Upload 13 files
Browse files- README.md +63 -3
- all_results.json +11 -0
- config.json +64 -0
- generation_config.json +16 -0
- model.safetensors +3 -0
- source.spm +0 -0
- special_tokens_map.json +5 -0
- target.spm +0 -0
- tokenizer_config.json +38 -0
- train_results.json +11 -0
- trainer_state.json +1908 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
CHANGED
|
@@ -1,3 +1,63 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: Helsinki-NLP/opus-mt-en-zh
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- zetavg/coct-en-zh-tw-translations-twp-300k
|
| 8 |
+
model-index:
|
| 9 |
+
- name: en-zhtw
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# en-zhtw
|
| 14 |
+
|
| 15 |
+
English-to-Traditional Chinese sentence translator
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-zh](https://huggingface.co/Helsinki-NLP/opus-mt-en-zh) on the [zetavg/coct-en-zh-tw-translations-twp-300k](https://huggingface.co/datasets/zetavg/coct-en-zh-tw-translations-twp-300k) dataset.
|
| 18 |
+
|
| 19 |
+
This is so it can output Traditional Chinese by default and make the translations more natural sounding.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
- input: English text only
|
| 24 |
+
- output: Traditional Chinese text translation
|
| 25 |
+
|
| 26 |
+
How to use:
|
| 27 |
+
|
| 28 |
+
```python
|
| 29 |
+
from transformers import pipeline
|
| 30 |
+
|
| 31 |
+
model_checkpoint = "agentlans/en-zhtw"
|
| 32 |
+
translator = pipeline("translation", model=model_checkpoint)
|
| 33 |
+
|
| 34 |
+
translator(["Even if you spend a day in Windsor you'll notice that it's a very multicultural city, yet still retaining a small town feel.", "Its main waterfront park stretches about 5 km (3.1 mi), from the 1929 Ambassador suspension bridge past the contemporary Windsor Sculpture Park."])
|
| 35 |
+
|
| 36 |
+
# [{'translation_text': '儘管在風沙住了一天,都會發現這裡是個非常多樣化的城市,但還是保留了一個小鎮的感覺。'}, {'translation_text': '從 1929 年的大使吊橋到今天的風雕公園,總長約 5 公里。'}]
|
| 37 |
+
```
|
| 38 |
+
|
| 39 |
+
## Intended uses & limitations
|
| 40 |
+
|
| 41 |
+
- English to Traditional Chinese translation
|
| 42 |
+
- Single sentence
|
| 43 |
+
- Limitations: may hallucinate or omit information, doesn't understand context, can still sound awkward or strange (as the above example shows)
|
| 44 |
+
|
| 45 |
+
## Training procedure
|
| 46 |
+
|
| 47 |
+
### Training hyperparameters
|
| 48 |
+
|
| 49 |
+
The following hyperparameters were used during training:
|
| 50 |
+
- learning_rate: 5e-05
|
| 51 |
+
- train_batch_size: 8
|
| 52 |
+
- eval_batch_size: 8
|
| 53 |
+
- seed: 42
|
| 54 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 55 |
+
- lr_scheduler_type: linear
|
| 56 |
+
- num_epochs: 3.0
|
| 57 |
+
|
| 58 |
+
### Framework versions
|
| 59 |
+
|
| 60 |
+
- Transformers 4.43.3
|
| 61 |
+
- Pytorch 2.3.0+cu121
|
| 62 |
+
- Datasets 2.20.0
|
| 63 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"num_input_tokens_seen": 67927868,
|
| 4 |
+
"total_flos": 1.7989403580039168e+16,
|
| 5 |
+
"train_loss": 1.1922986107342055,
|
| 6 |
+
"train_runtime": 2155.3414,
|
| 7 |
+
"train_samples": 310916,
|
| 8 |
+
"train_samples_per_second": 432.761,
|
| 9 |
+
"train_steps_per_second": 54.096,
|
| 10 |
+
"train_tokens_per_second": 31520.605
|
| 11 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Helsinki-NLP/opus-mt-en-zh",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "swish",
|
| 5 |
+
"add_bias_logits": false,
|
| 6 |
+
"add_final_layer_norm": false,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"MarianMTModel"
|
| 9 |
+
],
|
| 10 |
+
"attention_dropout": 0.0,
|
| 11 |
+
"bad_words_ids": [
|
| 12 |
+
[
|
| 13 |
+
65000
|
| 14 |
+
]
|
| 15 |
+
],
|
| 16 |
+
"bos_token_id": 0,
|
| 17 |
+
"classif_dropout": 0.0,
|
| 18 |
+
"classifier_dropout": 0.0,
|
| 19 |
+
"d_model": 512,
|
| 20 |
+
"decoder_attention_heads": 8,
|
| 21 |
+
"decoder_ffn_dim": 2048,
|
| 22 |
+
"decoder_layerdrop": 0.0,
|
| 23 |
+
"decoder_layers": 6,
|
| 24 |
+
"decoder_start_token_id": 65000,
|
| 25 |
+
"decoder_vocab_size": 65001,
|
| 26 |
+
"do_blenderbot_90_layernorm": false,
|
| 27 |
+
"dropout": 0.1,
|
| 28 |
+
"encoder_attention_heads": 8,
|
| 29 |
+
"encoder_ffn_dim": 2048,
|
| 30 |
+
"encoder_layerdrop": 0.0,
|
| 31 |
+
"encoder_layers": 6,
|
| 32 |
+
"eos_token_id": 0,
|
| 33 |
+
"extra_pos_embeddings": 0,
|
| 34 |
+
"force_bos_token_to_be_generated": false,
|
| 35 |
+
"forced_eos_token_id": 0,
|
| 36 |
+
"gradient_checkpointing": false,
|
| 37 |
+
"id2label": {
|
| 38 |
+
"0": "LABEL_0",
|
| 39 |
+
"1": "LABEL_1",
|
| 40 |
+
"2": "LABEL_2"
|
| 41 |
+
},
|
| 42 |
+
"init_std": 0.02,
|
| 43 |
+
"is_encoder_decoder": true,
|
| 44 |
+
"label2id": {
|
| 45 |
+
"LABEL_0": 0,
|
| 46 |
+
"LABEL_1": 1,
|
| 47 |
+
"LABEL_2": 2
|
| 48 |
+
},
|
| 49 |
+
"max_length": 512,
|
| 50 |
+
"max_position_embeddings": 512,
|
| 51 |
+
"model_type": "marian",
|
| 52 |
+
"normalize_before": false,
|
| 53 |
+
"normalize_embedding": false,
|
| 54 |
+
"num_beams": 4,
|
| 55 |
+
"num_hidden_layers": 6,
|
| 56 |
+
"pad_token_id": 65000,
|
| 57 |
+
"scale_embedding": true,
|
| 58 |
+
"share_encoder_decoder_embeddings": true,
|
| 59 |
+
"static_position_embeddings": true,
|
| 60 |
+
"torch_dtype": "float32",
|
| 61 |
+
"transformers_version": "4.43.3",
|
| 62 |
+
"use_cache": true,
|
| 63 |
+
"vocab_size": 65001
|
| 64 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bad_words_ids": [
|
| 3 |
+
[
|
| 4 |
+
65000
|
| 5 |
+
]
|
| 6 |
+
],
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"decoder_start_token_id": 65000,
|
| 9 |
+
"eos_token_id": 0,
|
| 10 |
+
"forced_eos_token_id": 0,
|
| 11 |
+
"max_length": 512,
|
| 12 |
+
"num_beams": 4,
|
| 13 |
+
"pad_token_id": 65000,
|
| 14 |
+
"renormalize_logits": true,
|
| 15 |
+
"transformers_version": "4.43.3"
|
| 16 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2527b97d2fa376dbfe40f7b62f5adbf21e09020a8d156d2cc43e7773b2b565cd
|
| 3 |
+
size 309965092
|
source.spm
ADDED
|
Binary file (806 kB). View file
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": "</s>",
|
| 3 |
+
"pad_token": "<pad>",
|
| 4 |
+
"unk_token": "<unk>"
|
| 5 |
+
}
|
target.spm
ADDED
|
Binary file (805 kB). View file
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "</s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<unk>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"65000": {
|
| 20 |
+
"content": "<pad>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
}
|
| 27 |
+
},
|
| 28 |
+
"clean_up_tokenization_spaces": true,
|
| 29 |
+
"eos_token": "</s>",
|
| 30 |
+
"model_max_length": 512,
|
| 31 |
+
"pad_token": "<pad>",
|
| 32 |
+
"separate_vocabs": false,
|
| 33 |
+
"source_lang": "eng",
|
| 34 |
+
"sp_model_kwargs": {},
|
| 35 |
+
"target_lang": "zho",
|
| 36 |
+
"tokenizer_class": "MarianTokenizer",
|
| 37 |
+
"unk_token": "<unk>"
|
| 38 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"num_input_tokens_seen": 67927868,
|
| 4 |
+
"total_flos": 1.7989403580039168e+16,
|
| 5 |
+
"train_loss": 1.1922986107342055,
|
| 6 |
+
"train_runtime": 2155.3414,
|
| 7 |
+
"train_samples": 310916,
|
| 8 |
+
"train_samples_per_second": 432.761,
|
| 9 |
+
"train_steps_per_second": 54.096,
|
| 10 |
+
"train_tokens_per_second": 31520.605
|
| 11 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1908 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 116595,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.012865045670912132,
|
| 13 |
+
"grad_norm": 7.8005571365356445,
|
| 14 |
+
"learning_rate": 4.978558257215147e-05,
|
| 15 |
+
"loss": 4.1174,
|
| 16 |
+
"num_input_tokens_seen": 290696,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.025730091341824263,
|
| 21 |
+
"grad_norm": 8.382389068603516,
|
| 22 |
+
"learning_rate": 4.957116514430293e-05,
|
| 23 |
+
"loss": 3.9583,
|
| 24 |
+
"num_input_tokens_seen": 580600,
|
| 25 |
+
"step": 1000
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.0385951370127364,
|
| 29 |
+
"grad_norm": 7.8291778564453125,
|
| 30 |
+
"learning_rate": 4.935674771645439e-05,
|
| 31 |
+
"loss": 3.859,
|
| 32 |
+
"num_input_tokens_seen": 874800,
|
| 33 |
+
"step": 1500
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.05146018268364853,
|
| 37 |
+
"grad_norm": 7.659093379974365,
|
| 38 |
+
"learning_rate": 4.914233028860586e-05,
|
| 39 |
+
"loss": 3.8451,
|
| 40 |
+
"num_input_tokens_seen": 1167104,
|
| 41 |
+
"step": 2000
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.06432522835456066,
|
| 45 |
+
"grad_norm": 9.296012878417969,
|
| 46 |
+
"learning_rate": 4.892791286075732e-05,
|
| 47 |
+
"loss": 3.7631,
|
| 48 |
+
"num_input_tokens_seen": 1460848,
|
| 49 |
+
"step": 2500
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.0771902740254728,
|
| 53 |
+
"grad_norm": 7.6745710372924805,
|
| 54 |
+
"learning_rate": 4.871349543290879e-05,
|
| 55 |
+
"loss": 3.7213,
|
| 56 |
+
"num_input_tokens_seen": 1756272,
|
| 57 |
+
"step": 3000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.09005531969638492,
|
| 61 |
+
"grad_norm": 7.863762378692627,
|
| 62 |
+
"learning_rate": 4.8499078005060254e-05,
|
| 63 |
+
"loss": 3.6711,
|
| 64 |
+
"num_input_tokens_seen": 2051400,
|
| 65 |
+
"step": 3500
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.10292036536729705,
|
| 69 |
+
"grad_norm": 9.283061027526855,
|
| 70 |
+
"learning_rate": 4.828466057721171e-05,
|
| 71 |
+
"loss": 3.6652,
|
| 72 |
+
"num_input_tokens_seen": 2341024,
|
| 73 |
+
"step": 4000
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.11578541103820919,
|
| 77 |
+
"grad_norm": 6.726513385772705,
|
| 78 |
+
"learning_rate": 4.807024314936318e-05,
|
| 79 |
+
"loss": 3.6139,
|
| 80 |
+
"num_input_tokens_seen": 2630600,
|
| 81 |
+
"step": 4500
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.1286504567091213,
|
| 85 |
+
"grad_norm": 8.104506492614746,
|
| 86 |
+
"learning_rate": 4.7855825721514643e-05,
|
| 87 |
+
"loss": 3.6039,
|
| 88 |
+
"num_input_tokens_seen": 2919840,
|
| 89 |
+
"step": 5000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.14151550238003344,
|
| 93 |
+
"grad_norm": 7.184753894805908,
|
| 94 |
+
"learning_rate": 4.764140829366611e-05,
|
| 95 |
+
"loss": 3.5984,
|
| 96 |
+
"num_input_tokens_seen": 3211736,
|
| 97 |
+
"step": 5500
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.1543805480509456,
|
| 101 |
+
"grad_norm": 8.069321632385254,
|
| 102 |
+
"learning_rate": 4.7426990865817574e-05,
|
| 103 |
+
"loss": 3.5789,
|
| 104 |
+
"num_input_tokens_seen": 3504520,
|
| 105 |
+
"step": 6000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.1672455937218577,
|
| 109 |
+
"grad_norm": 8.252145767211914,
|
| 110 |
+
"learning_rate": 4.721257343796904e-05,
|
| 111 |
+
"loss": 3.5405,
|
| 112 |
+
"num_input_tokens_seen": 3797624,
|
| 113 |
+
"step": 6500
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.18011063939276983,
|
| 117 |
+
"grad_norm": 7.835130214691162,
|
| 118 |
+
"learning_rate": 4.6998156010120505e-05,
|
| 119 |
+
"loss": 3.5301,
|
| 120 |
+
"num_input_tokens_seen": 4094448,
|
| 121 |
+
"step": 7000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.19297568506368198,
|
| 125 |
+
"grad_norm": 7.696624279022217,
|
| 126 |
+
"learning_rate": 4.678373858227197e-05,
|
| 127 |
+
"loss": 3.5305,
|
| 128 |
+
"num_input_tokens_seen": 4384360,
|
| 129 |
+
"step": 7500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.2058407307345941,
|
| 133 |
+
"grad_norm": 6.831740856170654,
|
| 134 |
+
"learning_rate": 4.6569321154423436e-05,
|
| 135 |
+
"loss": 3.5104,
|
| 136 |
+
"num_input_tokens_seen": 4676344,
|
| 137 |
+
"step": 8000
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.21870577640550623,
|
| 141 |
+
"grad_norm": 8.174054145812988,
|
| 142 |
+
"learning_rate": 4.63549037265749e-05,
|
| 143 |
+
"loss": 3.4725,
|
| 144 |
+
"num_input_tokens_seen": 4964600,
|
| 145 |
+
"step": 8500
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.23157082207641838,
|
| 149 |
+
"grad_norm": 8.504060745239258,
|
| 150 |
+
"learning_rate": 4.614048629872637e-05,
|
| 151 |
+
"loss": 3.4622,
|
| 152 |
+
"num_input_tokens_seen": 5252472,
|
| 153 |
+
"step": 9000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.2444358677473305,
|
| 157 |
+
"grad_norm": 6.625699996948242,
|
| 158 |
+
"learning_rate": 4.5926068870877826e-05,
|
| 159 |
+
"loss": 3.4745,
|
| 160 |
+
"num_input_tokens_seen": 5544856,
|
| 161 |
+
"step": 9500
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.2573009134182426,
|
| 165 |
+
"grad_norm": 6.5118513107299805,
|
| 166 |
+
"learning_rate": 4.571165144302929e-05,
|
| 167 |
+
"loss": 3.4726,
|
| 168 |
+
"num_input_tokens_seen": 5835512,
|
| 169 |
+
"step": 10000
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.27016595908915475,
|
| 173 |
+
"grad_norm": 7.566400527954102,
|
| 174 |
+
"learning_rate": 4.549723401518076e-05,
|
| 175 |
+
"loss": 3.4469,
|
| 176 |
+
"num_input_tokens_seen": 6123680,
|
| 177 |
+
"step": 10500
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.2830310047600669,
|
| 181 |
+
"grad_norm": 7.794484615325928,
|
| 182 |
+
"learning_rate": 4.528281658733222e-05,
|
| 183 |
+
"loss": 3.452,
|
| 184 |
+
"num_input_tokens_seen": 6413064,
|
| 185 |
+
"step": 11000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.29589605043097905,
|
| 189 |
+
"grad_norm": 7.974316120147705,
|
| 190 |
+
"learning_rate": 4.506839915948369e-05,
|
| 191 |
+
"loss": 3.4362,
|
| 192 |
+
"num_input_tokens_seen": 6702440,
|
| 193 |
+
"step": 11500
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.3087610961018912,
|
| 197 |
+
"grad_norm": 7.082245349884033,
|
| 198 |
+
"learning_rate": 4.4853981731635146e-05,
|
| 199 |
+
"loss": 3.4132,
|
| 200 |
+
"num_input_tokens_seen": 6994512,
|
| 201 |
+
"step": 12000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.3216261417728033,
|
| 205 |
+
"grad_norm": 7.03355598449707,
|
| 206 |
+
"learning_rate": 4.463956430378661e-05,
|
| 207 |
+
"loss": 3.4169,
|
| 208 |
+
"num_input_tokens_seen": 7288136,
|
| 209 |
+
"step": 12500
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.3344911874437154,
|
| 213 |
+
"grad_norm": 6.516682147979736,
|
| 214 |
+
"learning_rate": 4.442514687593808e-05,
|
| 215 |
+
"loss": 3.416,
|
| 216 |
+
"num_input_tokens_seen": 7578896,
|
| 217 |
+
"step": 13000
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.34735623311462754,
|
| 221 |
+
"grad_norm": 6.383710861206055,
|
| 222 |
+
"learning_rate": 4.421072944808954e-05,
|
| 223 |
+
"loss": 3.4127,
|
| 224 |
+
"num_input_tokens_seen": 7868256,
|
| 225 |
+
"step": 13500
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.36022127878553967,
|
| 229 |
+
"grad_norm": 7.31823205947876,
|
| 230 |
+
"learning_rate": 4.399631202024101e-05,
|
| 231 |
+
"loss": 3.3886,
|
| 232 |
+
"num_input_tokens_seen": 8160560,
|
| 233 |
+
"step": 14000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.37308632445645185,
|
| 237 |
+
"grad_norm": 7.401162624359131,
|
| 238 |
+
"learning_rate": 4.378189459239247e-05,
|
| 239 |
+
"loss": 3.4051,
|
| 240 |
+
"num_input_tokens_seen": 8451784,
|
| 241 |
+
"step": 14500
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.38595137012736397,
|
| 245 |
+
"grad_norm": 6.930325031280518,
|
| 246 |
+
"learning_rate": 4.356747716454393e-05,
|
| 247 |
+
"loss": 3.3821,
|
| 248 |
+
"num_input_tokens_seen": 8743248,
|
| 249 |
+
"step": 15000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.3988164157982761,
|
| 253 |
+
"grad_norm": 6.667317867279053,
|
| 254 |
+
"learning_rate": 4.33530597366954e-05,
|
| 255 |
+
"loss": 3.3649,
|
| 256 |
+
"num_input_tokens_seen": 9033824,
|
| 257 |
+
"step": 15500
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.4116814614691882,
|
| 261 |
+
"grad_norm": 8.706613540649414,
|
| 262 |
+
"learning_rate": 4.313864230884686e-05,
|
| 263 |
+
"loss": 3.3882,
|
| 264 |
+
"num_input_tokens_seen": 9326000,
|
| 265 |
+
"step": 16000
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.42454650714010034,
|
| 269 |
+
"grad_norm": 6.553988933563232,
|
| 270 |
+
"learning_rate": 4.292422488099833e-05,
|
| 271 |
+
"loss": 3.3477,
|
| 272 |
+
"num_input_tokens_seen": 9615136,
|
| 273 |
+
"step": 16500
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.43741155281101246,
|
| 277 |
+
"grad_norm": 8.549520492553711,
|
| 278 |
+
"learning_rate": 4.2709807453149794e-05,
|
| 279 |
+
"loss": 3.3446,
|
| 280 |
+
"num_input_tokens_seen": 9907896,
|
| 281 |
+
"step": 17000
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.4502765984819246,
|
| 285 |
+
"grad_norm": 6.12117862701416,
|
| 286 |
+
"learning_rate": 4.249539002530126e-05,
|
| 287 |
+
"loss": 3.3399,
|
| 288 |
+
"num_input_tokens_seen": 10199424,
|
| 289 |
+
"step": 17500
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.46314164415283676,
|
| 293 |
+
"grad_norm": 6.233087062835693,
|
| 294 |
+
"learning_rate": 4.2280972597452725e-05,
|
| 295 |
+
"loss": 3.3456,
|
| 296 |
+
"num_input_tokens_seen": 10489184,
|
| 297 |
+
"step": 18000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.4760066898237489,
|
| 301 |
+
"grad_norm": 6.620530605316162,
|
| 302 |
+
"learning_rate": 4.206655516960419e-05,
|
| 303 |
+
"loss": 3.3362,
|
| 304 |
+
"num_input_tokens_seen": 10784400,
|
| 305 |
+
"step": 18500
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.488871735494661,
|
| 309 |
+
"grad_norm": 6.852022647857666,
|
| 310 |
+
"learning_rate": 4.1852137741755656e-05,
|
| 311 |
+
"loss": 3.3319,
|
| 312 |
+
"num_input_tokens_seen": 11076656,
|
| 313 |
+
"step": 19000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.5017367811655732,
|
| 317 |
+
"grad_norm": 7.368551254272461,
|
| 318 |
+
"learning_rate": 4.1637720313907114e-05,
|
| 319 |
+
"loss": 3.3271,
|
| 320 |
+
"num_input_tokens_seen": 11371104,
|
| 321 |
+
"step": 19500
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.5146018268364853,
|
| 325 |
+
"grad_norm": 7.825785160064697,
|
| 326 |
+
"learning_rate": 4.142330288605858e-05,
|
| 327 |
+
"loss": 3.2941,
|
| 328 |
+
"num_input_tokens_seen": 11664608,
|
| 329 |
+
"step": 20000
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.5274668725073974,
|
| 333 |
+
"grad_norm": 7.652072429656982,
|
| 334 |
+
"learning_rate": 4.1208885458210045e-05,
|
| 335 |
+
"loss": 3.3174,
|
| 336 |
+
"num_input_tokens_seen": 11954656,
|
| 337 |
+
"step": 20500
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.5403319181783095,
|
| 341 |
+
"grad_norm": 6.378400802612305,
|
| 342 |
+
"learning_rate": 4.099446803036151e-05,
|
| 343 |
+
"loss": 3.3438,
|
| 344 |
+
"num_input_tokens_seen": 12245192,
|
| 345 |
+
"step": 21000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.5531969638492217,
|
| 349 |
+
"grad_norm": 6.9614434242248535,
|
| 350 |
+
"learning_rate": 4.0780050602512976e-05,
|
| 351 |
+
"loss": 3.2937,
|
| 352 |
+
"num_input_tokens_seen": 12534328,
|
| 353 |
+
"step": 21500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.5660620095201337,
|
| 357 |
+
"grad_norm": 7.3693318367004395,
|
| 358 |
+
"learning_rate": 4.056563317466444e-05,
|
| 359 |
+
"loss": 3.2893,
|
| 360 |
+
"num_input_tokens_seen": 12825376,
|
| 361 |
+
"step": 22000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.5789270551910459,
|
| 365 |
+
"grad_norm": 7.541472911834717,
|
| 366 |
+
"learning_rate": 4.03512157468159e-05,
|
| 367 |
+
"loss": 3.2868,
|
| 368 |
+
"num_input_tokens_seen": 13114616,
|
| 369 |
+
"step": 22500
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.5917921008619581,
|
| 373 |
+
"grad_norm": 7.473111629486084,
|
| 374 |
+
"learning_rate": 4.0136798318967366e-05,
|
| 375 |
+
"loss": 3.2725,
|
| 376 |
+
"num_input_tokens_seen": 13405272,
|
| 377 |
+
"step": 23000
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.6046571465328702,
|
| 381 |
+
"grad_norm": 6.550891399383545,
|
| 382 |
+
"learning_rate": 3.992238089111883e-05,
|
| 383 |
+
"loss": 3.3067,
|
| 384 |
+
"num_input_tokens_seen": 13699360,
|
| 385 |
+
"step": 23500
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.6175221922037823,
|
| 389 |
+
"grad_norm": 6.285316467285156,
|
| 390 |
+
"learning_rate": 3.97079634632703e-05,
|
| 391 |
+
"loss": 3.2861,
|
| 392 |
+
"num_input_tokens_seen": 13990416,
|
| 393 |
+
"step": 24000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.6303872378746944,
|
| 397 |
+
"grad_norm": 7.406656742095947,
|
| 398 |
+
"learning_rate": 3.949354603542176e-05,
|
| 399 |
+
"loss": 3.2772,
|
| 400 |
+
"num_input_tokens_seen": 14282464,
|
| 401 |
+
"step": 24500
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.6432522835456066,
|
| 405 |
+
"grad_norm": 7.1049065589904785,
|
| 406 |
+
"learning_rate": 3.927912860757322e-05,
|
| 407 |
+
"loss": 3.257,
|
| 408 |
+
"num_input_tokens_seen": 14575304,
|
| 409 |
+
"step": 25000
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.6561173292165187,
|
| 413 |
+
"grad_norm": 5.734112739562988,
|
| 414 |
+
"learning_rate": 3.9064711179724686e-05,
|
| 415 |
+
"loss": 3.2361,
|
| 416 |
+
"num_input_tokens_seen": 14863952,
|
| 417 |
+
"step": 25500
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.6689823748874308,
|
| 421 |
+
"grad_norm": 6.281294822692871,
|
| 422 |
+
"learning_rate": 3.885029375187615e-05,
|
| 423 |
+
"loss": 3.2489,
|
| 424 |
+
"num_input_tokens_seen": 15152296,
|
| 425 |
+
"step": 26000
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.681847420558343,
|
| 429 |
+
"grad_norm": 8.989299774169922,
|
| 430 |
+
"learning_rate": 3.863587632402762e-05,
|
| 431 |
+
"loss": 3.2436,
|
| 432 |
+
"num_input_tokens_seen": 15442488,
|
| 433 |
+
"step": 26500
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 0.6947124662292551,
|
| 437 |
+
"grad_norm": 7.305727481842041,
|
| 438 |
+
"learning_rate": 3.842145889617908e-05,
|
| 439 |
+
"loss": 3.2413,
|
| 440 |
+
"num_input_tokens_seen": 15733104,
|
| 441 |
+
"step": 27000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.7075775119001673,
|
| 445 |
+
"grad_norm": 5.735226631164551,
|
| 446 |
+
"learning_rate": 3.820704146833055e-05,
|
| 447 |
+
"loss": 3.2391,
|
| 448 |
+
"num_input_tokens_seen": 16025536,
|
| 449 |
+
"step": 27500
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.7204425575710793,
|
| 453 |
+
"grad_norm": 6.767416000366211,
|
| 454 |
+
"learning_rate": 3.7992624040482014e-05,
|
| 455 |
+
"loss": 3.2148,
|
| 456 |
+
"num_input_tokens_seen": 16313080,
|
| 457 |
+
"step": 28000
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.7333076032419915,
|
| 461 |
+
"grad_norm": 6.932997703552246,
|
| 462 |
+
"learning_rate": 3.777820661263348e-05,
|
| 463 |
+
"loss": 3.2245,
|
| 464 |
+
"num_input_tokens_seen": 16600696,
|
| 465 |
+
"step": 28500
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.7461726489129037,
|
| 469 |
+
"grad_norm": 7.29443359375,
|
| 470 |
+
"learning_rate": 3.7563789184784945e-05,
|
| 471 |
+
"loss": 3.2226,
|
| 472 |
+
"num_input_tokens_seen": 16889416,
|
| 473 |
+
"step": 29000
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.7590376945838158,
|
| 477 |
+
"grad_norm": 6.85066556930542,
|
| 478 |
+
"learning_rate": 3.734937175693641e-05,
|
| 479 |
+
"loss": 3.2464,
|
| 480 |
+
"num_input_tokens_seen": 17181624,
|
| 481 |
+
"step": 29500
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.7719027402547279,
|
| 485 |
+
"grad_norm": 7.167715072631836,
|
| 486 |
+
"learning_rate": 3.713495432908787e-05,
|
| 487 |
+
"loss": 3.2091,
|
| 488 |
+
"num_input_tokens_seen": 17470040,
|
| 489 |
+
"step": 30000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.78476778592564,
|
| 493 |
+
"grad_norm": 6.19227933883667,
|
| 494 |
+
"learning_rate": 3.6920536901239334e-05,
|
| 495 |
+
"loss": 3.2147,
|
| 496 |
+
"num_input_tokens_seen": 17762608,
|
| 497 |
+
"step": 30500
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.7976328315965522,
|
| 501 |
+
"grad_norm": 6.353000164031982,
|
| 502 |
+
"learning_rate": 3.67061194733908e-05,
|
| 503 |
+
"loss": 3.2076,
|
| 504 |
+
"num_input_tokens_seen": 18054152,
|
| 505 |
+
"step": 31000
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.8104978772674643,
|
| 509 |
+
"grad_norm": 6.809099197387695,
|
| 510 |
+
"learning_rate": 3.6491702045542265e-05,
|
| 511 |
+
"loss": 3.2129,
|
| 512 |
+
"num_input_tokens_seen": 18348664,
|
| 513 |
+
"step": 31500
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.8233629229383764,
|
| 517 |
+
"grad_norm": 6.5169677734375,
|
| 518 |
+
"learning_rate": 3.627728461769373e-05,
|
| 519 |
+
"loss": 3.218,
|
| 520 |
+
"num_input_tokens_seen": 18639328,
|
| 521 |
+
"step": 32000
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.8362279686092886,
|
| 525 |
+
"grad_norm": 7.095029830932617,
|
| 526 |
+
"learning_rate": 3.606286718984519e-05,
|
| 527 |
+
"loss": 3.222,
|
| 528 |
+
"num_input_tokens_seen": 18930776,
|
| 529 |
+
"step": 32500
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.8490930142802007,
|
| 533 |
+
"grad_norm": 7.541679382324219,
|
| 534 |
+
"learning_rate": 3.5848449761996655e-05,
|
| 535 |
+
"loss": 3.2153,
|
| 536 |
+
"num_input_tokens_seen": 19223592,
|
| 537 |
+
"step": 33000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.8619580599511129,
|
| 541 |
+
"grad_norm": 7.510098457336426,
|
| 542 |
+
"learning_rate": 3.563403233414812e-05,
|
| 543 |
+
"loss": 3.1922,
|
| 544 |
+
"num_input_tokens_seen": 19517672,
|
| 545 |
+
"step": 33500
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 0.8748231056220249,
|
| 549 |
+
"grad_norm": 6.9184956550598145,
|
| 550 |
+
"learning_rate": 3.5419614906299586e-05,
|
| 551 |
+
"loss": 3.1663,
|
| 552 |
+
"num_input_tokens_seen": 19806520,
|
| 553 |
+
"step": 34000
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.8876881512929371,
|
| 557 |
+
"grad_norm": 6.282911777496338,
|
| 558 |
+
"learning_rate": 3.520519747845105e-05,
|
| 559 |
+
"loss": 3.1922,
|
| 560 |
+
"num_input_tokens_seen": 20097768,
|
| 561 |
+
"step": 34500
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.9005531969638492,
|
| 565 |
+
"grad_norm": 7.266313552856445,
|
| 566 |
+
"learning_rate": 3.4990780050602516e-05,
|
| 567 |
+
"loss": 3.1741,
|
| 568 |
+
"num_input_tokens_seen": 20384448,
|
| 569 |
+
"step": 35000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.9134182426347613,
|
| 573 |
+
"grad_norm": 5.5496110916137695,
|
| 574 |
+
"learning_rate": 3.4776362622753975e-05,
|
| 575 |
+
"loss": 3.193,
|
| 576 |
+
"num_input_tokens_seen": 20672584,
|
| 577 |
+
"step": 35500
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.9262832883056735,
|
| 581 |
+
"grad_norm": 7.990514278411865,
|
| 582 |
+
"learning_rate": 3.456194519490544e-05,
|
| 583 |
+
"loss": 3.1539,
|
| 584 |
+
"num_input_tokens_seen": 20965184,
|
| 585 |
+
"step": 36000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.9391483339765856,
|
| 589 |
+
"grad_norm": 6.803572177886963,
|
| 590 |
+
"learning_rate": 3.4347527767056906e-05,
|
| 591 |
+
"loss": 3.16,
|
| 592 |
+
"num_input_tokens_seen": 21256728,
|
| 593 |
+
"step": 36500
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.9520133796474978,
|
| 597 |
+
"grad_norm": 7.202699661254883,
|
| 598 |
+
"learning_rate": 3.413311033920837e-05,
|
| 599 |
+
"loss": 3.1587,
|
| 600 |
+
"num_input_tokens_seen": 21553464,
|
| 601 |
+
"step": 37000
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.9648784253184098,
|
| 605 |
+
"grad_norm": 7.018800735473633,
|
| 606 |
+
"learning_rate": 3.391869291135984e-05,
|
| 607 |
+
"loss": 3.1395,
|
| 608 |
+
"num_input_tokens_seen": 21847744,
|
| 609 |
+
"step": 37500
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.977743470989322,
|
| 613 |
+
"grad_norm": 9.715666770935059,
|
| 614 |
+
"learning_rate": 3.37042754835113e-05,
|
| 615 |
+
"loss": 3.1493,
|
| 616 |
+
"num_input_tokens_seen": 22142256,
|
| 617 |
+
"step": 38000
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.9906085166602342,
|
| 621 |
+
"grad_norm": 6.174098491668701,
|
| 622 |
+
"learning_rate": 3.348985805566277e-05,
|
| 623 |
+
"loss": 3.1744,
|
| 624 |
+
"num_input_tokens_seen": 22433344,
|
| 625 |
+
"step": 38500
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.0034735623311464,
|
| 629 |
+
"grad_norm": 6.0936503410339355,
|
| 630 |
+
"learning_rate": 3.327544062781423e-05,
|
| 631 |
+
"loss": 3.1358,
|
| 632 |
+
"num_input_tokens_seen": 22726152,
|
| 633 |
+
"step": 39000
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.0163386080020584,
|
| 637 |
+
"grad_norm": 6.897722244262695,
|
| 638 |
+
"learning_rate": 3.30610231999657e-05,
|
| 639 |
+
"loss": 3.0054,
|
| 640 |
+
"num_input_tokens_seen": 23018744,
|
| 641 |
+
"step": 39500
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 1.0292036536729705,
|
| 645 |
+
"grad_norm": 6.8439412117004395,
|
| 646 |
+
"learning_rate": 3.2846605772117164e-05,
|
| 647 |
+
"loss": 2.9973,
|
| 648 |
+
"num_input_tokens_seen": 23307936,
|
| 649 |
+
"step": 40000
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 1.0420686993438826,
|
| 653 |
+
"grad_norm": 6.564641952514648,
|
| 654 |
+
"learning_rate": 3.263218834426862e-05,
|
| 655 |
+
"loss": 2.9964,
|
| 656 |
+
"num_input_tokens_seen": 23604824,
|
| 657 |
+
"step": 40500
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 1.0549337450147949,
|
| 661 |
+
"grad_norm": 6.155550479888916,
|
| 662 |
+
"learning_rate": 3.241777091642009e-05,
|
| 663 |
+
"loss": 3.0128,
|
| 664 |
+
"num_input_tokens_seen": 23895032,
|
| 665 |
+
"step": 41000
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 1.067798790685707,
|
| 669 |
+
"grad_norm": 6.811328887939453,
|
| 670 |
+
"learning_rate": 3.2203353488571554e-05,
|
| 671 |
+
"loss": 3.0221,
|
| 672 |
+
"num_input_tokens_seen": 24185928,
|
| 673 |
+
"step": 41500
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 1.080663836356619,
|
| 677 |
+
"grad_norm": 6.012444019317627,
|
| 678 |
+
"learning_rate": 3.198893606072302e-05,
|
| 679 |
+
"loss": 3.0283,
|
| 680 |
+
"num_input_tokens_seen": 24474600,
|
| 681 |
+
"step": 42000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.0935288820275313,
|
| 685 |
+
"grad_norm": 6.834691524505615,
|
| 686 |
+
"learning_rate": 3.1774518632874485e-05,
|
| 687 |
+
"loss": 3.001,
|
| 688 |
+
"num_input_tokens_seen": 24765648,
|
| 689 |
+
"step": 42500
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.1063939276984434,
|
| 693 |
+
"grad_norm": 7.075684070587158,
|
| 694 |
+
"learning_rate": 3.1560101205025943e-05,
|
| 695 |
+
"loss": 2.9998,
|
| 696 |
+
"num_input_tokens_seen": 25057256,
|
| 697 |
+
"step": 43000
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 1.1192589733693554,
|
| 701 |
+
"grad_norm": 6.3663716316223145,
|
| 702 |
+
"learning_rate": 3.134568377717741e-05,
|
| 703 |
+
"loss": 3.0107,
|
| 704 |
+
"num_input_tokens_seen": 25348904,
|
| 705 |
+
"step": 43500
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 1.1321240190402677,
|
| 709 |
+
"grad_norm": 7.406547546386719,
|
| 710 |
+
"learning_rate": 3.1131266349328874e-05,
|
| 711 |
+
"loss": 3.0029,
|
| 712 |
+
"num_input_tokens_seen": 25640496,
|
| 713 |
+
"step": 44000
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 1.1449890647111798,
|
| 717 |
+
"grad_norm": 7.625437259674072,
|
| 718 |
+
"learning_rate": 3.091684892148034e-05,
|
| 719 |
+
"loss": 3.0045,
|
| 720 |
+
"num_input_tokens_seen": 25934664,
|
| 721 |
+
"step": 44500
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 1.1578541103820919,
|
| 725 |
+
"grad_norm": 6.509032726287842,
|
| 726 |
+
"learning_rate": 3.0702431493631805e-05,
|
| 727 |
+
"loss": 3.0089,
|
| 728 |
+
"num_input_tokens_seen": 26225392,
|
| 729 |
+
"step": 45000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 1.170719156053004,
|
| 733 |
+
"grad_norm": 5.867618560791016,
|
| 734 |
+
"learning_rate": 3.0488014065783267e-05,
|
| 735 |
+
"loss": 2.9789,
|
| 736 |
+
"num_input_tokens_seen": 26516360,
|
| 737 |
+
"step": 45500
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.1835842017239162,
|
| 741 |
+
"grad_norm": 6.742827892303467,
|
| 742 |
+
"learning_rate": 3.0273596637934733e-05,
|
| 743 |
+
"loss": 2.9921,
|
| 744 |
+
"num_input_tokens_seen": 26811464,
|
| 745 |
+
"step": 46000
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.1964492473948283,
|
| 749 |
+
"grad_norm": 6.05054235458374,
|
| 750 |
+
"learning_rate": 3.0059179210086198e-05,
|
| 751 |
+
"loss": 3.0073,
|
| 752 |
+
"num_input_tokens_seen": 27102928,
|
| 753 |
+
"step": 46500
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 1.2093142930657403,
|
| 757 |
+
"grad_norm": 6.148196220397949,
|
| 758 |
+
"learning_rate": 2.9844761782237664e-05,
|
| 759 |
+
"loss": 3.0191,
|
| 760 |
+
"num_input_tokens_seen": 27389024,
|
| 761 |
+
"step": 47000
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 1.2221793387366526,
|
| 765 |
+
"grad_norm": 6.119533538818359,
|
| 766 |
+
"learning_rate": 2.963034435438913e-05,
|
| 767 |
+
"loss": 2.9884,
|
| 768 |
+
"num_input_tokens_seen": 27680744,
|
| 769 |
+
"step": 47500
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 1.2350443844075647,
|
| 773 |
+
"grad_norm": 5.91504430770874,
|
| 774 |
+
"learning_rate": 2.9415926926540588e-05,
|
| 775 |
+
"loss": 2.97,
|
| 776 |
+
"num_input_tokens_seen": 27972728,
|
| 777 |
+
"step": 48000
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 1.2479094300784768,
|
| 781 |
+
"grad_norm": 7.024054050445557,
|
| 782 |
+
"learning_rate": 2.9201509498692053e-05,
|
| 783 |
+
"loss": 3.0079,
|
| 784 |
+
"num_input_tokens_seen": 28267000,
|
| 785 |
+
"step": 48500
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 1.2607744757493888,
|
| 789 |
+
"grad_norm": 6.829626560211182,
|
| 790 |
+
"learning_rate": 2.898709207084352e-05,
|
| 791 |
+
"loss": 2.9945,
|
| 792 |
+
"num_input_tokens_seen": 28557872,
|
| 793 |
+
"step": 49000
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.2736395214203011,
|
| 797 |
+
"grad_norm": 6.172780990600586,
|
| 798 |
+
"learning_rate": 2.8772674642994984e-05,
|
| 799 |
+
"loss": 3.0175,
|
| 800 |
+
"num_input_tokens_seen": 28850024,
|
| 801 |
+
"step": 49500
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.2865045670912132,
|
| 805 |
+
"grad_norm": 6.888333320617676,
|
| 806 |
+
"learning_rate": 2.855825721514645e-05,
|
| 807 |
+
"loss": 2.9914,
|
| 808 |
+
"num_input_tokens_seen": 29142640,
|
| 809 |
+
"step": 50000
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 1.2993696127621253,
|
| 813 |
+
"grad_norm": 7.5561394691467285,
|
| 814 |
+
"learning_rate": 2.8343839787297915e-05,
|
| 815 |
+
"loss": 3.0081,
|
| 816 |
+
"num_input_tokens_seen": 29436480,
|
| 817 |
+
"step": 50500
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 1.3122346584330375,
|
| 821 |
+
"grad_norm": 6.160106182098389,
|
| 822 |
+
"learning_rate": 2.8129422359449377e-05,
|
| 823 |
+
"loss": 2.9796,
|
| 824 |
+
"num_input_tokens_seen": 29728032,
|
| 825 |
+
"step": 51000
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 1.3250997041039496,
|
| 829 |
+
"grad_norm": 6.359186172485352,
|
| 830 |
+
"learning_rate": 2.7915004931600843e-05,
|
| 831 |
+
"loss": 2.9663,
|
| 832 |
+
"num_input_tokens_seen": 30015064,
|
| 833 |
+
"step": 51500
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 1.3379647497748617,
|
| 837 |
+
"grad_norm": 5.363637447357178,
|
| 838 |
+
"learning_rate": 2.7700587503752308e-05,
|
| 839 |
+
"loss": 3.0251,
|
| 840 |
+
"num_input_tokens_seen": 30307168,
|
| 841 |
+
"step": 52000
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 1.3508297954457738,
|
| 845 |
+
"grad_norm": 6.702362537384033,
|
| 846 |
+
"learning_rate": 2.7486170075903773e-05,
|
| 847 |
+
"loss": 3.0027,
|
| 848 |
+
"num_input_tokens_seen": 30597808,
|
| 849 |
+
"step": 52500
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.363694841116686,
|
| 853 |
+
"grad_norm": 6.282807350158691,
|
| 854 |
+
"learning_rate": 2.727175264805524e-05,
|
| 855 |
+
"loss": 2.9954,
|
| 856 |
+
"num_input_tokens_seen": 30888840,
|
| 857 |
+
"step": 53000
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.376559886787598,
|
| 861 |
+
"grad_norm": 6.255498886108398,
|
| 862 |
+
"learning_rate": 2.7057335220206698e-05,
|
| 863 |
+
"loss": 3.0016,
|
| 864 |
+
"num_input_tokens_seen": 31178408,
|
| 865 |
+
"step": 53500
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 1.3894249324585102,
|
| 869 |
+
"grad_norm": 5.822259426116943,
|
| 870 |
+
"learning_rate": 2.6842917792358163e-05,
|
| 871 |
+
"loss": 2.9864,
|
| 872 |
+
"num_input_tokens_seen": 31466920,
|
| 873 |
+
"step": 54000
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 1.4022899781294225,
|
| 877 |
+
"grad_norm": 6.1176652908325195,
|
| 878 |
+
"learning_rate": 2.662850036450963e-05,
|
| 879 |
+
"loss": 2.9769,
|
| 880 |
+
"num_input_tokens_seen": 31757920,
|
| 881 |
+
"step": 54500
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 1.4151550238003345,
|
| 885 |
+
"grad_norm": 7.492593765258789,
|
| 886 |
+
"learning_rate": 2.6414082936661094e-05,
|
| 887 |
+
"loss": 2.9921,
|
| 888 |
+
"num_input_tokens_seen": 32049864,
|
| 889 |
+
"step": 55000
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 1.4280200694712466,
|
| 893 |
+
"grad_norm": 6.679434299468994,
|
| 894 |
+
"learning_rate": 2.619966550881256e-05,
|
| 895 |
+
"loss": 2.9667,
|
| 896 |
+
"num_input_tokens_seen": 32342072,
|
| 897 |
+
"step": 55500
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.4408851151421587,
|
| 901 |
+
"grad_norm": 6.818129539489746,
|
| 902 |
+
"learning_rate": 2.5985248080964018e-05,
|
| 903 |
+
"loss": 2.9678,
|
| 904 |
+
"num_input_tokens_seen": 32632672,
|
| 905 |
+
"step": 56000
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.453750160813071,
|
| 909 |
+
"grad_norm": 5.836079120635986,
|
| 910 |
+
"learning_rate": 2.5770830653115487e-05,
|
| 911 |
+
"loss": 2.9515,
|
| 912 |
+
"num_input_tokens_seen": 32927752,
|
| 913 |
+
"step": 56500
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.466615206483983,
|
| 917 |
+
"grad_norm": 7.332676410675049,
|
| 918 |
+
"learning_rate": 2.5556413225266952e-05,
|
| 919 |
+
"loss": 2.9725,
|
| 920 |
+
"num_input_tokens_seen": 33220536,
|
| 921 |
+
"step": 57000
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 1.479480252154895,
|
| 925 |
+
"grad_norm": 6.780636787414551,
|
| 926 |
+
"learning_rate": 2.5341995797418418e-05,
|
| 927 |
+
"loss": 2.9507,
|
| 928 |
+
"num_input_tokens_seen": 33511536,
|
| 929 |
+
"step": 57500
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 1.4923452978258074,
|
| 933 |
+
"grad_norm": 7.856017589569092,
|
| 934 |
+
"learning_rate": 2.5127578369569883e-05,
|
| 935 |
+
"loss": 2.9431,
|
| 936 |
+
"num_input_tokens_seen": 33801088,
|
| 937 |
+
"step": 58000
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 1.5052103434967194,
|
| 941 |
+
"grad_norm": 6.466399192810059,
|
| 942 |
+
"learning_rate": 2.4913160941721345e-05,
|
| 943 |
+
"loss": 2.9826,
|
| 944 |
+
"num_input_tokens_seen": 34091576,
|
| 945 |
+
"step": 58500
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 1.5180753891676315,
|
| 949 |
+
"grad_norm": 7.123006343841553,
|
| 950 |
+
"learning_rate": 2.4698743513872807e-05,
|
| 951 |
+
"loss": 2.9551,
|
| 952 |
+
"num_input_tokens_seen": 34385640,
|
| 953 |
+
"step": 59000
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 1.5309404348385436,
|
| 957 |
+
"grad_norm": 6.76849889755249,
|
| 958 |
+
"learning_rate": 2.4484326086024273e-05,
|
| 959 |
+
"loss": 2.9577,
|
| 960 |
+
"num_input_tokens_seen": 34677472,
|
| 961 |
+
"step": 59500
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 1.5438054805094557,
|
| 965 |
+
"grad_norm": 6.654425144195557,
|
| 966 |
+
"learning_rate": 2.426990865817574e-05,
|
| 967 |
+
"loss": 2.9669,
|
| 968 |
+
"num_input_tokens_seen": 34967440,
|
| 969 |
+
"step": 60000
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.556670526180368,
|
| 973 |
+
"grad_norm": 5.956307411193848,
|
| 974 |
+
"learning_rate": 2.40554912303272e-05,
|
| 975 |
+
"loss": 2.9519,
|
| 976 |
+
"num_input_tokens_seen": 35256688,
|
| 977 |
+
"step": 60500
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 1.5695355718512802,
|
| 981 |
+
"grad_norm": 6.195157527923584,
|
| 982 |
+
"learning_rate": 2.3841073802478666e-05,
|
| 983 |
+
"loss": 2.9379,
|
| 984 |
+
"num_input_tokens_seen": 35545424,
|
| 985 |
+
"step": 61000
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 1.5824006175221923,
|
| 989 |
+
"grad_norm": 6.981558322906494,
|
| 990 |
+
"learning_rate": 2.362665637463013e-05,
|
| 991 |
+
"loss": 2.9557,
|
| 992 |
+
"num_input_tokens_seen": 35834248,
|
| 993 |
+
"step": 61500
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 1.5952656631931044,
|
| 997 |
+
"grad_norm": 6.045523166656494,
|
| 998 |
+
"learning_rate": 2.3412238946781593e-05,
|
| 999 |
+
"loss": 2.9469,
|
| 1000 |
+
"num_input_tokens_seen": 36122472,
|
| 1001 |
+
"step": 62000
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 1.6081307088640164,
|
| 1005 |
+
"grad_norm": 7.8723297119140625,
|
| 1006 |
+
"learning_rate": 2.319782151893306e-05,
|
| 1007 |
+
"loss": 2.9537,
|
| 1008 |
+
"num_input_tokens_seen": 36413912,
|
| 1009 |
+
"step": 62500
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 1.6209957545349285,
|
| 1013 |
+
"grad_norm": 7.2311296463012695,
|
| 1014 |
+
"learning_rate": 2.2983404091084524e-05,
|
| 1015 |
+
"loss": 2.9507,
|
| 1016 |
+
"num_input_tokens_seen": 36706248,
|
| 1017 |
+
"step": 63000
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 1.6338608002058406,
|
| 1021 |
+
"grad_norm": 6.698265552520752,
|
| 1022 |
+
"learning_rate": 2.276898666323599e-05,
|
| 1023 |
+
"loss": 2.9525,
|
| 1024 |
+
"num_input_tokens_seen": 36995928,
|
| 1025 |
+
"step": 63500
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.6467258458767529,
|
| 1029 |
+
"grad_norm": 5.823113918304443,
|
| 1030 |
+
"learning_rate": 2.2554569235387455e-05,
|
| 1031 |
+
"loss": 2.9689,
|
| 1032 |
+
"num_input_tokens_seen": 37285032,
|
| 1033 |
+
"step": 64000
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 1.6595908915476651,
|
| 1037 |
+
"grad_norm": 6.0338134765625,
|
| 1038 |
+
"learning_rate": 2.2340151807538917e-05,
|
| 1039 |
+
"loss": 2.9312,
|
| 1040 |
+
"num_input_tokens_seen": 37575280,
|
| 1041 |
+
"step": 64500
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 1.6724559372185772,
|
| 1045 |
+
"grad_norm": 7.287151336669922,
|
| 1046 |
+
"learning_rate": 2.2125734379690383e-05,
|
| 1047 |
+
"loss": 2.9272,
|
| 1048 |
+
"num_input_tokens_seen": 37866864,
|
| 1049 |
+
"step": 65000
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 1.6853209828894893,
|
| 1053 |
+
"grad_norm": 6.978508949279785,
|
| 1054 |
+
"learning_rate": 2.1911316951841845e-05,
|
| 1055 |
+
"loss": 2.9399,
|
| 1056 |
+
"num_input_tokens_seen": 38160464,
|
| 1057 |
+
"step": 65500
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 1.6981860285604014,
|
| 1061 |
+
"grad_norm": 6.498319625854492,
|
| 1062 |
+
"learning_rate": 2.169689952399331e-05,
|
| 1063 |
+
"loss": 2.9323,
|
| 1064 |
+
"num_input_tokens_seen": 38450864,
|
| 1065 |
+
"step": 66000
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 1.7110510742313134,
|
| 1069 |
+
"grad_norm": 6.914408206939697,
|
| 1070 |
+
"learning_rate": 2.1482482096144776e-05,
|
| 1071 |
+
"loss": 2.9378,
|
| 1072 |
+
"num_input_tokens_seen": 38741808,
|
| 1073 |
+
"step": 66500
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 1.7239161199022257,
|
| 1077 |
+
"grad_norm": 7.851312160491943,
|
| 1078 |
+
"learning_rate": 2.1268064668296238e-05,
|
| 1079 |
+
"loss": 2.9346,
|
| 1080 |
+
"num_input_tokens_seen": 39034008,
|
| 1081 |
+
"step": 67000
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.7367811655731378,
|
| 1085 |
+
"grad_norm": 7.065863132476807,
|
| 1086 |
+
"learning_rate": 2.1053647240447703e-05,
|
| 1087 |
+
"loss": 2.9458,
|
| 1088 |
+
"num_input_tokens_seen": 39326632,
|
| 1089 |
+
"step": 67500
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 1.74964621124405,
|
| 1093 |
+
"grad_norm": 7.006825923919678,
|
| 1094 |
+
"learning_rate": 2.083922981259917e-05,
|
| 1095 |
+
"loss": 2.9241,
|
| 1096 |
+
"num_input_tokens_seen": 39616152,
|
| 1097 |
+
"step": 68000
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 1.7625112569149621,
|
| 1101 |
+
"grad_norm": 6.096765041351318,
|
| 1102 |
+
"learning_rate": 2.0624812384750634e-05,
|
| 1103 |
+
"loss": 2.9341,
|
| 1104 |
+
"num_input_tokens_seen": 39909336,
|
| 1105 |
+
"step": 68500
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 1.7753763025858742,
|
| 1109 |
+
"grad_norm": 6.418511390686035,
|
| 1110 |
+
"learning_rate": 2.04103949569021e-05,
|
| 1111 |
+
"loss": 2.9602,
|
| 1112 |
+
"num_input_tokens_seen": 40201392,
|
| 1113 |
+
"step": 69000
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 1.7882413482567863,
|
| 1117 |
+
"grad_norm": 8.561145782470703,
|
| 1118 |
+
"learning_rate": 2.019597752905356e-05,
|
| 1119 |
+
"loss": 2.8944,
|
| 1120 |
+
"num_input_tokens_seen": 40494488,
|
| 1121 |
+
"step": 69500
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 1.8011063939276983,
|
| 1125 |
+
"grad_norm": 6.326451778411865,
|
| 1126 |
+
"learning_rate": 1.9981560101205027e-05,
|
| 1127 |
+
"loss": 2.9622,
|
| 1128 |
+
"num_input_tokens_seen": 40783600,
|
| 1129 |
+
"step": 70000
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.8139714395986106,
|
| 1133 |
+
"grad_norm": 7.819330215454102,
|
| 1134 |
+
"learning_rate": 1.9767142673356493e-05,
|
| 1135 |
+
"loss": 2.9218,
|
| 1136 |
+
"num_input_tokens_seen": 41076096,
|
| 1137 |
+
"step": 70500
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.8268364852695227,
|
| 1141 |
+
"grad_norm": 7.052221298217773,
|
| 1142 |
+
"learning_rate": 1.9552725245507955e-05,
|
| 1143 |
+
"loss": 2.8852,
|
| 1144 |
+
"num_input_tokens_seen": 41371488,
|
| 1145 |
+
"step": 71000
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 1.839701530940435,
|
| 1149 |
+
"grad_norm": 6.763613700866699,
|
| 1150 |
+
"learning_rate": 1.933830781765942e-05,
|
| 1151 |
+
"loss": 2.9176,
|
| 1152 |
+
"num_input_tokens_seen": 41660952,
|
| 1153 |
+
"step": 71500
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 1.852566576611347,
|
| 1157 |
+
"grad_norm": 6.716059684753418,
|
| 1158 |
+
"learning_rate": 1.9123890389810882e-05,
|
| 1159 |
+
"loss": 2.9128,
|
| 1160 |
+
"num_input_tokens_seen": 41952344,
|
| 1161 |
+
"step": 72000
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 1.8654316222822591,
|
| 1165 |
+
"grad_norm": 5.6197381019592285,
|
| 1166 |
+
"learning_rate": 1.8909472961962348e-05,
|
| 1167 |
+
"loss": 2.9254,
|
| 1168 |
+
"num_input_tokens_seen": 42240960,
|
| 1169 |
+
"step": 72500
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 1.8782966679531712,
|
| 1173 |
+
"grad_norm": 7.378303050994873,
|
| 1174 |
+
"learning_rate": 1.8695055534113813e-05,
|
| 1175 |
+
"loss": 2.9128,
|
| 1176 |
+
"num_input_tokens_seen": 42531912,
|
| 1177 |
+
"step": 73000
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 1.8911617136240833,
|
| 1181 |
+
"grad_norm": 6.518546104431152,
|
| 1182 |
+
"learning_rate": 1.848063810626528e-05,
|
| 1183 |
+
"loss": 2.9244,
|
| 1184 |
+
"num_input_tokens_seen": 42824144,
|
| 1185 |
+
"step": 73500
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.9040267592949955,
|
| 1189 |
+
"grad_norm": 6.920441627502441,
|
| 1190 |
+
"learning_rate": 1.8266220678416744e-05,
|
| 1191 |
+
"loss": 2.9321,
|
| 1192 |
+
"num_input_tokens_seen": 43116312,
|
| 1193 |
+
"step": 74000
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.9168918049659076,
|
| 1197 |
+
"grad_norm": 8.135106086730957,
|
| 1198 |
+
"learning_rate": 1.805180325056821e-05,
|
| 1199 |
+
"loss": 2.9242,
|
| 1200 |
+
"num_input_tokens_seen": 43408792,
|
| 1201 |
+
"step": 74500
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 1.92975685063682,
|
| 1205 |
+
"grad_norm": 6.130031585693359,
|
| 1206 |
+
"learning_rate": 1.783738582271967e-05,
|
| 1207 |
+
"loss": 2.9233,
|
| 1208 |
+
"num_input_tokens_seen": 43702768,
|
| 1209 |
+
"step": 75000
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 1.942621896307732,
|
| 1213 |
+
"grad_norm": 6.980623245239258,
|
| 1214 |
+
"learning_rate": 1.7622968394871137e-05,
|
| 1215 |
+
"loss": 2.9175,
|
| 1216 |
+
"num_input_tokens_seen": 43991200,
|
| 1217 |
+
"step": 75500
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 1.955486941978644,
|
| 1221 |
+
"grad_norm": 6.8675456047058105,
|
| 1222 |
+
"learning_rate": 1.74085509670226e-05,
|
| 1223 |
+
"loss": 2.9169,
|
| 1224 |
+
"num_input_tokens_seen": 44281424,
|
| 1225 |
+
"step": 76000
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 1.968351987649556,
|
| 1229 |
+
"grad_norm": 6.631172180175781,
|
| 1230 |
+
"learning_rate": 1.7194133539174064e-05,
|
| 1231 |
+
"loss": 2.9198,
|
| 1232 |
+
"num_input_tokens_seen": 44569856,
|
| 1233 |
+
"step": 76500
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 1.9812170333204682,
|
| 1237 |
+
"grad_norm": 6.995504379272461,
|
| 1238 |
+
"learning_rate": 1.697971611132553e-05,
|
| 1239 |
+
"loss": 2.9182,
|
| 1240 |
+
"num_input_tokens_seen": 44862968,
|
| 1241 |
+
"step": 77000
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.9940820789913805,
|
| 1245 |
+
"grad_norm": 7.234148979187012,
|
| 1246 |
+
"learning_rate": 1.6765298683476992e-05,
|
| 1247 |
+
"loss": 2.9226,
|
| 1248 |
+
"num_input_tokens_seen": 45153272,
|
| 1249 |
+
"step": 77500
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 2.0069471246622927,
|
| 1253 |
+
"grad_norm": 6.20206356048584,
|
| 1254 |
+
"learning_rate": 1.6550881255628457e-05,
|
| 1255 |
+
"loss": 2.8863,
|
| 1256 |
+
"num_input_tokens_seen": 45443152,
|
| 1257 |
+
"step": 78000
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 2.019812170333205,
|
| 1261 |
+
"grad_norm": 6.416888236999512,
|
| 1262 |
+
"learning_rate": 1.6336463827779923e-05,
|
| 1263 |
+
"loss": 2.7699,
|
| 1264 |
+
"num_input_tokens_seen": 45732040,
|
| 1265 |
+
"step": 78500
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 2.032677216004117,
|
| 1269 |
+
"grad_norm": 7.381237506866455,
|
| 1270 |
+
"learning_rate": 1.612204639993139e-05,
|
| 1271 |
+
"loss": 2.7847,
|
| 1272 |
+
"num_input_tokens_seen": 46022712,
|
| 1273 |
+
"step": 79000
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 2.045542261675029,
|
| 1277 |
+
"grad_norm": 6.199607849121094,
|
| 1278 |
+
"learning_rate": 1.5907628972082854e-05,
|
| 1279 |
+
"loss": 2.7676,
|
| 1280 |
+
"num_input_tokens_seen": 46315064,
|
| 1281 |
+
"step": 79500
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 2.058407307345941,
|
| 1285 |
+
"grad_norm": 6.7973456382751465,
|
| 1286 |
+
"learning_rate": 1.5693211544234316e-05,
|
| 1287 |
+
"loss": 2.7909,
|
| 1288 |
+
"num_input_tokens_seen": 46608096,
|
| 1289 |
+
"step": 80000
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 2.071272353016853,
|
| 1293 |
+
"grad_norm": 5.843527317047119,
|
| 1294 |
+
"learning_rate": 1.547879411638578e-05,
|
| 1295 |
+
"loss": 2.7965,
|
| 1296 |
+
"num_input_tokens_seen": 46896800,
|
| 1297 |
+
"step": 80500
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 2.084137398687765,
|
| 1301 |
+
"grad_norm": 6.95015811920166,
|
| 1302 |
+
"learning_rate": 1.5264376688537247e-05,
|
| 1303 |
+
"loss": 2.7969,
|
| 1304 |
+
"num_input_tokens_seen": 47190120,
|
| 1305 |
+
"step": 81000
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 2.0970024443586777,
|
| 1309 |
+
"grad_norm": 7.737337589263916,
|
| 1310 |
+
"learning_rate": 1.5049959260688709e-05,
|
| 1311 |
+
"loss": 2.7876,
|
| 1312 |
+
"num_input_tokens_seen": 47483520,
|
| 1313 |
+
"step": 81500
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 2.1098674900295897,
|
| 1317 |
+
"grad_norm": 7.859601974487305,
|
| 1318 |
+
"learning_rate": 1.4835541832840174e-05,
|
| 1319 |
+
"loss": 2.7888,
|
| 1320 |
+
"num_input_tokens_seen": 47769600,
|
| 1321 |
+
"step": 82000
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 2.122732535700502,
|
| 1325 |
+
"grad_norm": 5.804116725921631,
|
| 1326 |
+
"learning_rate": 1.4621124404991638e-05,
|
| 1327 |
+
"loss": 2.7868,
|
| 1328 |
+
"num_input_tokens_seen": 48064320,
|
| 1329 |
+
"step": 82500
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 2.135597581371414,
|
| 1333 |
+
"grad_norm": 6.726932048797607,
|
| 1334 |
+
"learning_rate": 1.4406706977143104e-05,
|
| 1335 |
+
"loss": 2.8175,
|
| 1336 |
+
"num_input_tokens_seen": 48355560,
|
| 1337 |
+
"step": 83000
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 2.148462627042326,
|
| 1341 |
+
"grad_norm": 6.097367763519287,
|
| 1342 |
+
"learning_rate": 1.4192289549294569e-05,
|
| 1343 |
+
"loss": 2.7876,
|
| 1344 |
+
"num_input_tokens_seen": 48644608,
|
| 1345 |
+
"step": 83500
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 2.161327672713238,
|
| 1349 |
+
"grad_norm": 8.123278617858887,
|
| 1350 |
+
"learning_rate": 1.3977872121446031e-05,
|
| 1351 |
+
"loss": 2.7795,
|
| 1352 |
+
"num_input_tokens_seen": 48934720,
|
| 1353 |
+
"step": 84000
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 2.17419271838415,
|
| 1357 |
+
"grad_norm": 6.270246505737305,
|
| 1358 |
+
"learning_rate": 1.3763454693597497e-05,
|
| 1359 |
+
"loss": 2.7723,
|
| 1360 |
+
"num_input_tokens_seen": 49227264,
|
| 1361 |
+
"step": 84500
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 2.1870577640550626,
|
| 1365 |
+
"grad_norm": 7.330353260040283,
|
| 1366 |
+
"learning_rate": 1.354903726574896e-05,
|
| 1367 |
+
"loss": 2.7704,
|
| 1368 |
+
"num_input_tokens_seen": 49518072,
|
| 1369 |
+
"step": 85000
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 2.1999228097259746,
|
| 1373 |
+
"grad_norm": 7.461730003356934,
|
| 1374 |
+
"learning_rate": 1.3334619837900426e-05,
|
| 1375 |
+
"loss": 2.7744,
|
| 1376 |
+
"num_input_tokens_seen": 49809432,
|
| 1377 |
+
"step": 85500
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 2.2127878553968867,
|
| 1381 |
+
"grad_norm": 5.806447505950928,
|
| 1382 |
+
"learning_rate": 1.3120202410051891e-05,
|
| 1383 |
+
"loss": 2.7776,
|
| 1384 |
+
"num_input_tokens_seen": 50093416,
|
| 1385 |
+
"step": 86000
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 2.225652901067799,
|
| 1389 |
+
"grad_norm": 5.978988170623779,
|
| 1390 |
+
"learning_rate": 1.2905784982203353e-05,
|
| 1391 |
+
"loss": 2.7773,
|
| 1392 |
+
"num_input_tokens_seen": 50386496,
|
| 1393 |
+
"step": 86500
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"epoch": 2.238517946738711,
|
| 1397 |
+
"grad_norm": 6.581029891967773,
|
| 1398 |
+
"learning_rate": 1.2691367554354819e-05,
|
| 1399 |
+
"loss": 2.8044,
|
| 1400 |
+
"num_input_tokens_seen": 50680456,
|
| 1401 |
+
"step": 87000
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 2.251382992409623,
|
| 1405 |
+
"grad_norm": 6.622259616851807,
|
| 1406 |
+
"learning_rate": 1.2476950126506282e-05,
|
| 1407 |
+
"loss": 2.7959,
|
| 1408 |
+
"num_input_tokens_seen": 50973488,
|
| 1409 |
+
"step": 87500
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 2.2642480380805354,
|
| 1413 |
+
"grad_norm": 9.183111190795898,
|
| 1414 |
+
"learning_rate": 1.2262532698657748e-05,
|
| 1415 |
+
"loss": 2.7865,
|
| 1416 |
+
"num_input_tokens_seen": 51266744,
|
| 1417 |
+
"step": 88000
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 2.2771130837514475,
|
| 1421 |
+
"grad_norm": 6.282793045043945,
|
| 1422 |
+
"learning_rate": 1.2048115270809212e-05,
|
| 1423 |
+
"loss": 2.7768,
|
| 1424 |
+
"num_input_tokens_seen": 51556696,
|
| 1425 |
+
"step": 88500
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 2.2899781294223596,
|
| 1429 |
+
"grad_norm": 6.839522838592529,
|
| 1430 |
+
"learning_rate": 1.1833697842960677e-05,
|
| 1431 |
+
"loss": 2.7936,
|
| 1432 |
+
"num_input_tokens_seen": 51848936,
|
| 1433 |
+
"step": 89000
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 2.3028431750932716,
|
| 1437 |
+
"grad_norm": 5.936497211456299,
|
| 1438 |
+
"learning_rate": 1.1619280415112141e-05,
|
| 1439 |
+
"loss": 2.807,
|
| 1440 |
+
"num_input_tokens_seen": 52140680,
|
| 1441 |
+
"step": 89500
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 2.3157082207641837,
|
| 1445 |
+
"grad_norm": 6.789340972900391,
|
| 1446 |
+
"learning_rate": 1.1404862987263605e-05,
|
| 1447 |
+
"loss": 2.7843,
|
| 1448 |
+
"num_input_tokens_seen": 52429888,
|
| 1449 |
+
"step": 90000
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 2.3285732664350958,
|
| 1453 |
+
"grad_norm": 6.576247692108154,
|
| 1454 |
+
"learning_rate": 1.1190445559415068e-05,
|
| 1455 |
+
"loss": 2.7724,
|
| 1456 |
+
"num_input_tokens_seen": 52721144,
|
| 1457 |
+
"step": 90500
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 2.341438312106008,
|
| 1461 |
+
"grad_norm": 6.2103166580200195,
|
| 1462 |
+
"learning_rate": 1.0976028131566536e-05,
|
| 1463 |
+
"loss": 2.7929,
|
| 1464 |
+
"num_input_tokens_seen": 53013648,
|
| 1465 |
+
"step": 91000
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 2.35430335777692,
|
| 1469 |
+
"grad_norm": 7.041256904602051,
|
| 1470 |
+
"learning_rate": 1.0761610703718e-05,
|
| 1471 |
+
"loss": 2.7657,
|
| 1472 |
+
"num_input_tokens_seen": 53302912,
|
| 1473 |
+
"step": 91500
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 2.3671684034478324,
|
| 1477 |
+
"grad_norm": 6.339066028594971,
|
| 1478 |
+
"learning_rate": 1.0547193275869463e-05,
|
| 1479 |
+
"loss": 2.7841,
|
| 1480 |
+
"num_input_tokens_seen": 53596464,
|
| 1481 |
+
"step": 92000
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 2.3800334491187445,
|
| 1485 |
+
"grad_norm": 7.0336833000183105,
|
| 1486 |
+
"learning_rate": 1.0332775848020927e-05,
|
| 1487 |
+
"loss": 2.7859,
|
| 1488 |
+
"num_input_tokens_seen": 53886496,
|
| 1489 |
+
"step": 92500
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"epoch": 2.3928984947896565,
|
| 1493 |
+
"grad_norm": 5.826415538787842,
|
| 1494 |
+
"learning_rate": 1.0118358420172392e-05,
|
| 1495 |
+
"loss": 2.8007,
|
| 1496 |
+
"num_input_tokens_seen": 54176264,
|
| 1497 |
+
"step": 93000
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 2.4057635404605686,
|
| 1501 |
+
"grad_norm": 6.1079487800598145,
|
| 1502 |
+
"learning_rate": 9.903940992323856e-06,
|
| 1503 |
+
"loss": 2.7775,
|
| 1504 |
+
"num_input_tokens_seen": 54466856,
|
| 1505 |
+
"step": 93500
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 2.4186285861314807,
|
| 1509 |
+
"grad_norm": 5.203562259674072,
|
| 1510 |
+
"learning_rate": 9.689523564475322e-06,
|
| 1511 |
+
"loss": 2.7554,
|
| 1512 |
+
"num_input_tokens_seen": 54759176,
|
| 1513 |
+
"step": 94000
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 2.4314936318023928,
|
| 1517 |
+
"grad_norm": 6.122252941131592,
|
| 1518 |
+
"learning_rate": 9.475106136626785e-06,
|
| 1519 |
+
"loss": 2.7709,
|
| 1520 |
+
"num_input_tokens_seen": 55051272,
|
| 1521 |
+
"step": 94500
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 2.4443586774733053,
|
| 1525 |
+
"grad_norm": 6.208186149597168,
|
| 1526 |
+
"learning_rate": 9.260688708778249e-06,
|
| 1527 |
+
"loss": 2.7717,
|
| 1528 |
+
"num_input_tokens_seen": 55344160,
|
| 1529 |
+
"step": 95000
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 2.4572237231442173,
|
| 1533 |
+
"grad_norm": 6.000925064086914,
|
| 1534 |
+
"learning_rate": 9.046271280929714e-06,
|
| 1535 |
+
"loss": 2.7627,
|
| 1536 |
+
"num_input_tokens_seen": 55636256,
|
| 1537 |
+
"step": 95500
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 2.4700887688151294,
|
| 1541 |
+
"grad_norm": 7.118528842926025,
|
| 1542 |
+
"learning_rate": 8.831853853081178e-06,
|
| 1543 |
+
"loss": 2.7891,
|
| 1544 |
+
"num_input_tokens_seen": 55926232,
|
| 1545 |
+
"step": 96000
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 2.4829538144860415,
|
| 1549 |
+
"grad_norm": 6.965567111968994,
|
| 1550 |
+
"learning_rate": 8.617436425232644e-06,
|
| 1551 |
+
"loss": 2.7854,
|
| 1552 |
+
"num_input_tokens_seen": 56217216,
|
| 1553 |
+
"step": 96500
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 2.4958188601569535,
|
| 1557 |
+
"grad_norm": 6.334046840667725,
|
| 1558 |
+
"learning_rate": 8.403018997384107e-06,
|
| 1559 |
+
"loss": 2.7741,
|
| 1560 |
+
"num_input_tokens_seen": 56502960,
|
| 1561 |
+
"step": 97000
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 2.5086839058278656,
|
| 1565 |
+
"grad_norm": 6.356966495513916,
|
| 1566 |
+
"learning_rate": 8.188601569535573e-06,
|
| 1567 |
+
"loss": 2.7821,
|
| 1568 |
+
"num_input_tokens_seen": 56796832,
|
| 1569 |
+
"step": 97500
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 2.5215489514987777,
|
| 1573 |
+
"grad_norm": 6.108860015869141,
|
| 1574 |
+
"learning_rate": 7.974184141687037e-06,
|
| 1575 |
+
"loss": 2.7624,
|
| 1576 |
+
"num_input_tokens_seen": 57090056,
|
| 1577 |
+
"step": 98000
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 2.5344139971696897,
|
| 1581 |
+
"grad_norm": 6.559696197509766,
|
| 1582 |
+
"learning_rate": 7.7597667138385e-06,
|
| 1583 |
+
"loss": 2.7728,
|
| 1584 |
+
"num_input_tokens_seen": 57378920,
|
| 1585 |
+
"step": 98500
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 2.5472790428406022,
|
| 1589 |
+
"grad_norm": 7.9952473640441895,
|
| 1590 |
+
"learning_rate": 7.545349285989965e-06,
|
| 1591 |
+
"loss": 2.7741,
|
| 1592 |
+
"num_input_tokens_seen": 57672696,
|
| 1593 |
+
"step": 99000
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 2.5601440885115143,
|
| 1597 |
+
"grad_norm": 5.8723320960998535,
|
| 1598 |
+
"learning_rate": 7.3309318581414305e-06,
|
| 1599 |
+
"loss": 2.7708,
|
| 1600 |
+
"num_input_tokens_seen": 57962544,
|
| 1601 |
+
"step": 99500
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"epoch": 2.5730091341824264,
|
| 1605 |
+
"grad_norm": 5.872036933898926,
|
| 1606 |
+
"learning_rate": 7.116514430292895e-06,
|
| 1607 |
+
"loss": 2.754,
|
| 1608 |
+
"num_input_tokens_seen": 58254712,
|
| 1609 |
+
"step": 100000
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 2.5858741798533385,
|
| 1613 |
+
"grad_norm": 6.854528427124023,
|
| 1614 |
+
"learning_rate": 6.902097002444359e-06,
|
| 1615 |
+
"loss": 2.7553,
|
| 1616 |
+
"num_input_tokens_seen": 58547432,
|
| 1617 |
+
"step": 100500
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 2.5987392255242505,
|
| 1621 |
+
"grad_norm": 6.242632865905762,
|
| 1622 |
+
"learning_rate": 6.6876795745958235e-06,
|
| 1623 |
+
"loss": 2.7555,
|
| 1624 |
+
"num_input_tokens_seen": 58839640,
|
| 1625 |
+
"step": 101000
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 2.6116042711951626,
|
| 1629 |
+
"grad_norm": 5.893955230712891,
|
| 1630 |
+
"learning_rate": 6.473262146747287e-06,
|
| 1631 |
+
"loss": 2.743,
|
| 1632 |
+
"num_input_tokens_seen": 59126568,
|
| 1633 |
+
"step": 101500
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 2.624469316866075,
|
| 1637 |
+
"grad_norm": 7.543076038360596,
|
| 1638 |
+
"learning_rate": 6.258844718898753e-06,
|
| 1639 |
+
"loss": 2.7901,
|
| 1640 |
+
"num_input_tokens_seen": 59416160,
|
| 1641 |
+
"step": 102000
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 2.637334362536987,
|
| 1645 |
+
"grad_norm": 6.379047870635986,
|
| 1646 |
+
"learning_rate": 6.044427291050217e-06,
|
| 1647 |
+
"loss": 2.7763,
|
| 1648 |
+
"num_input_tokens_seen": 59705440,
|
| 1649 |
+
"step": 102500
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 2.6501994082078992,
|
| 1653 |
+
"grad_norm": 7.814338684082031,
|
| 1654 |
+
"learning_rate": 5.830009863201681e-06,
|
| 1655 |
+
"loss": 2.7587,
|
| 1656 |
+
"num_input_tokens_seen": 59997352,
|
| 1657 |
+
"step": 103000
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 2.6630644538788113,
|
| 1661 |
+
"grad_norm": 6.58440637588501,
|
| 1662 |
+
"learning_rate": 5.615592435353146e-06,
|
| 1663 |
+
"loss": 2.7562,
|
| 1664 |
+
"num_input_tokens_seen": 60289912,
|
| 1665 |
+
"step": 103500
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 2.6759294995497234,
|
| 1669 |
+
"grad_norm": 5.680325984954834,
|
| 1670 |
+
"learning_rate": 5.40117500750461e-06,
|
| 1671 |
+
"loss": 2.7502,
|
| 1672 |
+
"num_input_tokens_seen": 60580920,
|
| 1673 |
+
"step": 104000
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 2.6887945452206354,
|
| 1677 |
+
"grad_norm": 6.846250534057617,
|
| 1678 |
+
"learning_rate": 5.186757579656075e-06,
|
| 1679 |
+
"loss": 2.7138,
|
| 1680 |
+
"num_input_tokens_seen": 60874824,
|
| 1681 |
+
"step": 104500
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 2.7016595908915475,
|
| 1685 |
+
"grad_norm": 5.211071014404297,
|
| 1686 |
+
"learning_rate": 4.9723401518075395e-06,
|
| 1687 |
+
"loss": 2.777,
|
| 1688 |
+
"num_input_tokens_seen": 61169240,
|
| 1689 |
+
"step": 105000
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 2.7145246365624596,
|
| 1693 |
+
"grad_norm": 6.492147445678711,
|
| 1694 |
+
"learning_rate": 4.757922723959004e-06,
|
| 1695 |
+
"loss": 2.7709,
|
| 1696 |
+
"num_input_tokens_seen": 61457952,
|
| 1697 |
+
"step": 105500
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 2.727389682233372,
|
| 1701 |
+
"grad_norm": 6.307532787322998,
|
| 1702 |
+
"learning_rate": 4.543505296110468e-06,
|
| 1703 |
+
"loss": 2.7632,
|
| 1704 |
+
"num_input_tokens_seen": 61747000,
|
| 1705 |
+
"step": 106000
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 2.740254727904284,
|
| 1709 |
+
"grad_norm": 6.944429874420166,
|
| 1710 |
+
"learning_rate": 4.3290878682619325e-06,
|
| 1711 |
+
"loss": 2.7721,
|
| 1712 |
+
"num_input_tokens_seen": 62037496,
|
| 1713 |
+
"step": 106500
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 2.753119773575196,
|
| 1717 |
+
"grad_norm": 7.263415813446045,
|
| 1718 |
+
"learning_rate": 4.114670440413397e-06,
|
| 1719 |
+
"loss": 2.7227,
|
| 1720 |
+
"num_input_tokens_seen": 62328752,
|
| 1721 |
+
"step": 107000
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 2.7659848192461083,
|
| 1725 |
+
"grad_norm": 6.571951389312744,
|
| 1726 |
+
"learning_rate": 3.900253012564861e-06,
|
| 1727 |
+
"loss": 2.7442,
|
| 1728 |
+
"num_input_tokens_seen": 62623568,
|
| 1729 |
+
"step": 107500
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 2.7788498649170204,
|
| 1733 |
+
"grad_norm": 5.274496078491211,
|
| 1734 |
+
"learning_rate": 3.685835584716326e-06,
|
| 1735 |
+
"loss": 2.7609,
|
| 1736 |
+
"num_input_tokens_seen": 62911280,
|
| 1737 |
+
"step": 108000
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 2.791714910587933,
|
| 1741 |
+
"grad_norm": 5.882663249969482,
|
| 1742 |
+
"learning_rate": 3.47141815686779e-06,
|
| 1743 |
+
"loss": 2.7322,
|
| 1744 |
+
"num_input_tokens_seen": 63204016,
|
| 1745 |
+
"step": 108500
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 2.804579956258845,
|
| 1749 |
+
"grad_norm": 6.151833534240723,
|
| 1750 |
+
"learning_rate": 3.257000729019255e-06,
|
| 1751 |
+
"loss": 2.7582,
|
| 1752 |
+
"num_input_tokens_seen": 63493976,
|
| 1753 |
+
"step": 109000
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 2.817445001929757,
|
| 1757 |
+
"grad_norm": 6.4147233963012695,
|
| 1758 |
+
"learning_rate": 3.0425833011707193e-06,
|
| 1759 |
+
"loss": 2.7465,
|
| 1760 |
+
"num_input_tokens_seen": 63788848,
|
| 1761 |
+
"step": 109500
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 2.830310047600669,
|
| 1765 |
+
"grad_norm": 7.0969414710998535,
|
| 1766 |
+
"learning_rate": 2.8281658733221834e-06,
|
| 1767 |
+
"loss": 2.7422,
|
| 1768 |
+
"num_input_tokens_seen": 64079248,
|
| 1769 |
+
"step": 110000
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 2.843175093271581,
|
| 1773 |
+
"grad_norm": 6.523220539093018,
|
| 1774 |
+
"learning_rate": 2.613748445473648e-06,
|
| 1775 |
+
"loss": 2.7598,
|
| 1776 |
+
"num_input_tokens_seen": 64370480,
|
| 1777 |
+
"step": 110500
|
| 1778 |
+
},
|
| 1779 |
+
{
|
| 1780 |
+
"epoch": 2.856040138942493,
|
| 1781 |
+
"grad_norm": 6.571617126464844,
|
| 1782 |
+
"learning_rate": 2.3993310176251127e-06,
|
| 1783 |
+
"loss": 2.7381,
|
| 1784 |
+
"num_input_tokens_seen": 64660624,
|
| 1785 |
+
"step": 111000
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 2.8689051846134053,
|
| 1789 |
+
"grad_norm": 6.383349895477295,
|
| 1790 |
+
"learning_rate": 2.1849135897765773e-06,
|
| 1791 |
+
"loss": 2.738,
|
| 1792 |
+
"num_input_tokens_seen": 64949432,
|
| 1793 |
+
"step": 111500
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 2.8817702302843173,
|
| 1797 |
+
"grad_norm": 6.797569751739502,
|
| 1798 |
+
"learning_rate": 1.9704961619280415e-06,
|
| 1799 |
+
"loss": 2.7539,
|
| 1800 |
+
"num_input_tokens_seen": 65243120,
|
| 1801 |
+
"step": 112000
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 2.8946352759552294,
|
| 1805 |
+
"grad_norm": 6.340763568878174,
|
| 1806 |
+
"learning_rate": 1.756078734079506e-06,
|
| 1807 |
+
"loss": 2.7239,
|
| 1808 |
+
"num_input_tokens_seen": 65535664,
|
| 1809 |
+
"step": 112500
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 2.907500321626142,
|
| 1813 |
+
"grad_norm": 5.992878437042236,
|
| 1814 |
+
"learning_rate": 1.5416613062309707e-06,
|
| 1815 |
+
"loss": 2.7459,
|
| 1816 |
+
"num_input_tokens_seen": 65826080,
|
| 1817 |
+
"step": 113000
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 2.920365367297054,
|
| 1821 |
+
"grad_norm": 6.328054904937744,
|
| 1822 |
+
"learning_rate": 1.3272438783824349e-06,
|
| 1823 |
+
"loss": 2.7524,
|
| 1824 |
+
"num_input_tokens_seen": 66121728,
|
| 1825 |
+
"step": 113500
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"epoch": 2.933230412967966,
|
| 1829 |
+
"grad_norm": 5.5994486808776855,
|
| 1830 |
+
"learning_rate": 1.1128264505338995e-06,
|
| 1831 |
+
"loss": 2.7688,
|
| 1832 |
+
"num_input_tokens_seen": 66410432,
|
| 1833 |
+
"step": 114000
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 2.946095458638878,
|
| 1837 |
+
"grad_norm": 6.498249053955078,
|
| 1838 |
+
"learning_rate": 8.984090226853639e-07,
|
| 1839 |
+
"loss": 2.762,
|
| 1840 |
+
"num_input_tokens_seen": 66703552,
|
| 1841 |
+
"step": 114500
|
| 1842 |
+
},
|
| 1843 |
+
{
|
| 1844 |
+
"epoch": 2.95896050430979,
|
| 1845 |
+
"grad_norm": 5.900263786315918,
|
| 1846 |
+
"learning_rate": 6.839915948368284e-07,
|
| 1847 |
+
"loss": 2.7559,
|
| 1848 |
+
"num_input_tokens_seen": 66994216,
|
| 1849 |
+
"step": 115000
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 2.9718255499807027,
|
| 1853 |
+
"grad_norm": 6.3716864585876465,
|
| 1854 |
+
"learning_rate": 4.6957416698829286e-07,
|
| 1855 |
+
"loss": 2.7289,
|
| 1856 |
+
"num_input_tokens_seen": 67284840,
|
| 1857 |
+
"step": 115500
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 2.9846905956516148,
|
| 1861 |
+
"grad_norm": 7.285637378692627,
|
| 1862 |
+
"learning_rate": 2.5515673913975725e-07,
|
| 1863 |
+
"loss": 2.7593,
|
| 1864 |
+
"num_input_tokens_seen": 67578272,
|
| 1865 |
+
"step": 116000
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 2.997555641322527,
|
| 1869 |
+
"grad_norm": 5.382935523986816,
|
| 1870 |
+
"learning_rate": 4.073931129122175e-08,
|
| 1871 |
+
"loss": 2.7668,
|
| 1872 |
+
"num_input_tokens_seen": 67872888,
|
| 1873 |
+
"step": 116500
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"epoch": 3.0,
|
| 1877 |
+
"num_input_tokens_seen": 67927868,
|
| 1878 |
+
"step": 116595,
|
| 1879 |
+
"total_flos": 1.7989403580039168e+16,
|
| 1880 |
+
"train_loss": 1.1922986107342055,
|
| 1881 |
+
"train_runtime": 2155.3414,
|
| 1882 |
+
"train_samples_per_second": 432.761,
|
| 1883 |
+
"train_steps_per_second": 54.096,
|
| 1884 |
+
"train_tokens_per_second": 31520.605
|
| 1885 |
+
}
|
| 1886 |
+
],
|
| 1887 |
+
"logging_steps": 500,
|
| 1888 |
+
"max_steps": 116595,
|
| 1889 |
+
"num_input_tokens_seen": 67927868,
|
| 1890 |
+
"num_train_epochs": 3,
|
| 1891 |
+
"save_steps": 500,
|
| 1892 |
+
"stateful_callbacks": {
|
| 1893 |
+
"TrainerControl": {
|
| 1894 |
+
"args": {
|
| 1895 |
+
"should_epoch_stop": false,
|
| 1896 |
+
"should_evaluate": false,
|
| 1897 |
+
"should_log": false,
|
| 1898 |
+
"should_save": true,
|
| 1899 |
+
"should_training_stop": true
|
| 1900 |
+
},
|
| 1901 |
+
"attributes": {}
|
| 1902 |
+
}
|
| 1903 |
+
},
|
| 1904 |
+
"total_flos": 1.7989403580039168e+16,
|
| 1905 |
+
"train_batch_size": 8,
|
| 1906 |
+
"trial_name": null,
|
| 1907 |
+
"trial_params": null
|
| 1908 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2ab7adeb91926a4ec4ef2638ee7aa6be062e73ea336464fe5971f4ecd328639
|
| 3 |
+
size 5368
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|