End of training
Browse files- README.md +79 -0
- config.json +32 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- runs/Nov12_15-27-02_DESKTOP-A45193E/events.out.tfevents.1699795624.DESKTOP-A45193E +3 -0
- special_tokens_map.json +23 -0
- spiece.model +3 -0
- tokenizer_config.json +38 -0
- trainer_state.json +1428 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: google/mt5-small
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: text-translit-detector-ru
|
| 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 |
+
# text-translit-detector-ru
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.0393
|
| 19 |
+
- Mean Distance: 0
|
| 20 |
+
- Max Distance: 1
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 0.0001
|
| 40 |
+
- train_batch_size: 15
|
| 41 |
+
- eval_batch_size: 15
|
| 42 |
+
- seed: 42
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 46 |
+
- num_epochs: 20
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Mean Distance | Max Distance |
|
| 51 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------------:|:------------:|
|
| 52 |
+
| 0.2324 | 1.0 | 2664 | 0.1072 | 0 | 1 |
|
| 53 |
+
| 0.0151 | 2.0 | 5328 | 0.0436 | 0 | 1 |
|
| 54 |
+
| 0.0094 | 3.0 | 7992 | 0.0241 | 0 | 1 |
|
| 55 |
+
| 0.0056 | 4.0 | 10656 | 0.0309 | 0 | 1 |
|
| 56 |
+
| 0.0068 | 5.0 | 13320 | 0.0356 | 0 | 1 |
|
| 57 |
+
| 0.0041 | 6.0 | 15984 | 0.0186 | 0 | 1 |
|
| 58 |
+
| 0.0034 | 7.0 | 18648 | 0.0426 | 0 | 1 |
|
| 59 |
+
| 0.0043 | 8.0 | 21312 | 0.0172 | 0 | 1 |
|
| 60 |
+
| 0.004 | 9.0 | 23976 | 0.0272 | 0 | 1 |
|
| 61 |
+
| 0.0005 | 10.0 | 26640 | 0.0333 | 0 | 1 |
|
| 62 |
+
| 0.0025 | 11.0 | 29304 | 0.0358 | 0 | 1 |
|
| 63 |
+
| 0.0021 | 12.0 | 31968 | 0.0474 | 0 | 1 |
|
| 64 |
+
| 0.0007 | 13.0 | 34632 | 0.0402 | 0 | 1 |
|
| 65 |
+
| 0.0017 | 14.0 | 37296 | 0.0392 | 0 | 1 |
|
| 66 |
+
| 0.0007 | 15.0 | 39960 | 0.0394 | 0 | 1 |
|
| 67 |
+
| 0.0013 | 16.0 | 42624 | 0.0442 | 0 | 1 |
|
| 68 |
+
| 0.0002 | 17.0 | 45288 | 0.0443 | 0 | 1 |
|
| 69 |
+
| 0.0013 | 18.0 | 47952 | 0.0389 | 0 | 1 |
|
| 70 |
+
| 0.0001 | 19.0 | 50616 | 0.0412 | 0 | 1 |
|
| 71 |
+
| 0.0001 | 20.0 | 53280 | 0.0393 | 0 | 1 |
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
### Framework versions
|
| 75 |
+
|
| 76 |
+
- Transformers 4.35.0
|
| 77 |
+
- Pytorch 2.1.0+cu118
|
| 78 |
+
- Datasets 2.14.6
|
| 79 |
+
- Tokenizers 0.14.1
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/mt5-small",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MT5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 1024,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 512,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "gelu_new",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "gated-gelu",
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": true,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "mt5",
|
| 20 |
+
"num_decoder_layers": 8,
|
| 21 |
+
"num_heads": 6,
|
| 22 |
+
"num_layers": 8,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"relative_attention_max_distance": 128,
|
| 25 |
+
"relative_attention_num_buckets": 32,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"tokenizer_class": "T5Tokenizer",
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.35.0",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 250112
|
| 32 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.35.0"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:139f4efafa81328de028fe45cfd22391527b568ecc61cf081db24d84a0d357e1
|
| 3 |
+
size 1200729512
|
runs/Nov12_15-27-02_DESKTOP-A45193E/events.out.tfevents.1699795624.DESKTOP-A45193E
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a516146ba1a3a0134d3be7ecde0b3b4703f4834cc0427d2afc7dedce56be6d9
|
| 3 |
+
size 44274
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": {
|
| 3 |
+
"content": "</s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"pad_token": {
|
| 10 |
+
"content": "<pad>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
|
| 3 |
+
size 4309802
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "</s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<unk>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
}
|
| 27 |
+
},
|
| 28 |
+
"additional_special_tokens": [],
|
| 29 |
+
"clean_up_tokenization_spaces": true,
|
| 30 |
+
"eos_token": "</s>",
|
| 31 |
+
"extra_ids": 0,
|
| 32 |
+
"legacy": true,
|
| 33 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 34 |
+
"pad_token": "<pad>",
|
| 35 |
+
"sp_model_kwargs": {},
|
| 36 |
+
"tokenizer_class": "T5Tokenizer",
|
| 37 |
+
"unk_token": "<unk>"
|
| 38 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1428 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 53280,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 1.876876876876877e-08,
|
| 14 |
+
"loss": 26.3774,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.1,
|
| 19 |
+
"learning_rate": 5.011261261261262e-06,
|
| 20 |
+
"loss": 28.5448,
|
| 21 |
+
"step": 267
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.2,
|
| 25 |
+
"learning_rate": 1.0022522522522524e-05,
|
| 26 |
+
"loss": 27.0258,
|
| 27 |
+
"step": 534
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.3,
|
| 31 |
+
"learning_rate": 1.5033783783783784e-05,
|
| 32 |
+
"loss": 22.7776,
|
| 33 |
+
"step": 801
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.4,
|
| 37 |
+
"learning_rate": 2.0045045045045048e-05,
|
| 38 |
+
"loss": 17.4592,
|
| 39 |
+
"step": 1068
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.5,
|
| 43 |
+
"learning_rate": 2.505630630630631e-05,
|
| 44 |
+
"loss": 8.3509,
|
| 45 |
+
"step": 1335
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.6,
|
| 49 |
+
"learning_rate": 3.006756756756757e-05,
|
| 50 |
+
"loss": 0.8438,
|
| 51 |
+
"step": 1602
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.7,
|
| 55 |
+
"learning_rate": 3.507882882882883e-05,
|
| 56 |
+
"loss": 0.3406,
|
| 57 |
+
"step": 1869
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.8,
|
| 61 |
+
"learning_rate": 4.0090090090090096e-05,
|
| 62 |
+
"loss": 0.2968,
|
| 63 |
+
"step": 2136
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.9,
|
| 67 |
+
"learning_rate": 4.510135135135135e-05,
|
| 68 |
+
"loss": 0.2324,
|
| 69 |
+
"step": 2403
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.0,
|
| 73 |
+
"eval_loss": 0.10719971358776093,
|
| 74 |
+
"eval_max_distance": 1,
|
| 75 |
+
"eval_mean_distance": 0,
|
| 76 |
+
"eval_runtime": 1.1818,
|
| 77 |
+
"eval_samples_per_second": 302.937,
|
| 78 |
+
"eval_steps_per_second": 20.309,
|
| 79 |
+
"step": 2664
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.0,
|
| 83 |
+
"learning_rate": 5.011261261261262e-05,
|
| 84 |
+
"loss": 0.122,
|
| 85 |
+
"step": 2670
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 1.1,
|
| 89 |
+
"learning_rate": 5.512387387387388e-05,
|
| 90 |
+
"loss": 0.1234,
|
| 91 |
+
"step": 2937
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 1.2,
|
| 95 |
+
"learning_rate": 6.013513513513514e-05,
|
| 96 |
+
"loss": 0.1377,
|
| 97 |
+
"step": 3204
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 1.3,
|
| 101 |
+
"learning_rate": 6.514639639639641e-05,
|
| 102 |
+
"loss": 0.0721,
|
| 103 |
+
"step": 3471
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 1.4,
|
| 107 |
+
"learning_rate": 7.015765765765766e-05,
|
| 108 |
+
"loss": 0.0447,
|
| 109 |
+
"step": 3738
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.5,
|
| 113 |
+
"learning_rate": 7.516891891891891e-05,
|
| 114 |
+
"loss": 0.0262,
|
| 115 |
+
"step": 4005
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 1.6,
|
| 119 |
+
"learning_rate": 8.018018018018019e-05,
|
| 120 |
+
"loss": 0.0262,
|
| 121 |
+
"step": 4272
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.7,
|
| 125 |
+
"learning_rate": 8.519144144144144e-05,
|
| 126 |
+
"loss": 0.0235,
|
| 127 |
+
"step": 4539
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 1.8,
|
| 131 |
+
"learning_rate": 9.02027027027027e-05,
|
| 132 |
+
"loss": 0.0163,
|
| 133 |
+
"step": 4806
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 1.9,
|
| 137 |
+
"learning_rate": 9.521396396396397e-05,
|
| 138 |
+
"loss": 0.0151,
|
| 139 |
+
"step": 5073
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 2.0,
|
| 143 |
+
"eval_loss": 0.04358534514904022,
|
| 144 |
+
"eval_max_distance": 1,
|
| 145 |
+
"eval_mean_distance": 0,
|
| 146 |
+
"eval_runtime": 0.906,
|
| 147 |
+
"eval_samples_per_second": 395.165,
|
| 148 |
+
"eval_steps_per_second": 26.492,
|
| 149 |
+
"step": 5328
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 2.0,
|
| 153 |
+
"learning_rate": 9.997497497497498e-05,
|
| 154 |
+
"loss": 0.014,
|
| 155 |
+
"step": 5340
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 2.1,
|
| 159 |
+
"learning_rate": 9.941816816816817e-05,
|
| 160 |
+
"loss": 0.0136,
|
| 161 |
+
"step": 5607
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 2.2,
|
| 165 |
+
"learning_rate": 9.886136136136137e-05,
|
| 166 |
+
"loss": 0.007,
|
| 167 |
+
"step": 5874
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 2.31,
|
| 171 |
+
"learning_rate": 9.830455455455457e-05,
|
| 172 |
+
"loss": 0.0144,
|
| 173 |
+
"step": 6141
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 2.41,
|
| 177 |
+
"learning_rate": 9.774774774774775e-05,
|
| 178 |
+
"loss": 0.008,
|
| 179 |
+
"step": 6408
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 2.51,
|
| 183 |
+
"learning_rate": 9.719094094094095e-05,
|
| 184 |
+
"loss": 0.0109,
|
| 185 |
+
"step": 6675
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 2.61,
|
| 189 |
+
"learning_rate": 9.663413413413414e-05,
|
| 190 |
+
"loss": 0.0141,
|
| 191 |
+
"step": 6942
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.71,
|
| 195 |
+
"learning_rate": 9.607732732732732e-05,
|
| 196 |
+
"loss": 0.011,
|
| 197 |
+
"step": 7209
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 2.81,
|
| 201 |
+
"learning_rate": 9.552052052052053e-05,
|
| 202 |
+
"loss": 0.0136,
|
| 203 |
+
"step": 7476
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 2.91,
|
| 207 |
+
"learning_rate": 9.496371371371372e-05,
|
| 208 |
+
"loss": 0.0094,
|
| 209 |
+
"step": 7743
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 3.0,
|
| 213 |
+
"eval_loss": 0.024132976308465004,
|
| 214 |
+
"eval_max_distance": 1,
|
| 215 |
+
"eval_mean_distance": 0,
|
| 216 |
+
"eval_runtime": 0.9049,
|
| 217 |
+
"eval_samples_per_second": 395.615,
|
| 218 |
+
"eval_steps_per_second": 26.522,
|
| 219 |
+
"step": 7992
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 3.01,
|
| 223 |
+
"learning_rate": 9.440690690690692e-05,
|
| 224 |
+
"loss": 0.0158,
|
| 225 |
+
"step": 8010
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 3.11,
|
| 229 |
+
"learning_rate": 9.38501001001001e-05,
|
| 230 |
+
"loss": 0.0085,
|
| 231 |
+
"step": 8277
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 3.21,
|
| 235 |
+
"learning_rate": 9.329329329329329e-05,
|
| 236 |
+
"loss": 0.0074,
|
| 237 |
+
"step": 8544
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 3.31,
|
| 241 |
+
"learning_rate": 9.27364864864865e-05,
|
| 242 |
+
"loss": 0.0069,
|
| 243 |
+
"step": 8811
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 3.41,
|
| 247 |
+
"learning_rate": 9.217967967967968e-05,
|
| 248 |
+
"loss": 0.0049,
|
| 249 |
+
"step": 9078
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 3.51,
|
| 253 |
+
"learning_rate": 9.162287287287288e-05,
|
| 254 |
+
"loss": 0.0045,
|
| 255 |
+
"step": 9345
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 3.61,
|
| 259 |
+
"learning_rate": 9.106606606606607e-05,
|
| 260 |
+
"loss": 0.0053,
|
| 261 |
+
"step": 9612
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 3.71,
|
| 265 |
+
"learning_rate": 9.050925925925925e-05,
|
| 266 |
+
"loss": 0.0069,
|
| 267 |
+
"step": 9879
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 3.81,
|
| 271 |
+
"learning_rate": 8.995245245245245e-05,
|
| 272 |
+
"loss": 0.0067,
|
| 273 |
+
"step": 10146
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 3.91,
|
| 277 |
+
"learning_rate": 8.939564564564565e-05,
|
| 278 |
+
"loss": 0.0056,
|
| 279 |
+
"step": 10413
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 4.0,
|
| 283 |
+
"eval_loss": 0.030885161831974983,
|
| 284 |
+
"eval_max_distance": 1,
|
| 285 |
+
"eval_mean_distance": 0,
|
| 286 |
+
"eval_runtime": 0.9782,
|
| 287 |
+
"eval_samples_per_second": 365.991,
|
| 288 |
+
"eval_steps_per_second": 24.536,
|
| 289 |
+
"step": 10656
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 4.01,
|
| 293 |
+
"learning_rate": 8.883883883883885e-05,
|
| 294 |
+
"loss": 0.0057,
|
| 295 |
+
"step": 10680
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 4.11,
|
| 299 |
+
"learning_rate": 8.828203203203204e-05,
|
| 300 |
+
"loss": 0.0018,
|
| 301 |
+
"step": 10947
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 4.21,
|
| 305 |
+
"learning_rate": 8.772522522522522e-05,
|
| 306 |
+
"loss": 0.0034,
|
| 307 |
+
"step": 11214
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 4.31,
|
| 311 |
+
"learning_rate": 8.716841841841842e-05,
|
| 312 |
+
"loss": 0.0074,
|
| 313 |
+
"step": 11481
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 4.41,
|
| 317 |
+
"learning_rate": 8.661161161161162e-05,
|
| 318 |
+
"loss": 0.002,
|
| 319 |
+
"step": 11748
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 4.51,
|
| 323 |
+
"learning_rate": 8.605480480480482e-05,
|
| 324 |
+
"loss": 0.0121,
|
| 325 |
+
"step": 12015
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 4.61,
|
| 329 |
+
"learning_rate": 8.5497997997998e-05,
|
| 330 |
+
"loss": 0.0049,
|
| 331 |
+
"step": 12282
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 4.71,
|
| 335 |
+
"learning_rate": 8.49411911911912e-05,
|
| 336 |
+
"loss": 0.0045,
|
| 337 |
+
"step": 12549
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 4.81,
|
| 341 |
+
"learning_rate": 8.438438438438439e-05,
|
| 342 |
+
"loss": 0.0022,
|
| 343 |
+
"step": 12816
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 4.91,
|
| 347 |
+
"learning_rate": 8.382757757757757e-05,
|
| 348 |
+
"loss": 0.0068,
|
| 349 |
+
"step": 13083
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 5.0,
|
| 353 |
+
"eval_loss": 0.03561040014028549,
|
| 354 |
+
"eval_max_distance": 1,
|
| 355 |
+
"eval_mean_distance": 0,
|
| 356 |
+
"eval_runtime": 0.882,
|
| 357 |
+
"eval_samples_per_second": 405.884,
|
| 358 |
+
"eval_steps_per_second": 27.21,
|
| 359 |
+
"step": 13320
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 5.01,
|
| 363 |
+
"learning_rate": 8.327077077077078e-05,
|
| 364 |
+
"loss": 0.0063,
|
| 365 |
+
"step": 13350
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 5.11,
|
| 369 |
+
"learning_rate": 8.271396396396397e-05,
|
| 370 |
+
"loss": 0.002,
|
| 371 |
+
"step": 13617
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 5.21,
|
| 375 |
+
"learning_rate": 8.215715715715717e-05,
|
| 376 |
+
"loss": 0.007,
|
| 377 |
+
"step": 13884
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 5.31,
|
| 381 |
+
"learning_rate": 8.160035035035035e-05,
|
| 382 |
+
"loss": 0.0036,
|
| 383 |
+
"step": 14151
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 5.41,
|
| 387 |
+
"learning_rate": 8.104354354354354e-05,
|
| 388 |
+
"loss": 0.0036,
|
| 389 |
+
"step": 14418
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 5.51,
|
| 393 |
+
"learning_rate": 8.048673673673675e-05,
|
| 394 |
+
"loss": 0.0087,
|
| 395 |
+
"step": 14685
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 5.61,
|
| 399 |
+
"learning_rate": 7.992992992992994e-05,
|
| 400 |
+
"loss": 0.0013,
|
| 401 |
+
"step": 14952
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 5.71,
|
| 405 |
+
"learning_rate": 7.937312312312313e-05,
|
| 406 |
+
"loss": 0.0031,
|
| 407 |
+
"step": 15219
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 5.81,
|
| 411 |
+
"learning_rate": 7.881631631631632e-05,
|
| 412 |
+
"loss": 0.0031,
|
| 413 |
+
"step": 15486
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 5.91,
|
| 417 |
+
"learning_rate": 7.82595095095095e-05,
|
| 418 |
+
"loss": 0.0041,
|
| 419 |
+
"step": 15753
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 6.0,
|
| 423 |
+
"eval_loss": 0.018554789945483208,
|
| 424 |
+
"eval_max_distance": 1,
|
| 425 |
+
"eval_mean_distance": 0,
|
| 426 |
+
"eval_runtime": 0.8772,
|
| 427 |
+
"eval_samples_per_second": 408.133,
|
| 428 |
+
"eval_steps_per_second": 27.361,
|
| 429 |
+
"step": 15984
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 6.01,
|
| 433 |
+
"learning_rate": 7.77027027027027e-05,
|
| 434 |
+
"loss": 0.0044,
|
| 435 |
+
"step": 16020
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 6.11,
|
| 439 |
+
"learning_rate": 7.71458958958959e-05,
|
| 440 |
+
"loss": 0.0012,
|
| 441 |
+
"step": 16287
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 6.21,
|
| 445 |
+
"learning_rate": 7.65890890890891e-05,
|
| 446 |
+
"loss": 0.0036,
|
| 447 |
+
"step": 16554
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 6.31,
|
| 451 |
+
"learning_rate": 7.603228228228229e-05,
|
| 452 |
+
"loss": 0.0028,
|
| 453 |
+
"step": 16821
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 6.41,
|
| 457 |
+
"learning_rate": 7.547547547547547e-05,
|
| 458 |
+
"loss": 0.0039,
|
| 459 |
+
"step": 17088
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 6.51,
|
| 463 |
+
"learning_rate": 7.491866866866867e-05,
|
| 464 |
+
"loss": 0.0013,
|
| 465 |
+
"step": 17355
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 6.61,
|
| 469 |
+
"learning_rate": 7.436186186186187e-05,
|
| 470 |
+
"loss": 0.0026,
|
| 471 |
+
"step": 17622
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 6.72,
|
| 475 |
+
"learning_rate": 7.380505505505507e-05,
|
| 476 |
+
"loss": 0.0015,
|
| 477 |
+
"step": 17889
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 6.82,
|
| 481 |
+
"learning_rate": 7.324824824824825e-05,
|
| 482 |
+
"loss": 0.0009,
|
| 483 |
+
"step": 18156
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 6.92,
|
| 487 |
+
"learning_rate": 7.269144144144144e-05,
|
| 488 |
+
"loss": 0.0034,
|
| 489 |
+
"step": 18423
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 7.0,
|
| 493 |
+
"eval_loss": 0.04260706901550293,
|
| 494 |
+
"eval_max_distance": 1,
|
| 495 |
+
"eval_mean_distance": 0,
|
| 496 |
+
"eval_runtime": 0.9016,
|
| 497 |
+
"eval_samples_per_second": 397.069,
|
| 498 |
+
"eval_steps_per_second": 26.619,
|
| 499 |
+
"step": 18648
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 7.02,
|
| 503 |
+
"learning_rate": 7.213463463463464e-05,
|
| 504 |
+
"loss": 0.0027,
|
| 505 |
+
"step": 18690
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 7.12,
|
| 509 |
+
"learning_rate": 7.157782782782782e-05,
|
| 510 |
+
"loss": 0.0018,
|
| 511 |
+
"step": 18957
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 7.22,
|
| 515 |
+
"learning_rate": 7.102102102102103e-05,
|
| 516 |
+
"loss": 0.0024,
|
| 517 |
+
"step": 19224
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 7.32,
|
| 521 |
+
"learning_rate": 7.046421421421422e-05,
|
| 522 |
+
"loss": 0.0021,
|
| 523 |
+
"step": 19491
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 7.42,
|
| 527 |
+
"learning_rate": 6.99074074074074e-05,
|
| 528 |
+
"loss": 0.0017,
|
| 529 |
+
"step": 19758
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 7.52,
|
| 533 |
+
"learning_rate": 6.93506006006006e-05,
|
| 534 |
+
"loss": 0.0013,
|
| 535 |
+
"step": 20025
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 7.62,
|
| 539 |
+
"learning_rate": 6.879379379379379e-05,
|
| 540 |
+
"loss": 0.0025,
|
| 541 |
+
"step": 20292
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 7.72,
|
| 545 |
+
"learning_rate": 6.8236986986987e-05,
|
| 546 |
+
"loss": 0.0017,
|
| 547 |
+
"step": 20559
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 7.82,
|
| 551 |
+
"learning_rate": 6.768018018018019e-05,
|
| 552 |
+
"loss": 0.0022,
|
| 553 |
+
"step": 20826
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 7.92,
|
| 557 |
+
"learning_rate": 6.712337337337337e-05,
|
| 558 |
+
"loss": 0.0043,
|
| 559 |
+
"step": 21093
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 8.0,
|
| 563 |
+
"eval_loss": 0.017180927097797394,
|
| 564 |
+
"eval_max_distance": 1,
|
| 565 |
+
"eval_mean_distance": 0,
|
| 566 |
+
"eval_runtime": 0.8803,
|
| 567 |
+
"eval_samples_per_second": 406.66,
|
| 568 |
+
"eval_steps_per_second": 27.262,
|
| 569 |
+
"step": 21312
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 8.02,
|
| 573 |
+
"learning_rate": 6.656656656656657e-05,
|
| 574 |
+
"loss": 0.0035,
|
| 575 |
+
"step": 21360
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 8.12,
|
| 579 |
+
"learning_rate": 6.600975975975976e-05,
|
| 580 |
+
"loss": 0.0024,
|
| 581 |
+
"step": 21627
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 8.22,
|
| 585 |
+
"learning_rate": 6.545295295295295e-05,
|
| 586 |
+
"loss": 0.0036,
|
| 587 |
+
"step": 21894
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 8.32,
|
| 591 |
+
"learning_rate": 6.489614614614615e-05,
|
| 592 |
+
"loss": 0.0034,
|
| 593 |
+
"step": 22161
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 8.42,
|
| 597 |
+
"learning_rate": 6.433933933933934e-05,
|
| 598 |
+
"loss": 0.002,
|
| 599 |
+
"step": 22428
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 8.52,
|
| 603 |
+
"learning_rate": 6.378253253253254e-05,
|
| 604 |
+
"loss": 0.0029,
|
| 605 |
+
"step": 22695
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 8.62,
|
| 609 |
+
"learning_rate": 6.322572572572572e-05,
|
| 610 |
+
"loss": 0.002,
|
| 611 |
+
"step": 22962
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 8.72,
|
| 615 |
+
"learning_rate": 6.266891891891892e-05,
|
| 616 |
+
"loss": 0.0011,
|
| 617 |
+
"step": 23229
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 8.82,
|
| 621 |
+
"learning_rate": 6.211211211211212e-05,
|
| 622 |
+
"loss": 0.0006,
|
| 623 |
+
"step": 23496
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 8.92,
|
| 627 |
+
"learning_rate": 6.15553053053053e-05,
|
| 628 |
+
"loss": 0.004,
|
| 629 |
+
"step": 23763
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 9.0,
|
| 633 |
+
"eval_loss": 0.027217011898756027,
|
| 634 |
+
"eval_max_distance": 1,
|
| 635 |
+
"eval_mean_distance": 0,
|
| 636 |
+
"eval_runtime": 0.8897,
|
| 637 |
+
"eval_samples_per_second": 402.398,
|
| 638 |
+
"eval_steps_per_second": 26.976,
|
| 639 |
+
"step": 23976
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 9.02,
|
| 643 |
+
"learning_rate": 6.0998498498498503e-05,
|
| 644 |
+
"loss": 0.0038,
|
| 645 |
+
"step": 24030
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 9.12,
|
| 649 |
+
"learning_rate": 6.0441691691691695e-05,
|
| 650 |
+
"loss": 0.0022,
|
| 651 |
+
"step": 24297
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 9.22,
|
| 655 |
+
"learning_rate": 5.988488488488489e-05,
|
| 656 |
+
"loss": 0.0011,
|
| 657 |
+
"step": 24564
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 9.32,
|
| 661 |
+
"learning_rate": 5.932807807807807e-05,
|
| 662 |
+
"loss": 0.0013,
|
| 663 |
+
"step": 24831
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 9.42,
|
| 667 |
+
"learning_rate": 5.877127127127128e-05,
|
| 668 |
+
"loss": 0.0014,
|
| 669 |
+
"step": 25098
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 9.52,
|
| 673 |
+
"learning_rate": 5.821446446446447e-05,
|
| 674 |
+
"loss": 0.0037,
|
| 675 |
+
"step": 25365
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 9.62,
|
| 679 |
+
"learning_rate": 5.765765765765766e-05,
|
| 680 |
+
"loss": 0.0011,
|
| 681 |
+
"step": 25632
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 9.72,
|
| 685 |
+
"learning_rate": 5.7100850850850854e-05,
|
| 686 |
+
"loss": 0.0028,
|
| 687 |
+
"step": 25899
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 9.82,
|
| 691 |
+
"learning_rate": 5.654404404404404e-05,
|
| 692 |
+
"loss": 0.0012,
|
| 693 |
+
"step": 26166
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 9.92,
|
| 697 |
+
"learning_rate": 5.5987237237237245e-05,
|
| 698 |
+
"loss": 0.0005,
|
| 699 |
+
"step": 26433
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 10.0,
|
| 703 |
+
"eval_loss": 0.033312857151031494,
|
| 704 |
+
"eval_max_distance": 1,
|
| 705 |
+
"eval_mean_distance": 0,
|
| 706 |
+
"eval_runtime": 0.9102,
|
| 707 |
+
"eval_samples_per_second": 393.315,
|
| 708 |
+
"eval_steps_per_second": 26.367,
|
| 709 |
+
"step": 26640
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 10.02,
|
| 713 |
+
"learning_rate": 5.543043043043044e-05,
|
| 714 |
+
"loss": 0.0023,
|
| 715 |
+
"step": 26700
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 10.12,
|
| 719 |
+
"learning_rate": 5.487362362362363e-05,
|
| 720 |
+
"loss": 0.0032,
|
| 721 |
+
"step": 26967
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 10.22,
|
| 725 |
+
"learning_rate": 5.431681681681682e-05,
|
| 726 |
+
"loss": 0.0013,
|
| 727 |
+
"step": 27234
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 10.32,
|
| 731 |
+
"learning_rate": 5.3760010010010006e-05,
|
| 732 |
+
"loss": 0.0009,
|
| 733 |
+
"step": 27501
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 10.42,
|
| 737 |
+
"learning_rate": 5.320320320320321e-05,
|
| 738 |
+
"loss": 0.0039,
|
| 739 |
+
"step": 27768
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 10.52,
|
| 743 |
+
"learning_rate": 5.2646396396396403e-05,
|
| 744 |
+
"loss": 0.0008,
|
| 745 |
+
"step": 28035
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 10.62,
|
| 749 |
+
"learning_rate": 5.2089589589589595e-05,
|
| 750 |
+
"loss": 0.0009,
|
| 751 |
+
"step": 28302
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 10.72,
|
| 755 |
+
"learning_rate": 5.153278278278279e-05,
|
| 756 |
+
"loss": 0.002,
|
| 757 |
+
"step": 28569
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 10.82,
|
| 761 |
+
"learning_rate": 5.097597597597597e-05,
|
| 762 |
+
"loss": 0.0006,
|
| 763 |
+
"step": 28836
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 10.92,
|
| 767 |
+
"learning_rate": 5.0419169169169165e-05,
|
| 768 |
+
"loss": 0.0025,
|
| 769 |
+
"step": 29103
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 11.0,
|
| 773 |
+
"eval_loss": 0.03584469109773636,
|
| 774 |
+
"eval_max_distance": 1,
|
| 775 |
+
"eval_mean_distance": 0,
|
| 776 |
+
"eval_runtime": 0.8813,
|
| 777 |
+
"eval_samples_per_second": 406.214,
|
| 778 |
+
"eval_steps_per_second": 27.232,
|
| 779 |
+
"step": 29304
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 11.02,
|
| 783 |
+
"learning_rate": 4.9862362362362363e-05,
|
| 784 |
+
"loss": 0.0041,
|
| 785 |
+
"step": 29370
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 11.12,
|
| 789 |
+
"learning_rate": 4.930555555555556e-05,
|
| 790 |
+
"loss": 0.0002,
|
| 791 |
+
"step": 29637
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 11.23,
|
| 795 |
+
"learning_rate": 4.8748748748748754e-05,
|
| 796 |
+
"loss": 0.0001,
|
| 797 |
+
"step": 29904
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 11.33,
|
| 801 |
+
"learning_rate": 4.819194194194194e-05,
|
| 802 |
+
"loss": 0.0001,
|
| 803 |
+
"step": 30171
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 11.43,
|
| 807 |
+
"learning_rate": 4.763513513513514e-05,
|
| 808 |
+
"loss": 0.0003,
|
| 809 |
+
"step": 30438
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 11.53,
|
| 813 |
+
"learning_rate": 4.707832832832833e-05,
|
| 814 |
+
"loss": 0.003,
|
| 815 |
+
"step": 30705
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 11.63,
|
| 819 |
+
"learning_rate": 4.652152152152152e-05,
|
| 820 |
+
"loss": 0.0002,
|
| 821 |
+
"step": 30972
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 11.73,
|
| 825 |
+
"learning_rate": 4.596471471471472e-05,
|
| 826 |
+
"loss": 0.0037,
|
| 827 |
+
"step": 31239
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 11.83,
|
| 831 |
+
"learning_rate": 4.540790790790791e-05,
|
| 832 |
+
"loss": 0.0014,
|
| 833 |
+
"step": 31506
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 11.93,
|
| 837 |
+
"learning_rate": 4.48511011011011e-05,
|
| 838 |
+
"loss": 0.0021,
|
| 839 |
+
"step": 31773
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 12.0,
|
| 843 |
+
"eval_loss": 0.04740298539400101,
|
| 844 |
+
"eval_max_distance": 1,
|
| 845 |
+
"eval_mean_distance": 0,
|
| 846 |
+
"eval_runtime": 0.881,
|
| 847 |
+
"eval_samples_per_second": 406.347,
|
| 848 |
+
"eval_steps_per_second": 27.241,
|
| 849 |
+
"step": 31968
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 12.03,
|
| 853 |
+
"learning_rate": 4.42942942942943e-05,
|
| 854 |
+
"loss": 0.0006,
|
| 855 |
+
"step": 32040
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 12.13,
|
| 859 |
+
"learning_rate": 4.373748748748749e-05,
|
| 860 |
+
"loss": 0.0007,
|
| 861 |
+
"step": 32307
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 12.23,
|
| 865 |
+
"learning_rate": 4.318068068068069e-05,
|
| 866 |
+
"loss": 0.0015,
|
| 867 |
+
"step": 32574
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 12.33,
|
| 871 |
+
"learning_rate": 4.262387387387388e-05,
|
| 872 |
+
"loss": 0.0014,
|
| 873 |
+
"step": 32841
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 12.43,
|
| 877 |
+
"learning_rate": 4.2067067067067065e-05,
|
| 878 |
+
"loss": 0.0012,
|
| 879 |
+
"step": 33108
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 12.53,
|
| 883 |
+
"learning_rate": 4.1510260260260263e-05,
|
| 884 |
+
"loss": 0.0019,
|
| 885 |
+
"step": 33375
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 12.63,
|
| 889 |
+
"learning_rate": 4.0953453453453455e-05,
|
| 890 |
+
"loss": 0.0011,
|
| 891 |
+
"step": 33642
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 12.73,
|
| 895 |
+
"learning_rate": 4.039664664664665e-05,
|
| 896 |
+
"loss": 0.0016,
|
| 897 |
+
"step": 33909
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 12.83,
|
| 901 |
+
"learning_rate": 3.9839839839839846e-05,
|
| 902 |
+
"loss": 0.0001,
|
| 903 |
+
"step": 34176
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 12.93,
|
| 907 |
+
"learning_rate": 3.928303303303303e-05,
|
| 908 |
+
"loss": 0.0007,
|
| 909 |
+
"step": 34443
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 13.0,
|
| 913 |
+
"eval_loss": 0.0401989221572876,
|
| 914 |
+
"eval_max_distance": 1,
|
| 915 |
+
"eval_mean_distance": 0,
|
| 916 |
+
"eval_runtime": 0.887,
|
| 917 |
+
"eval_samples_per_second": 403.585,
|
| 918 |
+
"eval_steps_per_second": 27.056,
|
| 919 |
+
"step": 34632
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 13.03,
|
| 923 |
+
"learning_rate": 3.8726226226226223e-05,
|
| 924 |
+
"loss": 0.0006,
|
| 925 |
+
"step": 34710
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 13.13,
|
| 929 |
+
"learning_rate": 3.816941941941942e-05,
|
| 930 |
+
"loss": 0.0002,
|
| 931 |
+
"step": 34977
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 13.23,
|
| 935 |
+
"learning_rate": 3.7612612612612614e-05,
|
| 936 |
+
"loss": 0.0012,
|
| 937 |
+
"step": 35244
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 13.33,
|
| 941 |
+
"learning_rate": 3.705580580580581e-05,
|
| 942 |
+
"loss": 0.0027,
|
| 943 |
+
"step": 35511
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 13.43,
|
| 947 |
+
"learning_rate": 3.6498998998999e-05,
|
| 948 |
+
"loss": 0.0014,
|
| 949 |
+
"step": 35778
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 13.53,
|
| 953 |
+
"learning_rate": 3.594219219219219e-05,
|
| 954 |
+
"loss": 0.0006,
|
| 955 |
+
"step": 36045
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 13.63,
|
| 959 |
+
"learning_rate": 3.538538538538539e-05,
|
| 960 |
+
"loss": 0.0023,
|
| 961 |
+
"step": 36312
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 13.73,
|
| 965 |
+
"learning_rate": 3.482857857857858e-05,
|
| 966 |
+
"loss": 0.0,
|
| 967 |
+
"step": 36579
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 13.83,
|
| 971 |
+
"learning_rate": 3.427177177177177e-05,
|
| 972 |
+
"loss": 0.0056,
|
| 973 |
+
"step": 36846
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 13.93,
|
| 977 |
+
"learning_rate": 3.3714964964964965e-05,
|
| 978 |
+
"loss": 0.0017,
|
| 979 |
+
"step": 37113
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 14.0,
|
| 983 |
+
"eval_loss": 0.03919493407011032,
|
| 984 |
+
"eval_max_distance": 1,
|
| 985 |
+
"eval_mean_distance": 0,
|
| 986 |
+
"eval_runtime": 0.8793,
|
| 987 |
+
"eval_samples_per_second": 407.126,
|
| 988 |
+
"eval_steps_per_second": 27.293,
|
| 989 |
+
"step": 37296
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 14.03,
|
| 993 |
+
"learning_rate": 3.315815815815816e-05,
|
| 994 |
+
"loss": 0.0002,
|
| 995 |
+
"step": 37380
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 14.13,
|
| 999 |
+
"learning_rate": 3.260135135135135e-05,
|
| 1000 |
+
"loss": 0.0012,
|
| 1001 |
+
"step": 37647
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 14.23,
|
| 1005 |
+
"learning_rate": 3.204454454454455e-05,
|
| 1006 |
+
"loss": 0.0009,
|
| 1007 |
+
"step": 37914
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 14.33,
|
| 1011 |
+
"learning_rate": 3.148773773773774e-05,
|
| 1012 |
+
"loss": 0.0006,
|
| 1013 |
+
"step": 38181
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 14.43,
|
| 1017 |
+
"learning_rate": 3.093093093093093e-05,
|
| 1018 |
+
"loss": 0.0006,
|
| 1019 |
+
"step": 38448
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 14.53,
|
| 1023 |
+
"learning_rate": 3.0374124124124127e-05,
|
| 1024 |
+
"loss": 0.0015,
|
| 1025 |
+
"step": 38715
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 14.63,
|
| 1029 |
+
"learning_rate": 2.9817317317317315e-05,
|
| 1030 |
+
"loss": 0.0014,
|
| 1031 |
+
"step": 38982
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 14.73,
|
| 1035 |
+
"learning_rate": 2.9260510510510514e-05,
|
| 1036 |
+
"loss": 0.0009,
|
| 1037 |
+
"step": 39249
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 14.83,
|
| 1041 |
+
"learning_rate": 2.8703703703703706e-05,
|
| 1042 |
+
"loss": 0.0016,
|
| 1043 |
+
"step": 39516
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 14.93,
|
| 1047 |
+
"learning_rate": 2.8146896896896895e-05,
|
| 1048 |
+
"loss": 0.0007,
|
| 1049 |
+
"step": 39783
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 15.0,
|
| 1053 |
+
"eval_loss": 0.03942238539457321,
|
| 1054 |
+
"eval_max_distance": 1,
|
| 1055 |
+
"eval_mean_distance": 0,
|
| 1056 |
+
"eval_runtime": 0.8858,
|
| 1057 |
+
"eval_samples_per_second": 404.155,
|
| 1058 |
+
"eval_steps_per_second": 27.094,
|
| 1059 |
+
"step": 39960
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 15.03,
|
| 1063 |
+
"learning_rate": 2.7590090090090094e-05,
|
| 1064 |
+
"loss": 0.0003,
|
| 1065 |
+
"step": 40050
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 15.13,
|
| 1069 |
+
"learning_rate": 2.7033283283283286e-05,
|
| 1070 |
+
"loss": 0.0002,
|
| 1071 |
+
"step": 40317
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 15.23,
|
| 1075 |
+
"learning_rate": 2.6476476476476474e-05,
|
| 1076 |
+
"loss": 0.0002,
|
| 1077 |
+
"step": 40584
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 15.33,
|
| 1081 |
+
"learning_rate": 2.5919669669669673e-05,
|
| 1082 |
+
"loss": 0.0,
|
| 1083 |
+
"step": 40851
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 15.43,
|
| 1087 |
+
"learning_rate": 2.536286286286286e-05,
|
| 1088 |
+
"loss": 0.0017,
|
| 1089 |
+
"step": 41118
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 15.53,
|
| 1093 |
+
"learning_rate": 2.4806056056056057e-05,
|
| 1094 |
+
"loss": 0.0002,
|
| 1095 |
+
"step": 41385
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 15.64,
|
| 1099 |
+
"learning_rate": 2.4249249249249252e-05,
|
| 1100 |
+
"loss": 0.0007,
|
| 1101 |
+
"step": 41652
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 15.74,
|
| 1105 |
+
"learning_rate": 2.3692442442442444e-05,
|
| 1106 |
+
"loss": 0.0001,
|
| 1107 |
+
"step": 41919
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 15.84,
|
| 1111 |
+
"learning_rate": 2.3135635635635636e-05,
|
| 1112 |
+
"loss": 0.0011,
|
| 1113 |
+
"step": 42186
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 15.94,
|
| 1117 |
+
"learning_rate": 2.2578828828828828e-05,
|
| 1118 |
+
"loss": 0.0013,
|
| 1119 |
+
"step": 42453
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 16.0,
|
| 1123 |
+
"eval_loss": 0.04424785450100899,
|
| 1124 |
+
"eval_max_distance": 1,
|
| 1125 |
+
"eval_mean_distance": 0,
|
| 1126 |
+
"eval_runtime": 0.8837,
|
| 1127 |
+
"eval_samples_per_second": 405.133,
|
| 1128 |
+
"eval_steps_per_second": 27.16,
|
| 1129 |
+
"step": 42624
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 16.04,
|
| 1133 |
+
"learning_rate": 2.2022022022022024e-05,
|
| 1134 |
+
"loss": 0.0006,
|
| 1135 |
+
"step": 42720
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 16.14,
|
| 1139 |
+
"learning_rate": 2.146521521521522e-05,
|
| 1140 |
+
"loss": 0.0013,
|
| 1141 |
+
"step": 42987
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 16.24,
|
| 1145 |
+
"learning_rate": 2.0908408408408408e-05,
|
| 1146 |
+
"loss": 0.0005,
|
| 1147 |
+
"step": 43254
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 16.34,
|
| 1151 |
+
"learning_rate": 2.0351601601601603e-05,
|
| 1152 |
+
"loss": 0.0008,
|
| 1153 |
+
"step": 43521
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 16.44,
|
| 1157 |
+
"learning_rate": 1.9794794794794795e-05,
|
| 1158 |
+
"loss": 0.0003,
|
| 1159 |
+
"step": 43788
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 16.54,
|
| 1163 |
+
"learning_rate": 1.9237987987987987e-05,
|
| 1164 |
+
"loss": 0.0001,
|
| 1165 |
+
"step": 44055
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 16.64,
|
| 1169 |
+
"learning_rate": 1.8681181181181182e-05,
|
| 1170 |
+
"loss": 0.0005,
|
| 1171 |
+
"step": 44322
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 16.74,
|
| 1175 |
+
"learning_rate": 1.8124374374374374e-05,
|
| 1176 |
+
"loss": 0.0026,
|
| 1177 |
+
"step": 44589
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 16.84,
|
| 1181 |
+
"learning_rate": 1.756756756756757e-05,
|
| 1182 |
+
"loss": 0.0008,
|
| 1183 |
+
"step": 44856
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 16.94,
|
| 1187 |
+
"learning_rate": 1.701076076076076e-05,
|
| 1188 |
+
"loss": 0.0002,
|
| 1189 |
+
"step": 45123
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 17.0,
|
| 1193 |
+
"eval_loss": 0.04427039995789528,
|
| 1194 |
+
"eval_max_distance": 1,
|
| 1195 |
+
"eval_mean_distance": 0,
|
| 1196 |
+
"eval_runtime": 0.8885,
|
| 1197 |
+
"eval_samples_per_second": 402.91,
|
| 1198 |
+
"eval_steps_per_second": 27.011,
|
| 1199 |
+
"step": 45288
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 17.04,
|
| 1203 |
+
"learning_rate": 1.6453953953953954e-05,
|
| 1204 |
+
"loss": 0.0001,
|
| 1205 |
+
"step": 45390
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 17.14,
|
| 1209 |
+
"learning_rate": 1.589714714714715e-05,
|
| 1210 |
+
"loss": 0.0004,
|
| 1211 |
+
"step": 45657
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 17.24,
|
| 1215 |
+
"learning_rate": 1.534034034034034e-05,
|
| 1216 |
+
"loss": 0.0001,
|
| 1217 |
+
"step": 45924
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 17.34,
|
| 1221 |
+
"learning_rate": 1.4783533533533533e-05,
|
| 1222 |
+
"loss": 0.0011,
|
| 1223 |
+
"step": 46191
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 17.44,
|
| 1227 |
+
"learning_rate": 1.4226726726726727e-05,
|
| 1228 |
+
"loss": 0.001,
|
| 1229 |
+
"step": 46458
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 17.54,
|
| 1233 |
+
"learning_rate": 1.3669919919919922e-05,
|
| 1234 |
+
"loss": 0.0003,
|
| 1235 |
+
"step": 46725
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 17.64,
|
| 1239 |
+
"learning_rate": 1.3113113113113112e-05,
|
| 1240 |
+
"loss": 0.0007,
|
| 1241 |
+
"step": 46992
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 17.74,
|
| 1245 |
+
"learning_rate": 1.2556306306306306e-05,
|
| 1246 |
+
"loss": 0.0002,
|
| 1247 |
+
"step": 47259
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 17.84,
|
| 1251 |
+
"learning_rate": 1.19994994994995e-05,
|
| 1252 |
+
"loss": 0.0024,
|
| 1253 |
+
"step": 47526
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 17.94,
|
| 1257 |
+
"learning_rate": 1.1442692692692693e-05,
|
| 1258 |
+
"loss": 0.0013,
|
| 1259 |
+
"step": 47793
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 18.0,
|
| 1263 |
+
"eval_loss": 0.038870543241500854,
|
| 1264 |
+
"eval_max_distance": 1,
|
| 1265 |
+
"eval_mean_distance": 0,
|
| 1266 |
+
"eval_runtime": 0.8826,
|
| 1267 |
+
"eval_samples_per_second": 405.621,
|
| 1268 |
+
"eval_steps_per_second": 27.192,
|
| 1269 |
+
"step": 47952
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 18.04,
|
| 1273 |
+
"learning_rate": 1.0885885885885887e-05,
|
| 1274 |
+
"loss": 0.0005,
|
| 1275 |
+
"step": 48060
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 18.14,
|
| 1279 |
+
"learning_rate": 1.0329079079079079e-05,
|
| 1280 |
+
"loss": 0.0,
|
| 1281 |
+
"step": 48327
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 18.24,
|
| 1285 |
+
"learning_rate": 9.772272272272273e-06,
|
| 1286 |
+
"loss": 0.0005,
|
| 1287 |
+
"step": 48594
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 18.34,
|
| 1291 |
+
"learning_rate": 9.215465465465466e-06,
|
| 1292 |
+
"loss": 0.0017,
|
| 1293 |
+
"step": 48861
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 18.44,
|
| 1297 |
+
"learning_rate": 8.65865865865866e-06,
|
| 1298 |
+
"loss": 0.0003,
|
| 1299 |
+
"step": 49128
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 18.54,
|
| 1303 |
+
"learning_rate": 8.101851851851852e-06,
|
| 1304 |
+
"loss": 0.0012,
|
| 1305 |
+
"step": 49395
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 18.64,
|
| 1309 |
+
"learning_rate": 7.545045045045046e-06,
|
| 1310 |
+
"loss": 0.0,
|
| 1311 |
+
"step": 49662
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 18.74,
|
| 1315 |
+
"learning_rate": 6.9882382382382385e-06,
|
| 1316 |
+
"loss": 0.0011,
|
| 1317 |
+
"step": 49929
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 18.84,
|
| 1321 |
+
"learning_rate": 6.431431431431431e-06,
|
| 1322 |
+
"loss": 0.0013,
|
| 1323 |
+
"step": 50196
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 18.94,
|
| 1327 |
+
"learning_rate": 5.874624624624625e-06,
|
| 1328 |
+
"loss": 0.0001,
|
| 1329 |
+
"step": 50463
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 19.0,
|
| 1333 |
+
"eval_loss": 0.04122824966907501,
|
| 1334 |
+
"eval_max_distance": 1,
|
| 1335 |
+
"eval_mean_distance": 0,
|
| 1336 |
+
"eval_runtime": 0.8851,
|
| 1337 |
+
"eval_samples_per_second": 404.458,
|
| 1338 |
+
"eval_steps_per_second": 27.114,
|
| 1339 |
+
"step": 50616
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 19.04,
|
| 1343 |
+
"learning_rate": 5.317817817817819e-06,
|
| 1344 |
+
"loss": 0.0012,
|
| 1345 |
+
"step": 50730
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 19.14,
|
| 1349 |
+
"learning_rate": 4.7610110110110115e-06,
|
| 1350 |
+
"loss": 0.0001,
|
| 1351 |
+
"step": 50997
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 19.24,
|
| 1355 |
+
"learning_rate": 4.204204204204204e-06,
|
| 1356 |
+
"loss": 0.0002,
|
| 1357 |
+
"step": 51264
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 19.34,
|
| 1361 |
+
"learning_rate": 3.647397397397397e-06,
|
| 1362 |
+
"loss": 0.0,
|
| 1363 |
+
"step": 51531
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 19.44,
|
| 1367 |
+
"learning_rate": 3.090590590590591e-06,
|
| 1368 |
+
"loss": 0.0003,
|
| 1369 |
+
"step": 51798
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 19.54,
|
| 1373 |
+
"learning_rate": 2.533783783783784e-06,
|
| 1374 |
+
"loss": 0.0021,
|
| 1375 |
+
"step": 52065
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 19.64,
|
| 1379 |
+
"learning_rate": 1.976976976976977e-06,
|
| 1380 |
+
"loss": 0.0,
|
| 1381 |
+
"step": 52332
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 19.74,
|
| 1385 |
+
"learning_rate": 1.4201701701701704e-06,
|
| 1386 |
+
"loss": 0.0001,
|
| 1387 |
+
"step": 52599
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 19.84,
|
| 1391 |
+
"learning_rate": 8.633633633633634e-07,
|
| 1392 |
+
"loss": 0.0009,
|
| 1393 |
+
"step": 52866
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"epoch": 19.94,
|
| 1397 |
+
"learning_rate": 3.0655655655655656e-07,
|
| 1398 |
+
"loss": 0.0001,
|
| 1399 |
+
"step": 53133
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 20.0,
|
| 1403 |
+
"eval_loss": 0.0392613410949707,
|
| 1404 |
+
"eval_max_distance": 1,
|
| 1405 |
+
"eval_mean_distance": 0,
|
| 1406 |
+
"eval_runtime": 0.8819,
|
| 1407 |
+
"eval_samples_per_second": 405.923,
|
| 1408 |
+
"eval_steps_per_second": 27.213,
|
| 1409 |
+
"step": 53280
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 20.0,
|
| 1413 |
+
"step": 53280,
|
| 1414 |
+
"total_flos": 3.004276018040832e+16,
|
| 1415 |
+
"train_loss": 0.5359516274340651,
|
| 1416 |
+
"train_runtime": 5327.8303,
|
| 1417 |
+
"train_samples_per_second": 149.956,
|
| 1418 |
+
"train_steps_per_second": 10.0
|
| 1419 |
+
}
|
| 1420 |
+
],
|
| 1421 |
+
"logging_steps": 267,
|
| 1422 |
+
"max_steps": 53280,
|
| 1423 |
+
"num_train_epochs": 20,
|
| 1424 |
+
"save_steps": 533,
|
| 1425 |
+
"total_flos": 3.004276018040832e+16,
|
| 1426 |
+
"trial_name": null,
|
| 1427 |
+
"trial_params": null
|
| 1428 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c96f8fdbf9fd73c249b43d3bffe70a51dda3b7a8b070e37888600604b3e00bcb
|
| 3 |
+
size 4664
|