20250120
Browse files- added_tokens.json +3 -0
- config.json +34 -0
- model.safetensors +3 -0
- special_tokens_map.json +13 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- trainer_state.json +645 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[UNK]": 39979
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "nghuyong/ernie-3.0-mini-zh",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ErnieForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 384,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0"
|
| 13 |
+
},
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 1536,
|
| 16 |
+
"label2id": {
|
| 17 |
+
"LABEL_0": 0
|
| 18 |
+
},
|
| 19 |
+
"layer_norm_eps": 1e-05,
|
| 20 |
+
"max_position_embeddings": 2048,
|
| 21 |
+
"model_type": "ernie",
|
| 22 |
+
"num_attention_heads": 12,
|
| 23 |
+
"num_hidden_layers": 6,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"position_embedding_type": "absolute",
|
| 26 |
+
"problem_type": "regression",
|
| 27 |
+
"task_type_vocab_size": 16,
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.39.3",
|
| 30 |
+
"type_vocab_size": 4,
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"use_task_id": true,
|
| 33 |
+
"vocab_size": 40000
|
| 34 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88b40eab1794fb1555a54afad8729f11990a5797c55a948ad777e3d0cee5bc2d
|
| 3 |
+
size 107811804
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": {
|
| 5 |
+
"content": "[PAD]",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false
|
| 10 |
+
},
|
| 11 |
+
"sep_token": "[SEP]",
|
| 12 |
+
"unk_token": "[UNK]"
|
| 13 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[MASK]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"39979": {
|
| 36 |
+
"content": "[UNK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 50 |
+
"never_split": null,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"strip_accents": null,
|
| 54 |
+
"tokenize_chinese_chars": true,
|
| 55 |
+
"tokenizer_class": "BertTokenizer",
|
| 56 |
+
"unk_token": "[UNK]"
|
| 57 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,645 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.15410752594470978,
|
| 3 |
+
"best_model_checkpoint": "/root/autodl-tmp/Experiment/Finetuning/Finetuning Hyperparam/v4.0.1-nghuyong-ernie-3.0-mini-zh/checkpoint-16548",
|
| 4 |
+
"epoch": 31.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 24428,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.63,
|
| 13 |
+
"grad_norm": 3.7946994304656982,
|
| 14 |
+
"learning_rate": 1e-06,
|
| 15 |
+
"loss": 3.149,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_loss": 0.38300707936286926,
|
| 21 |
+
"eval_mse": 0.3830070885439162,
|
| 22 |
+
"eval_runtime": 2.9729,
|
| 23 |
+
"eval_samples_per_second": 1058.553,
|
| 24 |
+
"eval_steps_per_second": 132.529,
|
| 25 |
+
"step": 788
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 1.27,
|
| 29 |
+
"grad_norm": 11.180171012878418,
|
| 30 |
+
"learning_rate": 2e-06,
|
| 31 |
+
"loss": 0.4095,
|
| 32 |
+
"step": 1000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.9,
|
| 36 |
+
"grad_norm": 4.669135093688965,
|
| 37 |
+
"learning_rate": 1.9997961851558053e-06,
|
| 38 |
+
"loss": 0.3395,
|
| 39 |
+
"step": 1500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 2.0,
|
| 43 |
+
"eval_loss": 0.29351383447647095,
|
| 44 |
+
"eval_mse": 0.29351383644291107,
|
| 45 |
+
"eval_runtime": 6.3375,
|
| 46 |
+
"eval_samples_per_second": 496.569,
|
| 47 |
+
"eval_steps_per_second": 62.17,
|
| 48 |
+
"step": 1576
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 2.54,
|
| 52 |
+
"grad_norm": 8.825602531433105,
|
| 53 |
+
"learning_rate": 1.9991848237042032e-06,
|
| 54 |
+
"loss": 0.3054,
|
| 55 |
+
"step": 2000
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 3.0,
|
| 59 |
+
"eval_loss": 0.25713810324668884,
|
| 60 |
+
"eval_mse": 0.2571380933159888,
|
| 61 |
+
"eval_runtime": 6.4767,
|
| 62 |
+
"eval_samples_per_second": 485.894,
|
| 63 |
+
"eval_steps_per_second": 60.833,
|
| 64 |
+
"step": 2364
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 3.17,
|
| 68 |
+
"grad_norm": 7.739953517913818,
|
| 69 |
+
"learning_rate": 1.9981661648542715e-06,
|
| 70 |
+
"loss": 0.2776,
|
| 71 |
+
"step": 2500
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 3.81,
|
| 75 |
+
"grad_norm": 10.34103012084961,
|
| 76 |
+
"learning_rate": 1.9967406238415996e-06,
|
| 77 |
+
"loss": 0.2647,
|
| 78 |
+
"step": 3000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 4.0,
|
| 82 |
+
"eval_loss": 0.23777985572814941,
|
| 83 |
+
"eval_mse": 0.23777985193765389,
|
| 84 |
+
"eval_runtime": 6.6281,
|
| 85 |
+
"eval_samples_per_second": 474.796,
|
| 86 |
+
"eval_steps_per_second": 59.444,
|
| 87 |
+
"step": 3152
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 4.44,
|
| 91 |
+
"grad_norm": 7.974781036376953,
|
| 92 |
+
"learning_rate": 1.9949087817590264e-06,
|
| 93 |
+
"loss": 0.2526,
|
| 94 |
+
"step": 3500
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 5.0,
|
| 98 |
+
"eval_loss": 0.2172749936580658,
|
| 99 |
+
"eval_mse": 0.2172749924371511,
|
| 100 |
+
"eval_runtime": 5.4164,
|
| 101 |
+
"eval_samples_per_second": 581.01,
|
| 102 |
+
"eval_steps_per_second": 72.742,
|
| 103 |
+
"step": 3940
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 5.08,
|
| 107 |
+
"grad_norm": 9.380146980285645,
|
| 108 |
+
"learning_rate": 1.9926713853197696e-06,
|
| 109 |
+
"loss": 0.2378,
|
| 110 |
+
"step": 4000
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 5.71,
|
| 114 |
+
"grad_norm": 11.635780334472656,
|
| 115 |
+
"learning_rate": 1.9900293465530417e-06,
|
| 116 |
+
"loss": 0.2277,
|
| 117 |
+
"step": 4500
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 6.0,
|
| 121 |
+
"eval_loss": 0.20999611914157867,
|
| 122 |
+
"eval_mse": 0.20999612821573685,
|
| 123 |
+
"eval_runtime": 6.6044,
|
| 124 |
+
"eval_samples_per_second": 476.502,
|
| 125 |
+
"eval_steps_per_second": 59.657,
|
| 126 |
+
"step": 4728
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 6.35,
|
| 130 |
+
"grad_norm": 8.879988670349121,
|
| 131 |
+
"learning_rate": 1.9869837424322827e-06,
|
| 132 |
+
"loss": 0.2263,
|
| 133 |
+
"step": 5000
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 6.98,
|
| 137 |
+
"grad_norm": 10.700913429260254,
|
| 138 |
+
"learning_rate": 1.9835358144361507e-06,
|
| 139 |
+
"loss": 0.2129,
|
| 140 |
+
"step": 5500
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 7.0,
|
| 144 |
+
"eval_loss": 0.19987642765045166,
|
| 145 |
+
"eval_mse": 0.19987641025845929,
|
| 146 |
+
"eval_runtime": 6.5132,
|
| 147 |
+
"eval_samples_per_second": 483.173,
|
| 148 |
+
"eval_steps_per_second": 60.493,
|
| 149 |
+
"step": 5516
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 7.61,
|
| 153 |
+
"grad_norm": 8.578248023986816,
|
| 154 |
+
"learning_rate": 1.979686968042461e-06,
|
| 155 |
+
"loss": 0.2053,
|
| 156 |
+
"step": 6000
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 8.0,
|
| 160 |
+
"eval_loss": 0.1908576488494873,
|
| 161 |
+
"eval_mse": 0.19085766332291107,
|
| 162 |
+
"eval_runtime": 6.542,
|
| 163 |
+
"eval_samples_per_second": 481.047,
|
| 164 |
+
"eval_steps_per_second": 60.226,
|
| 165 |
+
"step": 6304
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 8.25,
|
| 169 |
+
"grad_norm": 7.703456878662109,
|
| 170 |
+
"learning_rate": 1.975438772155269e-06,
|
| 171 |
+
"loss": 0.2028,
|
| 172 |
+
"step": 6500
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 8.88,
|
| 176 |
+
"grad_norm": 5.999122142791748,
|
| 177 |
+
"learning_rate": 1.9707929584653408e-06,
|
| 178 |
+
"loss": 0.1984,
|
| 179 |
+
"step": 7000
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 9.0,
|
| 183 |
+
"eval_loss": 0.18801844120025635,
|
| 184 |
+
"eval_mse": 0.18801843036404595,
|
| 185 |
+
"eval_runtime": 6.3586,
|
| 186 |
+
"eval_samples_per_second": 494.92,
|
| 187 |
+
"eval_steps_per_second": 61.963,
|
| 188 |
+
"step": 7092
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 9.52,
|
| 192 |
+
"grad_norm": 4.026780128479004,
|
| 193 |
+
"learning_rate": 1.965751420744263e-06,
|
| 194 |
+
"loss": 0.1898,
|
| 195 |
+
"step": 7500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 10.0,
|
| 199 |
+
"eval_loss": 0.17908616364002228,
|
| 200 |
+
"eval_mse": 0.17908616463804863,
|
| 201 |
+
"eval_runtime": 6.0503,
|
| 202 |
+
"eval_samples_per_second": 520.14,
|
| 203 |
+
"eval_steps_per_second": 65.121,
|
| 204 |
+
"step": 7880
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 10.15,
|
| 208 |
+
"grad_norm": 13.863020896911621,
|
| 209 |
+
"learning_rate": 1.960316214072486e-06,
|
| 210 |
+
"loss": 0.1838,
|
| 211 |
+
"step": 8000
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 10.79,
|
| 215 |
+
"grad_norm": 8.270528793334961,
|
| 216 |
+
"learning_rate": 1.9544895540016116e-06,
|
| 217 |
+
"loss": 0.1833,
|
| 218 |
+
"step": 8500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 11.0,
|
| 222 |
+
"eval_loss": 0.17787215113639832,
|
| 223 |
+
"eval_mse": 0.17787216239741555,
|
| 224 |
+
"eval_runtime": 6.4275,
|
| 225 |
+
"eval_samples_per_second": 489.617,
|
| 226 |
+
"eval_steps_per_second": 61.299,
|
| 227 |
+
"step": 8668
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 11.42,
|
| 231 |
+
"grad_norm": 4.614955425262451,
|
| 232 |
+
"learning_rate": 1.948273815651269e-06,
|
| 233 |
+
"loss": 0.1744,
|
| 234 |
+
"step": 9000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 12.0,
|
| 238 |
+
"eval_loss": 0.17208915948867798,
|
| 239 |
+
"eval_mse": 0.17208916706729221,
|
| 240 |
+
"eval_runtime": 6.5286,
|
| 241 |
+
"eval_samples_per_second": 482.034,
|
| 242 |
+
"eval_steps_per_second": 60.35,
|
| 243 |
+
"step": 9456
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 12.06,
|
| 247 |
+
"grad_norm": 6.665430545806885,
|
| 248 |
+
"learning_rate": 1.941671532740945e-06,
|
| 249 |
+
"loss": 0.1772,
|
| 250 |
+
"step": 9500
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 12.69,
|
| 254 |
+
"grad_norm": 7.56500244140625,
|
| 255 |
+
"learning_rate": 1.934685396557165e-06,
|
| 256 |
+
"loss": 0.1693,
|
| 257 |
+
"step": 10000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 13.0,
|
| 261 |
+
"eval_loss": 0.1708821803331375,
|
| 262 |
+
"eval_mse": 0.1708821751524203,
|
| 263 |
+
"eval_runtime": 6.4009,
|
| 264 |
+
"eval_samples_per_second": 491.651,
|
| 265 |
+
"eval_steps_per_second": 61.554,
|
| 266 |
+
"step": 10244
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 13.32,
|
| 270 |
+
"grad_norm": 4.484550476074219,
|
| 271 |
+
"learning_rate": 1.9273182548564444e-06,
|
| 272 |
+
"loss": 0.1672,
|
| 273 |
+
"step": 10500
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 13.96,
|
| 277 |
+
"grad_norm": 7.24429988861084,
|
| 278 |
+
"learning_rate": 1.9195731107044594e-06,
|
| 279 |
+
"loss": 0.164,
|
| 280 |
+
"step": 11000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 14.0,
|
| 284 |
+
"eval_loss": 0.16326776146888733,
|
| 285 |
+
"eval_mse": 0.16326775885293762,
|
| 286 |
+
"eval_runtime": 6.5473,
|
| 287 |
+
"eval_samples_per_second": 480.658,
|
| 288 |
+
"eval_steps_per_second": 60.178,
|
| 289 |
+
"step": 11032
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 14.59,
|
| 293 |
+
"grad_norm": 5.866950511932373,
|
| 294 |
+
"learning_rate": 1.9114531212519067e-06,
|
| 295 |
+
"loss": 0.164,
|
| 296 |
+
"step": 11500
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 15.0,
|
| 300 |
+
"eval_loss": 0.1637822687625885,
|
| 301 |
+
"eval_mse": 0.1637822618402825,
|
| 302 |
+
"eval_runtime": 6.4327,
|
| 303 |
+
"eval_samples_per_second": 489.216,
|
| 304 |
+
"eval_steps_per_second": 61.249,
|
| 305 |
+
"step": 11820
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 15.23,
|
| 309 |
+
"grad_norm": 4.922129154205322,
|
| 310 |
+
"learning_rate": 1.902961596447557e-06,
|
| 311 |
+
"loss": 0.161,
|
| 312 |
+
"step": 12000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 15.86,
|
| 316 |
+
"grad_norm": 4.9291911125183105,
|
| 317 |
+
"learning_rate": 1.8941019976890202e-06,
|
| 318 |
+
"loss": 0.1567,
|
| 319 |
+
"step": 12500
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 16.0,
|
| 323 |
+
"eval_loss": 0.16271694004535675,
|
| 324 |
+
"eval_mse": 0.16271693369747306,
|
| 325 |
+
"eval_runtime": 6.435,
|
| 326 |
+
"eval_samples_per_second": 489.044,
|
| 327 |
+
"eval_steps_per_second": 61.228,
|
| 328 |
+
"step": 12608
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 16.5,
|
| 332 |
+
"grad_norm": 6.7055583000183105,
|
| 333 |
+
"learning_rate": 1.8848779364117772e-06,
|
| 334 |
+
"loss": 0.1565,
|
| 335 |
+
"step": 13000
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 17.0,
|
| 339 |
+
"eval_loss": 0.163142591714859,
|
| 340 |
+
"eval_mse": 0.16314259089138047,
|
| 341 |
+
"eval_runtime": 6.6313,
|
| 342 |
+
"eval_samples_per_second": 474.567,
|
| 343 |
+
"eval_steps_per_second": 59.415,
|
| 344 |
+
"step": 13396
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 17.13,
|
| 348 |
+
"grad_norm": 6.387050151824951,
|
| 349 |
+
"learning_rate": 1.8752931726170524e-06,
|
| 350 |
+
"loss": 0.1513,
|
| 351 |
+
"step": 13500
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 17.77,
|
| 355 |
+
"grad_norm": 4.200338840484619,
|
| 356 |
+
"learning_rate": 1.8653516133391248e-06,
|
| 357 |
+
"loss": 0.1465,
|
| 358 |
+
"step": 14000
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 18.0,
|
| 362 |
+
"eval_loss": 0.15735994279384613,
|
| 363 |
+
"eval_mse": 0.15735993839769294,
|
| 364 |
+
"eval_runtime": 6.3765,
|
| 365 |
+
"eval_samples_per_second": 493.533,
|
| 366 |
+
"eval_steps_per_second": 61.79,
|
| 367 |
+
"step": 14184
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 18.4,
|
| 371 |
+
"grad_norm": 8.57667350769043,
|
| 372 |
+
"learning_rate": 1.8550573110527048e-06,
|
| 373 |
+
"loss": 0.1507,
|
| 374 |
+
"step": 14500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 19.0,
|
| 378 |
+
"eval_loss": 0.15925408899784088,
|
| 379 |
+
"eval_mse": 0.15925409548753688,
|
| 380 |
+
"eval_runtime": 6.3908,
|
| 381 |
+
"eval_samples_per_second": 492.428,
|
| 382 |
+
"eval_steps_per_second": 61.651,
|
| 383 |
+
"step": 14972
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 19.04,
|
| 387 |
+
"grad_norm": 7.292795658111572,
|
| 388 |
+
"learning_rate": 1.8444144620210253e-06,
|
| 389 |
+
"loss": 0.1457,
|
| 390 |
+
"step": 15000
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 19.67,
|
| 394 |
+
"grad_norm": 6.043280124664307,
|
| 395 |
+
"learning_rate": 1.8334274045853211e-06,
|
| 396 |
+
"loss": 0.1445,
|
| 397 |
+
"step": 15500
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 20.0,
|
| 401 |
+
"eval_loss": 0.1564783751964569,
|
| 402 |
+
"eval_mse": 0.15647836555803193,
|
| 403 |
+
"eval_runtime": 6.5916,
|
| 404 |
+
"eval_samples_per_second": 477.427,
|
| 405 |
+
"eval_steps_per_second": 59.773,
|
| 406 |
+
"step": 15760
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 20.3,
|
| 410 |
+
"grad_norm": 5.833315849304199,
|
| 411 |
+
"learning_rate": 1.822100617396391e-06,
|
| 412 |
+
"loss": 0.1405,
|
| 413 |
+
"step": 16000
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 20.94,
|
| 417 |
+
"grad_norm": 5.3432793617248535,
|
| 418 |
+
"learning_rate": 1.810438717588967e-06,
|
| 419 |
+
"loss": 0.1385,
|
| 420 |
+
"step": 16500
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 21.0,
|
| 424 |
+
"eval_loss": 0.15410752594470978,
|
| 425 |
+
"eval_mse": 0.15410751673185336,
|
| 426 |
+
"eval_runtime": 6.6826,
|
| 427 |
+
"eval_samples_per_second": 470.926,
|
| 428 |
+
"eval_steps_per_second": 58.959,
|
| 429 |
+
"step": 16548
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 21.57,
|
| 433 |
+
"grad_norm": 4.962389945983887,
|
| 434 |
+
"learning_rate": 1.7984464588996339e-06,
|
| 435 |
+
"loss": 0.1393,
|
| 436 |
+
"step": 17000
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 22.0,
|
| 440 |
+
"eval_loss": 0.15984748303890228,
|
| 441 |
+
"eval_mse": 0.15984746704761707,
|
| 442 |
+
"eval_runtime": 4.5153,
|
| 443 |
+
"eval_samples_per_second": 696.962,
|
| 444 |
+
"eval_steps_per_second": 87.259,
|
| 445 |
+
"step": 17336
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 22.21,
|
| 449 |
+
"grad_norm": 6.73746395111084,
|
| 450 |
+
"learning_rate": 1.7861287297290642e-06,
|
| 451 |
+
"loss": 0.1364,
|
| 452 |
+
"step": 17500
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 22.84,
|
| 456 |
+
"grad_norm": 4.136258125305176,
|
| 457 |
+
"learning_rate": 1.773490551149361e-06,
|
| 458 |
+
"loss": 0.1369,
|
| 459 |
+
"step": 18000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 23.0,
|
| 463 |
+
"eval_loss": 0.1571136862039566,
|
| 464 |
+
"eval_mse": 0.15711369395451796,
|
| 465 |
+
"eval_runtime": 6.6457,
|
| 466 |
+
"eval_samples_per_second": 473.538,
|
| 467 |
+
"eval_steps_per_second": 59.286,
|
| 468 |
+
"step": 18124
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 23.48,
|
| 472 |
+
"grad_norm": 4.904695510864258,
|
| 473 |
+
"learning_rate": 1.7605370748573214e-06,
|
| 474 |
+
"loss": 0.1321,
|
| 475 |
+
"step": 18500
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 24.0,
|
| 479 |
+
"eval_loss": 0.15537777543067932,
|
| 480 |
+
"eval_mse": 0.15537776661203356,
|
| 481 |
+
"eval_runtime": 6.4398,
|
| 482 |
+
"eval_samples_per_second": 488.676,
|
| 483 |
+
"eval_steps_per_second": 61.182,
|
| 484 |
+
"step": 18912
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 24.11,
|
| 488 |
+
"grad_norm": 6.113712310791016,
|
| 489 |
+
"learning_rate": 1.7472735810744493e-06,
|
| 490 |
+
"loss": 0.1345,
|
| 491 |
+
"step": 19000
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 24.75,
|
| 495 |
+
"grad_norm": 4.913405895233154,
|
| 496 |
+
"learning_rate": 1.7337054763945822e-06,
|
| 497 |
+
"loss": 0.1298,
|
| 498 |
+
"step": 19500
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 25.0,
|
| 502 |
+
"eval_loss": 0.15441741049289703,
|
| 503 |
+
"eval_mse": 0.1544174113407979,
|
| 504 |
+
"eval_runtime": 6.5832,
|
| 505 |
+
"eval_samples_per_second": 478.035,
|
| 506 |
+
"eval_steps_per_second": 59.849,
|
| 507 |
+
"step": 19700
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 25.38,
|
| 511 |
+
"grad_norm": 6.102097511291504,
|
| 512 |
+
"learning_rate": 1.7198382915800032e-06,
|
| 513 |
+
"loss": 0.1328,
|
| 514 |
+
"step": 20000
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 26.0,
|
| 518 |
+
"eval_loss": 0.15451224148273468,
|
| 519 |
+
"eval_mse": 0.15451224737858407,
|
| 520 |
+
"eval_runtime": 6.7032,
|
| 521 |
+
"eval_samples_per_second": 469.48,
|
| 522 |
+
"eval_steps_per_second": 58.778,
|
| 523 |
+
"step": 20488
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 26.02,
|
| 527 |
+
"grad_norm": 3.6252963542938232,
|
| 528 |
+
"learning_rate": 1.705677679306937e-06,
|
| 529 |
+
"loss": 0.1249,
|
| 530 |
+
"step": 20500
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 26.65,
|
| 534 |
+
"grad_norm": 9.473875999450684,
|
| 535 |
+
"learning_rate": 1.6912294118613515e-06,
|
| 536 |
+
"loss": 0.1242,
|
| 537 |
+
"step": 21000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 27.0,
|
| 541 |
+
"eval_loss": 0.1551235318183899,
|
| 542 |
+
"eval_mse": 0.15512353782534866,
|
| 543 |
+
"eval_runtime": 4.9635,
|
| 544 |
+
"eval_samples_per_second": 634.03,
|
| 545 |
+
"eval_steps_per_second": 79.38,
|
| 546 |
+
"step": 21276
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 27.28,
|
| 550 |
+
"grad_norm": 7.1829023361206055,
|
| 551 |
+
"learning_rate": 1.676499378786004e-06,
|
| 552 |
+
"loss": 0.1243,
|
| 553 |
+
"step": 21500
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 27.92,
|
| 557 |
+
"grad_norm": 3.2615394592285156,
|
| 558 |
+
"learning_rate": 1.6614935844796863e-06,
|
| 559 |
+
"loss": 0.124,
|
| 560 |
+
"step": 22000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 28.0,
|
| 564 |
+
"eval_loss": 0.15653343498706818,
|
| 565 |
+
"eval_mse": 0.15653342717462115,
|
| 566 |
+
"eval_runtime": 6.3678,
|
| 567 |
+
"eval_samples_per_second": 494.206,
|
| 568 |
+
"eval_steps_per_second": 61.874,
|
| 569 |
+
"step": 22064
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 28.55,
|
| 573 |
+
"grad_norm": 3.4693961143493652,
|
| 574 |
+
"learning_rate": 1.6462181457496556e-06,
|
| 575 |
+
"loss": 0.121,
|
| 576 |
+
"step": 22500
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 29.0,
|
| 580 |
+
"eval_loss": 0.16021837294101715,
|
| 581 |
+
"eval_mse": 0.16021836760764882,
|
| 582 |
+
"eval_runtime": 6.4147,
|
| 583 |
+
"eval_samples_per_second": 490.594,
|
| 584 |
+
"eval_steps_per_second": 61.422,
|
| 585 |
+
"step": 22852
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 29.19,
|
| 589 |
+
"grad_norm": 4.559121608734131,
|
| 590 |
+
"learning_rate": 1.630679289318242e-06,
|
| 591 |
+
"loss": 0.1212,
|
| 592 |
+
"step": 23000
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 29.82,
|
| 596 |
+
"grad_norm": 5.630191326141357,
|
| 597 |
+
"learning_rate": 1.61488334928465e-06,
|
| 598 |
+
"loss": 0.1199,
|
| 599 |
+
"step": 23500
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 30.0,
|
| 603 |
+
"eval_loss": 0.15692943334579468,
|
| 604 |
+
"eval_mse": 0.15692943571123527,
|
| 605 |
+
"eval_runtime": 6.7232,
|
| 606 |
+
"eval_samples_per_second": 468.083,
|
| 607 |
+
"eval_steps_per_second": 58.603,
|
| 608 |
+
"step": 23640
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 30.46,
|
| 612 |
+
"grad_norm": 6.069174289703369,
|
| 613 |
+
"learning_rate": 1.5988367645429936e-06,
|
| 614 |
+
"loss": 0.1199,
|
| 615 |
+
"step": 24000
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 31.0,
|
| 619 |
+
"eval_loss": 0.155219167470932,
|
| 620 |
+
"eval_mse": 0.1552191666236313,
|
| 621 |
+
"eval_runtime": 6.459,
|
| 622 |
+
"eval_samples_per_second": 487.224,
|
| 623 |
+
"eval_steps_per_second": 61.0,
|
| 624 |
+
"step": 24428
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 31.0,
|
| 628 |
+
"step": 24428,
|
| 629 |
+
"total_flos": 1.2955645439479296e+16,
|
| 630 |
+
"train_loss": 0.23735684225714224,
|
| 631 |
+
"train_runtime": 2509.2105,
|
| 632 |
+
"train_samples_per_second": 1004.42,
|
| 633 |
+
"train_steps_per_second": 31.404
|
| 634 |
+
}
|
| 635 |
+
],
|
| 636 |
+
"logging_steps": 500,
|
| 637 |
+
"max_steps": 78800,
|
| 638 |
+
"num_input_tokens_seen": 0,
|
| 639 |
+
"num_train_epochs": 100,
|
| 640 |
+
"save_steps": 500,
|
| 641 |
+
"total_flos": 1.2955645439479296e+16,
|
| 642 |
+
"train_batch_size": 32,
|
| 643 |
+
"trial_name": null,
|
| 644 |
+
"trial_params": null
|
| 645 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e004fcbfc0f4050a659d6ad3f15fddf2d13449ebd000d2b2e38e49664cf2b6b
|
| 3 |
+
size 4984
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|