Upload folder using huggingface_hub
Browse files- all_results.json +15 -0
- checkpoint-15000/config.json +32 -0
- checkpoint-15000/model.safetensors +3 -0
- checkpoint-15000/optimizer.pt +3 -0
- checkpoint-15000/rng_state.pth +3 -0
- checkpoint-15000/scaler.pt +3 -0
- checkpoint-15000/scheduler.pt +3 -0
- checkpoint-15000/special_tokens_map.json +7 -0
- checkpoint-15000/tokenizer.json +0 -0
- checkpoint-15000/tokenizer_config.json +56 -0
- checkpoint-15000/trainer_state.json +304 -0
- checkpoint-15000/training_args.bin +3 -0
- checkpoint-15000/vocab.txt +0 -0
- checkpoint-16000/config.json +32 -0
- checkpoint-16000/model.safetensors +3 -0
- checkpoint-16000/optimizer.pt +3 -0
- checkpoint-16000/rng_state.pth +3 -0
- checkpoint-16000/scaler.pt +3 -0
- checkpoint-16000/scheduler.pt +3 -0
- checkpoint-16000/special_tokens_map.json +7 -0
- checkpoint-16000/tokenizer.json +0 -0
- checkpoint-16000/tokenizer_config.json +56 -0
- checkpoint-16000/trainer_state.json +322 -0
- checkpoint-16000/training_args.bin +3 -0
- checkpoint-16000/vocab.txt +0 -0
- checkpoint-16875/config.json +32 -0
- checkpoint-16875/model.safetensors +3 -0
- checkpoint-16875/optimizer.pt +3 -0
- checkpoint-16875/rng_state.pth +3 -0
- checkpoint-16875/scaler.pt +3 -0
- checkpoint-16875/scheduler.pt +3 -0
- checkpoint-16875/special_tokens_map.json +7 -0
- checkpoint-16875/tokenizer.json +0 -0
- checkpoint-16875/tokenizer_config.json +56 -0
- checkpoint-16875/trainer_state.json +322 -0
- checkpoint-16875/training_args.bin +3 -0
- checkpoint-16875/vocab.txt +0 -0
- config.json +32 -0
- eval_final_results.json +10 -0
- model.safetensors +3 -0
- runs/Jun28_05-39-58_eagle/events.out.tfevents.1751089199.eagle.2176823.0 +3 -0
- runs/Jun28_05-39-58_eagle/events.out.tfevents.1751089814.eagle.2176823.1 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- train_results.json +8 -0
- trainer_state.json +331 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.17947633564472198,
|
| 4 |
+
"eval_mae": 0.22917917370796204,
|
| 5 |
+
"eval_mse": 0.17947635054588318,
|
| 6 |
+
"eval_r2": 0.8307942152023315,
|
| 7 |
+
"eval_runtime": 4.7945,
|
| 8 |
+
"eval_samples_per_second": 2085.702,
|
| 9 |
+
"eval_steps_per_second": 130.356,
|
| 10 |
+
"total_flos": 3.551967355392e+16,
|
| 11 |
+
"train_loss": 0.17141379213686342,
|
| 12 |
+
"train_runtime": 610.1774,
|
| 13 |
+
"train_samples_per_second": 442.494,
|
| 14 |
+
"train_steps_per_second": 27.656
|
| 15 |
+
}
|
checkpoint-15000/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"gradient_checkpointing": false,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0"
|
| 13 |
+
},
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"label2id": {
|
| 17 |
+
"LABEL_0": 0
|
| 18 |
+
},
|
| 19 |
+
"layer_norm_eps": 1e-12,
|
| 20 |
+
"max_position_embeddings": 512,
|
| 21 |
+
"model_type": "bert",
|
| 22 |
+
"num_attention_heads": 12,
|
| 23 |
+
"num_hidden_layers": 12,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"position_embedding_type": "absolute",
|
| 26 |
+
"problem_type": "regression",
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.52.4",
|
| 29 |
+
"type_vocab_size": 2,
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 30522
|
| 32 |
+
}
|
checkpoint-15000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4400857bfafecd279d1b46340c644ceba22112716bef0016a9d503cad17c35e1
|
| 3 |
+
size 437955572
|
checkpoint-15000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b00bb9891e4232971b491cf80856ccadaf2e4cf037d906977955089af4c340ed
|
| 3 |
+
size 876032651
|
checkpoint-15000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:507ab62fbd42141677b999b60e7655e2c2957d52efa51302c4a4565e455304d2
|
| 3 |
+
size 14645
|
checkpoint-15000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:878a1a20c7da9d5d33fb0b2bea1a09cb895d67b09c0d94854b9c78f4fcea90d4
|
| 3 |
+
size 1383
|
checkpoint-15000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6acece3bbe0f1235697ed5165e0df732121305e96de3bdc982c3eae90c82ff23
|
| 3 |
+
size 1465
|
checkpoint-15000/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 |
+
}
|
checkpoint-15000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-15000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "BertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
checkpoint-15000/trainer_state.json
ADDED
|
@@ -0,0 +1,304 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 15000,
|
| 3 |
+
"best_metric": 0.8307942152023315,
|
| 4 |
+
"best_model_checkpoint": "ActionBert2-109M/checkpoint-15000",
|
| 5 |
+
"epoch": 2.6666666666666665,
|
| 6 |
+
"eval_steps": 1000,
|
| 7 |
+
"global_step": 15000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.17777777777777778,
|
| 14 |
+
"grad_norm": 3.1670663356781006,
|
| 15 |
+
"learning_rate": 1.8821925925925927e-05,
|
| 16 |
+
"loss": 0.3813,
|
| 17 |
+
"step": 1000
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.17777777777777778,
|
| 21 |
+
"eval_loss": 0.2506166696548462,
|
| 22 |
+
"eval_mae": 0.3367820978164673,
|
| 23 |
+
"eval_mse": 0.2506166696548462,
|
| 24 |
+
"eval_r2": 0.7637249827384949,
|
| 25 |
+
"eval_runtime": 4.791,
|
| 26 |
+
"eval_samples_per_second": 2087.248,
|
| 27 |
+
"eval_steps_per_second": 130.453,
|
| 28 |
+
"step": 1000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.35555555555555557,
|
| 32 |
+
"grad_norm": 3.0615577697753906,
|
| 33 |
+
"learning_rate": 1.7636740740740744e-05,
|
| 34 |
+
"loss": 0.263,
|
| 35 |
+
"step": 2000
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.35555555555555557,
|
| 39 |
+
"eval_loss": 0.2408183068037033,
|
| 40 |
+
"eval_mae": 0.31582972407341003,
|
| 41 |
+
"eval_mse": 0.24081829190254211,
|
| 42 |
+
"eval_r2": 0.7729626297950745,
|
| 43 |
+
"eval_runtime": 4.7936,
|
| 44 |
+
"eval_samples_per_second": 2086.113,
|
| 45 |
+
"eval_steps_per_second": 130.382,
|
| 46 |
+
"step": 2000
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.5333333333333333,
|
| 50 |
+
"grad_norm": 11.606523513793945,
|
| 51 |
+
"learning_rate": 1.6451555555555554e-05,
|
| 52 |
+
"loss": 0.2506,
|
| 53 |
+
"step": 3000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.5333333333333333,
|
| 57 |
+
"eval_loss": 0.21803471446037292,
|
| 58 |
+
"eval_mae": 0.29080167412757874,
|
| 59 |
+
"eval_mse": 0.21803471446037292,
|
| 60 |
+
"eval_r2": 0.7944424152374268,
|
| 61 |
+
"eval_runtime": 4.7889,
|
| 62 |
+
"eval_samples_per_second": 2088.155,
|
| 63 |
+
"eval_steps_per_second": 130.51,
|
| 64 |
+
"step": 3000
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.7111111111111111,
|
| 68 |
+
"grad_norm": 13.706526756286621,
|
| 69 |
+
"learning_rate": 1.5266370370370372e-05,
|
| 70 |
+
"loss": 0.2414,
|
| 71 |
+
"step": 4000
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.7111111111111111,
|
| 75 |
+
"eval_loss": 0.20693176984786987,
|
| 76 |
+
"eval_mae": 0.2782182991504669,
|
| 77 |
+
"eval_mse": 0.20693176984786987,
|
| 78 |
+
"eval_r2": 0.8049100041389465,
|
| 79 |
+
"eval_runtime": 4.7925,
|
| 80 |
+
"eval_samples_per_second": 2086.596,
|
| 81 |
+
"eval_steps_per_second": 130.412,
|
| 82 |
+
"step": 4000
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.8888888888888888,
|
| 86 |
+
"grad_norm": 6.0101423263549805,
|
| 87 |
+
"learning_rate": 1.4081185185185186e-05,
|
| 88 |
+
"loss": 0.2295,
|
| 89 |
+
"step": 5000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.8888888888888888,
|
| 93 |
+
"eval_loss": 0.2030615508556366,
|
| 94 |
+
"eval_mae": 0.27224966883659363,
|
| 95 |
+
"eval_mse": 0.2030615508556366,
|
| 96 |
+
"eval_r2": 0.8085587024688721,
|
| 97 |
+
"eval_runtime": 4.7946,
|
| 98 |
+
"eval_samples_per_second": 2085.665,
|
| 99 |
+
"eval_steps_per_second": 130.354,
|
| 100 |
+
"step": 5000
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.0666666666666667,
|
| 104 |
+
"grad_norm": 7.812684059143066,
|
| 105 |
+
"learning_rate": 1.2896000000000002e-05,
|
| 106 |
+
"loss": 0.1969,
|
| 107 |
+
"step": 6000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.0666666666666667,
|
| 111 |
+
"eval_loss": 0.19701267778873444,
|
| 112 |
+
"eval_mae": 0.2610624134540558,
|
| 113 |
+
"eval_mse": 0.19701267778873444,
|
| 114 |
+
"eval_r2": 0.8142614364624023,
|
| 115 |
+
"eval_runtime": 4.7965,
|
| 116 |
+
"eval_samples_per_second": 2084.853,
|
| 117 |
+
"eval_steps_per_second": 130.303,
|
| 118 |
+
"step": 6000
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 1.2444444444444445,
|
| 122 |
+
"grad_norm": 4.992111682891846,
|
| 123 |
+
"learning_rate": 1.1710814814814816e-05,
|
| 124 |
+
"loss": 0.1495,
|
| 125 |
+
"step": 7000
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.2444444444444445,
|
| 129 |
+
"eval_loss": 0.1891198754310608,
|
| 130 |
+
"eval_mae": 0.24995234608650208,
|
| 131 |
+
"eval_mse": 0.1891198605298996,
|
| 132 |
+
"eval_r2": 0.8217025995254517,
|
| 133 |
+
"eval_runtime": 4.7971,
|
| 134 |
+
"eval_samples_per_second": 2084.602,
|
| 135 |
+
"eval_steps_per_second": 130.288,
|
| 136 |
+
"step": 7000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.4222222222222223,
|
| 140 |
+
"grad_norm": 4.602079391479492,
|
| 141 |
+
"learning_rate": 1.052562962962963e-05,
|
| 142 |
+
"loss": 0.1557,
|
| 143 |
+
"step": 8000
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.4222222222222223,
|
| 147 |
+
"eval_loss": 0.18423964083194733,
|
| 148 |
+
"eval_mae": 0.2460847944021225,
|
| 149 |
+
"eval_mse": 0.18423964083194733,
|
| 150 |
+
"eval_r2": 0.8263035416603088,
|
| 151 |
+
"eval_runtime": 4.7986,
|
| 152 |
+
"eval_samples_per_second": 2083.948,
|
| 153 |
+
"eval_steps_per_second": 130.247,
|
| 154 |
+
"step": 8000
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.6,
|
| 158 |
+
"grad_norm": 4.8106303215026855,
|
| 159 |
+
"learning_rate": 9.340444444444445e-06,
|
| 160 |
+
"loss": 0.1474,
|
| 161 |
+
"step": 9000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.6,
|
| 165 |
+
"eval_loss": 0.18420642614364624,
|
| 166 |
+
"eval_mae": 0.24716965854167938,
|
| 167 |
+
"eval_mse": 0.18420642614364624,
|
| 168 |
+
"eval_r2": 0.8263348340988159,
|
| 169 |
+
"eval_runtime": 4.7984,
|
| 170 |
+
"eval_samples_per_second": 2084.015,
|
| 171 |
+
"eval_steps_per_second": 130.251,
|
| 172 |
+
"step": 9000
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.7777777777777777,
|
| 176 |
+
"grad_norm": 8.563740730285645,
|
| 177 |
+
"learning_rate": 8.156444444444444e-06,
|
| 178 |
+
"loss": 0.1419,
|
| 179 |
+
"step": 10000
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.7777777777777777,
|
| 183 |
+
"eval_loss": 0.18527014553546906,
|
| 184 |
+
"eval_mae": 0.24834123253822327,
|
| 185 |
+
"eval_mse": 0.18527014553546906,
|
| 186 |
+
"eval_r2": 0.8253320455551147,
|
| 187 |
+
"eval_runtime": 4.7987,
|
| 188 |
+
"eval_samples_per_second": 2083.902,
|
| 189 |
+
"eval_steps_per_second": 130.244,
|
| 190 |
+
"step": 10000
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.9555555555555557,
|
| 194 |
+
"grad_norm": 7.638633728027344,
|
| 195 |
+
"learning_rate": 6.97125925925926e-06,
|
| 196 |
+
"loss": 0.1513,
|
| 197 |
+
"step": 11000
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.9555555555555557,
|
| 201 |
+
"eval_loss": 0.19055569171905518,
|
| 202 |
+
"eval_mae": 0.2580980956554413,
|
| 203 |
+
"eval_mse": 0.19055569171905518,
|
| 204 |
+
"eval_r2": 0.8203489184379578,
|
| 205 |
+
"eval_runtime": 4.7998,
|
| 206 |
+
"eval_samples_per_second": 2083.401,
|
| 207 |
+
"eval_steps_per_second": 130.213,
|
| 208 |
+
"step": 11000
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 2.1333333333333333,
|
| 212 |
+
"grad_norm": 4.0671234130859375,
|
| 213 |
+
"learning_rate": 5.78725925925926e-06,
|
| 214 |
+
"loss": 0.1108,
|
| 215 |
+
"step": 12000
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 2.1333333333333333,
|
| 219 |
+
"eval_loss": 0.1817326694726944,
|
| 220 |
+
"eval_mae": 0.23058335483074188,
|
| 221 |
+
"eval_mse": 0.1817326694726944,
|
| 222 |
+
"eval_r2": 0.8286670446395874,
|
| 223 |
+
"eval_runtime": 4.8008,
|
| 224 |
+
"eval_samples_per_second": 2082.976,
|
| 225 |
+
"eval_steps_per_second": 130.186,
|
| 226 |
+
"step": 12000
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 2.311111111111111,
|
| 230 |
+
"grad_norm": 5.488609790802002,
|
| 231 |
+
"learning_rate": 4.602074074074074e-06,
|
| 232 |
+
"loss": 0.1026,
|
| 233 |
+
"step": 13000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.311111111111111,
|
| 237 |
+
"eval_loss": 0.18057070672512054,
|
| 238 |
+
"eval_mae": 0.22670522332191467,
|
| 239 |
+
"eval_mse": 0.18057070672512054,
|
| 240 |
+
"eval_r2": 0.8297625184059143,
|
| 241 |
+
"eval_runtime": 4.7977,
|
| 242 |
+
"eval_samples_per_second": 2084.337,
|
| 243 |
+
"eval_steps_per_second": 130.271,
|
| 244 |
+
"step": 13000
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 2.488888888888889,
|
| 248 |
+
"grad_norm": 1.5936788320541382,
|
| 249 |
+
"learning_rate": 3.416888888888889e-06,
|
| 250 |
+
"loss": 0.0945,
|
| 251 |
+
"step": 14000
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 2.488888888888889,
|
| 255 |
+
"eval_loss": 0.18265259265899658,
|
| 256 |
+
"eval_mae": 0.2341051697731018,
|
| 257 |
+
"eval_mse": 0.1826525777578354,
|
| 258 |
+
"eval_r2": 0.8277997970581055,
|
| 259 |
+
"eval_runtime": 4.8018,
|
| 260 |
+
"eval_samples_per_second": 2082.558,
|
| 261 |
+
"eval_steps_per_second": 130.16,
|
| 262 |
+
"step": 14000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 2.6666666666666665,
|
| 266 |
+
"grad_norm": 3.25566029548645,
|
| 267 |
+
"learning_rate": 2.231703703703704e-06,
|
| 268 |
+
"loss": 0.0936,
|
| 269 |
+
"step": 15000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 2.6666666666666665,
|
| 273 |
+
"eval_loss": 0.17947633564472198,
|
| 274 |
+
"eval_mae": 0.22917917370796204,
|
| 275 |
+
"eval_mse": 0.17947635054588318,
|
| 276 |
+
"eval_r2": 0.8307942152023315,
|
| 277 |
+
"eval_runtime": 4.7983,
|
| 278 |
+
"eval_samples_per_second": 2084.067,
|
| 279 |
+
"eval_steps_per_second": 130.254,
|
| 280 |
+
"step": 15000
|
| 281 |
+
}
|
| 282 |
+
],
|
| 283 |
+
"logging_steps": 1000,
|
| 284 |
+
"max_steps": 16875,
|
| 285 |
+
"num_input_tokens_seen": 0,
|
| 286 |
+
"num_train_epochs": 3,
|
| 287 |
+
"save_steps": 1000,
|
| 288 |
+
"stateful_callbacks": {
|
| 289 |
+
"TrainerControl": {
|
| 290 |
+
"args": {
|
| 291 |
+
"should_epoch_stop": false,
|
| 292 |
+
"should_evaluate": false,
|
| 293 |
+
"should_log": false,
|
| 294 |
+
"should_save": true,
|
| 295 |
+
"should_training_stop": false
|
| 296 |
+
},
|
| 297 |
+
"attributes": {}
|
| 298 |
+
}
|
| 299 |
+
},
|
| 300 |
+
"total_flos": 3.157304315904e+16,
|
| 301 |
+
"train_batch_size": 16,
|
| 302 |
+
"trial_name": null,
|
| 303 |
+
"trial_params": null
|
| 304 |
+
}
|
checkpoint-15000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6469c1e7453b12240fa9e2fd1a405e4e80693b9eaca3e469d6d1c772991b8d9
|
| 3 |
+
size 5713
|
checkpoint-15000/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-16000/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"gradient_checkpointing": false,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0"
|
| 13 |
+
},
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"label2id": {
|
| 17 |
+
"LABEL_0": 0
|
| 18 |
+
},
|
| 19 |
+
"layer_norm_eps": 1e-12,
|
| 20 |
+
"max_position_embeddings": 512,
|
| 21 |
+
"model_type": "bert",
|
| 22 |
+
"num_attention_heads": 12,
|
| 23 |
+
"num_hidden_layers": 12,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"position_embedding_type": "absolute",
|
| 26 |
+
"problem_type": "regression",
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.52.4",
|
| 29 |
+
"type_vocab_size": 2,
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 30522
|
| 32 |
+
}
|
checkpoint-16000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe99acb5842fa7ed0f230e8f945ba11158de4d9ecb6607ce3893b8fb2045306b
|
| 3 |
+
size 437955572
|
checkpoint-16000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ae1e4ffd6da2c8fbbdf6c2c6264dae56dd9a07c0243196ce6cbf0bdb02e3af1
|
| 3 |
+
size 876032651
|
checkpoint-16000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da8b2ad650dd398b86ca7c49f1619d87988f0ebdf6ba15620897b77dc3576a29
|
| 3 |
+
size 14645
|
checkpoint-16000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65a9ad3dd7b1f9201efa05536e4fec5421fff2e47828bda7c1f32574e9c6333c
|
| 3 |
+
size 1383
|
checkpoint-16000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c60e69bcdcbeba673f8ad9d4c21e33eea31746a10560be4badce767f827b2fc
|
| 3 |
+
size 1465
|
checkpoint-16000/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 |
+
}
|
checkpoint-16000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-16000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "BertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
checkpoint-16000/trainer_state.json
ADDED
|
@@ -0,0 +1,322 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 15000,
|
| 3 |
+
"best_metric": 0.8307942152023315,
|
| 4 |
+
"best_model_checkpoint": "ActionBert2-109M/checkpoint-15000",
|
| 5 |
+
"epoch": 2.8444444444444446,
|
| 6 |
+
"eval_steps": 1000,
|
| 7 |
+
"global_step": 16000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.17777777777777778,
|
| 14 |
+
"grad_norm": 3.1670663356781006,
|
| 15 |
+
"learning_rate": 1.8821925925925927e-05,
|
| 16 |
+
"loss": 0.3813,
|
| 17 |
+
"step": 1000
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.17777777777777778,
|
| 21 |
+
"eval_loss": 0.2506166696548462,
|
| 22 |
+
"eval_mae": 0.3367820978164673,
|
| 23 |
+
"eval_mse": 0.2506166696548462,
|
| 24 |
+
"eval_r2": 0.7637249827384949,
|
| 25 |
+
"eval_runtime": 4.791,
|
| 26 |
+
"eval_samples_per_second": 2087.248,
|
| 27 |
+
"eval_steps_per_second": 130.453,
|
| 28 |
+
"step": 1000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.35555555555555557,
|
| 32 |
+
"grad_norm": 3.0615577697753906,
|
| 33 |
+
"learning_rate": 1.7636740740740744e-05,
|
| 34 |
+
"loss": 0.263,
|
| 35 |
+
"step": 2000
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.35555555555555557,
|
| 39 |
+
"eval_loss": 0.2408183068037033,
|
| 40 |
+
"eval_mae": 0.31582972407341003,
|
| 41 |
+
"eval_mse": 0.24081829190254211,
|
| 42 |
+
"eval_r2": 0.7729626297950745,
|
| 43 |
+
"eval_runtime": 4.7936,
|
| 44 |
+
"eval_samples_per_second": 2086.113,
|
| 45 |
+
"eval_steps_per_second": 130.382,
|
| 46 |
+
"step": 2000
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.5333333333333333,
|
| 50 |
+
"grad_norm": 11.606523513793945,
|
| 51 |
+
"learning_rate": 1.6451555555555554e-05,
|
| 52 |
+
"loss": 0.2506,
|
| 53 |
+
"step": 3000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.5333333333333333,
|
| 57 |
+
"eval_loss": 0.21803471446037292,
|
| 58 |
+
"eval_mae": 0.29080167412757874,
|
| 59 |
+
"eval_mse": 0.21803471446037292,
|
| 60 |
+
"eval_r2": 0.7944424152374268,
|
| 61 |
+
"eval_runtime": 4.7889,
|
| 62 |
+
"eval_samples_per_second": 2088.155,
|
| 63 |
+
"eval_steps_per_second": 130.51,
|
| 64 |
+
"step": 3000
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.7111111111111111,
|
| 68 |
+
"grad_norm": 13.706526756286621,
|
| 69 |
+
"learning_rate": 1.5266370370370372e-05,
|
| 70 |
+
"loss": 0.2414,
|
| 71 |
+
"step": 4000
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.7111111111111111,
|
| 75 |
+
"eval_loss": 0.20693176984786987,
|
| 76 |
+
"eval_mae": 0.2782182991504669,
|
| 77 |
+
"eval_mse": 0.20693176984786987,
|
| 78 |
+
"eval_r2": 0.8049100041389465,
|
| 79 |
+
"eval_runtime": 4.7925,
|
| 80 |
+
"eval_samples_per_second": 2086.596,
|
| 81 |
+
"eval_steps_per_second": 130.412,
|
| 82 |
+
"step": 4000
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.8888888888888888,
|
| 86 |
+
"grad_norm": 6.0101423263549805,
|
| 87 |
+
"learning_rate": 1.4081185185185186e-05,
|
| 88 |
+
"loss": 0.2295,
|
| 89 |
+
"step": 5000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.8888888888888888,
|
| 93 |
+
"eval_loss": 0.2030615508556366,
|
| 94 |
+
"eval_mae": 0.27224966883659363,
|
| 95 |
+
"eval_mse": 0.2030615508556366,
|
| 96 |
+
"eval_r2": 0.8085587024688721,
|
| 97 |
+
"eval_runtime": 4.7946,
|
| 98 |
+
"eval_samples_per_second": 2085.665,
|
| 99 |
+
"eval_steps_per_second": 130.354,
|
| 100 |
+
"step": 5000
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.0666666666666667,
|
| 104 |
+
"grad_norm": 7.812684059143066,
|
| 105 |
+
"learning_rate": 1.2896000000000002e-05,
|
| 106 |
+
"loss": 0.1969,
|
| 107 |
+
"step": 6000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.0666666666666667,
|
| 111 |
+
"eval_loss": 0.19701267778873444,
|
| 112 |
+
"eval_mae": 0.2610624134540558,
|
| 113 |
+
"eval_mse": 0.19701267778873444,
|
| 114 |
+
"eval_r2": 0.8142614364624023,
|
| 115 |
+
"eval_runtime": 4.7965,
|
| 116 |
+
"eval_samples_per_second": 2084.853,
|
| 117 |
+
"eval_steps_per_second": 130.303,
|
| 118 |
+
"step": 6000
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 1.2444444444444445,
|
| 122 |
+
"grad_norm": 4.992111682891846,
|
| 123 |
+
"learning_rate": 1.1710814814814816e-05,
|
| 124 |
+
"loss": 0.1495,
|
| 125 |
+
"step": 7000
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.2444444444444445,
|
| 129 |
+
"eval_loss": 0.1891198754310608,
|
| 130 |
+
"eval_mae": 0.24995234608650208,
|
| 131 |
+
"eval_mse": 0.1891198605298996,
|
| 132 |
+
"eval_r2": 0.8217025995254517,
|
| 133 |
+
"eval_runtime": 4.7971,
|
| 134 |
+
"eval_samples_per_second": 2084.602,
|
| 135 |
+
"eval_steps_per_second": 130.288,
|
| 136 |
+
"step": 7000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.4222222222222223,
|
| 140 |
+
"grad_norm": 4.602079391479492,
|
| 141 |
+
"learning_rate": 1.052562962962963e-05,
|
| 142 |
+
"loss": 0.1557,
|
| 143 |
+
"step": 8000
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.4222222222222223,
|
| 147 |
+
"eval_loss": 0.18423964083194733,
|
| 148 |
+
"eval_mae": 0.2460847944021225,
|
| 149 |
+
"eval_mse": 0.18423964083194733,
|
| 150 |
+
"eval_r2": 0.8263035416603088,
|
| 151 |
+
"eval_runtime": 4.7986,
|
| 152 |
+
"eval_samples_per_second": 2083.948,
|
| 153 |
+
"eval_steps_per_second": 130.247,
|
| 154 |
+
"step": 8000
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.6,
|
| 158 |
+
"grad_norm": 4.8106303215026855,
|
| 159 |
+
"learning_rate": 9.340444444444445e-06,
|
| 160 |
+
"loss": 0.1474,
|
| 161 |
+
"step": 9000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.6,
|
| 165 |
+
"eval_loss": 0.18420642614364624,
|
| 166 |
+
"eval_mae": 0.24716965854167938,
|
| 167 |
+
"eval_mse": 0.18420642614364624,
|
| 168 |
+
"eval_r2": 0.8263348340988159,
|
| 169 |
+
"eval_runtime": 4.7984,
|
| 170 |
+
"eval_samples_per_second": 2084.015,
|
| 171 |
+
"eval_steps_per_second": 130.251,
|
| 172 |
+
"step": 9000
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.7777777777777777,
|
| 176 |
+
"grad_norm": 8.563740730285645,
|
| 177 |
+
"learning_rate": 8.156444444444444e-06,
|
| 178 |
+
"loss": 0.1419,
|
| 179 |
+
"step": 10000
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.7777777777777777,
|
| 183 |
+
"eval_loss": 0.18527014553546906,
|
| 184 |
+
"eval_mae": 0.24834123253822327,
|
| 185 |
+
"eval_mse": 0.18527014553546906,
|
| 186 |
+
"eval_r2": 0.8253320455551147,
|
| 187 |
+
"eval_runtime": 4.7987,
|
| 188 |
+
"eval_samples_per_second": 2083.902,
|
| 189 |
+
"eval_steps_per_second": 130.244,
|
| 190 |
+
"step": 10000
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.9555555555555557,
|
| 194 |
+
"grad_norm": 7.638633728027344,
|
| 195 |
+
"learning_rate": 6.97125925925926e-06,
|
| 196 |
+
"loss": 0.1513,
|
| 197 |
+
"step": 11000
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.9555555555555557,
|
| 201 |
+
"eval_loss": 0.19055569171905518,
|
| 202 |
+
"eval_mae": 0.2580980956554413,
|
| 203 |
+
"eval_mse": 0.19055569171905518,
|
| 204 |
+
"eval_r2": 0.8203489184379578,
|
| 205 |
+
"eval_runtime": 4.7998,
|
| 206 |
+
"eval_samples_per_second": 2083.401,
|
| 207 |
+
"eval_steps_per_second": 130.213,
|
| 208 |
+
"step": 11000
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 2.1333333333333333,
|
| 212 |
+
"grad_norm": 4.0671234130859375,
|
| 213 |
+
"learning_rate": 5.78725925925926e-06,
|
| 214 |
+
"loss": 0.1108,
|
| 215 |
+
"step": 12000
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 2.1333333333333333,
|
| 219 |
+
"eval_loss": 0.1817326694726944,
|
| 220 |
+
"eval_mae": 0.23058335483074188,
|
| 221 |
+
"eval_mse": 0.1817326694726944,
|
| 222 |
+
"eval_r2": 0.8286670446395874,
|
| 223 |
+
"eval_runtime": 4.8008,
|
| 224 |
+
"eval_samples_per_second": 2082.976,
|
| 225 |
+
"eval_steps_per_second": 130.186,
|
| 226 |
+
"step": 12000
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 2.311111111111111,
|
| 230 |
+
"grad_norm": 5.488609790802002,
|
| 231 |
+
"learning_rate": 4.602074074074074e-06,
|
| 232 |
+
"loss": 0.1026,
|
| 233 |
+
"step": 13000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.311111111111111,
|
| 237 |
+
"eval_loss": 0.18057070672512054,
|
| 238 |
+
"eval_mae": 0.22670522332191467,
|
| 239 |
+
"eval_mse": 0.18057070672512054,
|
| 240 |
+
"eval_r2": 0.8297625184059143,
|
| 241 |
+
"eval_runtime": 4.7977,
|
| 242 |
+
"eval_samples_per_second": 2084.337,
|
| 243 |
+
"eval_steps_per_second": 130.271,
|
| 244 |
+
"step": 13000
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 2.488888888888889,
|
| 248 |
+
"grad_norm": 1.5936788320541382,
|
| 249 |
+
"learning_rate": 3.416888888888889e-06,
|
| 250 |
+
"loss": 0.0945,
|
| 251 |
+
"step": 14000
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 2.488888888888889,
|
| 255 |
+
"eval_loss": 0.18265259265899658,
|
| 256 |
+
"eval_mae": 0.2341051697731018,
|
| 257 |
+
"eval_mse": 0.1826525777578354,
|
| 258 |
+
"eval_r2": 0.8277997970581055,
|
| 259 |
+
"eval_runtime": 4.8018,
|
| 260 |
+
"eval_samples_per_second": 2082.558,
|
| 261 |
+
"eval_steps_per_second": 130.16,
|
| 262 |
+
"step": 14000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 2.6666666666666665,
|
| 266 |
+
"grad_norm": 3.25566029548645,
|
| 267 |
+
"learning_rate": 2.231703703703704e-06,
|
| 268 |
+
"loss": 0.0936,
|
| 269 |
+
"step": 15000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 2.6666666666666665,
|
| 273 |
+
"eval_loss": 0.17947633564472198,
|
| 274 |
+
"eval_mae": 0.22917917370796204,
|
| 275 |
+
"eval_mse": 0.17947635054588318,
|
| 276 |
+
"eval_r2": 0.8307942152023315,
|
| 277 |
+
"eval_runtime": 4.7983,
|
| 278 |
+
"eval_samples_per_second": 2084.067,
|
| 279 |
+
"eval_steps_per_second": 130.254,
|
| 280 |
+
"step": 15000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 2.8444444444444446,
|
| 284 |
+
"grad_norm": 2.2979111671447754,
|
| 285 |
+
"learning_rate": 1.0477037037037039e-06,
|
| 286 |
+
"loss": 0.0978,
|
| 287 |
+
"step": 16000
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 2.8444444444444446,
|
| 291 |
+
"eval_loss": 0.1797763854265213,
|
| 292 |
+
"eval_mae": 0.2279701679944992,
|
| 293 |
+
"eval_mse": 0.1797763854265213,
|
| 294 |
+
"eval_r2": 0.8305113911628723,
|
| 295 |
+
"eval_runtime": 4.8025,
|
| 296 |
+
"eval_samples_per_second": 2082.257,
|
| 297 |
+
"eval_steps_per_second": 130.141,
|
| 298 |
+
"step": 16000
|
| 299 |
+
}
|
| 300 |
+
],
|
| 301 |
+
"logging_steps": 1000,
|
| 302 |
+
"max_steps": 16875,
|
| 303 |
+
"num_input_tokens_seen": 0,
|
| 304 |
+
"num_train_epochs": 3,
|
| 305 |
+
"save_steps": 1000,
|
| 306 |
+
"stateful_callbacks": {
|
| 307 |
+
"TrainerControl": {
|
| 308 |
+
"args": {
|
| 309 |
+
"should_epoch_stop": false,
|
| 310 |
+
"should_evaluate": false,
|
| 311 |
+
"should_log": false,
|
| 312 |
+
"should_save": true,
|
| 313 |
+
"should_training_stop": false
|
| 314 |
+
},
|
| 315 |
+
"attributes": {}
|
| 316 |
+
}
|
| 317 |
+
},
|
| 318 |
+
"total_flos": 3.3677912702976e+16,
|
| 319 |
+
"train_batch_size": 16,
|
| 320 |
+
"trial_name": null,
|
| 321 |
+
"trial_params": null
|
| 322 |
+
}
|
checkpoint-16000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6469c1e7453b12240fa9e2fd1a405e4e80693b9eaca3e469d6d1c772991b8d9
|
| 3 |
+
size 5713
|
checkpoint-16000/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-16875/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"gradient_checkpointing": false,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0"
|
| 13 |
+
},
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"label2id": {
|
| 17 |
+
"LABEL_0": 0
|
| 18 |
+
},
|
| 19 |
+
"layer_norm_eps": 1e-12,
|
| 20 |
+
"max_position_embeddings": 512,
|
| 21 |
+
"model_type": "bert",
|
| 22 |
+
"num_attention_heads": 12,
|
| 23 |
+
"num_hidden_layers": 12,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"position_embedding_type": "absolute",
|
| 26 |
+
"problem_type": "regression",
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.52.4",
|
| 29 |
+
"type_vocab_size": 2,
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 30522
|
| 32 |
+
}
|
checkpoint-16875/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f418bc288e566c45cb57fc95d12a663fe2598c29f866b80e04fd015a472c8342
|
| 3 |
+
size 437955572
|
checkpoint-16875/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b0c5380e6267bc9fe75085fbf650e72b4aa6bc8a5f03fc5af4f016862c91bf8
|
| 3 |
+
size 876032651
|
checkpoint-16875/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:295ff34c4215874c2e30c50aa545b99a399fe5b10b4c54ff8fc1c36c367e259a
|
| 3 |
+
size 14645
|
checkpoint-16875/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de0991df256d89e227d907e72cc749a8b09dcbf3ce19de1d2412987ca834e3d2
|
| 3 |
+
size 1383
|
checkpoint-16875/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d37c4c84255e807fff277ba8083294a0380189f76b5bb5b226cf6e17fbf9b8f
|
| 3 |
+
size 1465
|
checkpoint-16875/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 |
+
}
|
checkpoint-16875/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-16875/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "BertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
checkpoint-16875/trainer_state.json
ADDED
|
@@ -0,0 +1,322 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 15000,
|
| 3 |
+
"best_metric": 0.8307942152023315,
|
| 4 |
+
"best_model_checkpoint": "ActionBert2-109M/checkpoint-15000",
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 1000,
|
| 7 |
+
"global_step": 16875,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.17777777777777778,
|
| 14 |
+
"grad_norm": 3.1670663356781006,
|
| 15 |
+
"learning_rate": 1.8821925925925927e-05,
|
| 16 |
+
"loss": 0.3813,
|
| 17 |
+
"step": 1000
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.17777777777777778,
|
| 21 |
+
"eval_loss": 0.2506166696548462,
|
| 22 |
+
"eval_mae": 0.3367820978164673,
|
| 23 |
+
"eval_mse": 0.2506166696548462,
|
| 24 |
+
"eval_r2": 0.7637249827384949,
|
| 25 |
+
"eval_runtime": 4.791,
|
| 26 |
+
"eval_samples_per_second": 2087.248,
|
| 27 |
+
"eval_steps_per_second": 130.453,
|
| 28 |
+
"step": 1000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.35555555555555557,
|
| 32 |
+
"grad_norm": 3.0615577697753906,
|
| 33 |
+
"learning_rate": 1.7636740740740744e-05,
|
| 34 |
+
"loss": 0.263,
|
| 35 |
+
"step": 2000
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.35555555555555557,
|
| 39 |
+
"eval_loss": 0.2408183068037033,
|
| 40 |
+
"eval_mae": 0.31582972407341003,
|
| 41 |
+
"eval_mse": 0.24081829190254211,
|
| 42 |
+
"eval_r2": 0.7729626297950745,
|
| 43 |
+
"eval_runtime": 4.7936,
|
| 44 |
+
"eval_samples_per_second": 2086.113,
|
| 45 |
+
"eval_steps_per_second": 130.382,
|
| 46 |
+
"step": 2000
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.5333333333333333,
|
| 50 |
+
"grad_norm": 11.606523513793945,
|
| 51 |
+
"learning_rate": 1.6451555555555554e-05,
|
| 52 |
+
"loss": 0.2506,
|
| 53 |
+
"step": 3000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.5333333333333333,
|
| 57 |
+
"eval_loss": 0.21803471446037292,
|
| 58 |
+
"eval_mae": 0.29080167412757874,
|
| 59 |
+
"eval_mse": 0.21803471446037292,
|
| 60 |
+
"eval_r2": 0.7944424152374268,
|
| 61 |
+
"eval_runtime": 4.7889,
|
| 62 |
+
"eval_samples_per_second": 2088.155,
|
| 63 |
+
"eval_steps_per_second": 130.51,
|
| 64 |
+
"step": 3000
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.7111111111111111,
|
| 68 |
+
"grad_norm": 13.706526756286621,
|
| 69 |
+
"learning_rate": 1.5266370370370372e-05,
|
| 70 |
+
"loss": 0.2414,
|
| 71 |
+
"step": 4000
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.7111111111111111,
|
| 75 |
+
"eval_loss": 0.20693176984786987,
|
| 76 |
+
"eval_mae": 0.2782182991504669,
|
| 77 |
+
"eval_mse": 0.20693176984786987,
|
| 78 |
+
"eval_r2": 0.8049100041389465,
|
| 79 |
+
"eval_runtime": 4.7925,
|
| 80 |
+
"eval_samples_per_second": 2086.596,
|
| 81 |
+
"eval_steps_per_second": 130.412,
|
| 82 |
+
"step": 4000
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.8888888888888888,
|
| 86 |
+
"grad_norm": 6.0101423263549805,
|
| 87 |
+
"learning_rate": 1.4081185185185186e-05,
|
| 88 |
+
"loss": 0.2295,
|
| 89 |
+
"step": 5000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.8888888888888888,
|
| 93 |
+
"eval_loss": 0.2030615508556366,
|
| 94 |
+
"eval_mae": 0.27224966883659363,
|
| 95 |
+
"eval_mse": 0.2030615508556366,
|
| 96 |
+
"eval_r2": 0.8085587024688721,
|
| 97 |
+
"eval_runtime": 4.7946,
|
| 98 |
+
"eval_samples_per_second": 2085.665,
|
| 99 |
+
"eval_steps_per_second": 130.354,
|
| 100 |
+
"step": 5000
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.0666666666666667,
|
| 104 |
+
"grad_norm": 7.812684059143066,
|
| 105 |
+
"learning_rate": 1.2896000000000002e-05,
|
| 106 |
+
"loss": 0.1969,
|
| 107 |
+
"step": 6000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.0666666666666667,
|
| 111 |
+
"eval_loss": 0.19701267778873444,
|
| 112 |
+
"eval_mae": 0.2610624134540558,
|
| 113 |
+
"eval_mse": 0.19701267778873444,
|
| 114 |
+
"eval_r2": 0.8142614364624023,
|
| 115 |
+
"eval_runtime": 4.7965,
|
| 116 |
+
"eval_samples_per_second": 2084.853,
|
| 117 |
+
"eval_steps_per_second": 130.303,
|
| 118 |
+
"step": 6000
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 1.2444444444444445,
|
| 122 |
+
"grad_norm": 4.992111682891846,
|
| 123 |
+
"learning_rate": 1.1710814814814816e-05,
|
| 124 |
+
"loss": 0.1495,
|
| 125 |
+
"step": 7000
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.2444444444444445,
|
| 129 |
+
"eval_loss": 0.1891198754310608,
|
| 130 |
+
"eval_mae": 0.24995234608650208,
|
| 131 |
+
"eval_mse": 0.1891198605298996,
|
| 132 |
+
"eval_r2": 0.8217025995254517,
|
| 133 |
+
"eval_runtime": 4.7971,
|
| 134 |
+
"eval_samples_per_second": 2084.602,
|
| 135 |
+
"eval_steps_per_second": 130.288,
|
| 136 |
+
"step": 7000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.4222222222222223,
|
| 140 |
+
"grad_norm": 4.602079391479492,
|
| 141 |
+
"learning_rate": 1.052562962962963e-05,
|
| 142 |
+
"loss": 0.1557,
|
| 143 |
+
"step": 8000
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.4222222222222223,
|
| 147 |
+
"eval_loss": 0.18423964083194733,
|
| 148 |
+
"eval_mae": 0.2460847944021225,
|
| 149 |
+
"eval_mse": 0.18423964083194733,
|
| 150 |
+
"eval_r2": 0.8263035416603088,
|
| 151 |
+
"eval_runtime": 4.7986,
|
| 152 |
+
"eval_samples_per_second": 2083.948,
|
| 153 |
+
"eval_steps_per_second": 130.247,
|
| 154 |
+
"step": 8000
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.6,
|
| 158 |
+
"grad_norm": 4.8106303215026855,
|
| 159 |
+
"learning_rate": 9.340444444444445e-06,
|
| 160 |
+
"loss": 0.1474,
|
| 161 |
+
"step": 9000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.6,
|
| 165 |
+
"eval_loss": 0.18420642614364624,
|
| 166 |
+
"eval_mae": 0.24716965854167938,
|
| 167 |
+
"eval_mse": 0.18420642614364624,
|
| 168 |
+
"eval_r2": 0.8263348340988159,
|
| 169 |
+
"eval_runtime": 4.7984,
|
| 170 |
+
"eval_samples_per_second": 2084.015,
|
| 171 |
+
"eval_steps_per_second": 130.251,
|
| 172 |
+
"step": 9000
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.7777777777777777,
|
| 176 |
+
"grad_norm": 8.563740730285645,
|
| 177 |
+
"learning_rate": 8.156444444444444e-06,
|
| 178 |
+
"loss": 0.1419,
|
| 179 |
+
"step": 10000
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.7777777777777777,
|
| 183 |
+
"eval_loss": 0.18527014553546906,
|
| 184 |
+
"eval_mae": 0.24834123253822327,
|
| 185 |
+
"eval_mse": 0.18527014553546906,
|
| 186 |
+
"eval_r2": 0.8253320455551147,
|
| 187 |
+
"eval_runtime": 4.7987,
|
| 188 |
+
"eval_samples_per_second": 2083.902,
|
| 189 |
+
"eval_steps_per_second": 130.244,
|
| 190 |
+
"step": 10000
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.9555555555555557,
|
| 194 |
+
"grad_norm": 7.638633728027344,
|
| 195 |
+
"learning_rate": 6.97125925925926e-06,
|
| 196 |
+
"loss": 0.1513,
|
| 197 |
+
"step": 11000
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.9555555555555557,
|
| 201 |
+
"eval_loss": 0.19055569171905518,
|
| 202 |
+
"eval_mae": 0.2580980956554413,
|
| 203 |
+
"eval_mse": 0.19055569171905518,
|
| 204 |
+
"eval_r2": 0.8203489184379578,
|
| 205 |
+
"eval_runtime": 4.7998,
|
| 206 |
+
"eval_samples_per_second": 2083.401,
|
| 207 |
+
"eval_steps_per_second": 130.213,
|
| 208 |
+
"step": 11000
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 2.1333333333333333,
|
| 212 |
+
"grad_norm": 4.0671234130859375,
|
| 213 |
+
"learning_rate": 5.78725925925926e-06,
|
| 214 |
+
"loss": 0.1108,
|
| 215 |
+
"step": 12000
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 2.1333333333333333,
|
| 219 |
+
"eval_loss": 0.1817326694726944,
|
| 220 |
+
"eval_mae": 0.23058335483074188,
|
| 221 |
+
"eval_mse": 0.1817326694726944,
|
| 222 |
+
"eval_r2": 0.8286670446395874,
|
| 223 |
+
"eval_runtime": 4.8008,
|
| 224 |
+
"eval_samples_per_second": 2082.976,
|
| 225 |
+
"eval_steps_per_second": 130.186,
|
| 226 |
+
"step": 12000
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 2.311111111111111,
|
| 230 |
+
"grad_norm": 5.488609790802002,
|
| 231 |
+
"learning_rate": 4.602074074074074e-06,
|
| 232 |
+
"loss": 0.1026,
|
| 233 |
+
"step": 13000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.311111111111111,
|
| 237 |
+
"eval_loss": 0.18057070672512054,
|
| 238 |
+
"eval_mae": 0.22670522332191467,
|
| 239 |
+
"eval_mse": 0.18057070672512054,
|
| 240 |
+
"eval_r2": 0.8297625184059143,
|
| 241 |
+
"eval_runtime": 4.7977,
|
| 242 |
+
"eval_samples_per_second": 2084.337,
|
| 243 |
+
"eval_steps_per_second": 130.271,
|
| 244 |
+
"step": 13000
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 2.488888888888889,
|
| 248 |
+
"grad_norm": 1.5936788320541382,
|
| 249 |
+
"learning_rate": 3.416888888888889e-06,
|
| 250 |
+
"loss": 0.0945,
|
| 251 |
+
"step": 14000
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 2.488888888888889,
|
| 255 |
+
"eval_loss": 0.18265259265899658,
|
| 256 |
+
"eval_mae": 0.2341051697731018,
|
| 257 |
+
"eval_mse": 0.1826525777578354,
|
| 258 |
+
"eval_r2": 0.8277997970581055,
|
| 259 |
+
"eval_runtime": 4.8018,
|
| 260 |
+
"eval_samples_per_second": 2082.558,
|
| 261 |
+
"eval_steps_per_second": 130.16,
|
| 262 |
+
"step": 14000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 2.6666666666666665,
|
| 266 |
+
"grad_norm": 3.25566029548645,
|
| 267 |
+
"learning_rate": 2.231703703703704e-06,
|
| 268 |
+
"loss": 0.0936,
|
| 269 |
+
"step": 15000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 2.6666666666666665,
|
| 273 |
+
"eval_loss": 0.17947633564472198,
|
| 274 |
+
"eval_mae": 0.22917917370796204,
|
| 275 |
+
"eval_mse": 0.17947635054588318,
|
| 276 |
+
"eval_r2": 0.8307942152023315,
|
| 277 |
+
"eval_runtime": 4.7983,
|
| 278 |
+
"eval_samples_per_second": 2084.067,
|
| 279 |
+
"eval_steps_per_second": 130.254,
|
| 280 |
+
"step": 15000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 2.8444444444444446,
|
| 284 |
+
"grad_norm": 2.2979111671447754,
|
| 285 |
+
"learning_rate": 1.0477037037037039e-06,
|
| 286 |
+
"loss": 0.0978,
|
| 287 |
+
"step": 16000
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 2.8444444444444446,
|
| 291 |
+
"eval_loss": 0.1797763854265213,
|
| 292 |
+
"eval_mae": 0.2279701679944992,
|
| 293 |
+
"eval_mse": 0.1797763854265213,
|
| 294 |
+
"eval_r2": 0.8305113911628723,
|
| 295 |
+
"eval_runtime": 4.8025,
|
| 296 |
+
"eval_samples_per_second": 2082.257,
|
| 297 |
+
"eval_steps_per_second": 130.141,
|
| 298 |
+
"step": 16000
|
| 299 |
+
}
|
| 300 |
+
],
|
| 301 |
+
"logging_steps": 1000,
|
| 302 |
+
"max_steps": 16875,
|
| 303 |
+
"num_input_tokens_seen": 0,
|
| 304 |
+
"num_train_epochs": 3,
|
| 305 |
+
"save_steps": 1000,
|
| 306 |
+
"stateful_callbacks": {
|
| 307 |
+
"TrainerControl": {
|
| 308 |
+
"args": {
|
| 309 |
+
"should_epoch_stop": false,
|
| 310 |
+
"should_evaluate": false,
|
| 311 |
+
"should_log": false,
|
| 312 |
+
"should_save": true,
|
| 313 |
+
"should_training_stop": true
|
| 314 |
+
},
|
| 315 |
+
"attributes": {}
|
| 316 |
+
}
|
| 317 |
+
},
|
| 318 |
+
"total_flos": 3.551967355392e+16,
|
| 319 |
+
"train_batch_size": 16,
|
| 320 |
+
"trial_name": null,
|
| 321 |
+
"trial_params": null
|
| 322 |
+
}
|
checkpoint-16875/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6469c1e7453b12240fa9e2fd1a405e4e80693b9eaca3e469d6d1c772991b8d9
|
| 3 |
+
size 5713
|
checkpoint-16875/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"gradient_checkpointing": false,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0"
|
| 13 |
+
},
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"label2id": {
|
| 17 |
+
"LABEL_0": 0
|
| 18 |
+
},
|
| 19 |
+
"layer_norm_eps": 1e-12,
|
| 20 |
+
"max_position_embeddings": 512,
|
| 21 |
+
"model_type": "bert",
|
| 22 |
+
"num_attention_heads": 12,
|
| 23 |
+
"num_hidden_layers": 12,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"position_embedding_type": "absolute",
|
| 26 |
+
"problem_type": "regression",
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.52.4",
|
| 29 |
+
"type_vocab_size": 2,
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 30522
|
| 32 |
+
}
|
eval_final_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.17947633564472198,
|
| 4 |
+
"eval_mae": 0.22917917370796204,
|
| 5 |
+
"eval_mse": 0.17947635054588318,
|
| 6 |
+
"eval_r2": 0.8307942152023315,
|
| 7 |
+
"eval_runtime": 4.7945,
|
| 8 |
+
"eval_samples_per_second": 2085.702,
|
| 9 |
+
"eval_steps_per_second": 130.356
|
| 10 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4400857bfafecd279d1b46340c644ceba22112716bef0016a9d503cad17c35e1
|
| 3 |
+
size 437955572
|
runs/Jun28_05-39-58_eagle/events.out.tfevents.1751089199.eagle.2176823.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:594ecdfa9d77e76c6da3f64f548a0d72d00f785b6b2d189cbb817f7f1a401f19
|
| 3 |
+
size 15278
|
runs/Jun28_05-39-58_eagle/events.out.tfevents.1751089814.eagle.2176823.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:764f7072447db1976369ccd0c0d5d20d04a04ee4456bdc901cc465d159b04d60
|
| 3 |
+
size 507
|
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 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "BertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 3.551967355392e+16,
|
| 4 |
+
"train_loss": 0.17141379213686342,
|
| 5 |
+
"train_runtime": 610.1774,
|
| 6 |
+
"train_samples_per_second": 442.494,
|
| 7 |
+
"train_steps_per_second": 27.656
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,331 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 15000,
|
| 3 |
+
"best_metric": 0.8307942152023315,
|
| 4 |
+
"best_model_checkpoint": "ActionBert2-109M/checkpoint-15000",
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 1000,
|
| 7 |
+
"global_step": 16875,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.17777777777777778,
|
| 14 |
+
"grad_norm": 3.1670663356781006,
|
| 15 |
+
"learning_rate": 1.8821925925925927e-05,
|
| 16 |
+
"loss": 0.3813,
|
| 17 |
+
"step": 1000
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.17777777777777778,
|
| 21 |
+
"eval_loss": 0.2506166696548462,
|
| 22 |
+
"eval_mae": 0.3367820978164673,
|
| 23 |
+
"eval_mse": 0.2506166696548462,
|
| 24 |
+
"eval_r2": 0.7637249827384949,
|
| 25 |
+
"eval_runtime": 4.791,
|
| 26 |
+
"eval_samples_per_second": 2087.248,
|
| 27 |
+
"eval_steps_per_second": 130.453,
|
| 28 |
+
"step": 1000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.35555555555555557,
|
| 32 |
+
"grad_norm": 3.0615577697753906,
|
| 33 |
+
"learning_rate": 1.7636740740740744e-05,
|
| 34 |
+
"loss": 0.263,
|
| 35 |
+
"step": 2000
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.35555555555555557,
|
| 39 |
+
"eval_loss": 0.2408183068037033,
|
| 40 |
+
"eval_mae": 0.31582972407341003,
|
| 41 |
+
"eval_mse": 0.24081829190254211,
|
| 42 |
+
"eval_r2": 0.7729626297950745,
|
| 43 |
+
"eval_runtime": 4.7936,
|
| 44 |
+
"eval_samples_per_second": 2086.113,
|
| 45 |
+
"eval_steps_per_second": 130.382,
|
| 46 |
+
"step": 2000
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.5333333333333333,
|
| 50 |
+
"grad_norm": 11.606523513793945,
|
| 51 |
+
"learning_rate": 1.6451555555555554e-05,
|
| 52 |
+
"loss": 0.2506,
|
| 53 |
+
"step": 3000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.5333333333333333,
|
| 57 |
+
"eval_loss": 0.21803471446037292,
|
| 58 |
+
"eval_mae": 0.29080167412757874,
|
| 59 |
+
"eval_mse": 0.21803471446037292,
|
| 60 |
+
"eval_r2": 0.7944424152374268,
|
| 61 |
+
"eval_runtime": 4.7889,
|
| 62 |
+
"eval_samples_per_second": 2088.155,
|
| 63 |
+
"eval_steps_per_second": 130.51,
|
| 64 |
+
"step": 3000
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.7111111111111111,
|
| 68 |
+
"grad_norm": 13.706526756286621,
|
| 69 |
+
"learning_rate": 1.5266370370370372e-05,
|
| 70 |
+
"loss": 0.2414,
|
| 71 |
+
"step": 4000
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.7111111111111111,
|
| 75 |
+
"eval_loss": 0.20693176984786987,
|
| 76 |
+
"eval_mae": 0.2782182991504669,
|
| 77 |
+
"eval_mse": 0.20693176984786987,
|
| 78 |
+
"eval_r2": 0.8049100041389465,
|
| 79 |
+
"eval_runtime": 4.7925,
|
| 80 |
+
"eval_samples_per_second": 2086.596,
|
| 81 |
+
"eval_steps_per_second": 130.412,
|
| 82 |
+
"step": 4000
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.8888888888888888,
|
| 86 |
+
"grad_norm": 6.0101423263549805,
|
| 87 |
+
"learning_rate": 1.4081185185185186e-05,
|
| 88 |
+
"loss": 0.2295,
|
| 89 |
+
"step": 5000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.8888888888888888,
|
| 93 |
+
"eval_loss": 0.2030615508556366,
|
| 94 |
+
"eval_mae": 0.27224966883659363,
|
| 95 |
+
"eval_mse": 0.2030615508556366,
|
| 96 |
+
"eval_r2": 0.8085587024688721,
|
| 97 |
+
"eval_runtime": 4.7946,
|
| 98 |
+
"eval_samples_per_second": 2085.665,
|
| 99 |
+
"eval_steps_per_second": 130.354,
|
| 100 |
+
"step": 5000
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.0666666666666667,
|
| 104 |
+
"grad_norm": 7.812684059143066,
|
| 105 |
+
"learning_rate": 1.2896000000000002e-05,
|
| 106 |
+
"loss": 0.1969,
|
| 107 |
+
"step": 6000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.0666666666666667,
|
| 111 |
+
"eval_loss": 0.19701267778873444,
|
| 112 |
+
"eval_mae": 0.2610624134540558,
|
| 113 |
+
"eval_mse": 0.19701267778873444,
|
| 114 |
+
"eval_r2": 0.8142614364624023,
|
| 115 |
+
"eval_runtime": 4.7965,
|
| 116 |
+
"eval_samples_per_second": 2084.853,
|
| 117 |
+
"eval_steps_per_second": 130.303,
|
| 118 |
+
"step": 6000
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 1.2444444444444445,
|
| 122 |
+
"grad_norm": 4.992111682891846,
|
| 123 |
+
"learning_rate": 1.1710814814814816e-05,
|
| 124 |
+
"loss": 0.1495,
|
| 125 |
+
"step": 7000
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.2444444444444445,
|
| 129 |
+
"eval_loss": 0.1891198754310608,
|
| 130 |
+
"eval_mae": 0.24995234608650208,
|
| 131 |
+
"eval_mse": 0.1891198605298996,
|
| 132 |
+
"eval_r2": 0.8217025995254517,
|
| 133 |
+
"eval_runtime": 4.7971,
|
| 134 |
+
"eval_samples_per_second": 2084.602,
|
| 135 |
+
"eval_steps_per_second": 130.288,
|
| 136 |
+
"step": 7000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.4222222222222223,
|
| 140 |
+
"grad_norm": 4.602079391479492,
|
| 141 |
+
"learning_rate": 1.052562962962963e-05,
|
| 142 |
+
"loss": 0.1557,
|
| 143 |
+
"step": 8000
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.4222222222222223,
|
| 147 |
+
"eval_loss": 0.18423964083194733,
|
| 148 |
+
"eval_mae": 0.2460847944021225,
|
| 149 |
+
"eval_mse": 0.18423964083194733,
|
| 150 |
+
"eval_r2": 0.8263035416603088,
|
| 151 |
+
"eval_runtime": 4.7986,
|
| 152 |
+
"eval_samples_per_second": 2083.948,
|
| 153 |
+
"eval_steps_per_second": 130.247,
|
| 154 |
+
"step": 8000
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.6,
|
| 158 |
+
"grad_norm": 4.8106303215026855,
|
| 159 |
+
"learning_rate": 9.340444444444445e-06,
|
| 160 |
+
"loss": 0.1474,
|
| 161 |
+
"step": 9000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.6,
|
| 165 |
+
"eval_loss": 0.18420642614364624,
|
| 166 |
+
"eval_mae": 0.24716965854167938,
|
| 167 |
+
"eval_mse": 0.18420642614364624,
|
| 168 |
+
"eval_r2": 0.8263348340988159,
|
| 169 |
+
"eval_runtime": 4.7984,
|
| 170 |
+
"eval_samples_per_second": 2084.015,
|
| 171 |
+
"eval_steps_per_second": 130.251,
|
| 172 |
+
"step": 9000
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.7777777777777777,
|
| 176 |
+
"grad_norm": 8.563740730285645,
|
| 177 |
+
"learning_rate": 8.156444444444444e-06,
|
| 178 |
+
"loss": 0.1419,
|
| 179 |
+
"step": 10000
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.7777777777777777,
|
| 183 |
+
"eval_loss": 0.18527014553546906,
|
| 184 |
+
"eval_mae": 0.24834123253822327,
|
| 185 |
+
"eval_mse": 0.18527014553546906,
|
| 186 |
+
"eval_r2": 0.8253320455551147,
|
| 187 |
+
"eval_runtime": 4.7987,
|
| 188 |
+
"eval_samples_per_second": 2083.902,
|
| 189 |
+
"eval_steps_per_second": 130.244,
|
| 190 |
+
"step": 10000
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.9555555555555557,
|
| 194 |
+
"grad_norm": 7.638633728027344,
|
| 195 |
+
"learning_rate": 6.97125925925926e-06,
|
| 196 |
+
"loss": 0.1513,
|
| 197 |
+
"step": 11000
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.9555555555555557,
|
| 201 |
+
"eval_loss": 0.19055569171905518,
|
| 202 |
+
"eval_mae": 0.2580980956554413,
|
| 203 |
+
"eval_mse": 0.19055569171905518,
|
| 204 |
+
"eval_r2": 0.8203489184379578,
|
| 205 |
+
"eval_runtime": 4.7998,
|
| 206 |
+
"eval_samples_per_second": 2083.401,
|
| 207 |
+
"eval_steps_per_second": 130.213,
|
| 208 |
+
"step": 11000
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 2.1333333333333333,
|
| 212 |
+
"grad_norm": 4.0671234130859375,
|
| 213 |
+
"learning_rate": 5.78725925925926e-06,
|
| 214 |
+
"loss": 0.1108,
|
| 215 |
+
"step": 12000
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 2.1333333333333333,
|
| 219 |
+
"eval_loss": 0.1817326694726944,
|
| 220 |
+
"eval_mae": 0.23058335483074188,
|
| 221 |
+
"eval_mse": 0.1817326694726944,
|
| 222 |
+
"eval_r2": 0.8286670446395874,
|
| 223 |
+
"eval_runtime": 4.8008,
|
| 224 |
+
"eval_samples_per_second": 2082.976,
|
| 225 |
+
"eval_steps_per_second": 130.186,
|
| 226 |
+
"step": 12000
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 2.311111111111111,
|
| 230 |
+
"grad_norm": 5.488609790802002,
|
| 231 |
+
"learning_rate": 4.602074074074074e-06,
|
| 232 |
+
"loss": 0.1026,
|
| 233 |
+
"step": 13000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.311111111111111,
|
| 237 |
+
"eval_loss": 0.18057070672512054,
|
| 238 |
+
"eval_mae": 0.22670522332191467,
|
| 239 |
+
"eval_mse": 0.18057070672512054,
|
| 240 |
+
"eval_r2": 0.8297625184059143,
|
| 241 |
+
"eval_runtime": 4.7977,
|
| 242 |
+
"eval_samples_per_second": 2084.337,
|
| 243 |
+
"eval_steps_per_second": 130.271,
|
| 244 |
+
"step": 13000
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 2.488888888888889,
|
| 248 |
+
"grad_norm": 1.5936788320541382,
|
| 249 |
+
"learning_rate": 3.416888888888889e-06,
|
| 250 |
+
"loss": 0.0945,
|
| 251 |
+
"step": 14000
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 2.488888888888889,
|
| 255 |
+
"eval_loss": 0.18265259265899658,
|
| 256 |
+
"eval_mae": 0.2341051697731018,
|
| 257 |
+
"eval_mse": 0.1826525777578354,
|
| 258 |
+
"eval_r2": 0.8277997970581055,
|
| 259 |
+
"eval_runtime": 4.8018,
|
| 260 |
+
"eval_samples_per_second": 2082.558,
|
| 261 |
+
"eval_steps_per_second": 130.16,
|
| 262 |
+
"step": 14000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 2.6666666666666665,
|
| 266 |
+
"grad_norm": 3.25566029548645,
|
| 267 |
+
"learning_rate": 2.231703703703704e-06,
|
| 268 |
+
"loss": 0.0936,
|
| 269 |
+
"step": 15000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 2.6666666666666665,
|
| 273 |
+
"eval_loss": 0.17947633564472198,
|
| 274 |
+
"eval_mae": 0.22917917370796204,
|
| 275 |
+
"eval_mse": 0.17947635054588318,
|
| 276 |
+
"eval_r2": 0.8307942152023315,
|
| 277 |
+
"eval_runtime": 4.7983,
|
| 278 |
+
"eval_samples_per_second": 2084.067,
|
| 279 |
+
"eval_steps_per_second": 130.254,
|
| 280 |
+
"step": 15000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 2.8444444444444446,
|
| 284 |
+
"grad_norm": 2.2979111671447754,
|
| 285 |
+
"learning_rate": 1.0477037037037039e-06,
|
| 286 |
+
"loss": 0.0978,
|
| 287 |
+
"step": 16000
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 2.8444444444444446,
|
| 291 |
+
"eval_loss": 0.1797763854265213,
|
| 292 |
+
"eval_mae": 0.2279701679944992,
|
| 293 |
+
"eval_mse": 0.1797763854265213,
|
| 294 |
+
"eval_r2": 0.8305113911628723,
|
| 295 |
+
"eval_runtime": 4.8025,
|
| 296 |
+
"eval_samples_per_second": 2082.257,
|
| 297 |
+
"eval_steps_per_second": 130.141,
|
| 298 |
+
"step": 16000
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 3.0,
|
| 302 |
+
"step": 16875,
|
| 303 |
+
"total_flos": 3.551967355392e+16,
|
| 304 |
+
"train_loss": 0.17141379213686342,
|
| 305 |
+
"train_runtime": 610.1774,
|
| 306 |
+
"train_samples_per_second": 442.494,
|
| 307 |
+
"train_steps_per_second": 27.656
|
| 308 |
+
}
|
| 309 |
+
],
|
| 310 |
+
"logging_steps": 1000,
|
| 311 |
+
"max_steps": 16875,
|
| 312 |
+
"num_input_tokens_seen": 0,
|
| 313 |
+
"num_train_epochs": 3,
|
| 314 |
+
"save_steps": 1000,
|
| 315 |
+
"stateful_callbacks": {
|
| 316 |
+
"TrainerControl": {
|
| 317 |
+
"args": {
|
| 318 |
+
"should_epoch_stop": false,
|
| 319 |
+
"should_evaluate": false,
|
| 320 |
+
"should_log": false,
|
| 321 |
+
"should_save": true,
|
| 322 |
+
"should_training_stop": true
|
| 323 |
+
},
|
| 324 |
+
"attributes": {}
|
| 325 |
+
}
|
| 326 |
+
},
|
| 327 |
+
"total_flos": 3.551967355392e+16,
|
| 328 |
+
"train_batch_size": 16,
|
| 329 |
+
"trial_name": null,
|
| 330 |
+
"trial_params": null
|
| 331 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6469c1e7453b12240fa9e2fd1a405e4e80693b9eaca3e469d6d1c772991b8d9
|
| 3 |
+
size 5713
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|