Upload model weights
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- finbert_lora_min_preproc_!?_counts/checkpoint-11780/model.safetensors +3 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-11780/optimizer.pt +3 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-11780/rng_state.pth +3 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-11780/scaler.pt +3 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-11780/scheduler.pt +3 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-11780/special_tokens_map.json +7 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-11780/tokenizer.json +0 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-11780/tokenizer_config.json +58 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-11780/trainer_state.json +109 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-11780/training_args.bin +3 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-11780/vocab.txt +0 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-2356/model.safetensors +3 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-2356/optimizer.pt +3 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-2356/rng_state.pth +3 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-2356/scaler.pt +3 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-2356/scheduler.pt +3 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-2356/special_tokens_map.json +7 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-2356/tokenizer.json +0 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-2356/tokenizer_config.json +58 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-2356/trainer_state.json +49 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-2356/training_args.bin +3 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-2356/vocab.txt +0 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-4712/model.safetensors +3 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-4712/optimizer.pt +3 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-4712/rng_state.pth +3 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-4712/scaler.pt +3 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-4712/scheduler.pt +3 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-4712/special_tokens_map.json +7 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-4712/tokenizer.json +0 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-4712/tokenizer_config.json +58 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-4712/trainer_state.json +64 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-4712/training_args.bin +3 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-4712/vocab.txt +0 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-7068/model.safetensors +3 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-7068/optimizer.pt +3 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-7068/rng_state.pth +3 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-7068/scaler.pt +3 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-7068/scheduler.pt +3 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-7068/special_tokens_map.json +7 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-7068/tokenizer.json +0 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-7068/tokenizer_config.json +58 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-7068/trainer_state.json +79 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-7068/training_args.bin +3 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-7068/vocab.txt +0 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-9424/model.safetensors +3 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-9424/optimizer.pt +3 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-9424/rng_state.pth +3 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-9424/scaler.pt +3 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-9424/scheduler.pt +3 -0
- finbert_lora_min_preproc_!?_counts/checkpoint-9424/special_tokens_map.json +7 -0
finbert_lora_min_preproc_!?_counts/checkpoint-11780/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0468e417f5948d9e7cd58f1ddacdeb0b17b3c55ba8e5a2a89f1fd7bd267d3b21
|
| 3 |
+
size 448726780
|
finbert_lora_min_preproc_!?_counts/checkpoint-11780/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fd742d73c9e7bf5cbb01e4da707a659a397272a3a45c56489d05627d0c50b82
|
| 3 |
+
size 21573242
|
finbert_lora_min_preproc_!?_counts/checkpoint-11780/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a931f2a7b0659cb40e0c9d637976743b95c2093e92acfdae9156aeb907532c91
|
| 3 |
+
size 14244
|
finbert_lora_min_preproc_!?_counts/checkpoint-11780/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d51593ca0c3e0aa87ee0f6999bede68275838908c1ee06993ef664fb9cef5fc
|
| 3 |
+
size 988
|
finbert_lora_min_preproc_!?_counts/checkpoint-11780/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b32377d5249f5af1a19c87ec58c8ab1bc3c8e45187e0212881906397210d4c46
|
| 3 |
+
size 1064
|
finbert_lora_min_preproc_!?_counts/checkpoint-11780/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
finbert_lora_min_preproc_!?_counts/checkpoint-11780/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
finbert_lora_min_preproc_!?_counts/checkpoint-11780/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"model_max_length": 512,
|
| 51 |
+
"never_split": null,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"strip_accents": null,
|
| 55 |
+
"tokenize_chinese_chars": true,
|
| 56 |
+
"tokenizer_class": "BertTokenizer",
|
| 57 |
+
"unk_token": "[UNK]"
|
| 58 |
+
}
|
finbert_lora_min_preproc_!?_counts/checkpoint-11780/trainer_state.json
ADDED
|
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 5.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 11780,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 1.0,
|
| 14 |
+
"grad_norm": 11.115736961364746,
|
| 15 |
+
"learning_rate": 1.67145390070922e-05,
|
| 16 |
+
"loss": 0.6787,
|
| 17 |
+
"step": 2356
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.0,
|
| 21 |
+
"eval_loss": 0.5063199400901794,
|
| 22 |
+
"eval_runtime": 35.607,
|
| 23 |
+
"eval_samples_per_second": 264.611,
|
| 24 |
+
"eval_steps_per_second": 33.083,
|
| 25 |
+
"step": 2356
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 2.0,
|
| 29 |
+
"grad_norm": 9.299896240234375,
|
| 30 |
+
"learning_rate": 1.2537234042553193e-05,
|
| 31 |
+
"loss": 0.4788,
|
| 32 |
+
"step": 4712
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.0,
|
| 36 |
+
"eval_loss": 0.45463240146636963,
|
| 37 |
+
"eval_runtime": 34.8873,
|
| 38 |
+
"eval_samples_per_second": 270.069,
|
| 39 |
+
"eval_steps_per_second": 33.766,
|
| 40 |
+
"step": 4712
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 3.0,
|
| 44 |
+
"grad_norm": 10.606963157653809,
|
| 45 |
+
"learning_rate": 8.361702127659575e-06,
|
| 46 |
+
"loss": 0.4244,
|
| 47 |
+
"step": 7068
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 3.0,
|
| 51 |
+
"eval_loss": 0.42691749334335327,
|
| 52 |
+
"eval_runtime": 35.7558,
|
| 53 |
+
"eval_samples_per_second": 263.51,
|
| 54 |
+
"eval_steps_per_second": 32.946,
|
| 55 |
+
"step": 7068
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 4.0,
|
| 59 |
+
"grad_norm": 19.405630111694336,
|
| 60 |
+
"learning_rate": 4.186170212765957e-06,
|
| 61 |
+
"loss": 0.3954,
|
| 62 |
+
"step": 9424
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 4.0,
|
| 66 |
+
"eval_loss": 0.4201417565345764,
|
| 67 |
+
"eval_runtime": 35.2439,
|
| 68 |
+
"eval_samples_per_second": 267.337,
|
| 69 |
+
"eval_steps_per_second": 33.424,
|
| 70 |
+
"step": 9424
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 5.0,
|
| 74 |
+
"grad_norm": 12.378179550170898,
|
| 75 |
+
"learning_rate": 8.865248226950355e-09,
|
| 76 |
+
"loss": 0.3776,
|
| 77 |
+
"step": 11780
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 5.0,
|
| 81 |
+
"eval_loss": 0.41366884112358093,
|
| 82 |
+
"eval_runtime": 35.1938,
|
| 83 |
+
"eval_samples_per_second": 267.717,
|
| 84 |
+
"eval_steps_per_second": 33.472,
|
| 85 |
+
"step": 11780
|
| 86 |
+
}
|
| 87 |
+
],
|
| 88 |
+
"logging_steps": 500,
|
| 89 |
+
"max_steps": 11780,
|
| 90 |
+
"num_input_tokens_seen": 0,
|
| 91 |
+
"num_train_epochs": 5,
|
| 92 |
+
"save_steps": 500,
|
| 93 |
+
"stateful_callbacks": {
|
| 94 |
+
"TrainerControl": {
|
| 95 |
+
"args": {
|
| 96 |
+
"should_epoch_stop": false,
|
| 97 |
+
"should_evaluate": false,
|
| 98 |
+
"should_log": false,
|
| 99 |
+
"should_save": true,
|
| 100 |
+
"should_training_stop": true
|
| 101 |
+
},
|
| 102 |
+
"attributes": {}
|
| 103 |
+
}
|
| 104 |
+
},
|
| 105 |
+
"total_flos": 0.0,
|
| 106 |
+
"train_batch_size": 16,
|
| 107 |
+
"trial_name": null,
|
| 108 |
+
"trial_params": null
|
| 109 |
+
}
|
finbert_lora_min_preproc_!?_counts/checkpoint-11780/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:725e2fe58a72e4b29fe3f6a5b626eac75fe0a4ad9fe868ba53adb37455faa43c
|
| 3 |
+
size 5368
|
finbert_lora_min_preproc_!?_counts/checkpoint-11780/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
finbert_lora_min_preproc_!?_counts/checkpoint-2356/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db35fec93a39fd3c35088726c559f26d745d2fb596563a54adcdc6f916f9e267
|
| 3 |
+
size 448726780
|
finbert_lora_min_preproc_!?_counts/checkpoint-2356/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2474faeb1d645a89cd06898a096b143b789adae148b1a658e60983314e5b889
|
| 3 |
+
size 21573242
|
finbert_lora_min_preproc_!?_counts/checkpoint-2356/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8234425ebe1f20b90a57493484f22bcf986ea42006d38e4f79647ef40738e57
|
| 3 |
+
size 14244
|
finbert_lora_min_preproc_!?_counts/checkpoint-2356/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f341c779725deee8988be43ec54b0f0a9a2dda1cba241891ebe666e4aff2407
|
| 3 |
+
size 988
|
finbert_lora_min_preproc_!?_counts/checkpoint-2356/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7fe589cc000ba64b43850090ccf6eb762e6fb08c080c081766e34c43f47ef28
|
| 3 |
+
size 1064
|
finbert_lora_min_preproc_!?_counts/checkpoint-2356/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
finbert_lora_min_preproc_!?_counts/checkpoint-2356/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
finbert_lora_min_preproc_!?_counts/checkpoint-2356/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"model_max_length": 512,
|
| 51 |
+
"never_split": null,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"strip_accents": null,
|
| 55 |
+
"tokenize_chinese_chars": true,
|
| 56 |
+
"tokenizer_class": "BertTokenizer",
|
| 57 |
+
"unk_token": "[UNK]"
|
| 58 |
+
}
|
finbert_lora_min_preproc_!?_counts/checkpoint-2356/trainer_state.json
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2356,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 1.0,
|
| 14 |
+
"grad_norm": 11.115736961364746,
|
| 15 |
+
"learning_rate": 1.67145390070922e-05,
|
| 16 |
+
"loss": 0.6787,
|
| 17 |
+
"step": 2356
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.0,
|
| 21 |
+
"eval_loss": 0.5063199400901794,
|
| 22 |
+
"eval_runtime": 35.607,
|
| 23 |
+
"eval_samples_per_second": 264.611,
|
| 24 |
+
"eval_steps_per_second": 33.083,
|
| 25 |
+
"step": 2356
|
| 26 |
+
}
|
| 27 |
+
],
|
| 28 |
+
"logging_steps": 500,
|
| 29 |
+
"max_steps": 11780,
|
| 30 |
+
"num_input_tokens_seen": 0,
|
| 31 |
+
"num_train_epochs": 5,
|
| 32 |
+
"save_steps": 500,
|
| 33 |
+
"stateful_callbacks": {
|
| 34 |
+
"TrainerControl": {
|
| 35 |
+
"args": {
|
| 36 |
+
"should_epoch_stop": false,
|
| 37 |
+
"should_evaluate": false,
|
| 38 |
+
"should_log": false,
|
| 39 |
+
"should_save": true,
|
| 40 |
+
"should_training_stop": false
|
| 41 |
+
},
|
| 42 |
+
"attributes": {}
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"total_flos": 0.0,
|
| 46 |
+
"train_batch_size": 16,
|
| 47 |
+
"trial_name": null,
|
| 48 |
+
"trial_params": null
|
| 49 |
+
}
|
finbert_lora_min_preproc_!?_counts/checkpoint-2356/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:725e2fe58a72e4b29fe3f6a5b626eac75fe0a4ad9fe868ba53adb37455faa43c
|
| 3 |
+
size 5368
|
finbert_lora_min_preproc_!?_counts/checkpoint-2356/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
finbert_lora_min_preproc_!?_counts/checkpoint-4712/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:560e16332626b46250dad54da1225d7bedafe6f325b3d2fd81c83ccdeb106d0f
|
| 3 |
+
size 448726780
|
finbert_lora_min_preproc_!?_counts/checkpoint-4712/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd098dbe526f15416f93f1155a12c6f39678b1b9d2a1209014d7be2cf11e6d31
|
| 3 |
+
size 21573242
|
finbert_lora_min_preproc_!?_counts/checkpoint-4712/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8e1b8b9445a5be059577a7069f588e8473a6218058baa7d60b183630c4128fa
|
| 3 |
+
size 14244
|
finbert_lora_min_preproc_!?_counts/checkpoint-4712/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4afc8c4224adb5ee49e930ccb8e817836d27ed9557454893b0a375dc213de635
|
| 3 |
+
size 988
|
finbert_lora_min_preproc_!?_counts/checkpoint-4712/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a92b14c791876f730d83283639ccf0437b6d940edb33a7f0034af2d7b909ee00
|
| 3 |
+
size 1064
|
finbert_lora_min_preproc_!?_counts/checkpoint-4712/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
finbert_lora_min_preproc_!?_counts/checkpoint-4712/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
finbert_lora_min_preproc_!?_counts/checkpoint-4712/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"model_max_length": 512,
|
| 51 |
+
"never_split": null,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"strip_accents": null,
|
| 55 |
+
"tokenize_chinese_chars": true,
|
| 56 |
+
"tokenizer_class": "BertTokenizer",
|
| 57 |
+
"unk_token": "[UNK]"
|
| 58 |
+
}
|
finbert_lora_min_preproc_!?_counts/checkpoint-4712/trainer_state.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 4712,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 1.0,
|
| 14 |
+
"grad_norm": 11.115736961364746,
|
| 15 |
+
"learning_rate": 1.67145390070922e-05,
|
| 16 |
+
"loss": 0.6787,
|
| 17 |
+
"step": 2356
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.0,
|
| 21 |
+
"eval_loss": 0.5063199400901794,
|
| 22 |
+
"eval_runtime": 35.607,
|
| 23 |
+
"eval_samples_per_second": 264.611,
|
| 24 |
+
"eval_steps_per_second": 33.083,
|
| 25 |
+
"step": 2356
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 2.0,
|
| 29 |
+
"grad_norm": 9.299896240234375,
|
| 30 |
+
"learning_rate": 1.2537234042553193e-05,
|
| 31 |
+
"loss": 0.4788,
|
| 32 |
+
"step": 4712
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.0,
|
| 36 |
+
"eval_loss": 0.45463240146636963,
|
| 37 |
+
"eval_runtime": 34.8873,
|
| 38 |
+
"eval_samples_per_second": 270.069,
|
| 39 |
+
"eval_steps_per_second": 33.766,
|
| 40 |
+
"step": 4712
|
| 41 |
+
}
|
| 42 |
+
],
|
| 43 |
+
"logging_steps": 500,
|
| 44 |
+
"max_steps": 11780,
|
| 45 |
+
"num_input_tokens_seen": 0,
|
| 46 |
+
"num_train_epochs": 5,
|
| 47 |
+
"save_steps": 500,
|
| 48 |
+
"stateful_callbacks": {
|
| 49 |
+
"TrainerControl": {
|
| 50 |
+
"args": {
|
| 51 |
+
"should_epoch_stop": false,
|
| 52 |
+
"should_evaluate": false,
|
| 53 |
+
"should_log": false,
|
| 54 |
+
"should_save": true,
|
| 55 |
+
"should_training_stop": false
|
| 56 |
+
},
|
| 57 |
+
"attributes": {}
|
| 58 |
+
}
|
| 59 |
+
},
|
| 60 |
+
"total_flos": 0.0,
|
| 61 |
+
"train_batch_size": 16,
|
| 62 |
+
"trial_name": null,
|
| 63 |
+
"trial_params": null
|
| 64 |
+
}
|
finbert_lora_min_preproc_!?_counts/checkpoint-4712/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:725e2fe58a72e4b29fe3f6a5b626eac75fe0a4ad9fe868ba53adb37455faa43c
|
| 3 |
+
size 5368
|
finbert_lora_min_preproc_!?_counts/checkpoint-4712/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
finbert_lora_min_preproc_!?_counts/checkpoint-7068/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afd33db6715e43fe9035d84cdd41fd361b144a296ac1867058d0c452dacbd65a
|
| 3 |
+
size 448726780
|
finbert_lora_min_preproc_!?_counts/checkpoint-7068/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:709581918e320026a61a584eb98cf80593ee67adaf08828d9a4777ba1ff2ea87
|
| 3 |
+
size 21573242
|
finbert_lora_min_preproc_!?_counts/checkpoint-7068/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d2bd502e3435745ef53e40b9f0514dd653c1a9b7fb3a79ffb441c80847353aa
|
| 3 |
+
size 14244
|
finbert_lora_min_preproc_!?_counts/checkpoint-7068/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ba5fe912ee9627be345b08f77228a0b591de4c15a5f322e2a63f2145bdd875b
|
| 3 |
+
size 988
|
finbert_lora_min_preproc_!?_counts/checkpoint-7068/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9501e101d249b8657f0f5a4bc52a62622b89b076dcaf6b8024fc6546a90e07c3
|
| 3 |
+
size 1064
|
finbert_lora_min_preproc_!?_counts/checkpoint-7068/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
finbert_lora_min_preproc_!?_counts/checkpoint-7068/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
finbert_lora_min_preproc_!?_counts/checkpoint-7068/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"model_max_length": 512,
|
| 51 |
+
"never_split": null,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"strip_accents": null,
|
| 55 |
+
"tokenize_chinese_chars": true,
|
| 56 |
+
"tokenizer_class": "BertTokenizer",
|
| 57 |
+
"unk_token": "[UNK]"
|
| 58 |
+
}
|
finbert_lora_min_preproc_!?_counts/checkpoint-7068/trainer_state.json
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 7068,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 1.0,
|
| 14 |
+
"grad_norm": 11.115736961364746,
|
| 15 |
+
"learning_rate": 1.67145390070922e-05,
|
| 16 |
+
"loss": 0.6787,
|
| 17 |
+
"step": 2356
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.0,
|
| 21 |
+
"eval_loss": 0.5063199400901794,
|
| 22 |
+
"eval_runtime": 35.607,
|
| 23 |
+
"eval_samples_per_second": 264.611,
|
| 24 |
+
"eval_steps_per_second": 33.083,
|
| 25 |
+
"step": 2356
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 2.0,
|
| 29 |
+
"grad_norm": 9.299896240234375,
|
| 30 |
+
"learning_rate": 1.2537234042553193e-05,
|
| 31 |
+
"loss": 0.4788,
|
| 32 |
+
"step": 4712
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.0,
|
| 36 |
+
"eval_loss": 0.45463240146636963,
|
| 37 |
+
"eval_runtime": 34.8873,
|
| 38 |
+
"eval_samples_per_second": 270.069,
|
| 39 |
+
"eval_steps_per_second": 33.766,
|
| 40 |
+
"step": 4712
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 3.0,
|
| 44 |
+
"grad_norm": 10.606963157653809,
|
| 45 |
+
"learning_rate": 8.361702127659575e-06,
|
| 46 |
+
"loss": 0.4244,
|
| 47 |
+
"step": 7068
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 3.0,
|
| 51 |
+
"eval_loss": 0.42691749334335327,
|
| 52 |
+
"eval_runtime": 35.7558,
|
| 53 |
+
"eval_samples_per_second": 263.51,
|
| 54 |
+
"eval_steps_per_second": 32.946,
|
| 55 |
+
"step": 7068
|
| 56 |
+
}
|
| 57 |
+
],
|
| 58 |
+
"logging_steps": 500,
|
| 59 |
+
"max_steps": 11780,
|
| 60 |
+
"num_input_tokens_seen": 0,
|
| 61 |
+
"num_train_epochs": 5,
|
| 62 |
+
"save_steps": 500,
|
| 63 |
+
"stateful_callbacks": {
|
| 64 |
+
"TrainerControl": {
|
| 65 |
+
"args": {
|
| 66 |
+
"should_epoch_stop": false,
|
| 67 |
+
"should_evaluate": false,
|
| 68 |
+
"should_log": false,
|
| 69 |
+
"should_save": true,
|
| 70 |
+
"should_training_stop": false
|
| 71 |
+
},
|
| 72 |
+
"attributes": {}
|
| 73 |
+
}
|
| 74 |
+
},
|
| 75 |
+
"total_flos": 0.0,
|
| 76 |
+
"train_batch_size": 16,
|
| 77 |
+
"trial_name": null,
|
| 78 |
+
"trial_params": null
|
| 79 |
+
}
|
finbert_lora_min_preproc_!?_counts/checkpoint-7068/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:725e2fe58a72e4b29fe3f6a5b626eac75fe0a4ad9fe868ba53adb37455faa43c
|
| 3 |
+
size 5368
|
finbert_lora_min_preproc_!?_counts/checkpoint-7068/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
finbert_lora_min_preproc_!?_counts/checkpoint-9424/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba78350bd20a213db02c1d5bd63627a3ad9e6afc0880cdc05434ad7c23c4a170
|
| 3 |
+
size 448726780
|
finbert_lora_min_preproc_!?_counts/checkpoint-9424/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad76132e54cdf213b44b428a342f50cab78e52eb634fe0271dae0f4659b93f62
|
| 3 |
+
size 21573242
|
finbert_lora_min_preproc_!?_counts/checkpoint-9424/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a68fd5a69285d569dbb315a89d90807e8d84a3352378ad79fc89f1abf87d75a
|
| 3 |
+
size 14244
|
finbert_lora_min_preproc_!?_counts/checkpoint-9424/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52a372d65dff74e82843d2e16be76ac8f6dfcd79b436b05ec20be121044341ef
|
| 3 |
+
size 988
|
finbert_lora_min_preproc_!?_counts/checkpoint-9424/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:efcb144c2fbfa0d52bc6d2a4fc30ecc9f22abb92da18c32db31456a960aaa9f8
|
| 3 |
+
size 1064
|
finbert_lora_min_preproc_!?_counts/checkpoint-9424/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|