Upload folder using huggingface_hub
Browse files- all_results.json +31 -0
- mnli-m_results.json +8 -0
- mnli-mm_results.json +8 -0
- ood_results.json +11 -0
- pred_mnli-m.npz.npy +3 -0
- pred_mnli-mm.npz.npy +3 -0
- pred_ood.npz.npy +3 -0
- pred_transfer.npz.npy +3 -0
- pytorch_model.bin +3 -0
- rep_mnli-m.pt +3 -0
- rep_mnli-mm.pt +3 -0
- rep_ood.pt +3 -0
- special_tokens_map.json +125 -0
- spiece.model +3 -0
- test_results.json +17 -0
- tokenizer.json +0 -0
- tokenizer_config.json +938 -0
- train_results.json +7 -0
- trainer_state.json +934 -0
- training_args.bin +3 -0
- transfer_results.json +8 -0
all_results.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"ave/id": 0.6183582919486497,
|
| 3 |
+
"ave/ood": 0.49783333333333335,
|
| 4 |
+
"ave/transfer": 0.5572038203617151,
|
| 5 |
+
"epoch": 5.0,
|
| 6 |
+
"eval_accuracy": 0.5572038203617151,
|
| 7 |
+
"eval_combined_score": 0.5572038203617151,
|
| 8 |
+
"eval_constituent_accuracy": 0.5011,
|
| 9 |
+
"eval_lexical_overlap_accuracy": 0.4999,
|
| 10 |
+
"eval_loss": 0.9355756640434265,
|
| 11 |
+
"eval_runtime": 7.4268,
|
| 12 |
+
"eval_samples_per_second": 1325.196,
|
| 13 |
+
"eval_steps_per_second": 5.251,
|
| 14 |
+
"eval_subsequence_accuracy": 0.4925,
|
| 15 |
+
"gap/constituent": 0.11725829194864967,
|
| 16 |
+
"gap/lexical_overlap": 0.11845829194864965,
|
| 17 |
+
"gap/ood": 0.12052495861531631,
|
| 18 |
+
"gap/subsequence": 0.12585829194864967,
|
| 19 |
+
"gap/transfer": 0.061154471586934545,
|
| 20 |
+
"mnli-m": 0.6116148751910341,
|
| 21 |
+
"mnli-mm": 0.6251017087062652,
|
| 22 |
+
"ood": 0.49783333333333335,
|
| 23 |
+
"ood/constituent": 0.5011,
|
| 24 |
+
"ood/lexical_overlap": 0.4999,
|
| 25 |
+
"ood/subsequence": 0.4925,
|
| 26 |
+
"train_loss": 1.1215235922762437,
|
| 27 |
+
"train_runtime": 4186.3943,
|
| 28 |
+
"train_samples_per_second": 469.022,
|
| 29 |
+
"train_steps_per_second": 14.657,
|
| 30 |
+
"transfer": 0.5572038203617151
|
| 31 |
+
}
|
mnli-m_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eval_accuracy": 0.6116148751910341,
|
| 3 |
+
"eval_combined_score": 0.6116148751910341,
|
| 4 |
+
"eval_loss": 0.8905634880065918,
|
| 5 |
+
"eval_runtime": 7.7559,
|
| 6 |
+
"eval_samples_per_second": 1265.494,
|
| 7 |
+
"eval_steps_per_second": 5.028
|
| 8 |
+
}
|
mnli-mm_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eval_accuracy": 0.6251017087062652,
|
| 3 |
+
"eval_combined_score": 0.6251017087062652,
|
| 4 |
+
"eval_loss": 0.8752594590187073,
|
| 5 |
+
"eval_runtime": 7.3898,
|
| 6 |
+
"eval_samples_per_second": 1330.487,
|
| 7 |
+
"eval_steps_per_second": 5.278
|
| 8 |
+
}
|
ood_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eval_accuracy": 0.49783333333333335,
|
| 3 |
+
"eval_combined_score": 0.49783333333333335,
|
| 4 |
+
"eval_constituent_accuracy": 0.5011,
|
| 5 |
+
"eval_lexical_overlap_accuracy": 0.4999,
|
| 6 |
+
"eval_loss": 1.2784428596496582,
|
| 7 |
+
"eval_runtime": 19.2146,
|
| 8 |
+
"eval_samples_per_second": 1561.311,
|
| 9 |
+
"eval_steps_per_second": 6.141,
|
| 10 |
+
"eval_subsequence_accuracy": 0.4925
|
| 11 |
+
}
|
pred_mnli-m.npz.npy
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce6812b15315b0794b9a871c867284613e8383f5ca6864513c331c57a7251007
|
| 3 |
+
size 117908
|
pred_mnli-mm.npz.npy
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42aaf4a006cd301d95b4b06c09a947f1d1cc15b84d3413c75e477bd34b15e63e
|
| 3 |
+
size 118112
|
pred_ood.npz.npy
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:241f2f5e715a90f4a9e83cd5633aab95afb43a2121b011c87985c1787184a187
|
| 3 |
+
size 360128
|
pred_transfer.npz.npy
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e70260e1dde009bcbbf621bf39b332a751d3577bf57859a9eef998d2b9f8cc3
|
| 3 |
+
size 118232
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bde620ca0501ed8f6269ee3837ad0565d6e113bcfe0fa50326d8804444bf9d25
|
| 3 |
+
size 95770018
|
rep_mnli-m.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b57163b1d5697a653dfac1a75f288403c44b6dc3465390cbca55f0658ffe32b2
|
| 3 |
+
size 80426082
|
rep_mnli-mm.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a85be4a5f23b4fcb17606cabb56d38833470c37a9b4f8ae896c4ba738cdce478
|
| 3 |
+
size 80565428
|
rep_ood.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d0e7a910a2f709b794d34b501e487aabb502d9f823f5455fdba89fb44e59ece
|
| 3 |
+
size 245823706
|
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 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"ave/id": 0.6183582919486497,
|
| 3 |
+
"ave/ood": 0.49783333333333335,
|
| 4 |
+
"ave/transfer": 0.5572038203617151,
|
| 5 |
+
"gap/constituent": 0.11725829194864967,
|
| 6 |
+
"gap/lexical_overlap": 0.11845829194864965,
|
| 7 |
+
"gap/ood": 0.12052495861531631,
|
| 8 |
+
"gap/subsequence": 0.12585829194864967,
|
| 9 |
+
"gap/transfer": 0.061154471586934545,
|
| 10 |
+
"mnli-m": 0.6116148751910341,
|
| 11 |
+
"mnli-mm": 0.6251017087062652,
|
| 12 |
+
"ood": 0.49783333333333335,
|
| 13 |
+
"ood/constituent": 0.5011,
|
| 14 |
+
"ood/lexical_overlap": 0.4999,
|
| 15 |
+
"ood/subsequence": 0.4925,
|
| 16 |
+
"transfer": 0.5572038203617151
|
| 17 |
+
}
|
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": 1.1215235922762437,
|
| 4 |
+
"train_runtime": 4186.3943,
|
| 5 |
+
"train_samples_per_second": 469.022,
|
| 6 |
+
"train_steps_per_second": 14.657
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,934 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6116148751910341,
|
| 3 |
+
"best_model_checkpoint": "outputs/t5-tiny/weak_tiny_poe/mnli_21/checkpoint-61360",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 61360,
|
| 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": 1.0741028785705566,
|
| 14 |
+
"learning_rate": 4.9592568448500655e-05,
|
| 15 |
+
"loss": 1.2614,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.08,
|
| 20 |
+
"grad_norm": 0.6355718374252319,
|
| 21 |
+
"learning_rate": 4.918513689700131e-05,
|
| 22 |
+
"loss": 1.2516,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.12,
|
| 27 |
+
"grad_norm": 0.8562185168266296,
|
| 28 |
+
"learning_rate": 4.877770534550195e-05,
|
| 29 |
+
"loss": 1.2444,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.16,
|
| 34 |
+
"grad_norm": 1.435200810432434,
|
| 35 |
+
"learning_rate": 4.8370273794002606e-05,
|
| 36 |
+
"loss": 1.2294,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.2,
|
| 41 |
+
"grad_norm": 2.3618035316467285,
|
| 42 |
+
"learning_rate": 4.7962842242503265e-05,
|
| 43 |
+
"loss": 1.2231,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.24,
|
| 48 |
+
"grad_norm": 1.9568185806274414,
|
| 49 |
+
"learning_rate": 4.755541069100392e-05,
|
| 50 |
+
"loss": 1.2171,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.29,
|
| 55 |
+
"grad_norm": 2.025542974472046,
|
| 56 |
+
"learning_rate": 4.7147979139504564e-05,
|
| 57 |
+
"loss": 1.2158,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.33,
|
| 62 |
+
"grad_norm": 1.468313217163086,
|
| 63 |
+
"learning_rate": 4.6740547588005216e-05,
|
| 64 |
+
"loss": 1.1951,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.37,
|
| 69 |
+
"grad_norm": 2.4365932941436768,
|
| 70 |
+
"learning_rate": 4.633311603650587e-05,
|
| 71 |
+
"loss": 1.203,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.41,
|
| 76 |
+
"grad_norm": 1.7032877206802368,
|
| 77 |
+
"learning_rate": 4.592568448500652e-05,
|
| 78 |
+
"loss": 1.1952,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.45,
|
| 83 |
+
"grad_norm": 2.0673813819885254,
|
| 84 |
+
"learning_rate": 4.5518252933507174e-05,
|
| 85 |
+
"loss": 1.1958,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.49,
|
| 90 |
+
"grad_norm": 1.7614480257034302,
|
| 91 |
+
"learning_rate": 4.511082138200782e-05,
|
| 92 |
+
"loss": 1.1933,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.53,
|
| 97 |
+
"grad_norm": 3.3648741245269775,
|
| 98 |
+
"learning_rate": 4.470338983050847e-05,
|
| 99 |
+
"loss": 1.1862,
|
| 100 |
+
"step": 6500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.57,
|
| 104 |
+
"grad_norm": 1.8836809396743774,
|
| 105 |
+
"learning_rate": 4.429595827900913e-05,
|
| 106 |
+
"loss": 1.1926,
|
| 107 |
+
"step": 7000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.61,
|
| 111 |
+
"grad_norm": 2.070249080657959,
|
| 112 |
+
"learning_rate": 4.3888526727509784e-05,
|
| 113 |
+
"loss": 1.1841,
|
| 114 |
+
"step": 7500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.65,
|
| 118 |
+
"grad_norm": 2.4235424995422363,
|
| 119 |
+
"learning_rate": 4.348109517601043e-05,
|
| 120 |
+
"loss": 1.1755,
|
| 121 |
+
"step": 8000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.69,
|
| 125 |
+
"grad_norm": 1.2773147821426392,
|
| 126 |
+
"learning_rate": 4.307366362451108e-05,
|
| 127 |
+
"loss": 1.1906,
|
| 128 |
+
"step": 8500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.73,
|
| 132 |
+
"grad_norm": 4.709882736206055,
|
| 133 |
+
"learning_rate": 4.2666232073011735e-05,
|
| 134 |
+
"loss": 1.1683,
|
| 135 |
+
"step": 9000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.77,
|
| 139 |
+
"grad_norm": 2.064504384994507,
|
| 140 |
+
"learning_rate": 4.225880052151239e-05,
|
| 141 |
+
"loss": 1.1703,
|
| 142 |
+
"step": 9500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.81,
|
| 146 |
+
"grad_norm": 2.670032262802124,
|
| 147 |
+
"learning_rate": 4.185136897001304e-05,
|
| 148 |
+
"loss": 1.1622,
|
| 149 |
+
"step": 10000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.86,
|
| 153 |
+
"grad_norm": 1.9821618795394897,
|
| 154 |
+
"learning_rate": 4.144393741851369e-05,
|
| 155 |
+
"loss": 1.1571,
|
| 156 |
+
"step": 10500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.9,
|
| 160 |
+
"grad_norm": 2.3936009407043457,
|
| 161 |
+
"learning_rate": 4.103650586701434e-05,
|
| 162 |
+
"loss": 1.1616,
|
| 163 |
+
"step": 11000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.94,
|
| 167 |
+
"grad_norm": 2.637899398803711,
|
| 168 |
+
"learning_rate": 4.0629074315515e-05,
|
| 169 |
+
"loss": 1.1677,
|
| 170 |
+
"step": 11500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.98,
|
| 174 |
+
"grad_norm": 2.4801619052886963,
|
| 175 |
+
"learning_rate": 4.022164276401565e-05,
|
| 176 |
+
"loss": 1.1514,
|
| 177 |
+
"step": 12000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.0,
|
| 181 |
+
"eval_accuracy": 0.4945491594498217,
|
| 182 |
+
"eval_combined_score": 0.4945491594498217,
|
| 183 |
+
"eval_loss": 1.0730257034301758,
|
| 184 |
+
"eval_runtime": 4.8512,
|
| 185 |
+
"eval_samples_per_second": 2023.214,
|
| 186 |
+
"eval_steps_per_second": 8.039,
|
| 187 |
+
"step": 12272
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 1.02,
|
| 191 |
+
"grad_norm": 2.4936630725860596,
|
| 192 |
+
"learning_rate": 3.98142112125163e-05,
|
| 193 |
+
"loss": 1.1492,
|
| 194 |
+
"step": 12500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.06,
|
| 198 |
+
"grad_norm": 2.4125094413757324,
|
| 199 |
+
"learning_rate": 3.940677966101695e-05,
|
| 200 |
+
"loss": 1.1456,
|
| 201 |
+
"step": 13000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.1,
|
| 205 |
+
"grad_norm": 1.6422048807144165,
|
| 206 |
+
"learning_rate": 3.89993481095176e-05,
|
| 207 |
+
"loss": 1.1404,
|
| 208 |
+
"step": 13500
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.14,
|
| 212 |
+
"grad_norm": 2.566889762878418,
|
| 213 |
+
"learning_rate": 3.8591916558018254e-05,
|
| 214 |
+
"loss": 1.145,
|
| 215 |
+
"step": 14000
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.18,
|
| 219 |
+
"grad_norm": 2.594127893447876,
|
| 220 |
+
"learning_rate": 3.818448500651891e-05,
|
| 221 |
+
"loss": 1.1498,
|
| 222 |
+
"step": 14500
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 1.22,
|
| 226 |
+
"grad_norm": 2.0145516395568848,
|
| 227 |
+
"learning_rate": 3.777705345501956e-05,
|
| 228 |
+
"loss": 1.1434,
|
| 229 |
+
"step": 15000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 1.26,
|
| 233 |
+
"grad_norm": 2.318466901779175,
|
| 234 |
+
"learning_rate": 3.7369621903520205e-05,
|
| 235 |
+
"loss": 1.1339,
|
| 236 |
+
"step": 15500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.3,
|
| 240 |
+
"grad_norm": 2.0532548427581787,
|
| 241 |
+
"learning_rate": 3.6962190352020865e-05,
|
| 242 |
+
"loss": 1.1474,
|
| 243 |
+
"step": 16000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.34,
|
| 247 |
+
"grad_norm": 2.050147294998169,
|
| 248 |
+
"learning_rate": 3.655475880052152e-05,
|
| 249 |
+
"loss": 1.1398,
|
| 250 |
+
"step": 16500
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.39,
|
| 254 |
+
"grad_norm": 2.1561617851257324,
|
| 255 |
+
"learning_rate": 3.614732724902217e-05,
|
| 256 |
+
"loss": 1.139,
|
| 257 |
+
"step": 17000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.43,
|
| 261 |
+
"grad_norm": 2.1412413120269775,
|
| 262 |
+
"learning_rate": 3.5739895697522816e-05,
|
| 263 |
+
"loss": 1.1429,
|
| 264 |
+
"step": 17500
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.47,
|
| 268 |
+
"grad_norm": 1.999888300895691,
|
| 269 |
+
"learning_rate": 3.533246414602347e-05,
|
| 270 |
+
"loss": 1.1335,
|
| 271 |
+
"step": 18000
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 1.51,
|
| 275 |
+
"grad_norm": 3.487457275390625,
|
| 276 |
+
"learning_rate": 3.492503259452412e-05,
|
| 277 |
+
"loss": 1.134,
|
| 278 |
+
"step": 18500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.55,
|
| 282 |
+
"grad_norm": 2.8775036334991455,
|
| 283 |
+
"learning_rate": 3.451760104302477e-05,
|
| 284 |
+
"loss": 1.1441,
|
| 285 |
+
"step": 19000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.59,
|
| 289 |
+
"grad_norm": 2.7384023666381836,
|
| 290 |
+
"learning_rate": 3.4110169491525426e-05,
|
| 291 |
+
"loss": 1.1341,
|
| 292 |
+
"step": 19500
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 1.63,
|
| 296 |
+
"grad_norm": 3.0970985889434814,
|
| 297 |
+
"learning_rate": 3.370273794002607e-05,
|
| 298 |
+
"loss": 1.1268,
|
| 299 |
+
"step": 20000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.67,
|
| 303 |
+
"grad_norm": 3.6261987686157227,
|
| 304 |
+
"learning_rate": 3.329530638852673e-05,
|
| 305 |
+
"loss": 1.1328,
|
| 306 |
+
"step": 20500
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.71,
|
| 310 |
+
"grad_norm": 2.8419606685638428,
|
| 311 |
+
"learning_rate": 3.2887874837027384e-05,
|
| 312 |
+
"loss": 1.1249,
|
| 313 |
+
"step": 21000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.75,
|
| 317 |
+
"grad_norm": 1.8945815563201904,
|
| 318 |
+
"learning_rate": 3.2480443285528036e-05,
|
| 319 |
+
"loss": 1.1294,
|
| 320 |
+
"step": 21500
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.79,
|
| 324 |
+
"grad_norm": 2.6052589416503906,
|
| 325 |
+
"learning_rate": 3.207301173402868e-05,
|
| 326 |
+
"loss": 1.1336,
|
| 327 |
+
"step": 22000
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.83,
|
| 331 |
+
"grad_norm": 2.4897425174713135,
|
| 332 |
+
"learning_rate": 3.1665580182529335e-05,
|
| 333 |
+
"loss": 1.1297,
|
| 334 |
+
"step": 22500
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 1.87,
|
| 338 |
+
"grad_norm": 2.1377058029174805,
|
| 339 |
+
"learning_rate": 3.125814863102999e-05,
|
| 340 |
+
"loss": 1.117,
|
| 341 |
+
"step": 23000
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 1.91,
|
| 345 |
+
"grad_norm": 2.3489041328430176,
|
| 346 |
+
"learning_rate": 3.085071707953064e-05,
|
| 347 |
+
"loss": 1.1242,
|
| 348 |
+
"step": 23500
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 1.96,
|
| 352 |
+
"grad_norm": 2.4663751125335693,
|
| 353 |
+
"learning_rate": 3.044328552803129e-05,
|
| 354 |
+
"loss": 1.1249,
|
| 355 |
+
"step": 24000
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 2.0,
|
| 359 |
+
"grad_norm": 1.7375434637069702,
|
| 360 |
+
"learning_rate": 3.003585397653194e-05,
|
| 361 |
+
"loss": 1.1148,
|
| 362 |
+
"step": 24500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 2.0,
|
| 366 |
+
"eval_accuracy": 0.5651553744268976,
|
| 367 |
+
"eval_combined_score": 0.5651553744268976,
|
| 368 |
+
"eval_loss": 0.956773579120636,
|
| 369 |
+
"eval_runtime": 4.3422,
|
| 370 |
+
"eval_samples_per_second": 2260.392,
|
| 371 |
+
"eval_steps_per_second": 8.982,
|
| 372 |
+
"step": 24544
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 2.04,
|
| 376 |
+
"grad_norm": 3.0487465858459473,
|
| 377 |
+
"learning_rate": 2.9628422425032598e-05,
|
| 378 |
+
"loss": 1.1135,
|
| 379 |
+
"step": 25000
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 2.08,
|
| 383 |
+
"grad_norm": 2.7948238849639893,
|
| 384 |
+
"learning_rate": 2.922099087353325e-05,
|
| 385 |
+
"loss": 1.1193,
|
| 386 |
+
"step": 25500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 2.12,
|
| 390 |
+
"grad_norm": 2.9265005588531494,
|
| 391 |
+
"learning_rate": 2.88135593220339e-05,
|
| 392 |
+
"loss": 1.1221,
|
| 393 |
+
"step": 26000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 2.16,
|
| 397 |
+
"grad_norm": 2.115213632583618,
|
| 398 |
+
"learning_rate": 2.8406127770534552e-05,
|
| 399 |
+
"loss": 1.1178,
|
| 400 |
+
"step": 26500
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 2.2,
|
| 404 |
+
"grad_norm": 2.7759642601013184,
|
| 405 |
+
"learning_rate": 2.7998696219035204e-05,
|
| 406 |
+
"loss": 1.1106,
|
| 407 |
+
"step": 27000
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 2.24,
|
| 411 |
+
"grad_norm": 3.3535237312316895,
|
| 412 |
+
"learning_rate": 2.7591264667535854e-05,
|
| 413 |
+
"loss": 1.1223,
|
| 414 |
+
"step": 27500
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 2.28,
|
| 418 |
+
"grad_norm": 4.240155220031738,
|
| 419 |
+
"learning_rate": 2.7183833116036506e-05,
|
| 420 |
+
"loss": 1.1006,
|
| 421 |
+
"step": 28000
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 2.32,
|
| 425 |
+
"grad_norm": 2.35819411277771,
|
| 426 |
+
"learning_rate": 2.6776401564537155e-05,
|
| 427 |
+
"loss": 1.1082,
|
| 428 |
+
"step": 28500
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 2.36,
|
| 432 |
+
"grad_norm": 2.635653257369995,
|
| 433 |
+
"learning_rate": 2.6368970013037815e-05,
|
| 434 |
+
"loss": 1.1047,
|
| 435 |
+
"step": 29000
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 2.4,
|
| 439 |
+
"grad_norm": 2.2701103687286377,
|
| 440 |
+
"learning_rate": 2.5961538461538464e-05,
|
| 441 |
+
"loss": 1.1003,
|
| 442 |
+
"step": 29500
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 2.44,
|
| 446 |
+
"grad_norm": 3.0462381839752197,
|
| 447 |
+
"learning_rate": 2.5554106910039117e-05,
|
| 448 |
+
"loss": 1.1127,
|
| 449 |
+
"step": 30000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 2.49,
|
| 453 |
+
"grad_norm": 2.489602565765381,
|
| 454 |
+
"learning_rate": 2.5146675358539766e-05,
|
| 455 |
+
"loss": 1.1028,
|
| 456 |
+
"step": 30500
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 2.53,
|
| 460 |
+
"grad_norm": 2.6888344287872314,
|
| 461 |
+
"learning_rate": 2.473924380704042e-05,
|
| 462 |
+
"loss": 1.0982,
|
| 463 |
+
"step": 31000
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 2.57,
|
| 467 |
+
"grad_norm": 3.001851797103882,
|
| 468 |
+
"learning_rate": 2.433181225554107e-05,
|
| 469 |
+
"loss": 1.1097,
|
| 470 |
+
"step": 31500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 2.61,
|
| 474 |
+
"grad_norm": 2.212657928466797,
|
| 475 |
+
"learning_rate": 2.392438070404172e-05,
|
| 476 |
+
"loss": 1.11,
|
| 477 |
+
"step": 32000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 2.65,
|
| 481 |
+
"grad_norm": 2.230945110321045,
|
| 482 |
+
"learning_rate": 2.3516949152542376e-05,
|
| 483 |
+
"loss": 1.0993,
|
| 484 |
+
"step": 32500
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 2.69,
|
| 488 |
+
"grad_norm": 3.2973270416259766,
|
| 489 |
+
"learning_rate": 2.3109517601043025e-05,
|
| 490 |
+
"loss": 1.1137,
|
| 491 |
+
"step": 33000
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 2.73,
|
| 495 |
+
"grad_norm": 3.0208470821380615,
|
| 496 |
+
"learning_rate": 2.2702086049543678e-05,
|
| 497 |
+
"loss": 1.1057,
|
| 498 |
+
"step": 33500
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 2.77,
|
| 502 |
+
"grad_norm": 1.68820059299469,
|
| 503 |
+
"learning_rate": 2.229465449804433e-05,
|
| 504 |
+
"loss": 1.1048,
|
| 505 |
+
"step": 34000
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 2.81,
|
| 509 |
+
"grad_norm": 3.023021936416626,
|
| 510 |
+
"learning_rate": 2.188722294654498e-05,
|
| 511 |
+
"loss": 1.091,
|
| 512 |
+
"step": 34500
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 2.85,
|
| 516 |
+
"grad_norm": 2.254213571548462,
|
| 517 |
+
"learning_rate": 2.1479791395045636e-05,
|
| 518 |
+
"loss": 1.1049,
|
| 519 |
+
"step": 35000
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 2.89,
|
| 523 |
+
"grad_norm": 3.3968422412872314,
|
| 524 |
+
"learning_rate": 2.1072359843546285e-05,
|
| 525 |
+
"loss": 1.0982,
|
| 526 |
+
"step": 35500
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 2.93,
|
| 530 |
+
"grad_norm": 2.841524124145508,
|
| 531 |
+
"learning_rate": 2.0664928292046937e-05,
|
| 532 |
+
"loss": 1.0937,
|
| 533 |
+
"step": 36000
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 2.97,
|
| 537 |
+
"grad_norm": 3.070187568664551,
|
| 538 |
+
"learning_rate": 2.0257496740547587e-05,
|
| 539 |
+
"loss": 1.1048,
|
| 540 |
+
"step": 36500
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 3.0,
|
| 544 |
+
"eval_accuracy": 0.5710646968925115,
|
| 545 |
+
"eval_combined_score": 0.5710646968925115,
|
| 546 |
+
"eval_loss": 0.9583811163902283,
|
| 547 |
+
"eval_runtime": 4.5767,
|
| 548 |
+
"eval_samples_per_second": 2144.543,
|
| 549 |
+
"eval_steps_per_second": 8.521,
|
| 550 |
+
"step": 36816
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 3.01,
|
| 554 |
+
"grad_norm": 2.1366419792175293,
|
| 555 |
+
"learning_rate": 1.9850065189048242e-05,
|
| 556 |
+
"loss": 1.094,
|
| 557 |
+
"step": 37000
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 3.06,
|
| 561 |
+
"grad_norm": 3.5920097827911377,
|
| 562 |
+
"learning_rate": 1.944263363754889e-05,
|
| 563 |
+
"loss": 1.0943,
|
| 564 |
+
"step": 37500
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 3.1,
|
| 568 |
+
"grad_norm": 3.099132537841797,
|
| 569 |
+
"learning_rate": 1.9035202086049544e-05,
|
| 570 |
+
"loss": 1.1039,
|
| 571 |
+
"step": 38000
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 3.14,
|
| 575 |
+
"grad_norm": 2.7153160572052,
|
| 576 |
+
"learning_rate": 1.8627770534550197e-05,
|
| 577 |
+
"loss": 1.0928,
|
| 578 |
+
"step": 38500
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 3.18,
|
| 582 |
+
"grad_norm": 2.752225875854492,
|
| 583 |
+
"learning_rate": 1.8220338983050846e-05,
|
| 584 |
+
"loss": 1.098,
|
| 585 |
+
"step": 39000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 3.22,
|
| 589 |
+
"grad_norm": 2.1102657318115234,
|
| 590 |
+
"learning_rate": 1.7812907431551502e-05,
|
| 591 |
+
"loss": 1.0968,
|
| 592 |
+
"step": 39500
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 3.26,
|
| 596 |
+
"grad_norm": 2.7974390983581543,
|
| 597 |
+
"learning_rate": 1.740547588005215e-05,
|
| 598 |
+
"loss": 1.09,
|
| 599 |
+
"step": 40000
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 3.3,
|
| 603 |
+
"grad_norm": 2.8349063396453857,
|
| 604 |
+
"learning_rate": 1.6998044328552804e-05,
|
| 605 |
+
"loss": 1.0862,
|
| 606 |
+
"step": 40500
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 3.34,
|
| 610 |
+
"grad_norm": 2.360250234603882,
|
| 611 |
+
"learning_rate": 1.6590612777053456e-05,
|
| 612 |
+
"loss": 1.0953,
|
| 613 |
+
"step": 41000
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 3.38,
|
| 617 |
+
"grad_norm": 3.601504325866699,
|
| 618 |
+
"learning_rate": 1.618318122555411e-05,
|
| 619 |
+
"loss": 1.0841,
|
| 620 |
+
"step": 41500
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 3.42,
|
| 624 |
+
"grad_norm": 2.5209643840789795,
|
| 625 |
+
"learning_rate": 1.577574967405476e-05,
|
| 626 |
+
"loss": 1.0847,
|
| 627 |
+
"step": 42000
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 3.46,
|
| 631 |
+
"grad_norm": 3.1257715225219727,
|
| 632 |
+
"learning_rate": 1.536831812255541e-05,
|
| 633 |
+
"loss": 1.0991,
|
| 634 |
+
"step": 42500
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 3.5,
|
| 638 |
+
"grad_norm": 3.250303268432617,
|
| 639 |
+
"learning_rate": 1.4960886571056063e-05,
|
| 640 |
+
"loss": 1.098,
|
| 641 |
+
"step": 43000
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 3.54,
|
| 645 |
+
"grad_norm": 3.4005048274993896,
|
| 646 |
+
"learning_rate": 1.4553455019556716e-05,
|
| 647 |
+
"loss": 1.0839,
|
| 648 |
+
"step": 43500
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 3.59,
|
| 652 |
+
"grad_norm": 2.8816983699798584,
|
| 653 |
+
"learning_rate": 1.4146023468057368e-05,
|
| 654 |
+
"loss": 1.0849,
|
| 655 |
+
"step": 44000
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 3.63,
|
| 659 |
+
"grad_norm": 2.870222568511963,
|
| 660 |
+
"learning_rate": 1.373859191655802e-05,
|
| 661 |
+
"loss": 1.0994,
|
| 662 |
+
"step": 44500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 3.67,
|
| 666 |
+
"grad_norm": 3.1101572513580322,
|
| 667 |
+
"learning_rate": 1.333116036505867e-05,
|
| 668 |
+
"loss": 1.0927,
|
| 669 |
+
"step": 45000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 3.71,
|
| 673 |
+
"grad_norm": 3.555572986602783,
|
| 674 |
+
"learning_rate": 1.2923728813559321e-05,
|
| 675 |
+
"loss": 1.0915,
|
| 676 |
+
"step": 45500
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 3.75,
|
| 680 |
+
"grad_norm": 3.06459379196167,
|
| 681 |
+
"learning_rate": 1.2516297262059975e-05,
|
| 682 |
+
"loss": 1.0952,
|
| 683 |
+
"step": 46000
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 3.79,
|
| 687 |
+
"grad_norm": 3.103626012802124,
|
| 688 |
+
"learning_rate": 1.2108865710560626e-05,
|
| 689 |
+
"loss": 1.0859,
|
| 690 |
+
"step": 46500
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 3.83,
|
| 694 |
+
"grad_norm": 3.8208911418914795,
|
| 695 |
+
"learning_rate": 1.1701434159061279e-05,
|
| 696 |
+
"loss": 1.0966,
|
| 697 |
+
"step": 47000
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 3.87,
|
| 701 |
+
"grad_norm": 2.8707382678985596,
|
| 702 |
+
"learning_rate": 1.1294002607561931e-05,
|
| 703 |
+
"loss": 1.0752,
|
| 704 |
+
"step": 47500
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 3.91,
|
| 708 |
+
"grad_norm": 4.298058032989502,
|
| 709 |
+
"learning_rate": 1.0886571056062582e-05,
|
| 710 |
+
"loss": 1.092,
|
| 711 |
+
"step": 48000
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 3.95,
|
| 715 |
+
"grad_norm": 2.011492967605591,
|
| 716 |
+
"learning_rate": 1.0479139504563235e-05,
|
| 717 |
+
"loss": 1.0789,
|
| 718 |
+
"step": 48500
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 3.99,
|
| 722 |
+
"grad_norm": 3.2206387519836426,
|
| 723 |
+
"learning_rate": 1.0071707953063886e-05,
|
| 724 |
+
"loss": 1.075,
|
| 725 |
+
"step": 49000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 4.0,
|
| 729 |
+
"eval_accuracy": 0.5978604177279674,
|
| 730 |
+
"eval_combined_score": 0.5978604177279674,
|
| 731 |
+
"eval_loss": 0.9132007360458374,
|
| 732 |
+
"eval_runtime": 3.8437,
|
| 733 |
+
"eval_samples_per_second": 2553.526,
|
| 734 |
+
"eval_steps_per_second": 10.146,
|
| 735 |
+
"step": 49088
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 4.03,
|
| 739 |
+
"grad_norm": 3.0595147609710693,
|
| 740 |
+
"learning_rate": 9.664276401564537e-06,
|
| 741 |
+
"loss": 1.0901,
|
| 742 |
+
"step": 49500
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 4.07,
|
| 746 |
+
"grad_norm": 2.2460098266601562,
|
| 747 |
+
"learning_rate": 9.25684485006519e-06,
|
| 748 |
+
"loss": 1.0802,
|
| 749 |
+
"step": 50000
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 4.12,
|
| 753 |
+
"grad_norm": 2.1211585998535156,
|
| 754 |
+
"learning_rate": 8.84941329856584e-06,
|
| 755 |
+
"loss": 1.0886,
|
| 756 |
+
"step": 50500
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 4.16,
|
| 760 |
+
"grad_norm": 2.7433323860168457,
|
| 761 |
+
"learning_rate": 8.441981747066494e-06,
|
| 762 |
+
"loss": 1.0814,
|
| 763 |
+
"step": 51000
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 4.2,
|
| 767 |
+
"grad_norm": 3.3154397010803223,
|
| 768 |
+
"learning_rate": 8.034550195567145e-06,
|
| 769 |
+
"loss": 1.0877,
|
| 770 |
+
"step": 51500
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 4.24,
|
| 774 |
+
"grad_norm": 3.0281894207000732,
|
| 775 |
+
"learning_rate": 7.627118644067798e-06,
|
| 776 |
+
"loss": 1.0773,
|
| 777 |
+
"step": 52000
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 4.28,
|
| 781 |
+
"grad_norm": 2.553225517272949,
|
| 782 |
+
"learning_rate": 7.219687092568449e-06,
|
| 783 |
+
"loss": 1.0869,
|
| 784 |
+
"step": 52500
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 4.32,
|
| 788 |
+
"grad_norm": 2.8887219429016113,
|
| 789 |
+
"learning_rate": 6.812255541069101e-06,
|
| 790 |
+
"loss": 1.0756,
|
| 791 |
+
"step": 53000
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 4.36,
|
| 795 |
+
"grad_norm": 2.1609950065612793,
|
| 796 |
+
"learning_rate": 6.404823989569752e-06,
|
| 797 |
+
"loss": 1.0884,
|
| 798 |
+
"step": 53500
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 4.4,
|
| 802 |
+
"grad_norm": 3.0557539463043213,
|
| 803 |
+
"learning_rate": 5.997392438070405e-06,
|
| 804 |
+
"loss": 1.0886,
|
| 805 |
+
"step": 54000
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 4.44,
|
| 809 |
+
"grad_norm": 2.783965587615967,
|
| 810 |
+
"learning_rate": 5.5899608865710565e-06,
|
| 811 |
+
"loss": 1.0827,
|
| 812 |
+
"step": 54500
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 4.48,
|
| 816 |
+
"grad_norm": 3.0575108528137207,
|
| 817 |
+
"learning_rate": 5.182529335071708e-06,
|
| 818 |
+
"loss": 1.0886,
|
| 819 |
+
"step": 55000
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 4.52,
|
| 823 |
+
"grad_norm": 2.5954906940460205,
|
| 824 |
+
"learning_rate": 4.77509778357236e-06,
|
| 825 |
+
"loss": 1.0773,
|
| 826 |
+
"step": 55500
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 4.56,
|
| 830 |
+
"grad_norm": 2.1589512825012207,
|
| 831 |
+
"learning_rate": 4.367666232073012e-06,
|
| 832 |
+
"loss": 1.0693,
|
| 833 |
+
"step": 56000
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 4.6,
|
| 837 |
+
"grad_norm": 2.5202431678771973,
|
| 838 |
+
"learning_rate": 3.9602346805736635e-06,
|
| 839 |
+
"loss": 1.0803,
|
| 840 |
+
"step": 56500
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 4.64,
|
| 844 |
+
"grad_norm": 2.588782787322998,
|
| 845 |
+
"learning_rate": 3.5528031290743156e-06,
|
| 846 |
+
"loss": 1.0816,
|
| 847 |
+
"step": 57000
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 4.69,
|
| 851 |
+
"grad_norm": 2.994828701019287,
|
| 852 |
+
"learning_rate": 3.1453715775749674e-06,
|
| 853 |
+
"loss": 1.0682,
|
| 854 |
+
"step": 57500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 4.73,
|
| 858 |
+
"grad_norm": 2.9718551635742188,
|
| 859 |
+
"learning_rate": 2.7379400260756195e-06,
|
| 860 |
+
"loss": 1.0786,
|
| 861 |
+
"step": 58000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 4.77,
|
| 865 |
+
"grad_norm": 3.181231737136841,
|
| 866 |
+
"learning_rate": 2.3305084745762712e-06,
|
| 867 |
+
"loss": 1.0818,
|
| 868 |
+
"step": 58500
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 4.81,
|
| 872 |
+
"grad_norm": 2.3970162868499756,
|
| 873 |
+
"learning_rate": 1.9230769230769234e-06,
|
| 874 |
+
"loss": 1.0816,
|
| 875 |
+
"step": 59000
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 4.85,
|
| 879 |
+
"grad_norm": 2.8263609409332275,
|
| 880 |
+
"learning_rate": 1.5156453715775751e-06,
|
| 881 |
+
"loss": 1.0755,
|
| 882 |
+
"step": 59500
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 4.89,
|
| 886 |
+
"grad_norm": 3.2032511234283447,
|
| 887 |
+
"learning_rate": 1.108213820078227e-06,
|
| 888 |
+
"loss": 1.0764,
|
| 889 |
+
"step": 60000
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 4.93,
|
| 893 |
+
"grad_norm": 3.6272828578948975,
|
| 894 |
+
"learning_rate": 7.007822685788788e-07,
|
| 895 |
+
"loss": 1.0855,
|
| 896 |
+
"step": 60500
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 4.97,
|
| 900 |
+
"grad_norm": 2.672410249710083,
|
| 901 |
+
"learning_rate": 2.9335071707953065e-07,
|
| 902 |
+
"loss": 1.0755,
|
| 903 |
+
"step": 61000
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 5.0,
|
| 907 |
+
"eval_accuracy": 0.6116148751910341,
|
| 908 |
+
"eval_combined_score": 0.6116148751910341,
|
| 909 |
+
"eval_loss": 0.8905634880065918,
|
| 910 |
+
"eval_runtime": 4.8808,
|
| 911 |
+
"eval_samples_per_second": 2010.92,
|
| 912 |
+
"eval_steps_per_second": 7.99,
|
| 913 |
+
"step": 61360
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 5.0,
|
| 917 |
+
"step": 61360,
|
| 918 |
+
"total_flos": 0.0,
|
| 919 |
+
"train_loss": 1.1215235922762437,
|
| 920 |
+
"train_runtime": 4186.3943,
|
| 921 |
+
"train_samples_per_second": 469.022,
|
| 922 |
+
"train_steps_per_second": 14.657
|
| 923 |
+
}
|
| 924 |
+
],
|
| 925 |
+
"logging_steps": 500,
|
| 926 |
+
"max_steps": 61360,
|
| 927 |
+
"num_input_tokens_seen": 0,
|
| 928 |
+
"num_train_epochs": 5,
|
| 929 |
+
"save_steps": 500,
|
| 930 |
+
"total_flos": 0.0,
|
| 931 |
+
"train_batch_size": 32,
|
| 932 |
+
"trial_name": null,
|
| 933 |
+
"trial_params": null
|
| 934 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fa5fe51a26b5a11be035a3d2c4ddae6b89c38c2fb8722a105062c00ddf1b03b
|
| 3 |
+
size 5880
|
transfer_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eval_accuracy": 0.5572038203617151,
|
| 3 |
+
"eval_combined_score": 0.5572038203617151,
|
| 4 |
+
"eval_loss": 0.9355756640434265,
|
| 5 |
+
"eval_runtime": 7.4268,
|
| 6 |
+
"eval_samples_per_second": 1325.196,
|
| 7 |
+
"eval_steps_per_second": 5.251
|
| 8 |
+
}
|