Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- distilbert/distilbert_base_uncased_amazon/README.md +76 -0
- distilbert/distilbert_base_uncased_amazon/all_results.json +23 -0
- distilbert/distilbert_base_uncased_amazon/checkpoint-550/config.json +76 -0
- distilbert/distilbert_base_uncased_amazon/checkpoint-550/model.safetensors +3 -0
- distilbert/distilbert_base_uncased_amazon/checkpoint-550/optimizer.pt +3 -0
- distilbert/distilbert_base_uncased_amazon/checkpoint-550/rng_state_0.pth +3 -0
- distilbert/distilbert_base_uncased_amazon/checkpoint-550/rng_state_1.pth +3 -0
- distilbert/distilbert_base_uncased_amazon/checkpoint-550/scheduler.pt +3 -0
- distilbert/distilbert_base_uncased_amazon/checkpoint-550/special_tokens_map.json +7 -0
- distilbert/distilbert_base_uncased_amazon/checkpoint-550/tokenizer.json +0 -0
- distilbert/distilbert_base_uncased_amazon/checkpoint-550/tokenizer_config.json +55 -0
- distilbert/distilbert_base_uncased_amazon/checkpoint-550/trainer_state.json +527 -0
- distilbert/distilbert_base_uncased_amazon/checkpoint-550/training_args.bin +3 -0
- distilbert/distilbert_base_uncased_amazon/checkpoint-550/vocab.txt +0 -0
- distilbert/distilbert_base_uncased_amazon/config.json +76 -0
- distilbert/distilbert_base_uncased_amazon/eval_results.json +11 -0
- distilbert/distilbert_base_uncased_amazon/model.safetensors +3 -0
- distilbert/distilbert_base_uncased_amazon/run.log +4 -0
- distilbert/distilbert_base_uncased_amazon/special_tokens_map.json +7 -0
- distilbert/distilbert_base_uncased_amazon/test_results.json +10 -0
- distilbert/distilbert_base_uncased_amazon/tokenizer.json +0 -0
- distilbert/distilbert_base_uncased_amazon/tokenizer_config.json +55 -0
- distilbert/distilbert_base_uncased_amazon/train_results.json +8 -0
- distilbert/distilbert_base_uncased_amazon/trainer_state.json +550 -0
- distilbert/distilbert_base_uncased_amazon/training_args.bin +3 -0
- distilbert/distilbert_base_uncased_amazon/vocab.txt +0 -0
- distilbert/distilbert_base_uncased_ledgar/README.md +93 -0
- distilbert/distilbert_base_uncased_ledgar/all_results.json +23 -0
- distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/config.json +230 -0
- distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/model.safetensors +3 -0
- distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/optimizer.pt +3 -0
- distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/rng_state_0.pth +3 -0
- distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/rng_state_1.pth +3 -0
- distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/scheduler.pt +3 -0
- distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/special_tokens_map.json +7 -0
- distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/tokenizer.json +0 -0
- distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/tokenizer_config.json +55 -0
- distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/trainer_state.json +1113 -0
- distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/training_args.bin +3 -0
- distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/vocab.txt +0 -0
- distilbert/distilbert_base_uncased_ledgar/config.json +230 -0
- distilbert/distilbert_base_uncased_ledgar/eval_results.json +11 -0
- distilbert/distilbert_base_uncased_ledgar/model.safetensors +3 -0
- distilbert/distilbert_base_uncased_ledgar/run.log +4 -0
- distilbert/distilbert_base_uncased_ledgar/special_tokens_map.json +7 -0
- distilbert/distilbert_base_uncased_ledgar/test_results.json +10 -0
- distilbert/distilbert_base_uncased_ledgar/tokenizer.json +0 -0
- distilbert/distilbert_base_uncased_ledgar/tokenizer_config.json +55 -0
- distilbert/distilbert_base_uncased_ledgar/train_results.json +8 -0
- distilbert/distilbert_base_uncased_ledgar/trainer_state.json +1122 -0
distilbert/distilbert_base_uncased_amazon/README.md
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: distilbert/distilbert-base-uncased
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: distilbert_base_uncased_amazon
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# distilbert_base_uncased_amazon
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.9130
|
| 21 |
+
- Accuracy: 0.7576
|
| 22 |
+
- F1 Macro: 0.6904
|
| 23 |
+
- F1 Micro: 0.7576
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 2e-05
|
| 43 |
+
- train_batch_size: 32
|
| 44 |
+
- eval_batch_size: 32
|
| 45 |
+
- seed: 42
|
| 46 |
+
- distributed_type: multi-GPU
|
| 47 |
+
- num_devices: 2
|
| 48 |
+
- total_train_batch_size: 64
|
| 49 |
+
- total_eval_batch_size: 64
|
| 50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: linear
|
| 52 |
+
- num_epochs: 3.0
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro |
|
| 57 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:|
|
| 58 |
+
| 2.6322 | 0.26 | 50 | 2.5191 | 0.4750 | 0.3209 | 0.4750 |
|
| 59 |
+
| 1.9044 | 0.53 | 100 | 1.8323 | 0.6014 | 0.4626 | 0.6014 |
|
| 60 |
+
| 1.5127 | 0.79 | 150 | 1.4810 | 0.6574 | 0.5154 | 0.6574 |
|
| 61 |
+
| 1.2857 | 1.05 | 200 | 1.2679 | 0.6983 | 0.5795 | 0.6983 |
|
| 62 |
+
| 1.0669 | 1.32 | 250 | 1.1415 | 0.7306 | 0.6376 | 0.7306 |
|
| 63 |
+
| 1.0931 | 1.58 | 300 | 1.0669 | 0.7312 | 0.6333 | 0.7312 |
|
| 64 |
+
| 0.9879 | 1.84 | 350 | 1.0102 | 0.7437 | 0.6542 | 0.7437 |
|
| 65 |
+
| 0.8936 | 2.11 | 400 | 0.9650 | 0.7444 | 0.6640 | 0.7444 |
|
| 66 |
+
| 0.8345 | 2.37 | 450 | 0.9389 | 0.7582 | 0.6900 | 0.7582 |
|
| 67 |
+
| 0.7851 | 2.63 | 500 | 0.9208 | 0.7628 | 0.6924 | 0.7628 |
|
| 68 |
+
| 0.8439 | 2.89 | 550 | 0.9130 | 0.7576 | 0.6904 | 0.7576 |
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
### Framework versions
|
| 72 |
+
|
| 73 |
+
- Transformers 4.39.0.dev0
|
| 74 |
+
- Pytorch 2.2.1+cu121
|
| 75 |
+
- Datasets 2.18.0
|
| 76 |
+
- Tokenizers 0.15.2
|
distilbert/distilbert_base_uncased_amazon/all_results.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.7575757575757576,
|
| 4 |
+
"eval_f1_macro": 0.6903636946713366,
|
| 5 |
+
"eval_f1_micro": 0.7575757575757576,
|
| 6 |
+
"eval_loss": 0.9129917025566101,
|
| 7 |
+
"eval_runtime": 0.8205,
|
| 8 |
+
"eval_samples": 1518,
|
| 9 |
+
"eval_samples_per_second": 1850.15,
|
| 10 |
+
"eval_steps_per_second": 29.251,
|
| 11 |
+
"test_accuracy": 0.7977602108036891,
|
| 12 |
+
"test_f1_macro": 0.7193918798114766,
|
| 13 |
+
"test_f1_micro": 0.7977602108036891,
|
| 14 |
+
"test_loss": 0.8355989456176758,
|
| 15 |
+
"test_runtime": 0.8172,
|
| 16 |
+
"test_samples_per_second": 1857.675,
|
| 17 |
+
"test_steps_per_second": 29.37,
|
| 18 |
+
"train_loss": 1.337625675870661,
|
| 19 |
+
"train_runtime": 76.5319,
|
| 20 |
+
"train_samples": 12144,
|
| 21 |
+
"train_samples_per_second": 476.037,
|
| 22 |
+
"train_steps_per_second": 7.448
|
| 23 |
+
}
|
distilbert/distilbert_base_uncased_amazon/checkpoint-550/config.json
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert/distilbert-base-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"finetuning_task": "text-classification",
|
| 11 |
+
"hidden_dim": 3072,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "0",
|
| 14 |
+
"1": "1",
|
| 15 |
+
"2": "10",
|
| 16 |
+
"3": "11",
|
| 17 |
+
"4": "12",
|
| 18 |
+
"5": "13",
|
| 19 |
+
"6": "14",
|
| 20 |
+
"7": "15",
|
| 21 |
+
"8": "16",
|
| 22 |
+
"9": "17",
|
| 23 |
+
"10": "18",
|
| 24 |
+
"11": "19",
|
| 25 |
+
"12": "2",
|
| 26 |
+
"13": "20",
|
| 27 |
+
"14": "21",
|
| 28 |
+
"15": "22",
|
| 29 |
+
"16": "3",
|
| 30 |
+
"17": "4",
|
| 31 |
+
"18": "5",
|
| 32 |
+
"19": "6",
|
| 33 |
+
"20": "7",
|
| 34 |
+
"21": "8",
|
| 35 |
+
"22": "9"
|
| 36 |
+
},
|
| 37 |
+
"initializer_range": 0.02,
|
| 38 |
+
"label2id": {
|
| 39 |
+
"0": 0,
|
| 40 |
+
"1": 1,
|
| 41 |
+
"10": 2,
|
| 42 |
+
"11": 3,
|
| 43 |
+
"12": 4,
|
| 44 |
+
"13": 5,
|
| 45 |
+
"14": 6,
|
| 46 |
+
"15": 7,
|
| 47 |
+
"16": 8,
|
| 48 |
+
"17": 9,
|
| 49 |
+
"18": 10,
|
| 50 |
+
"19": 11,
|
| 51 |
+
"2": 12,
|
| 52 |
+
"20": 13,
|
| 53 |
+
"21": 14,
|
| 54 |
+
"22": 15,
|
| 55 |
+
"3": 16,
|
| 56 |
+
"4": 17,
|
| 57 |
+
"5": 18,
|
| 58 |
+
"6": 19,
|
| 59 |
+
"7": 20,
|
| 60 |
+
"8": 21,
|
| 61 |
+
"9": 22
|
| 62 |
+
},
|
| 63 |
+
"max_position_embeddings": 512,
|
| 64 |
+
"model_type": "distilbert",
|
| 65 |
+
"n_heads": 12,
|
| 66 |
+
"n_layers": 6,
|
| 67 |
+
"pad_token_id": 0,
|
| 68 |
+
"problem_type": "single_label_classification",
|
| 69 |
+
"qa_dropout": 0.1,
|
| 70 |
+
"seq_classif_dropout": 0.2,
|
| 71 |
+
"sinusoidal_pos_embds": false,
|
| 72 |
+
"tie_weights_": true,
|
| 73 |
+
"torch_dtype": "float32",
|
| 74 |
+
"transformers_version": "4.39.0.dev0",
|
| 75 |
+
"vocab_size": 30522
|
| 76 |
+
}
|
distilbert/distilbert_base_uncased_amazon/checkpoint-550/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7a2b20954a040273afa09c71bc0fc3b9c120c59929ac11f51e2563bf7a8a3ac
|
| 3 |
+
size 267897164
|
distilbert/distilbert_base_uncased_amazon/checkpoint-550/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b734bde4381f1d0ff452ecc329f9c084a5551b1f87df5fac7cf62cd4efbd74b1
|
| 3 |
+
size 535856442
|
distilbert/distilbert_base_uncased_amazon/checkpoint-550/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b67a83968d47ceab6c21e55fd13bff581ec3a9c894292d9d0afe411a920a0b7b
|
| 3 |
+
size 14512
|
distilbert/distilbert_base_uncased_amazon/checkpoint-550/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:483ba1aa85118f9a035ef3245808628af83afe4b124f3325c5abd172c655e78f
|
| 3 |
+
size 14512
|
distilbert/distilbert_base_uncased_amazon/checkpoint-550/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6304996f9341a5bf8bd2ea4d7e28f3f6c868b8f16d95b47d99cce2e178763052
|
| 3 |
+
size 1064
|
distilbert/distilbert_base_uncased_amazon/checkpoint-550/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 |
+
}
|
distilbert/distilbert_base_uncased_amazon/checkpoint-550/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
distilbert/distilbert_base_uncased_amazon/checkpoint-550/tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_lower_case": true,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"strip_accents": null,
|
| 52 |
+
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
distilbert/distilbert_base_uncased_amazon/checkpoint-550/trainer_state.json
ADDED
|
@@ -0,0 +1,527 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9129917025566101,
|
| 3 |
+
"best_model_checkpoint": "../../experiments_checkpoints/MAdAiLab/distilbert/distilbert_base_uncased_amazon/checkpoint-550",
|
| 4 |
+
"epoch": 2.8947368421052633,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 550,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05,
|
| 13 |
+
"grad_norm": 1.327728271484375,
|
| 14 |
+
"learning_rate": 1.9649122807017544e-05,
|
| 15 |
+
"loss": 3.109,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.11,
|
| 20 |
+
"grad_norm": 1.7082853317260742,
|
| 21 |
+
"learning_rate": 1.929824561403509e-05,
|
| 22 |
+
"loss": 3.048,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.16,
|
| 27 |
+
"grad_norm": 1.893571138381958,
|
| 28 |
+
"learning_rate": 1.894736842105263e-05,
|
| 29 |
+
"loss": 2.9327,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.21,
|
| 34 |
+
"grad_norm": 1.9520453214645386,
|
| 35 |
+
"learning_rate": 1.8596491228070176e-05,
|
| 36 |
+
"loss": 2.7781,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.26,
|
| 41 |
+
"grad_norm": 2.1847422122955322,
|
| 42 |
+
"learning_rate": 1.824561403508772e-05,
|
| 43 |
+
"loss": 2.6322,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.26,
|
| 48 |
+
"eval_accuracy": 0.4749670619235837,
|
| 49 |
+
"eval_f1_macro": 0.3209193957177527,
|
| 50 |
+
"eval_f1_micro": 0.4749670619235837,
|
| 51 |
+
"eval_loss": 2.519139528274536,
|
| 52 |
+
"eval_runtime": 0.7577,
|
| 53 |
+
"eval_samples_per_second": 2003.426,
|
| 54 |
+
"eval_steps_per_second": 31.675,
|
| 55 |
+
"step": 50
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.32,
|
| 59 |
+
"grad_norm": 2.446019411087036,
|
| 60 |
+
"learning_rate": 1.7894736842105264e-05,
|
| 61 |
+
"loss": 2.4648,
|
| 62 |
+
"step": 60
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.37,
|
| 66 |
+
"grad_norm": 2.346569538116455,
|
| 67 |
+
"learning_rate": 1.754385964912281e-05,
|
| 68 |
+
"loss": 2.2919,
|
| 69 |
+
"step": 70
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.42,
|
| 73 |
+
"grad_norm": 2.682988405227661,
|
| 74 |
+
"learning_rate": 1.719298245614035e-05,
|
| 75 |
+
"loss": 2.1292,
|
| 76 |
+
"step": 80
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.47,
|
| 80 |
+
"grad_norm": 2.50565242767334,
|
| 81 |
+
"learning_rate": 1.6842105263157896e-05,
|
| 82 |
+
"loss": 2.0467,
|
| 83 |
+
"step": 90
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.53,
|
| 87 |
+
"grad_norm": 2.4023382663726807,
|
| 88 |
+
"learning_rate": 1.649122807017544e-05,
|
| 89 |
+
"loss": 1.9044,
|
| 90 |
+
"step": 100
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.53,
|
| 94 |
+
"eval_accuracy": 0.6014492753623188,
|
| 95 |
+
"eval_f1_macro": 0.4625900098895629,
|
| 96 |
+
"eval_f1_micro": 0.6014492753623188,
|
| 97 |
+
"eval_loss": 1.8323251008987427,
|
| 98 |
+
"eval_runtime": 0.7593,
|
| 99 |
+
"eval_samples_per_second": 1999.241,
|
| 100 |
+
"eval_steps_per_second": 31.609,
|
| 101 |
+
"step": 100
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.58,
|
| 105 |
+
"grad_norm": 2.8123605251312256,
|
| 106 |
+
"learning_rate": 1.6140350877192984e-05,
|
| 107 |
+
"loss": 1.7838,
|
| 108 |
+
"step": 110
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.63,
|
| 112 |
+
"grad_norm": 2.5916481018066406,
|
| 113 |
+
"learning_rate": 1.578947368421053e-05,
|
| 114 |
+
"loss": 1.7117,
|
| 115 |
+
"step": 120
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.68,
|
| 119 |
+
"grad_norm": 3.583634853363037,
|
| 120 |
+
"learning_rate": 1.543859649122807e-05,
|
| 121 |
+
"loss": 1.6639,
|
| 122 |
+
"step": 130
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.74,
|
| 126 |
+
"grad_norm": 3.1771187782287598,
|
| 127 |
+
"learning_rate": 1.5087719298245615e-05,
|
| 128 |
+
"loss": 1.6064,
|
| 129 |
+
"step": 140
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.79,
|
| 133 |
+
"grad_norm": 3.575974464416504,
|
| 134 |
+
"learning_rate": 1.4736842105263159e-05,
|
| 135 |
+
"loss": 1.5127,
|
| 136 |
+
"step": 150
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.79,
|
| 140 |
+
"eval_accuracy": 0.6574440052700923,
|
| 141 |
+
"eval_f1_macro": 0.5153852800565432,
|
| 142 |
+
"eval_f1_micro": 0.6574440052700923,
|
| 143 |
+
"eval_loss": 1.4809564352035522,
|
| 144 |
+
"eval_runtime": 0.7651,
|
| 145 |
+
"eval_samples_per_second": 1984.0,
|
| 146 |
+
"eval_steps_per_second": 31.368,
|
| 147 |
+
"step": 150
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.84,
|
| 151 |
+
"grad_norm": 3.4453086853027344,
|
| 152 |
+
"learning_rate": 1.4385964912280704e-05,
|
| 153 |
+
"loss": 1.5096,
|
| 154 |
+
"step": 160
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.89,
|
| 158 |
+
"grad_norm": 3.194457530975342,
|
| 159 |
+
"learning_rate": 1.4035087719298246e-05,
|
| 160 |
+
"loss": 1.4366,
|
| 161 |
+
"step": 170
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.95,
|
| 165 |
+
"grad_norm": 2.7298433780670166,
|
| 166 |
+
"learning_rate": 1.3684210526315791e-05,
|
| 167 |
+
"loss": 1.3785,
|
| 168 |
+
"step": 180
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.0,
|
| 172 |
+
"grad_norm": 3.8832905292510986,
|
| 173 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 174 |
+
"loss": 1.4003,
|
| 175 |
+
"step": 190
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 1.05,
|
| 179 |
+
"grad_norm": 3.53489089012146,
|
| 180 |
+
"learning_rate": 1.2982456140350879e-05,
|
| 181 |
+
"loss": 1.2857,
|
| 182 |
+
"step": 200
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.05,
|
| 186 |
+
"eval_accuracy": 0.6982872200263505,
|
| 187 |
+
"eval_f1_macro": 0.5795313200947776,
|
| 188 |
+
"eval_f1_micro": 0.6982872200263505,
|
| 189 |
+
"eval_loss": 1.2679345607757568,
|
| 190 |
+
"eval_runtime": 0.8173,
|
| 191 |
+
"eval_samples_per_second": 1857.339,
|
| 192 |
+
"eval_steps_per_second": 29.365,
|
| 193 |
+
"step": 200
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.11,
|
| 197 |
+
"grad_norm": 3.6431682109832764,
|
| 198 |
+
"learning_rate": 1.263157894736842e-05,
|
| 199 |
+
"loss": 1.2646,
|
| 200 |
+
"step": 210
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.16,
|
| 204 |
+
"grad_norm": 3.8024988174438477,
|
| 205 |
+
"learning_rate": 1.2280701754385966e-05,
|
| 206 |
+
"loss": 1.229,
|
| 207 |
+
"step": 220
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.21,
|
| 211 |
+
"grad_norm": 4.475400924682617,
|
| 212 |
+
"learning_rate": 1.192982456140351e-05,
|
| 213 |
+
"loss": 1.2163,
|
| 214 |
+
"step": 230
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.26,
|
| 218 |
+
"grad_norm": 3.2734055519104004,
|
| 219 |
+
"learning_rate": 1.1578947368421053e-05,
|
| 220 |
+
"loss": 1.12,
|
| 221 |
+
"step": 240
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.32,
|
| 225 |
+
"grad_norm": 3.5318431854248047,
|
| 226 |
+
"learning_rate": 1.1228070175438597e-05,
|
| 227 |
+
"loss": 1.0669,
|
| 228 |
+
"step": 250
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.32,
|
| 232 |
+
"eval_accuracy": 0.730566534914361,
|
| 233 |
+
"eval_f1_macro": 0.6376220869475787,
|
| 234 |
+
"eval_f1_micro": 0.730566534914361,
|
| 235 |
+
"eval_loss": 1.1414965391159058,
|
| 236 |
+
"eval_runtime": 0.7652,
|
| 237 |
+
"eval_samples_per_second": 1983.819,
|
| 238 |
+
"eval_steps_per_second": 31.365,
|
| 239 |
+
"step": 250
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.37,
|
| 243 |
+
"grad_norm": 3.1338298320770264,
|
| 244 |
+
"learning_rate": 1.0877192982456142e-05,
|
| 245 |
+
"loss": 1.0747,
|
| 246 |
+
"step": 260
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.42,
|
| 250 |
+
"grad_norm": 3.7175045013427734,
|
| 251 |
+
"learning_rate": 1.0526315789473684e-05,
|
| 252 |
+
"loss": 1.1091,
|
| 253 |
+
"step": 270
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 1.47,
|
| 257 |
+
"grad_norm": 2.825385093688965,
|
| 258 |
+
"learning_rate": 1.017543859649123e-05,
|
| 259 |
+
"loss": 1.0954,
|
| 260 |
+
"step": 280
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.53,
|
| 264 |
+
"grad_norm": 4.713174343109131,
|
| 265 |
+
"learning_rate": 9.824561403508772e-06,
|
| 266 |
+
"loss": 0.9891,
|
| 267 |
+
"step": 290
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.58,
|
| 271 |
+
"grad_norm": 4.003322124481201,
|
| 272 |
+
"learning_rate": 9.473684210526315e-06,
|
| 273 |
+
"loss": 1.0931,
|
| 274 |
+
"step": 300
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.58,
|
| 278 |
+
"eval_accuracy": 0.7312252964426877,
|
| 279 |
+
"eval_f1_macro": 0.6332619788197302,
|
| 280 |
+
"eval_f1_micro": 0.7312252964426877,
|
| 281 |
+
"eval_loss": 1.0668787956237793,
|
| 282 |
+
"eval_runtime": 0.7678,
|
| 283 |
+
"eval_samples_per_second": 1977.083,
|
| 284 |
+
"eval_steps_per_second": 31.258,
|
| 285 |
+
"step": 300
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.63,
|
| 289 |
+
"grad_norm": 3.055854082107544,
|
| 290 |
+
"learning_rate": 9.12280701754386e-06,
|
| 291 |
+
"loss": 1.0605,
|
| 292 |
+
"step": 310
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 1.68,
|
| 296 |
+
"grad_norm": 3.6614320278167725,
|
| 297 |
+
"learning_rate": 8.771929824561405e-06,
|
| 298 |
+
"loss": 0.9953,
|
| 299 |
+
"step": 320
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.74,
|
| 303 |
+
"grad_norm": 4.1040449142456055,
|
| 304 |
+
"learning_rate": 8.421052631578948e-06,
|
| 305 |
+
"loss": 1.0317,
|
| 306 |
+
"step": 330
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.79,
|
| 310 |
+
"grad_norm": 4.793609619140625,
|
| 311 |
+
"learning_rate": 8.070175438596492e-06,
|
| 312 |
+
"loss": 1.1011,
|
| 313 |
+
"step": 340
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.84,
|
| 317 |
+
"grad_norm": 5.102194786071777,
|
| 318 |
+
"learning_rate": 7.719298245614036e-06,
|
| 319 |
+
"loss": 0.9879,
|
| 320 |
+
"step": 350
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.84,
|
| 324 |
+
"eval_accuracy": 0.7437417654808959,
|
| 325 |
+
"eval_f1_macro": 0.6541772971492381,
|
| 326 |
+
"eval_f1_micro": 0.7437417654808959,
|
| 327 |
+
"eval_loss": 1.0101571083068848,
|
| 328 |
+
"eval_runtime": 0.8196,
|
| 329 |
+
"eval_samples_per_second": 1852.047,
|
| 330 |
+
"eval_steps_per_second": 29.281,
|
| 331 |
+
"step": 350
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.89,
|
| 335 |
+
"grad_norm": 5.22916841506958,
|
| 336 |
+
"learning_rate": 7.368421052631579e-06,
|
| 337 |
+
"loss": 0.9148,
|
| 338 |
+
"step": 360
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.95,
|
| 342 |
+
"grad_norm": 4.314509391784668,
|
| 343 |
+
"learning_rate": 7.017543859649123e-06,
|
| 344 |
+
"loss": 0.9774,
|
| 345 |
+
"step": 370
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.0,
|
| 349 |
+
"grad_norm": 4.692554950714111,
|
| 350 |
+
"learning_rate": 6.666666666666667e-06,
|
| 351 |
+
"loss": 0.9843,
|
| 352 |
+
"step": 380
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 2.05,
|
| 356 |
+
"grad_norm": 4.54512357711792,
|
| 357 |
+
"learning_rate": 6.31578947368421e-06,
|
| 358 |
+
"loss": 0.9259,
|
| 359 |
+
"step": 390
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 2.11,
|
| 363 |
+
"grad_norm": 3.737957715988159,
|
| 364 |
+
"learning_rate": 5.964912280701755e-06,
|
| 365 |
+
"loss": 0.8936,
|
| 366 |
+
"step": 400
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 2.11,
|
| 370 |
+
"eval_accuracy": 0.7444005270092227,
|
| 371 |
+
"eval_f1_macro": 0.6640066115044797,
|
| 372 |
+
"eval_f1_micro": 0.7444005270092227,
|
| 373 |
+
"eval_loss": 0.9649816751480103,
|
| 374 |
+
"eval_runtime": 0.8189,
|
| 375 |
+
"eval_samples_per_second": 1853.724,
|
| 376 |
+
"eval_steps_per_second": 29.308,
|
| 377 |
+
"step": 400
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 2.16,
|
| 381 |
+
"grad_norm": 3.669529914855957,
|
| 382 |
+
"learning_rate": 5.6140350877192985e-06,
|
| 383 |
+
"loss": 0.8246,
|
| 384 |
+
"step": 410
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 2.21,
|
| 388 |
+
"grad_norm": 3.788975954055786,
|
| 389 |
+
"learning_rate": 5.263157894736842e-06,
|
| 390 |
+
"loss": 0.8956,
|
| 391 |
+
"step": 420
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 2.26,
|
| 395 |
+
"grad_norm": 4.400717258453369,
|
| 396 |
+
"learning_rate": 4.912280701754386e-06,
|
| 397 |
+
"loss": 0.8508,
|
| 398 |
+
"step": 430
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 2.32,
|
| 402 |
+
"grad_norm": 4.932755470275879,
|
| 403 |
+
"learning_rate": 4.56140350877193e-06,
|
| 404 |
+
"loss": 0.9209,
|
| 405 |
+
"step": 440
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 2.37,
|
| 409 |
+
"grad_norm": 3.4981260299682617,
|
| 410 |
+
"learning_rate": 4.210526315789474e-06,
|
| 411 |
+
"loss": 0.8345,
|
| 412 |
+
"step": 450
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 2.37,
|
| 416 |
+
"eval_accuracy": 0.7582345191040843,
|
| 417 |
+
"eval_f1_macro": 0.6900497906953322,
|
| 418 |
+
"eval_f1_micro": 0.7582345191040843,
|
| 419 |
+
"eval_loss": 0.9388595819473267,
|
| 420 |
+
"eval_runtime": 0.8212,
|
| 421 |
+
"eval_samples_per_second": 1848.509,
|
| 422 |
+
"eval_steps_per_second": 29.225,
|
| 423 |
+
"step": 450
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.42,
|
| 427 |
+
"grad_norm": 3.988497257232666,
|
| 428 |
+
"learning_rate": 3.859649122807018e-06,
|
| 429 |
+
"loss": 0.8174,
|
| 430 |
+
"step": 460
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 2.47,
|
| 434 |
+
"grad_norm": 4.119844913482666,
|
| 435 |
+
"learning_rate": 3.5087719298245615e-06,
|
| 436 |
+
"loss": 0.9026,
|
| 437 |
+
"step": 470
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 2.53,
|
| 441 |
+
"grad_norm": 3.8894877433776855,
|
| 442 |
+
"learning_rate": 3.157894736842105e-06,
|
| 443 |
+
"loss": 0.8755,
|
| 444 |
+
"step": 480
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.58,
|
| 448 |
+
"grad_norm": 3.8152105808258057,
|
| 449 |
+
"learning_rate": 2.8070175438596493e-06,
|
| 450 |
+
"loss": 0.8427,
|
| 451 |
+
"step": 490
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 2.63,
|
| 455 |
+
"grad_norm": 3.738555908203125,
|
| 456 |
+
"learning_rate": 2.456140350877193e-06,
|
| 457 |
+
"loss": 0.7851,
|
| 458 |
+
"step": 500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.63,
|
| 462 |
+
"eval_accuracy": 0.7628458498023716,
|
| 463 |
+
"eval_f1_macro": 0.6923797058622336,
|
| 464 |
+
"eval_f1_micro": 0.7628458498023716,
|
| 465 |
+
"eval_loss": 0.9207842350006104,
|
| 466 |
+
"eval_runtime": 0.8212,
|
| 467 |
+
"eval_samples_per_second": 1848.55,
|
| 468 |
+
"eval_steps_per_second": 29.226,
|
| 469 |
+
"step": 500
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 2.68,
|
| 473 |
+
"grad_norm": 4.088294506072998,
|
| 474 |
+
"learning_rate": 2.105263157894737e-06,
|
| 475 |
+
"loss": 0.8308,
|
| 476 |
+
"step": 510
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 2.74,
|
| 480 |
+
"grad_norm": 4.426513195037842,
|
| 481 |
+
"learning_rate": 1.7543859649122807e-06,
|
| 482 |
+
"loss": 0.8498,
|
| 483 |
+
"step": 520
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.79,
|
| 487 |
+
"grad_norm": 3.5125749111175537,
|
| 488 |
+
"learning_rate": 1.4035087719298246e-06,
|
| 489 |
+
"loss": 0.8491,
|
| 490 |
+
"step": 530
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 2.84,
|
| 494 |
+
"grad_norm": 4.475162982940674,
|
| 495 |
+
"learning_rate": 1.0526315789473685e-06,
|
| 496 |
+
"loss": 0.7996,
|
| 497 |
+
"step": 540
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 2.89,
|
| 501 |
+
"grad_norm": 4.1890549659729,
|
| 502 |
+
"learning_rate": 7.017543859649123e-07,
|
| 503 |
+
"loss": 0.8439,
|
| 504 |
+
"step": 550
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 2.89,
|
| 508 |
+
"eval_accuracy": 0.7575757575757576,
|
| 509 |
+
"eval_f1_macro": 0.6903636946713366,
|
| 510 |
+
"eval_f1_micro": 0.7575757575757576,
|
| 511 |
+
"eval_loss": 0.9129917025566101,
|
| 512 |
+
"eval_runtime": 0.8209,
|
| 513 |
+
"eval_samples_per_second": 1849.148,
|
| 514 |
+
"eval_steps_per_second": 29.236,
|
| 515 |
+
"step": 550
|
| 516 |
+
}
|
| 517 |
+
],
|
| 518 |
+
"logging_steps": 10,
|
| 519 |
+
"max_steps": 570,
|
| 520 |
+
"num_input_tokens_seen": 0,
|
| 521 |
+
"num_train_epochs": 3,
|
| 522 |
+
"save_steps": 50,
|
| 523 |
+
"total_flos": 1166149628723200.0,
|
| 524 |
+
"train_batch_size": 32,
|
| 525 |
+
"trial_name": null,
|
| 526 |
+
"trial_params": null
|
| 527 |
+
}
|
distilbert/distilbert_base_uncased_amazon/checkpoint-550/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:603c6424933245f35a2f655b8c521a4ff45efd3684afacb7c5dcb242ad12888a
|
| 3 |
+
size 5112
|
distilbert/distilbert_base_uncased_amazon/checkpoint-550/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
distilbert/distilbert_base_uncased_amazon/config.json
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert/distilbert-base-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"finetuning_task": "text-classification",
|
| 11 |
+
"hidden_dim": 3072,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "0",
|
| 14 |
+
"1": "1",
|
| 15 |
+
"2": "10",
|
| 16 |
+
"3": "11",
|
| 17 |
+
"4": "12",
|
| 18 |
+
"5": "13",
|
| 19 |
+
"6": "14",
|
| 20 |
+
"7": "15",
|
| 21 |
+
"8": "16",
|
| 22 |
+
"9": "17",
|
| 23 |
+
"10": "18",
|
| 24 |
+
"11": "19",
|
| 25 |
+
"12": "2",
|
| 26 |
+
"13": "20",
|
| 27 |
+
"14": "21",
|
| 28 |
+
"15": "22",
|
| 29 |
+
"16": "3",
|
| 30 |
+
"17": "4",
|
| 31 |
+
"18": "5",
|
| 32 |
+
"19": "6",
|
| 33 |
+
"20": "7",
|
| 34 |
+
"21": "8",
|
| 35 |
+
"22": "9"
|
| 36 |
+
},
|
| 37 |
+
"initializer_range": 0.02,
|
| 38 |
+
"label2id": {
|
| 39 |
+
"0": 0,
|
| 40 |
+
"1": 1,
|
| 41 |
+
"10": 2,
|
| 42 |
+
"11": 3,
|
| 43 |
+
"12": 4,
|
| 44 |
+
"13": 5,
|
| 45 |
+
"14": 6,
|
| 46 |
+
"15": 7,
|
| 47 |
+
"16": 8,
|
| 48 |
+
"17": 9,
|
| 49 |
+
"18": 10,
|
| 50 |
+
"19": 11,
|
| 51 |
+
"2": 12,
|
| 52 |
+
"20": 13,
|
| 53 |
+
"21": 14,
|
| 54 |
+
"22": 15,
|
| 55 |
+
"3": 16,
|
| 56 |
+
"4": 17,
|
| 57 |
+
"5": 18,
|
| 58 |
+
"6": 19,
|
| 59 |
+
"7": 20,
|
| 60 |
+
"8": 21,
|
| 61 |
+
"9": 22
|
| 62 |
+
},
|
| 63 |
+
"max_position_embeddings": 512,
|
| 64 |
+
"model_type": "distilbert",
|
| 65 |
+
"n_heads": 12,
|
| 66 |
+
"n_layers": 6,
|
| 67 |
+
"pad_token_id": 0,
|
| 68 |
+
"problem_type": "single_label_classification",
|
| 69 |
+
"qa_dropout": 0.1,
|
| 70 |
+
"seq_classif_dropout": 0.2,
|
| 71 |
+
"sinusoidal_pos_embds": false,
|
| 72 |
+
"tie_weights_": true,
|
| 73 |
+
"torch_dtype": "float32",
|
| 74 |
+
"transformers_version": "4.39.0.dev0",
|
| 75 |
+
"vocab_size": 30522
|
| 76 |
+
}
|
distilbert/distilbert_base_uncased_amazon/eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.7575757575757576,
|
| 4 |
+
"eval_f1_macro": 0.6903636946713366,
|
| 5 |
+
"eval_f1_micro": 0.7575757575757576,
|
| 6 |
+
"eval_loss": 0.9129917025566101,
|
| 7 |
+
"eval_runtime": 0.8205,
|
| 8 |
+
"eval_samples": 1518,
|
| 9 |
+
"eval_samples_per_second": 1850.15,
|
| 10 |
+
"eval_steps_per_second": 29.251
|
| 11 |
+
}
|
distilbert/distilbert_base_uncased_amazon/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7a2b20954a040273afa09c71bc0fc3b9c120c59929ac11f51e2563bf7a8a3ac
|
| 3 |
+
size 267897164
|
distilbert/distilbert_base_uncased_amazon/run.log
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
03/15/2024 10:49:01 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: True, 16-bits training: False
|
| 2 |
+
03/15/2024 10:49:01 - WARNING - __main__ - Process rank: 1, device: cuda:1, n_gpu: 1, distributed training: True, 16-bits training: False
|
| 3 |
+
03/15/2024 10:49:04 - WARNING - __main__ - The label2id key in the model config.json is not equal to the label2id key of this run. You can ignore this if you are doing finetuning.
|
| 4 |
+
03/15/2024 10:49:05 - WARNING - __main__ - The label2id key in the model config.json is not equal to the label2id key of this run. You can ignore this if you are doing finetuning.
|
distilbert/distilbert_base_uncased_amazon/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 |
+
}
|
distilbert/distilbert_base_uncased_amazon/test_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"test_accuracy": 0.7977602108036891,
|
| 4 |
+
"test_f1_macro": 0.7193918798114766,
|
| 5 |
+
"test_f1_micro": 0.7977602108036891,
|
| 6 |
+
"test_loss": 0.8355989456176758,
|
| 7 |
+
"test_runtime": 0.8172,
|
| 8 |
+
"test_samples_per_second": 1857.675,
|
| 9 |
+
"test_steps_per_second": 29.37
|
| 10 |
+
}
|
distilbert/distilbert_base_uncased_amazon/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
distilbert/distilbert_base_uncased_amazon/tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_lower_case": true,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"strip_accents": null,
|
| 52 |
+
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
distilbert/distilbert_base_uncased_amazon/train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 1.337625675870661,
|
| 4 |
+
"train_runtime": 76.5319,
|
| 5 |
+
"train_samples": 12144,
|
| 6 |
+
"train_samples_per_second": 476.037,
|
| 7 |
+
"train_steps_per_second": 7.448
|
| 8 |
+
}
|
distilbert/distilbert_base_uncased_amazon/trainer_state.json
ADDED
|
@@ -0,0 +1,550 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9129917025566101,
|
| 3 |
+
"best_model_checkpoint": "../../experiments_checkpoints/MAdAiLab/distilbert/distilbert_base_uncased_amazon/checkpoint-550",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 570,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05,
|
| 13 |
+
"grad_norm": 1.327728271484375,
|
| 14 |
+
"learning_rate": 1.9649122807017544e-05,
|
| 15 |
+
"loss": 3.109,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.11,
|
| 20 |
+
"grad_norm": 1.7082853317260742,
|
| 21 |
+
"learning_rate": 1.929824561403509e-05,
|
| 22 |
+
"loss": 3.048,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.16,
|
| 27 |
+
"grad_norm": 1.893571138381958,
|
| 28 |
+
"learning_rate": 1.894736842105263e-05,
|
| 29 |
+
"loss": 2.9327,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.21,
|
| 34 |
+
"grad_norm": 1.9520453214645386,
|
| 35 |
+
"learning_rate": 1.8596491228070176e-05,
|
| 36 |
+
"loss": 2.7781,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.26,
|
| 41 |
+
"grad_norm": 2.1847422122955322,
|
| 42 |
+
"learning_rate": 1.824561403508772e-05,
|
| 43 |
+
"loss": 2.6322,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.26,
|
| 48 |
+
"eval_accuracy": 0.4749670619235837,
|
| 49 |
+
"eval_f1_macro": 0.3209193957177527,
|
| 50 |
+
"eval_f1_micro": 0.4749670619235837,
|
| 51 |
+
"eval_loss": 2.519139528274536,
|
| 52 |
+
"eval_runtime": 0.7577,
|
| 53 |
+
"eval_samples_per_second": 2003.426,
|
| 54 |
+
"eval_steps_per_second": 31.675,
|
| 55 |
+
"step": 50
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.32,
|
| 59 |
+
"grad_norm": 2.446019411087036,
|
| 60 |
+
"learning_rate": 1.7894736842105264e-05,
|
| 61 |
+
"loss": 2.4648,
|
| 62 |
+
"step": 60
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.37,
|
| 66 |
+
"grad_norm": 2.346569538116455,
|
| 67 |
+
"learning_rate": 1.754385964912281e-05,
|
| 68 |
+
"loss": 2.2919,
|
| 69 |
+
"step": 70
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.42,
|
| 73 |
+
"grad_norm": 2.682988405227661,
|
| 74 |
+
"learning_rate": 1.719298245614035e-05,
|
| 75 |
+
"loss": 2.1292,
|
| 76 |
+
"step": 80
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.47,
|
| 80 |
+
"grad_norm": 2.50565242767334,
|
| 81 |
+
"learning_rate": 1.6842105263157896e-05,
|
| 82 |
+
"loss": 2.0467,
|
| 83 |
+
"step": 90
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.53,
|
| 87 |
+
"grad_norm": 2.4023382663726807,
|
| 88 |
+
"learning_rate": 1.649122807017544e-05,
|
| 89 |
+
"loss": 1.9044,
|
| 90 |
+
"step": 100
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.53,
|
| 94 |
+
"eval_accuracy": 0.6014492753623188,
|
| 95 |
+
"eval_f1_macro": 0.4625900098895629,
|
| 96 |
+
"eval_f1_micro": 0.6014492753623188,
|
| 97 |
+
"eval_loss": 1.8323251008987427,
|
| 98 |
+
"eval_runtime": 0.7593,
|
| 99 |
+
"eval_samples_per_second": 1999.241,
|
| 100 |
+
"eval_steps_per_second": 31.609,
|
| 101 |
+
"step": 100
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.58,
|
| 105 |
+
"grad_norm": 2.8123605251312256,
|
| 106 |
+
"learning_rate": 1.6140350877192984e-05,
|
| 107 |
+
"loss": 1.7838,
|
| 108 |
+
"step": 110
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.63,
|
| 112 |
+
"grad_norm": 2.5916481018066406,
|
| 113 |
+
"learning_rate": 1.578947368421053e-05,
|
| 114 |
+
"loss": 1.7117,
|
| 115 |
+
"step": 120
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.68,
|
| 119 |
+
"grad_norm": 3.583634853363037,
|
| 120 |
+
"learning_rate": 1.543859649122807e-05,
|
| 121 |
+
"loss": 1.6639,
|
| 122 |
+
"step": 130
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.74,
|
| 126 |
+
"grad_norm": 3.1771187782287598,
|
| 127 |
+
"learning_rate": 1.5087719298245615e-05,
|
| 128 |
+
"loss": 1.6064,
|
| 129 |
+
"step": 140
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.79,
|
| 133 |
+
"grad_norm": 3.575974464416504,
|
| 134 |
+
"learning_rate": 1.4736842105263159e-05,
|
| 135 |
+
"loss": 1.5127,
|
| 136 |
+
"step": 150
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.79,
|
| 140 |
+
"eval_accuracy": 0.6574440052700923,
|
| 141 |
+
"eval_f1_macro": 0.5153852800565432,
|
| 142 |
+
"eval_f1_micro": 0.6574440052700923,
|
| 143 |
+
"eval_loss": 1.4809564352035522,
|
| 144 |
+
"eval_runtime": 0.7651,
|
| 145 |
+
"eval_samples_per_second": 1984.0,
|
| 146 |
+
"eval_steps_per_second": 31.368,
|
| 147 |
+
"step": 150
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.84,
|
| 151 |
+
"grad_norm": 3.4453086853027344,
|
| 152 |
+
"learning_rate": 1.4385964912280704e-05,
|
| 153 |
+
"loss": 1.5096,
|
| 154 |
+
"step": 160
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.89,
|
| 158 |
+
"grad_norm": 3.194457530975342,
|
| 159 |
+
"learning_rate": 1.4035087719298246e-05,
|
| 160 |
+
"loss": 1.4366,
|
| 161 |
+
"step": 170
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.95,
|
| 165 |
+
"grad_norm": 2.7298433780670166,
|
| 166 |
+
"learning_rate": 1.3684210526315791e-05,
|
| 167 |
+
"loss": 1.3785,
|
| 168 |
+
"step": 180
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.0,
|
| 172 |
+
"grad_norm": 3.8832905292510986,
|
| 173 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 174 |
+
"loss": 1.4003,
|
| 175 |
+
"step": 190
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 1.05,
|
| 179 |
+
"grad_norm": 3.53489089012146,
|
| 180 |
+
"learning_rate": 1.2982456140350879e-05,
|
| 181 |
+
"loss": 1.2857,
|
| 182 |
+
"step": 200
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.05,
|
| 186 |
+
"eval_accuracy": 0.6982872200263505,
|
| 187 |
+
"eval_f1_macro": 0.5795313200947776,
|
| 188 |
+
"eval_f1_micro": 0.6982872200263505,
|
| 189 |
+
"eval_loss": 1.2679345607757568,
|
| 190 |
+
"eval_runtime": 0.8173,
|
| 191 |
+
"eval_samples_per_second": 1857.339,
|
| 192 |
+
"eval_steps_per_second": 29.365,
|
| 193 |
+
"step": 200
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.11,
|
| 197 |
+
"grad_norm": 3.6431682109832764,
|
| 198 |
+
"learning_rate": 1.263157894736842e-05,
|
| 199 |
+
"loss": 1.2646,
|
| 200 |
+
"step": 210
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.16,
|
| 204 |
+
"grad_norm": 3.8024988174438477,
|
| 205 |
+
"learning_rate": 1.2280701754385966e-05,
|
| 206 |
+
"loss": 1.229,
|
| 207 |
+
"step": 220
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.21,
|
| 211 |
+
"grad_norm": 4.475400924682617,
|
| 212 |
+
"learning_rate": 1.192982456140351e-05,
|
| 213 |
+
"loss": 1.2163,
|
| 214 |
+
"step": 230
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.26,
|
| 218 |
+
"grad_norm": 3.2734055519104004,
|
| 219 |
+
"learning_rate": 1.1578947368421053e-05,
|
| 220 |
+
"loss": 1.12,
|
| 221 |
+
"step": 240
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.32,
|
| 225 |
+
"grad_norm": 3.5318431854248047,
|
| 226 |
+
"learning_rate": 1.1228070175438597e-05,
|
| 227 |
+
"loss": 1.0669,
|
| 228 |
+
"step": 250
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.32,
|
| 232 |
+
"eval_accuracy": 0.730566534914361,
|
| 233 |
+
"eval_f1_macro": 0.6376220869475787,
|
| 234 |
+
"eval_f1_micro": 0.730566534914361,
|
| 235 |
+
"eval_loss": 1.1414965391159058,
|
| 236 |
+
"eval_runtime": 0.7652,
|
| 237 |
+
"eval_samples_per_second": 1983.819,
|
| 238 |
+
"eval_steps_per_second": 31.365,
|
| 239 |
+
"step": 250
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.37,
|
| 243 |
+
"grad_norm": 3.1338298320770264,
|
| 244 |
+
"learning_rate": 1.0877192982456142e-05,
|
| 245 |
+
"loss": 1.0747,
|
| 246 |
+
"step": 260
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.42,
|
| 250 |
+
"grad_norm": 3.7175045013427734,
|
| 251 |
+
"learning_rate": 1.0526315789473684e-05,
|
| 252 |
+
"loss": 1.1091,
|
| 253 |
+
"step": 270
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 1.47,
|
| 257 |
+
"grad_norm": 2.825385093688965,
|
| 258 |
+
"learning_rate": 1.017543859649123e-05,
|
| 259 |
+
"loss": 1.0954,
|
| 260 |
+
"step": 280
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.53,
|
| 264 |
+
"grad_norm": 4.713174343109131,
|
| 265 |
+
"learning_rate": 9.824561403508772e-06,
|
| 266 |
+
"loss": 0.9891,
|
| 267 |
+
"step": 290
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.58,
|
| 271 |
+
"grad_norm": 4.003322124481201,
|
| 272 |
+
"learning_rate": 9.473684210526315e-06,
|
| 273 |
+
"loss": 1.0931,
|
| 274 |
+
"step": 300
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.58,
|
| 278 |
+
"eval_accuracy": 0.7312252964426877,
|
| 279 |
+
"eval_f1_macro": 0.6332619788197302,
|
| 280 |
+
"eval_f1_micro": 0.7312252964426877,
|
| 281 |
+
"eval_loss": 1.0668787956237793,
|
| 282 |
+
"eval_runtime": 0.7678,
|
| 283 |
+
"eval_samples_per_second": 1977.083,
|
| 284 |
+
"eval_steps_per_second": 31.258,
|
| 285 |
+
"step": 300
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.63,
|
| 289 |
+
"grad_norm": 3.055854082107544,
|
| 290 |
+
"learning_rate": 9.12280701754386e-06,
|
| 291 |
+
"loss": 1.0605,
|
| 292 |
+
"step": 310
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 1.68,
|
| 296 |
+
"grad_norm": 3.6614320278167725,
|
| 297 |
+
"learning_rate": 8.771929824561405e-06,
|
| 298 |
+
"loss": 0.9953,
|
| 299 |
+
"step": 320
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.74,
|
| 303 |
+
"grad_norm": 4.1040449142456055,
|
| 304 |
+
"learning_rate": 8.421052631578948e-06,
|
| 305 |
+
"loss": 1.0317,
|
| 306 |
+
"step": 330
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.79,
|
| 310 |
+
"grad_norm": 4.793609619140625,
|
| 311 |
+
"learning_rate": 8.070175438596492e-06,
|
| 312 |
+
"loss": 1.1011,
|
| 313 |
+
"step": 340
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.84,
|
| 317 |
+
"grad_norm": 5.102194786071777,
|
| 318 |
+
"learning_rate": 7.719298245614036e-06,
|
| 319 |
+
"loss": 0.9879,
|
| 320 |
+
"step": 350
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.84,
|
| 324 |
+
"eval_accuracy": 0.7437417654808959,
|
| 325 |
+
"eval_f1_macro": 0.6541772971492381,
|
| 326 |
+
"eval_f1_micro": 0.7437417654808959,
|
| 327 |
+
"eval_loss": 1.0101571083068848,
|
| 328 |
+
"eval_runtime": 0.8196,
|
| 329 |
+
"eval_samples_per_second": 1852.047,
|
| 330 |
+
"eval_steps_per_second": 29.281,
|
| 331 |
+
"step": 350
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.89,
|
| 335 |
+
"grad_norm": 5.22916841506958,
|
| 336 |
+
"learning_rate": 7.368421052631579e-06,
|
| 337 |
+
"loss": 0.9148,
|
| 338 |
+
"step": 360
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.95,
|
| 342 |
+
"grad_norm": 4.314509391784668,
|
| 343 |
+
"learning_rate": 7.017543859649123e-06,
|
| 344 |
+
"loss": 0.9774,
|
| 345 |
+
"step": 370
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.0,
|
| 349 |
+
"grad_norm": 4.692554950714111,
|
| 350 |
+
"learning_rate": 6.666666666666667e-06,
|
| 351 |
+
"loss": 0.9843,
|
| 352 |
+
"step": 380
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 2.05,
|
| 356 |
+
"grad_norm": 4.54512357711792,
|
| 357 |
+
"learning_rate": 6.31578947368421e-06,
|
| 358 |
+
"loss": 0.9259,
|
| 359 |
+
"step": 390
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 2.11,
|
| 363 |
+
"grad_norm": 3.737957715988159,
|
| 364 |
+
"learning_rate": 5.964912280701755e-06,
|
| 365 |
+
"loss": 0.8936,
|
| 366 |
+
"step": 400
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 2.11,
|
| 370 |
+
"eval_accuracy": 0.7444005270092227,
|
| 371 |
+
"eval_f1_macro": 0.6640066115044797,
|
| 372 |
+
"eval_f1_micro": 0.7444005270092227,
|
| 373 |
+
"eval_loss": 0.9649816751480103,
|
| 374 |
+
"eval_runtime": 0.8189,
|
| 375 |
+
"eval_samples_per_second": 1853.724,
|
| 376 |
+
"eval_steps_per_second": 29.308,
|
| 377 |
+
"step": 400
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 2.16,
|
| 381 |
+
"grad_norm": 3.669529914855957,
|
| 382 |
+
"learning_rate": 5.6140350877192985e-06,
|
| 383 |
+
"loss": 0.8246,
|
| 384 |
+
"step": 410
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 2.21,
|
| 388 |
+
"grad_norm": 3.788975954055786,
|
| 389 |
+
"learning_rate": 5.263157894736842e-06,
|
| 390 |
+
"loss": 0.8956,
|
| 391 |
+
"step": 420
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 2.26,
|
| 395 |
+
"grad_norm": 4.400717258453369,
|
| 396 |
+
"learning_rate": 4.912280701754386e-06,
|
| 397 |
+
"loss": 0.8508,
|
| 398 |
+
"step": 430
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 2.32,
|
| 402 |
+
"grad_norm": 4.932755470275879,
|
| 403 |
+
"learning_rate": 4.56140350877193e-06,
|
| 404 |
+
"loss": 0.9209,
|
| 405 |
+
"step": 440
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 2.37,
|
| 409 |
+
"grad_norm": 3.4981260299682617,
|
| 410 |
+
"learning_rate": 4.210526315789474e-06,
|
| 411 |
+
"loss": 0.8345,
|
| 412 |
+
"step": 450
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 2.37,
|
| 416 |
+
"eval_accuracy": 0.7582345191040843,
|
| 417 |
+
"eval_f1_macro": 0.6900497906953322,
|
| 418 |
+
"eval_f1_micro": 0.7582345191040843,
|
| 419 |
+
"eval_loss": 0.9388595819473267,
|
| 420 |
+
"eval_runtime": 0.8212,
|
| 421 |
+
"eval_samples_per_second": 1848.509,
|
| 422 |
+
"eval_steps_per_second": 29.225,
|
| 423 |
+
"step": 450
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.42,
|
| 427 |
+
"grad_norm": 3.988497257232666,
|
| 428 |
+
"learning_rate": 3.859649122807018e-06,
|
| 429 |
+
"loss": 0.8174,
|
| 430 |
+
"step": 460
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 2.47,
|
| 434 |
+
"grad_norm": 4.119844913482666,
|
| 435 |
+
"learning_rate": 3.5087719298245615e-06,
|
| 436 |
+
"loss": 0.9026,
|
| 437 |
+
"step": 470
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 2.53,
|
| 441 |
+
"grad_norm": 3.8894877433776855,
|
| 442 |
+
"learning_rate": 3.157894736842105e-06,
|
| 443 |
+
"loss": 0.8755,
|
| 444 |
+
"step": 480
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.58,
|
| 448 |
+
"grad_norm": 3.8152105808258057,
|
| 449 |
+
"learning_rate": 2.8070175438596493e-06,
|
| 450 |
+
"loss": 0.8427,
|
| 451 |
+
"step": 490
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 2.63,
|
| 455 |
+
"grad_norm": 3.738555908203125,
|
| 456 |
+
"learning_rate": 2.456140350877193e-06,
|
| 457 |
+
"loss": 0.7851,
|
| 458 |
+
"step": 500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.63,
|
| 462 |
+
"eval_accuracy": 0.7628458498023716,
|
| 463 |
+
"eval_f1_macro": 0.6923797058622336,
|
| 464 |
+
"eval_f1_micro": 0.7628458498023716,
|
| 465 |
+
"eval_loss": 0.9207842350006104,
|
| 466 |
+
"eval_runtime": 0.8212,
|
| 467 |
+
"eval_samples_per_second": 1848.55,
|
| 468 |
+
"eval_steps_per_second": 29.226,
|
| 469 |
+
"step": 500
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 2.68,
|
| 473 |
+
"grad_norm": 4.088294506072998,
|
| 474 |
+
"learning_rate": 2.105263157894737e-06,
|
| 475 |
+
"loss": 0.8308,
|
| 476 |
+
"step": 510
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 2.74,
|
| 480 |
+
"grad_norm": 4.426513195037842,
|
| 481 |
+
"learning_rate": 1.7543859649122807e-06,
|
| 482 |
+
"loss": 0.8498,
|
| 483 |
+
"step": 520
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.79,
|
| 487 |
+
"grad_norm": 3.5125749111175537,
|
| 488 |
+
"learning_rate": 1.4035087719298246e-06,
|
| 489 |
+
"loss": 0.8491,
|
| 490 |
+
"step": 530
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 2.84,
|
| 494 |
+
"grad_norm": 4.475162982940674,
|
| 495 |
+
"learning_rate": 1.0526315789473685e-06,
|
| 496 |
+
"loss": 0.7996,
|
| 497 |
+
"step": 540
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 2.89,
|
| 501 |
+
"grad_norm": 4.1890549659729,
|
| 502 |
+
"learning_rate": 7.017543859649123e-07,
|
| 503 |
+
"loss": 0.8439,
|
| 504 |
+
"step": 550
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 2.89,
|
| 508 |
+
"eval_accuracy": 0.7575757575757576,
|
| 509 |
+
"eval_f1_macro": 0.6903636946713366,
|
| 510 |
+
"eval_f1_micro": 0.7575757575757576,
|
| 511 |
+
"eval_loss": 0.9129917025566101,
|
| 512 |
+
"eval_runtime": 0.8209,
|
| 513 |
+
"eval_samples_per_second": 1849.148,
|
| 514 |
+
"eval_steps_per_second": 29.236,
|
| 515 |
+
"step": 550
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 2.95,
|
| 519 |
+
"grad_norm": 3.682612419128418,
|
| 520 |
+
"learning_rate": 3.5087719298245616e-07,
|
| 521 |
+
"loss": 0.8467,
|
| 522 |
+
"step": 560
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 3.0,
|
| 526 |
+
"grad_norm": 3.6457090377807617,
|
| 527 |
+
"learning_rate": 0.0,
|
| 528 |
+
"loss": 0.9181,
|
| 529 |
+
"step": 570
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 3.0,
|
| 533 |
+
"step": 570,
|
| 534 |
+
"total_flos": 1208555069767680.0,
|
| 535 |
+
"train_loss": 1.337625675870661,
|
| 536 |
+
"train_runtime": 76.5319,
|
| 537 |
+
"train_samples_per_second": 476.037,
|
| 538 |
+
"train_steps_per_second": 7.448
|
| 539 |
+
}
|
| 540 |
+
],
|
| 541 |
+
"logging_steps": 10,
|
| 542 |
+
"max_steps": 570,
|
| 543 |
+
"num_input_tokens_seen": 0,
|
| 544 |
+
"num_train_epochs": 3,
|
| 545 |
+
"save_steps": 50,
|
| 546 |
+
"total_flos": 1208555069767680.0,
|
| 547 |
+
"train_batch_size": 32,
|
| 548 |
+
"trial_name": null,
|
| 549 |
+
"trial_params": null
|
| 550 |
+
}
|
distilbert/distilbert_base_uncased_amazon/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:603c6424933245f35a2f655b8c521a4ff45efd3684afacb7c5dcb242ad12888a
|
| 3 |
+
size 5112
|
distilbert/distilbert_base_uncased_amazon/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
distilbert/distilbert_base_uncased_ledgar/README.md
ADDED
|
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: distilbert/distilbert-base-uncased
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: distilbert_base_uncased_ledgar
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# distilbert_base_uncased_ledgar
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.6496
|
| 21 |
+
- Accuracy: 0.8311
|
| 22 |
+
- F1 Macro: 0.7116
|
| 23 |
+
- F1 Micro: 0.8311
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 2e-05
|
| 43 |
+
- train_batch_size: 32
|
| 44 |
+
- eval_batch_size: 32
|
| 45 |
+
- seed: 42
|
| 46 |
+
- distributed_type: multi-GPU
|
| 47 |
+
- num_devices: 2
|
| 48 |
+
- total_train_batch_size: 64
|
| 49 |
+
- total_eval_batch_size: 64
|
| 50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: linear
|
| 52 |
+
- num_epochs: 3.0
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro |
|
| 57 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:|
|
| 58 |
+
| 3.8165 | 0.11 | 100 | 3.5952 | 0.3489 | 0.0995 | 0.3489 |
|
| 59 |
+
| 2.8293 | 0.21 | 200 | 2.6737 | 0.5385 | 0.2375 | 0.5385 |
|
| 60 |
+
| 2.2564 | 0.32 | 300 | 2.0960 | 0.6212 | 0.3339 | 0.6212 |
|
| 61 |
+
| 1.8259 | 0.43 | 400 | 1.7118 | 0.6792 | 0.4269 | 0.6792 |
|
| 62 |
+
| 1.5846 | 0.53 | 500 | 1.4543 | 0.7232 | 0.4987 | 0.7232 |
|
| 63 |
+
| 1.3927 | 0.64 | 600 | 1.2635 | 0.758 | 0.5628 | 0.758 |
|
| 64 |
+
| 1.2065 | 0.75 | 700 | 1.1217 | 0.7719 | 0.5782 | 0.7719 |
|
| 65 |
+
| 1.16 | 0.85 | 800 | 1.0303 | 0.7832 | 0.5984 | 0.7832 |
|
| 66 |
+
| 1.0168 | 0.96 | 900 | 0.9443 | 0.7887 | 0.6119 | 0.7887 |
|
| 67 |
+
| 0.9006 | 1.07 | 1000 | 0.8958 | 0.7934 | 0.6142 | 0.7934 |
|
| 68 |
+
| 0.8956 | 1.17 | 1100 | 0.8517 | 0.8002 | 0.6294 | 0.8002 |
|
| 69 |
+
| 0.9159 | 1.28 | 1200 | 0.8184 | 0.8033 | 0.6412 | 0.8033 |
|
| 70 |
+
| 0.8237 | 1.39 | 1300 | 0.7814 | 0.8077 | 0.6529 | 0.8077 |
|
| 71 |
+
| 0.7341 | 1.49 | 1400 | 0.7654 | 0.8099 | 0.6600 | 0.8099 |
|
| 72 |
+
| 0.7475 | 1.6 | 1500 | 0.7458 | 0.8135 | 0.6650 | 0.8135 |
|
| 73 |
+
| 0.7699 | 1.71 | 1600 | 0.7288 | 0.8183 | 0.6810 | 0.8183 |
|
| 74 |
+
| 0.7472 | 1.81 | 1700 | 0.7125 | 0.8179 | 0.6820 | 0.8179 |
|
| 75 |
+
| 0.689 | 1.92 | 1800 | 0.6965 | 0.8201 | 0.6822 | 0.8201 |
|
| 76 |
+
| 0.6807 | 2.03 | 1900 | 0.6904 | 0.8192 | 0.6799 | 0.8192 |
|
| 77 |
+
| 0.6514 | 2.13 | 2000 | 0.6836 | 0.8239 | 0.6923 | 0.8239 |
|
| 78 |
+
| 0.6662 | 2.24 | 2100 | 0.6750 | 0.8267 | 0.7019 | 0.8267 |
|
| 79 |
+
| 0.6247 | 2.35 | 2200 | 0.6703 | 0.8284 | 0.7028 | 0.8284 |
|
| 80 |
+
| 0.6443 | 2.45 | 2300 | 0.6662 | 0.8265 | 0.7001 | 0.8265 |
|
| 81 |
+
| 0.632 | 2.56 | 2400 | 0.6571 | 0.8295 | 0.7078 | 0.8295 |
|
| 82 |
+
| 0.5922 | 2.67 | 2500 | 0.6539 | 0.8298 | 0.7084 | 0.8298 |
|
| 83 |
+
| 0.6423 | 2.77 | 2600 | 0.6519 | 0.8311 | 0.7139 | 0.8311 |
|
| 84 |
+
| 0.6156 | 2.88 | 2700 | 0.6500 | 0.8311 | 0.7123 | 0.8311 |
|
| 85 |
+
| 0.6097 | 2.99 | 2800 | 0.6496 | 0.8311 | 0.7116 | 0.8311 |
|
| 86 |
+
|
| 87 |
+
|
| 88 |
+
### Framework versions
|
| 89 |
+
|
| 90 |
+
- Transformers 4.39.0.dev0
|
| 91 |
+
- Pytorch 2.2.1+cu121
|
| 92 |
+
- Datasets 2.18.0
|
| 93 |
+
- Tokenizers 0.15.2
|
distilbert/distilbert_base_uncased_ledgar/all_results.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.8311,
|
| 4 |
+
"eval_f1_macro": 0.7116365414985335,
|
| 5 |
+
"eval_f1_micro": 0.8311,
|
| 6 |
+
"eval_loss": 0.6496002674102783,
|
| 7 |
+
"eval_runtime": 5.097,
|
| 8 |
+
"eval_samples": 10000,
|
| 9 |
+
"eval_samples_per_second": 1961.935,
|
| 10 |
+
"eval_steps_per_second": 30.802,
|
| 11 |
+
"test_accuracy": 0.831,
|
| 12 |
+
"test_f1_macro": 0.702504756659894,
|
| 13 |
+
"test_f1_micro": 0.831,
|
| 14 |
+
"test_loss": 0.6615453362464905,
|
| 15 |
+
"test_runtime": 5.1002,
|
| 16 |
+
"test_samples_per_second": 1960.689,
|
| 17 |
+
"test_steps_per_second": 30.783,
|
| 18 |
+
"train_loss": 1.1483757653470232,
|
| 19 |
+
"train_runtime": 441.0175,
|
| 20 |
+
"train_samples": 60000,
|
| 21 |
+
"train_samples_per_second": 408.147,
|
| 22 |
+
"train_steps_per_second": 6.381
|
| 23 |
+
}
|
distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/config.json
ADDED
|
@@ -0,0 +1,230 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert/distilbert-base-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"finetuning_task": "text-classification",
|
| 11 |
+
"hidden_dim": 3072,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "0",
|
| 14 |
+
"1": "1",
|
| 15 |
+
"2": "10",
|
| 16 |
+
"3": "11",
|
| 17 |
+
"4": "12",
|
| 18 |
+
"5": "13",
|
| 19 |
+
"6": "14",
|
| 20 |
+
"7": "15",
|
| 21 |
+
"8": "16",
|
| 22 |
+
"9": "17",
|
| 23 |
+
"10": "18",
|
| 24 |
+
"11": "19",
|
| 25 |
+
"12": "2",
|
| 26 |
+
"13": "20",
|
| 27 |
+
"14": "21",
|
| 28 |
+
"15": "22",
|
| 29 |
+
"16": "23",
|
| 30 |
+
"17": "24",
|
| 31 |
+
"18": "25",
|
| 32 |
+
"19": "26",
|
| 33 |
+
"20": "27",
|
| 34 |
+
"21": "28",
|
| 35 |
+
"22": "29",
|
| 36 |
+
"23": "3",
|
| 37 |
+
"24": "30",
|
| 38 |
+
"25": "31",
|
| 39 |
+
"26": "32",
|
| 40 |
+
"27": "33",
|
| 41 |
+
"28": "34",
|
| 42 |
+
"29": "35",
|
| 43 |
+
"30": "36",
|
| 44 |
+
"31": "37",
|
| 45 |
+
"32": "38",
|
| 46 |
+
"33": "39",
|
| 47 |
+
"34": "4",
|
| 48 |
+
"35": "40",
|
| 49 |
+
"36": "41",
|
| 50 |
+
"37": "42",
|
| 51 |
+
"38": "43",
|
| 52 |
+
"39": "44",
|
| 53 |
+
"40": "45",
|
| 54 |
+
"41": "46",
|
| 55 |
+
"42": "47",
|
| 56 |
+
"43": "48",
|
| 57 |
+
"44": "49",
|
| 58 |
+
"45": "5",
|
| 59 |
+
"46": "50",
|
| 60 |
+
"47": "51",
|
| 61 |
+
"48": "52",
|
| 62 |
+
"49": "53",
|
| 63 |
+
"50": "54",
|
| 64 |
+
"51": "55",
|
| 65 |
+
"52": "56",
|
| 66 |
+
"53": "57",
|
| 67 |
+
"54": "58",
|
| 68 |
+
"55": "59",
|
| 69 |
+
"56": "6",
|
| 70 |
+
"57": "60",
|
| 71 |
+
"58": "61",
|
| 72 |
+
"59": "62",
|
| 73 |
+
"60": "63",
|
| 74 |
+
"61": "64",
|
| 75 |
+
"62": "65",
|
| 76 |
+
"63": "66",
|
| 77 |
+
"64": "67",
|
| 78 |
+
"65": "68",
|
| 79 |
+
"66": "69",
|
| 80 |
+
"67": "7",
|
| 81 |
+
"68": "70",
|
| 82 |
+
"69": "71",
|
| 83 |
+
"70": "72",
|
| 84 |
+
"71": "73",
|
| 85 |
+
"72": "74",
|
| 86 |
+
"73": "75",
|
| 87 |
+
"74": "76",
|
| 88 |
+
"75": "77",
|
| 89 |
+
"76": "78",
|
| 90 |
+
"77": "79",
|
| 91 |
+
"78": "8",
|
| 92 |
+
"79": "80",
|
| 93 |
+
"80": "81",
|
| 94 |
+
"81": "82",
|
| 95 |
+
"82": "83",
|
| 96 |
+
"83": "84",
|
| 97 |
+
"84": "85",
|
| 98 |
+
"85": "86",
|
| 99 |
+
"86": "87",
|
| 100 |
+
"87": "88",
|
| 101 |
+
"88": "89",
|
| 102 |
+
"89": "9",
|
| 103 |
+
"90": "90",
|
| 104 |
+
"91": "91",
|
| 105 |
+
"92": "92",
|
| 106 |
+
"93": "93",
|
| 107 |
+
"94": "94",
|
| 108 |
+
"95": "95",
|
| 109 |
+
"96": "96",
|
| 110 |
+
"97": "97",
|
| 111 |
+
"98": "98",
|
| 112 |
+
"99": "99"
|
| 113 |
+
},
|
| 114 |
+
"initializer_range": 0.02,
|
| 115 |
+
"label2id": {
|
| 116 |
+
"0": 0,
|
| 117 |
+
"1": 1,
|
| 118 |
+
"10": 2,
|
| 119 |
+
"11": 3,
|
| 120 |
+
"12": 4,
|
| 121 |
+
"13": 5,
|
| 122 |
+
"14": 6,
|
| 123 |
+
"15": 7,
|
| 124 |
+
"16": 8,
|
| 125 |
+
"17": 9,
|
| 126 |
+
"18": 10,
|
| 127 |
+
"19": 11,
|
| 128 |
+
"2": 12,
|
| 129 |
+
"20": 13,
|
| 130 |
+
"21": 14,
|
| 131 |
+
"22": 15,
|
| 132 |
+
"23": 16,
|
| 133 |
+
"24": 17,
|
| 134 |
+
"25": 18,
|
| 135 |
+
"26": 19,
|
| 136 |
+
"27": 20,
|
| 137 |
+
"28": 21,
|
| 138 |
+
"29": 22,
|
| 139 |
+
"3": 23,
|
| 140 |
+
"30": 24,
|
| 141 |
+
"31": 25,
|
| 142 |
+
"32": 26,
|
| 143 |
+
"33": 27,
|
| 144 |
+
"34": 28,
|
| 145 |
+
"35": 29,
|
| 146 |
+
"36": 30,
|
| 147 |
+
"37": 31,
|
| 148 |
+
"38": 32,
|
| 149 |
+
"39": 33,
|
| 150 |
+
"4": 34,
|
| 151 |
+
"40": 35,
|
| 152 |
+
"41": 36,
|
| 153 |
+
"42": 37,
|
| 154 |
+
"43": 38,
|
| 155 |
+
"44": 39,
|
| 156 |
+
"45": 40,
|
| 157 |
+
"46": 41,
|
| 158 |
+
"47": 42,
|
| 159 |
+
"48": 43,
|
| 160 |
+
"49": 44,
|
| 161 |
+
"5": 45,
|
| 162 |
+
"50": 46,
|
| 163 |
+
"51": 47,
|
| 164 |
+
"52": 48,
|
| 165 |
+
"53": 49,
|
| 166 |
+
"54": 50,
|
| 167 |
+
"55": 51,
|
| 168 |
+
"56": 52,
|
| 169 |
+
"57": 53,
|
| 170 |
+
"58": 54,
|
| 171 |
+
"59": 55,
|
| 172 |
+
"6": 56,
|
| 173 |
+
"60": 57,
|
| 174 |
+
"61": 58,
|
| 175 |
+
"62": 59,
|
| 176 |
+
"63": 60,
|
| 177 |
+
"64": 61,
|
| 178 |
+
"65": 62,
|
| 179 |
+
"66": 63,
|
| 180 |
+
"67": 64,
|
| 181 |
+
"68": 65,
|
| 182 |
+
"69": 66,
|
| 183 |
+
"7": 67,
|
| 184 |
+
"70": 68,
|
| 185 |
+
"71": 69,
|
| 186 |
+
"72": 70,
|
| 187 |
+
"73": 71,
|
| 188 |
+
"74": 72,
|
| 189 |
+
"75": 73,
|
| 190 |
+
"76": 74,
|
| 191 |
+
"77": 75,
|
| 192 |
+
"78": 76,
|
| 193 |
+
"79": 77,
|
| 194 |
+
"8": 78,
|
| 195 |
+
"80": 79,
|
| 196 |
+
"81": 80,
|
| 197 |
+
"82": 81,
|
| 198 |
+
"83": 82,
|
| 199 |
+
"84": 83,
|
| 200 |
+
"85": 84,
|
| 201 |
+
"86": 85,
|
| 202 |
+
"87": 86,
|
| 203 |
+
"88": 87,
|
| 204 |
+
"89": 88,
|
| 205 |
+
"9": 89,
|
| 206 |
+
"90": 90,
|
| 207 |
+
"91": 91,
|
| 208 |
+
"92": 92,
|
| 209 |
+
"93": 93,
|
| 210 |
+
"94": 94,
|
| 211 |
+
"95": 95,
|
| 212 |
+
"96": 96,
|
| 213 |
+
"97": 97,
|
| 214 |
+
"98": 98,
|
| 215 |
+
"99": 99
|
| 216 |
+
},
|
| 217 |
+
"max_position_embeddings": 512,
|
| 218 |
+
"model_type": "distilbert",
|
| 219 |
+
"n_heads": 12,
|
| 220 |
+
"n_layers": 6,
|
| 221 |
+
"pad_token_id": 0,
|
| 222 |
+
"problem_type": "single_label_classification",
|
| 223 |
+
"qa_dropout": 0.1,
|
| 224 |
+
"seq_classif_dropout": 0.2,
|
| 225 |
+
"sinusoidal_pos_embds": false,
|
| 226 |
+
"tie_weights_": true,
|
| 227 |
+
"torch_dtype": "float32",
|
| 228 |
+
"transformers_version": "4.39.0.dev0",
|
| 229 |
+
"vocab_size": 30522
|
| 230 |
+
}
|
distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ec685698e6277f158449103bab1c0b6c591de79d4d0c987e20bf4a833e24674
|
| 3 |
+
size 268134024
|
distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9de7ad19b1a5e3691d405c9b4f1b33835a347bf01bc9689e00785be78d95a375
|
| 3 |
+
size 536330170
|
distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b693c5b10d531992f8036f776d77a9d7ba54034fa31d9ec5ee83a820ae00c4e
|
| 3 |
+
size 14512
|
distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:adca77897c88db1e42bf734b8e9fe963de6cf3593cd8fff4e7c12d92c57d58af
|
| 3 |
+
size 14512
|
distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0224ec79a76b1ee8bd4b2fe14836f2158ca8d6dcdad5b03a74c30ee27cece40
|
| 3 |
+
size 1064
|
distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/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 |
+
}
|
distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_lower_case": true,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"strip_accents": null,
|
| 52 |
+
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/trainer_state.json
ADDED
|
@@ -0,0 +1,1113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6496002674102783,
|
| 3 |
+
"best_model_checkpoint": "../../experiments_checkpoints/MAdAiLab/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800",
|
| 4 |
+
"epoch": 2.9850746268656714,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 2800,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"grad_norm": 1.8292617797851562,
|
| 14 |
+
"learning_rate": 1.9822316986496094e-05,
|
| 15 |
+
"loss": 4.5108,
|
| 16 |
+
"step": 25
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.05,
|
| 20 |
+
"grad_norm": 2.0646250247955322,
|
| 21 |
+
"learning_rate": 1.9644633972992183e-05,
|
| 22 |
+
"loss": 4.2737,
|
| 23 |
+
"step": 50
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.08,
|
| 27 |
+
"grad_norm": 2.6037521362304688,
|
| 28 |
+
"learning_rate": 1.9466950959488275e-05,
|
| 29 |
+
"loss": 4.06,
|
| 30 |
+
"step": 75
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.11,
|
| 34 |
+
"grad_norm": 2.8344316482543945,
|
| 35 |
+
"learning_rate": 1.9289267945984364e-05,
|
| 36 |
+
"loss": 3.8165,
|
| 37 |
+
"step": 100
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.11,
|
| 41 |
+
"eval_accuracy": 0.3489,
|
| 42 |
+
"eval_f1_macro": 0.09953942962664121,
|
| 43 |
+
"eval_f1_micro": 0.3489,
|
| 44 |
+
"eval_loss": 3.5951926708221436,
|
| 45 |
+
"eval_runtime": 5.032,
|
| 46 |
+
"eval_samples_per_second": 1987.289,
|
| 47 |
+
"eval_steps_per_second": 31.2,
|
| 48 |
+
"step": 100
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.13,
|
| 52 |
+
"grad_norm": 2.8050551414489746,
|
| 53 |
+
"learning_rate": 1.9111584932480457e-05,
|
| 54 |
+
"loss": 3.499,
|
| 55 |
+
"step": 125
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.16,
|
| 59 |
+
"grad_norm": 2.6794557571411133,
|
| 60 |
+
"learning_rate": 1.8933901918976546e-05,
|
| 61 |
+
"loss": 3.3343,
|
| 62 |
+
"step": 150
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.19,
|
| 66 |
+
"grad_norm": 3.4706735610961914,
|
| 67 |
+
"learning_rate": 1.8756218905472638e-05,
|
| 68 |
+
"loss": 3.0543,
|
| 69 |
+
"step": 175
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.21,
|
| 73 |
+
"grad_norm": 2.9294159412384033,
|
| 74 |
+
"learning_rate": 1.857853589196873e-05,
|
| 75 |
+
"loss": 2.8293,
|
| 76 |
+
"step": 200
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.21,
|
| 80 |
+
"eval_accuracy": 0.5385,
|
| 81 |
+
"eval_f1_macro": 0.2374650407061841,
|
| 82 |
+
"eval_f1_micro": 0.5385,
|
| 83 |
+
"eval_loss": 2.6737160682678223,
|
| 84 |
+
"eval_runtime": 5.0548,
|
| 85 |
+
"eval_samples_per_second": 1978.336,
|
| 86 |
+
"eval_steps_per_second": 31.06,
|
| 87 |
+
"step": 200
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.24,
|
| 91 |
+
"grad_norm": 3.2487082481384277,
|
| 92 |
+
"learning_rate": 1.8400852878464823e-05,
|
| 93 |
+
"loss": 2.6772,
|
| 94 |
+
"step": 225
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.27,
|
| 98 |
+
"grad_norm": 3.0436863899230957,
|
| 99 |
+
"learning_rate": 1.822316986496091e-05,
|
| 100 |
+
"loss": 2.4908,
|
| 101 |
+
"step": 250
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.29,
|
| 105 |
+
"grad_norm": 3.3318707942962646,
|
| 106 |
+
"learning_rate": 1.8045486851457e-05,
|
| 107 |
+
"loss": 2.3918,
|
| 108 |
+
"step": 275
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.32,
|
| 112 |
+
"grad_norm": 3.209085464477539,
|
| 113 |
+
"learning_rate": 1.7867803837953093e-05,
|
| 114 |
+
"loss": 2.2564,
|
| 115 |
+
"step": 300
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.32,
|
| 119 |
+
"eval_accuracy": 0.6212,
|
| 120 |
+
"eval_f1_macro": 0.3338736755701111,
|
| 121 |
+
"eval_f1_micro": 0.6212,
|
| 122 |
+
"eval_loss": 2.0960097312927246,
|
| 123 |
+
"eval_runtime": 5.0922,
|
| 124 |
+
"eval_samples_per_second": 1963.795,
|
| 125 |
+
"eval_steps_per_second": 30.832,
|
| 126 |
+
"step": 300
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.35,
|
| 130 |
+
"grad_norm": 3.3769121170043945,
|
| 131 |
+
"learning_rate": 1.7690120824449185e-05,
|
| 132 |
+
"loss": 2.1476,
|
| 133 |
+
"step": 325
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 0.37,
|
| 137 |
+
"grad_norm": 3.443783760070801,
|
| 138 |
+
"learning_rate": 1.7512437810945274e-05,
|
| 139 |
+
"loss": 2.0204,
|
| 140 |
+
"step": 350
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.4,
|
| 144 |
+
"grad_norm": 3.6128618717193604,
|
| 145 |
+
"learning_rate": 1.7334754797441367e-05,
|
| 146 |
+
"loss": 1.9127,
|
| 147 |
+
"step": 375
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.43,
|
| 151 |
+
"grad_norm": 3.1673097610473633,
|
| 152 |
+
"learning_rate": 1.715707178393746e-05,
|
| 153 |
+
"loss": 1.8259,
|
| 154 |
+
"step": 400
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.43,
|
| 158 |
+
"eval_accuracy": 0.6792,
|
| 159 |
+
"eval_f1_macro": 0.42690318122732035,
|
| 160 |
+
"eval_f1_micro": 0.6792,
|
| 161 |
+
"eval_loss": 1.711798071861267,
|
| 162 |
+
"eval_runtime": 5.0988,
|
| 163 |
+
"eval_samples_per_second": 1961.262,
|
| 164 |
+
"eval_steps_per_second": 30.792,
|
| 165 |
+
"step": 400
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.45,
|
| 169 |
+
"grad_norm": 3.0291733741760254,
|
| 170 |
+
"learning_rate": 1.6979388770433548e-05,
|
| 171 |
+
"loss": 1.7889,
|
| 172 |
+
"step": 425
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.48,
|
| 176 |
+
"grad_norm": 3.4015133380889893,
|
| 177 |
+
"learning_rate": 1.6801705756929637e-05,
|
| 178 |
+
"loss": 1.8087,
|
| 179 |
+
"step": 450
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.51,
|
| 183 |
+
"grad_norm": 3.399096965789795,
|
| 184 |
+
"learning_rate": 1.662402274342573e-05,
|
| 185 |
+
"loss": 1.6702,
|
| 186 |
+
"step": 475
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.53,
|
| 190 |
+
"grad_norm": 3.8419103622436523,
|
| 191 |
+
"learning_rate": 1.6446339729921822e-05,
|
| 192 |
+
"loss": 1.5846,
|
| 193 |
+
"step": 500
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.53,
|
| 197 |
+
"eval_accuracy": 0.7232,
|
| 198 |
+
"eval_f1_macro": 0.49873050046317474,
|
| 199 |
+
"eval_f1_micro": 0.7232,
|
| 200 |
+
"eval_loss": 1.454288363456726,
|
| 201 |
+
"eval_runtime": 4.9953,
|
| 202 |
+
"eval_samples_per_second": 2001.896,
|
| 203 |
+
"eval_steps_per_second": 31.43,
|
| 204 |
+
"step": 500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.56,
|
| 208 |
+
"grad_norm": 3.3140788078308105,
|
| 209 |
+
"learning_rate": 1.626865671641791e-05,
|
| 210 |
+
"loss": 1.521,
|
| 211 |
+
"step": 525
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.59,
|
| 215 |
+
"grad_norm": 3.006406307220459,
|
| 216 |
+
"learning_rate": 1.6090973702914003e-05,
|
| 217 |
+
"loss": 1.4858,
|
| 218 |
+
"step": 550
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.61,
|
| 222 |
+
"grad_norm": 3.3898396492004395,
|
| 223 |
+
"learning_rate": 1.5913290689410095e-05,
|
| 224 |
+
"loss": 1.3929,
|
| 225 |
+
"step": 575
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.64,
|
| 229 |
+
"grad_norm": 4.46132755279541,
|
| 230 |
+
"learning_rate": 1.5735607675906184e-05,
|
| 231 |
+
"loss": 1.3927,
|
| 232 |
+
"step": 600
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.64,
|
| 236 |
+
"eval_accuracy": 0.758,
|
| 237 |
+
"eval_f1_macro": 0.5628259172803456,
|
| 238 |
+
"eval_f1_micro": 0.758,
|
| 239 |
+
"eval_loss": 1.26346755027771,
|
| 240 |
+
"eval_runtime": 5.0937,
|
| 241 |
+
"eval_samples_per_second": 1963.223,
|
| 242 |
+
"eval_steps_per_second": 30.823,
|
| 243 |
+
"step": 600
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.67,
|
| 247 |
+
"grad_norm": 3.48401141166687,
|
| 248 |
+
"learning_rate": 1.5557924662402277e-05,
|
| 249 |
+
"loss": 1.333,
|
| 250 |
+
"step": 625
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.69,
|
| 254 |
+
"grad_norm": 3.8899550437927246,
|
| 255 |
+
"learning_rate": 1.5380241648898366e-05,
|
| 256 |
+
"loss": 1.2675,
|
| 257 |
+
"step": 650
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.72,
|
| 261 |
+
"grad_norm": 3.1978042125701904,
|
| 262 |
+
"learning_rate": 1.5202558635394458e-05,
|
| 263 |
+
"loss": 1.273,
|
| 264 |
+
"step": 675
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.75,
|
| 268 |
+
"grad_norm": 2.9463396072387695,
|
| 269 |
+
"learning_rate": 1.5024875621890549e-05,
|
| 270 |
+
"loss": 1.2065,
|
| 271 |
+
"step": 700
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.75,
|
| 275 |
+
"eval_accuracy": 0.7719,
|
| 276 |
+
"eval_f1_macro": 0.5781987999470919,
|
| 277 |
+
"eval_f1_micro": 0.7719,
|
| 278 |
+
"eval_loss": 1.1217072010040283,
|
| 279 |
+
"eval_runtime": 5.0931,
|
| 280 |
+
"eval_samples_per_second": 1963.422,
|
| 281 |
+
"eval_steps_per_second": 30.826,
|
| 282 |
+
"step": 700
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.77,
|
| 286 |
+
"grad_norm": 3.5176944732666016,
|
| 287 |
+
"learning_rate": 1.484719260838664e-05,
|
| 288 |
+
"loss": 1.1275,
|
| 289 |
+
"step": 725
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.8,
|
| 293 |
+
"grad_norm": 4.0801005363464355,
|
| 294 |
+
"learning_rate": 1.4669509594882732e-05,
|
| 295 |
+
"loss": 1.1847,
|
| 296 |
+
"step": 750
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.83,
|
| 300 |
+
"grad_norm": 4.6251397132873535,
|
| 301 |
+
"learning_rate": 1.449182658137882e-05,
|
| 302 |
+
"loss": 1.1809,
|
| 303 |
+
"step": 775
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.85,
|
| 307 |
+
"grad_norm": 3.544368028640747,
|
| 308 |
+
"learning_rate": 1.4314143567874911e-05,
|
| 309 |
+
"loss": 1.16,
|
| 310 |
+
"step": 800
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.85,
|
| 314 |
+
"eval_accuracy": 0.7832,
|
| 315 |
+
"eval_f1_macro": 0.5984417775290468,
|
| 316 |
+
"eval_f1_micro": 0.7832,
|
| 317 |
+
"eval_loss": 1.030264139175415,
|
| 318 |
+
"eval_runtime": 5.094,
|
| 319 |
+
"eval_samples_per_second": 1963.094,
|
| 320 |
+
"eval_steps_per_second": 30.821,
|
| 321 |
+
"step": 800
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.88,
|
| 325 |
+
"grad_norm": 4.991486072540283,
|
| 326 |
+
"learning_rate": 1.4136460554371004e-05,
|
| 327 |
+
"loss": 1.1233,
|
| 328 |
+
"step": 825
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.91,
|
| 332 |
+
"grad_norm": 3.317925453186035,
|
| 333 |
+
"learning_rate": 1.3958777540867094e-05,
|
| 334 |
+
"loss": 1.0539,
|
| 335 |
+
"step": 850
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.93,
|
| 339 |
+
"grad_norm": 4.44712495803833,
|
| 340 |
+
"learning_rate": 1.3781094527363185e-05,
|
| 341 |
+
"loss": 1.0876,
|
| 342 |
+
"step": 875
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.96,
|
| 346 |
+
"grad_norm": 4.135316848754883,
|
| 347 |
+
"learning_rate": 1.3603411513859277e-05,
|
| 348 |
+
"loss": 1.0168,
|
| 349 |
+
"step": 900
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.96,
|
| 353 |
+
"eval_accuracy": 0.7887,
|
| 354 |
+
"eval_f1_macro": 0.6118617070223085,
|
| 355 |
+
"eval_f1_micro": 0.7887,
|
| 356 |
+
"eval_loss": 0.9443017840385437,
|
| 357 |
+
"eval_runtime": 5.0979,
|
| 358 |
+
"eval_samples_per_second": 1961.573,
|
| 359 |
+
"eval_steps_per_second": 30.797,
|
| 360 |
+
"step": 900
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.99,
|
| 364 |
+
"grad_norm": 4.779892444610596,
|
| 365 |
+
"learning_rate": 1.3425728500355366e-05,
|
| 366 |
+
"loss": 1.0555,
|
| 367 |
+
"step": 925
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.01,
|
| 371 |
+
"grad_norm": 4.020134925842285,
|
| 372 |
+
"learning_rate": 1.3248045486851457e-05,
|
| 373 |
+
"loss": 0.9748,
|
| 374 |
+
"step": 950
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.04,
|
| 378 |
+
"grad_norm": 4.492050647735596,
|
| 379 |
+
"learning_rate": 1.307036247334755e-05,
|
| 380 |
+
"loss": 0.9662,
|
| 381 |
+
"step": 975
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.07,
|
| 385 |
+
"grad_norm": 3.679119348526001,
|
| 386 |
+
"learning_rate": 1.289267945984364e-05,
|
| 387 |
+
"loss": 0.9006,
|
| 388 |
+
"step": 1000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.07,
|
| 392 |
+
"eval_accuracy": 0.7934,
|
| 393 |
+
"eval_f1_macro": 0.6142121854229132,
|
| 394 |
+
"eval_f1_micro": 0.7934,
|
| 395 |
+
"eval_loss": 0.8957639932632446,
|
| 396 |
+
"eval_runtime": 5.092,
|
| 397 |
+
"eval_samples_per_second": 1963.867,
|
| 398 |
+
"eval_steps_per_second": 30.833,
|
| 399 |
+
"step": 1000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.09,
|
| 403 |
+
"grad_norm": 4.6417107582092285,
|
| 404 |
+
"learning_rate": 1.271499644633973e-05,
|
| 405 |
+
"loss": 0.9296,
|
| 406 |
+
"step": 1025
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.12,
|
| 410 |
+
"grad_norm": 4.246198654174805,
|
| 411 |
+
"learning_rate": 1.2537313432835823e-05,
|
| 412 |
+
"loss": 0.8785,
|
| 413 |
+
"step": 1050
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.15,
|
| 417 |
+
"grad_norm": 4.164609909057617,
|
| 418 |
+
"learning_rate": 1.2359630419331914e-05,
|
| 419 |
+
"loss": 0.9073,
|
| 420 |
+
"step": 1075
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.17,
|
| 424 |
+
"grad_norm": 4.187661647796631,
|
| 425 |
+
"learning_rate": 1.2181947405828003e-05,
|
| 426 |
+
"loss": 0.8956,
|
| 427 |
+
"step": 1100
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 1.17,
|
| 431 |
+
"eval_accuracy": 0.8002,
|
| 432 |
+
"eval_f1_macro": 0.6294238017197136,
|
| 433 |
+
"eval_f1_micro": 0.8002,
|
| 434 |
+
"eval_loss": 0.8517330288887024,
|
| 435 |
+
"eval_runtime": 5.0924,
|
| 436 |
+
"eval_samples_per_second": 1963.694,
|
| 437 |
+
"eval_steps_per_second": 30.83,
|
| 438 |
+
"step": 1100
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 1.2,
|
| 442 |
+
"grad_norm": 2.66513991355896,
|
| 443 |
+
"learning_rate": 1.2004264392324093e-05,
|
| 444 |
+
"loss": 0.8597,
|
| 445 |
+
"step": 1125
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 1.23,
|
| 449 |
+
"grad_norm": 3.2240054607391357,
|
| 450 |
+
"learning_rate": 1.1826581378820186e-05,
|
| 451 |
+
"loss": 0.8368,
|
| 452 |
+
"step": 1150
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.25,
|
| 456 |
+
"grad_norm": 4.226346015930176,
|
| 457 |
+
"learning_rate": 1.1648898365316276e-05,
|
| 458 |
+
"loss": 0.7925,
|
| 459 |
+
"step": 1175
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.28,
|
| 463 |
+
"grad_norm": 3.5720551013946533,
|
| 464 |
+
"learning_rate": 1.1471215351812369e-05,
|
| 465 |
+
"loss": 0.9159,
|
| 466 |
+
"step": 1200
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.28,
|
| 470 |
+
"eval_accuracy": 0.8033,
|
| 471 |
+
"eval_f1_macro": 0.6412470887223418,
|
| 472 |
+
"eval_f1_micro": 0.8033,
|
| 473 |
+
"eval_loss": 0.8183619379997253,
|
| 474 |
+
"eval_runtime": 5.0956,
|
| 475 |
+
"eval_samples_per_second": 1962.471,
|
| 476 |
+
"eval_steps_per_second": 30.811,
|
| 477 |
+
"step": 1200
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 1.31,
|
| 481 |
+
"grad_norm": 3.9309592247009277,
|
| 482 |
+
"learning_rate": 1.129353233830846e-05,
|
| 483 |
+
"loss": 0.8711,
|
| 484 |
+
"step": 1225
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 1.33,
|
| 488 |
+
"grad_norm": 3.1741673946380615,
|
| 489 |
+
"learning_rate": 1.111584932480455e-05,
|
| 490 |
+
"loss": 0.839,
|
| 491 |
+
"step": 1250
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 1.36,
|
| 495 |
+
"grad_norm": 3.3300561904907227,
|
| 496 |
+
"learning_rate": 1.0938166311300639e-05,
|
| 497 |
+
"loss": 0.8273,
|
| 498 |
+
"step": 1275
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 1.39,
|
| 502 |
+
"grad_norm": 4.480769634246826,
|
| 503 |
+
"learning_rate": 1.0760483297796731e-05,
|
| 504 |
+
"loss": 0.8237,
|
| 505 |
+
"step": 1300
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 1.39,
|
| 509 |
+
"eval_accuracy": 0.8077,
|
| 510 |
+
"eval_f1_macro": 0.6529082127640804,
|
| 511 |
+
"eval_f1_micro": 0.8077,
|
| 512 |
+
"eval_loss": 0.7814128994941711,
|
| 513 |
+
"eval_runtime": 5.0887,
|
| 514 |
+
"eval_samples_per_second": 1965.129,
|
| 515 |
+
"eval_steps_per_second": 30.853,
|
| 516 |
+
"step": 1300
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 1.41,
|
| 520 |
+
"grad_norm": 4.553057670593262,
|
| 521 |
+
"learning_rate": 1.0582800284292822e-05,
|
| 522 |
+
"loss": 0.8214,
|
| 523 |
+
"step": 1325
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 1.44,
|
| 527 |
+
"grad_norm": 3.766432046890259,
|
| 528 |
+
"learning_rate": 1.0405117270788913e-05,
|
| 529 |
+
"loss": 0.8174,
|
| 530 |
+
"step": 1350
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 1.47,
|
| 534 |
+
"grad_norm": 4.3826446533203125,
|
| 535 |
+
"learning_rate": 1.0227434257285005e-05,
|
| 536 |
+
"loss": 0.772,
|
| 537 |
+
"step": 1375
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 1.49,
|
| 541 |
+
"grad_norm": 3.777904748916626,
|
| 542 |
+
"learning_rate": 1.0049751243781096e-05,
|
| 543 |
+
"loss": 0.7341,
|
| 544 |
+
"step": 1400
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 1.49,
|
| 548 |
+
"eval_accuracy": 0.8099,
|
| 549 |
+
"eval_f1_macro": 0.6600339223452895,
|
| 550 |
+
"eval_f1_micro": 0.8099,
|
| 551 |
+
"eval_loss": 0.7653506994247437,
|
| 552 |
+
"eval_runtime": 5.0857,
|
| 553 |
+
"eval_samples_per_second": 1966.297,
|
| 554 |
+
"eval_steps_per_second": 30.871,
|
| 555 |
+
"step": 1400
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.52,
|
| 559 |
+
"grad_norm": 4.6313629150390625,
|
| 560 |
+
"learning_rate": 9.872068230277187e-06,
|
| 561 |
+
"loss": 0.7761,
|
| 562 |
+
"step": 1425
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.55,
|
| 566 |
+
"grad_norm": 3.6354401111602783,
|
| 567 |
+
"learning_rate": 9.694385216773277e-06,
|
| 568 |
+
"loss": 0.8205,
|
| 569 |
+
"step": 1450
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.57,
|
| 573 |
+
"grad_norm": 3.7265005111694336,
|
| 574 |
+
"learning_rate": 9.516702203269368e-06,
|
| 575 |
+
"loss": 0.7916,
|
| 576 |
+
"step": 1475
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.6,
|
| 580 |
+
"grad_norm": 3.4605891704559326,
|
| 581 |
+
"learning_rate": 9.339019189765458e-06,
|
| 582 |
+
"loss": 0.7475,
|
| 583 |
+
"step": 1500
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.6,
|
| 587 |
+
"eval_accuracy": 0.8135,
|
| 588 |
+
"eval_f1_macro": 0.6650413690305985,
|
| 589 |
+
"eval_f1_micro": 0.8135,
|
| 590 |
+
"eval_loss": 0.7457693815231323,
|
| 591 |
+
"eval_runtime": 5.0844,
|
| 592 |
+
"eval_samples_per_second": 1966.8,
|
| 593 |
+
"eval_steps_per_second": 30.879,
|
| 594 |
+
"step": 1500
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.63,
|
| 598 |
+
"grad_norm": 5.460809707641602,
|
| 599 |
+
"learning_rate": 9.161336176261551e-06,
|
| 600 |
+
"loss": 0.7576,
|
| 601 |
+
"step": 1525
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 1.65,
|
| 605 |
+
"grad_norm": 3.1193032264709473,
|
| 606 |
+
"learning_rate": 8.98365316275764e-06,
|
| 607 |
+
"loss": 0.7156,
|
| 608 |
+
"step": 1550
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 1.68,
|
| 612 |
+
"grad_norm": 3.7673654556274414,
|
| 613 |
+
"learning_rate": 8.805970149253732e-06,
|
| 614 |
+
"loss": 0.6944,
|
| 615 |
+
"step": 1575
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.71,
|
| 619 |
+
"grad_norm": 4.008440971374512,
|
| 620 |
+
"learning_rate": 8.628287135749823e-06,
|
| 621 |
+
"loss": 0.7699,
|
| 622 |
+
"step": 1600
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 1.71,
|
| 626 |
+
"eval_accuracy": 0.8183,
|
| 627 |
+
"eval_f1_macro": 0.681030771263254,
|
| 628 |
+
"eval_f1_micro": 0.8183,
|
| 629 |
+
"eval_loss": 0.7288192510604858,
|
| 630 |
+
"eval_runtime": 5.0906,
|
| 631 |
+
"eval_samples_per_second": 1964.407,
|
| 632 |
+
"eval_steps_per_second": 30.841,
|
| 633 |
+
"step": 1600
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.73,
|
| 637 |
+
"grad_norm": 3.998149871826172,
|
| 638 |
+
"learning_rate": 8.450604122245915e-06,
|
| 639 |
+
"loss": 0.742,
|
| 640 |
+
"step": 1625
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.76,
|
| 644 |
+
"grad_norm": 4.329924583435059,
|
| 645 |
+
"learning_rate": 8.272921108742004e-06,
|
| 646 |
+
"loss": 0.7505,
|
| 647 |
+
"step": 1650
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.79,
|
| 651 |
+
"grad_norm": 3.9420013427734375,
|
| 652 |
+
"learning_rate": 8.095238095238097e-06,
|
| 653 |
+
"loss": 0.7005,
|
| 654 |
+
"step": 1675
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.81,
|
| 658 |
+
"grad_norm": 4.527777194976807,
|
| 659 |
+
"learning_rate": 7.917555081734187e-06,
|
| 660 |
+
"loss": 0.7472,
|
| 661 |
+
"step": 1700
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.81,
|
| 665 |
+
"eval_accuracy": 0.8179,
|
| 666 |
+
"eval_f1_macro": 0.681973246053428,
|
| 667 |
+
"eval_f1_micro": 0.8179,
|
| 668 |
+
"eval_loss": 0.712536633014679,
|
| 669 |
+
"eval_runtime": 5.0869,
|
| 670 |
+
"eval_samples_per_second": 1965.828,
|
| 671 |
+
"eval_steps_per_second": 30.864,
|
| 672 |
+
"step": 1700
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 1.84,
|
| 676 |
+
"grad_norm": 5.481727600097656,
|
| 677 |
+
"learning_rate": 7.739872068230278e-06,
|
| 678 |
+
"loss": 0.7694,
|
| 679 |
+
"step": 1725
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 1.87,
|
| 683 |
+
"grad_norm": 3.634965658187866,
|
| 684 |
+
"learning_rate": 7.5621890547263685e-06,
|
| 685 |
+
"loss": 0.6916,
|
| 686 |
+
"step": 1750
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 1.89,
|
| 690 |
+
"grad_norm": 4.712828636169434,
|
| 691 |
+
"learning_rate": 7.38450604122246e-06,
|
| 692 |
+
"loss": 0.7452,
|
| 693 |
+
"step": 1775
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 1.92,
|
| 697 |
+
"grad_norm": 4.240174770355225,
|
| 698 |
+
"learning_rate": 7.20682302771855e-06,
|
| 699 |
+
"loss": 0.689,
|
| 700 |
+
"step": 1800
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 1.92,
|
| 704 |
+
"eval_accuracy": 0.8201,
|
| 705 |
+
"eval_f1_macro": 0.6821776177873132,
|
| 706 |
+
"eval_f1_micro": 0.8201,
|
| 707 |
+
"eval_loss": 0.6964806914329529,
|
| 708 |
+
"eval_runtime": 5.0903,
|
| 709 |
+
"eval_samples_per_second": 1964.526,
|
| 710 |
+
"eval_steps_per_second": 30.843,
|
| 711 |
+
"step": 1800
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.95,
|
| 715 |
+
"grad_norm": 3.659916639328003,
|
| 716 |
+
"learning_rate": 7.029140014214641e-06,
|
| 717 |
+
"loss": 0.8135,
|
| 718 |
+
"step": 1825
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 1.97,
|
| 722 |
+
"grad_norm": 4.639604091644287,
|
| 723 |
+
"learning_rate": 6.851457000710733e-06,
|
| 724 |
+
"loss": 0.7496,
|
| 725 |
+
"step": 1850
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 2.0,
|
| 729 |
+
"grad_norm": 4.354977607727051,
|
| 730 |
+
"learning_rate": 6.673773987206824e-06,
|
| 731 |
+
"loss": 0.6715,
|
| 732 |
+
"step": 1875
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 2.03,
|
| 736 |
+
"grad_norm": 3.503903865814209,
|
| 737 |
+
"learning_rate": 6.496090973702914e-06,
|
| 738 |
+
"loss": 0.6807,
|
| 739 |
+
"step": 1900
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 2.03,
|
| 743 |
+
"eval_accuracy": 0.8192,
|
| 744 |
+
"eval_f1_macro": 0.6798912747134073,
|
| 745 |
+
"eval_f1_micro": 0.8192,
|
| 746 |
+
"eval_loss": 0.6904103755950928,
|
| 747 |
+
"eval_runtime": 5.0876,
|
| 748 |
+
"eval_samples_per_second": 1965.568,
|
| 749 |
+
"eval_steps_per_second": 30.859,
|
| 750 |
+
"step": 1900
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 2.05,
|
| 754 |
+
"grad_norm": 2.8646299839019775,
|
| 755 |
+
"learning_rate": 6.318407960199006e-06,
|
| 756 |
+
"loss": 0.6768,
|
| 757 |
+
"step": 1925
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 2.08,
|
| 761 |
+
"grad_norm": 4.127985000610352,
|
| 762 |
+
"learning_rate": 6.140724946695097e-06,
|
| 763 |
+
"loss": 0.7144,
|
| 764 |
+
"step": 1950
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 2.11,
|
| 768 |
+
"grad_norm": 3.0997469425201416,
|
| 769 |
+
"learning_rate": 5.963041933191187e-06,
|
| 770 |
+
"loss": 0.6447,
|
| 771 |
+
"step": 1975
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 2.13,
|
| 775 |
+
"grad_norm": 4.458724498748779,
|
| 776 |
+
"learning_rate": 5.785358919687279e-06,
|
| 777 |
+
"loss": 0.6514,
|
| 778 |
+
"step": 2000
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 2.13,
|
| 782 |
+
"eval_accuracy": 0.8239,
|
| 783 |
+
"eval_f1_macro": 0.6922798719270521,
|
| 784 |
+
"eval_f1_micro": 0.8239,
|
| 785 |
+
"eval_loss": 0.6835533976554871,
|
| 786 |
+
"eval_runtime": 5.09,
|
| 787 |
+
"eval_samples_per_second": 1964.629,
|
| 788 |
+
"eval_steps_per_second": 30.845,
|
| 789 |
+
"step": 2000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 2.16,
|
| 793 |
+
"grad_norm": 3.7359683513641357,
|
| 794 |
+
"learning_rate": 5.607675906183369e-06,
|
| 795 |
+
"loss": 0.6547,
|
| 796 |
+
"step": 2025
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 2.19,
|
| 800 |
+
"grad_norm": 3.74875807762146,
|
| 801 |
+
"learning_rate": 5.42999289267946e-06,
|
| 802 |
+
"loss": 0.6577,
|
| 803 |
+
"step": 2050
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 2.21,
|
| 807 |
+
"grad_norm": 3.634157419204712,
|
| 808 |
+
"learning_rate": 5.2523098791755514e-06,
|
| 809 |
+
"loss": 0.6596,
|
| 810 |
+
"step": 2075
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 2.24,
|
| 814 |
+
"grad_norm": 4.218031406402588,
|
| 815 |
+
"learning_rate": 5.074626865671642e-06,
|
| 816 |
+
"loss": 0.6662,
|
| 817 |
+
"step": 2100
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 2.24,
|
| 821 |
+
"eval_accuracy": 0.8267,
|
| 822 |
+
"eval_f1_macro": 0.7018656510236515,
|
| 823 |
+
"eval_f1_micro": 0.8267,
|
| 824 |
+
"eval_loss": 0.6749560832977295,
|
| 825 |
+
"eval_runtime": 5.0908,
|
| 826 |
+
"eval_samples_per_second": 1964.309,
|
| 827 |
+
"eval_steps_per_second": 30.84,
|
| 828 |
+
"step": 2100
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 2.27,
|
| 832 |
+
"grad_norm": 4.950326442718506,
|
| 833 |
+
"learning_rate": 4.896943852167733e-06,
|
| 834 |
+
"loss": 0.6144,
|
| 835 |
+
"step": 2125
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 2.29,
|
| 839 |
+
"grad_norm": 3.0254364013671875,
|
| 840 |
+
"learning_rate": 4.719260838663824e-06,
|
| 841 |
+
"loss": 0.6402,
|
| 842 |
+
"step": 2150
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 2.32,
|
| 846 |
+
"grad_norm": 2.264652967453003,
|
| 847 |
+
"learning_rate": 4.541577825159915e-06,
|
| 848 |
+
"loss": 0.5597,
|
| 849 |
+
"step": 2175
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 2.35,
|
| 853 |
+
"grad_norm": 5.00731086730957,
|
| 854 |
+
"learning_rate": 4.363894811656006e-06,
|
| 855 |
+
"loss": 0.6247,
|
| 856 |
+
"step": 2200
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 2.35,
|
| 860 |
+
"eval_accuracy": 0.8284,
|
| 861 |
+
"eval_f1_macro": 0.7028136538357826,
|
| 862 |
+
"eval_f1_micro": 0.8284,
|
| 863 |
+
"eval_loss": 0.6703132390975952,
|
| 864 |
+
"eval_runtime": 5.0889,
|
| 865 |
+
"eval_samples_per_second": 1965.077,
|
| 866 |
+
"eval_steps_per_second": 30.852,
|
| 867 |
+
"step": 2200
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 2.37,
|
| 871 |
+
"grad_norm": 3.5009686946868896,
|
| 872 |
+
"learning_rate": 4.186211798152097e-06,
|
| 873 |
+
"loss": 0.5784,
|
| 874 |
+
"step": 2225
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 2.4,
|
| 878 |
+
"grad_norm": 3.339487075805664,
|
| 879 |
+
"learning_rate": 4.008528784648188e-06,
|
| 880 |
+
"loss": 0.6321,
|
| 881 |
+
"step": 2250
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 2.43,
|
| 885 |
+
"grad_norm": 4.3150129318237305,
|
| 886 |
+
"learning_rate": 3.8308457711442784e-06,
|
| 887 |
+
"loss": 0.6499,
|
| 888 |
+
"step": 2275
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 2.45,
|
| 892 |
+
"grad_norm": 3.9127256870269775,
|
| 893 |
+
"learning_rate": 3.65316275764037e-06,
|
| 894 |
+
"loss": 0.6443,
|
| 895 |
+
"step": 2300
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 2.45,
|
| 899 |
+
"eval_accuracy": 0.8265,
|
| 900 |
+
"eval_f1_macro": 0.7001404361966705,
|
| 901 |
+
"eval_f1_micro": 0.8265,
|
| 902 |
+
"eval_loss": 0.666212260723114,
|
| 903 |
+
"eval_runtime": 5.0933,
|
| 904 |
+
"eval_samples_per_second": 1963.351,
|
| 905 |
+
"eval_steps_per_second": 30.825,
|
| 906 |
+
"step": 2300
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 2.48,
|
| 910 |
+
"grad_norm": 4.648262023925781,
|
| 911 |
+
"learning_rate": 3.4754797441364606e-06,
|
| 912 |
+
"loss": 0.6597,
|
| 913 |
+
"step": 2325
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 2.51,
|
| 917 |
+
"grad_norm": 5.805054187774658,
|
| 918 |
+
"learning_rate": 3.297796730632552e-06,
|
| 919 |
+
"loss": 0.6679,
|
| 920 |
+
"step": 2350
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 2.53,
|
| 924 |
+
"grad_norm": 3.7240312099456787,
|
| 925 |
+
"learning_rate": 3.120113717128643e-06,
|
| 926 |
+
"loss": 0.6098,
|
| 927 |
+
"step": 2375
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 2.56,
|
| 931 |
+
"grad_norm": 6.238827705383301,
|
| 932 |
+
"learning_rate": 2.9424307036247335e-06,
|
| 933 |
+
"loss": 0.632,
|
| 934 |
+
"step": 2400
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 2.56,
|
| 938 |
+
"eval_accuracy": 0.8295,
|
| 939 |
+
"eval_f1_macro": 0.7077893947175455,
|
| 940 |
+
"eval_f1_micro": 0.8295,
|
| 941 |
+
"eval_loss": 0.6571224331855774,
|
| 942 |
+
"eval_runtime": 5.0923,
|
| 943 |
+
"eval_samples_per_second": 1963.743,
|
| 944 |
+
"eval_steps_per_second": 30.831,
|
| 945 |
+
"step": 2400
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 2.59,
|
| 949 |
+
"grad_norm": 2.7973475456237793,
|
| 950 |
+
"learning_rate": 2.764747690120825e-06,
|
| 951 |
+
"loss": 0.7127,
|
| 952 |
+
"step": 2425
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 2.61,
|
| 956 |
+
"grad_norm": 4.434217929840088,
|
| 957 |
+
"learning_rate": 2.5870646766169156e-06,
|
| 958 |
+
"loss": 0.6907,
|
| 959 |
+
"step": 2450
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 2.64,
|
| 963 |
+
"grad_norm": 5.4939188957214355,
|
| 964 |
+
"learning_rate": 2.4093816631130067e-06,
|
| 965 |
+
"loss": 0.6308,
|
| 966 |
+
"step": 2475
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 2.67,
|
| 970 |
+
"grad_norm": 6.5089430809021,
|
| 971 |
+
"learning_rate": 2.2316986496090974e-06,
|
| 972 |
+
"loss": 0.5922,
|
| 973 |
+
"step": 2500
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 2.67,
|
| 977 |
+
"eval_accuracy": 0.8298,
|
| 978 |
+
"eval_f1_macro": 0.7083519630678758,
|
| 979 |
+
"eval_f1_micro": 0.8298,
|
| 980 |
+
"eval_loss": 0.6538856029510498,
|
| 981 |
+
"eval_runtime": 5.111,
|
| 982 |
+
"eval_samples_per_second": 1956.564,
|
| 983 |
+
"eval_steps_per_second": 30.718,
|
| 984 |
+
"step": 2500
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 2.69,
|
| 988 |
+
"grad_norm": 4.474384307861328,
|
| 989 |
+
"learning_rate": 2.0540156361051885e-06,
|
| 990 |
+
"loss": 0.6384,
|
| 991 |
+
"step": 2525
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 2.72,
|
| 995 |
+
"grad_norm": 4.887701511383057,
|
| 996 |
+
"learning_rate": 1.8763326226012796e-06,
|
| 997 |
+
"loss": 0.614,
|
| 998 |
+
"step": 2550
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 2.75,
|
| 1002 |
+
"grad_norm": 6.661905288696289,
|
| 1003 |
+
"learning_rate": 1.6986496090973702e-06,
|
| 1004 |
+
"loss": 0.626,
|
| 1005 |
+
"step": 2575
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 2.77,
|
| 1009 |
+
"grad_norm": 4.168758392333984,
|
| 1010 |
+
"learning_rate": 1.5209665955934613e-06,
|
| 1011 |
+
"loss": 0.6423,
|
| 1012 |
+
"step": 2600
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 2.77,
|
| 1016 |
+
"eval_accuracy": 0.8311,
|
| 1017 |
+
"eval_f1_macro": 0.7138508038282735,
|
| 1018 |
+
"eval_f1_micro": 0.8311,
|
| 1019 |
+
"eval_loss": 0.6518952250480652,
|
| 1020 |
+
"eval_runtime": 5.0992,
|
| 1021 |
+
"eval_samples_per_second": 1961.08,
|
| 1022 |
+
"eval_steps_per_second": 30.789,
|
| 1023 |
+
"step": 2600
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 2.8,
|
| 1027 |
+
"grad_norm": 3.9610595703125,
|
| 1028 |
+
"learning_rate": 1.3432835820895524e-06,
|
| 1029 |
+
"loss": 0.6361,
|
| 1030 |
+
"step": 2625
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 2.83,
|
| 1034 |
+
"grad_norm": 5.312166213989258,
|
| 1035 |
+
"learning_rate": 1.1656005685856433e-06,
|
| 1036 |
+
"loss": 0.6638,
|
| 1037 |
+
"step": 2650
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 2.85,
|
| 1041 |
+
"grad_norm": 4.739462852478027,
|
| 1042 |
+
"learning_rate": 9.879175550817342e-07,
|
| 1043 |
+
"loss": 0.625,
|
| 1044 |
+
"step": 2675
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 2.88,
|
| 1048 |
+
"grad_norm": 5.244933128356934,
|
| 1049 |
+
"learning_rate": 8.102345415778253e-07,
|
| 1050 |
+
"loss": 0.6156,
|
| 1051 |
+
"step": 2700
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 2.88,
|
| 1055 |
+
"eval_accuracy": 0.8311,
|
| 1056 |
+
"eval_f1_macro": 0.7123382093925994,
|
| 1057 |
+
"eval_f1_micro": 0.8311,
|
| 1058 |
+
"eval_loss": 0.6500191688537598,
|
| 1059 |
+
"eval_runtime": 5.1041,
|
| 1060 |
+
"eval_samples_per_second": 1959.192,
|
| 1061 |
+
"eval_steps_per_second": 30.759,
|
| 1062 |
+
"step": 2700
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 2.91,
|
| 1066 |
+
"grad_norm": 3.2966127395629883,
|
| 1067 |
+
"learning_rate": 6.325515280739161e-07,
|
| 1068 |
+
"loss": 0.6181,
|
| 1069 |
+
"step": 2725
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 2.93,
|
| 1073 |
+
"grad_norm": 4.855289936065674,
|
| 1074 |
+
"learning_rate": 4.548685145700071e-07,
|
| 1075 |
+
"loss": 0.5952,
|
| 1076 |
+
"step": 2750
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 2.96,
|
| 1080 |
+
"grad_norm": 5.3126068115234375,
|
| 1081 |
+
"learning_rate": 2.771855010660981e-07,
|
| 1082 |
+
"loss": 0.5727,
|
| 1083 |
+
"step": 2775
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 2.99,
|
| 1087 |
+
"grad_norm": 3.789565324783325,
|
| 1088 |
+
"learning_rate": 9.950248756218906e-08,
|
| 1089 |
+
"loss": 0.6097,
|
| 1090 |
+
"step": 2800
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 2.99,
|
| 1094 |
+
"eval_accuracy": 0.8311,
|
| 1095 |
+
"eval_f1_macro": 0.7116365414985335,
|
| 1096 |
+
"eval_f1_micro": 0.8311,
|
| 1097 |
+
"eval_loss": 0.6496002674102783,
|
| 1098 |
+
"eval_runtime": 5.1014,
|
| 1099 |
+
"eval_samples_per_second": 1960.25,
|
| 1100 |
+
"eval_steps_per_second": 30.776,
|
| 1101 |
+
"step": 2800
|
| 1102 |
+
}
|
| 1103 |
+
],
|
| 1104 |
+
"logging_steps": 25,
|
| 1105 |
+
"max_steps": 2814,
|
| 1106 |
+
"num_input_tokens_seen": 0,
|
| 1107 |
+
"num_train_epochs": 3,
|
| 1108 |
+
"save_steps": 100,
|
| 1109 |
+
"total_flos": 5944911060795392.0,
|
| 1110 |
+
"train_batch_size": 32,
|
| 1111 |
+
"trial_name": null,
|
| 1112 |
+
"trial_params": null
|
| 1113 |
+
}
|
distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53ffad4f667aa5e1f376b4335012867e7a74247e897653d0c354bcf157f4e5e9
|
| 3 |
+
size 5112
|
distilbert/distilbert_base_uncased_ledgar/checkpoint-2800/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
distilbert/distilbert_base_uncased_ledgar/config.json
ADDED
|
@@ -0,0 +1,230 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert/distilbert-base-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"finetuning_task": "text-classification",
|
| 11 |
+
"hidden_dim": 3072,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "0",
|
| 14 |
+
"1": "1",
|
| 15 |
+
"2": "10",
|
| 16 |
+
"3": "11",
|
| 17 |
+
"4": "12",
|
| 18 |
+
"5": "13",
|
| 19 |
+
"6": "14",
|
| 20 |
+
"7": "15",
|
| 21 |
+
"8": "16",
|
| 22 |
+
"9": "17",
|
| 23 |
+
"10": "18",
|
| 24 |
+
"11": "19",
|
| 25 |
+
"12": "2",
|
| 26 |
+
"13": "20",
|
| 27 |
+
"14": "21",
|
| 28 |
+
"15": "22",
|
| 29 |
+
"16": "23",
|
| 30 |
+
"17": "24",
|
| 31 |
+
"18": "25",
|
| 32 |
+
"19": "26",
|
| 33 |
+
"20": "27",
|
| 34 |
+
"21": "28",
|
| 35 |
+
"22": "29",
|
| 36 |
+
"23": "3",
|
| 37 |
+
"24": "30",
|
| 38 |
+
"25": "31",
|
| 39 |
+
"26": "32",
|
| 40 |
+
"27": "33",
|
| 41 |
+
"28": "34",
|
| 42 |
+
"29": "35",
|
| 43 |
+
"30": "36",
|
| 44 |
+
"31": "37",
|
| 45 |
+
"32": "38",
|
| 46 |
+
"33": "39",
|
| 47 |
+
"34": "4",
|
| 48 |
+
"35": "40",
|
| 49 |
+
"36": "41",
|
| 50 |
+
"37": "42",
|
| 51 |
+
"38": "43",
|
| 52 |
+
"39": "44",
|
| 53 |
+
"40": "45",
|
| 54 |
+
"41": "46",
|
| 55 |
+
"42": "47",
|
| 56 |
+
"43": "48",
|
| 57 |
+
"44": "49",
|
| 58 |
+
"45": "5",
|
| 59 |
+
"46": "50",
|
| 60 |
+
"47": "51",
|
| 61 |
+
"48": "52",
|
| 62 |
+
"49": "53",
|
| 63 |
+
"50": "54",
|
| 64 |
+
"51": "55",
|
| 65 |
+
"52": "56",
|
| 66 |
+
"53": "57",
|
| 67 |
+
"54": "58",
|
| 68 |
+
"55": "59",
|
| 69 |
+
"56": "6",
|
| 70 |
+
"57": "60",
|
| 71 |
+
"58": "61",
|
| 72 |
+
"59": "62",
|
| 73 |
+
"60": "63",
|
| 74 |
+
"61": "64",
|
| 75 |
+
"62": "65",
|
| 76 |
+
"63": "66",
|
| 77 |
+
"64": "67",
|
| 78 |
+
"65": "68",
|
| 79 |
+
"66": "69",
|
| 80 |
+
"67": "7",
|
| 81 |
+
"68": "70",
|
| 82 |
+
"69": "71",
|
| 83 |
+
"70": "72",
|
| 84 |
+
"71": "73",
|
| 85 |
+
"72": "74",
|
| 86 |
+
"73": "75",
|
| 87 |
+
"74": "76",
|
| 88 |
+
"75": "77",
|
| 89 |
+
"76": "78",
|
| 90 |
+
"77": "79",
|
| 91 |
+
"78": "8",
|
| 92 |
+
"79": "80",
|
| 93 |
+
"80": "81",
|
| 94 |
+
"81": "82",
|
| 95 |
+
"82": "83",
|
| 96 |
+
"83": "84",
|
| 97 |
+
"84": "85",
|
| 98 |
+
"85": "86",
|
| 99 |
+
"86": "87",
|
| 100 |
+
"87": "88",
|
| 101 |
+
"88": "89",
|
| 102 |
+
"89": "9",
|
| 103 |
+
"90": "90",
|
| 104 |
+
"91": "91",
|
| 105 |
+
"92": "92",
|
| 106 |
+
"93": "93",
|
| 107 |
+
"94": "94",
|
| 108 |
+
"95": "95",
|
| 109 |
+
"96": "96",
|
| 110 |
+
"97": "97",
|
| 111 |
+
"98": "98",
|
| 112 |
+
"99": "99"
|
| 113 |
+
},
|
| 114 |
+
"initializer_range": 0.02,
|
| 115 |
+
"label2id": {
|
| 116 |
+
"0": 0,
|
| 117 |
+
"1": 1,
|
| 118 |
+
"10": 2,
|
| 119 |
+
"11": 3,
|
| 120 |
+
"12": 4,
|
| 121 |
+
"13": 5,
|
| 122 |
+
"14": 6,
|
| 123 |
+
"15": 7,
|
| 124 |
+
"16": 8,
|
| 125 |
+
"17": 9,
|
| 126 |
+
"18": 10,
|
| 127 |
+
"19": 11,
|
| 128 |
+
"2": 12,
|
| 129 |
+
"20": 13,
|
| 130 |
+
"21": 14,
|
| 131 |
+
"22": 15,
|
| 132 |
+
"23": 16,
|
| 133 |
+
"24": 17,
|
| 134 |
+
"25": 18,
|
| 135 |
+
"26": 19,
|
| 136 |
+
"27": 20,
|
| 137 |
+
"28": 21,
|
| 138 |
+
"29": 22,
|
| 139 |
+
"3": 23,
|
| 140 |
+
"30": 24,
|
| 141 |
+
"31": 25,
|
| 142 |
+
"32": 26,
|
| 143 |
+
"33": 27,
|
| 144 |
+
"34": 28,
|
| 145 |
+
"35": 29,
|
| 146 |
+
"36": 30,
|
| 147 |
+
"37": 31,
|
| 148 |
+
"38": 32,
|
| 149 |
+
"39": 33,
|
| 150 |
+
"4": 34,
|
| 151 |
+
"40": 35,
|
| 152 |
+
"41": 36,
|
| 153 |
+
"42": 37,
|
| 154 |
+
"43": 38,
|
| 155 |
+
"44": 39,
|
| 156 |
+
"45": 40,
|
| 157 |
+
"46": 41,
|
| 158 |
+
"47": 42,
|
| 159 |
+
"48": 43,
|
| 160 |
+
"49": 44,
|
| 161 |
+
"5": 45,
|
| 162 |
+
"50": 46,
|
| 163 |
+
"51": 47,
|
| 164 |
+
"52": 48,
|
| 165 |
+
"53": 49,
|
| 166 |
+
"54": 50,
|
| 167 |
+
"55": 51,
|
| 168 |
+
"56": 52,
|
| 169 |
+
"57": 53,
|
| 170 |
+
"58": 54,
|
| 171 |
+
"59": 55,
|
| 172 |
+
"6": 56,
|
| 173 |
+
"60": 57,
|
| 174 |
+
"61": 58,
|
| 175 |
+
"62": 59,
|
| 176 |
+
"63": 60,
|
| 177 |
+
"64": 61,
|
| 178 |
+
"65": 62,
|
| 179 |
+
"66": 63,
|
| 180 |
+
"67": 64,
|
| 181 |
+
"68": 65,
|
| 182 |
+
"69": 66,
|
| 183 |
+
"7": 67,
|
| 184 |
+
"70": 68,
|
| 185 |
+
"71": 69,
|
| 186 |
+
"72": 70,
|
| 187 |
+
"73": 71,
|
| 188 |
+
"74": 72,
|
| 189 |
+
"75": 73,
|
| 190 |
+
"76": 74,
|
| 191 |
+
"77": 75,
|
| 192 |
+
"78": 76,
|
| 193 |
+
"79": 77,
|
| 194 |
+
"8": 78,
|
| 195 |
+
"80": 79,
|
| 196 |
+
"81": 80,
|
| 197 |
+
"82": 81,
|
| 198 |
+
"83": 82,
|
| 199 |
+
"84": 83,
|
| 200 |
+
"85": 84,
|
| 201 |
+
"86": 85,
|
| 202 |
+
"87": 86,
|
| 203 |
+
"88": 87,
|
| 204 |
+
"89": 88,
|
| 205 |
+
"9": 89,
|
| 206 |
+
"90": 90,
|
| 207 |
+
"91": 91,
|
| 208 |
+
"92": 92,
|
| 209 |
+
"93": 93,
|
| 210 |
+
"94": 94,
|
| 211 |
+
"95": 95,
|
| 212 |
+
"96": 96,
|
| 213 |
+
"97": 97,
|
| 214 |
+
"98": 98,
|
| 215 |
+
"99": 99
|
| 216 |
+
},
|
| 217 |
+
"max_position_embeddings": 512,
|
| 218 |
+
"model_type": "distilbert",
|
| 219 |
+
"n_heads": 12,
|
| 220 |
+
"n_layers": 6,
|
| 221 |
+
"pad_token_id": 0,
|
| 222 |
+
"problem_type": "single_label_classification",
|
| 223 |
+
"qa_dropout": 0.1,
|
| 224 |
+
"seq_classif_dropout": 0.2,
|
| 225 |
+
"sinusoidal_pos_embds": false,
|
| 226 |
+
"tie_weights_": true,
|
| 227 |
+
"torch_dtype": "float32",
|
| 228 |
+
"transformers_version": "4.39.0.dev0",
|
| 229 |
+
"vocab_size": 30522
|
| 230 |
+
}
|
distilbert/distilbert_base_uncased_ledgar/eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.8311,
|
| 4 |
+
"eval_f1_macro": 0.7116365414985335,
|
| 5 |
+
"eval_f1_micro": 0.8311,
|
| 6 |
+
"eval_loss": 0.6496002674102783,
|
| 7 |
+
"eval_runtime": 5.097,
|
| 8 |
+
"eval_samples": 10000,
|
| 9 |
+
"eval_samples_per_second": 1961.935,
|
| 10 |
+
"eval_steps_per_second": 30.802
|
| 11 |
+
}
|
distilbert/distilbert_base_uncased_ledgar/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ec685698e6277f158449103bab1c0b6c591de79d4d0c987e20bf4a833e24674
|
| 3 |
+
size 268134024
|
distilbert/distilbert_base_uncased_ledgar/run.log
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
03/15/2024 17:10:37 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: True, 16-bits training: False
|
| 2 |
+
03/15/2024 17:10:37 - WARNING - __main__ - Process rank: 1, device: cuda:1, n_gpu: 1, distributed training: True, 16-bits training: False
|
| 3 |
+
03/15/2024 17:10:41 - WARNING - __main__ - The label2id key in the model config.json is not equal to the label2id key of this run. You can ignore this if you are doing finetuning.
|
| 4 |
+
03/15/2024 17:10:42 - WARNING - __main__ - The label2id key in the model config.json is not equal to the label2id key of this run. You can ignore this if you are doing finetuning.
|
distilbert/distilbert_base_uncased_ledgar/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 |
+
}
|
distilbert/distilbert_base_uncased_ledgar/test_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"test_accuracy": 0.831,
|
| 4 |
+
"test_f1_macro": 0.702504756659894,
|
| 5 |
+
"test_f1_micro": 0.831,
|
| 6 |
+
"test_loss": 0.6615453362464905,
|
| 7 |
+
"test_runtime": 5.1002,
|
| 8 |
+
"test_samples_per_second": 1960.689,
|
| 9 |
+
"test_steps_per_second": 30.783
|
| 10 |
+
}
|
distilbert/distilbert_base_uncased_ledgar/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
distilbert/distilbert_base_uncased_ledgar/tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_lower_case": true,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"strip_accents": null,
|
| 52 |
+
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
distilbert/distilbert_base_uncased_ledgar/train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 1.1483757653470232,
|
| 4 |
+
"train_runtime": 441.0175,
|
| 5 |
+
"train_samples": 60000,
|
| 6 |
+
"train_samples_per_second": 408.147,
|
| 7 |
+
"train_steps_per_second": 6.381
|
| 8 |
+
}
|
distilbert/distilbert_base_uncased_ledgar/trainer_state.json
ADDED
|
@@ -0,0 +1,1122 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6496002674102783,
|
| 3 |
+
"best_model_checkpoint": "../../experiments_checkpoints/MAdAiLab/distilbert/distilbert_base_uncased_ledgar/checkpoint-2800",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 2814,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"grad_norm": 1.8292617797851562,
|
| 14 |
+
"learning_rate": 1.9822316986496094e-05,
|
| 15 |
+
"loss": 4.5108,
|
| 16 |
+
"step": 25
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.05,
|
| 20 |
+
"grad_norm": 2.0646250247955322,
|
| 21 |
+
"learning_rate": 1.9644633972992183e-05,
|
| 22 |
+
"loss": 4.2737,
|
| 23 |
+
"step": 50
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.08,
|
| 27 |
+
"grad_norm": 2.6037521362304688,
|
| 28 |
+
"learning_rate": 1.9466950959488275e-05,
|
| 29 |
+
"loss": 4.06,
|
| 30 |
+
"step": 75
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.11,
|
| 34 |
+
"grad_norm": 2.8344316482543945,
|
| 35 |
+
"learning_rate": 1.9289267945984364e-05,
|
| 36 |
+
"loss": 3.8165,
|
| 37 |
+
"step": 100
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.11,
|
| 41 |
+
"eval_accuracy": 0.3489,
|
| 42 |
+
"eval_f1_macro": 0.09953942962664121,
|
| 43 |
+
"eval_f1_micro": 0.3489,
|
| 44 |
+
"eval_loss": 3.5951926708221436,
|
| 45 |
+
"eval_runtime": 5.032,
|
| 46 |
+
"eval_samples_per_second": 1987.289,
|
| 47 |
+
"eval_steps_per_second": 31.2,
|
| 48 |
+
"step": 100
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.13,
|
| 52 |
+
"grad_norm": 2.8050551414489746,
|
| 53 |
+
"learning_rate": 1.9111584932480457e-05,
|
| 54 |
+
"loss": 3.499,
|
| 55 |
+
"step": 125
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.16,
|
| 59 |
+
"grad_norm": 2.6794557571411133,
|
| 60 |
+
"learning_rate": 1.8933901918976546e-05,
|
| 61 |
+
"loss": 3.3343,
|
| 62 |
+
"step": 150
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.19,
|
| 66 |
+
"grad_norm": 3.4706735610961914,
|
| 67 |
+
"learning_rate": 1.8756218905472638e-05,
|
| 68 |
+
"loss": 3.0543,
|
| 69 |
+
"step": 175
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.21,
|
| 73 |
+
"grad_norm": 2.9294159412384033,
|
| 74 |
+
"learning_rate": 1.857853589196873e-05,
|
| 75 |
+
"loss": 2.8293,
|
| 76 |
+
"step": 200
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.21,
|
| 80 |
+
"eval_accuracy": 0.5385,
|
| 81 |
+
"eval_f1_macro": 0.2374650407061841,
|
| 82 |
+
"eval_f1_micro": 0.5385,
|
| 83 |
+
"eval_loss": 2.6737160682678223,
|
| 84 |
+
"eval_runtime": 5.0548,
|
| 85 |
+
"eval_samples_per_second": 1978.336,
|
| 86 |
+
"eval_steps_per_second": 31.06,
|
| 87 |
+
"step": 200
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.24,
|
| 91 |
+
"grad_norm": 3.2487082481384277,
|
| 92 |
+
"learning_rate": 1.8400852878464823e-05,
|
| 93 |
+
"loss": 2.6772,
|
| 94 |
+
"step": 225
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.27,
|
| 98 |
+
"grad_norm": 3.0436863899230957,
|
| 99 |
+
"learning_rate": 1.822316986496091e-05,
|
| 100 |
+
"loss": 2.4908,
|
| 101 |
+
"step": 250
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.29,
|
| 105 |
+
"grad_norm": 3.3318707942962646,
|
| 106 |
+
"learning_rate": 1.8045486851457e-05,
|
| 107 |
+
"loss": 2.3918,
|
| 108 |
+
"step": 275
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.32,
|
| 112 |
+
"grad_norm": 3.209085464477539,
|
| 113 |
+
"learning_rate": 1.7867803837953093e-05,
|
| 114 |
+
"loss": 2.2564,
|
| 115 |
+
"step": 300
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.32,
|
| 119 |
+
"eval_accuracy": 0.6212,
|
| 120 |
+
"eval_f1_macro": 0.3338736755701111,
|
| 121 |
+
"eval_f1_micro": 0.6212,
|
| 122 |
+
"eval_loss": 2.0960097312927246,
|
| 123 |
+
"eval_runtime": 5.0922,
|
| 124 |
+
"eval_samples_per_second": 1963.795,
|
| 125 |
+
"eval_steps_per_second": 30.832,
|
| 126 |
+
"step": 300
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.35,
|
| 130 |
+
"grad_norm": 3.3769121170043945,
|
| 131 |
+
"learning_rate": 1.7690120824449185e-05,
|
| 132 |
+
"loss": 2.1476,
|
| 133 |
+
"step": 325
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 0.37,
|
| 137 |
+
"grad_norm": 3.443783760070801,
|
| 138 |
+
"learning_rate": 1.7512437810945274e-05,
|
| 139 |
+
"loss": 2.0204,
|
| 140 |
+
"step": 350
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.4,
|
| 144 |
+
"grad_norm": 3.6128618717193604,
|
| 145 |
+
"learning_rate": 1.7334754797441367e-05,
|
| 146 |
+
"loss": 1.9127,
|
| 147 |
+
"step": 375
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.43,
|
| 151 |
+
"grad_norm": 3.1673097610473633,
|
| 152 |
+
"learning_rate": 1.715707178393746e-05,
|
| 153 |
+
"loss": 1.8259,
|
| 154 |
+
"step": 400
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.43,
|
| 158 |
+
"eval_accuracy": 0.6792,
|
| 159 |
+
"eval_f1_macro": 0.42690318122732035,
|
| 160 |
+
"eval_f1_micro": 0.6792,
|
| 161 |
+
"eval_loss": 1.711798071861267,
|
| 162 |
+
"eval_runtime": 5.0988,
|
| 163 |
+
"eval_samples_per_second": 1961.262,
|
| 164 |
+
"eval_steps_per_second": 30.792,
|
| 165 |
+
"step": 400
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.45,
|
| 169 |
+
"grad_norm": 3.0291733741760254,
|
| 170 |
+
"learning_rate": 1.6979388770433548e-05,
|
| 171 |
+
"loss": 1.7889,
|
| 172 |
+
"step": 425
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.48,
|
| 176 |
+
"grad_norm": 3.4015133380889893,
|
| 177 |
+
"learning_rate": 1.6801705756929637e-05,
|
| 178 |
+
"loss": 1.8087,
|
| 179 |
+
"step": 450
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.51,
|
| 183 |
+
"grad_norm": 3.399096965789795,
|
| 184 |
+
"learning_rate": 1.662402274342573e-05,
|
| 185 |
+
"loss": 1.6702,
|
| 186 |
+
"step": 475
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.53,
|
| 190 |
+
"grad_norm": 3.8419103622436523,
|
| 191 |
+
"learning_rate": 1.6446339729921822e-05,
|
| 192 |
+
"loss": 1.5846,
|
| 193 |
+
"step": 500
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.53,
|
| 197 |
+
"eval_accuracy": 0.7232,
|
| 198 |
+
"eval_f1_macro": 0.49873050046317474,
|
| 199 |
+
"eval_f1_micro": 0.7232,
|
| 200 |
+
"eval_loss": 1.454288363456726,
|
| 201 |
+
"eval_runtime": 4.9953,
|
| 202 |
+
"eval_samples_per_second": 2001.896,
|
| 203 |
+
"eval_steps_per_second": 31.43,
|
| 204 |
+
"step": 500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.56,
|
| 208 |
+
"grad_norm": 3.3140788078308105,
|
| 209 |
+
"learning_rate": 1.626865671641791e-05,
|
| 210 |
+
"loss": 1.521,
|
| 211 |
+
"step": 525
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.59,
|
| 215 |
+
"grad_norm": 3.006406307220459,
|
| 216 |
+
"learning_rate": 1.6090973702914003e-05,
|
| 217 |
+
"loss": 1.4858,
|
| 218 |
+
"step": 550
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.61,
|
| 222 |
+
"grad_norm": 3.3898396492004395,
|
| 223 |
+
"learning_rate": 1.5913290689410095e-05,
|
| 224 |
+
"loss": 1.3929,
|
| 225 |
+
"step": 575
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.64,
|
| 229 |
+
"grad_norm": 4.46132755279541,
|
| 230 |
+
"learning_rate": 1.5735607675906184e-05,
|
| 231 |
+
"loss": 1.3927,
|
| 232 |
+
"step": 600
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.64,
|
| 236 |
+
"eval_accuracy": 0.758,
|
| 237 |
+
"eval_f1_macro": 0.5628259172803456,
|
| 238 |
+
"eval_f1_micro": 0.758,
|
| 239 |
+
"eval_loss": 1.26346755027771,
|
| 240 |
+
"eval_runtime": 5.0937,
|
| 241 |
+
"eval_samples_per_second": 1963.223,
|
| 242 |
+
"eval_steps_per_second": 30.823,
|
| 243 |
+
"step": 600
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.67,
|
| 247 |
+
"grad_norm": 3.48401141166687,
|
| 248 |
+
"learning_rate": 1.5557924662402277e-05,
|
| 249 |
+
"loss": 1.333,
|
| 250 |
+
"step": 625
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.69,
|
| 254 |
+
"grad_norm": 3.8899550437927246,
|
| 255 |
+
"learning_rate": 1.5380241648898366e-05,
|
| 256 |
+
"loss": 1.2675,
|
| 257 |
+
"step": 650
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.72,
|
| 261 |
+
"grad_norm": 3.1978042125701904,
|
| 262 |
+
"learning_rate": 1.5202558635394458e-05,
|
| 263 |
+
"loss": 1.273,
|
| 264 |
+
"step": 675
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.75,
|
| 268 |
+
"grad_norm": 2.9463396072387695,
|
| 269 |
+
"learning_rate": 1.5024875621890549e-05,
|
| 270 |
+
"loss": 1.2065,
|
| 271 |
+
"step": 700
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.75,
|
| 275 |
+
"eval_accuracy": 0.7719,
|
| 276 |
+
"eval_f1_macro": 0.5781987999470919,
|
| 277 |
+
"eval_f1_micro": 0.7719,
|
| 278 |
+
"eval_loss": 1.1217072010040283,
|
| 279 |
+
"eval_runtime": 5.0931,
|
| 280 |
+
"eval_samples_per_second": 1963.422,
|
| 281 |
+
"eval_steps_per_second": 30.826,
|
| 282 |
+
"step": 700
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.77,
|
| 286 |
+
"grad_norm": 3.5176944732666016,
|
| 287 |
+
"learning_rate": 1.484719260838664e-05,
|
| 288 |
+
"loss": 1.1275,
|
| 289 |
+
"step": 725
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.8,
|
| 293 |
+
"grad_norm": 4.0801005363464355,
|
| 294 |
+
"learning_rate": 1.4669509594882732e-05,
|
| 295 |
+
"loss": 1.1847,
|
| 296 |
+
"step": 750
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.83,
|
| 300 |
+
"grad_norm": 4.6251397132873535,
|
| 301 |
+
"learning_rate": 1.449182658137882e-05,
|
| 302 |
+
"loss": 1.1809,
|
| 303 |
+
"step": 775
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.85,
|
| 307 |
+
"grad_norm": 3.544368028640747,
|
| 308 |
+
"learning_rate": 1.4314143567874911e-05,
|
| 309 |
+
"loss": 1.16,
|
| 310 |
+
"step": 800
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.85,
|
| 314 |
+
"eval_accuracy": 0.7832,
|
| 315 |
+
"eval_f1_macro": 0.5984417775290468,
|
| 316 |
+
"eval_f1_micro": 0.7832,
|
| 317 |
+
"eval_loss": 1.030264139175415,
|
| 318 |
+
"eval_runtime": 5.094,
|
| 319 |
+
"eval_samples_per_second": 1963.094,
|
| 320 |
+
"eval_steps_per_second": 30.821,
|
| 321 |
+
"step": 800
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.88,
|
| 325 |
+
"grad_norm": 4.991486072540283,
|
| 326 |
+
"learning_rate": 1.4136460554371004e-05,
|
| 327 |
+
"loss": 1.1233,
|
| 328 |
+
"step": 825
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.91,
|
| 332 |
+
"grad_norm": 3.317925453186035,
|
| 333 |
+
"learning_rate": 1.3958777540867094e-05,
|
| 334 |
+
"loss": 1.0539,
|
| 335 |
+
"step": 850
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.93,
|
| 339 |
+
"grad_norm": 4.44712495803833,
|
| 340 |
+
"learning_rate": 1.3781094527363185e-05,
|
| 341 |
+
"loss": 1.0876,
|
| 342 |
+
"step": 875
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.96,
|
| 346 |
+
"grad_norm": 4.135316848754883,
|
| 347 |
+
"learning_rate": 1.3603411513859277e-05,
|
| 348 |
+
"loss": 1.0168,
|
| 349 |
+
"step": 900
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.96,
|
| 353 |
+
"eval_accuracy": 0.7887,
|
| 354 |
+
"eval_f1_macro": 0.6118617070223085,
|
| 355 |
+
"eval_f1_micro": 0.7887,
|
| 356 |
+
"eval_loss": 0.9443017840385437,
|
| 357 |
+
"eval_runtime": 5.0979,
|
| 358 |
+
"eval_samples_per_second": 1961.573,
|
| 359 |
+
"eval_steps_per_second": 30.797,
|
| 360 |
+
"step": 900
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.99,
|
| 364 |
+
"grad_norm": 4.779892444610596,
|
| 365 |
+
"learning_rate": 1.3425728500355366e-05,
|
| 366 |
+
"loss": 1.0555,
|
| 367 |
+
"step": 925
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.01,
|
| 371 |
+
"grad_norm": 4.020134925842285,
|
| 372 |
+
"learning_rate": 1.3248045486851457e-05,
|
| 373 |
+
"loss": 0.9748,
|
| 374 |
+
"step": 950
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.04,
|
| 378 |
+
"grad_norm": 4.492050647735596,
|
| 379 |
+
"learning_rate": 1.307036247334755e-05,
|
| 380 |
+
"loss": 0.9662,
|
| 381 |
+
"step": 975
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.07,
|
| 385 |
+
"grad_norm": 3.679119348526001,
|
| 386 |
+
"learning_rate": 1.289267945984364e-05,
|
| 387 |
+
"loss": 0.9006,
|
| 388 |
+
"step": 1000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.07,
|
| 392 |
+
"eval_accuracy": 0.7934,
|
| 393 |
+
"eval_f1_macro": 0.6142121854229132,
|
| 394 |
+
"eval_f1_micro": 0.7934,
|
| 395 |
+
"eval_loss": 0.8957639932632446,
|
| 396 |
+
"eval_runtime": 5.092,
|
| 397 |
+
"eval_samples_per_second": 1963.867,
|
| 398 |
+
"eval_steps_per_second": 30.833,
|
| 399 |
+
"step": 1000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.09,
|
| 403 |
+
"grad_norm": 4.6417107582092285,
|
| 404 |
+
"learning_rate": 1.271499644633973e-05,
|
| 405 |
+
"loss": 0.9296,
|
| 406 |
+
"step": 1025
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.12,
|
| 410 |
+
"grad_norm": 4.246198654174805,
|
| 411 |
+
"learning_rate": 1.2537313432835823e-05,
|
| 412 |
+
"loss": 0.8785,
|
| 413 |
+
"step": 1050
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.15,
|
| 417 |
+
"grad_norm": 4.164609909057617,
|
| 418 |
+
"learning_rate": 1.2359630419331914e-05,
|
| 419 |
+
"loss": 0.9073,
|
| 420 |
+
"step": 1075
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.17,
|
| 424 |
+
"grad_norm": 4.187661647796631,
|
| 425 |
+
"learning_rate": 1.2181947405828003e-05,
|
| 426 |
+
"loss": 0.8956,
|
| 427 |
+
"step": 1100
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 1.17,
|
| 431 |
+
"eval_accuracy": 0.8002,
|
| 432 |
+
"eval_f1_macro": 0.6294238017197136,
|
| 433 |
+
"eval_f1_micro": 0.8002,
|
| 434 |
+
"eval_loss": 0.8517330288887024,
|
| 435 |
+
"eval_runtime": 5.0924,
|
| 436 |
+
"eval_samples_per_second": 1963.694,
|
| 437 |
+
"eval_steps_per_second": 30.83,
|
| 438 |
+
"step": 1100
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 1.2,
|
| 442 |
+
"grad_norm": 2.66513991355896,
|
| 443 |
+
"learning_rate": 1.2004264392324093e-05,
|
| 444 |
+
"loss": 0.8597,
|
| 445 |
+
"step": 1125
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 1.23,
|
| 449 |
+
"grad_norm": 3.2240054607391357,
|
| 450 |
+
"learning_rate": 1.1826581378820186e-05,
|
| 451 |
+
"loss": 0.8368,
|
| 452 |
+
"step": 1150
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.25,
|
| 456 |
+
"grad_norm": 4.226346015930176,
|
| 457 |
+
"learning_rate": 1.1648898365316276e-05,
|
| 458 |
+
"loss": 0.7925,
|
| 459 |
+
"step": 1175
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.28,
|
| 463 |
+
"grad_norm": 3.5720551013946533,
|
| 464 |
+
"learning_rate": 1.1471215351812369e-05,
|
| 465 |
+
"loss": 0.9159,
|
| 466 |
+
"step": 1200
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.28,
|
| 470 |
+
"eval_accuracy": 0.8033,
|
| 471 |
+
"eval_f1_macro": 0.6412470887223418,
|
| 472 |
+
"eval_f1_micro": 0.8033,
|
| 473 |
+
"eval_loss": 0.8183619379997253,
|
| 474 |
+
"eval_runtime": 5.0956,
|
| 475 |
+
"eval_samples_per_second": 1962.471,
|
| 476 |
+
"eval_steps_per_second": 30.811,
|
| 477 |
+
"step": 1200
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 1.31,
|
| 481 |
+
"grad_norm": 3.9309592247009277,
|
| 482 |
+
"learning_rate": 1.129353233830846e-05,
|
| 483 |
+
"loss": 0.8711,
|
| 484 |
+
"step": 1225
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 1.33,
|
| 488 |
+
"grad_norm": 3.1741673946380615,
|
| 489 |
+
"learning_rate": 1.111584932480455e-05,
|
| 490 |
+
"loss": 0.839,
|
| 491 |
+
"step": 1250
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 1.36,
|
| 495 |
+
"grad_norm": 3.3300561904907227,
|
| 496 |
+
"learning_rate": 1.0938166311300639e-05,
|
| 497 |
+
"loss": 0.8273,
|
| 498 |
+
"step": 1275
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 1.39,
|
| 502 |
+
"grad_norm": 4.480769634246826,
|
| 503 |
+
"learning_rate": 1.0760483297796731e-05,
|
| 504 |
+
"loss": 0.8237,
|
| 505 |
+
"step": 1300
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 1.39,
|
| 509 |
+
"eval_accuracy": 0.8077,
|
| 510 |
+
"eval_f1_macro": 0.6529082127640804,
|
| 511 |
+
"eval_f1_micro": 0.8077,
|
| 512 |
+
"eval_loss": 0.7814128994941711,
|
| 513 |
+
"eval_runtime": 5.0887,
|
| 514 |
+
"eval_samples_per_second": 1965.129,
|
| 515 |
+
"eval_steps_per_second": 30.853,
|
| 516 |
+
"step": 1300
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 1.41,
|
| 520 |
+
"grad_norm": 4.553057670593262,
|
| 521 |
+
"learning_rate": 1.0582800284292822e-05,
|
| 522 |
+
"loss": 0.8214,
|
| 523 |
+
"step": 1325
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 1.44,
|
| 527 |
+
"grad_norm": 3.766432046890259,
|
| 528 |
+
"learning_rate": 1.0405117270788913e-05,
|
| 529 |
+
"loss": 0.8174,
|
| 530 |
+
"step": 1350
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 1.47,
|
| 534 |
+
"grad_norm": 4.3826446533203125,
|
| 535 |
+
"learning_rate": 1.0227434257285005e-05,
|
| 536 |
+
"loss": 0.772,
|
| 537 |
+
"step": 1375
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 1.49,
|
| 541 |
+
"grad_norm": 3.777904748916626,
|
| 542 |
+
"learning_rate": 1.0049751243781096e-05,
|
| 543 |
+
"loss": 0.7341,
|
| 544 |
+
"step": 1400
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 1.49,
|
| 548 |
+
"eval_accuracy": 0.8099,
|
| 549 |
+
"eval_f1_macro": 0.6600339223452895,
|
| 550 |
+
"eval_f1_micro": 0.8099,
|
| 551 |
+
"eval_loss": 0.7653506994247437,
|
| 552 |
+
"eval_runtime": 5.0857,
|
| 553 |
+
"eval_samples_per_second": 1966.297,
|
| 554 |
+
"eval_steps_per_second": 30.871,
|
| 555 |
+
"step": 1400
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.52,
|
| 559 |
+
"grad_norm": 4.6313629150390625,
|
| 560 |
+
"learning_rate": 9.872068230277187e-06,
|
| 561 |
+
"loss": 0.7761,
|
| 562 |
+
"step": 1425
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.55,
|
| 566 |
+
"grad_norm": 3.6354401111602783,
|
| 567 |
+
"learning_rate": 9.694385216773277e-06,
|
| 568 |
+
"loss": 0.8205,
|
| 569 |
+
"step": 1450
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.57,
|
| 573 |
+
"grad_norm": 3.7265005111694336,
|
| 574 |
+
"learning_rate": 9.516702203269368e-06,
|
| 575 |
+
"loss": 0.7916,
|
| 576 |
+
"step": 1475
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.6,
|
| 580 |
+
"grad_norm": 3.4605891704559326,
|
| 581 |
+
"learning_rate": 9.339019189765458e-06,
|
| 582 |
+
"loss": 0.7475,
|
| 583 |
+
"step": 1500
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.6,
|
| 587 |
+
"eval_accuracy": 0.8135,
|
| 588 |
+
"eval_f1_macro": 0.6650413690305985,
|
| 589 |
+
"eval_f1_micro": 0.8135,
|
| 590 |
+
"eval_loss": 0.7457693815231323,
|
| 591 |
+
"eval_runtime": 5.0844,
|
| 592 |
+
"eval_samples_per_second": 1966.8,
|
| 593 |
+
"eval_steps_per_second": 30.879,
|
| 594 |
+
"step": 1500
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.63,
|
| 598 |
+
"grad_norm": 5.460809707641602,
|
| 599 |
+
"learning_rate": 9.161336176261551e-06,
|
| 600 |
+
"loss": 0.7576,
|
| 601 |
+
"step": 1525
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 1.65,
|
| 605 |
+
"grad_norm": 3.1193032264709473,
|
| 606 |
+
"learning_rate": 8.98365316275764e-06,
|
| 607 |
+
"loss": 0.7156,
|
| 608 |
+
"step": 1550
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 1.68,
|
| 612 |
+
"grad_norm": 3.7673654556274414,
|
| 613 |
+
"learning_rate": 8.805970149253732e-06,
|
| 614 |
+
"loss": 0.6944,
|
| 615 |
+
"step": 1575
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.71,
|
| 619 |
+
"grad_norm": 4.008440971374512,
|
| 620 |
+
"learning_rate": 8.628287135749823e-06,
|
| 621 |
+
"loss": 0.7699,
|
| 622 |
+
"step": 1600
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 1.71,
|
| 626 |
+
"eval_accuracy": 0.8183,
|
| 627 |
+
"eval_f1_macro": 0.681030771263254,
|
| 628 |
+
"eval_f1_micro": 0.8183,
|
| 629 |
+
"eval_loss": 0.7288192510604858,
|
| 630 |
+
"eval_runtime": 5.0906,
|
| 631 |
+
"eval_samples_per_second": 1964.407,
|
| 632 |
+
"eval_steps_per_second": 30.841,
|
| 633 |
+
"step": 1600
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.73,
|
| 637 |
+
"grad_norm": 3.998149871826172,
|
| 638 |
+
"learning_rate": 8.450604122245915e-06,
|
| 639 |
+
"loss": 0.742,
|
| 640 |
+
"step": 1625
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.76,
|
| 644 |
+
"grad_norm": 4.329924583435059,
|
| 645 |
+
"learning_rate": 8.272921108742004e-06,
|
| 646 |
+
"loss": 0.7505,
|
| 647 |
+
"step": 1650
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.79,
|
| 651 |
+
"grad_norm": 3.9420013427734375,
|
| 652 |
+
"learning_rate": 8.095238095238097e-06,
|
| 653 |
+
"loss": 0.7005,
|
| 654 |
+
"step": 1675
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.81,
|
| 658 |
+
"grad_norm": 4.527777194976807,
|
| 659 |
+
"learning_rate": 7.917555081734187e-06,
|
| 660 |
+
"loss": 0.7472,
|
| 661 |
+
"step": 1700
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.81,
|
| 665 |
+
"eval_accuracy": 0.8179,
|
| 666 |
+
"eval_f1_macro": 0.681973246053428,
|
| 667 |
+
"eval_f1_micro": 0.8179,
|
| 668 |
+
"eval_loss": 0.712536633014679,
|
| 669 |
+
"eval_runtime": 5.0869,
|
| 670 |
+
"eval_samples_per_second": 1965.828,
|
| 671 |
+
"eval_steps_per_second": 30.864,
|
| 672 |
+
"step": 1700
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 1.84,
|
| 676 |
+
"grad_norm": 5.481727600097656,
|
| 677 |
+
"learning_rate": 7.739872068230278e-06,
|
| 678 |
+
"loss": 0.7694,
|
| 679 |
+
"step": 1725
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 1.87,
|
| 683 |
+
"grad_norm": 3.634965658187866,
|
| 684 |
+
"learning_rate": 7.5621890547263685e-06,
|
| 685 |
+
"loss": 0.6916,
|
| 686 |
+
"step": 1750
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 1.89,
|
| 690 |
+
"grad_norm": 4.712828636169434,
|
| 691 |
+
"learning_rate": 7.38450604122246e-06,
|
| 692 |
+
"loss": 0.7452,
|
| 693 |
+
"step": 1775
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 1.92,
|
| 697 |
+
"grad_norm": 4.240174770355225,
|
| 698 |
+
"learning_rate": 7.20682302771855e-06,
|
| 699 |
+
"loss": 0.689,
|
| 700 |
+
"step": 1800
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 1.92,
|
| 704 |
+
"eval_accuracy": 0.8201,
|
| 705 |
+
"eval_f1_macro": 0.6821776177873132,
|
| 706 |
+
"eval_f1_micro": 0.8201,
|
| 707 |
+
"eval_loss": 0.6964806914329529,
|
| 708 |
+
"eval_runtime": 5.0903,
|
| 709 |
+
"eval_samples_per_second": 1964.526,
|
| 710 |
+
"eval_steps_per_second": 30.843,
|
| 711 |
+
"step": 1800
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.95,
|
| 715 |
+
"grad_norm": 3.659916639328003,
|
| 716 |
+
"learning_rate": 7.029140014214641e-06,
|
| 717 |
+
"loss": 0.8135,
|
| 718 |
+
"step": 1825
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 1.97,
|
| 722 |
+
"grad_norm": 4.639604091644287,
|
| 723 |
+
"learning_rate": 6.851457000710733e-06,
|
| 724 |
+
"loss": 0.7496,
|
| 725 |
+
"step": 1850
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 2.0,
|
| 729 |
+
"grad_norm": 4.354977607727051,
|
| 730 |
+
"learning_rate": 6.673773987206824e-06,
|
| 731 |
+
"loss": 0.6715,
|
| 732 |
+
"step": 1875
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 2.03,
|
| 736 |
+
"grad_norm": 3.503903865814209,
|
| 737 |
+
"learning_rate": 6.496090973702914e-06,
|
| 738 |
+
"loss": 0.6807,
|
| 739 |
+
"step": 1900
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 2.03,
|
| 743 |
+
"eval_accuracy": 0.8192,
|
| 744 |
+
"eval_f1_macro": 0.6798912747134073,
|
| 745 |
+
"eval_f1_micro": 0.8192,
|
| 746 |
+
"eval_loss": 0.6904103755950928,
|
| 747 |
+
"eval_runtime": 5.0876,
|
| 748 |
+
"eval_samples_per_second": 1965.568,
|
| 749 |
+
"eval_steps_per_second": 30.859,
|
| 750 |
+
"step": 1900
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 2.05,
|
| 754 |
+
"grad_norm": 2.8646299839019775,
|
| 755 |
+
"learning_rate": 6.318407960199006e-06,
|
| 756 |
+
"loss": 0.6768,
|
| 757 |
+
"step": 1925
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 2.08,
|
| 761 |
+
"grad_norm": 4.127985000610352,
|
| 762 |
+
"learning_rate": 6.140724946695097e-06,
|
| 763 |
+
"loss": 0.7144,
|
| 764 |
+
"step": 1950
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 2.11,
|
| 768 |
+
"grad_norm": 3.0997469425201416,
|
| 769 |
+
"learning_rate": 5.963041933191187e-06,
|
| 770 |
+
"loss": 0.6447,
|
| 771 |
+
"step": 1975
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 2.13,
|
| 775 |
+
"grad_norm": 4.458724498748779,
|
| 776 |
+
"learning_rate": 5.785358919687279e-06,
|
| 777 |
+
"loss": 0.6514,
|
| 778 |
+
"step": 2000
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 2.13,
|
| 782 |
+
"eval_accuracy": 0.8239,
|
| 783 |
+
"eval_f1_macro": 0.6922798719270521,
|
| 784 |
+
"eval_f1_micro": 0.8239,
|
| 785 |
+
"eval_loss": 0.6835533976554871,
|
| 786 |
+
"eval_runtime": 5.09,
|
| 787 |
+
"eval_samples_per_second": 1964.629,
|
| 788 |
+
"eval_steps_per_second": 30.845,
|
| 789 |
+
"step": 2000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 2.16,
|
| 793 |
+
"grad_norm": 3.7359683513641357,
|
| 794 |
+
"learning_rate": 5.607675906183369e-06,
|
| 795 |
+
"loss": 0.6547,
|
| 796 |
+
"step": 2025
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 2.19,
|
| 800 |
+
"grad_norm": 3.74875807762146,
|
| 801 |
+
"learning_rate": 5.42999289267946e-06,
|
| 802 |
+
"loss": 0.6577,
|
| 803 |
+
"step": 2050
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 2.21,
|
| 807 |
+
"grad_norm": 3.634157419204712,
|
| 808 |
+
"learning_rate": 5.2523098791755514e-06,
|
| 809 |
+
"loss": 0.6596,
|
| 810 |
+
"step": 2075
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 2.24,
|
| 814 |
+
"grad_norm": 4.218031406402588,
|
| 815 |
+
"learning_rate": 5.074626865671642e-06,
|
| 816 |
+
"loss": 0.6662,
|
| 817 |
+
"step": 2100
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 2.24,
|
| 821 |
+
"eval_accuracy": 0.8267,
|
| 822 |
+
"eval_f1_macro": 0.7018656510236515,
|
| 823 |
+
"eval_f1_micro": 0.8267,
|
| 824 |
+
"eval_loss": 0.6749560832977295,
|
| 825 |
+
"eval_runtime": 5.0908,
|
| 826 |
+
"eval_samples_per_second": 1964.309,
|
| 827 |
+
"eval_steps_per_second": 30.84,
|
| 828 |
+
"step": 2100
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 2.27,
|
| 832 |
+
"grad_norm": 4.950326442718506,
|
| 833 |
+
"learning_rate": 4.896943852167733e-06,
|
| 834 |
+
"loss": 0.6144,
|
| 835 |
+
"step": 2125
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 2.29,
|
| 839 |
+
"grad_norm": 3.0254364013671875,
|
| 840 |
+
"learning_rate": 4.719260838663824e-06,
|
| 841 |
+
"loss": 0.6402,
|
| 842 |
+
"step": 2150
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 2.32,
|
| 846 |
+
"grad_norm": 2.264652967453003,
|
| 847 |
+
"learning_rate": 4.541577825159915e-06,
|
| 848 |
+
"loss": 0.5597,
|
| 849 |
+
"step": 2175
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 2.35,
|
| 853 |
+
"grad_norm": 5.00731086730957,
|
| 854 |
+
"learning_rate": 4.363894811656006e-06,
|
| 855 |
+
"loss": 0.6247,
|
| 856 |
+
"step": 2200
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 2.35,
|
| 860 |
+
"eval_accuracy": 0.8284,
|
| 861 |
+
"eval_f1_macro": 0.7028136538357826,
|
| 862 |
+
"eval_f1_micro": 0.8284,
|
| 863 |
+
"eval_loss": 0.6703132390975952,
|
| 864 |
+
"eval_runtime": 5.0889,
|
| 865 |
+
"eval_samples_per_second": 1965.077,
|
| 866 |
+
"eval_steps_per_second": 30.852,
|
| 867 |
+
"step": 2200
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 2.37,
|
| 871 |
+
"grad_norm": 3.5009686946868896,
|
| 872 |
+
"learning_rate": 4.186211798152097e-06,
|
| 873 |
+
"loss": 0.5784,
|
| 874 |
+
"step": 2225
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 2.4,
|
| 878 |
+
"grad_norm": 3.339487075805664,
|
| 879 |
+
"learning_rate": 4.008528784648188e-06,
|
| 880 |
+
"loss": 0.6321,
|
| 881 |
+
"step": 2250
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 2.43,
|
| 885 |
+
"grad_norm": 4.3150129318237305,
|
| 886 |
+
"learning_rate": 3.8308457711442784e-06,
|
| 887 |
+
"loss": 0.6499,
|
| 888 |
+
"step": 2275
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 2.45,
|
| 892 |
+
"grad_norm": 3.9127256870269775,
|
| 893 |
+
"learning_rate": 3.65316275764037e-06,
|
| 894 |
+
"loss": 0.6443,
|
| 895 |
+
"step": 2300
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 2.45,
|
| 899 |
+
"eval_accuracy": 0.8265,
|
| 900 |
+
"eval_f1_macro": 0.7001404361966705,
|
| 901 |
+
"eval_f1_micro": 0.8265,
|
| 902 |
+
"eval_loss": 0.666212260723114,
|
| 903 |
+
"eval_runtime": 5.0933,
|
| 904 |
+
"eval_samples_per_second": 1963.351,
|
| 905 |
+
"eval_steps_per_second": 30.825,
|
| 906 |
+
"step": 2300
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 2.48,
|
| 910 |
+
"grad_norm": 4.648262023925781,
|
| 911 |
+
"learning_rate": 3.4754797441364606e-06,
|
| 912 |
+
"loss": 0.6597,
|
| 913 |
+
"step": 2325
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 2.51,
|
| 917 |
+
"grad_norm": 5.805054187774658,
|
| 918 |
+
"learning_rate": 3.297796730632552e-06,
|
| 919 |
+
"loss": 0.6679,
|
| 920 |
+
"step": 2350
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 2.53,
|
| 924 |
+
"grad_norm": 3.7240312099456787,
|
| 925 |
+
"learning_rate": 3.120113717128643e-06,
|
| 926 |
+
"loss": 0.6098,
|
| 927 |
+
"step": 2375
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 2.56,
|
| 931 |
+
"grad_norm": 6.238827705383301,
|
| 932 |
+
"learning_rate": 2.9424307036247335e-06,
|
| 933 |
+
"loss": 0.632,
|
| 934 |
+
"step": 2400
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 2.56,
|
| 938 |
+
"eval_accuracy": 0.8295,
|
| 939 |
+
"eval_f1_macro": 0.7077893947175455,
|
| 940 |
+
"eval_f1_micro": 0.8295,
|
| 941 |
+
"eval_loss": 0.6571224331855774,
|
| 942 |
+
"eval_runtime": 5.0923,
|
| 943 |
+
"eval_samples_per_second": 1963.743,
|
| 944 |
+
"eval_steps_per_second": 30.831,
|
| 945 |
+
"step": 2400
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 2.59,
|
| 949 |
+
"grad_norm": 2.7973475456237793,
|
| 950 |
+
"learning_rate": 2.764747690120825e-06,
|
| 951 |
+
"loss": 0.7127,
|
| 952 |
+
"step": 2425
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 2.61,
|
| 956 |
+
"grad_norm": 4.434217929840088,
|
| 957 |
+
"learning_rate": 2.5870646766169156e-06,
|
| 958 |
+
"loss": 0.6907,
|
| 959 |
+
"step": 2450
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 2.64,
|
| 963 |
+
"grad_norm": 5.4939188957214355,
|
| 964 |
+
"learning_rate": 2.4093816631130067e-06,
|
| 965 |
+
"loss": 0.6308,
|
| 966 |
+
"step": 2475
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 2.67,
|
| 970 |
+
"grad_norm": 6.5089430809021,
|
| 971 |
+
"learning_rate": 2.2316986496090974e-06,
|
| 972 |
+
"loss": 0.5922,
|
| 973 |
+
"step": 2500
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 2.67,
|
| 977 |
+
"eval_accuracy": 0.8298,
|
| 978 |
+
"eval_f1_macro": 0.7083519630678758,
|
| 979 |
+
"eval_f1_micro": 0.8298,
|
| 980 |
+
"eval_loss": 0.6538856029510498,
|
| 981 |
+
"eval_runtime": 5.111,
|
| 982 |
+
"eval_samples_per_second": 1956.564,
|
| 983 |
+
"eval_steps_per_second": 30.718,
|
| 984 |
+
"step": 2500
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 2.69,
|
| 988 |
+
"grad_norm": 4.474384307861328,
|
| 989 |
+
"learning_rate": 2.0540156361051885e-06,
|
| 990 |
+
"loss": 0.6384,
|
| 991 |
+
"step": 2525
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 2.72,
|
| 995 |
+
"grad_norm": 4.887701511383057,
|
| 996 |
+
"learning_rate": 1.8763326226012796e-06,
|
| 997 |
+
"loss": 0.614,
|
| 998 |
+
"step": 2550
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 2.75,
|
| 1002 |
+
"grad_norm": 6.661905288696289,
|
| 1003 |
+
"learning_rate": 1.6986496090973702e-06,
|
| 1004 |
+
"loss": 0.626,
|
| 1005 |
+
"step": 2575
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 2.77,
|
| 1009 |
+
"grad_norm": 4.168758392333984,
|
| 1010 |
+
"learning_rate": 1.5209665955934613e-06,
|
| 1011 |
+
"loss": 0.6423,
|
| 1012 |
+
"step": 2600
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 2.77,
|
| 1016 |
+
"eval_accuracy": 0.8311,
|
| 1017 |
+
"eval_f1_macro": 0.7138508038282735,
|
| 1018 |
+
"eval_f1_micro": 0.8311,
|
| 1019 |
+
"eval_loss": 0.6518952250480652,
|
| 1020 |
+
"eval_runtime": 5.0992,
|
| 1021 |
+
"eval_samples_per_second": 1961.08,
|
| 1022 |
+
"eval_steps_per_second": 30.789,
|
| 1023 |
+
"step": 2600
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 2.8,
|
| 1027 |
+
"grad_norm": 3.9610595703125,
|
| 1028 |
+
"learning_rate": 1.3432835820895524e-06,
|
| 1029 |
+
"loss": 0.6361,
|
| 1030 |
+
"step": 2625
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 2.83,
|
| 1034 |
+
"grad_norm": 5.312166213989258,
|
| 1035 |
+
"learning_rate": 1.1656005685856433e-06,
|
| 1036 |
+
"loss": 0.6638,
|
| 1037 |
+
"step": 2650
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 2.85,
|
| 1041 |
+
"grad_norm": 4.739462852478027,
|
| 1042 |
+
"learning_rate": 9.879175550817342e-07,
|
| 1043 |
+
"loss": 0.625,
|
| 1044 |
+
"step": 2675
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 2.88,
|
| 1048 |
+
"grad_norm": 5.244933128356934,
|
| 1049 |
+
"learning_rate": 8.102345415778253e-07,
|
| 1050 |
+
"loss": 0.6156,
|
| 1051 |
+
"step": 2700
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 2.88,
|
| 1055 |
+
"eval_accuracy": 0.8311,
|
| 1056 |
+
"eval_f1_macro": 0.7123382093925994,
|
| 1057 |
+
"eval_f1_micro": 0.8311,
|
| 1058 |
+
"eval_loss": 0.6500191688537598,
|
| 1059 |
+
"eval_runtime": 5.1041,
|
| 1060 |
+
"eval_samples_per_second": 1959.192,
|
| 1061 |
+
"eval_steps_per_second": 30.759,
|
| 1062 |
+
"step": 2700
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 2.91,
|
| 1066 |
+
"grad_norm": 3.2966127395629883,
|
| 1067 |
+
"learning_rate": 6.325515280739161e-07,
|
| 1068 |
+
"loss": 0.6181,
|
| 1069 |
+
"step": 2725
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 2.93,
|
| 1073 |
+
"grad_norm": 4.855289936065674,
|
| 1074 |
+
"learning_rate": 4.548685145700071e-07,
|
| 1075 |
+
"loss": 0.5952,
|
| 1076 |
+
"step": 2750
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 2.96,
|
| 1080 |
+
"grad_norm": 5.3126068115234375,
|
| 1081 |
+
"learning_rate": 2.771855010660981e-07,
|
| 1082 |
+
"loss": 0.5727,
|
| 1083 |
+
"step": 2775
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 2.99,
|
| 1087 |
+
"grad_norm": 3.789565324783325,
|
| 1088 |
+
"learning_rate": 9.950248756218906e-08,
|
| 1089 |
+
"loss": 0.6097,
|
| 1090 |
+
"step": 2800
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 2.99,
|
| 1094 |
+
"eval_accuracy": 0.8311,
|
| 1095 |
+
"eval_f1_macro": 0.7116365414985335,
|
| 1096 |
+
"eval_f1_micro": 0.8311,
|
| 1097 |
+
"eval_loss": 0.6496002674102783,
|
| 1098 |
+
"eval_runtime": 5.1014,
|
| 1099 |
+
"eval_samples_per_second": 1960.25,
|
| 1100 |
+
"eval_steps_per_second": 30.776,
|
| 1101 |
+
"step": 2800
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 3.0,
|
| 1105 |
+
"step": 2814,
|
| 1106 |
+
"total_flos": 5974635617189888.0,
|
| 1107 |
+
"train_loss": 1.1483757653470232,
|
| 1108 |
+
"train_runtime": 441.0175,
|
| 1109 |
+
"train_samples_per_second": 408.147,
|
| 1110 |
+
"train_steps_per_second": 6.381
|
| 1111 |
+
}
|
| 1112 |
+
],
|
| 1113 |
+
"logging_steps": 25,
|
| 1114 |
+
"max_steps": 2814,
|
| 1115 |
+
"num_input_tokens_seen": 0,
|
| 1116 |
+
"num_train_epochs": 3,
|
| 1117 |
+
"save_steps": 100,
|
| 1118 |
+
"total_flos": 5974635617189888.0,
|
| 1119 |
+
"train_batch_size": 32,
|
| 1120 |
+
"trial_name": null,
|
| 1121 |
+
"trial_params": null
|
| 1122 |
+
}
|