Upload folder using huggingface_hub
Browse files- all_results.json +21 -0
- ood_results.json +8 -0
- pred_ood.npz.npy +3 -0
- pred_qqp.npz.npy +3 -0
- pred_transfer.npz.npy +3 -0
- pytorch_model.bin +3 -0
- qqp_results.json +8 -0
- rep_ood.pt +3 -0
- rep_qqp.pt +3 -0
- special_tokens_map.json +125 -0
- spiece.model +3 -0
- test_results.json +10 -0
- tokenizer.json +0 -0
- tokenizer_config.json +938 -0
- train_results.json +7 -0
- trainer_state.json +871 -0
- training_args.bin +3 -0
- transfer_results.json +8 -0
all_results.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"ave/id": 0.8002366534419154,
|
| 3 |
+
"ave/ood": 0.5953417913274002,
|
| 4 |
+
"ave/transfer": 0.751798561151079,
|
| 5 |
+
"epoch": 5.0,
|
| 6 |
+
"eval_combined_score": 0.751798561151079,
|
| 7 |
+
"eval_f1": 0.751798561151079,
|
| 8 |
+
"eval_loss": 0.7870423793792725,
|
| 9 |
+
"eval_runtime": 1.8495,
|
| 10 |
+
"eval_samples_per_second": 220.598,
|
| 11 |
+
"eval_steps_per_second": 1.081,
|
| 12 |
+
"gap/ood": 0.20489486211451524,
|
| 13 |
+
"gap/transfer": 0.0484380922908364,
|
| 14 |
+
"ood": 0.5953417913274002,
|
| 15 |
+
"qqp": 0.8002366534419154,
|
| 16 |
+
"train_loss": 0.5264342698119119,
|
| 17 |
+
"train_runtime": 6200.063,
|
| 18 |
+
"train_samples_per_second": 293.421,
|
| 19 |
+
"train_steps_per_second": 9.17,
|
| 20 |
+
"transfer": 0.751798561151079
|
| 21 |
+
}
|
ood_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eval_combined_score": 0.5953417913274002,
|
| 3 |
+
"eval_f1": 0.5953417913274002,
|
| 4 |
+
"eval_loss": 1.1512255668640137,
|
| 5 |
+
"eval_runtime": 20.4375,
|
| 6 |
+
"eval_samples_per_second": 391.437,
|
| 7 |
+
"eval_steps_per_second": 1.566
|
| 8 |
+
}
|
pred_ood.npz.npy
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0583375eb46a898d2f9327934b745d8f23bb7811090223cced56601f9d662ef6
|
| 3 |
+
size 64128
|
pred_qqp.npz.npy
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51837f3f0b1f0917aacf4b24e8cb99e84099f4902076c6d116b52bb8ecef8212
|
| 3 |
+
size 323568
|
pred_transfer.npz.npy
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6744776a6e9b7b380cc02151d3e55d54fa0c2b7b9b7e9802fb4369365dc238f7
|
| 3 |
+
size 3392
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7f6b869515df4d58c8d97f87002bca6c91ef7d1bd24dbb74123b0afbf5cdd34
|
| 3 |
+
size 173407370
|
qqp_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eval_combined_score": 0.8002366534419154,
|
| 3 |
+
"eval_f1": 0.8002366534419154,
|
| 4 |
+
"eval_loss": 0.3343241512775421,
|
| 5 |
+
"eval_runtime": 96.9458,
|
| 6 |
+
"eval_samples_per_second": 417.037,
|
| 7 |
+
"eval_steps_per_second": 1.63
|
| 8 |
+
}
|
rep_ood.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac37766282465560553f6c4ee733820dc88d6de1cbbc2efd53e737c28c4673c4
|
| 3 |
+
size 196642482
|
rep_qqp.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd7fd82cf602b2a07584bafacf5d40284de3a82d406d1878270f19b7dfa7d487
|
| 3 |
+
size 993779266
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"eos_token": {
|
| 105 |
+
"content": "</s>",
|
| 106 |
+
"lstrip": false,
|
| 107 |
+
"normalized": false,
|
| 108 |
+
"rstrip": false,
|
| 109 |
+
"single_word": false
|
| 110 |
+
},
|
| 111 |
+
"pad_token": {
|
| 112 |
+
"content": "<pad>",
|
| 113 |
+
"lstrip": false,
|
| 114 |
+
"normalized": false,
|
| 115 |
+
"rstrip": false,
|
| 116 |
+
"single_word": false
|
| 117 |
+
},
|
| 118 |
+
"unk_token": {
|
| 119 |
+
"content": "<unk>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false
|
| 124 |
+
}
|
| 125 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
| 3 |
+
size 791656
|
test_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"ave/id": 0.8002366534419154,
|
| 3 |
+
"ave/ood": 0.5953417913274002,
|
| 4 |
+
"ave/transfer": 0.751798561151079,
|
| 5 |
+
"gap/ood": 0.20489486211451524,
|
| 6 |
+
"gap/transfer": 0.0484380922908364,
|
| 7 |
+
"ood": 0.5953417913274002,
|
| 8 |
+
"qqp": 0.8002366534419154,
|
| 9 |
+
"transfer": 0.751798561151079
|
| 10 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,938 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "</s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<unk>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"32000": {
|
| 28 |
+
"content": "<extra_id_99>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"32001": {
|
| 36 |
+
"content": "<extra_id_98>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"32002": {
|
| 44 |
+
"content": "<extra_id_97>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"32003": {
|
| 52 |
+
"content": "<extra_id_96>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"32004": {
|
| 60 |
+
"content": "<extra_id_95>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"32005": {
|
| 68 |
+
"content": "<extra_id_94>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"32006": {
|
| 76 |
+
"content": "<extra_id_93>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"32007": {
|
| 84 |
+
"content": "<extra_id_92>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"32008": {
|
| 92 |
+
"content": "<extra_id_91>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"32009": {
|
| 100 |
+
"content": "<extra_id_90>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"32010": {
|
| 108 |
+
"content": "<extra_id_89>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"32011": {
|
| 116 |
+
"content": "<extra_id_88>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"32012": {
|
| 124 |
+
"content": "<extra_id_87>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"32013": {
|
| 132 |
+
"content": "<extra_id_86>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"32014": {
|
| 140 |
+
"content": "<extra_id_85>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"32015": {
|
| 148 |
+
"content": "<extra_id_84>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"32016": {
|
| 156 |
+
"content": "<extra_id_83>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"32017": {
|
| 164 |
+
"content": "<extra_id_82>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"32018": {
|
| 172 |
+
"content": "<extra_id_81>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"32019": {
|
| 180 |
+
"content": "<extra_id_80>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"32020": {
|
| 188 |
+
"content": "<extra_id_79>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"32021": {
|
| 196 |
+
"content": "<extra_id_78>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"32022": {
|
| 204 |
+
"content": "<extra_id_77>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"32023": {
|
| 212 |
+
"content": "<extra_id_76>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"32024": {
|
| 220 |
+
"content": "<extra_id_75>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"32025": {
|
| 228 |
+
"content": "<extra_id_74>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"32026": {
|
| 236 |
+
"content": "<extra_id_73>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"32027": {
|
| 244 |
+
"content": "<extra_id_72>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"32028": {
|
| 252 |
+
"content": "<extra_id_71>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"32029": {
|
| 260 |
+
"content": "<extra_id_70>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"32030": {
|
| 268 |
+
"content": "<extra_id_69>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"32031": {
|
| 276 |
+
"content": "<extra_id_68>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"32032": {
|
| 284 |
+
"content": "<extra_id_67>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"32033": {
|
| 292 |
+
"content": "<extra_id_66>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"32034": {
|
| 300 |
+
"content": "<extra_id_65>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"32035": {
|
| 308 |
+
"content": "<extra_id_64>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"32036": {
|
| 316 |
+
"content": "<extra_id_63>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"32037": {
|
| 324 |
+
"content": "<extra_id_62>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"32038": {
|
| 332 |
+
"content": "<extra_id_61>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"32039": {
|
| 340 |
+
"content": "<extra_id_60>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"32040": {
|
| 348 |
+
"content": "<extra_id_59>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"32041": {
|
| 356 |
+
"content": "<extra_id_58>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"32042": {
|
| 364 |
+
"content": "<extra_id_57>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"32043": {
|
| 372 |
+
"content": "<extra_id_56>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"32044": {
|
| 380 |
+
"content": "<extra_id_55>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"32045": {
|
| 388 |
+
"content": "<extra_id_54>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"32046": {
|
| 396 |
+
"content": "<extra_id_53>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"32047": {
|
| 404 |
+
"content": "<extra_id_52>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"32048": {
|
| 412 |
+
"content": "<extra_id_51>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"32049": {
|
| 420 |
+
"content": "<extra_id_50>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"32050": {
|
| 428 |
+
"content": "<extra_id_49>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"32051": {
|
| 436 |
+
"content": "<extra_id_48>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"32052": {
|
| 444 |
+
"content": "<extra_id_47>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"32053": {
|
| 452 |
+
"content": "<extra_id_46>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"32054": {
|
| 460 |
+
"content": "<extra_id_45>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"32055": {
|
| 468 |
+
"content": "<extra_id_44>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"32056": {
|
| 476 |
+
"content": "<extra_id_43>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"32057": {
|
| 484 |
+
"content": "<extra_id_42>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"32058": {
|
| 492 |
+
"content": "<extra_id_41>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"32059": {
|
| 500 |
+
"content": "<extra_id_40>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"32060": {
|
| 508 |
+
"content": "<extra_id_39>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"32061": {
|
| 516 |
+
"content": "<extra_id_38>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"32062": {
|
| 524 |
+
"content": "<extra_id_37>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"32063": {
|
| 532 |
+
"content": "<extra_id_36>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"32064": {
|
| 540 |
+
"content": "<extra_id_35>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"32065": {
|
| 548 |
+
"content": "<extra_id_34>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"32066": {
|
| 556 |
+
"content": "<extra_id_33>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"32067": {
|
| 564 |
+
"content": "<extra_id_32>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"32068": {
|
| 572 |
+
"content": "<extra_id_31>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"32069": {
|
| 580 |
+
"content": "<extra_id_30>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"32070": {
|
| 588 |
+
"content": "<extra_id_29>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"32071": {
|
| 596 |
+
"content": "<extra_id_28>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"32072": {
|
| 604 |
+
"content": "<extra_id_27>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"32073": {
|
| 612 |
+
"content": "<extra_id_26>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"32074": {
|
| 620 |
+
"content": "<extra_id_25>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"32075": {
|
| 628 |
+
"content": "<extra_id_24>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"32076": {
|
| 636 |
+
"content": "<extra_id_23>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"32077": {
|
| 644 |
+
"content": "<extra_id_22>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"32078": {
|
| 652 |
+
"content": "<extra_id_21>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"32079": {
|
| 660 |
+
"content": "<extra_id_20>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"32080": {
|
| 668 |
+
"content": "<extra_id_19>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"32081": {
|
| 676 |
+
"content": "<extra_id_18>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"32082": {
|
| 684 |
+
"content": "<extra_id_17>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"32083": {
|
| 692 |
+
"content": "<extra_id_16>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"32084": {
|
| 700 |
+
"content": "<extra_id_15>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"32085": {
|
| 708 |
+
"content": "<extra_id_14>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"32086": {
|
| 716 |
+
"content": "<extra_id_13>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"32087": {
|
| 724 |
+
"content": "<extra_id_12>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"32088": {
|
| 732 |
+
"content": "<extra_id_11>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"32089": {
|
| 740 |
+
"content": "<extra_id_10>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"32090": {
|
| 748 |
+
"content": "<extra_id_9>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"32091": {
|
| 756 |
+
"content": "<extra_id_8>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"32092": {
|
| 764 |
+
"content": "<extra_id_7>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"32093": {
|
| 772 |
+
"content": "<extra_id_6>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"32094": {
|
| 780 |
+
"content": "<extra_id_5>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"32095": {
|
| 788 |
+
"content": "<extra_id_4>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"32096": {
|
| 796 |
+
"content": "<extra_id_3>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"32097": {
|
| 804 |
+
"content": "<extra_id_2>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"32098": {
|
| 812 |
+
"content": "<extra_id_1>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"32099": {
|
| 820 |
+
"content": "<extra_id_0>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
}
|
| 827 |
+
},
|
| 828 |
+
"additional_special_tokens": [
|
| 829 |
+
"<extra_id_0>",
|
| 830 |
+
"<extra_id_1>",
|
| 831 |
+
"<extra_id_2>",
|
| 832 |
+
"<extra_id_3>",
|
| 833 |
+
"<extra_id_4>",
|
| 834 |
+
"<extra_id_5>",
|
| 835 |
+
"<extra_id_6>",
|
| 836 |
+
"<extra_id_7>",
|
| 837 |
+
"<extra_id_8>",
|
| 838 |
+
"<extra_id_9>",
|
| 839 |
+
"<extra_id_10>",
|
| 840 |
+
"<extra_id_11>",
|
| 841 |
+
"<extra_id_12>",
|
| 842 |
+
"<extra_id_13>",
|
| 843 |
+
"<extra_id_14>",
|
| 844 |
+
"<extra_id_15>",
|
| 845 |
+
"<extra_id_16>",
|
| 846 |
+
"<extra_id_17>",
|
| 847 |
+
"<extra_id_18>",
|
| 848 |
+
"<extra_id_19>",
|
| 849 |
+
"<extra_id_20>",
|
| 850 |
+
"<extra_id_21>",
|
| 851 |
+
"<extra_id_22>",
|
| 852 |
+
"<extra_id_23>",
|
| 853 |
+
"<extra_id_24>",
|
| 854 |
+
"<extra_id_25>",
|
| 855 |
+
"<extra_id_26>",
|
| 856 |
+
"<extra_id_27>",
|
| 857 |
+
"<extra_id_28>",
|
| 858 |
+
"<extra_id_29>",
|
| 859 |
+
"<extra_id_30>",
|
| 860 |
+
"<extra_id_31>",
|
| 861 |
+
"<extra_id_32>",
|
| 862 |
+
"<extra_id_33>",
|
| 863 |
+
"<extra_id_34>",
|
| 864 |
+
"<extra_id_35>",
|
| 865 |
+
"<extra_id_36>",
|
| 866 |
+
"<extra_id_37>",
|
| 867 |
+
"<extra_id_38>",
|
| 868 |
+
"<extra_id_39>",
|
| 869 |
+
"<extra_id_40>",
|
| 870 |
+
"<extra_id_41>",
|
| 871 |
+
"<extra_id_42>",
|
| 872 |
+
"<extra_id_43>",
|
| 873 |
+
"<extra_id_44>",
|
| 874 |
+
"<extra_id_45>",
|
| 875 |
+
"<extra_id_46>",
|
| 876 |
+
"<extra_id_47>",
|
| 877 |
+
"<extra_id_48>",
|
| 878 |
+
"<extra_id_49>",
|
| 879 |
+
"<extra_id_50>",
|
| 880 |
+
"<extra_id_51>",
|
| 881 |
+
"<extra_id_52>",
|
| 882 |
+
"<extra_id_53>",
|
| 883 |
+
"<extra_id_54>",
|
| 884 |
+
"<extra_id_55>",
|
| 885 |
+
"<extra_id_56>",
|
| 886 |
+
"<extra_id_57>",
|
| 887 |
+
"<extra_id_58>",
|
| 888 |
+
"<extra_id_59>",
|
| 889 |
+
"<extra_id_60>",
|
| 890 |
+
"<extra_id_61>",
|
| 891 |
+
"<extra_id_62>",
|
| 892 |
+
"<extra_id_63>",
|
| 893 |
+
"<extra_id_64>",
|
| 894 |
+
"<extra_id_65>",
|
| 895 |
+
"<extra_id_66>",
|
| 896 |
+
"<extra_id_67>",
|
| 897 |
+
"<extra_id_68>",
|
| 898 |
+
"<extra_id_69>",
|
| 899 |
+
"<extra_id_70>",
|
| 900 |
+
"<extra_id_71>",
|
| 901 |
+
"<extra_id_72>",
|
| 902 |
+
"<extra_id_73>",
|
| 903 |
+
"<extra_id_74>",
|
| 904 |
+
"<extra_id_75>",
|
| 905 |
+
"<extra_id_76>",
|
| 906 |
+
"<extra_id_77>",
|
| 907 |
+
"<extra_id_78>",
|
| 908 |
+
"<extra_id_79>",
|
| 909 |
+
"<extra_id_80>",
|
| 910 |
+
"<extra_id_81>",
|
| 911 |
+
"<extra_id_82>",
|
| 912 |
+
"<extra_id_83>",
|
| 913 |
+
"<extra_id_84>",
|
| 914 |
+
"<extra_id_85>",
|
| 915 |
+
"<extra_id_86>",
|
| 916 |
+
"<extra_id_87>",
|
| 917 |
+
"<extra_id_88>",
|
| 918 |
+
"<extra_id_89>",
|
| 919 |
+
"<extra_id_90>",
|
| 920 |
+
"<extra_id_91>",
|
| 921 |
+
"<extra_id_92>",
|
| 922 |
+
"<extra_id_93>",
|
| 923 |
+
"<extra_id_94>",
|
| 924 |
+
"<extra_id_95>",
|
| 925 |
+
"<extra_id_96>",
|
| 926 |
+
"<extra_id_97>",
|
| 927 |
+
"<extra_id_98>",
|
| 928 |
+
"<extra_id_99>"
|
| 929 |
+
],
|
| 930 |
+
"clean_up_tokenization_spaces": true,
|
| 931 |
+
"eos_token": "</s>",
|
| 932 |
+
"extra_ids": 100,
|
| 933 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 934 |
+
"pad_token": "<pad>",
|
| 935 |
+
"sp_model_kwargs": {},
|
| 936 |
+
"tokenizer_class": "T5Tokenizer",
|
| 937 |
+
"unk_token": "<unk>"
|
| 938 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_loss": 0.5264342698119119,
|
| 4 |
+
"train_runtime": 6200.063,
|
| 5 |
+
"train_samples_per_second": 293.421,
|
| 6 |
+
"train_steps_per_second": 9.17
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,871 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8002366534419155,
|
| 3 |
+
"best_model_checkpoint": "outputs/t5-mini/weak_tiny_poe/qqp_21/checkpoint-56855",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 56855,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"grad_norm": 1.4761992692947388,
|
| 14 |
+
"learning_rate": 4.956028493536189e-05,
|
| 15 |
+
"loss": 0.7583,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.09,
|
| 20 |
+
"grad_norm": 2.450453519821167,
|
| 21 |
+
"learning_rate": 4.9120569870723775e-05,
|
| 22 |
+
"loss": 0.6838,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.13,
|
| 27 |
+
"grad_norm": 2.613905668258667,
|
| 28 |
+
"learning_rate": 4.868085480608566e-05,
|
| 29 |
+
"loss": 0.6626,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.18,
|
| 34 |
+
"grad_norm": 2.006730079650879,
|
| 35 |
+
"learning_rate": 4.824113974144755e-05,
|
| 36 |
+
"loss": 0.6505,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.22,
|
| 41 |
+
"grad_norm": 3.0432426929473877,
|
| 42 |
+
"learning_rate": 4.780142467680943e-05,
|
| 43 |
+
"loss": 0.6357,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.26,
|
| 48 |
+
"grad_norm": 2.369479179382324,
|
| 49 |
+
"learning_rate": 4.736170961217132e-05,
|
| 50 |
+
"loss": 0.6192,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.31,
|
| 55 |
+
"grad_norm": 3.6632206439971924,
|
| 56 |
+
"learning_rate": 4.6921994547533196e-05,
|
| 57 |
+
"loss": 0.6158,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.35,
|
| 62 |
+
"grad_norm": 1.6710329055786133,
|
| 63 |
+
"learning_rate": 4.6482279482895086e-05,
|
| 64 |
+
"loss": 0.6163,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.4,
|
| 69 |
+
"grad_norm": 1.6218762397766113,
|
| 70 |
+
"learning_rate": 4.6042564418256975e-05,
|
| 71 |
+
"loss": 0.6077,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.44,
|
| 76 |
+
"grad_norm": 1.753265142440796,
|
| 77 |
+
"learning_rate": 4.560284935361886e-05,
|
| 78 |
+
"loss": 0.6084,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.48,
|
| 83 |
+
"grad_norm": 2.213019371032715,
|
| 84 |
+
"learning_rate": 4.516313428898074e-05,
|
| 85 |
+
"loss": 0.5951,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.53,
|
| 90 |
+
"grad_norm": 1.2585835456848145,
|
| 91 |
+
"learning_rate": 4.472341922434263e-05,
|
| 92 |
+
"loss": 0.5929,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.57,
|
| 97 |
+
"grad_norm": 1.8762115240097046,
|
| 98 |
+
"learning_rate": 4.428370415970451e-05,
|
| 99 |
+
"loss": 0.5815,
|
| 100 |
+
"step": 6500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.62,
|
| 104 |
+
"grad_norm": 1.8141961097717285,
|
| 105 |
+
"learning_rate": 4.38439890950664e-05,
|
| 106 |
+
"loss": 0.5799,
|
| 107 |
+
"step": 7000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.66,
|
| 111 |
+
"grad_norm": 1.5737587213516235,
|
| 112 |
+
"learning_rate": 4.3404274030428286e-05,
|
| 113 |
+
"loss": 0.582,
|
| 114 |
+
"step": 7500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.7,
|
| 118 |
+
"grad_norm": 1.7630951404571533,
|
| 119 |
+
"learning_rate": 4.296455896579017e-05,
|
| 120 |
+
"loss": 0.5833,
|
| 121 |
+
"step": 8000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.75,
|
| 125 |
+
"grad_norm": 3.324857234954834,
|
| 126 |
+
"learning_rate": 4.252484390115206e-05,
|
| 127 |
+
"loss": 0.569,
|
| 128 |
+
"step": 8500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.79,
|
| 132 |
+
"grad_norm": 1.0849748849868774,
|
| 133 |
+
"learning_rate": 4.208512883651394e-05,
|
| 134 |
+
"loss": 0.5664,
|
| 135 |
+
"step": 9000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.84,
|
| 139 |
+
"grad_norm": 2.513084650039673,
|
| 140 |
+
"learning_rate": 4.1645413771875824e-05,
|
| 141 |
+
"loss": 0.5655,
|
| 142 |
+
"step": 9500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.88,
|
| 146 |
+
"grad_norm": 3.041181802749634,
|
| 147 |
+
"learning_rate": 4.1205698707237714e-05,
|
| 148 |
+
"loss": 0.5666,
|
| 149 |
+
"step": 10000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.92,
|
| 153 |
+
"grad_norm": 1.9409087896347046,
|
| 154 |
+
"learning_rate": 4.0765983642599596e-05,
|
| 155 |
+
"loss": 0.5612,
|
| 156 |
+
"step": 10500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.97,
|
| 160 |
+
"grad_norm": 1.8327817916870117,
|
| 161 |
+
"learning_rate": 4.0326268577961486e-05,
|
| 162 |
+
"loss": 0.5616,
|
| 163 |
+
"step": 11000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.0,
|
| 167 |
+
"eval_combined_score": 0.75431762556448,
|
| 168 |
+
"eval_f1": 0.75431762556448,
|
| 169 |
+
"eval_loss": 0.39584288001060486,
|
| 170 |
+
"eval_runtime": 35.7699,
|
| 171 |
+
"eval_samples_per_second": 1130.28,
|
| 172 |
+
"eval_steps_per_second": 4.417,
|
| 173 |
+
"step": 11371
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.01,
|
| 177 |
+
"grad_norm": 3.406697988510132,
|
| 178 |
+
"learning_rate": 3.988655351332337e-05,
|
| 179 |
+
"loss": 0.5595,
|
| 180 |
+
"step": 11500
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 1.06,
|
| 184 |
+
"grad_norm": 2.2096521854400635,
|
| 185 |
+
"learning_rate": 3.944683844868525e-05,
|
| 186 |
+
"loss": 0.5484,
|
| 187 |
+
"step": 12000
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 1.1,
|
| 191 |
+
"grad_norm": 1.2976303100585938,
|
| 192 |
+
"learning_rate": 3.900712338404714e-05,
|
| 193 |
+
"loss": 0.5485,
|
| 194 |
+
"step": 12500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.14,
|
| 198 |
+
"grad_norm": 2.539963960647583,
|
| 199 |
+
"learning_rate": 3.8567408319409024e-05,
|
| 200 |
+
"loss": 0.5468,
|
| 201 |
+
"step": 13000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.19,
|
| 205 |
+
"grad_norm": 2.3027236461639404,
|
| 206 |
+
"learning_rate": 3.812769325477091e-05,
|
| 207 |
+
"loss": 0.5472,
|
| 208 |
+
"step": 13500
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.23,
|
| 212 |
+
"grad_norm": 2.070688247680664,
|
| 213 |
+
"learning_rate": 3.76879781901328e-05,
|
| 214 |
+
"loss": 0.5425,
|
| 215 |
+
"step": 14000
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.28,
|
| 219 |
+
"grad_norm": 2.171999931335449,
|
| 220 |
+
"learning_rate": 3.724826312549468e-05,
|
| 221 |
+
"loss": 0.5409,
|
| 222 |
+
"step": 14500
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 1.32,
|
| 226 |
+
"grad_norm": 2.4110608100891113,
|
| 227 |
+
"learning_rate": 3.680854806085657e-05,
|
| 228 |
+
"loss": 0.5482,
|
| 229 |
+
"step": 15000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 1.36,
|
| 233 |
+
"grad_norm": 2.1505320072174072,
|
| 234 |
+
"learning_rate": 3.636883299621845e-05,
|
| 235 |
+
"loss": 0.5381,
|
| 236 |
+
"step": 15500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.41,
|
| 240 |
+
"grad_norm": 1.6976615190505981,
|
| 241 |
+
"learning_rate": 3.5929117931580335e-05,
|
| 242 |
+
"loss": 0.5403,
|
| 243 |
+
"step": 16000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.45,
|
| 247 |
+
"grad_norm": 1.6042710542678833,
|
| 248 |
+
"learning_rate": 3.5489402866942224e-05,
|
| 249 |
+
"loss": 0.5408,
|
| 250 |
+
"step": 16500
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.5,
|
| 254 |
+
"grad_norm": 2.5285661220550537,
|
| 255 |
+
"learning_rate": 3.504968780230411e-05,
|
| 256 |
+
"loss": 0.5372,
|
| 257 |
+
"step": 17000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.54,
|
| 261 |
+
"grad_norm": 1.611952543258667,
|
| 262 |
+
"learning_rate": 3.4609972737666e-05,
|
| 263 |
+
"loss": 0.5316,
|
| 264 |
+
"step": 17500
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.58,
|
| 268 |
+
"grad_norm": 2.74088978767395,
|
| 269 |
+
"learning_rate": 3.417025767302788e-05,
|
| 270 |
+
"loss": 0.5417,
|
| 271 |
+
"step": 18000
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 1.63,
|
| 275 |
+
"grad_norm": 1.620376706123352,
|
| 276 |
+
"learning_rate": 3.373054260838976e-05,
|
| 277 |
+
"loss": 0.5291,
|
| 278 |
+
"step": 18500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.67,
|
| 282 |
+
"grad_norm": 1.3796972036361694,
|
| 283 |
+
"learning_rate": 3.329082754375165e-05,
|
| 284 |
+
"loss": 0.536,
|
| 285 |
+
"step": 19000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.71,
|
| 289 |
+
"grad_norm": 2.2904984951019287,
|
| 290 |
+
"learning_rate": 3.2851112479113535e-05,
|
| 291 |
+
"loss": 0.5188,
|
| 292 |
+
"step": 19500
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 1.76,
|
| 296 |
+
"grad_norm": 3.1823525428771973,
|
| 297 |
+
"learning_rate": 3.241139741447542e-05,
|
| 298 |
+
"loss": 0.5252,
|
| 299 |
+
"step": 20000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.8,
|
| 303 |
+
"grad_norm": 1.8540767431259155,
|
| 304 |
+
"learning_rate": 3.197168234983731e-05,
|
| 305 |
+
"loss": 0.532,
|
| 306 |
+
"step": 20500
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.85,
|
| 310 |
+
"grad_norm": 2.533015251159668,
|
| 311 |
+
"learning_rate": 3.153196728519919e-05,
|
| 312 |
+
"loss": 0.5316,
|
| 313 |
+
"step": 21000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.89,
|
| 317 |
+
"grad_norm": 1.5881567001342773,
|
| 318 |
+
"learning_rate": 3.109225222056108e-05,
|
| 319 |
+
"loss": 0.5338,
|
| 320 |
+
"step": 21500
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.93,
|
| 324 |
+
"grad_norm": 1.6812840700149536,
|
| 325 |
+
"learning_rate": 3.065253715592296e-05,
|
| 326 |
+
"loss": 0.5298,
|
| 327 |
+
"step": 22000
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.98,
|
| 331 |
+
"grad_norm": 2.3194057941436768,
|
| 332 |
+
"learning_rate": 3.021282209128485e-05,
|
| 333 |
+
"loss": 0.5277,
|
| 334 |
+
"step": 22500
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 2.0,
|
| 338 |
+
"eval_combined_score": 0.7885976005742216,
|
| 339 |
+
"eval_f1": 0.7885976005742216,
|
| 340 |
+
"eval_loss": 0.3457885980606079,
|
| 341 |
+
"eval_runtime": 35.6671,
|
| 342 |
+
"eval_samples_per_second": 1133.538,
|
| 343 |
+
"eval_steps_per_second": 4.43,
|
| 344 |
+
"step": 22742
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.02,
|
| 348 |
+
"grad_norm": 2.574708938598633,
|
| 349 |
+
"learning_rate": 2.9773107026646735e-05,
|
| 350 |
+
"loss": 0.5285,
|
| 351 |
+
"step": 23000
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 2.07,
|
| 355 |
+
"grad_norm": 2.895447254180908,
|
| 356 |
+
"learning_rate": 2.933339196200862e-05,
|
| 357 |
+
"loss": 0.513,
|
| 358 |
+
"step": 23500
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 2.11,
|
| 362 |
+
"grad_norm": 2.720695972442627,
|
| 363 |
+
"learning_rate": 2.8893676897370504e-05,
|
| 364 |
+
"loss": 0.5252,
|
| 365 |
+
"step": 24000
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 2.15,
|
| 369 |
+
"grad_norm": 2.181859016418457,
|
| 370 |
+
"learning_rate": 2.845396183273239e-05,
|
| 371 |
+
"loss": 0.5148,
|
| 372 |
+
"step": 24500
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 2.2,
|
| 376 |
+
"grad_norm": 1.2445052862167358,
|
| 377 |
+
"learning_rate": 2.8014246768094277e-05,
|
| 378 |
+
"loss": 0.5174,
|
| 379 |
+
"step": 25000
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 2.24,
|
| 383 |
+
"grad_norm": 2.124485731124878,
|
| 384 |
+
"learning_rate": 2.7574531703456163e-05,
|
| 385 |
+
"loss": 0.5052,
|
| 386 |
+
"step": 25500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 2.29,
|
| 390 |
+
"grad_norm": 1.8577401638031006,
|
| 391 |
+
"learning_rate": 2.7134816638818046e-05,
|
| 392 |
+
"loss": 0.5134,
|
| 393 |
+
"step": 26000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 2.33,
|
| 397 |
+
"grad_norm": 3.3754642009735107,
|
| 398 |
+
"learning_rate": 2.6695101574179932e-05,
|
| 399 |
+
"loss": 0.5106,
|
| 400 |
+
"step": 26500
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 2.37,
|
| 404 |
+
"grad_norm": 1.662766695022583,
|
| 405 |
+
"learning_rate": 2.625538650954182e-05,
|
| 406 |
+
"loss": 0.5131,
|
| 407 |
+
"step": 27000
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 2.42,
|
| 411 |
+
"grad_norm": 2.0520458221435547,
|
| 412 |
+
"learning_rate": 2.5815671444903705e-05,
|
| 413 |
+
"loss": 0.5048,
|
| 414 |
+
"step": 27500
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 2.46,
|
| 418 |
+
"grad_norm": 2.1979711055755615,
|
| 419 |
+
"learning_rate": 2.5375956380265588e-05,
|
| 420 |
+
"loss": 0.5161,
|
| 421 |
+
"step": 28000
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 2.51,
|
| 425 |
+
"grad_norm": 1.9927352666854858,
|
| 426 |
+
"learning_rate": 2.4936241315627474e-05,
|
| 427 |
+
"loss": 0.5083,
|
| 428 |
+
"step": 28500
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 2.55,
|
| 432 |
+
"grad_norm": 1.1663730144500732,
|
| 433 |
+
"learning_rate": 2.449652625098936e-05,
|
| 434 |
+
"loss": 0.5131,
|
| 435 |
+
"step": 29000
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 2.59,
|
| 439 |
+
"grad_norm": 1.8424278497695923,
|
| 440 |
+
"learning_rate": 2.4056811186351246e-05,
|
| 441 |
+
"loss": 0.5076,
|
| 442 |
+
"step": 29500
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 2.64,
|
| 446 |
+
"grad_norm": 1.6461939811706543,
|
| 447 |
+
"learning_rate": 2.3617096121713133e-05,
|
| 448 |
+
"loss": 0.5064,
|
| 449 |
+
"step": 30000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 2.68,
|
| 453 |
+
"grad_norm": 2.1023998260498047,
|
| 454 |
+
"learning_rate": 2.317738105707502e-05,
|
| 455 |
+
"loss": 0.5085,
|
| 456 |
+
"step": 30500
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 2.73,
|
| 460 |
+
"grad_norm": 2.8294382095336914,
|
| 461 |
+
"learning_rate": 2.27376659924369e-05,
|
| 462 |
+
"loss": 0.503,
|
| 463 |
+
"step": 31000
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 2.77,
|
| 467 |
+
"grad_norm": 2.6910927295684814,
|
| 468 |
+
"learning_rate": 2.2297950927798788e-05,
|
| 469 |
+
"loss": 0.5075,
|
| 470 |
+
"step": 31500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 2.81,
|
| 474 |
+
"grad_norm": 1.7387686967849731,
|
| 475 |
+
"learning_rate": 2.1858235863160674e-05,
|
| 476 |
+
"loss": 0.5057,
|
| 477 |
+
"step": 32000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 2.86,
|
| 481 |
+
"grad_norm": 2.62984037399292,
|
| 482 |
+
"learning_rate": 2.141852079852256e-05,
|
| 483 |
+
"loss": 0.5058,
|
| 484 |
+
"step": 32500
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 2.9,
|
| 488 |
+
"grad_norm": 2.4338366985321045,
|
| 489 |
+
"learning_rate": 2.0978805733884443e-05,
|
| 490 |
+
"loss": 0.5105,
|
| 491 |
+
"step": 33000
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 2.95,
|
| 495 |
+
"grad_norm": 1.7565324306488037,
|
| 496 |
+
"learning_rate": 2.053909066924633e-05,
|
| 497 |
+
"loss": 0.5046,
|
| 498 |
+
"step": 33500
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 2.99,
|
| 502 |
+
"grad_norm": 1.6135342121124268,
|
| 503 |
+
"learning_rate": 2.0099375604608216e-05,
|
| 504 |
+
"loss": 0.5071,
|
| 505 |
+
"step": 34000
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 3.0,
|
| 509 |
+
"eval_combined_score": 0.7936085219707057,
|
| 510 |
+
"eval_f1": 0.7936085219707057,
|
| 511 |
+
"eval_loss": 0.3366371691226959,
|
| 512 |
+
"eval_runtime": 35.2824,
|
| 513 |
+
"eval_samples_per_second": 1145.898,
|
| 514 |
+
"eval_steps_per_second": 4.478,
|
| 515 |
+
"step": 34113
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 3.03,
|
| 519 |
+
"grad_norm": 3.032174587249756,
|
| 520 |
+
"learning_rate": 1.9659660539970102e-05,
|
| 521 |
+
"loss": 0.4951,
|
| 522 |
+
"step": 34500
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 3.08,
|
| 526 |
+
"grad_norm": 2.865243673324585,
|
| 527 |
+
"learning_rate": 1.9219945475331985e-05,
|
| 528 |
+
"loss": 0.4966,
|
| 529 |
+
"step": 35000
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 3.12,
|
| 533 |
+
"grad_norm": 1.8979029655456543,
|
| 534 |
+
"learning_rate": 1.878023041069387e-05,
|
| 535 |
+
"loss": 0.4971,
|
| 536 |
+
"step": 35500
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 3.17,
|
| 540 |
+
"grad_norm": 2.6854591369628906,
|
| 541 |
+
"learning_rate": 1.8340515346055757e-05,
|
| 542 |
+
"loss": 0.4928,
|
| 543 |
+
"step": 36000
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 3.21,
|
| 547 |
+
"grad_norm": 2.190274953842163,
|
| 548 |
+
"learning_rate": 1.7900800281417643e-05,
|
| 549 |
+
"loss": 0.499,
|
| 550 |
+
"step": 36500
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 3.25,
|
| 554 |
+
"grad_norm": 2.532625913619995,
|
| 555 |
+
"learning_rate": 1.7461085216779526e-05,
|
| 556 |
+
"loss": 0.4995,
|
| 557 |
+
"step": 37000
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 3.3,
|
| 561 |
+
"grad_norm": 2.1517629623413086,
|
| 562 |
+
"learning_rate": 1.7021370152141413e-05,
|
| 563 |
+
"loss": 0.493,
|
| 564 |
+
"step": 37500
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 3.34,
|
| 568 |
+
"grad_norm": 2.9633235931396484,
|
| 569 |
+
"learning_rate": 1.65816550875033e-05,
|
| 570 |
+
"loss": 0.5014,
|
| 571 |
+
"step": 38000
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 3.39,
|
| 575 |
+
"grad_norm": 2.1532862186431885,
|
| 576 |
+
"learning_rate": 1.6141940022865185e-05,
|
| 577 |
+
"loss": 0.499,
|
| 578 |
+
"step": 38500
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 3.43,
|
| 582 |
+
"grad_norm": 2.8993899822235107,
|
| 583 |
+
"learning_rate": 1.5702224958227068e-05,
|
| 584 |
+
"loss": 0.4934,
|
| 585 |
+
"step": 39000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 3.47,
|
| 589 |
+
"grad_norm": 4.290128231048584,
|
| 590 |
+
"learning_rate": 1.5262509893588954e-05,
|
| 591 |
+
"loss": 0.4923,
|
| 592 |
+
"step": 39500
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 3.52,
|
| 596 |
+
"grad_norm": 1.6720905303955078,
|
| 597 |
+
"learning_rate": 1.482279482895084e-05,
|
| 598 |
+
"loss": 0.4873,
|
| 599 |
+
"step": 40000
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 3.56,
|
| 603 |
+
"grad_norm": 2.33063006401062,
|
| 604 |
+
"learning_rate": 1.4383079764312727e-05,
|
| 605 |
+
"loss": 0.4979,
|
| 606 |
+
"step": 40500
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 3.61,
|
| 610 |
+
"grad_norm": 1.8272016048431396,
|
| 611 |
+
"learning_rate": 1.3943364699674611e-05,
|
| 612 |
+
"loss": 0.4912,
|
| 613 |
+
"step": 41000
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 3.65,
|
| 617 |
+
"grad_norm": 1.9617942571640015,
|
| 618 |
+
"learning_rate": 1.3503649635036497e-05,
|
| 619 |
+
"loss": 0.5045,
|
| 620 |
+
"step": 41500
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 3.69,
|
| 624 |
+
"grad_norm": 1.7576007843017578,
|
| 625 |
+
"learning_rate": 1.3063934570398382e-05,
|
| 626 |
+
"loss": 0.4834,
|
| 627 |
+
"step": 42000
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 3.74,
|
| 631 |
+
"grad_norm": 3.1541335582733154,
|
| 632 |
+
"learning_rate": 1.2624219505760268e-05,
|
| 633 |
+
"loss": 0.4893,
|
| 634 |
+
"step": 42500
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 3.78,
|
| 638 |
+
"grad_norm": 2.4728527069091797,
|
| 639 |
+
"learning_rate": 1.2184504441122153e-05,
|
| 640 |
+
"loss": 0.4908,
|
| 641 |
+
"step": 43000
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 3.83,
|
| 645 |
+
"grad_norm": 1.833243727684021,
|
| 646 |
+
"learning_rate": 1.1744789376484039e-05,
|
| 647 |
+
"loss": 0.4905,
|
| 648 |
+
"step": 43500
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 3.87,
|
| 652 |
+
"grad_norm": 2.1114351749420166,
|
| 653 |
+
"learning_rate": 1.1305074311845925e-05,
|
| 654 |
+
"loss": 0.4971,
|
| 655 |
+
"step": 44000
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 3.91,
|
| 659 |
+
"grad_norm": 2.988950490951538,
|
| 660 |
+
"learning_rate": 1.086535924720781e-05,
|
| 661 |
+
"loss": 0.4954,
|
| 662 |
+
"step": 44500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 3.96,
|
| 666 |
+
"grad_norm": 1.7815330028533936,
|
| 667 |
+
"learning_rate": 1.0425644182569696e-05,
|
| 668 |
+
"loss": 0.4861,
|
| 669 |
+
"step": 45000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 4.0,
|
| 673 |
+
"eval_combined_score": 0.7983325743510702,
|
| 674 |
+
"eval_f1": 0.7983325743510702,
|
| 675 |
+
"eval_loss": 0.329210489988327,
|
| 676 |
+
"eval_runtime": 36.1124,
|
| 677 |
+
"eval_samples_per_second": 1119.561,
|
| 678 |
+
"eval_steps_per_second": 4.375,
|
| 679 |
+
"step": 45484
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 4.0,
|
| 683 |
+
"grad_norm": 1.9500830173492432,
|
| 684 |
+
"learning_rate": 9.98592911793158e-06,
|
| 685 |
+
"loss": 0.4975,
|
| 686 |
+
"step": 45500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 4.05,
|
| 690 |
+
"grad_norm": 2.2637670040130615,
|
| 691 |
+
"learning_rate": 9.546214053293467e-06,
|
| 692 |
+
"loss": 0.4919,
|
| 693 |
+
"step": 46000
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 4.09,
|
| 697 |
+
"grad_norm": 2.1222739219665527,
|
| 698 |
+
"learning_rate": 9.106498988655351e-06,
|
| 699 |
+
"loss": 0.4891,
|
| 700 |
+
"step": 46500
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 4.13,
|
| 704 |
+
"grad_norm": 2.9774413108825684,
|
| 705 |
+
"learning_rate": 8.666783924017237e-06,
|
| 706 |
+
"loss": 0.4823,
|
| 707 |
+
"step": 47000
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 4.18,
|
| 711 |
+
"grad_norm": 1.4093037843704224,
|
| 712 |
+
"learning_rate": 8.227068859379122e-06,
|
| 713 |
+
"loss": 0.4945,
|
| 714 |
+
"step": 47500
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 4.22,
|
| 718 |
+
"grad_norm": 2.2752432823181152,
|
| 719 |
+
"learning_rate": 7.787353794741008e-06,
|
| 720 |
+
"loss": 0.4803,
|
| 721 |
+
"step": 48000
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 4.27,
|
| 725 |
+
"grad_norm": 3.996915340423584,
|
| 726 |
+
"learning_rate": 7.347638730102893e-06,
|
| 727 |
+
"loss": 0.4786,
|
| 728 |
+
"step": 48500
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 4.31,
|
| 732 |
+
"grad_norm": 2.5842177867889404,
|
| 733 |
+
"learning_rate": 6.907923665464779e-06,
|
| 734 |
+
"loss": 0.4902,
|
| 735 |
+
"step": 49000
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 4.35,
|
| 739 |
+
"grad_norm": 1.688774824142456,
|
| 740 |
+
"learning_rate": 6.468208600826664e-06,
|
| 741 |
+
"loss": 0.4828,
|
| 742 |
+
"step": 49500
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 4.4,
|
| 746 |
+
"grad_norm": 0.9284757375717163,
|
| 747 |
+
"learning_rate": 6.02849353618855e-06,
|
| 748 |
+
"loss": 0.4737,
|
| 749 |
+
"step": 50000
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 4.44,
|
| 753 |
+
"grad_norm": 2.362175226211548,
|
| 754 |
+
"learning_rate": 5.588778471550435e-06,
|
| 755 |
+
"loss": 0.4893,
|
| 756 |
+
"step": 50500
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 4.49,
|
| 760 |
+
"grad_norm": 2.7047996520996094,
|
| 761 |
+
"learning_rate": 5.149063406912321e-06,
|
| 762 |
+
"loss": 0.4824,
|
| 763 |
+
"step": 51000
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 4.53,
|
| 767 |
+
"grad_norm": 2.2833824157714844,
|
| 768 |
+
"learning_rate": 4.709348342274207e-06,
|
| 769 |
+
"loss": 0.4862,
|
| 770 |
+
"step": 51500
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 4.57,
|
| 774 |
+
"grad_norm": 2.7893359661102295,
|
| 775 |
+
"learning_rate": 4.269633277636092e-06,
|
| 776 |
+
"loss": 0.4706,
|
| 777 |
+
"step": 52000
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 4.62,
|
| 781 |
+
"grad_norm": 1.4342833757400513,
|
| 782 |
+
"learning_rate": 3.8299182129979776e-06,
|
| 783 |
+
"loss": 0.4892,
|
| 784 |
+
"step": 52500
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 4.66,
|
| 788 |
+
"grad_norm": 1.9848226308822632,
|
| 789 |
+
"learning_rate": 3.3902031483598625e-06,
|
| 790 |
+
"loss": 0.4876,
|
| 791 |
+
"step": 53000
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 4.7,
|
| 795 |
+
"grad_norm": 2.6507408618927,
|
| 796 |
+
"learning_rate": 2.9504880837217483e-06,
|
| 797 |
+
"loss": 0.4764,
|
| 798 |
+
"step": 53500
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 4.75,
|
| 802 |
+
"grad_norm": 2.80248761177063,
|
| 803 |
+
"learning_rate": 2.5107730190836337e-06,
|
| 804 |
+
"loss": 0.4847,
|
| 805 |
+
"step": 54000
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 4.79,
|
| 809 |
+
"grad_norm": 2.777669668197632,
|
| 810 |
+
"learning_rate": 2.0710579544455195e-06,
|
| 811 |
+
"loss": 0.4924,
|
| 812 |
+
"step": 54500
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 4.84,
|
| 816 |
+
"grad_norm": 2.0418293476104736,
|
| 817 |
+
"learning_rate": 1.6313428898074047e-06,
|
| 818 |
+
"loss": 0.485,
|
| 819 |
+
"step": 55000
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 4.88,
|
| 823 |
+
"grad_norm": 2.3356010913848877,
|
| 824 |
+
"learning_rate": 1.1916278251692903e-06,
|
| 825 |
+
"loss": 0.4844,
|
| 826 |
+
"step": 55500
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 4.92,
|
| 830 |
+
"grad_norm": 3.416121244430542,
|
| 831 |
+
"learning_rate": 7.519127605311758e-07,
|
| 832 |
+
"loss": 0.4877,
|
| 833 |
+
"step": 56000
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 4.97,
|
| 837 |
+
"grad_norm": 1.7180390357971191,
|
| 838 |
+
"learning_rate": 3.121976958930613e-07,
|
| 839 |
+
"loss": 0.4822,
|
| 840 |
+
"step": 56500
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 5.0,
|
| 844 |
+
"eval_combined_score": 0.8002366534419155,
|
| 845 |
+
"eval_f1": 0.8002366534419155,
|
| 846 |
+
"eval_loss": 0.3343241214752197,
|
| 847 |
+
"eval_runtime": 35.6088,
|
| 848 |
+
"eval_samples_per_second": 1135.394,
|
| 849 |
+
"eval_steps_per_second": 4.437,
|
| 850 |
+
"step": 56855
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 5.0,
|
| 854 |
+
"step": 56855,
|
| 855 |
+
"total_flos": 0.0,
|
| 856 |
+
"train_loss": 0.5264342698119119,
|
| 857 |
+
"train_runtime": 6200.063,
|
| 858 |
+
"train_samples_per_second": 293.421,
|
| 859 |
+
"train_steps_per_second": 9.17
|
| 860 |
+
}
|
| 861 |
+
],
|
| 862 |
+
"logging_steps": 500,
|
| 863 |
+
"max_steps": 56855,
|
| 864 |
+
"num_input_tokens_seen": 0,
|
| 865 |
+
"num_train_epochs": 5,
|
| 866 |
+
"save_steps": 500,
|
| 867 |
+
"total_flos": 0.0,
|
| 868 |
+
"train_batch_size": 32,
|
| 869 |
+
"trial_name": null,
|
| 870 |
+
"trial_params": null
|
| 871 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73e7523831c0e1d40c6ef44a3e93d17d76597a15d0ab019cc9497a5b520625f6
|
| 3 |
+
size 5816
|
transfer_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eval_combined_score": 0.751798561151079,
|
| 3 |
+
"eval_f1": 0.751798561151079,
|
| 4 |
+
"eval_loss": 0.7870423793792725,
|
| 5 |
+
"eval_runtime": 1.8495,
|
| 6 |
+
"eval_samples_per_second": 220.598,
|
| 7 |
+
"eval_steps_per_second": 1.081
|
| 8 |
+
}
|