update from Yaxin
Browse files- README.md +69 -0
- all_results.json +15 -0
- config.json +30 -0
- eval_results.json +10 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- trainer_state.json +679 -0
- vocab.txt +0 -0
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- yelp_review_full
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: electra-base-discriminator-yelp-mlm
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Masked Language Modeling
|
| 14 |
+
type: fill-mask
|
| 15 |
+
dataset:
|
| 16 |
+
name: yelp_review_full yelp_review_full
|
| 17 |
+
type: yelp_review_full
|
| 18 |
+
args: yelp_review_full
|
| 19 |
+
metrics:
|
| 20 |
+
- name: Accuracy
|
| 21 |
+
type: accuracy
|
| 22 |
+
value: 0.678284391624956
|
| 23 |
+
---
|
| 24 |
+
|
| 25 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 26 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 27 |
+
|
| 28 |
+
# electra-base-discriminator-yelp-mlm
|
| 29 |
+
|
| 30 |
+
This model is a fine-tuned version of [google/electra-base-discriminator](https://huggingface.co/google/electra-base-discriminator) on the yelp_review_full yelp_review_full dataset.
|
| 31 |
+
It achieves the following results on the evaluation set:
|
| 32 |
+
- Loss: 1.5550
|
| 33 |
+
- Accuracy: 0.6783
|
| 34 |
+
|
| 35 |
+
## Model description
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Intended uses & limitations
|
| 40 |
+
|
| 41 |
+
More information needed
|
| 42 |
+
|
| 43 |
+
## Training and evaluation data
|
| 44 |
+
|
| 45 |
+
More information needed
|
| 46 |
+
|
| 47 |
+
## Training procedure
|
| 48 |
+
|
| 49 |
+
### Training hyperparameters
|
| 50 |
+
|
| 51 |
+
The following hyperparameters were used during training:
|
| 52 |
+
- learning_rate: 5e-05
|
| 53 |
+
- train_batch_size: 12
|
| 54 |
+
- eval_batch_size: 12
|
| 55 |
+
- seed: 42
|
| 56 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 57 |
+
- lr_scheduler_type: linear
|
| 58 |
+
- num_epochs: 3.0
|
| 59 |
+
|
| 60 |
+
### Training results
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
### Framework versions
|
| 65 |
+
|
| 66 |
+
- Transformers 4.18.0.dev0
|
| 67 |
+
- Pytorch 1.10.0
|
| 68 |
+
- Datasets 1.18.3
|
| 69 |
+
- Tokenizers 0.11.0
|
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.678284391624956,
|
| 4 |
+
"eval_loss": 1.5549513101577759,
|
| 5 |
+
"eval_runtime": 219.8849,
|
| 6 |
+
"eval_samples": 10970,
|
| 7 |
+
"eval_samples_per_second": 49.89,
|
| 8 |
+
"eval_steps_per_second": 4.161,
|
| 9 |
+
"perplexity": 4.734855980156241,
|
| 10 |
+
"train_loss": 1.8530674359188393,
|
| 11 |
+
"train_runtime": 31139.3919,
|
| 12 |
+
"train_samples": 218101,
|
| 13 |
+
"train_samples_per_second": 21.012,
|
| 14 |
+
"train_steps_per_second": 1.751
|
| 15 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/electra-base-discriminator",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ElectraForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"embedding_size": 768,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "electra",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"summary_activation": "gelu",
|
| 22 |
+
"summary_last_dropout": 0.1,
|
| 23 |
+
"summary_type": "first",
|
| 24 |
+
"summary_use_proj": true,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.18.0.dev0",
|
| 27 |
+
"type_vocab_size": 2,
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 30522
|
| 30 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.678284391624956,
|
| 4 |
+
"eval_loss": 1.5549513101577759,
|
| 5 |
+
"eval_runtime": 219.8849,
|
| 6 |
+
"eval_samples": 10970,
|
| 7 |
+
"eval_samples_per_second": 49.89,
|
| 8 |
+
"eval_steps_per_second": 4.161,
|
| 9 |
+
"perplexity": 4.734855980156241
|
| 10 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "google/electra-base-discriminator", "tokenizer_class": "ElectraTokenizer"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,679 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 54528,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 4.954151995305165e-05,
|
| 13 |
+
"loss": 4.1243,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.06,
|
| 18 |
+
"learning_rate": 4.908303990610329e-05,
|
| 19 |
+
"loss": 3.0378,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.08,
|
| 24 |
+
"learning_rate": 4.8624559859154934e-05,
|
| 25 |
+
"loss": 2.767,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.11,
|
| 30 |
+
"learning_rate": 4.816607981220658e-05,
|
| 31 |
+
"loss": 2.5961,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.14,
|
| 36 |
+
"learning_rate": 4.770759976525822e-05,
|
| 37 |
+
"loss": 2.4848,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.17,
|
| 42 |
+
"learning_rate": 4.724911971830986e-05,
|
| 43 |
+
"loss": 2.4087,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.19,
|
| 48 |
+
"learning_rate": 4.6790639671361505e-05,
|
| 49 |
+
"loss": 2.34,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.22,
|
| 54 |
+
"learning_rate": 4.6332159624413144e-05,
|
| 55 |
+
"loss": 2.3038,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.25,
|
| 60 |
+
"learning_rate": 4.587367957746479e-05,
|
| 61 |
+
"loss": 2.238,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.28,
|
| 66 |
+
"learning_rate": 4.5415199530516436e-05,
|
| 67 |
+
"loss": 2.224,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.3,
|
| 72 |
+
"learning_rate": 4.4956719483568075e-05,
|
| 73 |
+
"loss": 2.1801,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.33,
|
| 78 |
+
"learning_rate": 4.449823943661972e-05,
|
| 79 |
+
"loss": 2.1474,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.36,
|
| 84 |
+
"learning_rate": 4.403975938967137e-05,
|
| 85 |
+
"loss": 2.1175,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.39,
|
| 90 |
+
"learning_rate": 4.3581279342723007e-05,
|
| 91 |
+
"loss": 2.0952,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.41,
|
| 96 |
+
"learning_rate": 4.312279929577465e-05,
|
| 97 |
+
"loss": 2.0845,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.44,
|
| 102 |
+
"learning_rate": 4.26643192488263e-05,
|
| 103 |
+
"loss": 2.056,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.47,
|
| 108 |
+
"learning_rate": 4.220583920187793e-05,
|
| 109 |
+
"loss": 2.0451,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.5,
|
| 114 |
+
"learning_rate": 4.174735915492958e-05,
|
| 115 |
+
"loss": 2.0272,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.52,
|
| 120 |
+
"learning_rate": 4.128887910798122e-05,
|
| 121 |
+
"loss": 2.0085,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.55,
|
| 126 |
+
"learning_rate": 4.083039906103286e-05,
|
| 127 |
+
"loss": 1.989,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.58,
|
| 132 |
+
"learning_rate": 4.037191901408451e-05,
|
| 133 |
+
"loss": 1.9824,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.61,
|
| 138 |
+
"learning_rate": 3.9913438967136155e-05,
|
| 139 |
+
"loss": 1.966,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.63,
|
| 144 |
+
"learning_rate": 3.9454958920187794e-05,
|
| 145 |
+
"loss": 1.9524,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.66,
|
| 150 |
+
"learning_rate": 3.899647887323944e-05,
|
| 151 |
+
"loss": 1.9426,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.69,
|
| 156 |
+
"learning_rate": 3.8537998826291086e-05,
|
| 157 |
+
"loss": 1.9391,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.72,
|
| 162 |
+
"learning_rate": 3.8079518779342725e-05,
|
| 163 |
+
"loss": 1.9316,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.74,
|
| 168 |
+
"learning_rate": 3.762103873239437e-05,
|
| 169 |
+
"loss": 1.9163,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.77,
|
| 174 |
+
"learning_rate": 3.716255868544601e-05,
|
| 175 |
+
"loss": 1.9031,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.8,
|
| 180 |
+
"learning_rate": 3.670407863849765e-05,
|
| 181 |
+
"loss": 1.8949,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.83,
|
| 186 |
+
"learning_rate": 3.6245598591549296e-05,
|
| 187 |
+
"loss": 1.8862,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.85,
|
| 192 |
+
"learning_rate": 3.578711854460094e-05,
|
| 193 |
+
"loss": 1.8856,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.88,
|
| 198 |
+
"learning_rate": 3.532863849765258e-05,
|
| 199 |
+
"loss": 1.8817,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.91,
|
| 204 |
+
"learning_rate": 3.487015845070423e-05,
|
| 205 |
+
"loss": 1.8613,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.94,
|
| 210 |
+
"learning_rate": 3.4411678403755874e-05,
|
| 211 |
+
"loss": 1.8533,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.96,
|
| 216 |
+
"learning_rate": 3.395319835680751e-05,
|
| 217 |
+
"loss": 1.8591,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.99,
|
| 222 |
+
"learning_rate": 3.349471830985916e-05,
|
| 223 |
+
"loss": 1.8461,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.02,
|
| 228 |
+
"learning_rate": 3.30362382629108e-05,
|
| 229 |
+
"loss": 1.8417,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.05,
|
| 234 |
+
"learning_rate": 3.2577758215962444e-05,
|
| 235 |
+
"loss": 1.825,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.07,
|
| 240 |
+
"learning_rate": 3.211927816901409e-05,
|
| 241 |
+
"loss": 1.8193,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.1,
|
| 246 |
+
"learning_rate": 3.166079812206573e-05,
|
| 247 |
+
"loss": 1.817,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.13,
|
| 252 |
+
"learning_rate": 3.120231807511737e-05,
|
| 253 |
+
"loss": 1.8042,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.16,
|
| 258 |
+
"learning_rate": 3.0743838028169015e-05,
|
| 259 |
+
"loss": 1.7981,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.18,
|
| 264 |
+
"learning_rate": 3.0285357981220658e-05,
|
| 265 |
+
"loss": 1.8042,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.21,
|
| 270 |
+
"learning_rate": 2.98268779342723e-05,
|
| 271 |
+
"loss": 1.7944,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.24,
|
| 276 |
+
"learning_rate": 2.9368397887323946e-05,
|
| 277 |
+
"loss": 1.7904,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.27,
|
| 282 |
+
"learning_rate": 2.890991784037559e-05,
|
| 283 |
+
"loss": 1.7852,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.29,
|
| 288 |
+
"learning_rate": 2.8451437793427232e-05,
|
| 289 |
+
"loss": 1.7744,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.32,
|
| 294 |
+
"learning_rate": 2.7992957746478874e-05,
|
| 295 |
+
"loss": 1.7684,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.35,
|
| 300 |
+
"learning_rate": 2.753447769953052e-05,
|
| 301 |
+
"loss": 1.7698,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.38,
|
| 306 |
+
"learning_rate": 2.7075997652582163e-05,
|
| 307 |
+
"loss": 1.7746,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.4,
|
| 312 |
+
"learning_rate": 2.6617517605633802e-05,
|
| 313 |
+
"loss": 1.7667,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.43,
|
| 318 |
+
"learning_rate": 2.6159037558685445e-05,
|
| 319 |
+
"loss": 1.7642,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.46,
|
| 324 |
+
"learning_rate": 2.5700557511737088e-05,
|
| 325 |
+
"loss": 1.7575,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.49,
|
| 330 |
+
"learning_rate": 2.5242077464788734e-05,
|
| 331 |
+
"loss": 1.7573,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.51,
|
| 336 |
+
"learning_rate": 2.4783597417840377e-05,
|
| 337 |
+
"loss": 1.7442,
|
| 338 |
+
"step": 27500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.54,
|
| 342 |
+
"learning_rate": 2.432511737089202e-05,
|
| 343 |
+
"loss": 1.7433,
|
| 344 |
+
"step": 28000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.57,
|
| 348 |
+
"learning_rate": 2.3866637323943662e-05,
|
| 349 |
+
"loss": 1.7487,
|
| 350 |
+
"step": 28500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.6,
|
| 354 |
+
"learning_rate": 2.3408157276995308e-05,
|
| 355 |
+
"loss": 1.7338,
|
| 356 |
+
"step": 29000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.62,
|
| 360 |
+
"learning_rate": 2.2949677230046947e-05,
|
| 361 |
+
"loss": 1.7282,
|
| 362 |
+
"step": 29500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 1.65,
|
| 366 |
+
"learning_rate": 2.2491197183098593e-05,
|
| 367 |
+
"loss": 1.7302,
|
| 368 |
+
"step": 30000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 1.68,
|
| 372 |
+
"learning_rate": 2.2032717136150236e-05,
|
| 373 |
+
"loss": 1.725,
|
| 374 |
+
"step": 30500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.71,
|
| 378 |
+
"learning_rate": 2.157423708920188e-05,
|
| 379 |
+
"loss": 1.7152,
|
| 380 |
+
"step": 31000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.73,
|
| 384 |
+
"learning_rate": 2.111575704225352e-05,
|
| 385 |
+
"loss": 1.723,
|
| 386 |
+
"step": 31500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 1.76,
|
| 390 |
+
"learning_rate": 2.0657276995305167e-05,
|
| 391 |
+
"loss": 1.7078,
|
| 392 |
+
"step": 32000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 1.79,
|
| 396 |
+
"learning_rate": 2.0198796948356807e-05,
|
| 397 |
+
"loss": 1.7119,
|
| 398 |
+
"step": 32500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.82,
|
| 402 |
+
"learning_rate": 1.974031690140845e-05,
|
| 403 |
+
"loss": 1.7088,
|
| 404 |
+
"step": 33000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.84,
|
| 408 |
+
"learning_rate": 1.9281836854460095e-05,
|
| 409 |
+
"loss": 1.7054,
|
| 410 |
+
"step": 33500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.87,
|
| 414 |
+
"learning_rate": 1.8823356807511738e-05,
|
| 415 |
+
"loss": 1.7057,
|
| 416 |
+
"step": 34000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.9,
|
| 420 |
+
"learning_rate": 1.836487676056338e-05,
|
| 421 |
+
"loss": 1.7088,
|
| 422 |
+
"step": 34500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.93,
|
| 426 |
+
"learning_rate": 1.7906396713615027e-05,
|
| 427 |
+
"loss": 1.689,
|
| 428 |
+
"step": 35000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.95,
|
| 432 |
+
"learning_rate": 1.7447916666666666e-05,
|
| 433 |
+
"loss": 1.6948,
|
| 434 |
+
"step": 35500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.98,
|
| 438 |
+
"learning_rate": 1.698943661971831e-05,
|
| 439 |
+
"loss": 1.6877,
|
| 440 |
+
"step": 36000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 2.01,
|
| 444 |
+
"learning_rate": 1.6530956572769955e-05,
|
| 445 |
+
"loss": 1.6983,
|
| 446 |
+
"step": 36500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 2.04,
|
| 450 |
+
"learning_rate": 1.6072476525821598e-05,
|
| 451 |
+
"loss": 1.6694,
|
| 452 |
+
"step": 37000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 2.06,
|
| 456 |
+
"learning_rate": 1.561399647887324e-05,
|
| 457 |
+
"loss": 1.6874,
|
| 458 |
+
"step": 37500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.09,
|
| 462 |
+
"learning_rate": 1.5155516431924883e-05,
|
| 463 |
+
"loss": 1.6714,
|
| 464 |
+
"step": 38000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.12,
|
| 468 |
+
"learning_rate": 1.4697036384976526e-05,
|
| 469 |
+
"loss": 1.6783,
|
| 470 |
+
"step": 38500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 2.15,
|
| 474 |
+
"learning_rate": 1.423855633802817e-05,
|
| 475 |
+
"loss": 1.6766,
|
| 476 |
+
"step": 39000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 2.17,
|
| 480 |
+
"learning_rate": 1.3780076291079813e-05,
|
| 481 |
+
"loss": 1.6707,
|
| 482 |
+
"step": 39500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 2.2,
|
| 486 |
+
"learning_rate": 1.3321596244131457e-05,
|
| 487 |
+
"loss": 1.6723,
|
| 488 |
+
"step": 40000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 2.23,
|
| 492 |
+
"learning_rate": 1.28631161971831e-05,
|
| 493 |
+
"loss": 1.6708,
|
| 494 |
+
"step": 40500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 2.26,
|
| 498 |
+
"learning_rate": 1.2404636150234742e-05,
|
| 499 |
+
"loss": 1.6667,
|
| 500 |
+
"step": 41000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 2.28,
|
| 504 |
+
"learning_rate": 1.1946156103286385e-05,
|
| 505 |
+
"loss": 1.6594,
|
| 506 |
+
"step": 41500
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.31,
|
| 510 |
+
"learning_rate": 1.148767605633803e-05,
|
| 511 |
+
"loss": 1.659,
|
| 512 |
+
"step": 42000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 2.34,
|
| 516 |
+
"learning_rate": 1.1029196009389672e-05,
|
| 517 |
+
"loss": 1.6619,
|
| 518 |
+
"step": 42500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 2.37,
|
| 522 |
+
"learning_rate": 1.0570715962441315e-05,
|
| 523 |
+
"loss": 1.6518,
|
| 524 |
+
"step": 43000
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 2.39,
|
| 528 |
+
"learning_rate": 1.0112235915492959e-05,
|
| 529 |
+
"loss": 1.6567,
|
| 530 |
+
"step": 43500
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 2.42,
|
| 534 |
+
"learning_rate": 9.653755868544602e-06,
|
| 535 |
+
"loss": 1.6555,
|
| 536 |
+
"step": 44000
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 2.45,
|
| 540 |
+
"learning_rate": 9.195275821596244e-06,
|
| 541 |
+
"loss": 1.6434,
|
| 542 |
+
"step": 44500
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 2.48,
|
| 546 |
+
"learning_rate": 8.736795774647887e-06,
|
| 547 |
+
"loss": 1.6505,
|
| 548 |
+
"step": 45000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 2.5,
|
| 552 |
+
"learning_rate": 8.278315727699531e-06,
|
| 553 |
+
"loss": 1.6449,
|
| 554 |
+
"step": 45500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 2.53,
|
| 558 |
+
"learning_rate": 7.819835680751174e-06,
|
| 559 |
+
"loss": 1.6454,
|
| 560 |
+
"step": 46000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 2.56,
|
| 564 |
+
"learning_rate": 7.361355633802818e-06,
|
| 565 |
+
"loss": 1.631,
|
| 566 |
+
"step": 46500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 2.59,
|
| 570 |
+
"learning_rate": 6.9028755868544595e-06,
|
| 571 |
+
"loss": 1.6445,
|
| 572 |
+
"step": 47000
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 2.61,
|
| 576 |
+
"learning_rate": 6.444395539906104e-06,
|
| 577 |
+
"loss": 1.6401,
|
| 578 |
+
"step": 47500
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.64,
|
| 582 |
+
"learning_rate": 5.9859154929577465e-06,
|
| 583 |
+
"loss": 1.6463,
|
| 584 |
+
"step": 48000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 2.67,
|
| 588 |
+
"learning_rate": 5.52743544600939e-06,
|
| 589 |
+
"loss": 1.6307,
|
| 590 |
+
"step": 48500
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 2.7,
|
| 594 |
+
"learning_rate": 5.068955399061033e-06,
|
| 595 |
+
"loss": 1.6453,
|
| 596 |
+
"step": 49000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 2.72,
|
| 600 |
+
"learning_rate": 4.610475352112676e-06,
|
| 601 |
+
"loss": 1.6415,
|
| 602 |
+
"step": 49500
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 2.75,
|
| 606 |
+
"learning_rate": 4.15199530516432e-06,
|
| 607 |
+
"loss": 1.628,
|
| 608 |
+
"step": 50000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 2.78,
|
| 612 |
+
"learning_rate": 3.693515258215963e-06,
|
| 613 |
+
"loss": 1.6362,
|
| 614 |
+
"step": 50500
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 2.81,
|
| 618 |
+
"learning_rate": 3.2350352112676055e-06,
|
| 619 |
+
"loss": 1.6241,
|
| 620 |
+
"step": 51000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.83,
|
| 624 |
+
"learning_rate": 2.776555164319249e-06,
|
| 625 |
+
"loss": 1.6352,
|
| 626 |
+
"step": 51500
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 2.86,
|
| 630 |
+
"learning_rate": 2.318075117370892e-06,
|
| 631 |
+
"loss": 1.6413,
|
| 632 |
+
"step": 52000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 2.89,
|
| 636 |
+
"learning_rate": 1.8595950704225353e-06,
|
| 637 |
+
"loss": 1.6281,
|
| 638 |
+
"step": 52500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 2.92,
|
| 642 |
+
"learning_rate": 1.4011150234741783e-06,
|
| 643 |
+
"loss": 1.6331,
|
| 644 |
+
"step": 53000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 2.94,
|
| 648 |
+
"learning_rate": 9.426349765258218e-07,
|
| 649 |
+
"loss": 1.6384,
|
| 650 |
+
"step": 53500
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 2.97,
|
| 654 |
+
"learning_rate": 4.841549295774648e-07,
|
| 655 |
+
"loss": 1.6336,
|
| 656 |
+
"step": 54000
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 3.0,
|
| 660 |
+
"learning_rate": 2.5674882629107985e-08,
|
| 661 |
+
"loss": 1.6306,
|
| 662 |
+
"step": 54500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 3.0,
|
| 666 |
+
"step": 54528,
|
| 667 |
+
"total_flos": 1.722156986294784e+17,
|
| 668 |
+
"train_loss": 1.8530674359188393,
|
| 669 |
+
"train_runtime": 31139.3919,
|
| 670 |
+
"train_samples_per_second": 21.012,
|
| 671 |
+
"train_steps_per_second": 1.751
|
| 672 |
+
}
|
| 673 |
+
],
|
| 674 |
+
"max_steps": 54528,
|
| 675 |
+
"num_train_epochs": 3,
|
| 676 |
+
"total_flos": 1.722156986294784e+17,
|
| 677 |
+
"trial_name": null,
|
| 678 |
+
"trial_params": null
|
| 679 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|