Add HuggingFaceH4/qwen-1.5-0.5b-ift-v1.0 checkpoint
Browse files- README.md +67 -0
- added_tokens.json +5 -0
- all_results.json +14 -0
- config.json +28 -0
- eval_results.json +9 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +21 -0
- tokenizer.json +0 -0
- tokenizer_config.json +43 -0
- train_results.json +8 -0
- trainer_state.json +1055 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
base_model: Qwen/Qwen1.5-0.5B
|
| 4 |
+
tags:
|
| 5 |
+
- alignment-handbook
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
datasets:
|
| 8 |
+
- HuggingFaceH4/deita-6k-v0-sft
|
| 9 |
+
model-index:
|
| 10 |
+
- name: qwen-1.5-0.5b-sft-v1.0
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# qwen-1.5-0.5b-sft-v1.0
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen1.5-0.5B](https://huggingface.co/Qwen/Qwen1.5-0.5B) on the HuggingFaceH4/deita-6k-v0-sft dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.2566
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 2e-05
|
| 41 |
+
- train_batch_size: 16
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- num_devices: 8
|
| 46 |
+
- total_train_batch_size: 128
|
| 47 |
+
- total_eval_batch_size: 64
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: cosine
|
| 50 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 51 |
+
- num_epochs: 3
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 57 |
+
| 1.3015 | 1.0 | 237 | 1.2711 |
|
| 58 |
+
| 1.2352 | 2.0 | 474 | 1.2562 |
|
| 59 |
+
| 1.1719 | 3.0 | 711 | 1.2566 |
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
### Framework versions
|
| 63 |
+
|
| 64 |
+
- Transformers 4.39.0.dev0
|
| 65 |
+
- Pytorch 2.1.2+cu121
|
| 66 |
+
- Datasets 2.16.1
|
| 67 |
+
- Tokenizers 0.15.1
|
added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|endoftext|>": 151643,
|
| 3 |
+
"<|im_end|>": 151645,
|
| 4 |
+
"<|im_start|>": 151644
|
| 5 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 1.2565690279006958,
|
| 4 |
+
"eval_runtime": 4.0099,
|
| 5 |
+
"eval_samples": 300,
|
| 6 |
+
"eval_samples_per_second": 367.59,
|
| 7 |
+
"eval_steps_per_second": 5.985,
|
| 8 |
+
"perplexity": 3.51334659076565,
|
| 9 |
+
"train_loss": 1.242754081298195,
|
| 10 |
+
"train_runtime": 610.9223,
|
| 11 |
+
"train_samples": 5700,
|
| 12 |
+
"train_samples_per_second": 148.462,
|
| 13 |
+
"train_steps_per_second": 1.164
|
| 14 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Qwen/Qwen1.5-0.5B",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151643,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 1024,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 2816,
|
| 13 |
+
"max_position_embeddings": 32768,
|
| 14 |
+
"max_window_layers": 21,
|
| 15 |
+
"model_type": "qwen2",
|
| 16 |
+
"num_attention_heads": 16,
|
| 17 |
+
"num_hidden_layers": 24,
|
| 18 |
+
"num_key_value_heads": 16,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_theta": 1000000.0,
|
| 21 |
+
"sliding_window": 32768,
|
| 22 |
+
"tie_word_embeddings": true,
|
| 23 |
+
"torch_dtype": "bfloat16",
|
| 24 |
+
"transformers_version": "4.39.0.dev0",
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"use_sliding_window": false,
|
| 27 |
+
"vocab_size": 151648
|
| 28 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 1.2565690279006958,
|
| 4 |
+
"eval_runtime": 4.0099,
|
| 5 |
+
"eval_samples": 300,
|
| 6 |
+
"eval_samples_per_second": 367.59,
|
| 7 |
+
"eval_steps_per_second": 5.985,
|
| 8 |
+
"perplexity": 3.51334659076565
|
| 9 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"eos_token_id": 151643,
|
| 4 |
+
"max_new_tokens": 2048,
|
| 5 |
+
"transformers_version": "4.39.0.dev0"
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fa986d548b1f928cb3da32cded697707267c9d8ff5643743818b4d993ccabbd
|
| 3 |
+
size 927418280
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<|im_start|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"content": "<|im_end|>",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
}
|
| 17 |
+
],
|
| 18 |
+
"bos_token": "<|im_start|>",
|
| 19 |
+
"eos_token": "<|im_end|>",
|
| 20 |
+
"pad_token": "<|im_end|>"
|
| 21 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"151643": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"151644": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"151645": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
}
|
| 28 |
+
},
|
| 29 |
+
"additional_special_tokens": [
|
| 30 |
+
"<|im_start|>",
|
| 31 |
+
"<|im_end|>"
|
| 32 |
+
],
|
| 33 |
+
"bos_token": "<|im_start|>",
|
| 34 |
+
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 35 |
+
"clean_up_tokenization_spaces": false,
|
| 36 |
+
"eos_token": "<|im_end|>",
|
| 37 |
+
"errors": "replace",
|
| 38 |
+
"model_max_length": 32768,
|
| 39 |
+
"pad_token": "<|im_end|>",
|
| 40 |
+
"split_special_tokens": false,
|
| 41 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 42 |
+
"unk_token": null
|
| 43 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 1.242754081298195,
|
| 4 |
+
"train_runtime": 610.9223,
|
| 5 |
+
"train_samples": 5700,
|
| 6 |
+
"train_samples_per_second": 148.462,
|
| 7 |
+
"train_steps_per_second": 1.164
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1055 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 711,
|
| 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 |
+
"grad_norm": 6.7530055713569785,
|
| 14 |
+
"learning_rate": 2.7777777777777776e-07,
|
| 15 |
+
"loss": 1.4781,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.02,
|
| 20 |
+
"grad_norm": 6.606048584660583,
|
| 21 |
+
"learning_rate": 1.3888888888888892e-06,
|
| 22 |
+
"loss": 1.3861,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.04,
|
| 27 |
+
"grad_norm": 5.138983961367188,
|
| 28 |
+
"learning_rate": 2.7777777777777783e-06,
|
| 29 |
+
"loss": 1.4422,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.06,
|
| 34 |
+
"grad_norm": 1.2528549295189984,
|
| 35 |
+
"learning_rate": 4.166666666666667e-06,
|
| 36 |
+
"loss": 1.3677,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.08,
|
| 41 |
+
"grad_norm": 1.6826024664234687,
|
| 42 |
+
"learning_rate": 5.555555555555557e-06,
|
| 43 |
+
"loss": 1.3277,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.11,
|
| 48 |
+
"grad_norm": 1.049153253140281,
|
| 49 |
+
"learning_rate": 6.944444444444445e-06,
|
| 50 |
+
"loss": 1.3513,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.13,
|
| 55 |
+
"grad_norm": 1.1637754450319215,
|
| 56 |
+
"learning_rate": 8.333333333333334e-06,
|
| 57 |
+
"loss": 1.3602,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.15,
|
| 62 |
+
"grad_norm": 0.9614901239317104,
|
| 63 |
+
"learning_rate": 9.722222222222223e-06,
|
| 64 |
+
"loss": 1.3316,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.17,
|
| 69 |
+
"grad_norm": 0.8800168840313798,
|
| 70 |
+
"learning_rate": 1.1111111111111113e-05,
|
| 71 |
+
"loss": 1.2865,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.19,
|
| 76 |
+
"grad_norm": 0.8743147668040568,
|
| 77 |
+
"learning_rate": 1.25e-05,
|
| 78 |
+
"loss": 1.3439,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.21,
|
| 83 |
+
"grad_norm": 0.8090973361916171,
|
| 84 |
+
"learning_rate": 1.388888888888889e-05,
|
| 85 |
+
"loss": 1.3323,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.23,
|
| 90 |
+
"grad_norm": 0.7791934698691907,
|
| 91 |
+
"learning_rate": 1.5277777777777777e-05,
|
| 92 |
+
"loss": 1.3316,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.25,
|
| 97 |
+
"grad_norm": 0.7332468554264387,
|
| 98 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 99 |
+
"loss": 1.3418,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.27,
|
| 104 |
+
"grad_norm": 0.7367875442634256,
|
| 105 |
+
"learning_rate": 1.8055555555555558e-05,
|
| 106 |
+
"loss": 1.3488,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.3,
|
| 111 |
+
"grad_norm": 3.454271660640428,
|
| 112 |
+
"learning_rate": 1.9444444444444445e-05,
|
| 113 |
+
"loss": 1.3402,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.32,
|
| 118 |
+
"grad_norm": 1.41303669264439,
|
| 119 |
+
"learning_rate": 1.999891231617599e-05,
|
| 120 |
+
"loss": 1.3198,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.34,
|
| 125 |
+
"grad_norm": 0.7111760423501922,
|
| 126 |
+
"learning_rate": 1.9992266216318037e-05,
|
| 127 |
+
"loss": 1.291,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.36,
|
| 132 |
+
"grad_norm": 0.6985734110465796,
|
| 133 |
+
"learning_rate": 1.997958229642588e-05,
|
| 134 |
+
"loss": 1.3195,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.38,
|
| 139 |
+
"grad_norm": 0.6774596159630265,
|
| 140 |
+
"learning_rate": 1.996086822074945e-05,
|
| 141 |
+
"loss": 1.3296,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.4,
|
| 146 |
+
"grad_norm": 0.68714971160374,
|
| 147 |
+
"learning_rate": 1.9936135297256183e-05,
|
| 148 |
+
"loss": 1.3106,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.42,
|
| 153 |
+
"grad_norm": 0.7055100697390134,
|
| 154 |
+
"learning_rate": 1.9905398470798207e-05,
|
| 155 |
+
"loss": 1.3251,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.44,
|
| 160 |
+
"grad_norm": 0.7442856779901117,
|
| 161 |
+
"learning_rate": 1.9868676314081907e-05,
|
| 162 |
+
"loss": 1.3154,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.46,
|
| 167 |
+
"grad_norm": 0.6786674709866586,
|
| 168 |
+
"learning_rate": 1.9825991016445387e-05,
|
| 169 |
+
"loss": 1.305,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.49,
|
| 174 |
+
"grad_norm": 0.701320710348796,
|
| 175 |
+
"learning_rate": 1.9777368370450582e-05,
|
| 176 |
+
"loss": 1.2797,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.51,
|
| 181 |
+
"grad_norm": 0.7694290958620503,
|
| 182 |
+
"learning_rate": 1.9722837756298112e-05,
|
| 183 |
+
"loss": 1.3094,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.53,
|
| 188 |
+
"grad_norm": 0.7198163251696982,
|
| 189 |
+
"learning_rate": 1.9662432124074325e-05,
|
| 190 |
+
"loss": 1.3283,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.55,
|
| 195 |
+
"grad_norm": 0.7451781825097182,
|
| 196 |
+
"learning_rate": 1.9596187973841218e-05,
|
| 197 |
+
"loss": 1.2966,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.57,
|
| 202 |
+
"grad_norm": 0.7153678487864736,
|
| 203 |
+
"learning_rate": 1.9524145333581315e-05,
|
| 204 |
+
"loss": 1.3192,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.59,
|
| 209 |
+
"grad_norm": 2.8370131166342687,
|
| 210 |
+
"learning_rate": 1.9446347735010765e-05,
|
| 211 |
+
"loss": 1.2988,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.61,
|
| 216 |
+
"grad_norm": 0.7273784346266812,
|
| 217 |
+
"learning_rate": 1.9362842187275354e-05,
|
| 218 |
+
"loss": 1.2815,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.63,
|
| 223 |
+
"grad_norm": 0.7610942375358005,
|
| 224 |
+
"learning_rate": 1.9273679148545246e-05,
|
| 225 |
+
"loss": 1.3121,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.65,
|
| 230 |
+
"grad_norm": 0.719303870712118,
|
| 231 |
+
"learning_rate": 1.917891249552568e-05,
|
| 232 |
+
"loss": 1.3196,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.68,
|
| 237 |
+
"grad_norm": 0.6786014692189536,
|
| 238 |
+
"learning_rate": 1.9078599490901984e-05,
|
| 239 |
+
"loss": 1.3033,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.7,
|
| 244 |
+
"grad_norm": 0.6704522856064519,
|
| 245 |
+
"learning_rate": 1.897280074873868e-05,
|
| 246 |
+
"loss": 1.2896,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.72,
|
| 251 |
+
"grad_norm": 0.6769924161484794,
|
| 252 |
+
"learning_rate": 1.8861580197853423e-05,
|
| 253 |
+
"loss": 1.2808,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.74,
|
| 258 |
+
"grad_norm": 0.7274733092656871,
|
| 259 |
+
"learning_rate": 1.8745005043188104e-05,
|
| 260 |
+
"loss": 1.3052,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.76,
|
| 265 |
+
"grad_norm": 0.7143035239809652,
|
| 266 |
+
"learning_rate": 1.862314572520028e-05,
|
| 267 |
+
"loss": 1.3003,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.78,
|
| 272 |
+
"grad_norm": 0.7146392109064191,
|
| 273 |
+
"learning_rate": 1.8496075877299585e-05,
|
| 274 |
+
"loss": 1.2748,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.8,
|
| 279 |
+
"grad_norm": 0.7061207940556439,
|
| 280 |
+
"learning_rate": 1.8363872281354796e-05,
|
| 281 |
+
"loss": 1.305,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.82,
|
| 286 |
+
"grad_norm": 0.6945437033981094,
|
| 287 |
+
"learning_rate": 1.8226614821298444e-05,
|
| 288 |
+
"loss": 1.3006,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.84,
|
| 293 |
+
"grad_norm": 0.6847371880670944,
|
| 294 |
+
"learning_rate": 1.808438643485698e-05,
|
| 295 |
+
"loss": 1.2705,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.86,
|
| 300 |
+
"grad_norm": 0.6784008869899278,
|
| 301 |
+
"learning_rate": 1.793727306343574e-05,
|
| 302 |
+
"loss": 1.2532,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.89,
|
| 307 |
+
"grad_norm": 0.7037870009631069,
|
| 308 |
+
"learning_rate": 1.7785363600188894e-05,
|
| 309 |
+
"loss": 1.2638,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.91,
|
| 314 |
+
"grad_norm": 0.6664930383710185,
|
| 315 |
+
"learning_rate": 1.762874983630582e-05,
|
| 316 |
+
"loss": 1.2586,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.93,
|
| 321 |
+
"grad_norm": 0.6773413303705628,
|
| 322 |
+
"learning_rate": 1.7467526405546344e-05,
|
| 323 |
+
"loss": 1.3138,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.95,
|
| 328 |
+
"grad_norm": 0.6935109696579653,
|
| 329 |
+
"learning_rate": 1.7301790727058344e-05,
|
| 330 |
+
"loss": 1.2752,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.97,
|
| 335 |
+
"grad_norm": 0.7212086786238647,
|
| 336 |
+
"learning_rate": 1.7131642946512314e-05,
|
| 337 |
+
"loss": 1.3091,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.99,
|
| 342 |
+
"grad_norm": 0.7924454572717287,
|
| 343 |
+
"learning_rate": 1.6957185875588403e-05,
|
| 344 |
+
"loss": 1.3015,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.0,
|
| 349 |
+
"eval_loss": 1.2710920572280884,
|
| 350 |
+
"eval_runtime": 4.2577,
|
| 351 |
+
"eval_samples_per_second": 346.195,
|
| 352 |
+
"eval_steps_per_second": 5.637,
|
| 353 |
+
"step": 237
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.01,
|
| 357 |
+
"grad_norm": 0.796377689560899,
|
| 358 |
+
"learning_rate": 1.6778524929852513e-05,
|
| 359 |
+
"loss": 1.2628,
|
| 360 |
+
"step": 240
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.03,
|
| 364 |
+
"grad_norm": 0.7364886186224426,
|
| 365 |
+
"learning_rate": 1.659576806505905e-05,
|
| 366 |
+
"loss": 1.2284,
|
| 367 |
+
"step": 245
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.05,
|
| 371 |
+
"grad_norm": 0.7049213011696083,
|
| 372 |
+
"learning_rate": 1.640902571191869e-05,
|
| 373 |
+
"loss": 1.2187,
|
| 374 |
+
"step": 250
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.08,
|
| 378 |
+
"grad_norm": 1.9377903386730986,
|
| 379 |
+
"learning_rate": 1.6218410709370735e-05,
|
| 380 |
+
"loss": 1.2438,
|
| 381 |
+
"step": 255
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.1,
|
| 385 |
+
"grad_norm": 0.7011828464498495,
|
| 386 |
+
"learning_rate": 1.6024038236400246e-05,
|
| 387 |
+
"loss": 1.1998,
|
| 388 |
+
"step": 260
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.12,
|
| 392 |
+
"grad_norm": 2.5996069923788436,
|
| 393 |
+
"learning_rate": 1.582602574244121e-05,
|
| 394 |
+
"loss": 1.1919,
|
| 395 |
+
"step": 265
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.14,
|
| 399 |
+
"grad_norm": 0.679979871549876,
|
| 400 |
+
"learning_rate": 1.562449287640781e-05,
|
| 401 |
+
"loss": 1.2456,
|
| 402 |
+
"step": 270
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.16,
|
| 406 |
+
"grad_norm": 0.71927352282914,
|
| 407 |
+
"learning_rate": 1.5419561414396657e-05,
|
| 408 |
+
"loss": 1.2493,
|
| 409 |
+
"step": 275
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.18,
|
| 413 |
+
"grad_norm": 0.7190913662714845,
|
| 414 |
+
"learning_rate": 1.5211355186103655e-05,
|
| 415 |
+
"loss": 1.2058,
|
| 416 |
+
"step": 280
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.2,
|
| 420 |
+
"grad_norm": 0.7182017182110072,
|
| 421 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 422 |
+
"loss": 1.2371,
|
| 423 |
+
"step": 285
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.22,
|
| 427 |
+
"grad_norm": 0.705180903431495,
|
| 428 |
+
"learning_rate": 1.4785623567312492e-05,
|
| 429 |
+
"loss": 1.1976,
|
| 430 |
+
"step": 290
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.24,
|
| 434 |
+
"grad_norm": 0.6883033004979775,
|
| 435 |
+
"learning_rate": 1.4568355424854113e-05,
|
| 436 |
+
"loss": 1.2768,
|
| 437 |
+
"step": 295
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.27,
|
| 441 |
+
"grad_norm": 0.6815574246451964,
|
| 442 |
+
"learning_rate": 1.4348326856751496e-05,
|
| 443 |
+
"loss": 1.2334,
|
| 444 |
+
"step": 300
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.29,
|
| 448 |
+
"grad_norm": 0.6804999351991194,
|
| 449 |
+
"learning_rate": 1.412567081511659e-05,
|
| 450 |
+
"loss": 1.2183,
|
| 451 |
+
"step": 305
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.31,
|
| 455 |
+
"grad_norm": 0.7193921850993512,
|
| 456 |
+
"learning_rate": 1.3900521839710428e-05,
|
| 457 |
+
"loss": 1.2032,
|
| 458 |
+
"step": 310
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.33,
|
| 462 |
+
"grad_norm": 0.6954927887572464,
|
| 463 |
+
"learning_rate": 1.367301597664757e-05,
|
| 464 |
+
"loss": 1.2289,
|
| 465 |
+
"step": 315
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.35,
|
| 469 |
+
"grad_norm": 0.708546670689236,
|
| 470 |
+
"learning_rate": 1.3443290696190335e-05,
|
| 471 |
+
"loss": 1.229,
|
| 472 |
+
"step": 320
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.37,
|
| 476 |
+
"grad_norm": 0.7124305795556933,
|
| 477 |
+
"learning_rate": 1.3211484809682482e-05,
|
| 478 |
+
"loss": 1.2434,
|
| 479 |
+
"step": 325
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.39,
|
| 483 |
+
"grad_norm": 0.6866449286630997,
|
| 484 |
+
"learning_rate": 1.2977738385672558e-05,
|
| 485 |
+
"loss": 1.2587,
|
| 486 |
+
"step": 330
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.41,
|
| 490 |
+
"grad_norm": 0.7158743341618767,
|
| 491 |
+
"learning_rate": 1.2742192665277569e-05,
|
| 492 |
+
"loss": 1.2522,
|
| 493 |
+
"step": 335
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.43,
|
| 497 |
+
"grad_norm": 0.6741832926767023,
|
| 498 |
+
"learning_rate": 1.250498997683813e-05,
|
| 499 |
+
"loss": 1.2318,
|
| 500 |
+
"step": 340
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.46,
|
| 504 |
+
"grad_norm": 0.7018162451875303,
|
| 505 |
+
"learning_rate": 1.2266273649916669e-05,
|
| 506 |
+
"loss": 1.2017,
|
| 507 |
+
"step": 345
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.48,
|
| 511 |
+
"grad_norm": 0.6814770297513967,
|
| 512 |
+
"learning_rate": 1.202618792869063e-05,
|
| 513 |
+
"loss": 1.2043,
|
| 514 |
+
"step": 350
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.5,
|
| 518 |
+
"grad_norm": 0.6877213251148805,
|
| 519 |
+
"learning_rate": 1.178487788479303e-05,
|
| 520 |
+
"loss": 1.216,
|
| 521 |
+
"step": 355
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.52,
|
| 525 |
+
"grad_norm": 0.6722566603288663,
|
| 526 |
+
"learning_rate": 1.1542489329653024e-05,
|
| 527 |
+
"loss": 1.2367,
|
| 528 |
+
"step": 360
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.54,
|
| 532 |
+
"grad_norm": 0.6835971864599367,
|
| 533 |
+
"learning_rate": 1.129916872638945e-05,
|
| 534 |
+
"loss": 1.2611,
|
| 535 |
+
"step": 365
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.56,
|
| 539 |
+
"grad_norm": 0.7040578619734443,
|
| 540 |
+
"learning_rate": 1.1055063101310581e-05,
|
| 541 |
+
"loss": 1.2252,
|
| 542 |
+
"step": 370
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.58,
|
| 546 |
+
"grad_norm": 0.679881563899439,
|
| 547 |
+
"learning_rate": 1.08103199550736e-05,
|
| 548 |
+
"loss": 1.2321,
|
| 549 |
+
"step": 375
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.6,
|
| 553 |
+
"grad_norm": 0.6794312105046864,
|
| 554 |
+
"learning_rate": 1.0565087173557396e-05,
|
| 555 |
+
"loss": 1.2252,
|
| 556 |
+
"step": 380
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.62,
|
| 560 |
+
"grad_norm": 0.6889618373928458,
|
| 561 |
+
"learning_rate": 1.0319512938502654e-05,
|
| 562 |
+
"loss": 1.2256,
|
| 563 |
+
"step": 385
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.65,
|
| 567 |
+
"grad_norm": 0.6921906751981153,
|
| 568 |
+
"learning_rate": 1.0073745637973125e-05,
|
| 569 |
+
"loss": 1.2344,
|
| 570 |
+
"step": 390
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.67,
|
| 574 |
+
"grad_norm": 0.6993543043577237,
|
| 575 |
+
"learning_rate": 9.827933776692236e-06,
|
| 576 |
+
"loss": 1.2391,
|
| 577 |
+
"step": 395
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.69,
|
| 581 |
+
"grad_norm": 0.6959462039565184,
|
| 582 |
+
"learning_rate": 9.582225886309217e-06,
|
| 583 |
+
"loss": 1.2155,
|
| 584 |
+
"step": 400
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.71,
|
| 588 |
+
"grad_norm": 0.6863551427574576,
|
| 589 |
+
"learning_rate": 9.336770435648963e-06,
|
| 590 |
+
"loss": 1.252,
|
| 591 |
+
"step": 405
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.73,
|
| 595 |
+
"grad_norm": 0.7184772923029549,
|
| 596 |
+
"learning_rate": 9.091715740999829e-06,
|
| 597 |
+
"loss": 1.2295,
|
| 598 |
+
"step": 410
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.75,
|
| 602 |
+
"grad_norm": 0.6949962185725445,
|
| 603 |
+
"learning_rate": 8.84720987649363e-06,
|
| 604 |
+
"loss": 1.2044,
|
| 605 |
+
"step": 415
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.77,
|
| 609 |
+
"grad_norm": 0.6710588422516326,
|
| 610 |
+
"learning_rate": 8.60340058463194e-06,
|
| 611 |
+
"loss": 1.2407,
|
| 612 |
+
"step": 420
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.79,
|
| 616 |
+
"grad_norm": 0.6482064194341762,
|
| 617 |
+
"learning_rate": 8.360435187012789e-06,
|
| 618 |
+
"loss": 1.2637,
|
| 619 |
+
"step": 425
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.81,
|
| 623 |
+
"grad_norm": 0.6715553002740511,
|
| 624 |
+
"learning_rate": 8.118460495311687e-06,
|
| 625 |
+
"loss": 1.2795,
|
| 626 |
+
"step": 430
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.84,
|
| 630 |
+
"grad_norm": 1.1764818802442565,
|
| 631 |
+
"learning_rate": 7.877622722570772e-06,
|
| 632 |
+
"loss": 1.2228,
|
| 633 |
+
"step": 435
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.86,
|
| 637 |
+
"grad_norm": 0.6932612325260208,
|
| 638 |
+
"learning_rate": 7.638067394849672e-06,
|
| 639 |
+
"loss": 1.2272,
|
| 640 |
+
"step": 440
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.88,
|
| 644 |
+
"grad_norm": 0.7017921905179951,
|
| 645 |
+
"learning_rate": 7.3999392632914936e-06,
|
| 646 |
+
"loss": 1.2476,
|
| 647 |
+
"step": 445
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.9,
|
| 651 |
+
"grad_norm": 0.6556538474805375,
|
| 652 |
+
"learning_rate": 7.163382216657033e-06,
|
| 653 |
+
"loss": 1.2249,
|
| 654 |
+
"step": 450
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.92,
|
| 658 |
+
"grad_norm": 0.6649783838358192,
|
| 659 |
+
"learning_rate": 6.928539194380101e-06,
|
| 660 |
+
"loss": 1.2166,
|
| 661 |
+
"step": 455
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.94,
|
| 665 |
+
"grad_norm": 0.6582704106972542,
|
| 666 |
+
"learning_rate": 6.6955521001964526e-06,
|
| 667 |
+
"loss": 1.2149,
|
| 668 |
+
"step": 460
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.96,
|
| 672 |
+
"grad_norm": 0.6842373684969378,
|
| 673 |
+
"learning_rate": 6.464561716398565e-06,
|
| 674 |
+
"loss": 1.2089,
|
| 675 |
+
"step": 465
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.98,
|
| 679 |
+
"grad_norm": 0.6763842453630291,
|
| 680 |
+
"learning_rate": 6.2357076187680325e-06,
|
| 681 |
+
"loss": 1.2352,
|
| 682 |
+
"step": 470
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 2.0,
|
| 686 |
+
"eval_loss": 1.2562438249588013,
|
| 687 |
+
"eval_runtime": 4.0229,
|
| 688 |
+
"eval_samples_per_second": 366.403,
|
| 689 |
+
"eval_steps_per_second": 5.966,
|
| 690 |
+
"step": 474
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.0,
|
| 694 |
+
"grad_norm": 0.703770585858162,
|
| 695 |
+
"learning_rate": 6.009128092236983e-06,
|
| 696 |
+
"loss": 1.2048,
|
| 697 |
+
"step": 475
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.03,
|
| 701 |
+
"grad_norm": 0.6786892775253128,
|
| 702 |
+
"learning_rate": 5.78496004732952e-06,
|
| 703 |
+
"loss": 1.1518,
|
| 704 |
+
"step": 480
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.05,
|
| 708 |
+
"grad_norm": 0.70326378053169,
|
| 709 |
+
"learning_rate": 5.563338937433622e-06,
|
| 710 |
+
"loss": 1.197,
|
| 711 |
+
"step": 485
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.07,
|
| 715 |
+
"grad_norm": 0.6916875060651468,
|
| 716 |
+
"learning_rate": 5.344398676953526e-06,
|
| 717 |
+
"loss": 1.2111,
|
| 718 |
+
"step": 490
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.09,
|
| 722 |
+
"grad_norm": 0.6475152204206446,
|
| 723 |
+
"learning_rate": 5.128271560392037e-06,
|
| 724 |
+
"loss": 1.1739,
|
| 725 |
+
"step": 495
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 2.11,
|
| 729 |
+
"grad_norm": 0.6813942164053138,
|
| 730 |
+
"learning_rate": 4.915088182411674e-06,
|
| 731 |
+
"loss": 1.1905,
|
| 732 |
+
"step": 500
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 2.13,
|
| 736 |
+
"grad_norm": 0.6486602612694303,
|
| 737 |
+
"learning_rate": 4.7049773589229306e-06,
|
| 738 |
+
"loss": 1.2063,
|
| 739 |
+
"step": 505
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 2.15,
|
| 743 |
+
"grad_norm": 0.6731868552171755,
|
| 744 |
+
"learning_rate": 4.498066049247344e-06,
|
| 745 |
+
"loss": 1.2198,
|
| 746 |
+
"step": 510
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 2.17,
|
| 750 |
+
"grad_norm": 0.685788252482629,
|
| 751 |
+
"learning_rate": 4.29447927940242e-06,
|
| 752 |
+
"loss": 1.1706,
|
| 753 |
+
"step": 515
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 2.19,
|
| 757 |
+
"grad_norm": 0.6713780690925405,
|
| 758 |
+
"learning_rate": 4.094340066554742e-06,
|
| 759 |
+
"loss": 1.1887,
|
| 760 |
+
"step": 520
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 2.22,
|
| 764 |
+
"grad_norm": 0.6669181028932704,
|
| 765 |
+
"learning_rate": 3.897769344686929e-06,
|
| 766 |
+
"loss": 1.1933,
|
| 767 |
+
"step": 525
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 2.24,
|
| 771 |
+
"grad_norm": 0.6681179890022899,
|
| 772 |
+
"learning_rate": 3.7048858915233665e-06,
|
| 773 |
+
"loss": 1.2061,
|
| 774 |
+
"step": 530
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 2.26,
|
| 778 |
+
"grad_norm": 0.6688074058150556,
|
| 779 |
+
"learning_rate": 3.5158062567588468e-06,
|
| 780 |
+
"loss": 1.1585,
|
| 781 |
+
"step": 535
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 2.28,
|
| 785 |
+
"grad_norm": 0.6500738740113599,
|
| 786 |
+
"learning_rate": 3.330644691633492e-06,
|
| 787 |
+
"loss": 1.1793,
|
| 788 |
+
"step": 540
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 2.3,
|
| 792 |
+
"grad_norm": 0.6546313173839559,
|
| 793 |
+
"learning_rate": 3.149513079896521e-06,
|
| 794 |
+
"loss": 1.2088,
|
| 795 |
+
"step": 545
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 2.32,
|
| 799 |
+
"grad_norm": 0.6544093029161898,
|
| 800 |
+
"learning_rate": 2.9725208702005736e-06,
|
| 801 |
+
"loss": 1.1975,
|
| 802 |
+
"step": 550
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 2.34,
|
| 806 |
+
"grad_norm": 0.6458002129205276,
|
| 807 |
+
"learning_rate": 2.7997750099674282e-06,
|
| 808 |
+
"loss": 1.1913,
|
| 809 |
+
"step": 555
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 2.36,
|
| 813 |
+
"grad_norm": 0.6571017394804074,
|
| 814 |
+
"learning_rate": 2.631379880765107e-06,
|
| 815 |
+
"loss": 1.1876,
|
| 816 |
+
"step": 560
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 2.38,
|
| 820 |
+
"grad_norm": 0.6563720392014831,
|
| 821 |
+
"learning_rate": 2.467437235235378e-06,
|
| 822 |
+
"loss": 1.1677,
|
| 823 |
+
"step": 565
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 2.41,
|
| 827 |
+
"grad_norm": 0.6640825824608834,
|
| 828 |
+
"learning_rate": 2.3080461356097938e-06,
|
| 829 |
+
"loss": 1.1876,
|
| 830 |
+
"step": 570
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 2.43,
|
| 834 |
+
"grad_norm": 0.6332904461492966,
|
| 835 |
+
"learning_rate": 2.153302893851401e-06,
|
| 836 |
+
"loss": 1.1553,
|
| 837 |
+
"step": 575
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 2.45,
|
| 841 |
+
"grad_norm": 0.654023164181366,
|
| 842 |
+
"learning_rate": 2.0033010134583085e-06,
|
| 843 |
+
"loss": 1.1896,
|
| 844 |
+
"step": 580
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 2.47,
|
| 848 |
+
"grad_norm": 0.6359350507881623,
|
| 849 |
+
"learning_rate": 1.8581311329642592e-06,
|
| 850 |
+
"loss": 1.1526,
|
| 851 |
+
"step": 585
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 2.49,
|
| 855 |
+
"grad_norm": 0.6238559177863219,
|
| 856 |
+
"learning_rate": 1.7178809711703525e-06,
|
| 857 |
+
"loss": 1.1847,
|
| 858 |
+
"step": 590
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 2.51,
|
| 862 |
+
"grad_norm": 0.6479836099852851,
|
| 863 |
+
"learning_rate": 1.5826352741410333e-06,
|
| 864 |
+
"loss": 1.1883,
|
| 865 |
+
"step": 595
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 2.53,
|
| 869 |
+
"grad_norm": 0.6615350392909103,
|
| 870 |
+
"learning_rate": 1.452475763996326e-06,
|
| 871 |
+
"loss": 1.1562,
|
| 872 |
+
"step": 600
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 2.55,
|
| 876 |
+
"grad_norm": 0.659005508964398,
|
| 877 |
+
"learning_rate": 1.3274810895313083e-06,
|
| 878 |
+
"loss": 1.1666,
|
| 879 |
+
"step": 605
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 2.57,
|
| 883 |
+
"grad_norm": 0.6530124794164938,
|
| 884 |
+
"learning_rate": 1.207726778692625e-06,
|
| 885 |
+
"loss": 1.1694,
|
| 886 |
+
"step": 610
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 2.59,
|
| 890 |
+
"grad_norm": 0.637671650897288,
|
| 891 |
+
"learning_rate": 1.0932851929407828e-06,
|
| 892 |
+
"loss": 1.21,
|
| 893 |
+
"step": 615
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 2.62,
|
| 897 |
+
"grad_norm": 0.6426650375048046,
|
| 898 |
+
"learning_rate": 9.842254835257792e-07,
|
| 899 |
+
"loss": 1.1983,
|
| 900 |
+
"step": 620
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 2.64,
|
| 904 |
+
"grad_norm": 0.6549427233533902,
|
| 905 |
+
"learning_rate": 8.806135497025181e-07,
|
| 906 |
+
"loss": 1.1796,
|
| 907 |
+
"step": 625
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 2.66,
|
| 911 |
+
"grad_norm": 0.637483284013688,
|
| 912 |
+
"learning_rate": 7.825119989112173e-07,
|
| 913 |
+
"loss": 1.2032,
|
| 914 |
+
"step": 630
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 2.68,
|
| 918 |
+
"grad_norm": 0.6458643762516288,
|
| 919 |
+
"learning_rate": 6.899801089469205e-07,
|
| 920 |
+
"loss": 1.1898,
|
| 921 |
+
"step": 635
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 2.7,
|
| 925 |
+
"grad_norm": 0.6560437400254089,
|
| 926 |
+
"learning_rate": 6.030737921409169e-07,
|
| 927 |
+
"loss": 1.1815,
|
| 928 |
+
"step": 640
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 2.72,
|
| 932 |
+
"grad_norm": 0.6346340189110924,
|
| 933 |
+
"learning_rate": 5.218455615757601e-07,
|
| 934 |
+
"loss": 1.1829,
|
| 935 |
+
"step": 645
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 2.74,
|
| 939 |
+
"grad_norm": 0.6408145596532006,
|
| 940 |
+
"learning_rate": 4.4634449935427203e-07,
|
| 941 |
+
"loss": 1.1653,
|
| 942 |
+
"step": 650
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 2.76,
|
| 946 |
+
"grad_norm": 0.6553954626425612,
|
| 947 |
+
"learning_rate": 3.7661622694171393e-07,
|
| 948 |
+
"loss": 1.2129,
|
| 949 |
+
"step": 655
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 2.78,
|
| 953 |
+
"grad_norm": 0.6949305164155417,
|
| 954 |
+
"learning_rate": 3.127028775990515e-07,
|
| 955 |
+
"loss": 1.1822,
|
| 956 |
+
"step": 660
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 2.81,
|
| 960 |
+
"grad_norm": 0.6657650684680331,
|
| 961 |
+
"learning_rate": 2.546430709239578e-07,
|
| 962 |
+
"loss": 1.1818,
|
| 963 |
+
"step": 665
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 2.83,
|
| 967 |
+
"grad_norm": 0.6438354912565324,
|
| 968 |
+
"learning_rate": 2.02471889514948e-07,
|
| 969 |
+
"loss": 1.1696,
|
| 970 |
+
"step": 670
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 2.85,
|
| 974 |
+
"grad_norm": 0.6330124825001247,
|
| 975 |
+
"learning_rate": 1.562208577727442e-07,
|
| 976 |
+
"loss": 1.1443,
|
| 977 |
+
"step": 675
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 2.87,
|
| 981 |
+
"grad_norm": 0.6389378157102353,
|
| 982 |
+
"learning_rate": 1.1591792285167603e-07,
|
| 983 |
+
"loss": 1.1657,
|
| 984 |
+
"step": 680
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 2.89,
|
| 988 |
+
"grad_norm": 0.6353907126618263,
|
| 989 |
+
"learning_rate": 8.158743777263334e-08,
|
| 990 |
+
"loss": 1.183,
|
| 991 |
+
"step": 685
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 2.91,
|
| 995 |
+
"grad_norm": 0.644204938538006,
|
| 996 |
+
"learning_rate": 5.325014670776951e-08,
|
| 997 |
+
"loss": 1.1641,
|
| 998 |
+
"step": 690
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 2.93,
|
| 1002 |
+
"grad_norm": 0.6585816956828645,
|
| 1003 |
+
"learning_rate": 3.092317244584919e-08,
|
| 1004 |
+
"loss": 1.2134,
|
| 1005 |
+
"step": 695
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 2.95,
|
| 1009 |
+
"grad_norm": 0.6523630752795228,
|
| 1010 |
+
"learning_rate": 1.4620006045816814e-08,
|
| 1011 |
+
"loss": 1.2174,
|
| 1012 |
+
"step": 700
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 2.97,
|
| 1016 |
+
"grad_norm": 0.659207596228058,
|
| 1017 |
+
"learning_rate": 4.3504986848297295e-09,
|
| 1018 |
+
"loss": 1.1732,
|
| 1019 |
+
"step": 705
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 3.0,
|
| 1023 |
+
"grad_norm": 0.6428302138785816,
|
| 1024 |
+
"learning_rate": 1.2085570569642102e-10,
|
| 1025 |
+
"loss": 1.1719,
|
| 1026 |
+
"step": 710
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 3.0,
|
| 1030 |
+
"eval_loss": 1.2565690279006958,
|
| 1031 |
+
"eval_runtime": 4.0115,
|
| 1032 |
+
"eval_samples_per_second": 367.448,
|
| 1033 |
+
"eval_steps_per_second": 5.983,
|
| 1034 |
+
"step": 711
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 3.0,
|
| 1038 |
+
"step": 711,
|
| 1039 |
+
"total_flos": 138562624290816.0,
|
| 1040 |
+
"train_loss": 1.242754081298195,
|
| 1041 |
+
"train_runtime": 610.9223,
|
| 1042 |
+
"train_samples_per_second": 148.462,
|
| 1043 |
+
"train_steps_per_second": 1.164
|
| 1044 |
+
}
|
| 1045 |
+
],
|
| 1046 |
+
"logging_steps": 5,
|
| 1047 |
+
"max_steps": 711,
|
| 1048 |
+
"num_input_tokens_seen": 0,
|
| 1049 |
+
"num_train_epochs": 3,
|
| 1050 |
+
"save_steps": 100,
|
| 1051 |
+
"total_flos": 138562624290816.0,
|
| 1052 |
+
"train_batch_size": 16,
|
| 1053 |
+
"trial_name": null,
|
| 1054 |
+
"trial_params": null
|
| 1055 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a92ef2ea409da1f33aebe132541e59a6691e29d747db727837f2e99c2ee8547
|
| 3 |
+
size 6520
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|