ethio-xlmr base
Browse files- README.md +54 -0
- all_results.json +14 -0
- config.json +28 -0
- eval_results.json +9 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +15 -0
- tokenizer_config.json +21 -0
- train_results.json +8 -0
- trainer_state.json +1219 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: xlm-roberta-base
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: ethio_xlmr_base
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# ethio_xlmr_base
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 3.1618
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 5e-05
|
| 38 |
+
- train_batch_size: 48
|
| 39 |
+
- eval_batch_size: 24
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 10.0
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
### Framework versions
|
| 50 |
+
|
| 51 |
+
- Transformers 4.33.1
|
| 52 |
+
- Pytorch 2.0.1+cu117
|
| 53 |
+
- Datasets 2.14.4
|
| 54 |
+
- Tokenizers 0.13.3
|
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_loss": 3.161780834197998,
|
| 4 |
+
"eval_runtime": 2455.7469,
|
| 5 |
+
"eval_samples": 181215,
|
| 6 |
+
"eval_samples_per_second": 73.792,
|
| 7 |
+
"eval_steps_per_second": 3.075,
|
| 8 |
+
"perplexity": 23.612608650107834,
|
| 9 |
+
"train_loss": 3.866458753945259,
|
| 10 |
+
"train_runtime": 140181.055,
|
| 11 |
+
"train_samples": 724891,
|
| 12 |
+
"train_samples_per_second": 51.711,
|
| 13 |
+
"train_steps_per_second": 1.077
|
| 14 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "xlm-roberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"XLMRobertaForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "xlm-roberta",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"output_past": true,
|
| 21 |
+
"pad_token_id": 1,
|
| 22 |
+
"position_embedding_type": "absolute",
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.33.1",
|
| 25 |
+
"type_vocab_size": 1,
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 70002
|
| 28 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_loss": 3.161780834197998,
|
| 4 |
+
"eval_runtime": 2455.7469,
|
| 5 |
+
"eval_samples": 181215,
|
| 6 |
+
"eval_samples_per_second": 73.792,
|
| 7 |
+
"eval_steps_per_second": 3.075,
|
| 8 |
+
"perplexity": 23.612608650107834
|
| 9 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3832e592e5a98405330ae1bb8c89ffe30cdbdd8c80ec74b335c3c1a31a58fc64
|
| 3 |
+
size 1119169989
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77084c3681ca7e8c3ca12fe1023eca75344c2806ad9bf61bccfb948a1986e635
|
| 3 |
+
size 559570229
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0aac8a4b57325652a09cc5f0a740dc1b42028cd06d67b0437bf6c4d6df94a325
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55b61d99d2ed2001312d6b9e3c2f2b0f464d7204ceb9acba6d539ea534cc898f
|
| 3 |
+
size 627
|
sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17222963fdc50cff64fd9b0ec00ef13b14d0b62c02bf3aa717fde09a9c784cfa
|
| 3 |
+
size 1630156
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"mask_token": {
|
| 7 |
+
"__type": "AddedToken",
|
| 8 |
+
"content": "<mask>",
|
| 9 |
+
"lstrip": true,
|
| 10 |
+
"normalized": true,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"single_word": false
|
| 13 |
+
},
|
| 14 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 15 |
+
"pad_token": "<pad>",
|
| 16 |
+
"sep_token": "</s>",
|
| 17 |
+
"sp_model_kwargs": {},
|
| 18 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 19 |
+
"unk_token": "<unk>",
|
| 20 |
+
"use_fast": true
|
| 21 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 3.866458753945259,
|
| 4 |
+
"train_runtime": 140181.055,
|
| 5 |
+
"train_samples": 724891,
|
| 6 |
+
"train_samples_per_second": 51.711,
|
| 7 |
+
"train_steps_per_second": 1.077
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1219 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.621639517944643,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 100000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"learning_rate": 4.983445901205139e-05,
|
| 14 |
+
"loss": 7.9646,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.07,
|
| 19 |
+
"learning_rate": 4.9668918024102774e-05,
|
| 20 |
+
"loss": 7.067,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.1,
|
| 25 |
+
"learning_rate": 4.950337703615415e-05,
|
| 26 |
+
"loss": 6.6489,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.13,
|
| 31 |
+
"learning_rate": 4.933783604820554e-05,
|
| 32 |
+
"loss": 6.4267,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.17,
|
| 37 |
+
"learning_rate": 4.9172295060256924e-05,
|
| 38 |
+
"loss": 6.2394,
|
| 39 |
+
"step": 2500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.2,
|
| 43 |
+
"learning_rate": 4.900675407230831e-05,
|
| 44 |
+
"loss": 6.1117,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.23,
|
| 49 |
+
"learning_rate": 4.884121308435969e-05,
|
| 50 |
+
"loss": 5.9807,
|
| 51 |
+
"step": 3500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.26,
|
| 55 |
+
"learning_rate": 4.8675672096411075e-05,
|
| 56 |
+
"loss": 5.8532,
|
| 57 |
+
"step": 4000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.3,
|
| 61 |
+
"learning_rate": 4.851013110846246e-05,
|
| 62 |
+
"loss": 5.7589,
|
| 63 |
+
"step": 4500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.33,
|
| 67 |
+
"learning_rate": 4.8344590120513846e-05,
|
| 68 |
+
"loss": 5.661,
|
| 69 |
+
"step": 5000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.36,
|
| 73 |
+
"learning_rate": 4.8179049132565225e-05,
|
| 74 |
+
"loss": 5.5663,
|
| 75 |
+
"step": 5500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.4,
|
| 79 |
+
"learning_rate": 4.801350814461661e-05,
|
| 80 |
+
"loss": 5.5025,
|
| 81 |
+
"step": 6000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.43,
|
| 85 |
+
"learning_rate": 4.7847967156667996e-05,
|
| 86 |
+
"loss": 5.4251,
|
| 87 |
+
"step": 6500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.46,
|
| 91 |
+
"learning_rate": 4.768242616871938e-05,
|
| 92 |
+
"loss": 5.35,
|
| 93 |
+
"step": 7000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.5,
|
| 97 |
+
"learning_rate": 4.751688518077076e-05,
|
| 98 |
+
"loss": 5.2991,
|
| 99 |
+
"step": 7500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.53,
|
| 103 |
+
"learning_rate": 4.735134419282215e-05,
|
| 104 |
+
"loss": 5.2476,
|
| 105 |
+
"step": 8000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.56,
|
| 109 |
+
"learning_rate": 4.718580320487353e-05,
|
| 110 |
+
"loss": 5.1949,
|
| 111 |
+
"step": 8500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.6,
|
| 115 |
+
"learning_rate": 4.702026221692492e-05,
|
| 116 |
+
"loss": 5.1361,
|
| 117 |
+
"step": 9000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.63,
|
| 121 |
+
"learning_rate": 4.68547212289763e-05,
|
| 122 |
+
"loss": 5.0988,
|
| 123 |
+
"step": 9500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.66,
|
| 127 |
+
"learning_rate": 4.668918024102768e-05,
|
| 128 |
+
"loss": 5.0639,
|
| 129 |
+
"step": 10000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.7,
|
| 133 |
+
"learning_rate": 4.652363925307907e-05,
|
| 134 |
+
"loss": 5.037,
|
| 135 |
+
"step": 10500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.73,
|
| 139 |
+
"learning_rate": 4.6358098265130454e-05,
|
| 140 |
+
"loss": 4.9896,
|
| 141 |
+
"step": 11000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.76,
|
| 145 |
+
"learning_rate": 4.619255727718183e-05,
|
| 146 |
+
"loss": 4.9501,
|
| 147 |
+
"step": 11500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.79,
|
| 151 |
+
"learning_rate": 4.602701628923322e-05,
|
| 152 |
+
"loss": 4.9465,
|
| 153 |
+
"step": 12000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.83,
|
| 157 |
+
"learning_rate": 4.58614753012846e-05,
|
| 158 |
+
"loss": 4.9,
|
| 159 |
+
"step": 12500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.86,
|
| 163 |
+
"learning_rate": 4.569593431333598e-05,
|
| 164 |
+
"loss": 4.8633,
|
| 165 |
+
"step": 13000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.89,
|
| 169 |
+
"learning_rate": 4.553039332538737e-05,
|
| 170 |
+
"loss": 4.8352,
|
| 171 |
+
"step": 13500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.93,
|
| 175 |
+
"learning_rate": 4.536485233743875e-05,
|
| 176 |
+
"loss": 4.7846,
|
| 177 |
+
"step": 14000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.96,
|
| 181 |
+
"learning_rate": 4.5199311349490134e-05,
|
| 182 |
+
"loss": 4.775,
|
| 183 |
+
"step": 14500
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.99,
|
| 187 |
+
"learning_rate": 4.503377036154152e-05,
|
| 188 |
+
"loss": 4.7556,
|
| 189 |
+
"step": 15000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.03,
|
| 193 |
+
"learning_rate": 4.48682293735929e-05,
|
| 194 |
+
"loss": 4.7332,
|
| 195 |
+
"step": 15500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.06,
|
| 199 |
+
"learning_rate": 4.4702688385644284e-05,
|
| 200 |
+
"loss": 4.7188,
|
| 201 |
+
"step": 16000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.09,
|
| 205 |
+
"learning_rate": 4.453714739769567e-05,
|
| 206 |
+
"loss": 4.6928,
|
| 207 |
+
"step": 16500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.13,
|
| 211 |
+
"learning_rate": 4.4371606409747055e-05,
|
| 212 |
+
"loss": 4.6792,
|
| 213 |
+
"step": 17000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.16,
|
| 217 |
+
"learning_rate": 4.4206065421798434e-05,
|
| 218 |
+
"loss": 4.6542,
|
| 219 |
+
"step": 17500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.19,
|
| 223 |
+
"learning_rate": 4.404052443384982e-05,
|
| 224 |
+
"loss": 4.6433,
|
| 225 |
+
"step": 18000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.23,
|
| 229 |
+
"learning_rate": 4.3874983445901206e-05,
|
| 230 |
+
"loss": 4.616,
|
| 231 |
+
"step": 18500
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.26,
|
| 235 |
+
"learning_rate": 4.370944245795259e-05,
|
| 236 |
+
"loss": 4.6071,
|
| 237 |
+
"step": 19000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.29,
|
| 241 |
+
"learning_rate": 4.354390147000397e-05,
|
| 242 |
+
"loss": 4.5814,
|
| 243 |
+
"step": 19500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.32,
|
| 247 |
+
"learning_rate": 4.3378360482055356e-05,
|
| 248 |
+
"loss": 4.5617,
|
| 249 |
+
"step": 20000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.36,
|
| 253 |
+
"learning_rate": 4.321281949410674e-05,
|
| 254 |
+
"loss": 4.5472,
|
| 255 |
+
"step": 20500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.39,
|
| 259 |
+
"learning_rate": 4.304727850615813e-05,
|
| 260 |
+
"loss": 4.5401,
|
| 261 |
+
"step": 21000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.42,
|
| 265 |
+
"learning_rate": 4.2881737518209507e-05,
|
| 266 |
+
"loss": 4.5001,
|
| 267 |
+
"step": 21500
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.46,
|
| 271 |
+
"learning_rate": 4.271619653026089e-05,
|
| 272 |
+
"loss": 4.4979,
|
| 273 |
+
"step": 22000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.49,
|
| 277 |
+
"learning_rate": 4.255065554231228e-05,
|
| 278 |
+
"loss": 4.4717,
|
| 279 |
+
"step": 22500
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.52,
|
| 283 |
+
"learning_rate": 4.2385114554363664e-05,
|
| 284 |
+
"loss": 4.4488,
|
| 285 |
+
"step": 23000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.56,
|
| 289 |
+
"learning_rate": 4.221957356641504e-05,
|
| 290 |
+
"loss": 4.4499,
|
| 291 |
+
"step": 23500
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 1.59,
|
| 295 |
+
"learning_rate": 4.205403257846643e-05,
|
| 296 |
+
"loss": 4.4122,
|
| 297 |
+
"step": 24000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.62,
|
| 301 |
+
"learning_rate": 4.1888491590517814e-05,
|
| 302 |
+
"loss": 4.4016,
|
| 303 |
+
"step": 24500
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.66,
|
| 307 |
+
"learning_rate": 4.17229506025692e-05,
|
| 308 |
+
"loss": 4.3926,
|
| 309 |
+
"step": 25000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.69,
|
| 313 |
+
"learning_rate": 4.155740961462058e-05,
|
| 314 |
+
"loss": 4.3787,
|
| 315 |
+
"step": 25500
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.72,
|
| 319 |
+
"learning_rate": 4.1391868626671964e-05,
|
| 320 |
+
"loss": 4.379,
|
| 321 |
+
"step": 26000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.75,
|
| 325 |
+
"learning_rate": 4.122632763872335e-05,
|
| 326 |
+
"loss": 4.3696,
|
| 327 |
+
"step": 26500
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.79,
|
| 331 |
+
"learning_rate": 4.1060786650774736e-05,
|
| 332 |
+
"loss": 4.3436,
|
| 333 |
+
"step": 27000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.82,
|
| 337 |
+
"learning_rate": 4.089524566282612e-05,
|
| 338 |
+
"loss": 4.3236,
|
| 339 |
+
"step": 27500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.85,
|
| 343 |
+
"learning_rate": 4.07297046748775e-05,
|
| 344 |
+
"loss": 4.3132,
|
| 345 |
+
"step": 28000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.89,
|
| 349 |
+
"learning_rate": 4.0564163686928886e-05,
|
| 350 |
+
"loss": 4.3176,
|
| 351 |
+
"step": 28500
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.92,
|
| 355 |
+
"learning_rate": 4.039862269898027e-05,
|
| 356 |
+
"loss": 4.2956,
|
| 357 |
+
"step": 29000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 1.95,
|
| 361 |
+
"learning_rate": 4.023308171103166e-05,
|
| 362 |
+
"loss": 4.2884,
|
| 363 |
+
"step": 29500
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.99,
|
| 367 |
+
"learning_rate": 4.0067540723083036e-05,
|
| 368 |
+
"loss": 4.2735,
|
| 369 |
+
"step": 30000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 2.02,
|
| 373 |
+
"learning_rate": 3.990199973513442e-05,
|
| 374 |
+
"loss": 4.2596,
|
| 375 |
+
"step": 30500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 2.05,
|
| 379 |
+
"learning_rate": 3.973645874718581e-05,
|
| 380 |
+
"loss": 4.2534,
|
| 381 |
+
"step": 31000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.09,
|
| 385 |
+
"learning_rate": 3.9570917759237194e-05,
|
| 386 |
+
"loss": 4.2429,
|
| 387 |
+
"step": 31500
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 2.12,
|
| 391 |
+
"learning_rate": 3.940537677128857e-05,
|
| 392 |
+
"loss": 4.2193,
|
| 393 |
+
"step": 32000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 2.15,
|
| 397 |
+
"learning_rate": 3.923983578333996e-05,
|
| 398 |
+
"loss": 4.2025,
|
| 399 |
+
"step": 32500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 2.19,
|
| 403 |
+
"learning_rate": 3.9074294795391344e-05,
|
| 404 |
+
"loss": 4.1868,
|
| 405 |
+
"step": 33000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 2.22,
|
| 409 |
+
"learning_rate": 3.890875380744273e-05,
|
| 410 |
+
"loss": 4.1895,
|
| 411 |
+
"step": 33500
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 2.25,
|
| 415 |
+
"learning_rate": 3.874321281949411e-05,
|
| 416 |
+
"loss": 4.1681,
|
| 417 |
+
"step": 34000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 2.28,
|
| 421 |
+
"learning_rate": 3.8577671831545494e-05,
|
| 422 |
+
"loss": 4.18,
|
| 423 |
+
"step": 34500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.32,
|
| 427 |
+
"learning_rate": 3.841213084359688e-05,
|
| 428 |
+
"loss": 4.1666,
|
| 429 |
+
"step": 35000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.35,
|
| 433 |
+
"learning_rate": 3.8246589855648266e-05,
|
| 434 |
+
"loss": 4.136,
|
| 435 |
+
"step": 35500
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 2.38,
|
| 439 |
+
"learning_rate": 3.8081048867699645e-05,
|
| 440 |
+
"loss": 4.1456,
|
| 441 |
+
"step": 36000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 2.42,
|
| 445 |
+
"learning_rate": 3.791550787975103e-05,
|
| 446 |
+
"loss": 4.1194,
|
| 447 |
+
"step": 36500
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 2.45,
|
| 451 |
+
"learning_rate": 3.7749966891802416e-05,
|
| 452 |
+
"loss": 4.1111,
|
| 453 |
+
"step": 37000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 2.48,
|
| 457 |
+
"learning_rate": 3.7584425903853795e-05,
|
| 458 |
+
"loss": 4.092,
|
| 459 |
+
"step": 37500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.52,
|
| 463 |
+
"learning_rate": 3.741888491590518e-05,
|
| 464 |
+
"loss": 4.0972,
|
| 465 |
+
"step": 38000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.55,
|
| 469 |
+
"learning_rate": 3.7253343927956566e-05,
|
| 470 |
+
"loss": 4.0929,
|
| 471 |
+
"step": 38500
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.58,
|
| 475 |
+
"learning_rate": 3.7087802940007945e-05,
|
| 476 |
+
"loss": 4.0645,
|
| 477 |
+
"step": 39000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 2.62,
|
| 481 |
+
"learning_rate": 3.692226195205933e-05,
|
| 482 |
+
"loss": 4.0618,
|
| 483 |
+
"step": 39500
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.65,
|
| 487 |
+
"learning_rate": 3.675672096411072e-05,
|
| 488 |
+
"loss": 4.0674,
|
| 489 |
+
"step": 40000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.68,
|
| 493 |
+
"learning_rate": 3.6591179976162096e-05,
|
| 494 |
+
"loss": 4.0467,
|
| 495 |
+
"step": 40500
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 2.71,
|
| 499 |
+
"learning_rate": 3.642563898821348e-05,
|
| 500 |
+
"loss": 4.0345,
|
| 501 |
+
"step": 41000
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.75,
|
| 505 |
+
"learning_rate": 3.626009800026487e-05,
|
| 506 |
+
"loss": 4.01,
|
| 507 |
+
"step": 41500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 2.78,
|
| 511 |
+
"learning_rate": 3.6094557012316246e-05,
|
| 512 |
+
"loss": 4.0087,
|
| 513 |
+
"step": 42000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 2.81,
|
| 517 |
+
"learning_rate": 3.592901602436763e-05,
|
| 518 |
+
"loss": 4.0112,
|
| 519 |
+
"step": 42500
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 2.85,
|
| 523 |
+
"learning_rate": 3.576347503641902e-05,
|
| 524 |
+
"loss": 4.0137,
|
| 525 |
+
"step": 43000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 2.88,
|
| 529 |
+
"learning_rate": 3.55979340484704e-05,
|
| 530 |
+
"loss": 4.005,
|
| 531 |
+
"step": 43500
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 2.91,
|
| 535 |
+
"learning_rate": 3.543239306052178e-05,
|
| 536 |
+
"loss": 4.0055,
|
| 537 |
+
"step": 44000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 2.95,
|
| 541 |
+
"learning_rate": 3.526685207257317e-05,
|
| 542 |
+
"loss": 3.98,
|
| 543 |
+
"step": 44500
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 2.98,
|
| 547 |
+
"learning_rate": 3.5101311084624553e-05,
|
| 548 |
+
"loss": 3.9646,
|
| 549 |
+
"step": 45000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 3.01,
|
| 553 |
+
"learning_rate": 3.493577009667594e-05,
|
| 554 |
+
"loss": 3.9678,
|
| 555 |
+
"step": 45500
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 3.05,
|
| 559 |
+
"learning_rate": 3.477022910872732e-05,
|
| 560 |
+
"loss": 3.9427,
|
| 561 |
+
"step": 46000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 3.08,
|
| 565 |
+
"learning_rate": 3.4604688120778704e-05,
|
| 566 |
+
"loss": 3.9335,
|
| 567 |
+
"step": 46500
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 3.11,
|
| 571 |
+
"learning_rate": 3.443914713283009e-05,
|
| 572 |
+
"loss": 3.9361,
|
| 573 |
+
"step": 47000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 3.15,
|
| 577 |
+
"learning_rate": 3.4273606144881475e-05,
|
| 578 |
+
"loss": 3.9476,
|
| 579 |
+
"step": 47500
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 3.18,
|
| 583 |
+
"learning_rate": 3.4108065156932854e-05,
|
| 584 |
+
"loss": 3.924,
|
| 585 |
+
"step": 48000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 3.21,
|
| 589 |
+
"learning_rate": 3.394252416898424e-05,
|
| 590 |
+
"loss": 3.9141,
|
| 591 |
+
"step": 48500
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 3.24,
|
| 595 |
+
"learning_rate": 3.3776983181035626e-05,
|
| 596 |
+
"loss": 3.9092,
|
| 597 |
+
"step": 49000
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 3.28,
|
| 601 |
+
"learning_rate": 3.361144219308701e-05,
|
| 602 |
+
"loss": 3.8767,
|
| 603 |
+
"step": 49500
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 3.31,
|
| 607 |
+
"learning_rate": 3.344590120513839e-05,
|
| 608 |
+
"loss": 3.9022,
|
| 609 |
+
"step": 50000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 3.34,
|
| 613 |
+
"learning_rate": 3.3280360217189776e-05,
|
| 614 |
+
"loss": 3.8732,
|
| 615 |
+
"step": 50500
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 3.38,
|
| 619 |
+
"learning_rate": 3.311481922924116e-05,
|
| 620 |
+
"loss": 3.8522,
|
| 621 |
+
"step": 51000
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 3.41,
|
| 625 |
+
"learning_rate": 3.294927824129255e-05,
|
| 626 |
+
"loss": 3.8773,
|
| 627 |
+
"step": 51500
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 3.44,
|
| 631 |
+
"learning_rate": 3.2783737253343926e-05,
|
| 632 |
+
"loss": 3.8715,
|
| 633 |
+
"step": 52000
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 3.48,
|
| 637 |
+
"learning_rate": 3.261819626539531e-05,
|
| 638 |
+
"loss": 3.8549,
|
| 639 |
+
"step": 52500
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 3.51,
|
| 643 |
+
"learning_rate": 3.24526552774467e-05,
|
| 644 |
+
"loss": 3.8547,
|
| 645 |
+
"step": 53000
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 3.54,
|
| 649 |
+
"learning_rate": 3.228711428949808e-05,
|
| 650 |
+
"loss": 3.8408,
|
| 651 |
+
"step": 53500
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 3.58,
|
| 655 |
+
"learning_rate": 3.212157330154946e-05,
|
| 656 |
+
"loss": 3.8309,
|
| 657 |
+
"step": 54000
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 3.61,
|
| 661 |
+
"learning_rate": 3.195603231360085e-05,
|
| 662 |
+
"loss": 3.8275,
|
| 663 |
+
"step": 54500
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 3.64,
|
| 667 |
+
"learning_rate": 3.1790491325652234e-05,
|
| 668 |
+
"loss": 3.8257,
|
| 669 |
+
"step": 55000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 3.68,
|
| 673 |
+
"learning_rate": 3.162495033770362e-05,
|
| 674 |
+
"loss": 3.8233,
|
| 675 |
+
"step": 55500
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 3.71,
|
| 679 |
+
"learning_rate": 3.1459409349755005e-05,
|
| 680 |
+
"loss": 3.8184,
|
| 681 |
+
"step": 56000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 3.74,
|
| 685 |
+
"learning_rate": 3.1293868361806384e-05,
|
| 686 |
+
"loss": 3.7942,
|
| 687 |
+
"step": 56500
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 3.77,
|
| 691 |
+
"learning_rate": 3.112832737385777e-05,
|
| 692 |
+
"loss": 3.8072,
|
| 693 |
+
"step": 57000
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 3.81,
|
| 697 |
+
"learning_rate": 3.0962786385909155e-05,
|
| 698 |
+
"loss": 3.787,
|
| 699 |
+
"step": 57500
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 3.84,
|
| 703 |
+
"learning_rate": 3.079724539796054e-05,
|
| 704 |
+
"loss": 3.7954,
|
| 705 |
+
"step": 58000
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 3.87,
|
| 709 |
+
"learning_rate": 3.063170441001192e-05,
|
| 710 |
+
"loss": 3.7816,
|
| 711 |
+
"step": 58500
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 3.91,
|
| 715 |
+
"learning_rate": 3.0466163422063302e-05,
|
| 716 |
+
"loss": 3.7723,
|
| 717 |
+
"step": 59000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 3.94,
|
| 721 |
+
"learning_rate": 3.0300622434114688e-05,
|
| 722 |
+
"loss": 3.7713,
|
| 723 |
+
"step": 59500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 3.97,
|
| 727 |
+
"learning_rate": 3.0135081446166074e-05,
|
| 728 |
+
"loss": 3.7619,
|
| 729 |
+
"step": 60000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 4.01,
|
| 733 |
+
"learning_rate": 2.9969540458217453e-05,
|
| 734 |
+
"loss": 3.7479,
|
| 735 |
+
"step": 60500
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 4.04,
|
| 739 |
+
"learning_rate": 2.980399947026884e-05,
|
| 740 |
+
"loss": 3.7411,
|
| 741 |
+
"step": 61000
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 4.07,
|
| 745 |
+
"learning_rate": 2.9638458482320224e-05,
|
| 746 |
+
"loss": 3.7416,
|
| 747 |
+
"step": 61500
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 4.11,
|
| 751 |
+
"learning_rate": 2.947291749437161e-05,
|
| 752 |
+
"loss": 3.7423,
|
| 753 |
+
"step": 62000
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 4.14,
|
| 757 |
+
"learning_rate": 2.930737650642299e-05,
|
| 758 |
+
"loss": 3.7344,
|
| 759 |
+
"step": 62500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 4.17,
|
| 763 |
+
"learning_rate": 2.9141835518474375e-05,
|
| 764 |
+
"loss": 3.7244,
|
| 765 |
+
"step": 63000
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 4.2,
|
| 769 |
+
"learning_rate": 2.897629453052576e-05,
|
| 770 |
+
"loss": 3.739,
|
| 771 |
+
"step": 63500
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 4.24,
|
| 775 |
+
"learning_rate": 2.8810753542577146e-05,
|
| 776 |
+
"loss": 3.7142,
|
| 777 |
+
"step": 64000
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 4.27,
|
| 781 |
+
"learning_rate": 2.8645212554628525e-05,
|
| 782 |
+
"loss": 3.7158,
|
| 783 |
+
"step": 64500
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 4.3,
|
| 787 |
+
"learning_rate": 2.847967156667991e-05,
|
| 788 |
+
"loss": 3.7159,
|
| 789 |
+
"step": 65000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 4.34,
|
| 793 |
+
"learning_rate": 2.8314130578731296e-05,
|
| 794 |
+
"loss": 3.6938,
|
| 795 |
+
"step": 65500
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 4.37,
|
| 799 |
+
"learning_rate": 2.8148589590782682e-05,
|
| 800 |
+
"loss": 3.692,
|
| 801 |
+
"step": 66000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 4.4,
|
| 805 |
+
"learning_rate": 2.798304860283406e-05,
|
| 806 |
+
"loss": 3.6779,
|
| 807 |
+
"step": 66500
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 4.44,
|
| 811 |
+
"learning_rate": 2.7817507614885447e-05,
|
| 812 |
+
"loss": 3.6856,
|
| 813 |
+
"step": 67000
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 4.47,
|
| 817 |
+
"learning_rate": 2.7651966626936832e-05,
|
| 818 |
+
"loss": 3.6771,
|
| 819 |
+
"step": 67500
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 4.5,
|
| 823 |
+
"learning_rate": 2.7486425638988218e-05,
|
| 824 |
+
"loss": 3.672,
|
| 825 |
+
"step": 68000
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 4.54,
|
| 829 |
+
"learning_rate": 2.7320884651039597e-05,
|
| 830 |
+
"loss": 3.6788,
|
| 831 |
+
"step": 68500
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 4.57,
|
| 835 |
+
"learning_rate": 2.7155343663090983e-05,
|
| 836 |
+
"loss": 3.6562,
|
| 837 |
+
"step": 69000
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 4.6,
|
| 841 |
+
"learning_rate": 2.698980267514237e-05,
|
| 842 |
+
"loss": 3.6582,
|
| 843 |
+
"step": 69500
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 4.64,
|
| 847 |
+
"learning_rate": 2.682426168719375e-05,
|
| 848 |
+
"loss": 3.6605,
|
| 849 |
+
"step": 70000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 4.67,
|
| 853 |
+
"learning_rate": 2.6658720699245133e-05,
|
| 854 |
+
"loss": 3.6535,
|
| 855 |
+
"step": 70500
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 4.7,
|
| 859 |
+
"learning_rate": 2.649317971129652e-05,
|
| 860 |
+
"loss": 3.649,
|
| 861 |
+
"step": 71000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 4.73,
|
| 865 |
+
"learning_rate": 2.63276387233479e-05,
|
| 866 |
+
"loss": 3.6455,
|
| 867 |
+
"step": 71500
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 4.77,
|
| 871 |
+
"learning_rate": 2.6162097735399287e-05,
|
| 872 |
+
"loss": 3.6437,
|
| 873 |
+
"step": 72000
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 4.8,
|
| 877 |
+
"learning_rate": 2.599655674745067e-05,
|
| 878 |
+
"loss": 3.6402,
|
| 879 |
+
"step": 72500
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 4.83,
|
| 883 |
+
"learning_rate": 2.583101575950205e-05,
|
| 884 |
+
"loss": 3.6257,
|
| 885 |
+
"step": 73000
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 4.87,
|
| 889 |
+
"learning_rate": 2.5665474771553437e-05,
|
| 890 |
+
"loss": 3.6125,
|
| 891 |
+
"step": 73500
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 4.9,
|
| 895 |
+
"learning_rate": 2.5499933783604823e-05,
|
| 896 |
+
"loss": 3.6132,
|
| 897 |
+
"step": 74000
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 4.93,
|
| 901 |
+
"learning_rate": 2.5334392795656202e-05,
|
| 902 |
+
"loss": 3.612,
|
| 903 |
+
"step": 74500
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 4.97,
|
| 907 |
+
"learning_rate": 2.5168851807707588e-05,
|
| 908 |
+
"loss": 3.6139,
|
| 909 |
+
"step": 75000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 5.0,
|
| 913 |
+
"learning_rate": 2.5003310819758973e-05,
|
| 914 |
+
"loss": 3.5995,
|
| 915 |
+
"step": 75500
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 5.03,
|
| 919 |
+
"learning_rate": 2.4837769831810356e-05,
|
| 920 |
+
"loss": 3.6016,
|
| 921 |
+
"step": 76000
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 5.07,
|
| 925 |
+
"learning_rate": 2.467222884386174e-05,
|
| 926 |
+
"loss": 3.5882,
|
| 927 |
+
"step": 76500
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 5.1,
|
| 931 |
+
"learning_rate": 2.4506687855913124e-05,
|
| 932 |
+
"loss": 3.6023,
|
| 933 |
+
"step": 77000
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 5.13,
|
| 937 |
+
"learning_rate": 2.434114686796451e-05,
|
| 938 |
+
"loss": 3.6025,
|
| 939 |
+
"step": 77500
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 5.16,
|
| 943 |
+
"learning_rate": 2.417560588001589e-05,
|
| 944 |
+
"loss": 3.5897,
|
| 945 |
+
"step": 78000
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 5.2,
|
| 949 |
+
"learning_rate": 2.4010064892067277e-05,
|
| 950 |
+
"loss": 3.5767,
|
| 951 |
+
"step": 78500
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 5.23,
|
| 955 |
+
"learning_rate": 2.384452390411866e-05,
|
| 956 |
+
"loss": 3.5835,
|
| 957 |
+
"step": 79000
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 5.26,
|
| 961 |
+
"learning_rate": 2.3678982916170045e-05,
|
| 962 |
+
"loss": 3.5579,
|
| 963 |
+
"step": 79500
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 5.3,
|
| 967 |
+
"learning_rate": 2.3513441928221428e-05,
|
| 968 |
+
"loss": 3.5708,
|
| 969 |
+
"step": 80000
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 5.33,
|
| 973 |
+
"learning_rate": 2.3347900940272813e-05,
|
| 974 |
+
"loss": 3.5613,
|
| 975 |
+
"step": 80500
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 5.36,
|
| 979 |
+
"learning_rate": 2.3182359952324196e-05,
|
| 980 |
+
"loss": 3.5632,
|
| 981 |
+
"step": 81000
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 5.4,
|
| 985 |
+
"learning_rate": 2.301681896437558e-05,
|
| 986 |
+
"loss": 3.5688,
|
| 987 |
+
"step": 81500
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 5.43,
|
| 991 |
+
"learning_rate": 2.2851277976426967e-05,
|
| 992 |
+
"loss": 3.5563,
|
| 993 |
+
"step": 82000
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 5.46,
|
| 997 |
+
"learning_rate": 2.268573698847835e-05,
|
| 998 |
+
"loss": 3.5438,
|
| 999 |
+
"step": 82500
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 5.5,
|
| 1003 |
+
"learning_rate": 2.2520196000529735e-05,
|
| 1004 |
+
"loss": 3.5384,
|
| 1005 |
+
"step": 83000
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 5.53,
|
| 1009 |
+
"learning_rate": 2.2354655012581117e-05,
|
| 1010 |
+
"loss": 3.5491,
|
| 1011 |
+
"step": 83500
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 5.56,
|
| 1015 |
+
"learning_rate": 2.21891140246325e-05,
|
| 1016 |
+
"loss": 3.5491,
|
| 1017 |
+
"step": 84000
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 5.6,
|
| 1021 |
+
"learning_rate": 2.2023573036683885e-05,
|
| 1022 |
+
"loss": 3.5437,
|
| 1023 |
+
"step": 84500
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 5.63,
|
| 1027 |
+
"learning_rate": 2.1858032048735268e-05,
|
| 1028 |
+
"loss": 3.5335,
|
| 1029 |
+
"step": 85000
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 5.66,
|
| 1033 |
+
"learning_rate": 2.169249106078665e-05,
|
| 1034 |
+
"loss": 3.5302,
|
| 1035 |
+
"step": 85500
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 5.69,
|
| 1039 |
+
"learning_rate": 2.1526950072838036e-05,
|
| 1040 |
+
"loss": 3.5227,
|
| 1041 |
+
"step": 86000
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 5.73,
|
| 1045 |
+
"learning_rate": 2.1361409084889418e-05,
|
| 1046 |
+
"loss": 3.5239,
|
| 1047 |
+
"step": 86500
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 5.76,
|
| 1051 |
+
"learning_rate": 2.1195868096940804e-05,
|
| 1052 |
+
"loss": 3.5148,
|
| 1053 |
+
"step": 87000
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 5.79,
|
| 1057 |
+
"learning_rate": 2.1030327108992186e-05,
|
| 1058 |
+
"loss": 3.5282,
|
| 1059 |
+
"step": 87500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 5.83,
|
| 1063 |
+
"learning_rate": 2.0864786121043572e-05,
|
| 1064 |
+
"loss": 3.5222,
|
| 1065 |
+
"step": 88000
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 5.86,
|
| 1069 |
+
"learning_rate": 2.0699245133094954e-05,
|
| 1070 |
+
"loss": 3.5179,
|
| 1071 |
+
"step": 88500
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 5.89,
|
| 1075 |
+
"learning_rate": 2.053370414514634e-05,
|
| 1076 |
+
"loss": 3.4973,
|
| 1077 |
+
"step": 89000
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 5.93,
|
| 1081 |
+
"learning_rate": 2.0368163157197722e-05,
|
| 1082 |
+
"loss": 3.5072,
|
| 1083 |
+
"step": 89500
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 5.96,
|
| 1087 |
+
"learning_rate": 2.0202622169249108e-05,
|
| 1088 |
+
"loss": 3.5043,
|
| 1089 |
+
"step": 90000
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 5.99,
|
| 1093 |
+
"learning_rate": 2.003708118130049e-05,
|
| 1094 |
+
"loss": 3.5099,
|
| 1095 |
+
"step": 90500
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 6.03,
|
| 1099 |
+
"learning_rate": 1.9871540193351876e-05,
|
| 1100 |
+
"loss": 3.4962,
|
| 1101 |
+
"step": 91000
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 6.06,
|
| 1105 |
+
"learning_rate": 1.9705999205403258e-05,
|
| 1106 |
+
"loss": 3.4934,
|
| 1107 |
+
"step": 91500
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 6.09,
|
| 1111 |
+
"learning_rate": 1.9540458217454644e-05,
|
| 1112 |
+
"loss": 3.484,
|
| 1113 |
+
"step": 92000
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 6.13,
|
| 1117 |
+
"learning_rate": 1.9374917229506026e-05,
|
| 1118 |
+
"loss": 3.4683,
|
| 1119 |
+
"step": 92500
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 6.16,
|
| 1123 |
+
"learning_rate": 1.9209376241557412e-05,
|
| 1124 |
+
"loss": 3.4929,
|
| 1125 |
+
"step": 93000
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 6.19,
|
| 1129 |
+
"learning_rate": 1.9043835253608794e-05,
|
| 1130 |
+
"loss": 3.4759,
|
| 1131 |
+
"step": 93500
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 6.22,
|
| 1135 |
+
"learning_rate": 1.887829426566018e-05,
|
| 1136 |
+
"loss": 3.4733,
|
| 1137 |
+
"step": 94000
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 6.26,
|
| 1141 |
+
"learning_rate": 1.8712753277711562e-05,
|
| 1142 |
+
"loss": 3.4746,
|
| 1143 |
+
"step": 94500
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 6.29,
|
| 1147 |
+
"learning_rate": 1.8547212289762948e-05,
|
| 1148 |
+
"loss": 3.4734,
|
| 1149 |
+
"step": 95000
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 6.32,
|
| 1153 |
+
"learning_rate": 1.838167130181433e-05,
|
| 1154 |
+
"loss": 3.4738,
|
| 1155 |
+
"step": 95500
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 6.36,
|
| 1159 |
+
"learning_rate": 1.8216130313865716e-05,
|
| 1160 |
+
"loss": 3.4768,
|
| 1161 |
+
"step": 96000
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 6.39,
|
| 1165 |
+
"learning_rate": 1.80505893259171e-05,
|
| 1166 |
+
"loss": 3.4731,
|
| 1167 |
+
"step": 96500
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 6.42,
|
| 1171 |
+
"learning_rate": 1.7885048337968484e-05,
|
| 1172 |
+
"loss": 3.4659,
|
| 1173 |
+
"step": 97000
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 6.46,
|
| 1177 |
+
"learning_rate": 1.7719507350019866e-05,
|
| 1178 |
+
"loss": 3.4642,
|
| 1179 |
+
"step": 97500
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 6.49,
|
| 1183 |
+
"learning_rate": 1.755396636207125e-05,
|
| 1184 |
+
"loss": 3.4595,
|
| 1185 |
+
"step": 98000
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 6.52,
|
| 1189 |
+
"learning_rate": 1.738842537412263e-05,
|
| 1190 |
+
"loss": 3.4715,
|
| 1191 |
+
"step": 98500
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 6.56,
|
| 1195 |
+
"learning_rate": 1.7222884386174017e-05,
|
| 1196 |
+
"loss": 3.4457,
|
| 1197 |
+
"step": 99000
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 6.59,
|
| 1201 |
+
"learning_rate": 1.70573433982254e-05,
|
| 1202 |
+
"loss": 3.4621,
|
| 1203 |
+
"step": 99500
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 6.62,
|
| 1207 |
+
"learning_rate": 1.6891802410276785e-05,
|
| 1208 |
+
"loss": 3.446,
|
| 1209 |
+
"step": 100000
|
| 1210 |
+
}
|
| 1211 |
+
],
|
| 1212 |
+
"logging_steps": 500,
|
| 1213 |
+
"max_steps": 151020,
|
| 1214 |
+
"num_train_epochs": 10,
|
| 1215 |
+
"save_steps": 100000,
|
| 1216 |
+
"total_flos": 1.2639573579451392e+18,
|
| 1217 |
+
"trial_name": null,
|
| 1218 |
+
"trial_params": null
|
| 1219 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2377555161a9203790a40b5d774fd4a5ca2696bf3a21b4c2a8aa945588b63a1e
|
| 3 |
+
size 4027
|