Upload folder using huggingface_hub
Browse files- .gitattributes +3 -0
- checkpoint-1100/model.safetensors +3 -0
- checkpoint-1100/optimizer.pt +3 -0
- checkpoint-1100/rng_state.pth +3 -0
- checkpoint-1100/scheduler.pt +3 -0
- checkpoint-1100/sentencepiece.bpe.model +3 -0
- checkpoint-1100/special_tokens_map.json +51 -0
- checkpoint-1100/tokenizer.json +3 -0
- checkpoint-1100/tokenizer_config.json +62 -0
- checkpoint-1100/trainer_state.json +229 -0
- checkpoint-1100/training_args.bin +3 -0
- checkpoint-1600/model.safetensors +3 -0
- checkpoint-1600/optimizer.pt +3 -0
- checkpoint-1600/rng_state.pth +3 -0
- checkpoint-1600/scheduler.pt +3 -0
- checkpoint-1600/sentencepiece.bpe.model +3 -0
- checkpoint-1600/special_tokens_map.json +51 -0
- checkpoint-1600/tokenizer.json +3 -0
- checkpoint-1600/tokenizer_config.json +62 -0
- checkpoint-1600/trainer_state.json +314 -0
- checkpoint-1600/training_args.bin +3 -0
- model.safetensors +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +3 -0
- tokenizer_config.json +62 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
checkpoint-1100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
checkpoint-1600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
checkpoint-1100/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b66c242f59af7e4b516c2b5be311457519f9d0e0b9aabcc32f73ba193a1d5f9
|
| 3 |
+
size 1112204984
|
checkpoint-1100/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d990f229200416765c76b3d9635b4d2e3df448db3d58b15a2da9280e2e7e8151
|
| 3 |
+
size 2106370618
|
checkpoint-1100/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73ad35afe7245582c3a30c2d911f786a320ba177c1efc7548bb163ec485239fa
|
| 3 |
+
size 14244
|
checkpoint-1100/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:520f2081c479c0da3683abcee293f6eed9e80636974af78345346e76ee096a64
|
| 3 |
+
size 1064
|
checkpoint-1100/sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
| 3 |
+
size 5069051
|
checkpoint-1100/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-1100/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
|
| 3 |
+
size 17082999
|
checkpoint-1100/tokenizer_config.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"250001": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": true,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "<mask>",
|
| 50 |
+
"max_length": 128,
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"pad_to_multiple_of": null,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"pad_token_type_id": 0,
|
| 55 |
+
"padding_side": "right",
|
| 56 |
+
"sep_token": "</s>",
|
| 57 |
+
"stride": 0,
|
| 58 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 59 |
+
"truncation_side": "right",
|
| 60 |
+
"truncation_strategy": "longest_first",
|
| 61 |
+
"unk_token": "<unk>"
|
| 62 |
+
}
|
checkpoint-1100/trainer_state.json
ADDED
|
@@ -0,0 +1,229 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6374164810690424,
|
| 3 |
+
"best_model_checkpoint": "./trained_on_contrastive_encoder_10_epoch_question_medium_freeze_2/checkpoint-1100",
|
| 4 |
+
"epoch": 0.7037747920665387,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 1100,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06397952655150352,
|
| 13 |
+
"grad_norm": 5.158140659332275,
|
| 14 |
+
"learning_rate": 2.9709e-05,
|
| 15 |
+
"loss": 0.6802,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06397952655150352,
|
| 20 |
+
"eval_accuracy": 0.5121975115117077,
|
| 21 |
+
"eval_f1_pos": 0.43103645297680265,
|
| 22 |
+
"eval_loss": 0.7163140177726746,
|
| 23 |
+
"eval_runtime": 39.2125,
|
| 24 |
+
"eval_samples_per_second": 260.3,
|
| 25 |
+
"eval_steps_per_second": 16.27,
|
| 26 |
+
"step": 100
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.12795905310300704,
|
| 30 |
+
"grad_norm": 50.45295333862305,
|
| 31 |
+
"learning_rate": 2.9412000000000002e-05,
|
| 32 |
+
"loss": 0.6254,
|
| 33 |
+
"step": 200
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.12795905310300704,
|
| 37 |
+
"eval_accuracy": 0.8308023905163123,
|
| 38 |
+
"eval_f1_pos": 0.5072753209700428,
|
| 39 |
+
"eval_loss": 0.5211790800094604,
|
| 40 |
+
"eval_runtime": 39.2675,
|
| 41 |
+
"eval_samples_per_second": 259.935,
|
| 42 |
+
"eval_steps_per_second": 16.248,
|
| 43 |
+
"step": 200
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.19193857965451055,
|
| 47 |
+
"grad_norm": 12.228692054748535,
|
| 48 |
+
"learning_rate": 2.9112000000000002e-05,
|
| 49 |
+
"loss": 0.5678,
|
| 50 |
+
"step": 300
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.19193857965451055,
|
| 54 |
+
"eval_accuracy": 0.8537278338395219,
|
| 55 |
+
"eval_f1_pos": 0.5485334139703659,
|
| 56 |
+
"eval_loss": 0.4735589623451233,
|
| 57 |
+
"eval_runtime": 39.1813,
|
| 58 |
+
"eval_samples_per_second": 260.507,
|
| 59 |
+
"eval_steps_per_second": 16.283,
|
| 60 |
+
"step": 300
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.2559181062060141,
|
| 64 |
+
"grad_norm": 1.158460259437561,
|
| 65 |
+
"learning_rate": 2.8815e-05,
|
| 66 |
+
"loss": 0.5457,
|
| 67 |
+
"step": 400
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.2559181062060141,
|
| 71 |
+
"eval_accuracy": 0.8593122367003038,
|
| 72 |
+
"eval_f1_pos": 0.5470031545741325,
|
| 73 |
+
"eval_loss": 0.45852354168891907,
|
| 74 |
+
"eval_runtime": 39.2525,
|
| 75 |
+
"eval_samples_per_second": 260.034,
|
| 76 |
+
"eval_steps_per_second": 16.254,
|
| 77 |
+
"step": 400
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.3198976327575176,
|
| 81 |
+
"grad_norm": 9.899066925048828,
|
| 82 |
+
"learning_rate": 2.8515e-05,
|
| 83 |
+
"loss": 0.5424,
|
| 84 |
+
"step": 500
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.3198976327575176,
|
| 88 |
+
"eval_accuracy": 0.7876947193102772,
|
| 89 |
+
"eval_f1_pos": 0.5585658993685069,
|
| 90 |
+
"eval_loss": 0.4260188937187195,
|
| 91 |
+
"eval_runtime": 39.5171,
|
| 92 |
+
"eval_samples_per_second": 258.293,
|
| 93 |
+
"eval_steps_per_second": 16.145,
|
| 94 |
+
"step": 500
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.3838771593090211,
|
| 98 |
+
"grad_norm": 4.964751720428467,
|
| 99 |
+
"learning_rate": 2.8215e-05,
|
| 100 |
+
"loss": 0.4716,
|
| 101 |
+
"step": 600
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.3838771593090211,
|
| 105 |
+
"eval_accuracy": 0.8305084745762712,
|
| 106 |
+
"eval_f1_pos": 0.5976744186046512,
|
| 107 |
+
"eval_loss": 0.46330758929252625,
|
| 108 |
+
"eval_runtime": 39.2652,
|
| 109 |
+
"eval_samples_per_second": 259.95,
|
| 110 |
+
"eval_steps_per_second": 16.248,
|
| 111 |
+
"step": 600
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.44785668586052463,
|
| 115 |
+
"grad_norm": 22.154949188232422,
|
| 116 |
+
"learning_rate": 2.7915e-05,
|
| 117 |
+
"loss": 0.4965,
|
| 118 |
+
"step": 700
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.44785668586052463,
|
| 122 |
+
"eval_accuracy": 0.8427549720779857,
|
| 123 |
+
"eval_f1_pos": 0.5925361766945926,
|
| 124 |
+
"eval_loss": 0.4442957639694214,
|
| 125 |
+
"eval_runtime": 39.0594,
|
| 126 |
+
"eval_samples_per_second": 261.32,
|
| 127 |
+
"eval_steps_per_second": 16.334,
|
| 128 |
+
"step": 700
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.5118362124120281,
|
| 132 |
+
"grad_norm": 2.4270291328430176,
|
| 133 |
+
"learning_rate": 2.7615e-05,
|
| 134 |
+
"loss": 0.4711,
|
| 135 |
+
"step": 800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.5118362124120281,
|
| 139 |
+
"eval_accuracy": 0.8275693151758597,
|
| 140 |
+
"eval_f1_pos": 0.6188826331745344,
|
| 141 |
+
"eval_loss": 0.46320080757141113,
|
| 142 |
+
"eval_runtime": 39.2923,
|
| 143 |
+
"eval_samples_per_second": 259.771,
|
| 144 |
+
"eval_steps_per_second": 16.237,
|
| 145 |
+
"step": 800
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.5758157389635317,
|
| 149 |
+
"grad_norm": 5.09190559387207,
|
| 150 |
+
"learning_rate": 2.7315e-05,
|
| 151 |
+
"loss": 0.459,
|
| 152 |
+
"step": 900
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.5758157389635317,
|
| 156 |
+
"eval_accuracy": 0.8317821103164494,
|
| 157 |
+
"eval_f1_pos": 0.628274518294003,
|
| 158 |
+
"eval_loss": 0.4244905710220337,
|
| 159 |
+
"eval_runtime": 39.1291,
|
| 160 |
+
"eval_samples_per_second": 260.854,
|
| 161 |
+
"eval_steps_per_second": 16.305,
|
| 162 |
+
"step": 900
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.6397952655150352,
|
| 166 |
+
"grad_norm": 5.881589889526367,
|
| 167 |
+
"learning_rate": 2.7015e-05,
|
| 168 |
+
"loss": 0.4549,
|
| 169 |
+
"step": 1000
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.6397952655150352,
|
| 173 |
+
"eval_accuracy": 0.7797589889291663,
|
| 174 |
+
"eval_f1_pos": 0.5955379632961497,
|
| 175 |
+
"eval_loss": 0.42638295888900757,
|
| 176 |
+
"eval_runtime": 39.158,
|
| 177 |
+
"eval_samples_per_second": 260.662,
|
| 178 |
+
"eval_steps_per_second": 16.293,
|
| 179 |
+
"step": 1000
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.7037747920665387,
|
| 183 |
+
"grad_norm": 4.328377723693848,
|
| 184 |
+
"learning_rate": 2.6715e-05,
|
| 185 |
+
"loss": 0.4537,
|
| 186 |
+
"step": 1100
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.7037747920665387,
|
| 190 |
+
"eval_accuracy": 0.8405016165376702,
|
| 191 |
+
"eval_f1_pos": 0.6374164810690424,
|
| 192 |
+
"eval_loss": 0.38711538910865784,
|
| 193 |
+
"eval_runtime": 39.2656,
|
| 194 |
+
"eval_samples_per_second": 259.947,
|
| 195 |
+
"eval_steps_per_second": 16.248,
|
| 196 |
+
"step": 1100
|
| 197 |
+
}
|
| 198 |
+
],
|
| 199 |
+
"logging_steps": 100,
|
| 200 |
+
"max_steps": 10000,
|
| 201 |
+
"num_input_tokens_seen": 0,
|
| 202 |
+
"num_train_epochs": 7,
|
| 203 |
+
"save_steps": 100,
|
| 204 |
+
"stateful_callbacks": {
|
| 205 |
+
"EarlyStoppingCallback": {
|
| 206 |
+
"args": {
|
| 207 |
+
"early_stopping_patience": 2,
|
| 208 |
+
"early_stopping_threshold": 0.0
|
| 209 |
+
},
|
| 210 |
+
"attributes": {
|
| 211 |
+
"early_stopping_patience_counter": 0
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"TrainerControl": {
|
| 215 |
+
"args": {
|
| 216 |
+
"should_epoch_stop": false,
|
| 217 |
+
"should_evaluate": false,
|
| 218 |
+
"should_log": false,
|
| 219 |
+
"should_save": true,
|
| 220 |
+
"should_training_stop": false
|
| 221 |
+
},
|
| 222 |
+
"attributes": {}
|
| 223 |
+
}
|
| 224 |
+
},
|
| 225 |
+
"total_flos": 0.0,
|
| 226 |
+
"train_batch_size": 16,
|
| 227 |
+
"trial_name": null,
|
| 228 |
+
"trial_params": null
|
| 229 |
+
}
|
checkpoint-1100/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:22e9182a0c83a61efb7c1d7502abc67edd78b2ca5e16cb469bd582cfedf7be9e
|
| 3 |
+
size 5432
|
checkpoint-1600/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca7c0838e1ae39eb70c65b78b543dff513ee4e89acf07fa8d1034e3140267d71
|
| 3 |
+
size 1112204984
|
checkpoint-1600/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8143fbf7ca30e0b0e5c51b7cb22a60aae6a94f6658ae463c59f3a18567f3ebec
|
| 3 |
+
size 2106370618
|
checkpoint-1600/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0bce63751ce7f84816d15b924b8dbf6ede28c685a0c00a59b51c22f39f22216
|
| 3 |
+
size 14244
|
checkpoint-1600/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa263ed387e5d745020a0cfaa84271a8ec122b9352005d4aefa320d795ad2101
|
| 3 |
+
size 1064
|
checkpoint-1600/sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
| 3 |
+
size 5069051
|
checkpoint-1600/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-1600/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
|
| 3 |
+
size 17082999
|
checkpoint-1600/tokenizer_config.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"250001": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": true,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "<mask>",
|
| 50 |
+
"max_length": 128,
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"pad_to_multiple_of": null,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"pad_token_type_id": 0,
|
| 55 |
+
"padding_side": "right",
|
| 56 |
+
"sep_token": "</s>",
|
| 57 |
+
"stride": 0,
|
| 58 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 59 |
+
"truncation_side": "right",
|
| 60 |
+
"truncation_strategy": "longest_first",
|
| 61 |
+
"unk_token": "<unk>"
|
| 62 |
+
}
|
checkpoint-1600/trainer_state.json
ADDED
|
@@ -0,0 +1,314 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6639657888813865,
|
| 3 |
+
"best_model_checkpoint": "./trained_on_contrastive_encoder_10_epoch_question_medium_freeze_2/checkpoint-1400",
|
| 4 |
+
"epoch": 1.0236724248240563,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 1600,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06397952655150352,
|
| 13 |
+
"grad_norm": 6.57439661026001,
|
| 14 |
+
"learning_rate": 9.903e-06,
|
| 15 |
+
"loss": 0.7001,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06397952655150352,
|
| 20 |
+
"eval_accuracy": 0.21808562751053198,
|
| 21 |
+
"eval_f1_pos": 0.3580793050752031,
|
| 22 |
+
"eval_loss": 0.7560768723487854,
|
| 23 |
+
"eval_runtime": 39.7516,
|
| 24 |
+
"eval_samples_per_second": 256.77,
|
| 25 |
+
"eval_steps_per_second": 16.05,
|
| 26 |
+
"step": 100
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.12795905310300704,
|
| 30 |
+
"grad_norm": 79.49400329589844,
|
| 31 |
+
"learning_rate": 9.805000000000002e-06,
|
| 32 |
+
"loss": 0.6813,
|
| 33 |
+
"step": 200
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.12795905310300704,
|
| 37 |
+
"eval_accuracy": 0.7106887430194965,
|
| 38 |
+
"eval_f1_pos": 0.45284417268853067,
|
| 39 |
+
"eval_loss": 0.5536114573478699,
|
| 40 |
+
"eval_runtime": 40.0362,
|
| 41 |
+
"eval_samples_per_second": 254.944,
|
| 42 |
+
"eval_steps_per_second": 15.936,
|
| 43 |
+
"step": 200
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.19193857965451055,
|
| 47 |
+
"grad_norm": 9.357890129089355,
|
| 48 |
+
"learning_rate": 9.706000000000002e-06,
|
| 49 |
+
"loss": 0.6009,
|
| 50 |
+
"step": 300
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.19193857965451055,
|
| 54 |
+
"eval_accuracy": 0.6335847947487019,
|
| 55 |
+
"eval_f1_pos": 0.4565533275210695,
|
| 56 |
+
"eval_loss": 0.5767261981964111,
|
| 57 |
+
"eval_runtime": 39.9062,
|
| 58 |
+
"eval_samples_per_second": 255.775,
|
| 59 |
+
"eval_steps_per_second": 15.987,
|
| 60 |
+
"step": 300
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.2559181062060141,
|
| 64 |
+
"grad_norm": 18.08504295349121,
|
| 65 |
+
"learning_rate": 9.606000000000001e-06,
|
| 66 |
+
"loss": 0.5918,
|
| 67 |
+
"step": 400
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.2559181062060141,
|
| 71 |
+
"eval_accuracy": 0.8085627510531987,
|
| 72 |
+
"eval_f1_pos": 0.5248054474708171,
|
| 73 |
+
"eval_loss": 0.4491700530052185,
|
| 74 |
+
"eval_runtime": 39.5058,
|
| 75 |
+
"eval_samples_per_second": 258.367,
|
| 76 |
+
"eval_steps_per_second": 16.15,
|
| 77 |
+
"step": 400
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.3198976327575176,
|
| 81 |
+
"grad_norm": 14.061025619506836,
|
| 82 |
+
"learning_rate": 9.506e-06,
|
| 83 |
+
"loss": 0.5667,
|
| 84 |
+
"step": 500
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.3198976327575176,
|
| 88 |
+
"eval_accuracy": 0.8257078475555991,
|
| 89 |
+
"eval_f1_pos": 0.5640774320019603,
|
| 90 |
+
"eval_loss": 0.407839834690094,
|
| 91 |
+
"eval_runtime": 39.7704,
|
| 92 |
+
"eval_samples_per_second": 256.648,
|
| 93 |
+
"eval_steps_per_second": 16.042,
|
| 94 |
+
"step": 500
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.3838771593090211,
|
| 98 |
+
"grad_norm": 12.516818046569824,
|
| 99 |
+
"learning_rate": 9.406000000000001e-06,
|
| 100 |
+
"loss": 0.4927,
|
| 101 |
+
"step": 600
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.3838771593090211,
|
| 105 |
+
"eval_accuracy": 0.7215636328010189,
|
| 106 |
+
"eval_f1_pos": 0.5404269081500647,
|
| 107 |
+
"eval_loss": 0.5605168342590332,
|
| 108 |
+
"eval_runtime": 39.3685,
|
| 109 |
+
"eval_samples_per_second": 259.268,
|
| 110 |
+
"eval_steps_per_second": 16.206,
|
| 111 |
+
"step": 600
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.44785668586052463,
|
| 115 |
+
"grad_norm": 38.32394790649414,
|
| 116 |
+
"learning_rate": 9.306e-06,
|
| 117 |
+
"loss": 0.481,
|
| 118 |
+
"step": 700
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.44785668586052463,
|
| 122 |
+
"eval_accuracy": 0.8186538649946116,
|
| 123 |
+
"eval_f1_pos": 0.6009915930157361,
|
| 124 |
+
"eval_loss": 0.4341912567615509,
|
| 125 |
+
"eval_runtime": 40.1944,
|
| 126 |
+
"eval_samples_per_second": 253.941,
|
| 127 |
+
"eval_steps_per_second": 15.873,
|
| 128 |
+
"step": 700
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.5118362124120281,
|
| 132 |
+
"grad_norm": 9.896209716796875,
|
| 133 |
+
"learning_rate": 9.206000000000001e-06,
|
| 134 |
+
"loss": 0.4631,
|
| 135 |
+
"step": 800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.5118362124120281,
|
| 139 |
+
"eval_accuracy": 0.757421377486039,
|
| 140 |
+
"eval_f1_pos": 0.5699895797151788,
|
| 141 |
+
"eval_loss": 0.49195003509521484,
|
| 142 |
+
"eval_runtime": 39.1824,
|
| 143 |
+
"eval_samples_per_second": 260.5,
|
| 144 |
+
"eval_steps_per_second": 16.283,
|
| 145 |
+
"step": 800
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.5758157389635317,
|
| 149 |
+
"grad_norm": 11.049246788024902,
|
| 150 |
+
"learning_rate": 9.106e-06,
|
| 151 |
+
"loss": 0.4741,
|
| 152 |
+
"step": 900
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.5758157389635317,
|
| 156 |
+
"eval_accuracy": 0.8210051925149408,
|
| 157 |
+
"eval_f1_pos": 0.6167400881057269,
|
| 158 |
+
"eval_loss": 0.3933488130569458,
|
| 159 |
+
"eval_runtime": 39.9623,
|
| 160 |
+
"eval_samples_per_second": 255.416,
|
| 161 |
+
"eval_steps_per_second": 15.965,
|
| 162 |
+
"step": 900
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.6397952655150352,
|
| 166 |
+
"grad_norm": 17.43934440612793,
|
| 167 |
+
"learning_rate": 9.006e-06,
|
| 168 |
+
"loss": 0.454,
|
| 169 |
+
"step": 1000
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.6397952655150352,
|
| 173 |
+
"eval_accuracy": 0.7290095032820614,
|
| 174 |
+
"eval_f1_pos": 0.566593544343466,
|
| 175 |
+
"eval_loss": 0.5808197259902954,
|
| 176 |
+
"eval_runtime": 39.4301,
|
| 177 |
+
"eval_samples_per_second": 258.863,
|
| 178 |
+
"eval_steps_per_second": 16.181,
|
| 179 |
+
"step": 1000
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.7037747920665387,
|
| 183 |
+
"grad_norm": 6.886244773864746,
|
| 184 |
+
"learning_rate": 8.906e-06,
|
| 185 |
+
"loss": 0.461,
|
| 186 |
+
"step": 1100
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.7037747920665387,
|
| 190 |
+
"eval_accuracy": 0.8396198687175468,
|
| 191 |
+
"eval_f1_pos": 0.6426544422615149,
|
| 192 |
+
"eval_loss": 0.3872079849243164,
|
| 193 |
+
"eval_runtime": 40.3537,
|
| 194 |
+
"eval_samples_per_second": 252.938,
|
| 195 |
+
"eval_steps_per_second": 15.81,
|
| 196 |
+
"step": 1100
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.7677543186180422,
|
| 200 |
+
"grad_norm": 18.952091217041016,
|
| 201 |
+
"learning_rate": 8.806000000000002e-06,
|
| 202 |
+
"loss": 0.4602,
|
| 203 |
+
"step": 1200
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.7677543186180422,
|
| 207 |
+
"eval_accuracy": 0.8450083276183011,
|
| 208 |
+
"eval_f1_pos": 0.6449730700179533,
|
| 209 |
+
"eval_loss": 0.36067792773246765,
|
| 210 |
+
"eval_runtime": 40.2049,
|
| 211 |
+
"eval_samples_per_second": 253.875,
|
| 212 |
+
"eval_steps_per_second": 15.869,
|
| 213 |
+
"step": 1200
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.8317338451695457,
|
| 217 |
+
"grad_norm": 13.816661834716797,
|
| 218 |
+
"learning_rate": 8.706000000000001e-06,
|
| 219 |
+
"loss": 0.454,
|
| 220 |
+
"step": 1300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.8317338451695457,
|
| 224 |
+
"eval_accuracy": 0.7875967473302635,
|
| 225 |
+
"eval_f1_pos": 0.6160113354587319,
|
| 226 |
+
"eval_loss": 0.42329227924346924,
|
| 227 |
+
"eval_runtime": 39.908,
|
| 228 |
+
"eval_samples_per_second": 255.763,
|
| 229 |
+
"eval_steps_per_second": 15.987,
|
| 230 |
+
"step": 1300
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.8957133717210493,
|
| 234 |
+
"grad_norm": 16.50107765197754,
|
| 235 |
+
"learning_rate": 8.606e-06,
|
| 236 |
+
"loss": 0.4296,
|
| 237 |
+
"step": 1400
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.8957133717210493,
|
| 241 |
+
"eval_accuracy": 0.8537278338395219,
|
| 242 |
+
"eval_f1_pos": 0.6639657888813865,
|
| 243 |
+
"eval_loss": 0.35989442467689514,
|
| 244 |
+
"eval_runtime": 40.4566,
|
| 245 |
+
"eval_samples_per_second": 252.295,
|
| 246 |
+
"eval_steps_per_second": 15.77,
|
| 247 |
+
"step": 1400
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.9596928982725528,
|
| 251 |
+
"grad_norm": 27.01910972595215,
|
| 252 |
+
"learning_rate": 8.506000000000001e-06,
|
| 253 |
+
"loss": 0.4107,
|
| 254 |
+
"step": 1500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.9596928982725528,
|
| 258 |
+
"eval_accuracy": 0.7782894092289605,
|
| 259 |
+
"eval_f1_pos": 0.6119019036185903,
|
| 260 |
+
"eval_loss": 0.47975867986679077,
|
| 261 |
+
"eval_runtime": 40.5381,
|
| 262 |
+
"eval_samples_per_second": 251.788,
|
| 263 |
+
"eval_steps_per_second": 15.738,
|
| 264 |
+
"step": 1500
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.0236724248240563,
|
| 268 |
+
"grad_norm": 47.78235626220703,
|
| 269 |
+
"learning_rate": 8.406e-06,
|
| 270 |
+
"loss": 0.388,
|
| 271 |
+
"step": 1600
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 1.0236724248240563,
|
| 275 |
+
"eval_accuracy": 0.8391300088174782,
|
| 276 |
+
"eval_f1_pos": 0.6596185737976783,
|
| 277 |
+
"eval_loss": 0.40939557552337646,
|
| 278 |
+
"eval_runtime": 41.6225,
|
| 279 |
+
"eval_samples_per_second": 245.228,
|
| 280 |
+
"eval_steps_per_second": 15.328,
|
| 281 |
+
"step": 1600
|
| 282 |
+
}
|
| 283 |
+
],
|
| 284 |
+
"logging_steps": 100,
|
| 285 |
+
"max_steps": 10000,
|
| 286 |
+
"num_input_tokens_seen": 0,
|
| 287 |
+
"num_train_epochs": 7,
|
| 288 |
+
"save_steps": 100,
|
| 289 |
+
"stateful_callbacks": {
|
| 290 |
+
"EarlyStoppingCallback": {
|
| 291 |
+
"args": {
|
| 292 |
+
"early_stopping_patience": 2,
|
| 293 |
+
"early_stopping_threshold": 0.0
|
| 294 |
+
},
|
| 295 |
+
"attributes": {
|
| 296 |
+
"early_stopping_patience_counter": 2
|
| 297 |
+
}
|
| 298 |
+
},
|
| 299 |
+
"TrainerControl": {
|
| 300 |
+
"args": {
|
| 301 |
+
"should_epoch_stop": false,
|
| 302 |
+
"should_evaluate": false,
|
| 303 |
+
"should_log": false,
|
| 304 |
+
"should_save": true,
|
| 305 |
+
"should_training_stop": true
|
| 306 |
+
},
|
| 307 |
+
"attributes": {}
|
| 308 |
+
}
|
| 309 |
+
},
|
| 310 |
+
"total_flos": 0.0,
|
| 311 |
+
"train_batch_size": 16,
|
| 312 |
+
"trial_name": null,
|
| 313 |
+
"trial_params": null
|
| 314 |
+
}
|
checkpoint-1600/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7723484b76e3b6987a8b0a858181c2717fdd25b357cc44ab00f93c060430bb84
|
| 3 |
+
size 5432
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b66c242f59af7e4b516c2b5be311457519f9d0e0b9aabcc32f73ba193a1d5f9
|
| 3 |
+
size 1112204984
|
sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
| 3 |
+
size 5069051
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
|
| 3 |
+
size 17082999
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"250001": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": true,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "<mask>",
|
| 50 |
+
"max_length": 128,
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"pad_to_multiple_of": null,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"pad_token_type_id": 0,
|
| 55 |
+
"padding_side": "right",
|
| 56 |
+
"sep_token": "</s>",
|
| 57 |
+
"stride": 0,
|
| 58 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 59 |
+
"truncation_side": "right",
|
| 60 |
+
"truncation_strategy": "longest_first",
|
| 61 |
+
"unk_token": "<unk>"
|
| 62 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:22e9182a0c83a61efb7c1d7502abc67edd78b2ca5e16cb469bd582cfedf7be9e
|
| 3 |
+
size 5432
|