+
"normalized": false,
|
| 704 |
+
"rstrip": true,
|
| 705 |
+
"single_word": true,
|
| 706 |
+
"special": true
|
| 707 |
+
},
|
| 708 |
+
"32085": {
|
| 709 |
+
"content": "<extra_id_14>",
|
| 710 |
+
"lstrip": true,
|
| 711 |
+
"normalized": false,
|
| 712 |
+
"rstrip": true,
|
| 713 |
+
"single_word": true,
|
| 714 |
+
"special": true
|
| 715 |
+
},
|
| 716 |
+
"32086": {
|
| 717 |
+
"content": "<extra_id_13>",
|
| 718 |
+
"lstrip": true,
|
| 719 |
+
"normalized": false,
|
| 720 |
+
"rstrip": true,
|
| 721 |
+
"single_word": true,
|
| 722 |
+
"special": true
|
| 723 |
+
},
|
| 724 |
+
"32087": {
|
| 725 |
+
"content": "<extra_id_12>",
|
| 726 |
+
"lstrip": true,
|
| 727 |
+
"normalized": false,
|
| 728 |
+
"rstrip": true,
|
| 729 |
+
"single_word": true,
|
| 730 |
+
"special": true
|
| 731 |
+
},
|
| 732 |
+
"32088": {
|
| 733 |
+
"content": "<extra_id_11>",
|
| 734 |
+
"lstrip": true,
|
| 735 |
+
"normalized": false,
|
| 736 |
+
"rstrip": true,
|
| 737 |
+
"single_word": true,
|
| 738 |
+
"special": true
|
| 739 |
+
},
|
| 740 |
+
"32089": {
|
| 741 |
+
"content": "<extra_id_10>",
|
| 742 |
+
"lstrip": true,
|
| 743 |
+
"normalized": false,
|
| 744 |
+
"rstrip": true,
|
| 745 |
+
"single_word": true,
|
| 746 |
+
"special": true
|
| 747 |
+
},
|
| 748 |
+
"32090": {
|
| 749 |
+
"content": "<extra_id_9>",
|
| 750 |
+
"lstrip": true,
|
| 751 |
+
"normalized": false,
|
| 752 |
+
"rstrip": true,
|
| 753 |
+
"single_word": true,
|
| 754 |
+
"special": true
|
| 755 |
+
},
|
| 756 |
+
"32091": {
|
| 757 |
+
"content": "<extra_id_8>",
|
| 758 |
+
"lstrip": true,
|
| 759 |
+
"normalized": false,
|
| 760 |
+
"rstrip": true,
|
| 761 |
+
"single_word": true,
|
| 762 |
+
"special": true
|
| 763 |
+
},
|
| 764 |
+
"32092": {
|
| 765 |
+
"content": "<extra_id_7>",
|
| 766 |
+
"lstrip": true,
|
| 767 |
+
"normalized": false,
|
| 768 |
+
"rstrip": true,
|
| 769 |
+
"single_word": true,
|
| 770 |
+
"special": true
|
| 771 |
+
},
|
| 772 |
+
"32093": {
|
| 773 |
+
"content": "<extra_id_6>",
|
| 774 |
+
"lstrip": true,
|
| 775 |
+
"normalized": false,
|
| 776 |
+
"rstrip": true,
|
| 777 |
+
"single_word": true,
|
| 778 |
+
"special": true
|
| 779 |
+
},
|
| 780 |
+
"32094": {
|
| 781 |
+
"content": "<extra_id_5>",
|
| 782 |
+
"lstrip": true,
|
| 783 |
+
"normalized": false,
|
| 784 |
+
"rstrip": true,
|
| 785 |
+
"single_word": true,
|
| 786 |
+
"special": true
|
| 787 |
+
},
|
| 788 |
+
"32095": {
|
| 789 |
+
"content": "<extra_id_4>",
|
| 790 |
+
"lstrip": true,
|
| 791 |
+
"normalized": false,
|
| 792 |
+
"rstrip": true,
|
| 793 |
+
"single_word": true,
|
| 794 |
+
"special": true
|
| 795 |
+
},
|
| 796 |
+
"32096": {
|
| 797 |
+
"content": "<extra_id_3>",
|
| 798 |
+
"lstrip": true,
|
| 799 |
+
"normalized": false,
|
| 800 |
+
"rstrip": true,
|
| 801 |
+
"single_word": true,
|
| 802 |
+
"special": true
|
| 803 |
+
},
|
| 804 |
+
"32097": {
|
| 805 |
+
"content": "<extra_id_2>",
|
| 806 |
+
"lstrip": true,
|
| 807 |
+
"normalized": false,
|
| 808 |
+
"rstrip": true,
|
| 809 |
+
"single_word": true,
|
| 810 |
+
"special": true
|
| 811 |
+
},
|
| 812 |
+
"32098": {
|
| 813 |
+
"content": "<extra_id_1>",
|
| 814 |
+
"lstrip": true,
|
| 815 |
+
"normalized": false,
|
| 816 |
+
"rstrip": true,
|
| 817 |
+
"single_word": true,
|
| 818 |
+
"special": true
|
| 819 |
+
},
|
| 820 |
+
"32099": {
|
| 821 |
+
"content": "<extra_id_0>",
|
| 822 |
+
"lstrip": true,
|
| 823 |
+
"normalized": false,
|
| 824 |
+
"rstrip": true,
|
| 825 |
+
"single_word": true,
|
| 826 |
+
"special": true
|
| 827 |
+
}
|
| 828 |
+
},
|
| 829 |
+
"additional_special_tokens": [
|
| 830 |
+
"<extra_id_0>",
|
| 831 |
+
"<extra_id_1>",
|
| 832 |
+
"<extra_id_2>",
|
| 833 |
+
"<extra_id_3>",
|
| 834 |
+
"<extra_id_4>",
|
| 835 |
+
"<extra_id_5>",
|
| 836 |
+
"<extra_id_6>",
|
| 837 |
+
"<extra_id_7>",
|
| 838 |
+
"<extra_id_8>",
|
| 839 |
+
"<extra_id_9>",
|
| 840 |
+
"<extra_id_10>",
|
| 841 |
+
"<extra_id_11>",
|
| 842 |
+
"<extra_id_12>",
|
| 843 |
+
"<extra_id_13>",
|
| 844 |
+
"<extra_id_14>",
|
| 845 |
+
"<extra_id_15>",
|
| 846 |
+
"<extra_id_16>",
|
| 847 |
+
"<extra_id_17>",
|
| 848 |
+
"<extra_id_18>",
|
| 849 |
+
"<extra_id_19>",
|
| 850 |
+
"<extra_id_20>",
|
| 851 |
+
"<extra_id_21>",
|
| 852 |
+
"<extra_id_22>",
|
| 853 |
+
"<extra_id_23>",
|
| 854 |
+
"<extra_id_24>",
|
| 855 |
+
"<extra_id_25>",
|
| 856 |
+
"<extra_id_26>",
|
| 857 |
+
"<extra_id_27>",
|
| 858 |
+
"<extra_id_28>",
|
| 859 |
+
"<extra_id_29>",
|
| 860 |
+
"<extra_id_30>",
|
| 861 |
+
"<extra_id_31>",
|
| 862 |
+
"<extra_id_32>",
|
| 863 |
+
"<extra_id_33>",
|
| 864 |
+
"<extra_id_34>",
|
| 865 |
+
"<extra_id_35>",
|
| 866 |
+
"<extra_id_36>",
|
| 867 |
+
"<extra_id_37>",
|
| 868 |
+
"<extra_id_38>",
|
| 869 |
+
"<extra_id_39>",
|
| 870 |
+
"<extra_id_40>",
|
| 871 |
+
"<extra_id_41>",
|
| 872 |
+
"<extra_id_42>",
|
| 873 |
+
"<extra_id_43>",
|
| 874 |
+
"<extra_id_44>",
|
| 875 |
+
"<extra_id_45>",
|
| 876 |
+
"<extra_id_46>",
|
| 877 |
+
"<extra_id_47>",
|
| 878 |
+
"<extra_id_48>",
|
| 879 |
+
"<extra_id_49>",
|
| 880 |
+
"<extra_id_50>",
|
| 881 |
+
"<extra_id_51>",
|
| 882 |
+
"<extra_id_52>",
|
| 883 |
+
"<extra_id_53>",
|
| 884 |
+
"<extra_id_54>",
|
| 885 |
+
"<extra_id_55>",
|
| 886 |
+
"<extra_id_56>",
|
| 887 |
+
"<extra_id_57>",
|
| 888 |
+
"<extra_id_58>",
|
| 889 |
+
"<extra_id_59>",
|
| 890 |
+
"<extra_id_60>",
|
| 891 |
+
"<extra_id_61>",
|
| 892 |
+
"<extra_id_62>",
|
| 893 |
+
"<extra_id_63>",
|
| 894 |
+
"<extra_id_64>",
|
| 895 |
+
"<extra_id_65>",
|
| 896 |
+
"<extra_id_66>",
|
| 897 |
+
"<extra_id_67>",
|
| 898 |
+
"<extra_id_68>",
|
| 899 |
+
"<extra_id_69>",
|
| 900 |
+
"<extra_id_70>",
|
| 901 |
+
"<extra_id_71>",
|
| 902 |
+
"<extra_id_72>",
|
| 903 |
+
"<extra_id_73>",
|
| 904 |
+
"<extra_id_74>",
|
| 905 |
+
"<extra_id_75>",
|
| 906 |
+
"<extra_id_76>",
|
| 907 |
+
"<extra_id_77>",
|
| 908 |
+
"<extra_id_78>",
|
| 909 |
+
"<extra_id_79>",
|
| 910 |
+
"<extra_id_80>",
|
| 911 |
+
"<extra_id_81>",
|
| 912 |
+
"<extra_id_82>",
|
| 913 |
+
"<extra_id_83>",
|
| 914 |
+
"<extra_id_84>",
|
| 915 |
+
"<extra_id_85>",
|
| 916 |
+
"<extra_id_86>",
|
| 917 |
+
"<extra_id_87>",
|
| 918 |
+
"<extra_id_88>",
|
| 919 |
+
"<extra_id_89>",
|
| 920 |
+
"<extra_id_90>",
|
| 921 |
+
"<extra_id_91>",
|
| 922 |
+
"<extra_id_92>",
|
| 923 |
+
"<extra_id_93>",
|
| 924 |
+
"<extra_id_94>",
|
| 925 |
+
"<extra_id_95>",
|
| 926 |
+
"<extra_id_96>",
|
| 927 |
+
"<extra_id_97>",
|
| 928 |
+
"<extra_id_98>",
|
| 929 |
+
"<extra_id_99>"
|
| 930 |
+
],
|
| 931 |
+
"clean_up_tokenization_spaces": false,
|
| 932 |
+
"eos_token": "</s>",
|
| 933 |
+
"extra_ids": 100,
|
| 934 |
+
"extra_special_tokens": {},
|
| 935 |
+
"legacy": true,
|
| 936 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 937 |
+
"pad_token": "<pad>",
|
| 938 |
+
"sp_model_kwargs": {},
|
| 939 |
+
"tokenizer_class": "T5Tokenizer",
|
| 940 |
+
"unk_token": "<unk>"
|
| 941 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2448 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 19.999535243996903,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 32260,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.061967467079783116,
|
| 14 |
+
"grad_norm": 20.777441024780273,
|
| 15 |
+
"learning_rate": 9.97179169249845e-06,
|
| 16 |
+
"loss": 5.1314,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.12393493415956623,
|
| 21 |
+
"grad_norm": 7.313554763793945,
|
| 22 |
+
"learning_rate": 9.940793552386857e-06,
|
| 23 |
+
"loss": 2.5079,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.18590240123934934,
|
| 28 |
+
"grad_norm": 6.049108982086182,
|
| 29 |
+
"learning_rate": 9.909795412275263e-06,
|
| 30 |
+
"loss": 2.262,
|
| 31 |
+
"step": 300
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.24786986831913246,
|
| 35 |
+
"grad_norm": 7.533471584320068,
|
| 36 |
+
"learning_rate": 9.878797272163671e-06,
|
| 37 |
+
"loss": 2.1505,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.30983733539891556,
|
| 42 |
+
"grad_norm": 7.321562767028809,
|
| 43 |
+
"learning_rate": 9.847799132052077e-06,
|
| 44 |
+
"loss": 2.0719,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.3718048024786987,
|
| 49 |
+
"grad_norm": 9.049120903015137,
|
| 50 |
+
"learning_rate": 9.816800991940483e-06,
|
| 51 |
+
"loss": 2.0476,
|
| 52 |
+
"step": 600
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.4337722695584818,
|
| 56 |
+
"grad_norm": 4.262355804443359,
|
| 57 |
+
"learning_rate": 9.785802851828891e-06,
|
| 58 |
+
"loss": 2.0214,
|
| 59 |
+
"step": 700
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.4957397366382649,
|
| 63 |
+
"grad_norm": 4.2409491539001465,
|
| 64 |
+
"learning_rate": 9.754804711717297e-06,
|
| 65 |
+
"loss": 2.0108,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.557707203718048,
|
| 70 |
+
"grad_norm": 4.823696136474609,
|
| 71 |
+
"learning_rate": 9.723806571605703e-06,
|
| 72 |
+
"loss": 1.9636,
|
| 73 |
+
"step": 900
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.6196746707978311,
|
| 77 |
+
"grad_norm": 16.929576873779297,
|
| 78 |
+
"learning_rate": 9.692808431494111e-06,
|
| 79 |
+
"loss": 1.9787,
|
| 80 |
+
"step": 1000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.6816421378776143,
|
| 84 |
+
"grad_norm": 4.100649833679199,
|
| 85 |
+
"learning_rate": 9.661810291382517e-06,
|
| 86 |
+
"loss": 1.9076,
|
| 87 |
+
"step": 1100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.7436096049573974,
|
| 91 |
+
"grad_norm": 8.428403854370117,
|
| 92 |
+
"learning_rate": 9.630812151270923e-06,
|
| 93 |
+
"loss": 1.9312,
|
| 94 |
+
"step": 1200
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.8055770720371804,
|
| 98 |
+
"grad_norm": 21.134408950805664,
|
| 99 |
+
"learning_rate": 9.599814011159331e-06,
|
| 100 |
+
"loss": 1.9262,
|
| 101 |
+
"step": 1300
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.8675445391169636,
|
| 105 |
+
"grad_norm": 4.445871829986572,
|
| 106 |
+
"learning_rate": 9.568815871047737e-06,
|
| 107 |
+
"loss": 1.9038,
|
| 108 |
+
"step": 1400
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.9295120061967467,
|
| 112 |
+
"grad_norm": 10.70151424407959,
|
| 113 |
+
"learning_rate": 9.537817730936143e-06,
|
| 114 |
+
"loss": 1.909,
|
| 115 |
+
"step": 1500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.9914794732765299,
|
| 119 |
+
"grad_norm": 4.220454692840576,
|
| 120 |
+
"learning_rate": 9.506819590824551e-06,
|
| 121 |
+
"loss": 1.9011,
|
| 122 |
+
"step": 1600
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.9995352439969016,
|
| 126 |
+
"eval_loss": 1.478387713432312,
|
| 127 |
+
"eval_runtime": 71.2201,
|
| 128 |
+
"eval_samples_per_second": 45.31,
|
| 129 |
+
"eval_steps_per_second": 22.662,
|
| 130 |
+
"step": 1613
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.0539116963594113,
|
| 134 |
+
"grad_norm": 5.241837024688721,
|
| 135 |
+
"learning_rate": 9.475821450712957e-06,
|
| 136 |
+
"loss": 1.8493,
|
| 137 |
+
"step": 1700
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.1158791634391945,
|
| 141 |
+
"grad_norm": 8.490580558776855,
|
| 142 |
+
"learning_rate": 9.444823310601364e-06,
|
| 143 |
+
"loss": 1.8844,
|
| 144 |
+
"step": 1800
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.1778466305189776,
|
| 148 |
+
"grad_norm": 4.5867743492126465,
|
| 149 |
+
"learning_rate": 9.413825170489771e-06,
|
| 150 |
+
"loss": 1.8588,
|
| 151 |
+
"step": 1900
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.2398140975987606,
|
| 155 |
+
"grad_norm": 5.750781536102295,
|
| 156 |
+
"learning_rate": 9.382827030378178e-06,
|
| 157 |
+
"loss": 1.8462,
|
| 158 |
+
"step": 2000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.3017815646785438,
|
| 162 |
+
"grad_norm": 3.4414772987365723,
|
| 163 |
+
"learning_rate": 9.351828890266584e-06,
|
| 164 |
+
"loss": 1.8476,
|
| 165 |
+
"step": 2100
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.363749031758327,
|
| 169 |
+
"grad_norm": 3.991649627685547,
|
| 170 |
+
"learning_rate": 9.320830750154991e-06,
|
| 171 |
+
"loss": 1.8111,
|
| 172 |
+
"step": 2200
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.42571649883811,
|
| 176 |
+
"grad_norm": 3.774946689605713,
|
| 177 |
+
"learning_rate": 9.289832610043398e-06,
|
| 178 |
+
"loss": 1.8224,
|
| 179 |
+
"step": 2300
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.487683965917893,
|
| 183 |
+
"grad_norm": 11.512676239013672,
|
| 184 |
+
"learning_rate": 9.258834469931804e-06,
|
| 185 |
+
"loss": 1.8164,
|
| 186 |
+
"step": 2400
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.5496514329976763,
|
| 190 |
+
"grad_norm": 4.229243755340576,
|
| 191 |
+
"learning_rate": 9.227836329820212e-06,
|
| 192 |
+
"loss": 1.8052,
|
| 193 |
+
"step": 2500
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.6116189000774592,
|
| 197 |
+
"grad_norm": 3.6015431880950928,
|
| 198 |
+
"learning_rate": 9.196838189708618e-06,
|
| 199 |
+
"loss": 1.8253,
|
| 200 |
+
"step": 2600
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.6735863671572424,
|
| 204 |
+
"grad_norm": 3.8703105449676514,
|
| 205 |
+
"learning_rate": 9.165840049597024e-06,
|
| 206 |
+
"loss": 1.7702,
|
| 207 |
+
"step": 2700
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.7355538342370256,
|
| 211 |
+
"grad_norm": 3.6859114170074463,
|
| 212 |
+
"learning_rate": 9.134841909485432e-06,
|
| 213 |
+
"loss": 1.7925,
|
| 214 |
+
"step": 2800
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.7975213013168085,
|
| 218 |
+
"grad_norm": 6.744151592254639,
|
| 219 |
+
"learning_rate": 9.103843769373838e-06,
|
| 220 |
+
"loss": 1.7995,
|
| 221 |
+
"step": 2900
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.859488768396592,
|
| 225 |
+
"grad_norm": 5.791450500488281,
|
| 226 |
+
"learning_rate": 9.072845629262244e-06,
|
| 227 |
+
"loss": 1.7894,
|
| 228 |
+
"step": 3000
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.921456235476375,
|
| 232 |
+
"grad_norm": 5.028300762176514,
|
| 233 |
+
"learning_rate": 9.041847489150652e-06,
|
| 234 |
+
"loss": 1.7955,
|
| 235 |
+
"step": 3100
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 1.9834237025561579,
|
| 239 |
+
"grad_norm": 8.930970191955566,
|
| 240 |
+
"learning_rate": 9.010849349039058e-06,
|
| 241 |
+
"loss": 1.7856,
|
| 242 |
+
"step": 3200
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.9995352439969016,
|
| 246 |
+
"eval_loss": 1.438106894493103,
|
| 247 |
+
"eval_runtime": 71.4662,
|
| 248 |
+
"eval_samples_per_second": 45.154,
|
| 249 |
+
"eval_steps_per_second": 22.584,
|
| 250 |
+
"step": 3226
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 2.0458559256390396,
|
| 254 |
+
"grad_norm": 4.4157915115356445,
|
| 255 |
+
"learning_rate": 8.979851208927464e-06,
|
| 256 |
+
"loss": 1.7661,
|
| 257 |
+
"step": 3300
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 2.1078233927188226,
|
| 261 |
+
"grad_norm": 5.970052242279053,
|
| 262 |
+
"learning_rate": 8.948853068815872e-06,
|
| 263 |
+
"loss": 1.7539,
|
| 264 |
+
"step": 3400
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 2.1697908597986055,
|
| 268 |
+
"grad_norm": 6.610071659088135,
|
| 269 |
+
"learning_rate": 8.917854928704278e-06,
|
| 270 |
+
"loss": 1.7629,
|
| 271 |
+
"step": 3500
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 2.231758326878389,
|
| 275 |
+
"grad_norm": 5.124378204345703,
|
| 276 |
+
"learning_rate": 8.886856788592684e-06,
|
| 277 |
+
"loss": 1.7512,
|
| 278 |
+
"step": 3600
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.293725793958172,
|
| 282 |
+
"grad_norm": 3.7913496494293213,
|
| 283 |
+
"learning_rate": 8.855858648481092e-06,
|
| 284 |
+
"loss": 1.7574,
|
| 285 |
+
"step": 3700
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.3556932610379553,
|
| 289 |
+
"grad_norm": 3.5346639156341553,
|
| 290 |
+
"learning_rate": 8.824860508369498e-06,
|
| 291 |
+
"loss": 1.7298,
|
| 292 |
+
"step": 3800
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 2.4176607281177382,
|
| 296 |
+
"grad_norm": 3.6782634258270264,
|
| 297 |
+
"learning_rate": 8.793862368257904e-06,
|
| 298 |
+
"loss": 1.756,
|
| 299 |
+
"step": 3900
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 2.479628195197521,
|
| 303 |
+
"grad_norm": 3.087649345397949,
|
| 304 |
+
"learning_rate": 8.762864228146312e-06,
|
| 305 |
+
"loss": 1.7557,
|
| 306 |
+
"step": 4000
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 2.541595662277304,
|
| 310 |
+
"grad_norm": 3.854729413986206,
|
| 311 |
+
"learning_rate": 8.731866088034718e-06,
|
| 312 |
+
"loss": 1.7425,
|
| 313 |
+
"step": 4100
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 2.6035631293570876,
|
| 317 |
+
"grad_norm": 3.7198565006256104,
|
| 318 |
+
"learning_rate": 8.700867947923124e-06,
|
| 319 |
+
"loss": 1.7379,
|
| 320 |
+
"step": 4200
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.6655305964368705,
|
| 324 |
+
"grad_norm": 4.5739593505859375,
|
| 325 |
+
"learning_rate": 8.669869807811532e-06,
|
| 326 |
+
"loss": 1.7379,
|
| 327 |
+
"step": 4300
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 2.727498063516654,
|
| 331 |
+
"grad_norm": 4.533520698547363,
|
| 332 |
+
"learning_rate": 8.638871667699938e-06,
|
| 333 |
+
"loss": 1.7475,
|
| 334 |
+
"step": 4400
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 2.789465530596437,
|
| 338 |
+
"grad_norm": 3.113757610321045,
|
| 339 |
+
"learning_rate": 8.607873527588344e-06,
|
| 340 |
+
"loss": 1.7243,
|
| 341 |
+
"step": 4500
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 2.85143299767622,
|
| 345 |
+
"grad_norm": 3.061246871948242,
|
| 346 |
+
"learning_rate": 8.576875387476752e-06,
|
| 347 |
+
"loss": 1.7114,
|
| 348 |
+
"step": 4600
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 2.9134004647560032,
|
| 352 |
+
"grad_norm": 9.025867462158203,
|
| 353 |
+
"learning_rate": 8.545877247365158e-06,
|
| 354 |
+
"loss": 1.7184,
|
| 355 |
+
"step": 4700
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 2.975367931835786,
|
| 359 |
+
"grad_norm": 18.252887725830078,
|
| 360 |
+
"learning_rate": 8.514879107253565e-06,
|
| 361 |
+
"loss": 1.7165,
|
| 362 |
+
"step": 4800
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 2.9995352439969016,
|
| 366 |
+
"eval_loss": 1.4203578233718872,
|
| 367 |
+
"eval_runtime": 71.3513,
|
| 368 |
+
"eval_samples_per_second": 45.227,
|
| 369 |
+
"eval_steps_per_second": 22.62,
|
| 370 |
+
"step": 4839
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 3.0378001549186675,
|
| 374 |
+
"grad_norm": 3.237386703491211,
|
| 375 |
+
"learning_rate": 8.483880967141972e-06,
|
| 376 |
+
"loss": 1.7036,
|
| 377 |
+
"step": 4900
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 3.099767621998451,
|
| 381 |
+
"grad_norm": 3.4343390464782715,
|
| 382 |
+
"learning_rate": 8.452882827030378e-06,
|
| 383 |
+
"loss": 1.6937,
|
| 384 |
+
"step": 5000
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 3.161735089078234,
|
| 388 |
+
"grad_norm": 4.684260845184326,
|
| 389 |
+
"learning_rate": 8.421884686918785e-06,
|
| 390 |
+
"loss": 1.6825,
|
| 391 |
+
"step": 5100
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 3.223702556158017,
|
| 395 |
+
"grad_norm": 4.4700236320495605,
|
| 396 |
+
"learning_rate": 8.390886546807192e-06,
|
| 397 |
+
"loss": 1.7013,
|
| 398 |
+
"step": 5200
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 3.2856700232378,
|
| 402 |
+
"grad_norm": 3.5046918392181396,
|
| 403 |
+
"learning_rate": 8.359888406695599e-06,
|
| 404 |
+
"loss": 1.6819,
|
| 405 |
+
"step": 5300
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 3.347637490317583,
|
| 409 |
+
"grad_norm": 3.9169533252716064,
|
| 410 |
+
"learning_rate": 8.328890266584005e-06,
|
| 411 |
+
"loss": 1.6939,
|
| 412 |
+
"step": 5400
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 3.4096049573973666,
|
| 416 |
+
"grad_norm": 3.2398970127105713,
|
| 417 |
+
"learning_rate": 8.297892126472413e-06,
|
| 418 |
+
"loss": 1.689,
|
| 419 |
+
"step": 5500
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 3.4715724244771495,
|
| 423 |
+
"grad_norm": 5.543476104736328,
|
| 424 |
+
"learning_rate": 8.266893986360819e-06,
|
| 425 |
+
"loss": 1.6819,
|
| 426 |
+
"step": 5600
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 3.5335398915569325,
|
| 430 |
+
"grad_norm": 3.900956153869629,
|
| 431 |
+
"learning_rate": 8.235895846249225e-06,
|
| 432 |
+
"loss": 1.7153,
|
| 433 |
+
"step": 5700
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 3.595507358636716,
|
| 437 |
+
"grad_norm": 3.7085001468658447,
|
| 438 |
+
"learning_rate": 8.204897706137633e-06,
|
| 439 |
+
"loss": 1.6663,
|
| 440 |
+
"step": 5800
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 3.657474825716499,
|
| 444 |
+
"grad_norm": 3.672489881515503,
|
| 445 |
+
"learning_rate": 8.173899566026039e-06,
|
| 446 |
+
"loss": 1.6961,
|
| 447 |
+
"step": 5900
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 3.719442292796282,
|
| 451 |
+
"grad_norm": 5.308550834655762,
|
| 452 |
+
"learning_rate": 8.142901425914445e-06,
|
| 453 |
+
"loss": 1.6702,
|
| 454 |
+
"step": 6000
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 3.781409759876065,
|
| 458 |
+
"grad_norm": 6.25948429107666,
|
| 459 |
+
"learning_rate": 8.111903285802853e-06,
|
| 460 |
+
"loss": 1.7,
|
| 461 |
+
"step": 6100
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 3.843377226955848,
|
| 465 |
+
"grad_norm": 4.889005661010742,
|
| 466 |
+
"learning_rate": 8.080905145691259e-06,
|
| 467 |
+
"loss": 1.6783,
|
| 468 |
+
"step": 6200
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 3.905344694035631,
|
| 472 |
+
"grad_norm": 3.8252604007720947,
|
| 473 |
+
"learning_rate": 8.049907005579665e-06,
|
| 474 |
+
"loss": 1.6679,
|
| 475 |
+
"step": 6300
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 3.9673121611154145,
|
| 479 |
+
"grad_norm": 5.56712532043457,
|
| 480 |
+
"learning_rate": 8.018908865468073e-06,
|
| 481 |
+
"loss": 1.6778,
|
| 482 |
+
"step": 6400
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 3.9995352439969016,
|
| 486 |
+
"eval_loss": 1.4068138599395752,
|
| 487 |
+
"eval_runtime": 71.8216,
|
| 488 |
+
"eval_samples_per_second": 44.931,
|
| 489 |
+
"eval_steps_per_second": 22.472,
|
| 490 |
+
"step": 6452
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 4.029744384198296,
|
| 494 |
+
"grad_norm": 4.865719318389893,
|
| 495 |
+
"learning_rate": 7.987910725356479e-06,
|
| 496 |
+
"loss": 1.6718,
|
| 497 |
+
"step": 6500
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 4.091711851278079,
|
| 501 |
+
"grad_norm": 3.5504400730133057,
|
| 502 |
+
"learning_rate": 7.956912585244885e-06,
|
| 503 |
+
"loss": 1.6252,
|
| 504 |
+
"step": 6600
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 4.153679318357862,
|
| 508 |
+
"grad_norm": 2.8009276390075684,
|
| 509 |
+
"learning_rate": 7.925914445133293e-06,
|
| 510 |
+
"loss": 1.6529,
|
| 511 |
+
"step": 6700
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 4.215646785437645,
|
| 515 |
+
"grad_norm": 3.3487560749053955,
|
| 516 |
+
"learning_rate": 7.894916305021699e-06,
|
| 517 |
+
"loss": 1.6402,
|
| 518 |
+
"step": 6800
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 4.277614252517428,
|
| 522 |
+
"grad_norm": 3.037754535675049,
|
| 523 |
+
"learning_rate": 7.863918164910105e-06,
|
| 524 |
+
"loss": 1.6659,
|
| 525 |
+
"step": 6900
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 4.339581719597211,
|
| 529 |
+
"grad_norm": 3.340179204940796,
|
| 530 |
+
"learning_rate": 7.832920024798513e-06,
|
| 531 |
+
"loss": 1.646,
|
| 532 |
+
"step": 7000
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 4.401549186676995,
|
| 536 |
+
"grad_norm": 4.411381244659424,
|
| 537 |
+
"learning_rate": 7.801921884686919e-06,
|
| 538 |
+
"loss": 1.6583,
|
| 539 |
+
"step": 7100
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 4.463516653756778,
|
| 543 |
+
"grad_norm": 4.7763352394104,
|
| 544 |
+
"learning_rate": 7.770923744575325e-06,
|
| 545 |
+
"loss": 1.6524,
|
| 546 |
+
"step": 7200
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 4.525484120836561,
|
| 550 |
+
"grad_norm": 3.343606472015381,
|
| 551 |
+
"learning_rate": 7.739925604463733e-06,
|
| 552 |
+
"loss": 1.6454,
|
| 553 |
+
"step": 7300
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 4.587451587916344,
|
| 557 |
+
"grad_norm": 5.252141952514648,
|
| 558 |
+
"learning_rate": 7.70892746435214e-06,
|
| 559 |
+
"loss": 1.6555,
|
| 560 |
+
"step": 7400
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 4.649419054996127,
|
| 564 |
+
"grad_norm": 2.8249170780181885,
|
| 565 |
+
"learning_rate": 7.677929324240545e-06,
|
| 566 |
+
"loss": 1.6506,
|
| 567 |
+
"step": 7500
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 4.711386522075911,
|
| 571 |
+
"grad_norm": 6.525687217712402,
|
| 572 |
+
"learning_rate": 7.646931184128953e-06,
|
| 573 |
+
"loss": 1.6215,
|
| 574 |
+
"step": 7600
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 4.7733539891556935,
|
| 578 |
+
"grad_norm": 4.455771446228027,
|
| 579 |
+
"learning_rate": 7.615933044017359e-06,
|
| 580 |
+
"loss": 1.6465,
|
| 581 |
+
"step": 7700
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 4.8353214562354765,
|
| 585 |
+
"grad_norm": 2.8847739696502686,
|
| 586 |
+
"learning_rate": 7.584934903905766e-06,
|
| 587 |
+
"loss": 1.6411,
|
| 588 |
+
"step": 7800
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 4.8972889233152594,
|
| 592 |
+
"grad_norm": 2.8771958351135254,
|
| 593 |
+
"learning_rate": 7.553936763794173e-06,
|
| 594 |
+
"loss": 1.6353,
|
| 595 |
+
"step": 7900
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 4.959256390395042,
|
| 599 |
+
"grad_norm": 3.5082240104675293,
|
| 600 |
+
"learning_rate": 7.522938623682579e-06,
|
| 601 |
+
"loss": 1.6679,
|
| 602 |
+
"step": 8000
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 4.999535243996902,
|
| 606 |
+
"eval_loss": 1.3975656032562256,
|
| 607 |
+
"eval_runtime": 71.9374,
|
| 608 |
+
"eval_samples_per_second": 44.858,
|
| 609 |
+
"eval_steps_per_second": 22.436,
|
| 610 |
+
"step": 8065
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 5.021688613477924,
|
| 614 |
+
"grad_norm": 3.450159788131714,
|
| 615 |
+
"learning_rate": 7.491940483570986e-06,
|
| 616 |
+
"loss": 1.6245,
|
| 617 |
+
"step": 8100
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 5.083656080557708,
|
| 621 |
+
"grad_norm": 3.078734874725342,
|
| 622 |
+
"learning_rate": 7.460942343459393e-06,
|
| 623 |
+
"loss": 1.5949,
|
| 624 |
+
"step": 8200
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 5.1456235476374905,
|
| 628 |
+
"grad_norm": 3.123811721801758,
|
| 629 |
+
"learning_rate": 7.4299442033477995e-06,
|
| 630 |
+
"loss": 1.5804,
|
| 631 |
+
"step": 8300
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 5.2075910147172735,
|
| 635 |
+
"grad_norm": 2.746354341506958,
|
| 636 |
+
"learning_rate": 7.3989460632362065e-06,
|
| 637 |
+
"loss": 1.6264,
|
| 638 |
+
"step": 8400
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 5.269558481797056,
|
| 642 |
+
"grad_norm": 3.969360113143921,
|
| 643 |
+
"learning_rate": 7.3679479231246135e-06,
|
| 644 |
+
"loss": 1.6285,
|
| 645 |
+
"step": 8500
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 5.331525948876839,
|
| 649 |
+
"grad_norm": 11.645624160766602,
|
| 650 |
+
"learning_rate": 7.33694978301302e-06,
|
| 651 |
+
"loss": 1.6196,
|
| 652 |
+
"step": 8600
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 5.393493415956623,
|
| 656 |
+
"grad_norm": 4.237279415130615,
|
| 657 |
+
"learning_rate": 7.305951642901427e-06,
|
| 658 |
+
"loss": 1.6271,
|
| 659 |
+
"step": 8700
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 5.455460883036406,
|
| 663 |
+
"grad_norm": 5.038291931152344,
|
| 664 |
+
"learning_rate": 7.2749535027898336e-06,
|
| 665 |
+
"loss": 1.6097,
|
| 666 |
+
"step": 8800
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 5.517428350116189,
|
| 670 |
+
"grad_norm": 6.474031448364258,
|
| 671 |
+
"learning_rate": 7.24395536267824e-06,
|
| 672 |
+
"loss": 1.6148,
|
| 673 |
+
"step": 8900
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 5.579395817195972,
|
| 677 |
+
"grad_norm": 3.735469341278076,
|
| 678 |
+
"learning_rate": 7.212957222566647e-06,
|
| 679 |
+
"loss": 1.608,
|
| 680 |
+
"step": 9000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 5.641363284275755,
|
| 684 |
+
"grad_norm": 4.774326801300049,
|
| 685 |
+
"learning_rate": 7.181959082455054e-06,
|
| 686 |
+
"loss": 1.6362,
|
| 687 |
+
"step": 9100
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 5.703330751355538,
|
| 691 |
+
"grad_norm": 6.094056606292725,
|
| 692 |
+
"learning_rate": 7.15096094234346e-06,
|
| 693 |
+
"loss": 1.5946,
|
| 694 |
+
"step": 9200
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 5.765298218435321,
|
| 698 |
+
"grad_norm": 2.613210439682007,
|
| 699 |
+
"learning_rate": 7.119962802231867e-06,
|
| 700 |
+
"loss": 1.6237,
|
| 701 |
+
"step": 9300
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 5.827265685515105,
|
| 705 |
+
"grad_norm": 5.291254043579102,
|
| 706 |
+
"learning_rate": 7.088964662120274e-06,
|
| 707 |
+
"loss": 1.6225,
|
| 708 |
+
"step": 9400
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 5.889233152594888,
|
| 712 |
+
"grad_norm": 3.139016628265381,
|
| 713 |
+
"learning_rate": 7.05796652200868e-06,
|
| 714 |
+
"loss": 1.6229,
|
| 715 |
+
"step": 9500
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 5.951200619674671,
|
| 719 |
+
"grad_norm": 2.9346985816955566,
|
| 720 |
+
"learning_rate": 7.026968381897087e-06,
|
| 721 |
+
"loss": 1.6091,
|
| 722 |
+
"step": 9600
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 5.999535243996902,
|
| 726 |
+
"eval_loss": 1.3893319368362427,
|
| 727 |
+
"eval_runtime": 71.9002,
|
| 728 |
+
"eval_samples_per_second": 44.882,
|
| 729 |
+
"eval_steps_per_second": 22.448,
|
| 730 |
+
"step": 9678
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 6.013632842757552,
|
| 734 |
+
"grad_norm": 2.6308019161224365,
|
| 735 |
+
"learning_rate": 6.995970241785494e-06,
|
| 736 |
+
"loss": 1.6145,
|
| 737 |
+
"step": 9700
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 6.075600309837335,
|
| 741 |
+
"grad_norm": 6.885835647583008,
|
| 742 |
+
"learning_rate": 6.9649721016739e-06,
|
| 743 |
+
"loss": 1.575,
|
| 744 |
+
"step": 9800
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 6.137567776917119,
|
| 748 |
+
"grad_norm": 8.84401798248291,
|
| 749 |
+
"learning_rate": 6.933973961562307e-06,
|
| 750 |
+
"loss": 1.5861,
|
| 751 |
+
"step": 9900
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 6.199535243996902,
|
| 755 |
+
"grad_norm": 3.830970287322998,
|
| 756 |
+
"learning_rate": 6.902975821450714e-06,
|
| 757 |
+
"loss": 1.6048,
|
| 758 |
+
"step": 10000
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 6.261502711076685,
|
| 762 |
+
"grad_norm": 2.8187596797943115,
|
| 763 |
+
"learning_rate": 6.87197768133912e-06,
|
| 764 |
+
"loss": 1.5923,
|
| 765 |
+
"step": 10100
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 6.323470178156468,
|
| 769 |
+
"grad_norm": 3.0165576934814453,
|
| 770 |
+
"learning_rate": 6.840979541227527e-06,
|
| 771 |
+
"loss": 1.5773,
|
| 772 |
+
"step": 10200
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 6.385437645236251,
|
| 776 |
+
"grad_norm": 8.133129119873047,
|
| 777 |
+
"learning_rate": 6.809981401115934e-06,
|
| 778 |
+
"loss": 1.576,
|
| 779 |
+
"step": 10300
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 6.447405112316034,
|
| 783 |
+
"grad_norm": 3.153198480606079,
|
| 784 |
+
"learning_rate": 6.77898326100434e-06,
|
| 785 |
+
"loss": 1.5922,
|
| 786 |
+
"step": 10400
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 6.5093725793958175,
|
| 790 |
+
"grad_norm": 3.5953714847564697,
|
| 791 |
+
"learning_rate": 6.7482951022938625e-06,
|
| 792 |
+
"loss": 1.5954,
|
| 793 |
+
"step": 10500
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 6.5713400464756,
|
| 797 |
+
"grad_norm": 3.0549609661102295,
|
| 798 |
+
"learning_rate": 6.7172969621822695e-06,
|
| 799 |
+
"loss": 1.5751,
|
| 800 |
+
"step": 10600
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 6.633307513555383,
|
| 804 |
+
"grad_norm": 3.2885892391204834,
|
| 805 |
+
"learning_rate": 6.686298822070676e-06,
|
| 806 |
+
"loss": 1.6103,
|
| 807 |
+
"step": 10700
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 6.695274980635166,
|
| 811 |
+
"grad_norm": 3.2449259757995605,
|
| 812 |
+
"learning_rate": 6.6553006819590826e-06,
|
| 813 |
+
"loss": 1.5879,
|
| 814 |
+
"step": 10800
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 6.757242447714949,
|
| 818 |
+
"grad_norm": 3.855558395385742,
|
| 819 |
+
"learning_rate": 6.6243025418474895e-06,
|
| 820 |
+
"loss": 1.5863,
|
| 821 |
+
"step": 10900
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 6.819209914794733,
|
| 825 |
+
"grad_norm": 7.185797214508057,
|
| 826 |
+
"learning_rate": 6.593304401735896e-06,
|
| 827 |
+
"loss": 1.5594,
|
| 828 |
+
"step": 11000
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 6.881177381874516,
|
| 832 |
+
"grad_norm": 5.2492804527282715,
|
| 833 |
+
"learning_rate": 6.562306261624303e-06,
|
| 834 |
+
"loss": 1.5716,
|
| 835 |
+
"step": 11100
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 6.943144848954299,
|
| 839 |
+
"grad_norm": 3.938108444213867,
|
| 840 |
+
"learning_rate": 6.53130812151271e-06,
|
| 841 |
+
"loss": 1.6033,
|
| 842 |
+
"step": 11200
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 6.999535243996902,
|
| 846 |
+
"eval_loss": 1.3868727684020996,
|
| 847 |
+
"eval_runtime": 71.7471,
|
| 848 |
+
"eval_samples_per_second": 44.977,
|
| 849 |
+
"eval_steps_per_second": 22.496,
|
| 850 |
+
"step": 11291
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 7.00557707203718,
|
| 854 |
+
"grad_norm": 3.1100411415100098,
|
| 855 |
+
"learning_rate": 6.500309981401116e-06,
|
| 856 |
+
"loss": 1.5961,
|
| 857 |
+
"step": 11300
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 7.067544539116963,
|
| 861 |
+
"grad_norm": 4.577524185180664,
|
| 862 |
+
"learning_rate": 6.469311841289523e-06,
|
| 863 |
+
"loss": 1.5562,
|
| 864 |
+
"step": 11400
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 7.129512006196746,
|
| 868 |
+
"grad_norm": 3.86492919921875,
|
| 869 |
+
"learning_rate": 6.43831370117793e-06,
|
| 870 |
+
"loss": 1.5757,
|
| 871 |
+
"step": 11500
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 7.19147947327653,
|
| 875 |
+
"grad_norm": 6.450658321380615,
|
| 876 |
+
"learning_rate": 6.407315561066336e-06,
|
| 877 |
+
"loss": 1.5467,
|
| 878 |
+
"step": 11600
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 7.253446940356313,
|
| 882 |
+
"grad_norm": 3.469329357147217,
|
| 883 |
+
"learning_rate": 6.376317420954743e-06,
|
| 884 |
+
"loss": 1.5676,
|
| 885 |
+
"step": 11700
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 7.315414407436096,
|
| 889 |
+
"grad_norm": 3.4291296005249023,
|
| 890 |
+
"learning_rate": 6.34531928084315e-06,
|
| 891 |
+
"loss": 1.5693,
|
| 892 |
+
"step": 11800
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 7.377381874515879,
|
| 896 |
+
"grad_norm": 2.776810884475708,
|
| 897 |
+
"learning_rate": 6.314321140731556e-06,
|
| 898 |
+
"loss": 1.5761,
|
| 899 |
+
"step": 11900
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 7.439349341595662,
|
| 903 |
+
"grad_norm": 3.687276840209961,
|
| 904 |
+
"learning_rate": 6.283323000619963e-06,
|
| 905 |
+
"loss": 1.5582,
|
| 906 |
+
"step": 12000
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 7.501316808675446,
|
| 910 |
+
"grad_norm": 3.623704195022583,
|
| 911 |
+
"learning_rate": 6.25232486050837e-06,
|
| 912 |
+
"loss": 1.557,
|
| 913 |
+
"step": 12100
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 7.563284275755229,
|
| 917 |
+
"grad_norm": 2.607255220413208,
|
| 918 |
+
"learning_rate": 6.221326720396776e-06,
|
| 919 |
+
"loss": 1.5467,
|
| 920 |
+
"step": 12200
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 7.625251742835012,
|
| 924 |
+
"grad_norm": 4.738313674926758,
|
| 925 |
+
"learning_rate": 6.190328580285183e-06,
|
| 926 |
+
"loss": 1.5648,
|
| 927 |
+
"step": 12300
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 7.687219209914795,
|
| 931 |
+
"grad_norm": 3.4459781646728516,
|
| 932 |
+
"learning_rate": 6.15933044017359e-06,
|
| 933 |
+
"loss": 1.57,
|
| 934 |
+
"step": 12400
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 7.749186676994578,
|
| 938 |
+
"grad_norm": 2.6644325256347656,
|
| 939 |
+
"learning_rate": 6.128332300061996e-06,
|
| 940 |
+
"loss": 1.5757,
|
| 941 |
+
"step": 12500
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 7.811154144074361,
|
| 945 |
+
"grad_norm": 6.151153564453125,
|
| 946 |
+
"learning_rate": 6.097334159950403e-06,
|
| 947 |
+
"loss": 1.5653,
|
| 948 |
+
"step": 12600
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 7.873121611154144,
|
| 952 |
+
"grad_norm": 4.14183235168457,
|
| 953 |
+
"learning_rate": 6.06633601983881e-06,
|
| 954 |
+
"loss": 1.5708,
|
| 955 |
+
"step": 12700
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 7.935089078233927,
|
| 959 |
+
"grad_norm": 11.848958015441895,
|
| 960 |
+
"learning_rate": 6.035337879727216e-06,
|
| 961 |
+
"loss": 1.5633,
|
| 962 |
+
"step": 12800
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 7.99705654531371,
|
| 966 |
+
"grad_norm": 3.1628572940826416,
|
| 967 |
+
"learning_rate": 6.004339739615623e-06,
|
| 968 |
+
"loss": 1.548,
|
| 969 |
+
"step": 12900
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 7.999535243996902,
|
| 973 |
+
"eval_loss": 1.3799071311950684,
|
| 974 |
+
"eval_runtime": 71.5231,
|
| 975 |
+
"eval_samples_per_second": 45.118,
|
| 976 |
+
"eval_steps_per_second": 22.566,
|
| 977 |
+
"step": 12904
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 8.059488768396593,
|
| 981 |
+
"grad_norm": 2.565005302429199,
|
| 982 |
+
"learning_rate": 5.97334159950403e-06,
|
| 983 |
+
"loss": 1.5559,
|
| 984 |
+
"step": 13000
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 8.121456235476375,
|
| 988 |
+
"grad_norm": 3.772648334503174,
|
| 989 |
+
"learning_rate": 5.942343459392436e-06,
|
| 990 |
+
"loss": 1.5516,
|
| 991 |
+
"step": 13100
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 8.183423702556158,
|
| 995 |
+
"grad_norm": 3.1010353565216064,
|
| 996 |
+
"learning_rate": 5.911345319280843e-06,
|
| 997 |
+
"loss": 1.5494,
|
| 998 |
+
"step": 13200
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 8.24539116963594,
|
| 1002 |
+
"grad_norm": 4.525482177734375,
|
| 1003 |
+
"learning_rate": 5.88034717916925e-06,
|
| 1004 |
+
"loss": 1.5391,
|
| 1005 |
+
"step": 13300
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 8.307358636715724,
|
| 1009 |
+
"grad_norm": 4.108111381530762,
|
| 1010 |
+
"learning_rate": 5.8493490390576564e-06,
|
| 1011 |
+
"loss": 1.5798,
|
| 1012 |
+
"step": 13400
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 8.369326103795508,
|
| 1016 |
+
"grad_norm": 3.5569262504577637,
|
| 1017 |
+
"learning_rate": 5.818350898946063e-06,
|
| 1018 |
+
"loss": 1.5332,
|
| 1019 |
+
"step": 13500
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 8.43129357087529,
|
| 1023 |
+
"grad_norm": 2.829259157180786,
|
| 1024 |
+
"learning_rate": 5.78735275883447e-06,
|
| 1025 |
+
"loss": 1.5564,
|
| 1026 |
+
"step": 13600
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 8.493261037955074,
|
| 1030 |
+
"grad_norm": 9.748035430908203,
|
| 1031 |
+
"learning_rate": 5.7563546187228765e-06,
|
| 1032 |
+
"loss": 1.5082,
|
| 1033 |
+
"step": 13700
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 8.555228505034856,
|
| 1037 |
+
"grad_norm": 5.017675399780273,
|
| 1038 |
+
"learning_rate": 5.7253564786112835e-06,
|
| 1039 |
+
"loss": 1.5086,
|
| 1040 |
+
"step": 13800
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 8.61719597211464,
|
| 1044 |
+
"grad_norm": 3.3384227752685547,
|
| 1045 |
+
"learning_rate": 5.6943583384996905e-06,
|
| 1046 |
+
"loss": 1.5682,
|
| 1047 |
+
"step": 13900
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 8.679163439194422,
|
| 1051 |
+
"grad_norm": 3.0591983795166016,
|
| 1052 |
+
"learning_rate": 5.663670179789214e-06,
|
| 1053 |
+
"loss": 1.5359,
|
| 1054 |
+
"step": 14000
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 8.741130906274206,
|
| 1058 |
+
"grad_norm": 3.4246435165405273,
|
| 1059 |
+
"learning_rate": 5.632672039677621e-06,
|
| 1060 |
+
"loss": 1.5611,
|
| 1061 |
+
"step": 14100
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 8.80309837335399,
|
| 1065 |
+
"grad_norm": 3.443187713623047,
|
| 1066 |
+
"learning_rate": 5.601673899566027e-06,
|
| 1067 |
+
"loss": 1.5592,
|
| 1068 |
+
"step": 14200
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 8.865065840433772,
|
| 1072 |
+
"grad_norm": 2.6613450050354004,
|
| 1073 |
+
"learning_rate": 5.570675759454434e-06,
|
| 1074 |
+
"loss": 1.5484,
|
| 1075 |
+
"step": 14300
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 8.927033307513556,
|
| 1079 |
+
"grad_norm": 3.1063573360443115,
|
| 1080 |
+
"learning_rate": 5.539677619342841e-06,
|
| 1081 |
+
"loss": 1.5146,
|
| 1082 |
+
"step": 14400
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 8.989000774593338,
|
| 1086 |
+
"grad_norm": 3.6589224338531494,
|
| 1087 |
+
"learning_rate": 5.508679479231247e-06,
|
| 1088 |
+
"loss": 1.5641,
|
| 1089 |
+
"step": 14500
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 8.999535243996903,
|
| 1093 |
+
"eval_loss": 1.3773841857910156,
|
| 1094 |
+
"eval_runtime": 71.387,
|
| 1095 |
+
"eval_samples_per_second": 45.204,
|
| 1096 |
+
"eval_steps_per_second": 22.609,
|
| 1097 |
+
"step": 14517
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 9.05143299767622,
|
| 1101 |
+
"grad_norm": 3.909100294113159,
|
| 1102 |
+
"learning_rate": 5.477681339119654e-06,
|
| 1103 |
+
"loss": 1.5137,
|
| 1104 |
+
"step": 14600
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 9.113400464756003,
|
| 1108 |
+
"grad_norm": 2.70833683013916,
|
| 1109 |
+
"learning_rate": 5.446683199008061e-06,
|
| 1110 |
+
"loss": 1.519,
|
| 1111 |
+
"step": 14700
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 9.175367931835787,
|
| 1115 |
+
"grad_norm": 2.6168839931488037,
|
| 1116 |
+
"learning_rate": 5.415685058896467e-06,
|
| 1117 |
+
"loss": 1.5082,
|
| 1118 |
+
"step": 14800
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 9.237335398915569,
|
| 1122 |
+
"grad_norm": 2.4784512519836426,
|
| 1123 |
+
"learning_rate": 5.384686918784874e-06,
|
| 1124 |
+
"loss": 1.5098,
|
| 1125 |
+
"step": 14900
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 9.299302865995353,
|
| 1129 |
+
"grad_norm": 2.7963085174560547,
|
| 1130 |
+
"learning_rate": 5.353688778673281e-06,
|
| 1131 |
+
"loss": 1.5257,
|
| 1132 |
+
"step": 15000
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 9.361270333075135,
|
| 1136 |
+
"grad_norm": 2.6264543533325195,
|
| 1137 |
+
"learning_rate": 5.322690638561687e-06,
|
| 1138 |
+
"loss": 1.5122,
|
| 1139 |
+
"step": 15100
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 9.423237800154919,
|
| 1143 |
+
"grad_norm": 2.796173095703125,
|
| 1144 |
+
"learning_rate": 5.291692498450094e-06,
|
| 1145 |
+
"loss": 1.5629,
|
| 1146 |
+
"step": 15200
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 9.485205267234702,
|
| 1150 |
+
"grad_norm": 2.661559820175171,
|
| 1151 |
+
"learning_rate": 5.260694358338501e-06,
|
| 1152 |
+
"loss": 1.5337,
|
| 1153 |
+
"step": 15300
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 9.547172734314485,
|
| 1157 |
+
"grad_norm": 2.721785068511963,
|
| 1158 |
+
"learning_rate": 5.229696218226907e-06,
|
| 1159 |
+
"loss": 1.5443,
|
| 1160 |
+
"step": 15400
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 9.609140201394268,
|
| 1164 |
+
"grad_norm": 3.5480453968048096,
|
| 1165 |
+
"learning_rate": 5.198698078115314e-06,
|
| 1166 |
+
"loss": 1.5475,
|
| 1167 |
+
"step": 15500
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 9.67110766847405,
|
| 1171 |
+
"grad_norm": 4.556975841522217,
|
| 1172 |
+
"learning_rate": 5.167699938003721e-06,
|
| 1173 |
+
"loss": 1.5032,
|
| 1174 |
+
"step": 15600
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 9.733075135553834,
|
| 1178 |
+
"grad_norm": 3.4796106815338135,
|
| 1179 |
+
"learning_rate": 5.136701797892127e-06,
|
| 1180 |
+
"loss": 1.5328,
|
| 1181 |
+
"step": 15700
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 9.795042602633618,
|
| 1185 |
+
"grad_norm": 2.3589675426483154,
|
| 1186 |
+
"learning_rate": 5.105703657780534e-06,
|
| 1187 |
+
"loss": 1.5333,
|
| 1188 |
+
"step": 15800
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 9.8570100697134,
|
| 1192 |
+
"grad_norm": 8.50188159942627,
|
| 1193 |
+
"learning_rate": 5.074705517668941e-06,
|
| 1194 |
+
"loss": 1.5401,
|
| 1195 |
+
"step": 15900
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 9.918977536793184,
|
| 1199 |
+
"grad_norm": 2.818558931350708,
|
| 1200 |
+
"learning_rate": 5.043707377557347e-06,
|
| 1201 |
+
"loss": 1.5305,
|
| 1202 |
+
"step": 16000
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 9.980945003872966,
|
| 1206 |
+
"grad_norm": 7.929882526397705,
|
| 1207 |
+
"learning_rate": 5.01301921884687e-06,
|
| 1208 |
+
"loss": 1.5037,
|
| 1209 |
+
"step": 16100
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 9.999535243996903,
|
| 1213 |
+
"eval_loss": 1.3749291896820068,
|
| 1214 |
+
"eval_runtime": 71.4165,
|
| 1215 |
+
"eval_samples_per_second": 45.186,
|
| 1216 |
+
"eval_steps_per_second": 22.6,
|
| 1217 |
+
"step": 16130
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 10.043377226955847,
|
| 1221 |
+
"grad_norm": 2.9387943744659424,
|
| 1222 |
+
"learning_rate": 4.982021078735277e-06,
|
| 1223 |
+
"loss": 1.5233,
|
| 1224 |
+
"step": 16200
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 10.105344694035631,
|
| 1228 |
+
"grad_norm": 3.994661331176758,
|
| 1229 |
+
"learning_rate": 4.951022938623683e-06,
|
| 1230 |
+
"loss": 1.4957,
|
| 1231 |
+
"step": 16300
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 10.167312161115415,
|
| 1235 |
+
"grad_norm": 5.1318840980529785,
|
| 1236 |
+
"learning_rate": 4.92002479851209e-06,
|
| 1237 |
+
"loss": 1.5198,
|
| 1238 |
+
"step": 16400
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 10.229279628195197,
|
| 1242 |
+
"grad_norm": 5.07450008392334,
|
| 1243 |
+
"learning_rate": 4.889026658400497e-06,
|
| 1244 |
+
"loss": 1.5168,
|
| 1245 |
+
"step": 16500
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 10.291247095274981,
|
| 1249 |
+
"grad_norm": 3.5865488052368164,
|
| 1250 |
+
"learning_rate": 4.858028518288903e-06,
|
| 1251 |
+
"loss": 1.5136,
|
| 1252 |
+
"step": 16600
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 10.353214562354763,
|
| 1256 |
+
"grad_norm": 3.8123815059661865,
|
| 1257 |
+
"learning_rate": 4.82703037817731e-06,
|
| 1258 |
+
"loss": 1.5095,
|
| 1259 |
+
"step": 16700
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 10.415182029434547,
|
| 1263 |
+
"grad_norm": 3.0475172996520996,
|
| 1264 |
+
"learning_rate": 4.796032238065717e-06,
|
| 1265 |
+
"loss": 1.5005,
|
| 1266 |
+
"step": 16800
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 10.47714949651433,
|
| 1270 |
+
"grad_norm": 3.0361108779907227,
|
| 1271 |
+
"learning_rate": 4.765034097954123e-06,
|
| 1272 |
+
"loss": 1.5169,
|
| 1273 |
+
"step": 16900
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 10.539116963594113,
|
| 1277 |
+
"grad_norm": 2.7775065898895264,
|
| 1278 |
+
"learning_rate": 4.73403595784253e-06,
|
| 1279 |
+
"loss": 1.5025,
|
| 1280 |
+
"step": 17000
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 10.601084430673897,
|
| 1284 |
+
"grad_norm": 4.8608598709106445,
|
| 1285 |
+
"learning_rate": 4.703037817730937e-06,
|
| 1286 |
+
"loss": 1.5216,
|
| 1287 |
+
"step": 17100
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 10.663051897753679,
|
| 1291 |
+
"grad_norm": 3.024165630340576,
|
| 1292 |
+
"learning_rate": 4.672039677619343e-06,
|
| 1293 |
+
"loss": 1.5107,
|
| 1294 |
+
"step": 17200
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 10.725019364833463,
|
| 1298 |
+
"grad_norm": 3.055216073989868,
|
| 1299 |
+
"learning_rate": 4.64104153750775e-06,
|
| 1300 |
+
"loss": 1.5083,
|
| 1301 |
+
"step": 17300
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 10.786986831913246,
|
| 1305 |
+
"grad_norm": 2.7835144996643066,
|
| 1306 |
+
"learning_rate": 4.610043397396157e-06,
|
| 1307 |
+
"loss": 1.501,
|
| 1308 |
+
"step": 17400
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 10.848954298993029,
|
| 1312 |
+
"grad_norm": 3.1248793601989746,
|
| 1313 |
+
"learning_rate": 4.579045257284563e-06,
|
| 1314 |
+
"loss": 1.519,
|
| 1315 |
+
"step": 17500
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 10.910921766072812,
|
| 1319 |
+
"grad_norm": 3.8737070560455322,
|
| 1320 |
+
"learning_rate": 4.54804711717297e-06,
|
| 1321 |
+
"loss": 1.5087,
|
| 1322 |
+
"step": 17600
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 10.972889233152594,
|
| 1326 |
+
"grad_norm": 2.474802017211914,
|
| 1327 |
+
"learning_rate": 4.517048977061377e-06,
|
| 1328 |
+
"loss": 1.4803,
|
| 1329 |
+
"step": 17700
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 10.999535243996903,
|
| 1333 |
+
"eval_loss": 1.3729863166809082,
|
| 1334 |
+
"eval_runtime": 71.8366,
|
| 1335 |
+
"eval_samples_per_second": 44.921,
|
| 1336 |
+
"eval_steps_per_second": 22.468,
|
| 1337 |
+
"step": 17743
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 11.035321456235476,
|
| 1341 |
+
"grad_norm": 2.705595016479492,
|
| 1342 |
+
"learning_rate": 4.486050836949783e-06,
|
| 1343 |
+
"loss": 1.5091,
|
| 1344 |
+
"step": 17800
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 11.09728892331526,
|
| 1348 |
+
"grad_norm": 2.9070913791656494,
|
| 1349 |
+
"learning_rate": 4.45505269683819e-06,
|
| 1350 |
+
"loss": 1.5065,
|
| 1351 |
+
"step": 17900
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 11.159256390395043,
|
| 1355 |
+
"grad_norm": 2.360722780227661,
|
| 1356 |
+
"learning_rate": 4.424054556726597e-06,
|
| 1357 |
+
"loss": 1.4999,
|
| 1358 |
+
"step": 18000
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 11.221223857474826,
|
| 1362 |
+
"grad_norm": 2.7821319103240967,
|
| 1363 |
+
"learning_rate": 4.393056416615003e-06,
|
| 1364 |
+
"loss": 1.4863,
|
| 1365 |
+
"step": 18100
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 11.28319132455461,
|
| 1369 |
+
"grad_norm": 3.3408045768737793,
|
| 1370 |
+
"learning_rate": 4.36205827650341e-06,
|
| 1371 |
+
"loss": 1.4846,
|
| 1372 |
+
"step": 18200
|
| 1373 |
+
},
|
| 1374 |
+
{
|
| 1375 |
+
"epoch": 11.345158791634391,
|
| 1376 |
+
"grad_norm": 2.658116579055786,
|
| 1377 |
+
"learning_rate": 4.331060136391817e-06,
|
| 1378 |
+
"loss": 1.4911,
|
| 1379 |
+
"step": 18300
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 11.407126258714175,
|
| 1383 |
+
"grad_norm": 7.110032081604004,
|
| 1384 |
+
"learning_rate": 4.300061996280223e-06,
|
| 1385 |
+
"loss": 1.5037,
|
| 1386 |
+
"step": 18400
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 11.469093725793957,
|
| 1390 |
+
"grad_norm": 3.009939193725586,
|
| 1391 |
+
"learning_rate": 4.26906385616863e-06,
|
| 1392 |
+
"loss": 1.481,
|
| 1393 |
+
"step": 18500
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"epoch": 11.531061192873741,
|
| 1397 |
+
"grad_norm": 3.2190310955047607,
|
| 1398 |
+
"learning_rate": 4.238065716057037e-06,
|
| 1399 |
+
"loss": 1.5163,
|
| 1400 |
+
"step": 18600
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 11.593028659953525,
|
| 1404 |
+
"grad_norm": 3.240391969680786,
|
| 1405 |
+
"learning_rate": 4.2070675759454435e-06,
|
| 1406 |
+
"loss": 1.4934,
|
| 1407 |
+
"step": 18700
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 11.654996127033307,
|
| 1411 |
+
"grad_norm": 2.4078099727630615,
|
| 1412 |
+
"learning_rate": 4.1760694358338505e-06,
|
| 1413 |
+
"loss": 1.5076,
|
| 1414 |
+
"step": 18800
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 11.716963594113091,
|
| 1418 |
+
"grad_norm": 2.757641077041626,
|
| 1419 |
+
"learning_rate": 4.1450712957222575e-06,
|
| 1420 |
+
"loss": 1.5011,
|
| 1421 |
+
"step": 18900
|
| 1422 |
+
},
|
| 1423 |
+
{
|
| 1424 |
+
"epoch": 11.778931061192873,
|
| 1425 |
+
"grad_norm": 3.859056234359741,
|
| 1426 |
+
"learning_rate": 4.11438313701178e-06,
|
| 1427 |
+
"loss": 1.5009,
|
| 1428 |
+
"step": 19000
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 11.840898528272657,
|
| 1432 |
+
"grad_norm": 2.826043128967285,
|
| 1433 |
+
"learning_rate": 4.083384996900187e-06,
|
| 1434 |
+
"loss": 1.5103,
|
| 1435 |
+
"step": 19100
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 11.90286599535244,
|
| 1439 |
+
"grad_norm": 3.0263473987579346,
|
| 1440 |
+
"learning_rate": 4.052386856788593e-06,
|
| 1441 |
+
"loss": 1.4945,
|
| 1442 |
+
"step": 19200
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 11.964833462432223,
|
| 1446 |
+
"grad_norm": 3.322974920272827,
|
| 1447 |
+
"learning_rate": 4.021388716677e-06,
|
| 1448 |
+
"loss": 1.4653,
|
| 1449 |
+
"step": 19300
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 11.999535243996903,
|
| 1453 |
+
"eval_loss": 1.3713266849517822,
|
| 1454 |
+
"eval_runtime": 71.4255,
|
| 1455 |
+
"eval_samples_per_second": 45.18,
|
| 1456 |
+
"eval_steps_per_second": 22.597,
|
| 1457 |
+
"step": 19356
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 12.027265685515104,
|
| 1461 |
+
"grad_norm": 3.6630640029907227,
|
| 1462 |
+
"learning_rate": 3.990390576565407e-06,
|
| 1463 |
+
"loss": 1.5061,
|
| 1464 |
+
"step": 19400
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 12.089233152594888,
|
| 1468 |
+
"grad_norm": 2.810619831085205,
|
| 1469 |
+
"learning_rate": 3.959392436453813e-06,
|
| 1470 |
+
"loss": 1.5,
|
| 1471 |
+
"step": 19500
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 12.15120061967467,
|
| 1475 |
+
"grad_norm": 2.4999682903289795,
|
| 1476 |
+
"learning_rate": 3.92839429634222e-06,
|
| 1477 |
+
"loss": 1.4863,
|
| 1478 |
+
"step": 19600
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 12.213168086754454,
|
| 1482 |
+
"grad_norm": 3.3250415325164795,
|
| 1483 |
+
"learning_rate": 3.897396156230627e-06,
|
| 1484 |
+
"loss": 1.4719,
|
| 1485 |
+
"step": 19700
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 12.275135553834238,
|
| 1489 |
+
"grad_norm": 3.2047810554504395,
|
| 1490 |
+
"learning_rate": 3.866398016119033e-06,
|
| 1491 |
+
"loss": 1.492,
|
| 1492 |
+
"step": 19800
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 12.33710302091402,
|
| 1496 |
+
"grad_norm": 2.8707590103149414,
|
| 1497 |
+
"learning_rate": 3.83539987600744e-06,
|
| 1498 |
+
"loss": 1.4772,
|
| 1499 |
+
"step": 19900
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 12.399070487993804,
|
| 1503 |
+
"grad_norm": 5.695312023162842,
|
| 1504 |
+
"learning_rate": 3.804401735895847e-06,
|
| 1505 |
+
"loss": 1.4785,
|
| 1506 |
+
"step": 20000
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 12.461037955073586,
|
| 1510 |
+
"grad_norm": 3.48818039894104,
|
| 1511 |
+
"learning_rate": 3.7734035957842536e-06,
|
| 1512 |
+
"loss": 1.4789,
|
| 1513 |
+
"step": 20100
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 12.52300542215337,
|
| 1517 |
+
"grad_norm": 2.8195247650146484,
|
| 1518 |
+
"learning_rate": 3.7424054556726597e-06,
|
| 1519 |
+
"loss": 1.4859,
|
| 1520 |
+
"step": 20200
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 12.584972889233153,
|
| 1524 |
+
"grad_norm": 3.1309738159179688,
|
| 1525 |
+
"learning_rate": 3.7114073155610663e-06,
|
| 1526 |
+
"loss": 1.4914,
|
| 1527 |
+
"step": 20300
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 12.646940356312935,
|
| 1531 |
+
"grad_norm": 2.7474892139434814,
|
| 1532 |
+
"learning_rate": 3.6804091754494733e-06,
|
| 1533 |
+
"loss": 1.4776,
|
| 1534 |
+
"step": 20400
|
| 1535 |
+
},
|
| 1536 |
+
{
|
| 1537 |
+
"epoch": 12.70890782339272,
|
| 1538 |
+
"grad_norm": 3.022172451019287,
|
| 1539 |
+
"learning_rate": 3.64941103533788e-06,
|
| 1540 |
+
"loss": 1.498,
|
| 1541 |
+
"step": 20500
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 12.770875290472501,
|
| 1545 |
+
"grad_norm": 2.747607946395874,
|
| 1546 |
+
"learning_rate": 3.6184128952262864e-06,
|
| 1547 |
+
"loss": 1.4901,
|
| 1548 |
+
"step": 20600
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 12.832842757552285,
|
| 1552 |
+
"grad_norm": 3.077296733856201,
|
| 1553 |
+
"learning_rate": 3.5874147551146933e-06,
|
| 1554 |
+
"loss": 1.4773,
|
| 1555 |
+
"step": 20700
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 12.894810224632067,
|
| 1559 |
+
"grad_norm": 4.3411078453063965,
|
| 1560 |
+
"learning_rate": 3.5564166150031e-06,
|
| 1561 |
+
"loss": 1.4909,
|
| 1562 |
+
"step": 20800
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 12.956777691711851,
|
| 1566 |
+
"grad_norm": 3.112104654312134,
|
| 1567 |
+
"learning_rate": 3.5254184748915065e-06,
|
| 1568 |
+
"loss": 1.5027,
|
| 1569 |
+
"step": 20900
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 12.999535243996903,
|
| 1573 |
+
"eval_loss": 1.3685630559921265,
|
| 1574 |
+
"eval_runtime": 70.8923,
|
| 1575 |
+
"eval_samples_per_second": 45.52,
|
| 1576 |
+
"eval_steps_per_second": 22.767,
|
| 1577 |
+
"step": 20969
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 13.019209914794732,
|
| 1581 |
+
"grad_norm": 2.8162424564361572,
|
| 1582 |
+
"learning_rate": 3.4944203347799134e-06,
|
| 1583 |
+
"loss": 1.4868,
|
| 1584 |
+
"step": 21000
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 13.081177381874516,
|
| 1588 |
+
"grad_norm": 2.862400770187378,
|
| 1589 |
+
"learning_rate": 3.4637321760694358e-06,
|
| 1590 |
+
"loss": 1.4565,
|
| 1591 |
+
"step": 21100
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 13.143144848954298,
|
| 1595 |
+
"grad_norm": 9.166791915893555,
|
| 1596 |
+
"learning_rate": 3.4327340359578427e-06,
|
| 1597 |
+
"loss": 1.4968,
|
| 1598 |
+
"step": 21200
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 13.205112316034082,
|
| 1602 |
+
"grad_norm": 2.9333505630493164,
|
| 1603 |
+
"learning_rate": 3.4017358958462493e-06,
|
| 1604 |
+
"loss": 1.4707,
|
| 1605 |
+
"step": 21300
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 13.267079783113866,
|
| 1609 |
+
"grad_norm": 3.7271652221679688,
|
| 1610 |
+
"learning_rate": 3.370737755734656e-06,
|
| 1611 |
+
"loss": 1.4769,
|
| 1612 |
+
"step": 21400
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 13.329047250193648,
|
| 1616 |
+
"grad_norm": 4.895938396453857,
|
| 1617 |
+
"learning_rate": 3.339739615623063e-06,
|
| 1618 |
+
"loss": 1.4825,
|
| 1619 |
+
"step": 21500
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 13.391014717273432,
|
| 1623 |
+
"grad_norm": 4.098718643188477,
|
| 1624 |
+
"learning_rate": 3.3087414755114694e-06,
|
| 1625 |
+
"loss": 1.4473,
|
| 1626 |
+
"step": 21600
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 13.452982184353214,
|
| 1630 |
+
"grad_norm": 2.393143892288208,
|
| 1631 |
+
"learning_rate": 3.277743335399876e-06,
|
| 1632 |
+
"loss": 1.4547,
|
| 1633 |
+
"step": 21700
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 13.514949651432998,
|
| 1637 |
+
"grad_norm": 2.8273305892944336,
|
| 1638 |
+
"learning_rate": 3.246745195288283e-06,
|
| 1639 |
+
"loss": 1.4937,
|
| 1640 |
+
"step": 21800
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 13.576917118512782,
|
| 1644 |
+
"grad_norm": 2.560944080352783,
|
| 1645 |
+
"learning_rate": 3.2157470551766895e-06,
|
| 1646 |
+
"loss": 1.4617,
|
| 1647 |
+
"step": 21900
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 13.638884585592564,
|
| 1651 |
+
"grad_norm": 2.7508301734924316,
|
| 1652 |
+
"learning_rate": 3.184748915065096e-06,
|
| 1653 |
+
"loss": 1.4681,
|
| 1654 |
+
"step": 22000
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 13.700852052672348,
|
| 1658 |
+
"grad_norm": 3.0896778106689453,
|
| 1659 |
+
"learning_rate": 3.153750774953503e-06,
|
| 1660 |
+
"loss": 1.4863,
|
| 1661 |
+
"step": 22100
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 13.76281951975213,
|
| 1665 |
+
"grad_norm": 3.0587971210479736,
|
| 1666 |
+
"learning_rate": 3.1227526348419096e-06,
|
| 1667 |
+
"loss": 1.4872,
|
| 1668 |
+
"step": 22200
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 13.824786986831914,
|
| 1672 |
+
"grad_norm": 5.594135284423828,
|
| 1673 |
+
"learning_rate": 3.091754494730316e-06,
|
| 1674 |
+
"loss": 1.4551,
|
| 1675 |
+
"step": 22300
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 13.886754453911696,
|
| 1679 |
+
"grad_norm": 4.74953031539917,
|
| 1680 |
+
"learning_rate": 3.060756354618723e-06,
|
| 1681 |
+
"loss": 1.458,
|
| 1682 |
+
"step": 22400
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 13.94872192099148,
|
| 1686 |
+
"grad_norm": 2.3097078800201416,
|
| 1687 |
+
"learning_rate": 3.0297582145071297e-06,
|
| 1688 |
+
"loss": 1.4707,
|
| 1689 |
+
"step": 22500
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 13.999535243996903,
|
| 1693 |
+
"eval_loss": 1.367042899131775,
|
| 1694 |
+
"eval_runtime": 71.4468,
|
| 1695 |
+
"eval_samples_per_second": 45.167,
|
| 1696 |
+
"eval_steps_per_second": 22.59,
|
| 1697 |
+
"step": 22582
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 14.01115414407436,
|
| 1701 |
+
"grad_norm": 2.73579478263855,
|
| 1702 |
+
"learning_rate": 2.9987600743955362e-06,
|
| 1703 |
+
"loss": 1.4815,
|
| 1704 |
+
"step": 22600
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 14.073121611154145,
|
| 1708 |
+
"grad_norm": 2.643583297729492,
|
| 1709 |
+
"learning_rate": 2.967761934283943e-06,
|
| 1710 |
+
"loss": 1.4623,
|
| 1711 |
+
"step": 22700
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 14.135089078233927,
|
| 1715 |
+
"grad_norm": 4.030912399291992,
|
| 1716 |
+
"learning_rate": 2.9367637941723498e-06,
|
| 1717 |
+
"loss": 1.4406,
|
| 1718 |
+
"step": 22800
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 14.19705654531371,
|
| 1722 |
+
"grad_norm": 3.95310378074646,
|
| 1723 |
+
"learning_rate": 2.9057656540607563e-06,
|
| 1724 |
+
"loss": 1.4533,
|
| 1725 |
+
"step": 22900
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 14.259024012393493,
|
| 1729 |
+
"grad_norm": 2.382369041442871,
|
| 1730 |
+
"learning_rate": 2.8747675139491633e-06,
|
| 1731 |
+
"loss": 1.4729,
|
| 1732 |
+
"step": 23000
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 14.320991479473276,
|
| 1736 |
+
"grad_norm": 3.3369767665863037,
|
| 1737 |
+
"learning_rate": 2.84376937383757e-06,
|
| 1738 |
+
"loss": 1.447,
|
| 1739 |
+
"step": 23100
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 14.38295894655306,
|
| 1743 |
+
"grad_norm": 3.532909393310547,
|
| 1744 |
+
"learning_rate": 2.8127712337259764e-06,
|
| 1745 |
+
"loss": 1.4646,
|
| 1746 |
+
"step": 23200
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 14.444926413632842,
|
| 1750 |
+
"grad_norm": 2.707247257232666,
|
| 1751 |
+
"learning_rate": 2.7817730936143834e-06,
|
| 1752 |
+
"loss": 1.4782,
|
| 1753 |
+
"step": 23300
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 14.506893880712626,
|
| 1757 |
+
"grad_norm": 2.511441707611084,
|
| 1758 |
+
"learning_rate": 2.75077495350279e-06,
|
| 1759 |
+
"loss": 1.4732,
|
| 1760 |
+
"step": 23400
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 14.568861347792408,
|
| 1764 |
+
"grad_norm": 6.0035576820373535,
|
| 1765 |
+
"learning_rate": 2.7197768133911965e-06,
|
| 1766 |
+
"loss": 1.4625,
|
| 1767 |
+
"step": 23500
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 14.630828814872192,
|
| 1771 |
+
"grad_norm": 3.396369695663452,
|
| 1772 |
+
"learning_rate": 2.6887786732796035e-06,
|
| 1773 |
+
"loss": 1.4794,
|
| 1774 |
+
"step": 23600
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 14.692796281951976,
|
| 1778 |
+
"grad_norm": 2.5729544162750244,
|
| 1779 |
+
"learning_rate": 2.65778053316801e-06,
|
| 1780 |
+
"loss": 1.4666,
|
| 1781 |
+
"step": 23700
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 14.754763749031758,
|
| 1785 |
+
"grad_norm": 2.8480477333068848,
|
| 1786 |
+
"learning_rate": 2.6270923744575328e-06,
|
| 1787 |
+
"loss": 1.4644,
|
| 1788 |
+
"step": 23800
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 14.816731216111542,
|
| 1792 |
+
"grad_norm": 2.4807331562042236,
|
| 1793 |
+
"learning_rate": 2.5960942343459393e-06,
|
| 1794 |
+
"loss": 1.4752,
|
| 1795 |
+
"step": 23900
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 14.878698683191324,
|
| 1799 |
+
"grad_norm": 2.850637435913086,
|
| 1800 |
+
"learning_rate": 2.5650960942343463e-06,
|
| 1801 |
+
"loss": 1.4769,
|
| 1802 |
+
"step": 24000
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 14.940666150271108,
|
| 1806 |
+
"grad_norm": 2.480095148086548,
|
| 1807 |
+
"learning_rate": 2.534097954122753e-06,
|
| 1808 |
+
"loss": 1.4791,
|
| 1809 |
+
"step": 24100
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 14.999535243996903,
|
| 1813 |
+
"eval_loss": 1.3670425415039062,
|
| 1814 |
+
"eval_runtime": 71.2802,
|
| 1815 |
+
"eval_samples_per_second": 45.272,
|
| 1816 |
+
"eval_steps_per_second": 22.643,
|
| 1817 |
+
"step": 24195
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 15.003098373353989,
|
| 1821 |
+
"grad_norm": 2.5988998413085938,
|
| 1822 |
+
"learning_rate": 2.5030998140111594e-06,
|
| 1823 |
+
"loss": 1.4693,
|
| 1824 |
+
"step": 24200
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 15.065065840433773,
|
| 1828 |
+
"grad_norm": 2.674956798553467,
|
| 1829 |
+
"learning_rate": 2.4721016738995664e-06,
|
| 1830 |
+
"loss": 1.4584,
|
| 1831 |
+
"step": 24300
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 15.127033307513555,
|
| 1835 |
+
"grad_norm": 20.858081817626953,
|
| 1836 |
+
"learning_rate": 2.441103533787973e-06,
|
| 1837 |
+
"loss": 1.4593,
|
| 1838 |
+
"step": 24400
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 15.189000774593339,
|
| 1842 |
+
"grad_norm": 2.9068284034729004,
|
| 1843 |
+
"learning_rate": 2.4101053936763795e-06,
|
| 1844 |
+
"loss": 1.437,
|
| 1845 |
+
"step": 24500
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 15.250968241673121,
|
| 1849 |
+
"grad_norm": 2.5827035903930664,
|
| 1850 |
+
"learning_rate": 2.3791072535647865e-06,
|
| 1851 |
+
"loss": 1.4371,
|
| 1852 |
+
"step": 24600
|
| 1853 |
+
},
|
| 1854 |
+
{
|
| 1855 |
+
"epoch": 15.312935708752905,
|
| 1856 |
+
"grad_norm": 2.852088451385498,
|
| 1857 |
+
"learning_rate": 2.348109113453193e-06,
|
| 1858 |
+
"loss": 1.4434,
|
| 1859 |
+
"step": 24700
|
| 1860 |
+
},
|
| 1861 |
+
{
|
| 1862 |
+
"epoch": 15.374903175832689,
|
| 1863 |
+
"grad_norm": 3.28821063041687,
|
| 1864 |
+
"learning_rate": 2.3171109733415996e-06,
|
| 1865 |
+
"loss": 1.4606,
|
| 1866 |
+
"step": 24800
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 15.43687064291247,
|
| 1870 |
+
"grad_norm": 3.762103319168091,
|
| 1871 |
+
"learning_rate": 2.2861128332300066e-06,
|
| 1872 |
+
"loss": 1.4584,
|
| 1873 |
+
"step": 24900
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"epoch": 15.498838109992255,
|
| 1877 |
+
"grad_norm": 2.845301866531372,
|
| 1878 |
+
"learning_rate": 2.255114693118413e-06,
|
| 1879 |
+
"loss": 1.4781,
|
| 1880 |
+
"step": 25000
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 15.560805577072037,
|
| 1884 |
+
"grad_norm": 3.243618965148926,
|
| 1885 |
+
"learning_rate": 2.2241165530068197e-06,
|
| 1886 |
+
"loss": 1.4489,
|
| 1887 |
+
"step": 25100
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 15.62277304415182,
|
| 1891 |
+
"grad_norm": 2.8567991256713867,
|
| 1892 |
+
"learning_rate": 2.1931184128952267e-06,
|
| 1893 |
+
"loss": 1.4768,
|
| 1894 |
+
"step": 25200
|
| 1895 |
+
},
|
| 1896 |
+
{
|
| 1897 |
+
"epoch": 15.684740511231603,
|
| 1898 |
+
"grad_norm": 2.683873414993286,
|
| 1899 |
+
"learning_rate": 2.162430254184749e-06,
|
| 1900 |
+
"loss": 1.4578,
|
| 1901 |
+
"step": 25300
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 15.746707978311386,
|
| 1905 |
+
"grad_norm": 3.3914294242858887,
|
| 1906 |
+
"learning_rate": 2.131432114073156e-06,
|
| 1907 |
+
"loss": 1.4564,
|
| 1908 |
+
"step": 25400
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 15.80867544539117,
|
| 1912 |
+
"grad_norm": 2.8761868476867676,
|
| 1913 |
+
"learning_rate": 2.1004339739615625e-06,
|
| 1914 |
+
"loss": 1.4648,
|
| 1915 |
+
"step": 25500
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"epoch": 15.870642912470952,
|
| 1919 |
+
"grad_norm": 3.788562059402466,
|
| 1920 |
+
"learning_rate": 2.069435833849969e-06,
|
| 1921 |
+
"loss": 1.4568,
|
| 1922 |
+
"step": 25600
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 15.932610379550736,
|
| 1926 |
+
"grad_norm": 3.973054885864258,
|
| 1927 |
+
"learning_rate": 2.038437693738376e-06,
|
| 1928 |
+
"loss": 1.4785,
|
| 1929 |
+
"step": 25700
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 15.994577846630518,
|
| 1933 |
+
"grad_norm": 4.635127544403076,
|
| 1934 |
+
"learning_rate": 2.0074395536267826e-06,
|
| 1935 |
+
"loss": 1.4741,
|
| 1936 |
+
"step": 25800
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 15.999535243996903,
|
| 1940 |
+
"eval_loss": 1.3650240898132324,
|
| 1941 |
+
"eval_runtime": 71.1811,
|
| 1942 |
+
"eval_samples_per_second": 45.335,
|
| 1943 |
+
"eval_steps_per_second": 22.675,
|
| 1944 |
+
"step": 25808
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 16.0570100697134,
|
| 1948 |
+
"grad_norm": 3.8094494342803955,
|
| 1949 |
+
"learning_rate": 1.976441413515189e-06,
|
| 1950 |
+
"loss": 1.4585,
|
| 1951 |
+
"step": 25900
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 16.118977536793185,
|
| 1955 |
+
"grad_norm": 2.649723529815674,
|
| 1956 |
+
"learning_rate": 1.945443273403596e-06,
|
| 1957 |
+
"loss": 1.4624,
|
| 1958 |
+
"step": 26000
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 16.180945003872967,
|
| 1962 |
+
"grad_norm": 2.537461757659912,
|
| 1963 |
+
"learning_rate": 1.9144451332920027e-06,
|
| 1964 |
+
"loss": 1.4576,
|
| 1965 |
+
"step": 26100
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 16.24291247095275,
|
| 1969 |
+
"grad_norm": 3.1259541511535645,
|
| 1970 |
+
"learning_rate": 1.8834469931804095e-06,
|
| 1971 |
+
"loss": 1.4657,
|
| 1972 |
+
"step": 26200
|
| 1973 |
+
},
|
| 1974 |
+
{
|
| 1975 |
+
"epoch": 16.30487993803253,
|
| 1976 |
+
"grad_norm": 3.396057367324829,
|
| 1977 |
+
"learning_rate": 1.8524488530688158e-06,
|
| 1978 |
+
"loss": 1.4532,
|
| 1979 |
+
"step": 26300
|
| 1980 |
+
},
|
| 1981 |
+
{
|
| 1982 |
+
"epoch": 16.366847405112317,
|
| 1983 |
+
"grad_norm": 2.7809932231903076,
|
| 1984 |
+
"learning_rate": 1.8214507129572226e-06,
|
| 1985 |
+
"loss": 1.4483,
|
| 1986 |
+
"step": 26400
|
| 1987 |
+
},
|
| 1988 |
+
{
|
| 1989 |
+
"epoch": 16.4288148721921,
|
| 1990 |
+
"grad_norm": 4.369870662689209,
|
| 1991 |
+
"learning_rate": 1.7904525728456294e-06,
|
| 1992 |
+
"loss": 1.4457,
|
| 1993 |
+
"step": 26500
|
| 1994 |
+
},
|
| 1995 |
+
{
|
| 1996 |
+
"epoch": 16.49078233927188,
|
| 1997 |
+
"grad_norm": 2.7700088024139404,
|
| 1998 |
+
"learning_rate": 1.759454432734036e-06,
|
| 1999 |
+
"loss": 1.4722,
|
| 2000 |
+
"step": 26600
|
| 2001 |
+
},
|
| 2002 |
+
{
|
| 2003 |
+
"epoch": 16.552749806351667,
|
| 2004 |
+
"grad_norm": 2.55792236328125,
|
| 2005 |
+
"learning_rate": 1.7284562926224427e-06,
|
| 2006 |
+
"loss": 1.4242,
|
| 2007 |
+
"step": 26700
|
| 2008 |
+
},
|
| 2009 |
+
{
|
| 2010 |
+
"epoch": 16.61471727343145,
|
| 2011 |
+
"grad_norm": 3.0416712760925293,
|
| 2012 |
+
"learning_rate": 1.6974581525108495e-06,
|
| 2013 |
+
"loss": 1.4516,
|
| 2014 |
+
"step": 26800
|
| 2015 |
+
},
|
| 2016 |
+
{
|
| 2017 |
+
"epoch": 16.67668474051123,
|
| 2018 |
+
"grad_norm": 2.6362993717193604,
|
| 2019 |
+
"learning_rate": 1.666460012399256e-06,
|
| 2020 |
+
"loss": 1.4263,
|
| 2021 |
+
"step": 26900
|
| 2022 |
+
},
|
| 2023 |
+
{
|
| 2024 |
+
"epoch": 16.738652207591016,
|
| 2025 |
+
"grad_norm": 2.5275797843933105,
|
| 2026 |
+
"learning_rate": 1.6354618722876628e-06,
|
| 2027 |
+
"loss": 1.4513,
|
| 2028 |
+
"step": 27000
|
| 2029 |
+
},
|
| 2030 |
+
{
|
| 2031 |
+
"epoch": 16.8006196746708,
|
| 2032 |
+
"grad_norm": 3.758063793182373,
|
| 2033 |
+
"learning_rate": 1.6044637321760696e-06,
|
| 2034 |
+
"loss": 1.4629,
|
| 2035 |
+
"step": 27100
|
| 2036 |
+
},
|
| 2037 |
+
{
|
| 2038 |
+
"epoch": 16.86258714175058,
|
| 2039 |
+
"grad_norm": 2.653982162475586,
|
| 2040 |
+
"learning_rate": 1.5734655920644761e-06,
|
| 2041 |
+
"loss": 1.4549,
|
| 2042 |
+
"step": 27200
|
| 2043 |
+
},
|
| 2044 |
+
{
|
| 2045 |
+
"epoch": 16.924554608830363,
|
| 2046 |
+
"grad_norm": 3.276362180709839,
|
| 2047 |
+
"learning_rate": 1.5424674519528829e-06,
|
| 2048 |
+
"loss": 1.4645,
|
| 2049 |
+
"step": 27300
|
| 2050 |
+
},
|
| 2051 |
+
{
|
| 2052 |
+
"epoch": 16.98652207591015,
|
| 2053 |
+
"grad_norm": 4.8964056968688965,
|
| 2054 |
+
"learning_rate": 1.5114693118412897e-06,
|
| 2055 |
+
"loss": 1.4292,
|
| 2056 |
+
"step": 27400
|
| 2057 |
+
},
|
| 2058 |
+
{
|
| 2059 |
+
"epoch": 16.999535243996903,
|
| 2060 |
+
"eval_loss": 1.3658363819122314,
|
| 2061 |
+
"eval_runtime": 71.5249,
|
| 2062 |
+
"eval_samples_per_second": 45.117,
|
| 2063 |
+
"eval_steps_per_second": 22.566,
|
| 2064 |
+
"step": 27421
|
| 2065 |
+
},
|
| 2066 |
+
{
|
| 2067 |
+
"epoch": 17.048954298993028,
|
| 2068 |
+
"grad_norm": 2.632962703704834,
|
| 2069 |
+
"learning_rate": 1.4804711717296962e-06,
|
| 2070 |
+
"loss": 1.4485,
|
| 2071 |
+
"step": 27500
|
| 2072 |
+
},
|
| 2073 |
+
{
|
| 2074 |
+
"epoch": 17.110921766072813,
|
| 2075 |
+
"grad_norm": 2.65366792678833,
|
| 2076 |
+
"learning_rate": 1.449473031618103e-06,
|
| 2077 |
+
"loss": 1.4335,
|
| 2078 |
+
"step": 27600
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 17.172889233152596,
|
| 2082 |
+
"grad_norm": 7.086144924163818,
|
| 2083 |
+
"learning_rate": 1.4184748915065097e-06,
|
| 2084 |
+
"loss": 1.4483,
|
| 2085 |
+
"step": 27700
|
| 2086 |
+
},
|
| 2087 |
+
{
|
| 2088 |
+
"epoch": 17.234856700232378,
|
| 2089 |
+
"grad_norm": 4.501598834991455,
|
| 2090 |
+
"learning_rate": 1.3874767513949163e-06,
|
| 2091 |
+
"loss": 1.4328,
|
| 2092 |
+
"step": 27800
|
| 2093 |
+
},
|
| 2094 |
+
{
|
| 2095 |
+
"epoch": 17.29682416731216,
|
| 2096 |
+
"grad_norm": 3.042269706726074,
|
| 2097 |
+
"learning_rate": 1.356478611283323e-06,
|
| 2098 |
+
"loss": 1.4476,
|
| 2099 |
+
"step": 27900
|
| 2100 |
+
},
|
| 2101 |
+
{
|
| 2102 |
+
"epoch": 17.358791634391945,
|
| 2103 |
+
"grad_norm": 2.902914047241211,
|
| 2104 |
+
"learning_rate": 1.3254804711717298e-06,
|
| 2105 |
+
"loss": 1.4551,
|
| 2106 |
+
"step": 28000
|
| 2107 |
+
},
|
| 2108 |
+
{
|
| 2109 |
+
"epoch": 17.420759101471727,
|
| 2110 |
+
"grad_norm": 4.015540599822998,
|
| 2111 |
+
"learning_rate": 1.2944823310601364e-06,
|
| 2112 |
+
"loss": 1.4408,
|
| 2113 |
+
"step": 28100
|
| 2114 |
+
},
|
| 2115 |
+
{
|
| 2116 |
+
"epoch": 17.48272656855151,
|
| 2117 |
+
"grad_norm": 2.1433181762695312,
|
| 2118 |
+
"learning_rate": 1.2634841909485432e-06,
|
| 2119 |
+
"loss": 1.4363,
|
| 2120 |
+
"step": 28200
|
| 2121 |
+
},
|
| 2122 |
+
{
|
| 2123 |
+
"epoch": 17.544694035631295,
|
| 2124 |
+
"grad_norm": 3.0657026767730713,
|
| 2125 |
+
"learning_rate": 1.23248605083695e-06,
|
| 2126 |
+
"loss": 1.4519,
|
| 2127 |
+
"step": 28300
|
| 2128 |
+
},
|
| 2129 |
+
{
|
| 2130 |
+
"epoch": 17.606661502711077,
|
| 2131 |
+
"grad_norm": 2.260270357131958,
|
| 2132 |
+
"learning_rate": 1.2014879107253565e-06,
|
| 2133 |
+
"loss": 1.4609,
|
| 2134 |
+
"step": 28400
|
| 2135 |
+
},
|
| 2136 |
+
{
|
| 2137 |
+
"epoch": 17.66862896979086,
|
| 2138 |
+
"grad_norm": 3.2962841987609863,
|
| 2139 |
+
"learning_rate": 1.1704897706137633e-06,
|
| 2140 |
+
"loss": 1.4267,
|
| 2141 |
+
"step": 28500
|
| 2142 |
+
},
|
| 2143 |
+
{
|
| 2144 |
+
"epoch": 17.73059643687064,
|
| 2145 |
+
"grad_norm": 2.8596572875976562,
|
| 2146 |
+
"learning_rate": 1.13949163050217e-06,
|
| 2147 |
+
"loss": 1.4485,
|
| 2148 |
+
"step": 28600
|
| 2149 |
+
},
|
| 2150 |
+
{
|
| 2151 |
+
"epoch": 17.792563903950427,
|
| 2152 |
+
"grad_norm": 2.8049371242523193,
|
| 2153 |
+
"learning_rate": 1.1084934903905766e-06,
|
| 2154 |
+
"loss": 1.4272,
|
| 2155 |
+
"step": 28700
|
| 2156 |
+
},
|
| 2157 |
+
{
|
| 2158 |
+
"epoch": 17.85453137103021,
|
| 2159 |
+
"grad_norm": 3.8641581535339355,
|
| 2160 |
+
"learning_rate": 1.0774953502789834e-06,
|
| 2161 |
+
"loss": 1.4426,
|
| 2162 |
+
"step": 28800
|
| 2163 |
+
},
|
| 2164 |
+
{
|
| 2165 |
+
"epoch": 17.91649883810999,
|
| 2166 |
+
"grad_norm": 2.718754529953003,
|
| 2167 |
+
"learning_rate": 1.0464972101673901e-06,
|
| 2168 |
+
"loss": 1.4696,
|
| 2169 |
+
"step": 28900
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"epoch": 17.978466305189777,
|
| 2173 |
+
"grad_norm": 2.8387906551361084,
|
| 2174 |
+
"learning_rate": 1.0154990700557969e-06,
|
| 2175 |
+
"loss": 1.437,
|
| 2176 |
+
"step": 29000
|
| 2177 |
+
},
|
| 2178 |
+
{
|
| 2179 |
+
"epoch": 17.999535243996903,
|
| 2180 |
+
"eval_loss": 1.3650579452514648,
|
| 2181 |
+
"eval_runtime": 71.088,
|
| 2182 |
+
"eval_samples_per_second": 45.394,
|
| 2183 |
+
"eval_steps_per_second": 22.704,
|
| 2184 |
+
"step": 29034
|
| 2185 |
+
},
|
| 2186 |
+
{
|
| 2187 |
+
"epoch": 18.040898528272656,
|
| 2188 |
+
"grad_norm": 7.15321159362793,
|
| 2189 |
+
"learning_rate": 9.845009299442034e-07,
|
| 2190 |
+
"loss": 1.4728,
|
| 2191 |
+
"step": 29100
|
| 2192 |
+
},
|
| 2193 |
+
{
|
| 2194 |
+
"epoch": 18.10286599535244,
|
| 2195 |
+
"grad_norm": 3.0295169353485107,
|
| 2196 |
+
"learning_rate": 9.535027898326102e-07,
|
| 2197 |
+
"loss": 1.444,
|
| 2198 |
+
"step": 29200
|
| 2199 |
+
},
|
| 2200 |
+
{
|
| 2201 |
+
"epoch": 18.164833462432224,
|
| 2202 |
+
"grad_norm": 4.30358362197876,
|
| 2203 |
+
"learning_rate": 9.225046497210168e-07,
|
| 2204 |
+
"loss": 1.4373,
|
| 2205 |
+
"step": 29300
|
| 2206 |
+
},
|
| 2207 |
+
{
|
| 2208 |
+
"epoch": 18.226800929512006,
|
| 2209 |
+
"grad_norm": 2.6451058387756348,
|
| 2210 |
+
"learning_rate": 8.915065096094234e-07,
|
| 2211 |
+
"loss": 1.4633,
|
| 2212 |
+
"step": 29400
|
| 2213 |
+
},
|
| 2214 |
+
{
|
| 2215 |
+
"epoch": 18.288768396591788,
|
| 2216 |
+
"grad_norm": 2.5222158432006836,
|
| 2217 |
+
"learning_rate": 8.605083694978301e-07,
|
| 2218 |
+
"loss": 1.4361,
|
| 2219 |
+
"step": 29500
|
| 2220 |
+
},
|
| 2221 |
+
{
|
| 2222 |
+
"epoch": 18.350735863671574,
|
| 2223 |
+
"grad_norm": 3.099586009979248,
|
| 2224 |
+
"learning_rate": 8.295102293862369e-07,
|
| 2225 |
+
"loss": 1.4451,
|
| 2226 |
+
"step": 29600
|
| 2227 |
+
},
|
| 2228 |
+
{
|
| 2229 |
+
"epoch": 18.412703330751356,
|
| 2230 |
+
"grad_norm": 2.569441795349121,
|
| 2231 |
+
"learning_rate": 7.985120892746435e-07,
|
| 2232 |
+
"loss": 1.4167,
|
| 2233 |
+
"step": 29700
|
| 2234 |
+
},
|
| 2235 |
+
{
|
| 2236 |
+
"epoch": 18.474670797831138,
|
| 2237 |
+
"grad_norm": 3.3484814167022705,
|
| 2238 |
+
"learning_rate": 7.678239305641662e-07,
|
| 2239 |
+
"loss": 1.4573,
|
| 2240 |
+
"step": 29800
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"epoch": 18.536638264910923,
|
| 2244 |
+
"grad_norm": 3.530923843383789,
|
| 2245 |
+
"learning_rate": 7.368257904525729e-07,
|
| 2246 |
+
"loss": 1.4653,
|
| 2247 |
+
"step": 29900
|
| 2248 |
+
},
|
| 2249 |
+
{
|
| 2250 |
+
"epoch": 18.598605731990705,
|
| 2251 |
+
"grad_norm": 2.9912829399108887,
|
| 2252 |
+
"learning_rate": 7.058276503409796e-07,
|
| 2253 |
+
"loss": 1.4376,
|
| 2254 |
+
"step": 30000
|
| 2255 |
+
},
|
| 2256 |
+
{
|
| 2257 |
+
"epoch": 18.660573199070488,
|
| 2258 |
+
"grad_norm": 4.254590034484863,
|
| 2259 |
+
"learning_rate": 6.748295102293862e-07,
|
| 2260 |
+
"loss": 1.4159,
|
| 2261 |
+
"step": 30100
|
| 2262 |
+
},
|
| 2263 |
+
{
|
| 2264 |
+
"epoch": 18.72254066615027,
|
| 2265 |
+
"grad_norm": 2.5701520442962646,
|
| 2266 |
+
"learning_rate": 6.43831370117793e-07,
|
| 2267 |
+
"loss": 1.4456,
|
| 2268 |
+
"step": 30200
|
| 2269 |
+
},
|
| 2270 |
+
{
|
| 2271 |
+
"epoch": 18.784508133230055,
|
| 2272 |
+
"grad_norm": 2.5587334632873535,
|
| 2273 |
+
"learning_rate": 6.131432114073156e-07,
|
| 2274 |
+
"loss": 1.4398,
|
| 2275 |
+
"step": 30300
|
| 2276 |
+
},
|
| 2277 |
+
{
|
| 2278 |
+
"epoch": 18.846475600309837,
|
| 2279 |
+
"grad_norm": 2.7531826496124268,
|
| 2280 |
+
"learning_rate": 5.821450712957223e-07,
|
| 2281 |
+
"loss": 1.4373,
|
| 2282 |
+
"step": 30400
|
| 2283 |
+
},
|
| 2284 |
+
{
|
| 2285 |
+
"epoch": 18.90844306738962,
|
| 2286 |
+
"grad_norm": 2.606565237045288,
|
| 2287 |
+
"learning_rate": 5.51146931184129e-07,
|
| 2288 |
+
"loss": 1.4322,
|
| 2289 |
+
"step": 30500
|
| 2290 |
+
},
|
| 2291 |
+
{
|
| 2292 |
+
"epoch": 18.970410534469405,
|
| 2293 |
+
"grad_norm": 2.6392128467559814,
|
| 2294 |
+
"learning_rate": 5.201487910725357e-07,
|
| 2295 |
+
"loss": 1.4442,
|
| 2296 |
+
"step": 30600
|
| 2297 |
+
},
|
| 2298 |
+
{
|
| 2299 |
+
"epoch": 18.999535243996903,
|
| 2300 |
+
"eval_loss": 1.3643269538879395,
|
| 2301 |
+
"eval_runtime": 71.2663,
|
| 2302 |
+
"eval_samples_per_second": 45.281,
|
| 2303 |
+
"eval_steps_per_second": 22.647,
|
| 2304 |
+
"step": 30647
|
| 2305 |
+
},
|
| 2306 |
+
{
|
| 2307 |
+
"epoch": 19.032842757552284,
|
| 2308 |
+
"grad_norm": 2.5503151416778564,
|
| 2309 |
+
"learning_rate": 4.891506509609424e-07,
|
| 2310 |
+
"loss": 1.4546,
|
| 2311 |
+
"step": 30700
|
| 2312 |
+
},
|
| 2313 |
+
{
|
| 2314 |
+
"epoch": 19.094810224632067,
|
| 2315 |
+
"grad_norm": 3.5481629371643066,
|
| 2316 |
+
"learning_rate": 4.5815251084934906e-07,
|
| 2317 |
+
"loss": 1.4389,
|
| 2318 |
+
"step": 30800
|
| 2319 |
+
},
|
| 2320 |
+
{
|
| 2321 |
+
"epoch": 19.156777691711852,
|
| 2322 |
+
"grad_norm": 2.849660634994507,
|
| 2323 |
+
"learning_rate": 4.271543707377557e-07,
|
| 2324 |
+
"loss": 1.4311,
|
| 2325 |
+
"step": 30900
|
| 2326 |
+
},
|
| 2327 |
+
{
|
| 2328 |
+
"epoch": 19.218745158791634,
|
| 2329 |
+
"grad_norm": 2.581972599029541,
|
| 2330 |
+
"learning_rate": 3.9615623062616244e-07,
|
| 2331 |
+
"loss": 1.4772,
|
| 2332 |
+
"step": 31000
|
| 2333 |
+
},
|
| 2334 |
+
{
|
| 2335 |
+
"epoch": 19.280712625871416,
|
| 2336 |
+
"grad_norm": 4.163836479187012,
|
| 2337 |
+
"learning_rate": 3.6515809051456916e-07,
|
| 2338 |
+
"loss": 1.4237,
|
| 2339 |
+
"step": 31100
|
| 2340 |
+
},
|
| 2341 |
+
{
|
| 2342 |
+
"epoch": 19.342680092951202,
|
| 2343 |
+
"grad_norm": 2.7274580001831055,
|
| 2344 |
+
"learning_rate": 3.341599504029758e-07,
|
| 2345 |
+
"loss": 1.4404,
|
| 2346 |
+
"step": 31200
|
| 2347 |
+
},
|
| 2348 |
+
{
|
| 2349 |
+
"epoch": 19.404647560030984,
|
| 2350 |
+
"grad_norm": 3.983724355697632,
|
| 2351 |
+
"learning_rate": 3.0316181029138253e-07,
|
| 2352 |
+
"loss": 1.4473,
|
| 2353 |
+
"step": 31300
|
| 2354 |
+
},
|
| 2355 |
+
{
|
| 2356 |
+
"epoch": 19.466615027110766,
|
| 2357 |
+
"grad_norm": 2.6508560180664062,
|
| 2358 |
+
"learning_rate": 2.7216367017978925e-07,
|
| 2359 |
+
"loss": 1.4563,
|
| 2360 |
+
"step": 31400
|
| 2361 |
+
},
|
| 2362 |
+
{
|
| 2363 |
+
"epoch": 19.52858249419055,
|
| 2364 |
+
"grad_norm": 2.608508348464966,
|
| 2365 |
+
"learning_rate": 2.4116553006819597e-07,
|
| 2366 |
+
"loss": 1.4381,
|
| 2367 |
+
"step": 31500
|
| 2368 |
+
},
|
| 2369 |
+
{
|
| 2370 |
+
"epoch": 19.590549961270334,
|
| 2371 |
+
"grad_norm": 3.2333600521087646,
|
| 2372 |
+
"learning_rate": 2.101673899566026e-07,
|
| 2373 |
+
"loss": 1.4418,
|
| 2374 |
+
"step": 31600
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"epoch": 19.652517428350116,
|
| 2378 |
+
"grad_norm": 5.008152008056641,
|
| 2379 |
+
"learning_rate": 1.7916924984500932e-07,
|
| 2380 |
+
"loss": 1.447,
|
| 2381 |
+
"step": 31700
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"epoch": 19.714484895429898,
|
| 2385 |
+
"grad_norm": 3.073624610900879,
|
| 2386 |
+
"learning_rate": 1.48171109733416e-07,
|
| 2387 |
+
"loss": 1.4241,
|
| 2388 |
+
"step": 31800
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 19.776452362509684,
|
| 2392 |
+
"grad_norm": 5.159261226654053,
|
| 2393 |
+
"learning_rate": 1.171729696218227e-07,
|
| 2394 |
+
"loss": 1.424,
|
| 2395 |
+
"step": 31900
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"epoch": 19.838419829589466,
|
| 2399 |
+
"grad_norm": 3.225008249282837,
|
| 2400 |
+
"learning_rate": 8.61748295102294e-08,
|
| 2401 |
+
"loss": 1.4327,
|
| 2402 |
+
"step": 32000
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 19.900387296669248,
|
| 2406 |
+
"grad_norm": 3.629281520843506,
|
| 2407 |
+
"learning_rate": 5.517668939863608e-08,
|
| 2408 |
+
"loss": 1.437,
|
| 2409 |
+
"step": 32100
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 19.962354763749033,
|
| 2413 |
+
"grad_norm": 2.323373556137085,
|
| 2414 |
+
"learning_rate": 2.417854928704278e-08,
|
| 2415 |
+
"loss": 1.4345,
|
| 2416 |
+
"step": 32200
|
| 2417 |
+
},
|
| 2418 |
+
{
|
| 2419 |
+
"epoch": 19.999535243996903,
|
| 2420 |
+
"eval_loss": 1.3642308712005615,
|
| 2421 |
+
"eval_runtime": 70.2626,
|
| 2422 |
+
"eval_samples_per_second": 45.928,
|
| 2423 |
+
"eval_steps_per_second": 22.971,
|
| 2424 |
+
"step": 32260
|
| 2425 |
+
}
|
| 2426 |
+
],
|
| 2427 |
+
"logging_steps": 100,
|
| 2428 |
+
"max_steps": 32260,
|
| 2429 |
+
"num_input_tokens_seen": 0,
|
| 2430 |
+
"num_train_epochs": 20,
|
| 2431 |
+
"save_steps": 500,
|
| 2432 |
+
"stateful_callbacks": {
|
| 2433 |
+
"TrainerControl": {
|
| 2434 |
+
"args": {
|
| 2435 |
+
"should_epoch_stop": false,
|
| 2436 |
+
"should_evaluate": false,
|
| 2437 |
+
"should_log": false,
|
| 2438 |
+
"should_save": true,
|
| 2439 |
+
"should_training_stop": true
|
| 2440 |
+
},
|
| 2441 |
+
"attributes": {}
|
| 2442 |
+
}
|
| 2443 |
+
},
|
| 2444 |
+
"total_flos": 2.2226940169519104e+17,
|
| 2445 |
+
"train_batch_size": 2,
|
| 2446 |
+
"trial_name": null,
|
| 2447 |
+
"trial_params": null
|
| 2448 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:481df95b3a0fad34cab9c2f1194c98d273531df33b717401035b0db384ea9ddc
|
| 3 |
+
size 5841
|