Commit
•
0a8e533
1
Parent(s):
c6dd428
upload loras
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- llama2_13b_peft/abstract_narrative_understanding/README.md +78 -0
- llama2_13b_peft/abstract_narrative_understanding/adapter_config.json +33 -0
- llama2_13b_peft/abstract_narrative_understanding/adapter_model.safetensors +3 -0
- llama2_13b_peft/abstract_narrative_understanding/all_results.json +11 -0
- llama2_13b_peft/abstract_narrative_understanding/eval_results.json +7 -0
- llama2_13b_peft/abstract_narrative_understanding/special_tokens_map.json +24 -0
- llama2_13b_peft/abstract_narrative_understanding/tokenizer.model +3 -0
- llama2_13b_peft/abstract_narrative_understanding/tokenizer_config.json +45 -0
- llama2_13b_peft/abstract_narrative_understanding/train_results.json +7 -0
- llama2_13b_peft/abstract_narrative_understanding/trainer_log.jsonl +80 -0
- llama2_13b_peft/abstract_narrative_understanding/trainer_state.json +589 -0
- llama2_13b_peft/abstract_narrative_understanding/training_args.bin +3 -0
- llama2_13b_peft/abstract_narrative_understanding/training_eval_loss.png +0 -0
- llama2_13b_peft/abstract_narrative_understanding/training_loss.png +0 -0
- llama2_13b_peft/alpaca/README.md +81 -0
- llama2_13b_peft/alpaca/adapter_config.json +33 -0
- llama2_13b_peft/alpaca/adapter_model.safetensors +3 -0
- llama2_13b_peft/alpaca/all_results.json +11 -0
- llama2_13b_peft/alpaca/eval_results.json +7 -0
- llama2_13b_peft/alpaca/special_tokens_map.json +24 -0
- llama2_13b_peft/alpaca/tokenizer.model +3 -0
- llama2_13b_peft/alpaca/tokenizer_config.json +45 -0
- llama2_13b_peft/alpaca/train_results.json +7 -0
- llama2_13b_peft/alpaca/trainer_log.jsonl +338 -0
- llama2_13b_peft/alpaca/trainer_state.json +2398 -0
- llama2_13b_peft/alpaca/training_args.bin +3 -0
- llama2_13b_peft/alpaca/training_eval_loss.png +0 -0
- llama2_13b_peft/alpaca/training_loss.png +0 -0
- llama2_13b_peft/cnn_dailymail/README.md +82 -0
- llama2_13b_peft/cnn_dailymail/adapter_config.json +33 -0
- llama2_13b_peft/cnn_dailymail/adapter_model.safetensors +3 -0
- llama2_13b_peft/cnn_dailymail/all_results.json +11 -0
- llama2_13b_peft/cnn_dailymail/eval_results.json +7 -0
- llama2_13b_peft/cnn_dailymail/special_tokens_map.json +24 -0
- llama2_13b_peft/cnn_dailymail/tokenizer.model +3 -0
- llama2_13b_peft/cnn_dailymail/tokenizer_config.json +45 -0
- llama2_13b_peft/cnn_dailymail/train_results.json +7 -0
- llama2_13b_peft/cnn_dailymail/trainer_log.jsonl +104 -0
- llama2_13b_peft/cnn_dailymail/trainer_state.json +761 -0
- llama2_13b_peft/cnn_dailymail/training_args.bin +3 -0
- llama2_13b_peft/cnn_dailymail/training_eval_loss.png +0 -0
- llama2_13b_peft/cnn_dailymail/training_loss.png +0 -0
- llama2_13b_peft/contextual_parametric_knowledge_conflicts/README.md +78 -0
- llama2_13b_peft/contextual_parametric_knowledge_conflicts/adapter_config.json +33 -0
- llama2_13b_peft/contextual_parametric_knowledge_conflicts/adapter_model.safetensors +3 -0
- llama2_13b_peft/contextual_parametric_knowledge_conflicts/all_results.json +11 -0
- llama2_13b_peft/contextual_parametric_knowledge_conflicts/eval_results.json +7 -0
- llama2_13b_peft/contextual_parametric_knowledge_conflicts/special_tokens_map.json +24 -0
- llama2_13b_peft/contextual_parametric_knowledge_conflicts/tokenizer.model +3 -0
- llama2_13b_peft/contextual_parametric_knowledge_conflicts/tokenizer_config.json +45 -0
llama2_13b_peft/abstract_narrative_understanding/README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- llama-factory
|
| 6 |
+
- lora
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: /data1/model/llama2/meta-llama/Llama2-13b
|
| 9 |
+
model-index:
|
| 10 |
+
- name: abstract_narrative_understanding_no_sys
|
| 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 |
+
# abstract_narrative_understanding_no_sys
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [/data1/model/llama2/meta-llama/Llama2-13b](https://huggingface.co//data1/model/llama2/meta-llama/Llama2-13b) on the abstract_narrative_understanding_no_sys dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.0775
|
| 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: 0.0001
|
| 41 |
+
- train_batch_size: 8
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- num_devices: 3
|
| 46 |
+
- total_train_batch_size: 24
|
| 47 |
+
- total_eval_batch_size: 24
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: cosine
|
| 50 |
+
- lr_scheduler_warmup_steps: 20
|
| 51 |
+
- num_epochs: 10.0
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 57 |
+
| 0.1783 | 0.59 | 50 | 0.1586 |
|
| 58 |
+
| 0.076 | 1.18 | 100 | 0.1166 |
|
| 59 |
+
| 0.0666 | 1.76 | 150 | 0.0825 |
|
| 60 |
+
| 0.0173 | 2.35 | 200 | 0.0773 |
|
| 61 |
+
| 0.0269 | 2.94 | 250 | 0.0836 |
|
| 62 |
+
| 0.0066 | 3.53 | 300 | 0.0656 |
|
| 63 |
+
| 0.003 | 4.12 | 350 | 0.0645 |
|
| 64 |
+
| 0.0027 | 4.71 | 400 | 0.0729 |
|
| 65 |
+
| 0.0011 | 5.29 | 450 | 0.0678 |
|
| 66 |
+
| 0.0009 | 5.88 | 500 | 0.0775 |
|
| 67 |
+
| 0.0017 | 6.47 | 550 | 0.0782 |
|
| 68 |
+
| 0.0001 | 7.06 | 600 | 0.0793 |
|
| 69 |
+
| 0.0001 | 7.65 | 650 | 0.0812 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- PEFT 0.9.0
|
| 75 |
+
- Transformers 4.38.2
|
| 76 |
+
- Pytorch 2.2.1
|
| 77 |
+
- Datasets 2.18.0
|
| 78 |
+
- Tokenizers 0.15.2
|
llama2_13b_peft/abstract_narrative_understanding/adapter_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "/data1/model/llama2/meta-llama/Llama2-13b",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 16,
|
| 13 |
+
"lora_dropout": 0.0,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 8,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"k_proj",
|
| 23 |
+
"v_proj",
|
| 24 |
+
"down_proj",
|
| 25 |
+
"up_proj",
|
| 26 |
+
"o_proj",
|
| 27 |
+
"gate_proj",
|
| 28 |
+
"q_proj"
|
| 29 |
+
],
|
| 30 |
+
"task_type": "CAUSAL_LM",
|
| 31 |
+
"use_dora": false,
|
| 32 |
+
"use_rslora": false
|
| 33 |
+
}
|
llama2_13b_peft/abstract_narrative_understanding/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c278b153aa2effab442633e3e881c97d93a4b8bfa4b91a9121708bc0eb844274
|
| 3 |
+
size 125248064
|
llama2_13b_peft/abstract_narrative_understanding/all_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 7.65,
|
| 3 |
+
"eval_loss": 0.0775449350476265,
|
| 4 |
+
"eval_runtime": 18.6993,
|
| 5 |
+
"eval_samples_per_second": 19.252,
|
| 6 |
+
"eval_steps_per_second": 0.802,
|
| 7 |
+
"train_loss": 0.0863784014862568,
|
| 8 |
+
"train_runtime": 2843.6931,
|
| 9 |
+
"train_samples_per_second": 7.174,
|
| 10 |
+
"train_steps_per_second": 0.299
|
| 11 |
+
}
|
llama2_13b_peft/abstract_narrative_understanding/eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 7.65,
|
| 3 |
+
"eval_loss": 0.0775449350476265,
|
| 4 |
+
"eval_runtime": 18.6993,
|
| 5 |
+
"eval_samples_per_second": 19.252,
|
| 6 |
+
"eval_steps_per_second": 0.802
|
| 7 |
+
}
|
llama2_13b_peft/abstract_narrative_understanding/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
llama2_13b_peft/abstract_narrative_understanding/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
llama2_13b_peft/abstract_narrative_understanding/tokenizer_config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content + '\\n' }}{% endif %}{% endfor %}",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"legacy": true,
|
| 36 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
+
"pad_token": "</s>",
|
| 38 |
+
"padding_side": "right",
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"spaces_between_special_tokens": false,
|
| 41 |
+
"split_special_tokens": false,
|
| 42 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 43 |
+
"unk_token": "<unk>",
|
| 44 |
+
"use_default_system_prompt": false
|
| 45 |
+
}
|
llama2_13b_peft/abstract_narrative_understanding/train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 7.65,
|
| 3 |
+
"train_loss": 0.0863784014862568,
|
| 4 |
+
"train_runtime": 2843.6931,
|
| 5 |
+
"train_samples_per_second": 7.174,
|
| 6 |
+
"train_steps_per_second": 0.299
|
| 7 |
+
}
|
llama2_13b_peft/abstract_narrative_understanding/trainer_log.jsonl
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 10, "total_steps": 850, "loss": 2.3117, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5e-05, "epoch": 0.12, "percentage": 1.18, "elapsed_time": "0:00:40", "remaining_time": "0:57:16"}
|
| 2 |
+
{"current_steps": 20, "total_steps": 850, "loss": 1.1002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001, "epoch": 0.24, "percentage": 2.35, "elapsed_time": "0:01:20", "remaining_time": "0:55:30"}
|
| 3 |
+
{"current_steps": 30, "total_steps": 850, "loss": 0.291, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.996418774081658e-05, "epoch": 0.35, "percentage": 3.53, "elapsed_time": "0:02:00", "remaining_time": "0:54:43"}
|
| 4 |
+
{"current_steps": 40, "total_steps": 850, "loss": 0.2298, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.985680226398261e-05, "epoch": 0.47, "percentage": 4.71, "elapsed_time": "0:02:39", "remaining_time": "0:53:53"}
|
| 5 |
+
{"current_steps": 50, "total_steps": 850, "loss": 0.1783, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.967799739815925e-05, "epoch": 0.59, "percentage": 5.88, "elapsed_time": "0:03:19", "remaining_time": "0:53:14"}
|
| 6 |
+
{"current_steps": 50, "total_steps": 850, "loss": null, "eval_loss": 0.15855231881141663, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.59, "percentage": 5.88, "elapsed_time": "0:03:19", "remaining_time": "0:53:14"}
|
| 7 |
+
{"current_steps": 60, "total_steps": 850, "loss": 0.1504, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.942802927959443e-05, "epoch": 0.71, "percentage": 7.06, "elapsed_time": "0:04:18", "remaining_time": "0:56:43"}
|
| 8 |
+
{"current_steps": 70, "total_steps": 850, "loss": 0.1438, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.910725598521013e-05, "epoch": 0.82, "percentage": 8.24, "elapsed_time": "0:04:58", "remaining_time": "0:55:26"}
|
| 9 |
+
{"current_steps": 80, "total_steps": 850, "loss": 0.126, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.871613701966067e-05, "epoch": 0.94, "percentage": 9.41, "elapsed_time": "0:05:38", "remaining_time": "0:54:17"}
|
| 10 |
+
{"current_steps": 90, "total_steps": 850, "loss": 0.0922, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.825523265709666e-05, "epoch": 1.06, "percentage": 10.59, "elapsed_time": "0:06:19", "remaining_time": "0:53:23"}
|
| 11 |
+
{"current_steps": 100, "total_steps": 850, "loss": 0.076, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.772520313857775e-05, "epoch": 1.18, "percentage": 11.76, "elapsed_time": "0:06:58", "remaining_time": "0:52:21"}
|
| 12 |
+
{"current_steps": 100, "total_steps": 850, "loss": null, "eval_loss": 0.11661680787801743, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.18, "percentage": 11.76, "elapsed_time": "0:06:58", "remaining_time": "0:52:21"}
|
| 13 |
+
{"current_steps": 110, "total_steps": 850, "loss": 0.0649, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.712680772628364e-05, "epoch": 1.29, "percentage": 12.94, "elapsed_time": "0:07:57", "remaining_time": "0:53:31"}
|
| 14 |
+
{"current_steps": 120, "total_steps": 850, "loss": 0.099, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.646090361587827e-05, "epoch": 1.41, "percentage": 14.12, "elapsed_time": "0:08:37", "remaining_time": "0:52:28"}
|
| 15 |
+
{"current_steps": 130, "total_steps": 850, "loss": 0.0877, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.572844470858537e-05, "epoch": 1.53, "percentage": 15.29, "elapsed_time": "0:09:17", "remaining_time": "0:51:27"}
|
| 16 |
+
{"current_steps": 140, "total_steps": 850, "loss": 0.0804, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.493048024473412e-05, "epoch": 1.65, "percentage": 16.47, "elapsed_time": "0:09:57", "remaining_time": "0:50:29"}
|
| 17 |
+
{"current_steps": 150, "total_steps": 850, "loss": 0.0666, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.406815330073244e-05, "epoch": 1.76, "percentage": 17.65, "elapsed_time": "0:10:37", "remaining_time": "0:49:33"}
|
| 18 |
+
{"current_steps": 150, "total_steps": 850, "loss": null, "eval_loss": 0.08253820985555649, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.76, "percentage": 17.65, "elapsed_time": "0:10:37", "remaining_time": "0:49:33"}
|
| 19 |
+
{"current_steps": 160, "total_steps": 850, "loss": 0.0862, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.314269915162114e-05, "epoch": 1.88, "percentage": 18.82, "elapsed_time": "0:11:36", "remaining_time": "0:50:01"}
|
| 20 |
+
{"current_steps": 170, "total_steps": 850, "loss": 0.063, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.215544350155422e-05, "epoch": 2.0, "percentage": 20.0, "elapsed_time": "0:12:15", "remaining_time": "0:49:03"}
|
| 21 |
+
{"current_steps": 180, "total_steps": 850, "loss": 0.0407, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.110780058474052e-05, "epoch": 2.12, "percentage": 21.18, "elapsed_time": "0:12:55", "remaining_time": "0:48:06"}
|
| 22 |
+
{"current_steps": 190, "total_steps": 850, "loss": 0.0328, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.000127113956674e-05, "epoch": 2.24, "percentage": 22.35, "elapsed_time": "0:13:35", "remaining_time": "0:47:12"}
|
| 23 |
+
{"current_steps": 200, "total_steps": 850, "loss": 0.0173, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.883744025880428e-05, "epoch": 2.35, "percentage": 23.53, "elapsed_time": "0:14:15", "remaining_time": "0:46:19"}
|
| 24 |
+
{"current_steps": 200, "total_steps": 850, "loss": null, "eval_loss": 0.07726477831602097, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.35, "percentage": 23.53, "elapsed_time": "0:14:15", "remaining_time": "0:46:19"}
|
| 25 |
+
{"current_steps": 210, "total_steps": 850, "loss": 0.0353, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.761797511897906e-05, "epoch": 2.47, "percentage": 24.71, "elapsed_time": "0:15:14", "remaining_time": "0:46:26"}
|
| 26 |
+
{"current_steps": 220, "total_steps": 850, "loss": 0.0265, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.634462259215719e-05, "epoch": 2.59, "percentage": 25.88, "elapsed_time": "0:15:54", "remaining_time": "0:45:32"}
|
| 27 |
+
{"current_steps": 230, "total_steps": 850, "loss": 0.0346, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.501920674356754e-05, "epoch": 2.71, "percentage": 27.06, "elapsed_time": "0:16:33", "remaining_time": "0:44:38"}
|
| 28 |
+
{"current_steps": 240, "total_steps": 850, "loss": 0.0228, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.364362621864595e-05, "epoch": 2.82, "percentage": 28.24, "elapsed_time": "0:17:13", "remaining_time": "0:43:46"}
|
| 29 |
+
{"current_steps": 250, "total_steps": 850, "loss": 0.0269, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.221985152324385e-05, "epoch": 2.94, "percentage": 29.41, "elapsed_time": "0:17:53", "remaining_time": "0:42:55"}
|
| 30 |
+
{"current_steps": 250, "total_steps": 850, "loss": null, "eval_loss": 0.08358720690011978, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.94, "percentage": 29.41, "elapsed_time": "0:17:53", "remaining_time": "0:42:55"}
|
| 31 |
+
{"current_steps": 260, "total_steps": 850, "loss": 0.0168, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.074992220089769e-05, "epoch": 3.06, "percentage": 30.59, "elapsed_time": "0:18:52", "remaining_time": "0:42:48"}
|
| 32 |
+
{"current_steps": 270, "total_steps": 850, "loss": 0.0164, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.923594391120236e-05, "epoch": 3.18, "percentage": 31.76, "elapsed_time": "0:19:31", "remaining_time": "0:41:56"}
|
| 33 |
+
{"current_steps": 280, "total_steps": 850, "loss": 0.0068, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.768008541347423e-05, "epoch": 3.29, "percentage": 32.94, "elapsed_time": "0:20:12", "remaining_time": "0:41:08"}
|
| 34 |
+
{"current_steps": 290, "total_steps": 850, "loss": 0.0141, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.608457546002424e-05, "epoch": 3.41, "percentage": 34.12, "elapsed_time": "0:20:52", "remaining_time": "0:40:19"}
|
| 35 |
+
{"current_steps": 300, "total_steps": 850, "loss": 0.0066, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.445169960349167e-05, "epoch": 3.53, "percentage": 35.29, "elapsed_time": "0:21:32", "remaining_time": "0:39:29"}
|
| 36 |
+
{"current_steps": 300, "total_steps": 850, "loss": null, "eval_loss": 0.06564046442508698, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.53, "percentage": 35.29, "elapsed_time": "0:21:32", "remaining_time": "0:39:29"}
|
| 37 |
+
{"current_steps": 310, "total_steps": 850, "loss": 0.0071, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.278379692281208e-05, "epoch": 3.65, "percentage": 36.47, "elapsed_time": "0:22:31", "remaining_time": "0:39:13"}
|
| 38 |
+
{"current_steps": 320, "total_steps": 850, "loss": 0.0065, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.10832566725092e-05, "epoch": 3.76, "percentage": 37.65, "elapsed_time": "0:23:10", "remaining_time": "0:38:23"}
|
| 39 |
+
{"current_steps": 330, "total_steps": 850, "loss": 0.005, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.935251486011087e-05, "epoch": 3.88, "percentage": 38.82, "elapsed_time": "0:23:50", "remaining_time": "0:37:34"}
|
| 40 |
+
{"current_steps": 340, "total_steps": 850, "loss": 0.0138, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.759405075659166e-05, "epoch": 4.0, "percentage": 40.0, "elapsed_time": "0:24:30", "remaining_time": "0:36:46"}
|
| 41 |
+
{"current_steps": 350, "total_steps": 850, "loss": 0.003, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.58103833448412e-05, "epoch": 4.12, "percentage": 41.18, "elapsed_time": "0:25:10", "remaining_time": "0:35:57"}
|
| 42 |
+
{"current_steps": 350, "total_steps": 850, "loss": null, "eval_loss": 0.06447144597768784, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.12, "percentage": 41.18, "elapsed_time": "0:25:10", "remaining_time": "0:35:57"}
|
| 43 |
+
{"current_steps": 360, "total_steps": 850, "loss": 0.0044, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.400406771124536e-05, "epoch": 4.24, "percentage": 42.35, "elapsed_time": "0:26:09", "remaining_time": "0:35:35"}
|
| 44 |
+
{"current_steps": 370, "total_steps": 850, "loss": 0.0045, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.21776913855496e-05, "epoch": 4.35, "percentage": 43.53, "elapsed_time": "0:26:48", "remaining_time": "0:34:47"}
|
| 45 |
+
{"current_steps": 380, "total_steps": 850, "loss": 0.0066, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.0333870634247645e-05, "epoch": 4.47, "percentage": 44.71, "elapsed_time": "0:27:29", "remaining_time": "0:33:59"}
|
| 46 |
+
{"current_steps": 390, "total_steps": 850, "loss": 0.0019, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.847524671280484e-05, "epoch": 4.59, "percentage": 45.88, "elapsed_time": "0:28:09", "remaining_time": "0:33:12"}
|
| 47 |
+
{"current_steps": 400, "total_steps": 850, "loss": 0.0027, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.660448208208513e-05, "epoch": 4.71, "percentage": 47.06, "elapsed_time": "0:28:49", "remaining_time": "0:32:25"}
|
| 48 |
+
{"current_steps": 400, "total_steps": 850, "loss": null, "eval_loss": 0.0728691965341568, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.71, "percentage": 47.06, "elapsed_time": "0:28:49", "remaining_time": "0:32:25"}
|
| 49 |
+
{"current_steps": 410, "total_steps": 850, "loss": 0.0054, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.472425659440157e-05, "epoch": 4.82, "percentage": 48.24, "elapsed_time": "0:29:47", "remaining_time": "0:31:58"}
|
| 50 |
+
{"current_steps": 420, "total_steps": 850, "loss": 0.0016, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.2837263654653715e-05, "epoch": 4.94, "percentage": 49.41, "elapsed_time": "0:30:27", "remaining_time": "0:31:10"}
|
| 51 |
+
{"current_steps": 430, "total_steps": 850, "loss": 0.0012, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.094620636205095e-05, "epoch": 5.06, "percentage": 50.59, "elapsed_time": "0:31:07", "remaining_time": "0:30:23"}
|
| 52 |
+
{"current_steps": 440, "total_steps": 850, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9053793637949067e-05, "epoch": 5.18, "percentage": 51.76, "elapsed_time": "0:31:47", "remaining_time": "0:29:37"}
|
| 53 |
+
{"current_steps": 450, "total_steps": 850, "loss": 0.0011, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.7162736345346303e-05, "epoch": 5.29, "percentage": 52.94, "elapsed_time": "0:32:26", "remaining_time": "0:28:50"}
|
| 54 |
+
{"current_steps": 450, "total_steps": 850, "loss": null, "eval_loss": 0.06781358271837234, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 5.29, "percentage": 52.94, "elapsed_time": "0:32:26", "remaining_time": "0:28:50"}
|
| 55 |
+
{"current_steps": 460, "total_steps": 850, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.527574340559844e-05, "epoch": 5.41, "percentage": 54.12, "elapsed_time": "0:33:25", "remaining_time": "0:28:20"}
|
| 56 |
+
{"current_steps": 470, "total_steps": 850, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.3395517917914895e-05, "epoch": 5.53, "percentage": 55.29, "elapsed_time": "0:34:05", "remaining_time": "0:27:33"}
|
| 57 |
+
{"current_steps": 480, "total_steps": 850, "loss": 0.0004, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.1524753287195165e-05, "epoch": 5.65, "percentage": 56.47, "elapsed_time": "0:34:45", "remaining_time": "0:26:47"}
|
| 58 |
+
{"current_steps": 490, "total_steps": 850, "loss": 0.0004, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.966612936575235e-05, "epoch": 5.76, "percentage": 57.65, "elapsed_time": "0:35:25", "remaining_time": "0:26:01"}
|
| 59 |
+
{"current_steps": 500, "total_steps": 850, "loss": 0.0009, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.7822308614450406e-05, "epoch": 5.88, "percentage": 58.82, "elapsed_time": "0:36:05", "remaining_time": "0:25:15"}
|
| 60 |
+
{"current_steps": 500, "total_steps": 850, "loss": null, "eval_loss": 0.0775449350476265, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 5.88, "percentage": 58.82, "elapsed_time": "0:36:05", "remaining_time": "0:25:15"}
|
| 61 |
+
{"current_steps": 510, "total_steps": 850, "loss": 0.0001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.599593228875465e-05, "epoch": 6.0, "percentage": 60.0, "elapsed_time": "0:37:04", "remaining_time": "0:24:42"}
|
| 62 |
+
{"current_steps": 520, "total_steps": 850, "loss": 0.0001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.41896166551588e-05, "epoch": 6.12, "percentage": 61.18, "elapsed_time": "0:37:44", "remaining_time": "0:23:56"}
|
| 63 |
+
{"current_steps": 530, "total_steps": 850, "loss": 0.0001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.240594924340835e-05, "epoch": 6.24, "percentage": 62.35, "elapsed_time": "0:38:23", "remaining_time": "0:23:11"}
|
| 64 |
+
{"current_steps": 540, "total_steps": 850, "loss": 0.0001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.0647485139889145e-05, "epoch": 6.35, "percentage": 63.53, "elapsed_time": "0:39:03", "remaining_time": "0:22:25"}
|
| 65 |
+
{"current_steps": 550, "total_steps": 850, "loss": 0.0017, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8916743327490803e-05, "epoch": 6.47, "percentage": 64.71, "elapsed_time": "0:39:43", "remaining_time": "0:21:40"}
|
| 66 |
+
{"current_steps": 550, "total_steps": 850, "loss": null, "eval_loss": 0.07820568978786469, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 6.47, "percentage": 64.71, "elapsed_time": "0:39:43", "remaining_time": "0:21:40"}
|
| 67 |
+
{"current_steps": 560, "total_steps": 850, "loss": 0.0001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.721620307718793e-05, "epoch": 6.59, "percentage": 65.88, "elapsed_time": "0:40:43", "remaining_time": "0:21:05"}
|
| 68 |
+
{"current_steps": 570, "total_steps": 850, "loss": 0.0001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.554830039650834e-05, "epoch": 6.71, "percentage": 67.06, "elapsed_time": "0:41:23", "remaining_time": "0:20:19"}
|
| 69 |
+
{"current_steps": 580, "total_steps": 850, "loss": 0.0001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.391542453997578e-05, "epoch": 6.82, "percentage": 68.24, "elapsed_time": "0:42:02", "remaining_time": "0:19:34"}
|
| 70 |
+
{"current_steps": 590, "total_steps": 850, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2319914586525777e-05, "epoch": 6.94, "percentage": 69.41, "elapsed_time": "0:42:42", "remaining_time": "0:18:49"}
|
| 71 |
+
{"current_steps": 600, "total_steps": 850, "loss": 0.0001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0764056088797645e-05, "epoch": 7.06, "percentage": 70.59, "elapsed_time": "0:43:21", "remaining_time": "0:18:04"}
|
| 72 |
+
{"current_steps": 600, "total_steps": 850, "loss": null, "eval_loss": 0.07926832884550095, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 7.06, "percentage": 70.59, "elapsed_time": "0:43:21", "remaining_time": "0:18:04"}
|
| 73 |
+
{"current_steps": 610, "total_steps": 850, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9250077799102322e-05, "epoch": 7.18, "percentage": 71.76, "elapsed_time": "0:44:20", "remaining_time": "0:17:26"}
|
| 74 |
+
{"current_steps": 620, "total_steps": 850, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7780148476756147e-05, "epoch": 7.29, "percentage": 72.94, "elapsed_time": "0:45:00", "remaining_time": "0:16:41"}
|
| 75 |
+
{"current_steps": 630, "total_steps": 850, "loss": 0.0001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6356373781354058e-05, "epoch": 7.41, "percentage": 74.12, "elapsed_time": "0:45:40", "remaining_time": "0:15:57"}
|
| 76 |
+
{"current_steps": 640, "total_steps": 850, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4980793256432474e-05, "epoch": 7.53, "percentage": 75.29, "elapsed_time": "0:46:20", "remaining_time": "0:15:12"}
|
| 77 |
+
{"current_steps": 650, "total_steps": 850, "loss": 0.0001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3655377407842812e-05, "epoch": 7.65, "percentage": 76.47, "elapsed_time": "0:46:59", "remaining_time": "0:14:27"}
|
| 78 |
+
{"current_steps": 650, "total_steps": 850, "loss": null, "eval_loss": 0.08116021752357483, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 7.65, "percentage": 76.47, "elapsed_time": "0:46:59", "remaining_time": "0:14:27"}
|
| 79 |
+
{"current_steps": 650, "total_steps": 850, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 7.65, "percentage": 76.47, "elapsed_time": "0:46:59", "remaining_time": "0:14:27"}
|
| 80 |
+
{"current_steps": 15, "total_steps": 15, "loss": null, "eval_loss": 0.0775449350476265, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 7.65, "percentage": 100.0, "elapsed_time": "0:47:50", "remaining_time": "0:00:00"}
|
llama2_13b_peft/abstract_narrative_understanding/trainer_state.json
ADDED
|
@@ -0,0 +1,589 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.0775449350476265,
|
| 3 |
+
"best_model_checkpoint": "ckpt/llama2_13b_fuze15_no_sys/abstract_narrative_understanding_no_sys/checkpoint-500",
|
| 4 |
+
"epoch": 7.647058823529412,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 650,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.12,
|
| 13 |
+
"grad_norm": 2.0217950344085693,
|
| 14 |
+
"learning_rate": 5e-05,
|
| 15 |
+
"loss": 2.3117,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.24,
|
| 20 |
+
"grad_norm": 0.8091562986373901,
|
| 21 |
+
"learning_rate": 0.0001,
|
| 22 |
+
"loss": 1.1002,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.35,
|
| 27 |
+
"grad_norm": 0.8186372518539429,
|
| 28 |
+
"learning_rate": 9.996418774081658e-05,
|
| 29 |
+
"loss": 0.291,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.47,
|
| 34 |
+
"grad_norm": 0.7440087199211121,
|
| 35 |
+
"learning_rate": 9.985680226398261e-05,
|
| 36 |
+
"loss": 0.2298,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.59,
|
| 41 |
+
"grad_norm": 0.86050945520401,
|
| 42 |
+
"learning_rate": 9.967799739815925e-05,
|
| 43 |
+
"loss": 0.1783,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.59,
|
| 48 |
+
"eval_loss": 0.15855231881141663,
|
| 49 |
+
"eval_runtime": 18.8402,
|
| 50 |
+
"eval_samples_per_second": 19.108,
|
| 51 |
+
"eval_steps_per_second": 0.796,
|
| 52 |
+
"step": 50
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.71,
|
| 56 |
+
"grad_norm": 1.0552955865859985,
|
| 57 |
+
"learning_rate": 9.942802927959443e-05,
|
| 58 |
+
"loss": 0.1504,
|
| 59 |
+
"step": 60
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.82,
|
| 63 |
+
"grad_norm": 1.1410902738571167,
|
| 64 |
+
"learning_rate": 9.910725598521013e-05,
|
| 65 |
+
"loss": 0.1438,
|
| 66 |
+
"step": 70
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.94,
|
| 70 |
+
"grad_norm": 0.8942976593971252,
|
| 71 |
+
"learning_rate": 9.871613701966067e-05,
|
| 72 |
+
"loss": 0.126,
|
| 73 |
+
"step": 80
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 1.06,
|
| 77 |
+
"grad_norm": 1.043587565422058,
|
| 78 |
+
"learning_rate": 9.825523265709666e-05,
|
| 79 |
+
"loss": 0.0922,
|
| 80 |
+
"step": 90
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.18,
|
| 84 |
+
"grad_norm": 0.6339874863624573,
|
| 85 |
+
"learning_rate": 9.772520313857775e-05,
|
| 86 |
+
"loss": 0.076,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.18,
|
| 91 |
+
"eval_loss": 0.11661680787801743,
|
| 92 |
+
"eval_runtime": 18.8492,
|
| 93 |
+
"eval_samples_per_second": 19.099,
|
| 94 |
+
"eval_steps_per_second": 0.796,
|
| 95 |
+
"step": 100
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.29,
|
| 99 |
+
"grad_norm": 1.4666110277175903,
|
| 100 |
+
"learning_rate": 9.712680772628364e-05,
|
| 101 |
+
"loss": 0.0649,
|
| 102 |
+
"step": 110
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.41,
|
| 106 |
+
"grad_norm": 0.6642812490463257,
|
| 107 |
+
"learning_rate": 9.646090361587827e-05,
|
| 108 |
+
"loss": 0.099,
|
| 109 |
+
"step": 120
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.53,
|
| 113 |
+
"grad_norm": 0.6947500705718994,
|
| 114 |
+
"learning_rate": 9.572844470858537e-05,
|
| 115 |
+
"loss": 0.0877,
|
| 116 |
+
"step": 130
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.65,
|
| 120 |
+
"grad_norm": 0.6531127691268921,
|
| 121 |
+
"learning_rate": 9.493048024473412e-05,
|
| 122 |
+
"loss": 0.0804,
|
| 123 |
+
"step": 140
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.76,
|
| 127 |
+
"grad_norm": 0.6246891021728516,
|
| 128 |
+
"learning_rate": 9.406815330073244e-05,
|
| 129 |
+
"loss": 0.0666,
|
| 130 |
+
"step": 150
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.76,
|
| 134 |
+
"eval_loss": 0.08253820985555649,
|
| 135 |
+
"eval_runtime": 18.8581,
|
| 136 |
+
"eval_samples_per_second": 19.09,
|
| 137 |
+
"eval_steps_per_second": 0.795,
|
| 138 |
+
"step": 150
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.88,
|
| 142 |
+
"grad_norm": 0.8410322666168213,
|
| 143 |
+
"learning_rate": 9.314269915162114e-05,
|
| 144 |
+
"loss": 0.0862,
|
| 145 |
+
"step": 160
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 2.0,
|
| 149 |
+
"grad_norm": 0.8153923153877258,
|
| 150 |
+
"learning_rate": 9.215544350155422e-05,
|
| 151 |
+
"loss": 0.063,
|
| 152 |
+
"step": 170
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.12,
|
| 156 |
+
"grad_norm": 0.4855154752731323,
|
| 157 |
+
"learning_rate": 9.110780058474052e-05,
|
| 158 |
+
"loss": 0.0407,
|
| 159 |
+
"step": 180
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 2.24,
|
| 163 |
+
"grad_norm": 0.3809996247291565,
|
| 164 |
+
"learning_rate": 9.000127113956674e-05,
|
| 165 |
+
"loss": 0.0328,
|
| 166 |
+
"step": 190
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 2.35,
|
| 170 |
+
"grad_norm": 0.4585777521133423,
|
| 171 |
+
"learning_rate": 8.883744025880428e-05,
|
| 172 |
+
"loss": 0.0173,
|
| 173 |
+
"step": 200
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 2.35,
|
| 177 |
+
"eval_loss": 0.07726477831602097,
|
| 178 |
+
"eval_runtime": 18.8583,
|
| 179 |
+
"eval_samples_per_second": 19.09,
|
| 180 |
+
"eval_steps_per_second": 0.795,
|
| 181 |
+
"step": 200
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 2.47,
|
| 185 |
+
"grad_norm": 1.3592562675476074,
|
| 186 |
+
"learning_rate": 8.761797511897906e-05,
|
| 187 |
+
"loss": 0.0353,
|
| 188 |
+
"step": 210
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.59,
|
| 192 |
+
"grad_norm": 0.32645800709724426,
|
| 193 |
+
"learning_rate": 8.634462259215719e-05,
|
| 194 |
+
"loss": 0.0265,
|
| 195 |
+
"step": 220
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.71,
|
| 199 |
+
"grad_norm": 0.7699334621429443,
|
| 200 |
+
"learning_rate": 8.501920674356754e-05,
|
| 201 |
+
"loss": 0.0346,
|
| 202 |
+
"step": 230
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 2.82,
|
| 206 |
+
"grad_norm": 0.7826615571975708,
|
| 207 |
+
"learning_rate": 8.364362621864595e-05,
|
| 208 |
+
"loss": 0.0228,
|
| 209 |
+
"step": 240
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.94,
|
| 213 |
+
"grad_norm": 1.523707389831543,
|
| 214 |
+
"learning_rate": 8.221985152324385e-05,
|
| 215 |
+
"loss": 0.0269,
|
| 216 |
+
"step": 250
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 2.94,
|
| 220 |
+
"eval_loss": 0.08358720690011978,
|
| 221 |
+
"eval_runtime": 18.8341,
|
| 222 |
+
"eval_samples_per_second": 19.114,
|
| 223 |
+
"eval_steps_per_second": 0.796,
|
| 224 |
+
"step": 250
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 3.06,
|
| 228 |
+
"grad_norm": 0.31683385372161865,
|
| 229 |
+
"learning_rate": 8.074992220089769e-05,
|
| 230 |
+
"loss": 0.0168,
|
| 231 |
+
"step": 260
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 3.18,
|
| 235 |
+
"grad_norm": 0.20376504957675934,
|
| 236 |
+
"learning_rate": 7.923594391120236e-05,
|
| 237 |
+
"loss": 0.0164,
|
| 238 |
+
"step": 270
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 3.29,
|
| 242 |
+
"grad_norm": 0.24734213948249817,
|
| 243 |
+
"learning_rate": 7.768008541347423e-05,
|
| 244 |
+
"loss": 0.0068,
|
| 245 |
+
"step": 280
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 3.41,
|
| 249 |
+
"grad_norm": 0.49086877703666687,
|
| 250 |
+
"learning_rate": 7.608457546002424e-05,
|
| 251 |
+
"loss": 0.0141,
|
| 252 |
+
"step": 290
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 3.53,
|
| 256 |
+
"grad_norm": 0.051008742302656174,
|
| 257 |
+
"learning_rate": 7.445169960349167e-05,
|
| 258 |
+
"loss": 0.0066,
|
| 259 |
+
"step": 300
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 3.53,
|
| 263 |
+
"eval_loss": 0.06564046442508698,
|
| 264 |
+
"eval_runtime": 18.8532,
|
| 265 |
+
"eval_samples_per_second": 19.095,
|
| 266 |
+
"eval_steps_per_second": 0.796,
|
| 267 |
+
"step": 300
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 3.65,
|
| 271 |
+
"grad_norm": 0.6045653223991394,
|
| 272 |
+
"learning_rate": 7.278379692281208e-05,
|
| 273 |
+
"loss": 0.0071,
|
| 274 |
+
"step": 310
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 3.76,
|
| 278 |
+
"grad_norm": 0.48832693696022034,
|
| 279 |
+
"learning_rate": 7.10832566725092e-05,
|
| 280 |
+
"loss": 0.0065,
|
| 281 |
+
"step": 320
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 3.88,
|
| 285 |
+
"grad_norm": 0.32412388920783997,
|
| 286 |
+
"learning_rate": 6.935251486011087e-05,
|
| 287 |
+
"loss": 0.005,
|
| 288 |
+
"step": 330
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 4.0,
|
| 292 |
+
"grad_norm": 2.07598614692688,
|
| 293 |
+
"learning_rate": 6.759405075659166e-05,
|
| 294 |
+
"loss": 0.0138,
|
| 295 |
+
"step": 340
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 4.12,
|
| 299 |
+
"grad_norm": 0.1396656185388565,
|
| 300 |
+
"learning_rate": 6.58103833448412e-05,
|
| 301 |
+
"loss": 0.003,
|
| 302 |
+
"step": 350
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 4.12,
|
| 306 |
+
"eval_loss": 0.06447144597768784,
|
| 307 |
+
"eval_runtime": 18.8594,
|
| 308 |
+
"eval_samples_per_second": 19.089,
|
| 309 |
+
"eval_steps_per_second": 0.795,
|
| 310 |
+
"step": 350
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 4.24,
|
| 314 |
+
"grad_norm": 0.07455724477767944,
|
| 315 |
+
"learning_rate": 6.400406771124536e-05,
|
| 316 |
+
"loss": 0.0044,
|
| 317 |
+
"step": 360
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 4.35,
|
| 321 |
+
"grad_norm": 0.2568245828151703,
|
| 322 |
+
"learning_rate": 6.21776913855496e-05,
|
| 323 |
+
"loss": 0.0045,
|
| 324 |
+
"step": 370
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 4.47,
|
| 328 |
+
"grad_norm": 0.5516663193702698,
|
| 329 |
+
"learning_rate": 6.0333870634247645e-05,
|
| 330 |
+
"loss": 0.0066,
|
| 331 |
+
"step": 380
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 4.59,
|
| 335 |
+
"grad_norm": 0.06458062678575516,
|
| 336 |
+
"learning_rate": 5.847524671280484e-05,
|
| 337 |
+
"loss": 0.0019,
|
| 338 |
+
"step": 390
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 4.71,
|
| 342 |
+
"grad_norm": 0.03421424329280853,
|
| 343 |
+
"learning_rate": 5.660448208208513e-05,
|
| 344 |
+
"loss": 0.0027,
|
| 345 |
+
"step": 400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 4.71,
|
| 349 |
+
"eval_loss": 0.0728691965341568,
|
| 350 |
+
"eval_runtime": 18.8498,
|
| 351 |
+
"eval_samples_per_second": 19.098,
|
| 352 |
+
"eval_steps_per_second": 0.796,
|
| 353 |
+
"step": 400
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 4.82,
|
| 357 |
+
"grad_norm": 0.1939074546098709,
|
| 358 |
+
"learning_rate": 5.472425659440157e-05,
|
| 359 |
+
"loss": 0.0054,
|
| 360 |
+
"step": 410
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 4.94,
|
| 364 |
+
"grad_norm": 0.18776360154151917,
|
| 365 |
+
"learning_rate": 5.2837263654653715e-05,
|
| 366 |
+
"loss": 0.0016,
|
| 367 |
+
"step": 420
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 5.06,
|
| 371 |
+
"grad_norm": 0.011647732928395271,
|
| 372 |
+
"learning_rate": 5.094620636205095e-05,
|
| 373 |
+
"loss": 0.0012,
|
| 374 |
+
"step": 430
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 5.18,
|
| 378 |
+
"grad_norm": 0.010027878917753696,
|
| 379 |
+
"learning_rate": 4.9053793637949067e-05,
|
| 380 |
+
"loss": 0.0002,
|
| 381 |
+
"step": 440
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 5.29,
|
| 385 |
+
"grad_norm": 0.02423482947051525,
|
| 386 |
+
"learning_rate": 4.7162736345346303e-05,
|
| 387 |
+
"loss": 0.0011,
|
| 388 |
+
"step": 450
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 5.29,
|
| 392 |
+
"eval_loss": 0.06781358271837234,
|
| 393 |
+
"eval_runtime": 18.8438,
|
| 394 |
+
"eval_samples_per_second": 19.104,
|
| 395 |
+
"eval_steps_per_second": 0.796,
|
| 396 |
+
"step": 450
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 5.41,
|
| 400 |
+
"grad_norm": 0.0043674008920788765,
|
| 401 |
+
"learning_rate": 4.527574340559844e-05,
|
| 402 |
+
"loss": 0.0002,
|
| 403 |
+
"step": 460
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 5.53,
|
| 407 |
+
"grad_norm": 0.013400307856500149,
|
| 408 |
+
"learning_rate": 4.3395517917914895e-05,
|
| 409 |
+
"loss": 0.0002,
|
| 410 |
+
"step": 470
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 5.65,
|
| 414 |
+
"grad_norm": 0.02295060083270073,
|
| 415 |
+
"learning_rate": 4.1524753287195165e-05,
|
| 416 |
+
"loss": 0.0004,
|
| 417 |
+
"step": 480
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 5.76,
|
| 421 |
+
"grad_norm": 0.027492625638842583,
|
| 422 |
+
"learning_rate": 3.966612936575235e-05,
|
| 423 |
+
"loss": 0.0004,
|
| 424 |
+
"step": 490
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 5.88,
|
| 428 |
+
"grad_norm": 0.2364090532064438,
|
| 429 |
+
"learning_rate": 3.7822308614450406e-05,
|
| 430 |
+
"loss": 0.0009,
|
| 431 |
+
"step": 500
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 5.88,
|
| 435 |
+
"eval_loss": 0.0775449350476265,
|
| 436 |
+
"eval_runtime": 18.8549,
|
| 437 |
+
"eval_samples_per_second": 19.093,
|
| 438 |
+
"eval_steps_per_second": 0.796,
|
| 439 |
+
"step": 500
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 6.0,
|
| 443 |
+
"grad_norm": 0.006466879975050688,
|
| 444 |
+
"learning_rate": 3.599593228875465e-05,
|
| 445 |
+
"loss": 0.0001,
|
| 446 |
+
"step": 510
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 6.12,
|
| 450 |
+
"grad_norm": 0.0022094016894698143,
|
| 451 |
+
"learning_rate": 3.41896166551588e-05,
|
| 452 |
+
"loss": 0.0001,
|
| 453 |
+
"step": 520
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 6.24,
|
| 457 |
+
"grad_norm": 0.0025171618908643723,
|
| 458 |
+
"learning_rate": 3.240594924340835e-05,
|
| 459 |
+
"loss": 0.0001,
|
| 460 |
+
"step": 530
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 6.35,
|
| 464 |
+
"grad_norm": 0.003617402631789446,
|
| 465 |
+
"learning_rate": 3.0647485139889145e-05,
|
| 466 |
+
"loss": 0.0001,
|
| 467 |
+
"step": 540
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 6.47,
|
| 471 |
+
"grad_norm": 0.00444138515740633,
|
| 472 |
+
"learning_rate": 2.8916743327490803e-05,
|
| 473 |
+
"loss": 0.0017,
|
| 474 |
+
"step": 550
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 6.47,
|
| 478 |
+
"eval_loss": 0.07820568978786469,
|
| 479 |
+
"eval_runtime": 18.8263,
|
| 480 |
+
"eval_samples_per_second": 19.122,
|
| 481 |
+
"eval_steps_per_second": 0.797,
|
| 482 |
+
"step": 550
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 6.59,
|
| 486 |
+
"grad_norm": 0.04611958935856819,
|
| 487 |
+
"learning_rate": 2.721620307718793e-05,
|
| 488 |
+
"loss": 0.0001,
|
| 489 |
+
"step": 560
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 6.71,
|
| 493 |
+
"grad_norm": 0.005136082414537668,
|
| 494 |
+
"learning_rate": 2.554830039650834e-05,
|
| 495 |
+
"loss": 0.0001,
|
| 496 |
+
"step": 570
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 6.82,
|
| 500 |
+
"grad_norm": 0.0014651508536189795,
|
| 501 |
+
"learning_rate": 2.391542453997578e-05,
|
| 502 |
+
"loss": 0.0001,
|
| 503 |
+
"step": 580
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 6.94,
|
| 507 |
+
"grad_norm": 0.0029225933831185102,
|
| 508 |
+
"learning_rate": 2.2319914586525777e-05,
|
| 509 |
+
"loss": 0.0,
|
| 510 |
+
"step": 590
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 7.06,
|
| 514 |
+
"grad_norm": 0.010204533115029335,
|
| 515 |
+
"learning_rate": 2.0764056088797645e-05,
|
| 516 |
+
"loss": 0.0001,
|
| 517 |
+
"step": 600
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 7.06,
|
| 521 |
+
"eval_loss": 0.07926832884550095,
|
| 522 |
+
"eval_runtime": 18.8273,
|
| 523 |
+
"eval_samples_per_second": 19.121,
|
| 524 |
+
"eval_steps_per_second": 0.797,
|
| 525 |
+
"step": 600
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 7.18,
|
| 529 |
+
"grad_norm": 0.0016622378025203943,
|
| 530 |
+
"learning_rate": 1.9250077799102322e-05,
|
| 531 |
+
"loss": 0.0,
|
| 532 |
+
"step": 610
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 7.29,
|
| 536 |
+
"grad_norm": 0.0054710181429982185,
|
| 537 |
+
"learning_rate": 1.7780148476756147e-05,
|
| 538 |
+
"loss": 0.0,
|
| 539 |
+
"step": 620
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 7.41,
|
| 543 |
+
"grad_norm": 0.003711065510287881,
|
| 544 |
+
"learning_rate": 1.6356373781354058e-05,
|
| 545 |
+
"loss": 0.0001,
|
| 546 |
+
"step": 630
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 7.53,
|
| 550 |
+
"grad_norm": 0.0011153242085129023,
|
| 551 |
+
"learning_rate": 1.4980793256432474e-05,
|
| 552 |
+
"loss": 0.0,
|
| 553 |
+
"step": 640
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 7.65,
|
| 557 |
+
"grad_norm": 0.014780309051275253,
|
| 558 |
+
"learning_rate": 1.3655377407842812e-05,
|
| 559 |
+
"loss": 0.0001,
|
| 560 |
+
"step": 650
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 7.65,
|
| 564 |
+
"eval_loss": 0.08116021752357483,
|
| 565 |
+
"eval_runtime": 18.8377,
|
| 566 |
+
"eval_samples_per_second": 19.111,
|
| 567 |
+
"eval_steps_per_second": 0.796,
|
| 568 |
+
"step": 650
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 7.65,
|
| 572 |
+
"step": 650,
|
| 573 |
+
"total_flos": 1.541550606773125e+18,
|
| 574 |
+
"train_loss": 0.0863784014862568,
|
| 575 |
+
"train_runtime": 2843.6931,
|
| 576 |
+
"train_samples_per_second": 7.174,
|
| 577 |
+
"train_steps_per_second": 0.299
|
| 578 |
+
}
|
| 579 |
+
],
|
| 580 |
+
"logging_steps": 10,
|
| 581 |
+
"max_steps": 850,
|
| 582 |
+
"num_input_tokens_seen": 0,
|
| 583 |
+
"num_train_epochs": 10,
|
| 584 |
+
"save_steps": 500,
|
| 585 |
+
"total_flos": 1.541550606773125e+18,
|
| 586 |
+
"train_batch_size": 8,
|
| 587 |
+
"trial_name": null,
|
| 588 |
+
"trial_params": null
|
| 589 |
+
}
|
llama2_13b_peft/abstract_narrative_understanding/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c13f2efe6e7a8ca780611c8deeaba1a047aa3f9ec1b761c9f8aba21759301a2
|
| 3 |
+
size 5112
|
llama2_13b_peft/abstract_narrative_understanding/training_eval_loss.png
ADDED
|
llama2_13b_peft/abstract_narrative_understanding/training_loss.png
ADDED
|
llama2_13b_peft/alpaca/README.md
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- llama-factory
|
| 6 |
+
- lora
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: /data1/model/llama2/meta-llama/Llama2-13b
|
| 9 |
+
model-index:
|
| 10 |
+
- name: alpaca_no_sys
|
| 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 |
+
# alpaca_no_sys
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [/data1/model/llama2/meta-llama/Llama2-13b](https://huggingface.co//data1/model/llama2/meta-llama/Llama2-13b) on the alpaca_no_sys dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.0082
|
| 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: 0.0001
|
| 41 |
+
- train_batch_size: 8
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- num_devices: 2
|
| 46 |
+
- total_train_batch_size: 16
|
| 47 |
+
- total_eval_batch_size: 16
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: cosine
|
| 50 |
+
- lr_scheduler_warmup_steps: 20
|
| 51 |
+
- num_epochs: 10.0
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 57 |
+
| 1.0429 | 0.07 | 200 | 1.0298 |
|
| 58 |
+
| 1.0505 | 0.14 | 400 | 1.0238 |
|
| 59 |
+
| 1.044 | 0.22 | 600 | 1.0194 |
|
| 60 |
+
| 1.0169 | 0.29 | 800 | 1.0172 |
|
| 61 |
+
| 1.02 | 0.36 | 1000 | 1.0154 |
|
| 62 |
+
| 0.9492 | 0.43 | 1200 | 1.0134 |
|
| 63 |
+
| 1.0051 | 0.51 | 1400 | 1.0117 |
|
| 64 |
+
| 1.0469 | 0.58 | 1600 | 1.0106 |
|
| 65 |
+
| 0.9994 | 0.65 | 1800 | 1.0094 |
|
| 66 |
+
| 1.0141 | 0.72 | 2000 | 1.0082 |
|
| 67 |
+
| 1.0891 | 0.8 | 2200 | 1.0073 |
|
| 68 |
+
| 1.0141 | 0.87 | 2400 | 1.0063 |
|
| 69 |
+
| 1.0002 | 0.94 | 2600 | 1.0059 |
|
| 70 |
+
| 0.9686 | 1.01 | 2800 | 1.0086 |
|
| 71 |
+
| 0.9767 | 1.09 | 3000 | 1.0141 |
|
| 72 |
+
| 0.9494 | 1.16 | 3200 | 1.0160 |
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
### Framework versions
|
| 76 |
+
|
| 77 |
+
- PEFT 0.9.0
|
| 78 |
+
- Transformers 4.38.2
|
| 79 |
+
- Pytorch 2.2.1
|
| 80 |
+
- Datasets 2.18.0
|
| 81 |
+
- Tokenizers 0.15.2
|
llama2_13b_peft/alpaca/adapter_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "/data1/model/llama2/meta-llama/Llama2-13b",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 16,
|
| 13 |
+
"lora_dropout": 0.0,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 8,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"o_proj",
|
| 23 |
+
"gate_proj",
|
| 24 |
+
"v_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"up_proj",
|
| 27 |
+
"q_proj",
|
| 28 |
+
"k_proj"
|
| 29 |
+
],
|
| 30 |
+
"task_type": "CAUSAL_LM",
|
| 31 |
+
"use_dora": false,
|
| 32 |
+
"use_rslora": false
|
| 33 |
+
}
|
llama2_13b_peft/alpaca/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89face3e5e4bb009020e5742eaa4fa7c830124d15007f50b345d18c3c0daf8df
|
| 3 |
+
size 125248064
|
llama2_13b_peft/alpaca/all_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.16,
|
| 3 |
+
"eval_loss": 1.0082145929336548,
|
| 4 |
+
"eval_runtime": 124.7969,
|
| 5 |
+
"eval_samples_per_second": 62.51,
|
| 6 |
+
"eval_steps_per_second": 3.91,
|
| 7 |
+
"train_loss": 1.015018144249916,
|
| 8 |
+
"train_runtime": 4695.8401,
|
| 9 |
+
"train_samples_per_second": 94.128,
|
| 10 |
+
"train_steps_per_second": 5.884
|
| 11 |
+
}
|
llama2_13b_peft/alpaca/eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.16,
|
| 3 |
+
"eval_loss": 1.0082145929336548,
|
| 4 |
+
"eval_runtime": 124.7969,
|
| 5 |
+
"eval_samples_per_second": 62.51,
|
| 6 |
+
"eval_steps_per_second": 3.91
|
| 7 |
+
}
|
llama2_13b_peft/alpaca/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
llama2_13b_peft/alpaca/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
llama2_13b_peft/alpaca/tokenizer_config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content + '\\n' }}{% endif %}{% endfor %}",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"legacy": true,
|
| 36 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
+
"pad_token": "</s>",
|
| 38 |
+
"padding_side": "right",
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"spaces_between_special_tokens": false,
|
| 41 |
+
"split_special_tokens": false,
|
| 42 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 43 |
+
"unk_token": "<unk>",
|
| 44 |
+
"use_default_system_prompt": false
|
| 45 |
+
}
|
llama2_13b_peft/alpaca/train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.16,
|
| 3 |
+
"train_loss": 1.015018144249916,
|
| 4 |
+
"train_runtime": 4695.8401,
|
| 5 |
+
"train_samples_per_second": 94.128,
|
| 6 |
+
"train_steps_per_second": 5.884
|
| 7 |
+
}
|
llama2_13b_peft/alpaca/trainer_log.jsonl
ADDED
|
@@ -0,0 +1,338 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 10, "total_steps": 27630, "loss": 1.4369, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5e-05, "epoch": 0.0, "percentage": 0.04, "elapsed_time": "0:00:10", "remaining_time": "8:15:16"}
|
| 2 |
+
{"current_steps": 20, "total_steps": 27630, "loss": 1.3624, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001, "epoch": 0.01, "percentage": 0.07, "elapsed_time": "0:00:19", "remaining_time": "7:33:01"}
|
| 3 |
+
{"current_steps": 30, "total_steps": 27630, "loss": 1.1589, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.999996763266864e-05, "epoch": 0.01, "percentage": 0.11, "elapsed_time": "0:00:28", "remaining_time": "7:16:26"}
|
| 4 |
+
{"current_steps": 40, "total_steps": 27630, "loss": 1.1103, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.999987053071647e-05, "epoch": 0.01, "percentage": 0.14, "elapsed_time": "0:00:35", "remaining_time": "6:42:44"}
|
| 5 |
+
{"current_steps": 50, "total_steps": 27630, "loss": 1.0601, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.99997086942692e-05, "epoch": 0.02, "percentage": 0.18, "elapsed_time": "0:00:43", "remaining_time": "6:37:46"}
|
| 6 |
+
{"current_steps": 60, "total_steps": 27630, "loss": 1.0302, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.999948212353635e-05, "epoch": 0.02, "percentage": 0.22, "elapsed_time": "0:00:50", "remaining_time": "6:30:17"}
|
| 7 |
+
{"current_steps": 70, "total_steps": 27630, "loss": 1.114, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.999919081881129e-05, "epoch": 0.03, "percentage": 0.25, "elapsed_time": "0:00:59", "remaining_time": "6:33:10"}
|
| 8 |
+
{"current_steps": 80, "total_steps": 27630, "loss": 1.0913, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.999883478047113e-05, "epoch": 0.03, "percentage": 0.29, "elapsed_time": "0:01:09", "remaining_time": "6:36:03"}
|
| 9 |
+
{"current_steps": 90, "total_steps": 27630, "loss": 1.0778, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.999841400897687e-05, "epoch": 0.03, "percentage": 0.33, "elapsed_time": "0:01:18", "remaining_time": "6:38:18"}
|
| 10 |
+
{"current_steps": 100, "total_steps": 27630, "loss": 1.0493, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.999792850487325e-05, "epoch": 0.04, "percentage": 0.36, "elapsed_time": "0:01:25", "remaining_time": "6:32:31"}
|
| 11 |
+
{"current_steps": 110, "total_steps": 27630, "loss": 1.0249, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.999737826878886e-05, "epoch": 0.04, "percentage": 0.4, "elapsed_time": "0:01:33", "remaining_time": "6:30:08"}
|
| 12 |
+
{"current_steps": 120, "total_steps": 27630, "loss": 1.0594, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.99967633014361e-05, "epoch": 0.04, "percentage": 0.43, "elapsed_time": "0:01:41", "remaining_time": "6:28:19"}
|
| 13 |
+
{"current_steps": 130, "total_steps": 27630, "loss": 1.0527, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.999608360361113e-05, "epoch": 0.05, "percentage": 0.47, "elapsed_time": "0:01:49", "remaining_time": "6:27:25"}
|
| 14 |
+
{"current_steps": 140, "total_steps": 27630, "loss": 1.0051, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.999533917619399e-05, "epoch": 0.05, "percentage": 0.51, "elapsed_time": "0:01:59", "remaining_time": "6:29:40"}
|
| 15 |
+
{"current_steps": 150, "total_steps": 27630, "loss": 0.9906, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.999453002014846e-05, "epoch": 0.05, "percentage": 0.54, "elapsed_time": "0:02:06", "remaining_time": "6:25:18"}
|
| 16 |
+
{"current_steps": 160, "total_steps": 27630, "loss": 1.0197, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.999365613652217e-05, "epoch": 0.06, "percentage": 0.58, "elapsed_time": "0:02:13", "remaining_time": "6:20:51"}
|
| 17 |
+
{"current_steps": 170, "total_steps": 27630, "loss": 1.0356, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.999271752644649e-05, "epoch": 0.06, "percentage": 0.62, "elapsed_time": "0:02:23", "remaining_time": "6:26:18"}
|
| 18 |
+
{"current_steps": 180, "total_steps": 27630, "loss": 1.0332, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.999171419113666e-05, "epoch": 0.07, "percentage": 0.65, "elapsed_time": "0:02:30", "remaining_time": "6:23:32"}
|
| 19 |
+
{"current_steps": 190, "total_steps": 27630, "loss": 1.0126, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.999064613189171e-05, "epoch": 0.07, "percentage": 0.69, "elapsed_time": "0:02:38", "remaining_time": "6:20:45"}
|
| 20 |
+
{"current_steps": 200, "total_steps": 27630, "loss": 1.0429, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.998951335009442e-05, "epoch": 0.07, "percentage": 0.72, "elapsed_time": "0:02:46", "remaining_time": "6:20:16"}
|
| 21 |
+
{"current_steps": 200, "total_steps": 27630, "loss": null, "eval_loss": 1.029819130897522, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.07, "percentage": 0.72, "elapsed_time": "0:02:46", "remaining_time": "6:20:16"}
|
| 22 |
+
{"current_steps": 210, "total_steps": 27630, "loss": 1.0431, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.998831584721141e-05, "epoch": 0.08, "percentage": 0.76, "elapsed_time": "0:04:59", "remaining_time": "10:51:19"}
|
| 23 |
+
{"current_steps": 220, "total_steps": 27630, "loss": 1.0374, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.998705362479307e-05, "epoch": 0.08, "percentage": 0.8, "elapsed_time": "0:05:09", "remaining_time": "10:42:39"}
|
| 24 |
+
{"current_steps": 230, "total_steps": 27630, "loss": 1.1065, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.99857266844736e-05, "epoch": 0.08, "percentage": 0.83, "elapsed_time": "0:05:17", "remaining_time": "10:30:52"}
|
| 25 |
+
{"current_steps": 240, "total_steps": 27630, "loss": 1.1105, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.998433502797095e-05, "epoch": 0.09, "percentage": 0.87, "elapsed_time": "0:05:24", "remaining_time": "10:17:51"}
|
| 26 |
+
{"current_steps": 250, "total_steps": 27630, "loss": 0.9839, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.998287865708694e-05, "epoch": 0.09, "percentage": 0.9, "elapsed_time": "0:05:32", "remaining_time": "10:06:47"}
|
| 27 |
+
{"current_steps": 260, "total_steps": 27630, "loss": 1.0401, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.998135757370708e-05, "epoch": 0.09, "percentage": 0.94, "elapsed_time": "0:05:40", "remaining_time": "9:56:33"}
|
| 28 |
+
{"current_steps": 270, "total_steps": 27630, "loss": 1.0461, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.997977177980074e-05, "epoch": 0.1, "percentage": 0.98, "elapsed_time": "0:05:48", "remaining_time": "9:49:11"}
|
| 29 |
+
{"current_steps": 280, "total_steps": 27630, "loss": 1.0662, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.9978121277421e-05, "epoch": 0.1, "percentage": 1.01, "elapsed_time": "0:05:57", "remaining_time": "9:42:19"}
|
| 30 |
+
{"current_steps": 290, "total_steps": 27630, "loss": 1.0736, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.99764060687048e-05, "epoch": 0.1, "percentage": 1.05, "elapsed_time": "0:06:06", "remaining_time": "9:35:51"}
|
| 31 |
+
{"current_steps": 300, "total_steps": 27630, "loss": 0.9963, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.997462615587276e-05, "epoch": 0.11, "percentage": 1.09, "elapsed_time": "0:06:14", "remaining_time": "9:28:28"}
|
| 32 |
+
{"current_steps": 310, "total_steps": 27630, "loss": 1.044, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.997278154122935e-05, "epoch": 0.11, "percentage": 1.12, "elapsed_time": "0:06:23", "remaining_time": "9:23:40"}
|
| 33 |
+
{"current_steps": 320, "total_steps": 27630, "loss": 1.0713, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.997087222716278e-05, "epoch": 0.12, "percentage": 1.16, "elapsed_time": "0:06:31", "remaining_time": "9:17:11"}
|
| 34 |
+
{"current_steps": 330, "total_steps": 27630, "loss": 1.0721, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.996889821614502e-05, "epoch": 0.12, "percentage": 1.19, "elapsed_time": "0:06:40", "remaining_time": "9:11:37"}
|
| 35 |
+
{"current_steps": 340, "total_steps": 27630, "loss": 1.0414, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.996685951073182e-05, "epoch": 0.12, "percentage": 1.23, "elapsed_time": "0:06:48", "remaining_time": "9:05:51"}
|
| 36 |
+
{"current_steps": 350, "total_steps": 27630, "loss": 0.9856, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.996475611356264e-05, "epoch": 0.13, "percentage": 1.27, "elapsed_time": "0:06:55", "remaining_time": "9:00:01"}
|
| 37 |
+
{"current_steps": 360, "total_steps": 27630, "loss": 1.0121, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.996258802736079e-05, "epoch": 0.13, "percentage": 1.3, "elapsed_time": "0:07:03", "remaining_time": "8:55:02"}
|
| 38 |
+
{"current_steps": 370, "total_steps": 27630, "loss": 1.0785, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.996035525493322e-05, "epoch": 0.13, "percentage": 1.34, "elapsed_time": "0:07:12", "remaining_time": "8:50:45"}
|
| 39 |
+
{"current_steps": 380, "total_steps": 27630, "loss": 0.996, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.995805779917073e-05, "epoch": 0.14, "percentage": 1.38, "elapsed_time": "0:07:20", "remaining_time": "8:46:51"}
|
| 40 |
+
{"current_steps": 390, "total_steps": 27630, "loss": 1.0557, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.99556956630478e-05, "epoch": 0.14, "percentage": 1.41, "elapsed_time": "0:07:29", "remaining_time": "8:43:28"}
|
| 41 |
+
{"current_steps": 400, "total_steps": 27630, "loss": 1.0505, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.995326884962268e-05, "epoch": 0.14, "percentage": 1.45, "elapsed_time": "0:07:37", "remaining_time": "8:38:37"}
|
| 42 |
+
{"current_steps": 400, "total_steps": 27630, "loss": null, "eval_loss": 1.023820400238037, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.14, "percentage": 1.45, "elapsed_time": "0:07:37", "remaining_time": "8:38:37"}
|
| 43 |
+
{"current_steps": 410, "total_steps": 27630, "loss": 0.9919, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.995077736203733e-05, "epoch": 0.15, "percentage": 1.48, "elapsed_time": "0:09:50", "remaining_time": "10:53:45"}
|
| 44 |
+
{"current_steps": 420, "total_steps": 27630, "loss": 1.0736, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.99482212035175e-05, "epoch": 0.15, "percentage": 1.52, "elapsed_time": "0:10:00", "remaining_time": "10:48:23"}
|
| 45 |
+
{"current_steps": 430, "total_steps": 27630, "loss": 1.0633, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.994560037737259e-05, "epoch": 0.16, "percentage": 1.56, "elapsed_time": "0:10:08", "remaining_time": "10:41:21"}
|
| 46 |
+
{"current_steps": 440, "total_steps": 27630, "loss": 1.049, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.994291488699579e-05, "epoch": 0.16, "percentage": 1.59, "elapsed_time": "0:10:15", "remaining_time": "10:34:13"}
|
| 47 |
+
{"current_steps": 450, "total_steps": 27630, "loss": 1.0022, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.994016473586398e-05, "epoch": 0.16, "percentage": 1.63, "elapsed_time": "0:10:23", "remaining_time": "10:28:02"}
|
| 48 |
+
{"current_steps": 460, "total_steps": 27630, "loss": 1.0076, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.993734992753777e-05, "epoch": 0.17, "percentage": 1.66, "elapsed_time": "0:10:34", "remaining_time": "10:25:03"}
|
| 49 |
+
{"current_steps": 470, "total_steps": 27630, "loss": 1.0298, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.993447046566146e-05, "epoch": 0.17, "percentage": 1.7, "elapsed_time": "0:10:44", "remaining_time": "10:20:26"}
|
| 50 |
+
{"current_steps": 480, "total_steps": 27630, "loss": 1.0635, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.993152635396308e-05, "epoch": 0.17, "percentage": 1.74, "elapsed_time": "0:10:52", "remaining_time": "10:14:51"}
|
| 51 |
+
{"current_steps": 490, "total_steps": 27630, "loss": 1.0183, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.992851759625433e-05, "epoch": 0.18, "percentage": 1.77, "elapsed_time": "0:11:00", "remaining_time": "10:09:51"}
|
| 52 |
+
{"current_steps": 500, "total_steps": 27630, "loss": 0.963, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.992544419643066e-05, "epoch": 0.18, "percentage": 1.81, "elapsed_time": "0:11:08", "remaining_time": "10:04:25"}
|
| 53 |
+
{"current_steps": 510, "total_steps": 27630, "loss": 0.9691, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.992230615847116e-05, "epoch": 0.18, "percentage": 1.85, "elapsed_time": "0:11:16", "remaining_time": "9:59:54"}
|
| 54 |
+
{"current_steps": 520, "total_steps": 27630, "loss": 1.0309, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.991910348643865e-05, "epoch": 0.19, "percentage": 1.88, "elapsed_time": "0:11:25", "remaining_time": "9:55:38"}
|
| 55 |
+
{"current_steps": 530, "total_steps": 27630, "loss": 1.0232, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.991583618447958e-05, "epoch": 0.19, "percentage": 1.92, "elapsed_time": "0:11:34", "remaining_time": "9:51:28"}
|
| 56 |
+
{"current_steps": 540, "total_steps": 27630, "loss": 1.0308, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.99125042568241e-05, "epoch": 0.2, "percentage": 1.95, "elapsed_time": "0:11:41", "remaining_time": "9:46:47"}
|
| 57 |
+
{"current_steps": 550, "total_steps": 27630, "loss": 1.0581, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.990910770778606e-05, "epoch": 0.2, "percentage": 1.99, "elapsed_time": "0:11:50", "remaining_time": "9:42:50"}
|
| 58 |
+
{"current_steps": 560, "total_steps": 27630, "loss": 0.958, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.990564654176293e-05, "epoch": 0.2, "percentage": 2.03, "elapsed_time": "0:11:58", "remaining_time": "9:38:52"}
|
| 59 |
+
{"current_steps": 570, "total_steps": 27630, "loss": 1.0258, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.990212076323586e-05, "epoch": 0.21, "percentage": 2.06, "elapsed_time": "0:12:07", "remaining_time": "9:35:27"}
|
| 60 |
+
{"current_steps": 580, "total_steps": 27630, "loss": 1.0724, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.989853037676965e-05, "epoch": 0.21, "percentage": 2.1, "elapsed_time": "0:12:15", "remaining_time": "9:31:37"}
|
| 61 |
+
{"current_steps": 590, "total_steps": 27630, "loss": 0.9847, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.989487538701279e-05, "epoch": 0.21, "percentage": 2.14, "elapsed_time": "0:12:23", "remaining_time": "9:28:02"}
|
| 62 |
+
{"current_steps": 600, "total_steps": 27630, "loss": 1.044, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.989115579869732e-05, "epoch": 0.22, "percentage": 2.17, "elapsed_time": "0:12:31", "remaining_time": "9:24:36"}
|
| 63 |
+
{"current_steps": 600, "total_steps": 27630, "loss": null, "eval_loss": 1.0194298028945923, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.22, "percentage": 2.17, "elapsed_time": "0:12:31", "remaining_time": "9:24:36"}
|
| 64 |
+
{"current_steps": 610, "total_steps": 27630, "loss": 1.0244, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.988737161663898e-05, "epoch": 0.22, "percentage": 2.21, "elapsed_time": "0:14:45", "remaining_time": "10:53:34"}
|
| 65 |
+
{"current_steps": 620, "total_steps": 27630, "loss": 1.0254, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.988352284573713e-05, "epoch": 0.22, "percentage": 2.24, "elapsed_time": "0:14:54", "remaining_time": "10:49:13"}
|
| 66 |
+
{"current_steps": 630, "total_steps": 27630, "loss": 1.1093, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.987960949097475e-05, "epoch": 0.23, "percentage": 2.28, "elapsed_time": "0:15:02", "remaining_time": "10:44:31"}
|
| 67 |
+
{"current_steps": 640, "total_steps": 27630, "loss": 1.0196, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.987563155741842e-05, "epoch": 0.23, "percentage": 2.32, "elapsed_time": "0:15:09", "remaining_time": "10:39:31"}
|
| 68 |
+
{"current_steps": 650, "total_steps": 27630, "loss": 1.012, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.987158905021836e-05, "epoch": 0.24, "percentage": 2.35, "elapsed_time": "0:15:17", "remaining_time": "10:34:35"}
|
| 69 |
+
{"current_steps": 660, "total_steps": 27630, "loss": 1.0219, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.986748197460837e-05, "epoch": 0.24, "percentage": 2.39, "elapsed_time": "0:15:24", "remaining_time": "10:29:55"}
|
| 70 |
+
{"current_steps": 670, "total_steps": 27630, "loss": 1.015, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.986331033590586e-05, "epoch": 0.24, "percentage": 2.42, "elapsed_time": "0:15:33", "remaining_time": "10:26:13"}
|
| 71 |
+
{"current_steps": 680, "total_steps": 27630, "loss": 1.1113, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.98590741395118e-05, "epoch": 0.25, "percentage": 2.46, "elapsed_time": "0:15:40", "remaining_time": "10:21:24"}
|
| 72 |
+
{"current_steps": 690, "total_steps": 27630, "loss": 1.0456, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.985477339091078e-05, "epoch": 0.25, "percentage": 2.5, "elapsed_time": "0:15:49", "remaining_time": "10:17:54"}
|
| 73 |
+
{"current_steps": 700, "total_steps": 27630, "loss": 1.0102, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.985040809567097e-05, "epoch": 0.25, "percentage": 2.53, "elapsed_time": "0:15:57", "remaining_time": "10:14:15"}
|
| 74 |
+
{"current_steps": 710, "total_steps": 27630, "loss": 1.0057, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.984597825944405e-05, "epoch": 0.26, "percentage": 2.57, "elapsed_time": "0:16:04", "remaining_time": "10:09:39"}
|
| 75 |
+
{"current_steps": 720, "total_steps": 27630, "loss": 0.9937, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.984148388796532e-05, "epoch": 0.26, "percentage": 2.61, "elapsed_time": "0:16:15", "remaining_time": "10:07:25"}
|
| 76 |
+
{"current_steps": 730, "total_steps": 27630, "loss": 0.9937, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.983692498705361e-05, "epoch": 0.26, "percentage": 2.64, "elapsed_time": "0:16:24", "remaining_time": "10:04:25"}
|
| 77 |
+
{"current_steps": 740, "total_steps": 27630, "loss": 1.0205, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.983230156261132e-05, "epoch": 0.27, "percentage": 2.68, "elapsed_time": "0:16:32", "remaining_time": "10:00:48"}
|
| 78 |
+
{"current_steps": 750, "total_steps": 27630, "loss": 1.0486, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.982761362062432e-05, "epoch": 0.27, "percentage": 2.71, "elapsed_time": "0:16:40", "remaining_time": "9:57:30"}
|
| 79 |
+
{"current_steps": 760, "total_steps": 27630, "loss": 1.0679, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.982286116716208e-05, "epoch": 0.28, "percentage": 2.75, "elapsed_time": "0:16:50", "remaining_time": "9:55:18"}
|
| 80 |
+
{"current_steps": 770, "total_steps": 27630, "loss": 1.0051, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.98180442083776e-05, "epoch": 0.28, "percentage": 2.79, "elapsed_time": "0:16:57", "remaining_time": "9:51:45"}
|
| 81 |
+
{"current_steps": 780, "total_steps": 27630, "loss": 1.0398, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.981316275050731e-05, "epoch": 0.28, "percentage": 2.82, "elapsed_time": "0:17:05", "remaining_time": "9:48:32"}
|
| 82 |
+
{"current_steps": 790, "total_steps": 27630, "loss": 1.0365, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.980821679987125e-05, "epoch": 0.29, "percentage": 2.86, "elapsed_time": "0:17:13", "remaining_time": "9:45:26"}
|
| 83 |
+
{"current_steps": 800, "total_steps": 27630, "loss": 1.0169, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.980320636287285e-05, "epoch": 0.29, "percentage": 2.9, "elapsed_time": "0:17:22", "remaining_time": "9:42:45"}
|
| 84 |
+
{"current_steps": 800, "total_steps": 27630, "loss": null, "eval_loss": 1.0172123908996582, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.29, "percentage": 2.9, "elapsed_time": "0:17:22", "remaining_time": "9:42:45"}
|
| 85 |
+
{"current_steps": 810, "total_steps": 27630, "loss": 1.0165, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.979813144599915e-05, "epoch": 0.29, "percentage": 2.93, "elapsed_time": "0:19:34", "remaining_time": "10:48:16"}
|
| 86 |
+
{"current_steps": 820, "total_steps": 27630, "loss": 1.0314, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.979299205582057e-05, "epoch": 0.3, "percentage": 2.97, "elapsed_time": "0:19:42", "remaining_time": "10:44:22"}
|
| 87 |
+
{"current_steps": 830, "total_steps": 27630, "loss": 0.9779, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.978778819899109e-05, "epoch": 0.3, "percentage": 3.0, "elapsed_time": "0:19:50", "remaining_time": "10:40:40"}
|
| 88 |
+
{"current_steps": 840, "total_steps": 27630, "loss": 0.9564, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.978251988224804e-05, "epoch": 0.3, "percentage": 3.04, "elapsed_time": "0:19:58", "remaining_time": "10:36:56"}
|
| 89 |
+
{"current_steps": 850, "total_steps": 27630, "loss": 1.0275, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.977718711241233e-05, "epoch": 0.31, "percentage": 3.08, "elapsed_time": "0:20:06", "remaining_time": "10:33:39"}
|
| 90 |
+
{"current_steps": 860, "total_steps": 27630, "loss": 1.0293, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.977178989638822e-05, "epoch": 0.31, "percentage": 3.11, "elapsed_time": "0:20:16", "remaining_time": "10:31:04"}
|
| 91 |
+
{"current_steps": 870, "total_steps": 27630, "loss": 1.0508, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.97663282411635e-05, "epoch": 0.31, "percentage": 3.15, "elapsed_time": "0:20:24", "remaining_time": "10:27:45"}
|
| 92 |
+
{"current_steps": 880, "total_steps": 27630, "loss": 0.9949, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.97608021538093e-05, "epoch": 0.32, "percentage": 3.18, "elapsed_time": "0:20:32", "remaining_time": "10:24:34"}
|
| 93 |
+
{"current_steps": 890, "total_steps": 27630, "loss": 1.0752, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.97552116414802e-05, "epoch": 0.32, "percentage": 3.22, "elapsed_time": "0:20:40", "remaining_time": "10:21:23"}
|
| 94 |
+
{"current_steps": 900, "total_steps": 27630, "loss": 0.9947, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.974955671141424e-05, "epoch": 0.33, "percentage": 3.26, "elapsed_time": "0:20:48", "remaining_time": "10:17:58"}
|
| 95 |
+
{"current_steps": 910, "total_steps": 27630, "loss": 1.0362, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.974383737093279e-05, "epoch": 0.33, "percentage": 3.29, "elapsed_time": "0:20:56", "remaining_time": "10:15:04"}
|
| 96 |
+
{"current_steps": 920, "total_steps": 27630, "loss": 1.0469, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.973805362744064e-05, "epoch": 0.33, "percentage": 3.33, "elapsed_time": "0:21:04", "remaining_time": "10:11:41"}
|
| 97 |
+
{"current_steps": 930, "total_steps": 27630, "loss": 0.9705, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.973220548842598e-05, "epoch": 0.34, "percentage": 3.37, "elapsed_time": "0:21:14", "remaining_time": "10:09:43"}
|
| 98 |
+
{"current_steps": 940, "total_steps": 27630, "loss": 0.9956, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.972629296146035e-05, "epoch": 0.34, "percentage": 3.4, "elapsed_time": "0:21:22", "remaining_time": "10:07:08"}
|
| 99 |
+
{"current_steps": 950, "total_steps": 27630, "loss": 1.0232, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.972031605419864e-05, "epoch": 0.34, "percentage": 3.44, "elapsed_time": "0:21:32", "remaining_time": "10:05:05"}
|
| 100 |
+
{"current_steps": 960, "total_steps": 27630, "loss": 1.0471, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.971427477437914e-05, "epoch": 0.35, "percentage": 3.47, "elapsed_time": "0:21:40", "remaining_time": "10:02:21"}
|
| 101 |
+
{"current_steps": 970, "total_steps": 27630, "loss": 0.9652, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.970816912982344e-05, "epoch": 0.35, "percentage": 3.51, "elapsed_time": "0:21:49", "remaining_time": "9:59:46"}
|
| 102 |
+
{"current_steps": 980, "total_steps": 27630, "loss": 0.9894, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.970199912843648e-05, "epoch": 0.35, "percentage": 3.55, "elapsed_time": "0:21:57", "remaining_time": "9:57:16"}
|
| 103 |
+
{"current_steps": 990, "total_steps": 27630, "loss": 1.0437, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.96957647782065e-05, "epoch": 0.36, "percentage": 3.58, "elapsed_time": "0:22:05", "remaining_time": "9:54:30"}
|
| 104 |
+
{"current_steps": 1000, "total_steps": 27630, "loss": 1.02, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.968946608720511e-05, "epoch": 0.36, "percentage": 3.62, "elapsed_time": "0:22:14", "remaining_time": "9:52:27"}
|
| 105 |
+
{"current_steps": 1000, "total_steps": 27630, "loss": null, "eval_loss": 1.0154483318328857, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.36, "percentage": 3.62, "elapsed_time": "0:22:14", "remaining_time": "9:52:27"}
|
| 106 |
+
{"current_steps": 1010, "total_steps": 27630, "loss": 1.0676, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.968310306358715e-05, "epoch": 0.37, "percentage": 3.66, "elapsed_time": "0:24:28", "remaining_time": "10:45:00"}
|
| 107 |
+
{"current_steps": 1020, "total_steps": 27630, "loss": 1.027, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.967667571559081e-05, "epoch": 0.37, "percentage": 3.69, "elapsed_time": "0:24:36", "remaining_time": "10:42:05"}
|
| 108 |
+
{"current_steps": 1030, "total_steps": 27630, "loss": 1.0004, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.967018405153749e-05, "epoch": 0.37, "percentage": 3.73, "elapsed_time": "0:24:46", "remaining_time": "10:39:39"}
|
| 109 |
+
{"current_steps": 1040, "total_steps": 27630, "loss": 1.0395, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.966362807983196e-05, "epoch": 0.38, "percentage": 3.76, "elapsed_time": "0:24:56", "remaining_time": "10:37:29"}
|
| 110 |
+
{"current_steps": 1050, "total_steps": 27630, "loss": 0.9948, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.965700780896216e-05, "epoch": 0.38, "percentage": 3.8, "elapsed_time": "0:25:05", "remaining_time": "10:34:58"}
|
| 111 |
+
{"current_steps": 1060, "total_steps": 27630, "loss": 1.0281, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.965032324749932e-05, "epoch": 0.38, "percentage": 3.84, "elapsed_time": "0:25:12", "remaining_time": "10:31:58"}
|
| 112 |
+
{"current_steps": 1070, "total_steps": 27630, "loss": 1.0094, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.964357440409789e-05, "epoch": 0.39, "percentage": 3.87, "elapsed_time": "0:25:21", "remaining_time": "10:29:30"}
|
| 113 |
+
{"current_steps": 1080, "total_steps": 27630, "loss": 1.0272, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.963676128749553e-05, "epoch": 0.39, "percentage": 3.91, "elapsed_time": "0:25:28", "remaining_time": "10:26:21"}
|
| 114 |
+
{"current_steps": 1090, "total_steps": 27630, "loss": 1.0191, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.96298839065132e-05, "epoch": 0.39, "percentage": 3.94, "elapsed_time": "0:25:38", "remaining_time": "10:24:14"}
|
| 115 |
+
{"current_steps": 1100, "total_steps": 27630, "loss": 1.08, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.962294227005493e-05, "epoch": 0.4, "percentage": 3.98, "elapsed_time": "0:25:47", "remaining_time": "10:21:51"}
|
| 116 |
+
{"current_steps": 1110, "total_steps": 27630, "loss": 0.9954, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.961593638710804e-05, "epoch": 0.4, "percentage": 4.02, "elapsed_time": "0:25:55", "remaining_time": "10:19:25"}
|
| 117 |
+
{"current_steps": 1120, "total_steps": 27630, "loss": 1.071, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.960886626674302e-05, "epoch": 0.41, "percentage": 4.05, "elapsed_time": "0:26:03", "remaining_time": "10:16:47"}
|
| 118 |
+
{"current_steps": 1130, "total_steps": 27630, "loss": 0.9725, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.960173191811348e-05, "epoch": 0.41, "percentage": 4.09, "elapsed_time": "0:26:12", "remaining_time": "10:14:29"}
|
| 119 |
+
{"current_steps": 1140, "total_steps": 27630, "loss": 1.0071, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.959453335045622e-05, "epoch": 0.41, "percentage": 4.13, "elapsed_time": "0:26:19", "remaining_time": "10:11:46"}
|
| 120 |
+
{"current_steps": 1150, "total_steps": 27630, "loss": 1.0108, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.958727057309115e-05, "epoch": 0.42, "percentage": 4.16, "elapsed_time": "0:26:29", "remaining_time": "10:10:04"}
|
| 121 |
+
{"current_steps": 1160, "total_steps": 27630, "loss": 1.0495, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.957994359542138e-05, "epoch": 0.42, "percentage": 4.2, "elapsed_time": "0:26:37", "remaining_time": "10:07:40"}
|
| 122 |
+
{"current_steps": 1170, "total_steps": 27630, "loss": 1.0015, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.957255242693308e-05, "epoch": 0.42, "percentage": 4.23, "elapsed_time": "0:26:46", "remaining_time": "10:05:29"}
|
| 123 |
+
{"current_steps": 1180, "total_steps": 27630, "loss": 1.0559, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.956509707719555e-05, "epoch": 0.43, "percentage": 4.27, "elapsed_time": "0:26:54", "remaining_time": "10:03:17"}
|
| 124 |
+
{"current_steps": 1190, "total_steps": 27630, "loss": 1.0134, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.955757755586119e-05, "epoch": 0.43, "percentage": 4.31, "elapsed_time": "0:27:03", "remaining_time": "10:01:20"}
|
| 125 |
+
{"current_steps": 1200, "total_steps": 27630, "loss": 0.9492, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.954999387266546e-05, "epoch": 0.43, "percentage": 4.34, "elapsed_time": "0:27:11", "remaining_time": "9:58:47"}
|
| 126 |
+
{"current_steps": 1200, "total_steps": 27630, "loss": null, "eval_loss": 1.0133627653121948, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.43, "percentage": 4.34, "elapsed_time": "0:27:11", "remaining_time": "9:58:47"}
|
| 127 |
+
{"current_steps": 1210, "total_steps": 27630, "loss": 0.9629, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.95423460374269e-05, "epoch": 0.44, "percentage": 4.38, "elapsed_time": "0:29:23", "remaining_time": "10:41:38"}
|
| 128 |
+
{"current_steps": 1220, "total_steps": 27630, "loss": 1.0384, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.953463406004713e-05, "epoch": 0.44, "percentage": 4.42, "elapsed_time": "0:29:30", "remaining_time": "10:38:41"}
|
| 129 |
+
{"current_steps": 1230, "total_steps": 27630, "loss": 1.0235, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.952685795051077e-05, "epoch": 0.45, "percentage": 4.45, "elapsed_time": "0:29:38", "remaining_time": "10:36:02"}
|
| 130 |
+
{"current_steps": 1240, "total_steps": 27630, "loss": 1.0395, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.951901771888552e-05, "epoch": 0.45, "percentage": 4.49, "elapsed_time": "0:29:46", "remaining_time": "10:33:40"}
|
| 131 |
+
{"current_steps": 1250, "total_steps": 27630, "loss": 1.0914, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.951111337532205e-05, "epoch": 0.45, "percentage": 4.52, "elapsed_time": "0:29:55", "remaining_time": "10:31:31"}
|
| 132 |
+
{"current_steps": 1260, "total_steps": 27630, "loss": 1.0714, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.950314493005408e-05, "epoch": 0.46, "percentage": 4.56, "elapsed_time": "0:30:03", "remaining_time": "10:28:55"}
|
| 133 |
+
{"current_steps": 1270, "total_steps": 27630, "loss": 1.0224, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.949511239339831e-05, "epoch": 0.46, "percentage": 4.6, "elapsed_time": "0:30:11", "remaining_time": "10:26:30"}
|
| 134 |
+
{"current_steps": 1280, "total_steps": 27630, "loss": 1.0152, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.948701577575439e-05, "epoch": 0.46, "percentage": 4.63, "elapsed_time": "0:30:21", "remaining_time": "10:24:49"}
|
| 135 |
+
{"current_steps": 1290, "total_steps": 27630, "loss": 0.8988, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.947885508760496e-05, "epoch": 0.47, "percentage": 4.67, "elapsed_time": "0:30:31", "remaining_time": "10:23:07"}
|
| 136 |
+
{"current_steps": 1300, "total_steps": 27630, "loss": 1.0242, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.94706303395156e-05, "epoch": 0.47, "percentage": 4.71, "elapsed_time": "0:30:39", "remaining_time": "10:20:49"}
|
| 137 |
+
{"current_steps": 1310, "total_steps": 27630, "loss": 1.0145, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.946234154213487e-05, "epoch": 0.47, "percentage": 4.74, "elapsed_time": "0:30:47", "remaining_time": "10:18:45"}
|
| 138 |
+
{"current_steps": 1320, "total_steps": 27630, "loss": 1.0197, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.94539887061942e-05, "epoch": 0.48, "percentage": 4.78, "elapsed_time": "0:30:55", "remaining_time": "10:16:20"}
|
| 139 |
+
{"current_steps": 1330, "total_steps": 27630, "loss": 1.0273, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.944557184250794e-05, "epoch": 0.48, "percentage": 4.81, "elapsed_time": "0:31:03", "remaining_time": "10:14:07"}
|
| 140 |
+
{"current_steps": 1340, "total_steps": 27630, "loss": 0.9561, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.943709096197335e-05, "epoch": 0.48, "percentage": 4.85, "elapsed_time": "0:31:11", "remaining_time": "10:12:06"}
|
| 141 |
+
{"current_steps": 1350, "total_steps": 27630, "loss": 0.9678, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.942854607557057e-05, "epoch": 0.49, "percentage": 4.89, "elapsed_time": "0:31:21", "remaining_time": "10:10:33"}
|
| 142 |
+
{"current_steps": 1360, "total_steps": 27630, "loss": 1.0429, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.941993719436262e-05, "epoch": 0.49, "percentage": 4.92, "elapsed_time": "0:31:31", "remaining_time": "10:08:59"}
|
| 143 |
+
{"current_steps": 1370, "total_steps": 27630, "loss": 1.0506, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.941126432949535e-05, "epoch": 0.5, "percentage": 4.96, "elapsed_time": "0:31:39", "remaining_time": "10:06:55"}
|
| 144 |
+
{"current_steps": 1380, "total_steps": 27630, "loss": 1.0326, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.940252749219746e-05, "epoch": 0.5, "percentage": 4.99, "elapsed_time": "0:31:48", "remaining_time": "10:04:55"}
|
| 145 |
+
{"current_steps": 1390, "total_steps": 27630, "loss": 1.0413, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.939372669378048e-05, "epoch": 0.5, "percentage": 5.03, "elapsed_time": "0:31:57", "remaining_time": "10:03:13"}
|
| 146 |
+
{"current_steps": 1400, "total_steps": 27630, "loss": 1.0051, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.938486194563875e-05, "epoch": 0.51, "percentage": 5.07, "elapsed_time": "0:32:04", "remaining_time": "10:00:57"}
|
| 147 |
+
{"current_steps": 1400, "total_steps": 27630, "loss": null, "eval_loss": 1.011703372001648, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.51, "percentage": 5.07, "elapsed_time": "0:32:04", "remaining_time": "10:00:57"}
|
| 148 |
+
{"current_steps": 1410, "total_steps": 27630, "loss": 1.0277, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.937593325924937e-05, "epoch": 0.51, "percentage": 5.1, "elapsed_time": "0:34:18", "remaining_time": "10:37:53"}
|
| 149 |
+
{"current_steps": 1420, "total_steps": 27630, "loss": 0.9802, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.936694064617227e-05, "epoch": 0.51, "percentage": 5.14, "elapsed_time": "0:34:26", "remaining_time": "10:35:44"}
|
| 150 |
+
{"current_steps": 1430, "total_steps": 27630, "loss": 0.9811, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.935788411805011e-05, "epoch": 0.52, "percentage": 5.18, "elapsed_time": "0:34:34", "remaining_time": "10:33:33"}
|
| 151 |
+
{"current_steps": 1440, "total_steps": 27630, "loss": 0.9972, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.934876368660836e-05, "epoch": 0.52, "percentage": 5.21, "elapsed_time": "0:34:43", "remaining_time": "10:31:27"}
|
| 152 |
+
{"current_steps": 1450, "total_steps": 27630, "loss": 1.1006, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.933957936365515e-05, "epoch": 0.52, "percentage": 5.25, "elapsed_time": "0:34:51", "remaining_time": "10:29:14"}
|
| 153 |
+
{"current_steps": 1460, "total_steps": 27630, "loss": 1.0139, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.933033116108134e-05, "epoch": 0.53, "percentage": 5.28, "elapsed_time": "0:35:01", "remaining_time": "10:27:40"}
|
| 154 |
+
{"current_steps": 1470, "total_steps": 27630, "loss": 0.993, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.932101909086056e-05, "epoch": 0.53, "percentage": 5.32, "elapsed_time": "0:35:08", "remaining_time": "10:25:20"}
|
| 155 |
+
{"current_steps": 1480, "total_steps": 27630, "loss": 1.0539, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.931164316504904e-05, "epoch": 0.54, "percentage": 5.36, "elapsed_time": "0:35:16", "remaining_time": "10:23:09"}
|
| 156 |
+
{"current_steps": 1490, "total_steps": 27630, "loss": 0.9599, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.930220339578576e-05, "epoch": 0.54, "percentage": 5.39, "elapsed_time": "0:35:24", "remaining_time": "10:21:18"}
|
| 157 |
+
{"current_steps": 1500, "total_steps": 27630, "loss": 0.9813, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.929269979529232e-05, "epoch": 0.54, "percentage": 5.43, "elapsed_time": "0:35:33", "remaining_time": "10:19:20"}
|
| 158 |
+
{"current_steps": 1510, "total_steps": 27630, "loss": 0.9637, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.928313237587296e-05, "epoch": 0.55, "percentage": 5.47, "elapsed_time": "0:35:44", "remaining_time": "10:18:22"}
|
| 159 |
+
{"current_steps": 1520, "total_steps": 27630, "loss": 1.0375, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.927350114991456e-05, "epoch": 0.55, "percentage": 5.5, "elapsed_time": "0:35:55", "remaining_time": "10:17:09"}
|
| 160 |
+
{"current_steps": 1530, "total_steps": 27630, "loss": 1.0053, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.92638061298866e-05, "epoch": 0.55, "percentage": 5.54, "elapsed_time": "0:36:04", "remaining_time": "10:15:22"}
|
| 161 |
+
{"current_steps": 1540, "total_steps": 27630, "loss": 1.0631, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.925404732834117e-05, "epoch": 0.56, "percentage": 5.57, "elapsed_time": "0:36:13", "remaining_time": "10:13:49"}
|
| 162 |
+
{"current_steps": 1550, "total_steps": 27630, "loss": 1.0134, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.924422475791288e-05, "epoch": 0.56, "percentage": 5.61, "elapsed_time": "0:36:21", "remaining_time": "10:11:51"}
|
| 163 |
+
{"current_steps": 1560, "total_steps": 27630, "loss": 0.9989, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.923433843131901e-05, "epoch": 0.56, "percentage": 5.65, "elapsed_time": "0:36:31", "remaining_time": "10:10:17"}
|
| 164 |
+
{"current_steps": 1570, "total_steps": 27630, "loss": 1.0896, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.922438836135928e-05, "epoch": 0.57, "percentage": 5.68, "elapsed_time": "0:36:39", "remaining_time": "10:08:27"}
|
| 165 |
+
{"current_steps": 1580, "total_steps": 27630, "loss": 0.9954, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.921437456091596e-05, "epoch": 0.57, "percentage": 5.72, "elapsed_time": "0:36:46", "remaining_time": "10:06:19"}
|
| 166 |
+
{"current_steps": 1590, "total_steps": 27630, "loss": 0.9937, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.920429704295391e-05, "epoch": 0.58, "percentage": 5.75, "elapsed_time": "0:36:55", "remaining_time": "10:04:36"}
|
| 167 |
+
{"current_steps": 1600, "total_steps": 27630, "loss": 1.0469, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.919415582052036e-05, "epoch": 0.58, "percentage": 5.79, "elapsed_time": "0:37:03", "remaining_time": "10:02:49"}
|
| 168 |
+
{"current_steps": 1600, "total_steps": 27630, "loss": null, "eval_loss": 1.0105613470077515, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.58, "percentage": 5.79, "elapsed_time": "0:37:03", "remaining_time": "10:02:49"}
|
| 169 |
+
{"current_steps": 1610, "total_steps": 27630, "loss": 1.0408, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.918395090674514e-05, "epoch": 0.58, "percentage": 5.83, "elapsed_time": "0:39:15", "remaining_time": "10:34:34"}
|
| 170 |
+
{"current_steps": 1620, "total_steps": 27630, "loss": 0.9893, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.917368231484045e-05, "epoch": 0.59, "percentage": 5.86, "elapsed_time": "0:39:23", "remaining_time": "10:32:35"}
|
| 171 |
+
{"current_steps": 1630, "total_steps": 27630, "loss": 1.0563, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.916335005810095e-05, "epoch": 0.59, "percentage": 5.9, "elapsed_time": "0:39:31", "remaining_time": "10:30:31"}
|
| 172 |
+
{"current_steps": 1640, "total_steps": 27630, "loss": 1.0061, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.91529541499038e-05, "epoch": 0.59, "percentage": 5.94, "elapsed_time": "0:39:39", "remaining_time": "10:28:27"}
|
| 173 |
+
{"current_steps": 1650, "total_steps": 27630, "loss": 0.9639, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.914249460370846e-05, "epoch": 0.6, "percentage": 5.97, "elapsed_time": "0:39:47", "remaining_time": "10:26:37"}
|
| 174 |
+
{"current_steps": 1660, "total_steps": 27630, "loss": 1.0289, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.913197143305684e-05, "epoch": 0.6, "percentage": 6.01, "elapsed_time": "0:39:57", "remaining_time": "10:25:07"}
|
| 175 |
+
{"current_steps": 1670, "total_steps": 27630, "loss": 1.0154, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.912138465157325e-05, "epoch": 0.6, "percentage": 6.04, "elapsed_time": "0:40:05", "remaining_time": "10:23:11"}
|
| 176 |
+
{"current_steps": 1680, "total_steps": 27630, "loss": 1.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.91107342729643e-05, "epoch": 0.61, "percentage": 6.08, "elapsed_time": "0:40:13", "remaining_time": "10:21:23"}
|
| 177 |
+
{"current_steps": 1690, "total_steps": 27630, "loss": 0.9887, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.910002031101895e-05, "epoch": 0.61, "percentage": 6.12, "elapsed_time": "0:40:22", "remaining_time": "10:19:40"}
|
| 178 |
+
{"current_steps": 1700, "total_steps": 27630, "loss": 1.0703, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.908924277960854e-05, "epoch": 0.62, "percentage": 6.15, "elapsed_time": "0:40:30", "remaining_time": "10:17:52"}
|
| 179 |
+
{"current_steps": 1710, "total_steps": 27630, "loss": 0.9495, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.907840169268662e-05, "epoch": 0.62, "percentage": 6.19, "elapsed_time": "0:40:38", "remaining_time": "10:16:03"}
|
| 180 |
+
{"current_steps": 1720, "total_steps": 27630, "loss": 0.9878, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.90674970642891e-05, "epoch": 0.62, "percentage": 6.23, "elapsed_time": "0:40:47", "remaining_time": "10:14:30"}
|
| 181 |
+
{"current_steps": 1730, "total_steps": 27630, "loss": 1.0351, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.905652890853411e-05, "epoch": 0.63, "percentage": 6.26, "elapsed_time": "0:40:55", "remaining_time": "10:12:47"}
|
| 182 |
+
{"current_steps": 1740, "total_steps": 27630, "loss": 1.0528, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.904549723962206e-05, "epoch": 0.63, "percentage": 6.3, "elapsed_time": "0:41:03", "remaining_time": "10:10:58"}
|
| 183 |
+
{"current_steps": 1750, "total_steps": 27630, "loss": 1.0159, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.903440207183558e-05, "epoch": 0.63, "percentage": 6.33, "elapsed_time": "0:41:11", "remaining_time": "10:09:11"}
|
| 184 |
+
{"current_steps": 1760, "total_steps": 27630, "loss": 0.9879, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.90232434195395e-05, "epoch": 0.64, "percentage": 6.37, "elapsed_time": "0:41:19", "remaining_time": "10:07:26"}
|
| 185 |
+
{"current_steps": 1770, "total_steps": 27630, "loss": 1.0221, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.901202129718086e-05, "epoch": 0.64, "percentage": 6.41, "elapsed_time": "0:41:27", "remaining_time": "10:05:44"}
|
| 186 |
+
{"current_steps": 1780, "total_steps": 27630, "loss": 1.037, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.900073571928886e-05, "epoch": 0.64, "percentage": 6.44, "elapsed_time": "0:41:35", "remaining_time": "10:04:02"}
|
| 187 |
+
{"current_steps": 1790, "total_steps": 27630, "loss": 1.0008, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.898938670047486e-05, "epoch": 0.65, "percentage": 6.48, "elapsed_time": "0:41:46", "remaining_time": "10:02:58"}
|
| 188 |
+
{"current_steps": 1800, "total_steps": 27630, "loss": 0.9994, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.897797425543236e-05, "epoch": 0.65, "percentage": 6.51, "elapsed_time": "0:41:53", "remaining_time": "10:01:10"}
|
| 189 |
+
{"current_steps": 1800, "total_steps": 27630, "loss": null, "eval_loss": 1.0094062089920044, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.65, "percentage": 6.51, "elapsed_time": "0:41:53", "remaining_time": "10:01:10"}
|
| 190 |
+
{"current_steps": 1810, "total_steps": 27630, "loss": 1.0093, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.896649839893699e-05, "epoch": 0.66, "percentage": 6.55, "elapsed_time": "0:44:07", "remaining_time": "10:29:26"}
|
| 191 |
+
{"current_steps": 1820, "total_steps": 27630, "loss": 1.0124, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.895495914584643e-05, "epoch": 0.66, "percentage": 6.59, "elapsed_time": "0:44:15", "remaining_time": "10:27:41"}
|
| 192 |
+
{"current_steps": 1830, "total_steps": 27630, "loss": 1.0197, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.894335651110051e-05, "epoch": 0.66, "percentage": 6.62, "elapsed_time": "0:44:23", "remaining_time": "10:25:57"}
|
| 193 |
+
{"current_steps": 1840, "total_steps": 27630, "loss": 0.9469, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.893169050972106e-05, "epoch": 0.67, "percentage": 6.66, "elapsed_time": "0:44:33", "remaining_time": "10:24:30"}
|
| 194 |
+
{"current_steps": 1850, "total_steps": 27630, "loss": 1.0153, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.8919961156812e-05, "epoch": 0.67, "percentage": 6.7, "elapsed_time": "0:44:41", "remaining_time": "10:22:41"}
|
| 195 |
+
{"current_steps": 1860, "total_steps": 27630, "loss": 1.0124, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.89081684675592e-05, "epoch": 0.67, "percentage": 6.73, "elapsed_time": "0:44:49", "remaining_time": "10:21:03"}
|
| 196 |
+
{"current_steps": 1870, "total_steps": 27630, "loss": 0.96, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.88963124572306e-05, "epoch": 0.68, "percentage": 6.77, "elapsed_time": "0:44:55", "remaining_time": "10:18:56"}
|
| 197 |
+
{"current_steps": 1880, "total_steps": 27630, "loss": 1.0448, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.88843931411761e-05, "epoch": 0.68, "percentage": 6.8, "elapsed_time": "0:45:03", "remaining_time": "10:17:11"}
|
| 198 |
+
{"current_steps": 1890, "total_steps": 27630, "loss": 1.0362, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.887241053482757e-05, "epoch": 0.68, "percentage": 6.84, "elapsed_time": "0:45:12", "remaining_time": "10:15:43"}
|
| 199 |
+
{"current_steps": 1900, "total_steps": 27630, "loss": 1.0658, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.886036465369877e-05, "epoch": 0.69, "percentage": 6.88, "elapsed_time": "0:45:19", "remaining_time": "10:13:49"}
|
| 200 |
+
{"current_steps": 1910, "total_steps": 27630, "loss": 1.0068, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.884825551338546e-05, "epoch": 0.69, "percentage": 6.91, "elapsed_time": "0:45:26", "remaining_time": "10:12:00"}
|
| 201 |
+
{"current_steps": 1920, "total_steps": 27630, "loss": 1.0147, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.883608312956524e-05, "epoch": 0.69, "percentage": 6.95, "elapsed_time": "0:45:36", "remaining_time": "10:10:38"}
|
| 202 |
+
{"current_steps": 1930, "total_steps": 27630, "loss": 0.9421, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.882384751799762e-05, "epoch": 0.7, "percentage": 6.99, "elapsed_time": "0:45:45", "remaining_time": "10:09:14"}
|
| 203 |
+
{"current_steps": 1940, "total_steps": 27630, "loss": 1.0032, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.881154869452395e-05, "epoch": 0.7, "percentage": 7.02, "elapsed_time": "0:45:52", "remaining_time": "10:07:33"}
|
| 204 |
+
{"current_steps": 1950, "total_steps": 27630, "loss": 1.0491, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.879918667506748e-05, "epoch": 0.71, "percentage": 7.06, "elapsed_time": "0:46:00", "remaining_time": "10:05:54"}
|
| 205 |
+
{"current_steps": 1960, "total_steps": 27630, "loss": 0.9823, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.87867614756332e-05, "epoch": 0.71, "percentage": 7.09, "elapsed_time": "0:46:07", "remaining_time": "10:04:10"}
|
| 206 |
+
{"current_steps": 1970, "total_steps": 27630, "loss": 1.0326, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.87742731123079e-05, "epoch": 0.71, "percentage": 7.13, "elapsed_time": "0:46:16", "remaining_time": "10:02:44"}
|
| 207 |
+
{"current_steps": 1980, "total_steps": 27630, "loss": 1.0256, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.876172160126024e-05, "epoch": 0.72, "percentage": 7.17, "elapsed_time": "0:46:24", "remaining_time": "10:01:13"}
|
| 208 |
+
{"current_steps": 1990, "total_steps": 27630, "loss": 1.0301, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.874910695874053e-05, "epoch": 0.72, "percentage": 7.2, "elapsed_time": "0:46:32", "remaining_time": "9:59:35"}
|
| 209 |
+
{"current_steps": 2000, "total_steps": 27630, "loss": 1.0141, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.873642920108091e-05, "epoch": 0.72, "percentage": 7.24, "elapsed_time": "0:46:39", "remaining_time": "9:58:00"}
|
| 210 |
+
{"current_steps": 2000, "total_steps": 27630, "loss": null, "eval_loss": 1.0082145929336548, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.72, "percentage": 7.24, "elapsed_time": "0:46:39", "remaining_time": "9:58:00"}
|
| 211 |
+
{"current_steps": 2010, "total_steps": 27630, "loss": 0.9554, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.872368834469514e-05, "epoch": 0.73, "percentage": 7.27, "elapsed_time": "0:48:54", "remaining_time": "10:23:26"}
|
| 212 |
+
{"current_steps": 2020, "total_steps": 27630, "loss": 1.0374, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.871088440607874e-05, "epoch": 0.73, "percentage": 7.31, "elapsed_time": "0:49:02", "remaining_time": "10:21:40"}
|
| 213 |
+
{"current_steps": 2030, "total_steps": 27630, "loss": 1.01, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.869801740180889e-05, "epoch": 0.73, "percentage": 7.35, "elapsed_time": "0:49:10", "remaining_time": "10:20:12"}
|
| 214 |
+
{"current_steps": 2040, "total_steps": 27630, "loss": 1.0244, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.86850873485444e-05, "epoch": 0.74, "percentage": 7.38, "elapsed_time": "0:49:19", "remaining_time": "10:18:42"}
|
| 215 |
+
{"current_steps": 2050, "total_steps": 27630, "loss": 0.9303, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.867209426302572e-05, "epoch": 0.74, "percentage": 7.42, "elapsed_time": "0:49:26", "remaining_time": "10:17:01"}
|
| 216 |
+
{"current_steps": 2060, "total_steps": 27630, "loss": 1.0851, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.865903816207493e-05, "epoch": 0.75, "percentage": 7.46, "elapsed_time": "0:49:34", "remaining_time": "10:15:27"}
|
| 217 |
+
{"current_steps": 2070, "total_steps": 27630, "loss": 1.0042, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.864591906259568e-05, "epoch": 0.75, "percentage": 7.49, "elapsed_time": "0:49:41", "remaining_time": "10:13:38"}
|
| 218 |
+
{"current_steps": 2080, "total_steps": 27630, "loss": 0.9866, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.863273698157315e-05, "epoch": 0.75, "percentage": 7.53, "elapsed_time": "0:49:52", "remaining_time": "10:12:39"}
|
| 219 |
+
{"current_steps": 2090, "total_steps": 27630, "loss": 1.056, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.861949193607411e-05, "epoch": 0.76, "percentage": 7.56, "elapsed_time": "0:50:00", "remaining_time": "10:11:01"}
|
| 220 |
+
{"current_steps": 2100, "total_steps": 27630, "loss": 0.9988, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.860618394324682e-05, "epoch": 0.76, "percentage": 7.6, "elapsed_time": "0:50:07", "remaining_time": "10:09:24"}
|
| 221 |
+
{"current_steps": 2110, "total_steps": 27630, "loss": 0.9562, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.859281302032106e-05, "epoch": 0.76, "percentage": 7.64, "elapsed_time": "0:50:15", "remaining_time": "10:07:56"}
|
| 222 |
+
{"current_steps": 2120, "total_steps": 27630, "loss": 1.0325, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.857937918460808e-05, "epoch": 0.77, "percentage": 7.67, "elapsed_time": "0:50:24", "remaining_time": "10:06:30"}
|
| 223 |
+
{"current_steps": 2130, "total_steps": 27630, "loss": 1.0458, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.856588245350056e-05, "epoch": 0.77, "percentage": 7.71, "elapsed_time": "0:50:33", "remaining_time": "10:05:15"}
|
| 224 |
+
{"current_steps": 2140, "total_steps": 27630, "loss": 1.089, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.855232284447262e-05, "epoch": 0.77, "percentage": 7.75, "elapsed_time": "0:50:41", "remaining_time": "10:03:44"}
|
| 225 |
+
{"current_steps": 2150, "total_steps": 27630, "loss": 1.0398, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.853870037507983e-05, "epoch": 0.78, "percentage": 7.78, "elapsed_time": "0:50:48", "remaining_time": "10:02:11"}
|
| 226 |
+
{"current_steps": 2160, "total_steps": 27630, "loss": 1.0038, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.852501506295907e-05, "epoch": 0.78, "percentage": 7.82, "elapsed_time": "0:50:57", "remaining_time": "10:00:53"}
|
| 227 |
+
{"current_steps": 2170, "total_steps": 27630, "loss": 1.0343, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.851126692582864e-05, "epoch": 0.79, "percentage": 7.85, "elapsed_time": "0:51:05", "remaining_time": "9:59:23"}
|
| 228 |
+
{"current_steps": 2180, "total_steps": 27630, "loss": 0.9986, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.849745598148817e-05, "epoch": 0.79, "percentage": 7.89, "elapsed_time": "0:51:13", "remaining_time": "9:57:58"}
|
| 229 |
+
{"current_steps": 2190, "total_steps": 27630, "loss": 1.035, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.848358224781857e-05, "epoch": 0.79, "percentage": 7.93, "elapsed_time": "0:51:22", "remaining_time": "9:56:49"}
|
| 230 |
+
{"current_steps": 2200, "total_steps": 27630, "loss": 1.0891, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.84696457427821e-05, "epoch": 0.8, "percentage": 7.96, "elapsed_time": "0:51:30", "remaining_time": "9:55:20"}
|
| 231 |
+
{"current_steps": 2200, "total_steps": 27630, "loss": null, "eval_loss": 1.0072919130325317, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.8, "percentage": 7.96, "elapsed_time": "0:51:30", "remaining_time": "9:55:20"}
|
| 232 |
+
{"current_steps": 2210, "total_steps": 27630, "loss": 1.0259, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.845564648442222e-05, "epoch": 0.8, "percentage": 8.0, "elapsed_time": "0:53:43", "remaining_time": "10:18:02"}
|
| 233 |
+
{"current_steps": 2220, "total_steps": 27630, "loss": 1.0457, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.844158449086371e-05, "epoch": 0.8, "percentage": 8.03, "elapsed_time": "0:53:53", "remaining_time": "10:16:55"}
|
| 234 |
+
{"current_steps": 2230, "total_steps": 27630, "loss": 0.9869, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.842745978031253e-05, "epoch": 0.81, "percentage": 8.07, "elapsed_time": "0:54:02", "remaining_time": "10:15:34"}
|
| 235 |
+
{"current_steps": 2240, "total_steps": 27630, "loss": 1.0158, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.841327237105585e-05, "epoch": 0.81, "percentage": 8.11, "elapsed_time": "0:54:12", "remaining_time": "10:14:31"}
|
| 236 |
+
{"current_steps": 2250, "total_steps": 27630, "loss": 0.997, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.8399022281462e-05, "epoch": 0.81, "percentage": 8.14, "elapsed_time": "0:54:21", "remaining_time": "10:13:08"}
|
| 237 |
+
{"current_steps": 2260, "total_steps": 27630, "loss": 1.0148, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.838470952998049e-05, "epoch": 0.82, "percentage": 8.18, "elapsed_time": "0:54:30", "remaining_time": "10:11:51"}
|
| 238 |
+
{"current_steps": 2270, "total_steps": 27630, "loss": 0.9787, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.837033413514191e-05, "epoch": 0.82, "percentage": 8.22, "elapsed_time": "0:54:39", "remaining_time": "10:10:37"}
|
| 239 |
+
{"current_steps": 2280, "total_steps": 27630, "loss": 0.9656, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.835589611555805e-05, "epoch": 0.83, "percentage": 8.25, "elapsed_time": "0:54:47", "remaining_time": "10:09:16"}
|
| 240 |
+
{"current_steps": 2290, "total_steps": 27630, "loss": 0.9837, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.834139548992165e-05, "epoch": 0.83, "percentage": 8.29, "elapsed_time": "0:54:55", "remaining_time": "10:07:49"}
|
| 241 |
+
{"current_steps": 2300, "total_steps": 27630, "loss": 1.0513, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.832683227700661e-05, "epoch": 0.83, "percentage": 8.32, "elapsed_time": "0:55:04", "remaining_time": "10:06:37"}
|
| 242 |
+
{"current_steps": 2310, "total_steps": 27630, "loss": 0.9649, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.831220649566782e-05, "epoch": 0.84, "percentage": 8.36, "elapsed_time": "0:55:13", "remaining_time": "10:05:20"}
|
| 243 |
+
{"current_steps": 2320, "total_steps": 27630, "loss": 1.0208, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.829751816484116e-05, "epoch": 0.84, "percentage": 8.4, "elapsed_time": "0:55:20", "remaining_time": "10:03:48"}
|
| 244 |
+
{"current_steps": 2330, "total_steps": 27630, "loss": 0.9512, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.828276730354353e-05, "epoch": 0.84, "percentage": 8.43, "elapsed_time": "0:55:30", "remaining_time": "10:02:46"}
|
| 245 |
+
{"current_steps": 2340, "total_steps": 27630, "loss": 0.976, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.826795393087278e-05, "epoch": 0.85, "percentage": 8.47, "elapsed_time": "0:55:40", "remaining_time": "10:01:45"}
|
| 246 |
+
{"current_steps": 2350, "total_steps": 27630, "loss": 1.0036, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.825307806600765e-05, "epoch": 0.85, "percentage": 8.51, "elapsed_time": "0:55:50", "remaining_time": "10:00:40"}
|
| 247 |
+
{"current_steps": 2360, "total_steps": 27630, "loss": 1.0555, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.823813972820786e-05, "epoch": 0.85, "percentage": 8.54, "elapsed_time": "0:55:58", "remaining_time": "9:59:17"}
|
| 248 |
+
{"current_steps": 2370, "total_steps": 27630, "loss": 1.0483, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.822313893681397e-05, "epoch": 0.86, "percentage": 8.58, "elapsed_time": "0:56:06", "remaining_time": "9:58:06"}
|
| 249 |
+
{"current_steps": 2380, "total_steps": 27630, "loss": 1.0102, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.820807571124738e-05, "epoch": 0.86, "percentage": 8.61, "elapsed_time": "0:56:15", "remaining_time": "9:56:48"}
|
| 250 |
+
{"current_steps": 2390, "total_steps": 27630, "loss": 1.0626, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.819295007101035e-05, "epoch": 0.87, "percentage": 8.65, "elapsed_time": "0:56:24", "remaining_time": "9:55:44"}
|
| 251 |
+
{"current_steps": 2400, "total_steps": 27630, "loss": 1.0141, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.817776203568596e-05, "epoch": 0.87, "percentage": 8.69, "elapsed_time": "0:56:33", "remaining_time": "9:54:36"}
|
| 252 |
+
{"current_steps": 2400, "total_steps": 27630, "loss": null, "eval_loss": 1.0063296556472778, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.87, "percentage": 8.69, "elapsed_time": "0:56:33", "remaining_time": "9:54:36"}
|
| 253 |
+
{"current_steps": 2410, "total_steps": 27630, "loss": 1.0222, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.816251162493804e-05, "epoch": 0.87, "percentage": 8.72, "elapsed_time": "0:58:48", "remaining_time": "10:15:26"}
|
| 254 |
+
{"current_steps": 2420, "total_steps": 27630, "loss": 0.9891, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.814719885851121e-05, "epoch": 0.88, "percentage": 8.76, "elapsed_time": "0:58:56", "remaining_time": "10:14:04"}
|
| 255 |
+
{"current_steps": 2430, "total_steps": 27630, "loss": 0.9785, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.81318237562308e-05, "epoch": 0.88, "percentage": 8.79, "elapsed_time": "0:59:06", "remaining_time": "10:12:57"}
|
| 256 |
+
{"current_steps": 2440, "total_steps": 27630, "loss": 0.9357, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.811638633800287e-05, "epoch": 0.88, "percentage": 8.83, "elapsed_time": "0:59:13", "remaining_time": "10:11:24"}
|
| 257 |
+
{"current_steps": 2450, "total_steps": 27630, "loss": 1.0485, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.81008866238141e-05, "epoch": 0.89, "percentage": 8.87, "elapsed_time": "0:59:23", "remaining_time": "10:10:19"}
|
| 258 |
+
{"current_steps": 2460, "total_steps": 27630, "loss": 1.0138, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.808532463373188e-05, "epoch": 0.89, "percentage": 8.9, "elapsed_time": "0:59:32", "remaining_time": "10:09:11"}
|
| 259 |
+
{"current_steps": 2470, "total_steps": 27630, "loss": 1.0421, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.806970038790423e-05, "epoch": 0.89, "percentage": 8.94, "elapsed_time": "0:59:41", "remaining_time": "10:08:01"}
|
| 260 |
+
{"current_steps": 2480, "total_steps": 27630, "loss": 0.9926, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.805401390655975e-05, "epoch": 0.9, "percentage": 8.98, "elapsed_time": "0:59:49", "remaining_time": "10:06:39"}
|
| 261 |
+
{"current_steps": 2490, "total_steps": 27630, "loss": 1.0013, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.803826521000761e-05, "epoch": 0.9, "percentage": 9.01, "elapsed_time": "0:59:57", "remaining_time": "10:05:25"}
|
| 262 |
+
{"current_steps": 2500, "total_steps": 27630, "loss": 0.9937, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.802245431863757e-05, "epoch": 0.9, "percentage": 9.05, "elapsed_time": "1:00:05", "remaining_time": "10:04:01"}
|
| 263 |
+
{"current_steps": 2510, "total_steps": 27630, "loss": 0.9986, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.800658125291984e-05, "epoch": 0.91, "percentage": 9.08, "elapsed_time": "1:00:13", "remaining_time": "10:02:39"}
|
| 264 |
+
{"current_steps": 2520, "total_steps": 27630, "loss": 0.9984, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.79906460334052e-05, "epoch": 0.91, "percentage": 9.12, "elapsed_time": "1:00:20", "remaining_time": "10:01:16"}
|
| 265 |
+
{"current_steps": 2530, "total_steps": 27630, "loss": 1.0273, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.797464868072488e-05, "epoch": 0.92, "percentage": 9.16, "elapsed_time": "1:00:28", "remaining_time": "9:59:57"}
|
| 266 |
+
{"current_steps": 2540, "total_steps": 27630, "loss": 1.0346, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.795858921559052e-05, "epoch": 0.92, "percentage": 9.19, "elapsed_time": "1:00:36", "remaining_time": "9:58:43"}
|
| 267 |
+
{"current_steps": 2550, "total_steps": 27630, "loss": 1.0691, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.79424676587942e-05, "epoch": 0.92, "percentage": 9.23, "elapsed_time": "1:00:44", "remaining_time": "9:57:29"}
|
| 268 |
+
{"current_steps": 2560, "total_steps": 27630, "loss": 1.009, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.792628403120842e-05, "epoch": 0.93, "percentage": 9.27, "elapsed_time": "1:00:52", "remaining_time": "9:56:05"}
|
| 269 |
+
{"current_steps": 2570, "total_steps": 27630, "loss": 1.0015, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.791003835378598e-05, "epoch": 0.93, "percentage": 9.3, "elapsed_time": "1:01:01", "remaining_time": "9:55:00"}
|
| 270 |
+
{"current_steps": 2580, "total_steps": 27630, "loss": 1.0177, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.789373064756008e-05, "epoch": 0.93, "percentage": 9.34, "elapsed_time": "1:01:10", "remaining_time": "9:53:54"}
|
| 271 |
+
{"current_steps": 2590, "total_steps": 27630, "loss": 1.0935, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.787736093364416e-05, "epoch": 0.94, "percentage": 9.37, "elapsed_time": "1:01:20", "remaining_time": "9:53:02"}
|
| 272 |
+
{"current_steps": 2600, "total_steps": 27630, "loss": 1.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.786092923323203e-05, "epoch": 0.94, "percentage": 9.41, "elapsed_time": "1:01:28", "remaining_time": "9:51:52"}
|
| 273 |
+
{"current_steps": 2600, "total_steps": 27630, "loss": null, "eval_loss": 1.005922555923462, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.94, "percentage": 9.41, "elapsed_time": "1:01:28", "remaining_time": "9:51:52"}
|
| 274 |
+
{"current_steps": 2610, "total_steps": 27630, "loss": 1.0305, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.784443556759766e-05, "epoch": 0.94, "percentage": 9.45, "elapsed_time": "1:03:42", "remaining_time": "10:10:38"}
|
| 275 |
+
{"current_steps": 2620, "total_steps": 27630, "loss": 1.0427, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.78278799580953e-05, "epoch": 0.95, "percentage": 9.48, "elapsed_time": "1:03:51", "remaining_time": "10:09:36"}
|
| 276 |
+
{"current_steps": 2630, "total_steps": 27630, "loss": 1.0059, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.781126242615939e-05, "epoch": 0.95, "percentage": 9.52, "elapsed_time": "1:04:01", "remaining_time": "10:08:35"}
|
| 277 |
+
{"current_steps": 2640, "total_steps": 27630, "loss": 1.0418, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.779458299330452e-05, "epoch": 0.96, "percentage": 9.55, "elapsed_time": "1:04:09", "remaining_time": "10:07:23"}
|
| 278 |
+
{"current_steps": 2650, "total_steps": 27630, "loss": 1.0092, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.777784168112545e-05, "epoch": 0.96, "percentage": 9.59, "elapsed_time": "1:04:19", "remaining_time": "10:06:19"}
|
| 279 |
+
{"current_steps": 2660, "total_steps": 27630, "loss": 0.9883, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.776103851129706e-05, "epoch": 0.96, "percentage": 9.63, "elapsed_time": "1:04:28", "remaining_time": "10:05:10"}
|
| 280 |
+
{"current_steps": 2670, "total_steps": 27630, "loss": 1.0753, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.774417350557428e-05, "epoch": 0.97, "percentage": 9.66, "elapsed_time": "1:04:38", "remaining_time": "10:04:17"}
|
| 281 |
+
{"current_steps": 2680, "total_steps": 27630, "loss": 1.0524, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.772724668579212e-05, "epoch": 0.97, "percentage": 9.7, "elapsed_time": "1:04:48", "remaining_time": "10:03:23"}
|
| 282 |
+
{"current_steps": 2690, "total_steps": 27630, "loss": 1.0562, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.771025807386562e-05, "epoch": 0.97, "percentage": 9.74, "elapsed_time": "1:04:56", "remaining_time": "10:02:03"}
|
| 283 |
+
{"current_steps": 2700, "total_steps": 27630, "loss": 0.9925, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.769320769178983e-05, "epoch": 0.98, "percentage": 9.77, "elapsed_time": "1:05:03", "remaining_time": "10:00:45"}
|
| 284 |
+
{"current_steps": 2710, "total_steps": 27630, "loss": 1.014, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.767609556163977e-05, "epoch": 0.98, "percentage": 9.81, "elapsed_time": "1:05:11", "remaining_time": "9:59:31"}
|
| 285 |
+
{"current_steps": 2720, "total_steps": 27630, "loss": 0.9677, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.765892170557038e-05, "epoch": 0.98, "percentage": 9.84, "elapsed_time": "1:05:18", "remaining_time": "9:58:10"}
|
| 286 |
+
{"current_steps": 2730, "total_steps": 27630, "loss": 0.9954, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.764168614581655e-05, "epoch": 0.99, "percentage": 9.88, "elapsed_time": "1:05:27", "remaining_time": "9:57:03"}
|
| 287 |
+
{"current_steps": 2740, "total_steps": 27630, "loss": 1.0029, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.762438890469304e-05, "epoch": 0.99, "percentage": 9.92, "elapsed_time": "1:05:36", "remaining_time": "9:56:00"}
|
| 288 |
+
{"current_steps": 2750, "total_steps": 27630, "loss": 1.0555, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.760703000459446e-05, "epoch": 1.0, "percentage": 9.95, "elapsed_time": "1:05:44", "remaining_time": "9:54:45"}
|
| 289 |
+
{"current_steps": 2760, "total_steps": 27630, "loss": 1.0394, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.758960946799528e-05, "epoch": 1.0, "percentage": 9.99, "elapsed_time": "1:05:53", "remaining_time": "9:53:44"}
|
| 290 |
+
{"current_steps": 2770, "total_steps": 27630, "loss": 0.9325, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.757212731744974e-05, "epoch": 1.0, "percentage": 10.03, "elapsed_time": "1:06:02", "remaining_time": "9:52:44"}
|
| 291 |
+
{"current_steps": 2780, "total_steps": 27630, "loss": 0.9711, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.755458357559186e-05, "epoch": 1.01, "percentage": 10.06, "elapsed_time": "1:06:09", "remaining_time": "9:51:26"}
|
| 292 |
+
{"current_steps": 2790, "total_steps": 27630, "loss": 0.9651, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.753697826513541e-05, "epoch": 1.01, "percentage": 10.1, "elapsed_time": "1:06:17", "remaining_time": "9:50:13"}
|
| 293 |
+
{"current_steps": 2800, "total_steps": 27630, "loss": 0.9686, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.751931140887387e-05, "epoch": 1.01, "percentage": 10.13, "elapsed_time": "1:06:25", "remaining_time": "9:49:02"}
|
| 294 |
+
{"current_steps": 2800, "total_steps": 27630, "loss": null, "eval_loss": 1.0086077451705933, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.01, "percentage": 10.13, "elapsed_time": "1:06:25", "remaining_time": "9:49:02"}
|
| 295 |
+
{"current_steps": 2810, "total_steps": 27630, "loss": 0.9267, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.750158302968039e-05, "epoch": 1.02, "percentage": 10.17, "elapsed_time": "1:08:40", "remaining_time": "10:06:36"}
|
| 296 |
+
{"current_steps": 2820, "total_steps": 27630, "loss": 1.0193, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.748379315050778e-05, "epoch": 1.02, "percentage": 10.21, "elapsed_time": "1:08:48", "remaining_time": "10:05:18"}
|
| 297 |
+
{"current_steps": 2830, "total_steps": 27630, "loss": 0.8893, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.74659417943885e-05, "epoch": 1.02, "percentage": 10.24, "elapsed_time": "1:08:56", "remaining_time": "10:04:05"}
|
| 298 |
+
{"current_steps": 2840, "total_steps": 27630, "loss": 0.937, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.744802898443456e-05, "epoch": 1.03, "percentage": 10.28, "elapsed_time": "1:09:04", "remaining_time": "10:02:58"}
|
| 299 |
+
{"current_steps": 2850, "total_steps": 27630, "loss": 0.949, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.743005474383755e-05, "epoch": 1.03, "percentage": 10.31, "elapsed_time": "1:09:12", "remaining_time": "10:01:46"}
|
| 300 |
+
{"current_steps": 2860, "total_steps": 27630, "loss": 0.9897, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.741201909586861e-05, "epoch": 1.04, "percentage": 10.35, "elapsed_time": "1:09:20", "remaining_time": "10:00:31"}
|
| 301 |
+
{"current_steps": 2870, "total_steps": 27630, "loss": 0.9393, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.739392206387838e-05, "epoch": 1.04, "percentage": 10.39, "elapsed_time": "1:09:29", "remaining_time": "9:59:28"}
|
| 302 |
+
{"current_steps": 2880, "total_steps": 27630, "loss": 0.9365, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.737576367129694e-05, "epoch": 1.04, "percentage": 10.42, "elapsed_time": "1:09:37", "remaining_time": "9:58:16"}
|
| 303 |
+
{"current_steps": 2890, "total_steps": 27630, "loss": 1.0074, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.735754394163386e-05, "epoch": 1.05, "percentage": 10.46, "elapsed_time": "1:09:45", "remaining_time": "9:57:07"}
|
| 304 |
+
{"current_steps": 2900, "total_steps": 27630, "loss": 0.9682, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.73392628984781e-05, "epoch": 1.05, "percentage": 10.5, "elapsed_time": "1:09:53", "remaining_time": "9:56:02"}
|
| 305 |
+
{"current_steps": 2910, "total_steps": 27630, "loss": 0.9753, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.732092056549799e-05, "epoch": 1.05, "percentage": 10.53, "elapsed_time": "1:10:01", "remaining_time": "9:54:54"}
|
| 306 |
+
{"current_steps": 2920, "total_steps": 27630, "loss": 0.926, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.730251696644122e-05, "epoch": 1.06, "percentage": 10.57, "elapsed_time": "1:10:08", "remaining_time": "9:53:37"}
|
| 307 |
+
{"current_steps": 2930, "total_steps": 27630, "loss": 0.9993, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.728405212513483e-05, "epoch": 1.06, "percentage": 10.6, "elapsed_time": "1:10:16", "remaining_time": "9:52:23"}
|
| 308 |
+
{"current_steps": 2940, "total_steps": 27630, "loss": 0.9879, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.726552606548512e-05, "epoch": 1.06, "percentage": 10.64, "elapsed_time": "1:10:24", "remaining_time": "9:51:15"}
|
| 309 |
+
{"current_steps": 2950, "total_steps": 27630, "loss": 0.9626, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.724693881147761e-05, "epoch": 1.07, "percentage": 10.68, "elapsed_time": "1:10:32", "remaining_time": "9:50:13"}
|
| 310 |
+
{"current_steps": 2960, "total_steps": 27630, "loss": 0.9767, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.722829038717717e-05, "epoch": 1.07, "percentage": 10.71, "elapsed_time": "1:10:40", "remaining_time": "9:48:59"}
|
| 311 |
+
{"current_steps": 2970, "total_steps": 27630, "loss": 0.9357, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.720958081672773e-05, "epoch": 1.07, "percentage": 10.75, "elapsed_time": "1:10:47", "remaining_time": "9:47:48"}
|
| 312 |
+
{"current_steps": 2980, "total_steps": 27630, "loss": 0.9705, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.719081012435247e-05, "epoch": 1.08, "percentage": 10.79, "elapsed_time": "1:10:54", "remaining_time": "9:46:35"}
|
| 313 |
+
{"current_steps": 2990, "total_steps": 27630, "loss": 0.9727, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.717197833435367e-05, "epoch": 1.08, "percentage": 10.82, "elapsed_time": "1:11:02", "remaining_time": "9:45:28"}
|
| 314 |
+
{"current_steps": 3000, "total_steps": 27630, "loss": 0.9767, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.715308547111273e-05, "epoch": 1.09, "percentage": 10.86, "elapsed_time": "1:11:10", "remaining_time": "9:44:21"}
|
| 315 |
+
{"current_steps": 3000, "total_steps": 27630, "loss": null, "eval_loss": 1.014098048210144, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.09, "percentage": 10.86, "elapsed_time": "1:11:10", "remaining_time": "9:44:21"}
|
| 316 |
+
{"current_steps": 3010, "total_steps": 27630, "loss": 0.9605, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.713413155909009e-05, "epoch": 1.09, "percentage": 10.89, "elapsed_time": "1:13:25", "remaining_time": "10:00:32"}
|
| 317 |
+
{"current_steps": 3020, "total_steps": 27630, "loss": 0.9611, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.711511662282527e-05, "epoch": 1.09, "percentage": 10.93, "elapsed_time": "1:13:34", "remaining_time": "9:59:30"}
|
| 318 |
+
{"current_steps": 3030, "total_steps": 27630, "loss": 0.9222, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.709604068693679e-05, "epoch": 1.1, "percentage": 10.97, "elapsed_time": "1:13:43", "remaining_time": "9:58:31"}
|
| 319 |
+
{"current_steps": 3040, "total_steps": 27630, "loss": 0.9369, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.707690377612211e-05, "epoch": 1.1, "percentage": 11.0, "elapsed_time": "1:13:51", "remaining_time": "9:57:28"}
|
| 320 |
+
{"current_steps": 3050, "total_steps": 27630, "loss": 0.8864, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.705770591515768e-05, "epoch": 1.1, "percentage": 11.04, "elapsed_time": "1:14:00", "remaining_time": "9:56:26"}
|
| 321 |
+
{"current_steps": 3060, "total_steps": 27630, "loss": 0.9753, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.703844712889884e-05, "epoch": 1.11, "percentage": 11.07, "elapsed_time": "1:14:09", "remaining_time": "9:55:22"}
|
| 322 |
+
{"current_steps": 3070, "total_steps": 27630, "loss": 0.9233, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.701912744227979e-05, "epoch": 1.11, "percentage": 11.11, "elapsed_time": "1:14:16", "remaining_time": "9:54:10"}
|
| 323 |
+
{"current_steps": 3080, "total_steps": 27630, "loss": 0.987, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.699974688031363e-05, "epoch": 1.11, "percentage": 11.15, "elapsed_time": "1:14:23", "remaining_time": "9:52:59"}
|
| 324 |
+
{"current_steps": 3090, "total_steps": 27630, "loss": 0.8833, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.69803054680922e-05, "epoch": 1.12, "percentage": 11.18, "elapsed_time": "1:14:32", "remaining_time": "9:51:55"}
|
| 325 |
+
{"current_steps": 3100, "total_steps": 27630, "loss": 0.9894, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.696080323078621e-05, "epoch": 1.12, "percentage": 11.22, "elapsed_time": "1:14:39", "remaining_time": "9:50:49"}
|
| 326 |
+
{"current_steps": 3110, "total_steps": 27630, "loss": 0.9417, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.694124019364505e-05, "epoch": 1.13, "percentage": 11.26, "elapsed_time": "1:14:47", "remaining_time": "9:49:42"}
|
| 327 |
+
{"current_steps": 3120, "total_steps": 27630, "loss": 0.9251, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.692161638199686e-05, "epoch": 1.13, "percentage": 11.29, "elapsed_time": "1:14:55", "remaining_time": "9:48:35"}
|
| 328 |
+
{"current_steps": 3130, "total_steps": 27630, "loss": 0.9447, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.690193182124844e-05, "epoch": 1.13, "percentage": 11.33, "elapsed_time": "1:15:04", "remaining_time": "9:47:40"}
|
| 329 |
+
{"current_steps": 3140, "total_steps": 27630, "loss": 0.9984, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.68821865368853e-05, "epoch": 1.14, "percentage": 11.36, "elapsed_time": "1:15:13", "remaining_time": "9:46:43"}
|
| 330 |
+
{"current_steps": 3150, "total_steps": 27630, "loss": 0.9422, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.686238055447148e-05, "epoch": 1.14, "percentage": 11.4, "elapsed_time": "1:15:22", "remaining_time": "9:45:45"}
|
| 331 |
+
{"current_steps": 3160, "total_steps": 27630, "loss": 0.9199, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.684251389964967e-05, "epoch": 1.14, "percentage": 11.44, "elapsed_time": "1:15:29", "remaining_time": "9:44:37"}
|
| 332 |
+
{"current_steps": 3170, "total_steps": 27630, "loss": 0.9249, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.68225865981411e-05, "epoch": 1.15, "percentage": 11.47, "elapsed_time": "1:15:40", "remaining_time": "9:43:52"}
|
| 333 |
+
{"current_steps": 3180, "total_steps": 27630, "loss": 0.947, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.680259867574552e-05, "epoch": 1.15, "percentage": 11.51, "elapsed_time": "1:15:49", "remaining_time": "9:42:59"}
|
| 334 |
+
{"current_steps": 3190, "total_steps": 27630, "loss": 0.9956, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.678255015834112e-05, "epoch": 1.15, "percentage": 11.55, "elapsed_time": "1:15:57", "remaining_time": "9:41:53"}
|
| 335 |
+
{"current_steps": 3200, "total_steps": 27630, "loss": 0.9494, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.676244107188463e-05, "epoch": 1.16, "percentage": 11.58, "elapsed_time": "1:16:06", "remaining_time": "9:41:02"}
|
| 336 |
+
{"current_steps": 3200, "total_steps": 27630, "loss": null, "eval_loss": 1.0160499811172485, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.16, "percentage": 11.58, "elapsed_time": "1:16:06", "remaining_time": "9:41:02"}
|
| 337 |
+
{"current_steps": 3200, "total_steps": 27630, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.16, "percentage": 11.58, "elapsed_time": "1:16:06", "remaining_time": "9:41:02"}
|
| 338 |
+
{"current_steps": 488, "total_steps": 488, "loss": null, "eval_loss": 1.0082145929336548, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.16, "percentage": 100.0, "elapsed_time": "1:20:24", "remaining_time": "0:00:00"}
|
llama2_13b_peft/alpaca/trainer_state.json
ADDED
|
@@ -0,0 +1,2398 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0082145929336548,
|
| 3 |
+
"best_model_checkpoint": "ckpt/llama2_13b_fuze15_no_sys/alpaca_no_sys/checkpoint-2000",
|
| 4 |
+
"epoch": 1.158161418747738,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 3200,
|
| 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": 0.2189224660396576,
|
| 14 |
+
"learning_rate": 5e-05,
|
| 15 |
+
"loss": 1.4369,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.01,
|
| 20 |
+
"grad_norm": 0.4817655384540558,
|
| 21 |
+
"learning_rate": 0.0001,
|
| 22 |
+
"loss": 1.3624,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.01,
|
| 27 |
+
"grad_norm": 0.35323551297187805,
|
| 28 |
+
"learning_rate": 9.999996763266864e-05,
|
| 29 |
+
"loss": 1.1589,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.01,
|
| 34 |
+
"grad_norm": 0.2697048485279083,
|
| 35 |
+
"learning_rate": 9.999987053071647e-05,
|
| 36 |
+
"loss": 1.1103,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"grad_norm": 0.34059372544288635,
|
| 42 |
+
"learning_rate": 9.99997086942692e-05,
|
| 43 |
+
"loss": 1.0601,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.02,
|
| 48 |
+
"grad_norm": 0.2907443344593048,
|
| 49 |
+
"learning_rate": 9.999948212353635e-05,
|
| 50 |
+
"loss": 1.0302,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03,
|
| 55 |
+
"grad_norm": 0.4002208113670349,
|
| 56 |
+
"learning_rate": 9.999919081881129e-05,
|
| 57 |
+
"loss": 1.114,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.03,
|
| 62 |
+
"grad_norm": 0.4364459216594696,
|
| 63 |
+
"learning_rate": 9.999883478047113e-05,
|
| 64 |
+
"loss": 1.0913,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.03,
|
| 69 |
+
"grad_norm": 0.322396844625473,
|
| 70 |
+
"learning_rate": 9.999841400897687e-05,
|
| 71 |
+
"loss": 1.0778,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.04,
|
| 76 |
+
"grad_norm": 0.5678238868713379,
|
| 77 |
+
"learning_rate": 9.999792850487325e-05,
|
| 78 |
+
"loss": 1.0493,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.04,
|
| 83 |
+
"grad_norm": 0.2919568717479706,
|
| 84 |
+
"learning_rate": 9.999737826878886e-05,
|
| 85 |
+
"loss": 1.0249,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.04,
|
| 90 |
+
"grad_norm": 0.3787660300731659,
|
| 91 |
+
"learning_rate": 9.99967633014361e-05,
|
| 92 |
+
"loss": 1.0594,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.05,
|
| 97 |
+
"grad_norm": 0.33062055706977844,
|
| 98 |
+
"learning_rate": 9.999608360361113e-05,
|
| 99 |
+
"loss": 1.0527,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.05,
|
| 104 |
+
"grad_norm": 0.3306855857372284,
|
| 105 |
+
"learning_rate": 9.999533917619399e-05,
|
| 106 |
+
"loss": 1.0051,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.05,
|
| 111 |
+
"grad_norm": 0.41762664914131165,
|
| 112 |
+
"learning_rate": 9.999453002014846e-05,
|
| 113 |
+
"loss": 0.9906,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.06,
|
| 118 |
+
"grad_norm": 0.291189044713974,
|
| 119 |
+
"learning_rate": 9.999365613652217e-05,
|
| 120 |
+
"loss": 1.0197,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.06,
|
| 125 |
+
"grad_norm": 0.30276551842689514,
|
| 126 |
+
"learning_rate": 9.999271752644649e-05,
|
| 127 |
+
"loss": 1.0356,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.07,
|
| 132 |
+
"grad_norm": 0.25866344571113586,
|
| 133 |
+
"learning_rate": 9.999171419113666e-05,
|
| 134 |
+
"loss": 1.0332,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.07,
|
| 139 |
+
"grad_norm": 0.1927756369113922,
|
| 140 |
+
"learning_rate": 9.999064613189171e-05,
|
| 141 |
+
"loss": 1.0126,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.07,
|
| 146 |
+
"grad_norm": 0.2776283621788025,
|
| 147 |
+
"learning_rate": 9.998951335009442e-05,
|
| 148 |
+
"loss": 1.0429,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.07,
|
| 153 |
+
"eval_loss": 1.029819130897522,
|
| 154 |
+
"eval_runtime": 124.6792,
|
| 155 |
+
"eval_samples_per_second": 62.569,
|
| 156 |
+
"eval_steps_per_second": 3.914,
|
| 157 |
+
"step": 200
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.08,
|
| 161 |
+
"grad_norm": 0.320551335811615,
|
| 162 |
+
"learning_rate": 9.998831584721141e-05,
|
| 163 |
+
"loss": 1.0431,
|
| 164 |
+
"step": 210
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.08,
|
| 168 |
+
"grad_norm": 0.46670058369636536,
|
| 169 |
+
"learning_rate": 9.998705362479307e-05,
|
| 170 |
+
"loss": 1.0374,
|
| 171 |
+
"step": 220
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.08,
|
| 175 |
+
"grad_norm": 0.30959388613700867,
|
| 176 |
+
"learning_rate": 9.99857266844736e-05,
|
| 177 |
+
"loss": 1.1065,
|
| 178 |
+
"step": 230
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.09,
|
| 182 |
+
"grad_norm": 0.3016811013221741,
|
| 183 |
+
"learning_rate": 9.998433502797095e-05,
|
| 184 |
+
"loss": 1.1105,
|
| 185 |
+
"step": 240
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.09,
|
| 189 |
+
"grad_norm": 0.356992244720459,
|
| 190 |
+
"learning_rate": 9.998287865708694e-05,
|
| 191 |
+
"loss": 0.9839,
|
| 192 |
+
"step": 250
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.09,
|
| 196 |
+
"grad_norm": 0.29836413264274597,
|
| 197 |
+
"learning_rate": 9.998135757370708e-05,
|
| 198 |
+
"loss": 1.0401,
|
| 199 |
+
"step": 260
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.1,
|
| 203 |
+
"grad_norm": 0.4305395483970642,
|
| 204 |
+
"learning_rate": 9.997977177980074e-05,
|
| 205 |
+
"loss": 1.0461,
|
| 206 |
+
"step": 270
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.1,
|
| 210 |
+
"grad_norm": 0.2959505021572113,
|
| 211 |
+
"learning_rate": 9.9978121277421e-05,
|
| 212 |
+
"loss": 1.0662,
|
| 213 |
+
"step": 280
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.1,
|
| 217 |
+
"grad_norm": 0.2577110826969147,
|
| 218 |
+
"learning_rate": 9.99764060687048e-05,
|
| 219 |
+
"loss": 1.0736,
|
| 220 |
+
"step": 290
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.11,
|
| 224 |
+
"grad_norm": 0.2583490014076233,
|
| 225 |
+
"learning_rate": 9.997462615587276e-05,
|
| 226 |
+
"loss": 0.9963,
|
| 227 |
+
"step": 300
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.11,
|
| 231 |
+
"grad_norm": 0.29901596903800964,
|
| 232 |
+
"learning_rate": 9.997278154122935e-05,
|
| 233 |
+
"loss": 1.044,
|
| 234 |
+
"step": 310
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.12,
|
| 238 |
+
"grad_norm": 0.24256502091884613,
|
| 239 |
+
"learning_rate": 9.997087222716278e-05,
|
| 240 |
+
"loss": 1.0713,
|
| 241 |
+
"step": 320
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.12,
|
| 245 |
+
"grad_norm": 0.267166405916214,
|
| 246 |
+
"learning_rate": 9.996889821614502e-05,
|
| 247 |
+
"loss": 1.0721,
|
| 248 |
+
"step": 330
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.12,
|
| 252 |
+
"grad_norm": 0.21612702310085297,
|
| 253 |
+
"learning_rate": 9.996685951073182e-05,
|
| 254 |
+
"loss": 1.0414,
|
| 255 |
+
"step": 340
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.13,
|
| 259 |
+
"grad_norm": 0.3107874095439911,
|
| 260 |
+
"learning_rate": 9.996475611356264e-05,
|
| 261 |
+
"loss": 0.9856,
|
| 262 |
+
"step": 350
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.13,
|
| 266 |
+
"grad_norm": 0.27626070380210876,
|
| 267 |
+
"learning_rate": 9.996258802736079e-05,
|
| 268 |
+
"loss": 1.0121,
|
| 269 |
+
"step": 360
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.13,
|
| 273 |
+
"grad_norm": 0.2957281172275543,
|
| 274 |
+
"learning_rate": 9.996035525493322e-05,
|
| 275 |
+
"loss": 1.0785,
|
| 276 |
+
"step": 370
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.14,
|
| 280 |
+
"grad_norm": 0.3168753981590271,
|
| 281 |
+
"learning_rate": 9.995805779917073e-05,
|
| 282 |
+
"loss": 0.996,
|
| 283 |
+
"step": 380
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.14,
|
| 287 |
+
"grad_norm": 0.24823521077632904,
|
| 288 |
+
"learning_rate": 9.99556956630478e-05,
|
| 289 |
+
"loss": 1.0557,
|
| 290 |
+
"step": 390
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.14,
|
| 294 |
+
"grad_norm": 0.3291969895362854,
|
| 295 |
+
"learning_rate": 9.995326884962268e-05,
|
| 296 |
+
"loss": 1.0505,
|
| 297 |
+
"step": 400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.14,
|
| 301 |
+
"eval_loss": 1.023820400238037,
|
| 302 |
+
"eval_runtime": 124.7265,
|
| 303 |
+
"eval_samples_per_second": 62.545,
|
| 304 |
+
"eval_steps_per_second": 3.913,
|
| 305 |
+
"step": 400
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.15,
|
| 309 |
+
"grad_norm": 0.3567464351654053,
|
| 310 |
+
"learning_rate": 9.995077736203733e-05,
|
| 311 |
+
"loss": 0.9919,
|
| 312 |
+
"step": 410
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.15,
|
| 316 |
+
"grad_norm": 0.2938403785228729,
|
| 317 |
+
"learning_rate": 9.99482212035175e-05,
|
| 318 |
+
"loss": 1.0736,
|
| 319 |
+
"step": 420
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 0.16,
|
| 323 |
+
"grad_norm": 0.27481499314308167,
|
| 324 |
+
"learning_rate": 9.994560037737259e-05,
|
| 325 |
+
"loss": 1.0633,
|
| 326 |
+
"step": 430
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.16,
|
| 330 |
+
"grad_norm": 0.34652218222618103,
|
| 331 |
+
"learning_rate": 9.994291488699579e-05,
|
| 332 |
+
"loss": 1.049,
|
| 333 |
+
"step": 440
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.16,
|
| 337 |
+
"grad_norm": 0.23733928799629211,
|
| 338 |
+
"learning_rate": 9.994016473586398e-05,
|
| 339 |
+
"loss": 1.0022,
|
| 340 |
+
"step": 450
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.17,
|
| 344 |
+
"grad_norm": 0.2666071653366089,
|
| 345 |
+
"learning_rate": 9.993734992753777e-05,
|
| 346 |
+
"loss": 1.0076,
|
| 347 |
+
"step": 460
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 0.17,
|
| 351 |
+
"grad_norm": 0.22843866050243378,
|
| 352 |
+
"learning_rate": 9.993447046566146e-05,
|
| 353 |
+
"loss": 1.0298,
|
| 354 |
+
"step": 470
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.17,
|
| 358 |
+
"grad_norm": 0.4334356486797333,
|
| 359 |
+
"learning_rate": 9.993152635396308e-05,
|
| 360 |
+
"loss": 1.0635,
|
| 361 |
+
"step": 480
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.18,
|
| 365 |
+
"grad_norm": 0.25845977663993835,
|
| 366 |
+
"learning_rate": 9.992851759625433e-05,
|
| 367 |
+
"loss": 1.0183,
|
| 368 |
+
"step": 490
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.18,
|
| 372 |
+
"grad_norm": 0.26029086112976074,
|
| 373 |
+
"learning_rate": 9.992544419643066e-05,
|
| 374 |
+
"loss": 0.963,
|
| 375 |
+
"step": 500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.18,
|
| 379 |
+
"grad_norm": 0.23090577125549316,
|
| 380 |
+
"learning_rate": 9.992230615847116e-05,
|
| 381 |
+
"loss": 0.9691,
|
| 382 |
+
"step": 510
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.19,
|
| 386 |
+
"grad_norm": 0.2835213243961334,
|
| 387 |
+
"learning_rate": 9.991910348643865e-05,
|
| 388 |
+
"loss": 1.0309,
|
| 389 |
+
"step": 520
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.19,
|
| 393 |
+
"grad_norm": 0.2612157166004181,
|
| 394 |
+
"learning_rate": 9.991583618447958e-05,
|
| 395 |
+
"loss": 1.0232,
|
| 396 |
+
"step": 530
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.2,
|
| 400 |
+
"grad_norm": 0.43860122561454773,
|
| 401 |
+
"learning_rate": 9.99125042568241e-05,
|
| 402 |
+
"loss": 1.0308,
|
| 403 |
+
"step": 540
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.2,
|
| 407 |
+
"grad_norm": 0.2504933476448059,
|
| 408 |
+
"learning_rate": 9.990910770778606e-05,
|
| 409 |
+
"loss": 1.0581,
|
| 410 |
+
"step": 550
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.2,
|
| 414 |
+
"grad_norm": 0.2778143286705017,
|
| 415 |
+
"learning_rate": 9.990564654176293e-05,
|
| 416 |
+
"loss": 0.958,
|
| 417 |
+
"step": 560
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.21,
|
| 421 |
+
"grad_norm": 0.29035818576812744,
|
| 422 |
+
"learning_rate": 9.990212076323586e-05,
|
| 423 |
+
"loss": 1.0258,
|
| 424 |
+
"step": 570
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.21,
|
| 428 |
+
"grad_norm": 0.307841032743454,
|
| 429 |
+
"learning_rate": 9.989853037676965e-05,
|
| 430 |
+
"loss": 1.0724,
|
| 431 |
+
"step": 580
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.21,
|
| 435 |
+
"grad_norm": 0.3011914789676666,
|
| 436 |
+
"learning_rate": 9.989487538701279e-05,
|
| 437 |
+
"loss": 0.9847,
|
| 438 |
+
"step": 590
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.22,
|
| 442 |
+
"grad_norm": 0.27195674180984497,
|
| 443 |
+
"learning_rate": 9.989115579869732e-05,
|
| 444 |
+
"loss": 1.044,
|
| 445 |
+
"step": 600
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.22,
|
| 449 |
+
"eval_loss": 1.0194298028945923,
|
| 450 |
+
"eval_runtime": 124.7334,
|
| 451 |
+
"eval_samples_per_second": 62.541,
|
| 452 |
+
"eval_steps_per_second": 3.912,
|
| 453 |
+
"step": 600
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.22,
|
| 457 |
+
"grad_norm": 0.2725551724433899,
|
| 458 |
+
"learning_rate": 9.988737161663898e-05,
|
| 459 |
+
"loss": 1.0244,
|
| 460 |
+
"step": 610
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.22,
|
| 464 |
+
"grad_norm": 0.2821577787399292,
|
| 465 |
+
"learning_rate": 9.988352284573713e-05,
|
| 466 |
+
"loss": 1.0254,
|
| 467 |
+
"step": 620
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.23,
|
| 471 |
+
"grad_norm": 0.3664613664150238,
|
| 472 |
+
"learning_rate": 9.987960949097475e-05,
|
| 473 |
+
"loss": 1.1093,
|
| 474 |
+
"step": 630
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.23,
|
| 478 |
+
"grad_norm": 0.3072526156902313,
|
| 479 |
+
"learning_rate": 9.987563155741842e-05,
|
| 480 |
+
"loss": 1.0196,
|
| 481 |
+
"step": 640
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.24,
|
| 485 |
+
"grad_norm": 0.24550805985927582,
|
| 486 |
+
"learning_rate": 9.987158905021836e-05,
|
| 487 |
+
"loss": 1.012,
|
| 488 |
+
"step": 650
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.24,
|
| 492 |
+
"grad_norm": 0.2521149814128876,
|
| 493 |
+
"learning_rate": 9.986748197460837e-05,
|
| 494 |
+
"loss": 1.0219,
|
| 495 |
+
"step": 660
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.24,
|
| 499 |
+
"grad_norm": 0.34175044298171997,
|
| 500 |
+
"learning_rate": 9.986331033590586e-05,
|
| 501 |
+
"loss": 1.015,
|
| 502 |
+
"step": 670
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.25,
|
| 506 |
+
"grad_norm": 0.30103522539138794,
|
| 507 |
+
"learning_rate": 9.98590741395118e-05,
|
| 508 |
+
"loss": 1.1113,
|
| 509 |
+
"step": 680
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.25,
|
| 513 |
+
"grad_norm": 0.2344699651002884,
|
| 514 |
+
"learning_rate": 9.985477339091078e-05,
|
| 515 |
+
"loss": 1.0456,
|
| 516 |
+
"step": 690
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.25,
|
| 520 |
+
"grad_norm": 0.26754796504974365,
|
| 521 |
+
"learning_rate": 9.985040809567097e-05,
|
| 522 |
+
"loss": 1.0102,
|
| 523 |
+
"step": 700
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 0.26,
|
| 527 |
+
"grad_norm": 0.31665658950805664,
|
| 528 |
+
"learning_rate": 9.984597825944405e-05,
|
| 529 |
+
"loss": 1.0057,
|
| 530 |
+
"step": 710
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.26,
|
| 534 |
+
"grad_norm": 0.2716057300567627,
|
| 535 |
+
"learning_rate": 9.984148388796532e-05,
|
| 536 |
+
"loss": 0.9937,
|
| 537 |
+
"step": 720
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.26,
|
| 541 |
+
"grad_norm": 0.2589300274848938,
|
| 542 |
+
"learning_rate": 9.983692498705361e-05,
|
| 543 |
+
"loss": 0.9937,
|
| 544 |
+
"step": 730
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.27,
|
| 548 |
+
"grad_norm": 0.2215312272310257,
|
| 549 |
+
"learning_rate": 9.983230156261132e-05,
|
| 550 |
+
"loss": 1.0205,
|
| 551 |
+
"step": 740
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.27,
|
| 555 |
+
"grad_norm": 0.26202231645584106,
|
| 556 |
+
"learning_rate": 9.982761362062432e-05,
|
| 557 |
+
"loss": 1.0486,
|
| 558 |
+
"step": 750
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.28,
|
| 562 |
+
"grad_norm": 0.21432209014892578,
|
| 563 |
+
"learning_rate": 9.982286116716208e-05,
|
| 564 |
+
"loss": 1.0679,
|
| 565 |
+
"step": 760
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 0.28,
|
| 569 |
+
"grad_norm": 0.4230276048183441,
|
| 570 |
+
"learning_rate": 9.98180442083776e-05,
|
| 571 |
+
"loss": 1.0051,
|
| 572 |
+
"step": 770
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.28,
|
| 576 |
+
"grad_norm": 0.26559358835220337,
|
| 577 |
+
"learning_rate": 9.981316275050731e-05,
|
| 578 |
+
"loss": 1.0398,
|
| 579 |
+
"step": 780
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.29,
|
| 583 |
+
"grad_norm": 0.2559758722782135,
|
| 584 |
+
"learning_rate": 9.980821679987125e-05,
|
| 585 |
+
"loss": 1.0365,
|
| 586 |
+
"step": 790
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.29,
|
| 590 |
+
"grad_norm": 0.34101855754852295,
|
| 591 |
+
"learning_rate": 9.980320636287285e-05,
|
| 592 |
+
"loss": 1.0169,
|
| 593 |
+
"step": 800
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.29,
|
| 597 |
+
"eval_loss": 1.0172123908996582,
|
| 598 |
+
"eval_runtime": 124.7169,
|
| 599 |
+
"eval_samples_per_second": 62.55,
|
| 600 |
+
"eval_steps_per_second": 3.913,
|
| 601 |
+
"step": 800
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.29,
|
| 605 |
+
"grad_norm": 0.3401408791542053,
|
| 606 |
+
"learning_rate": 9.979813144599915e-05,
|
| 607 |
+
"loss": 1.0165,
|
| 608 |
+
"step": 810
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.3,
|
| 612 |
+
"grad_norm": 0.34302470088005066,
|
| 613 |
+
"learning_rate": 9.979299205582057e-05,
|
| 614 |
+
"loss": 1.0314,
|
| 615 |
+
"step": 820
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.3,
|
| 619 |
+
"grad_norm": 0.2908473610877991,
|
| 620 |
+
"learning_rate": 9.978778819899109e-05,
|
| 621 |
+
"loss": 0.9779,
|
| 622 |
+
"step": 830
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 0.3,
|
| 626 |
+
"grad_norm": 0.229986771941185,
|
| 627 |
+
"learning_rate": 9.978251988224804e-05,
|
| 628 |
+
"loss": 0.9564,
|
| 629 |
+
"step": 840
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 0.31,
|
| 633 |
+
"grad_norm": 0.441243052482605,
|
| 634 |
+
"learning_rate": 9.977718711241233e-05,
|
| 635 |
+
"loss": 1.0275,
|
| 636 |
+
"step": 850
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 0.31,
|
| 640 |
+
"grad_norm": 0.2620699107646942,
|
| 641 |
+
"learning_rate": 9.977178989638822e-05,
|
| 642 |
+
"loss": 1.0293,
|
| 643 |
+
"step": 860
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 0.31,
|
| 647 |
+
"grad_norm": 0.27257561683654785,
|
| 648 |
+
"learning_rate": 9.97663282411635e-05,
|
| 649 |
+
"loss": 1.0508,
|
| 650 |
+
"step": 870
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.32,
|
| 654 |
+
"grad_norm": 0.306587278842926,
|
| 655 |
+
"learning_rate": 9.97608021538093e-05,
|
| 656 |
+
"loss": 0.9949,
|
| 657 |
+
"step": 880
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.32,
|
| 661 |
+
"grad_norm": 0.30046141147613525,
|
| 662 |
+
"learning_rate": 9.97552116414802e-05,
|
| 663 |
+
"loss": 1.0752,
|
| 664 |
+
"step": 890
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 0.33,
|
| 668 |
+
"grad_norm": 0.2749102711677551,
|
| 669 |
+
"learning_rate": 9.974955671141424e-05,
|
| 670 |
+
"loss": 0.9947,
|
| 671 |
+
"step": 900
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 0.33,
|
| 675 |
+
"grad_norm": 0.38608163595199585,
|
| 676 |
+
"learning_rate": 9.974383737093279e-05,
|
| 677 |
+
"loss": 1.0362,
|
| 678 |
+
"step": 910
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 0.33,
|
| 682 |
+
"grad_norm": 0.24529774487018585,
|
| 683 |
+
"learning_rate": 9.973805362744064e-05,
|
| 684 |
+
"loss": 1.0469,
|
| 685 |
+
"step": 920
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 0.34,
|
| 689 |
+
"grad_norm": 0.33143192529678345,
|
| 690 |
+
"learning_rate": 9.973220548842598e-05,
|
| 691 |
+
"loss": 0.9705,
|
| 692 |
+
"step": 930
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.34,
|
| 696 |
+
"grad_norm": 0.3112998306751251,
|
| 697 |
+
"learning_rate": 9.972629296146035e-05,
|
| 698 |
+
"loss": 0.9956,
|
| 699 |
+
"step": 940
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.34,
|
| 703 |
+
"grad_norm": 0.32970279455184937,
|
| 704 |
+
"learning_rate": 9.972031605419864e-05,
|
| 705 |
+
"loss": 1.0232,
|
| 706 |
+
"step": 950
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.35,
|
| 710 |
+
"grad_norm": 0.256101131439209,
|
| 711 |
+
"learning_rate": 9.971427477437914e-05,
|
| 712 |
+
"loss": 1.0471,
|
| 713 |
+
"step": 960
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.35,
|
| 717 |
+
"grad_norm": 0.4258672595024109,
|
| 718 |
+
"learning_rate": 9.970816912982344e-05,
|
| 719 |
+
"loss": 0.9652,
|
| 720 |
+
"step": 970
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.35,
|
| 724 |
+
"grad_norm": 0.3143826425075531,
|
| 725 |
+
"learning_rate": 9.970199912843648e-05,
|
| 726 |
+
"loss": 0.9894,
|
| 727 |
+
"step": 980
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.36,
|
| 731 |
+
"grad_norm": 0.2868054509162903,
|
| 732 |
+
"learning_rate": 9.96957647782065e-05,
|
| 733 |
+
"loss": 1.0437,
|
| 734 |
+
"step": 990
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.36,
|
| 738 |
+
"grad_norm": 0.2594622075557709,
|
| 739 |
+
"learning_rate": 9.968946608720511e-05,
|
| 740 |
+
"loss": 1.02,
|
| 741 |
+
"step": 1000
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.36,
|
| 745 |
+
"eval_loss": 1.0154483318328857,
|
| 746 |
+
"eval_runtime": 124.672,
|
| 747 |
+
"eval_samples_per_second": 62.572,
|
| 748 |
+
"eval_steps_per_second": 3.914,
|
| 749 |
+
"step": 1000
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 0.37,
|
| 753 |
+
"grad_norm": 0.2359086573123932,
|
| 754 |
+
"learning_rate": 9.968310306358715e-05,
|
| 755 |
+
"loss": 1.0676,
|
| 756 |
+
"step": 1010
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 0.37,
|
| 760 |
+
"grad_norm": 0.22080975770950317,
|
| 761 |
+
"learning_rate": 9.967667571559081e-05,
|
| 762 |
+
"loss": 1.027,
|
| 763 |
+
"step": 1020
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 0.37,
|
| 767 |
+
"grad_norm": 0.3211756944656372,
|
| 768 |
+
"learning_rate": 9.967018405153749e-05,
|
| 769 |
+
"loss": 1.0004,
|
| 770 |
+
"step": 1030
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.38,
|
| 774 |
+
"grad_norm": 0.3681553602218628,
|
| 775 |
+
"learning_rate": 9.966362807983196e-05,
|
| 776 |
+
"loss": 1.0395,
|
| 777 |
+
"step": 1040
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.38,
|
| 781 |
+
"grad_norm": 0.3180038332939148,
|
| 782 |
+
"learning_rate": 9.965700780896216e-05,
|
| 783 |
+
"loss": 0.9948,
|
| 784 |
+
"step": 1050
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 0.38,
|
| 788 |
+
"grad_norm": 0.25071969628334045,
|
| 789 |
+
"learning_rate": 9.965032324749932e-05,
|
| 790 |
+
"loss": 1.0281,
|
| 791 |
+
"step": 1060
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 0.39,
|
| 795 |
+
"grad_norm": 0.2274983674287796,
|
| 796 |
+
"learning_rate": 9.964357440409789e-05,
|
| 797 |
+
"loss": 1.0094,
|
| 798 |
+
"step": 1070
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 0.39,
|
| 802 |
+
"grad_norm": 0.24825724959373474,
|
| 803 |
+
"learning_rate": 9.963676128749553e-05,
|
| 804 |
+
"loss": 1.0272,
|
| 805 |
+
"step": 1080
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 0.39,
|
| 809 |
+
"grad_norm": 0.3256381154060364,
|
| 810 |
+
"learning_rate": 9.96298839065132e-05,
|
| 811 |
+
"loss": 1.0191,
|
| 812 |
+
"step": 1090
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.4,
|
| 816 |
+
"grad_norm": 0.31695234775543213,
|
| 817 |
+
"learning_rate": 9.962294227005493e-05,
|
| 818 |
+
"loss": 1.08,
|
| 819 |
+
"step": 1100
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.4,
|
| 823 |
+
"grad_norm": 0.288083553314209,
|
| 824 |
+
"learning_rate": 9.961593638710804e-05,
|
| 825 |
+
"loss": 0.9954,
|
| 826 |
+
"step": 1110
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.41,
|
| 830 |
+
"grad_norm": 0.29730525612831116,
|
| 831 |
+
"learning_rate": 9.960886626674302e-05,
|
| 832 |
+
"loss": 1.071,
|
| 833 |
+
"step": 1120
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.41,
|
| 837 |
+
"grad_norm": 0.2090187519788742,
|
| 838 |
+
"learning_rate": 9.960173191811348e-05,
|
| 839 |
+
"loss": 0.9725,
|
| 840 |
+
"step": 1130
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 0.41,
|
| 844 |
+
"grad_norm": 0.2811983525753021,
|
| 845 |
+
"learning_rate": 9.959453335045622e-05,
|
| 846 |
+
"loss": 1.0071,
|
| 847 |
+
"step": 1140
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 0.42,
|
| 851 |
+
"grad_norm": 0.27806761860847473,
|
| 852 |
+
"learning_rate": 9.958727057309115e-05,
|
| 853 |
+
"loss": 1.0108,
|
| 854 |
+
"step": 1150
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.42,
|
| 858 |
+
"grad_norm": 0.2864569127559662,
|
| 859 |
+
"learning_rate": 9.957994359542138e-05,
|
| 860 |
+
"loss": 1.0495,
|
| 861 |
+
"step": 1160
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.42,
|
| 865 |
+
"grad_norm": 0.3440109193325043,
|
| 866 |
+
"learning_rate": 9.957255242693308e-05,
|
| 867 |
+
"loss": 1.0015,
|
| 868 |
+
"step": 1170
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 0.43,
|
| 872 |
+
"grad_norm": 0.2824917435646057,
|
| 873 |
+
"learning_rate": 9.956509707719555e-05,
|
| 874 |
+
"loss": 1.0559,
|
| 875 |
+
"step": 1180
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 0.43,
|
| 879 |
+
"grad_norm": 0.3080492317676544,
|
| 880 |
+
"learning_rate": 9.955757755586119e-05,
|
| 881 |
+
"loss": 1.0134,
|
| 882 |
+
"step": 1190
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.43,
|
| 886 |
+
"grad_norm": 0.2890901565551758,
|
| 887 |
+
"learning_rate": 9.954999387266546e-05,
|
| 888 |
+
"loss": 0.9492,
|
| 889 |
+
"step": 1200
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 0.43,
|
| 893 |
+
"eval_loss": 1.0133627653121948,
|
| 894 |
+
"eval_runtime": 124.7104,
|
| 895 |
+
"eval_samples_per_second": 62.553,
|
| 896 |
+
"eval_steps_per_second": 3.913,
|
| 897 |
+
"step": 1200
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.44,
|
| 901 |
+
"grad_norm": 0.33987322449684143,
|
| 902 |
+
"learning_rate": 9.95423460374269e-05,
|
| 903 |
+
"loss": 0.9629,
|
| 904 |
+
"step": 1210
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 0.44,
|
| 908 |
+
"grad_norm": 0.29403063654899597,
|
| 909 |
+
"learning_rate": 9.953463406004713e-05,
|
| 910 |
+
"loss": 1.0384,
|
| 911 |
+
"step": 1220
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 0.45,
|
| 915 |
+
"grad_norm": 0.20130111277103424,
|
| 916 |
+
"learning_rate": 9.952685795051077e-05,
|
| 917 |
+
"loss": 1.0235,
|
| 918 |
+
"step": 1230
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 0.45,
|
| 922 |
+
"grad_norm": 0.1973690539598465,
|
| 923 |
+
"learning_rate": 9.951901771888552e-05,
|
| 924 |
+
"loss": 1.0395,
|
| 925 |
+
"step": 1240
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 0.45,
|
| 929 |
+
"grad_norm": 0.24519580602645874,
|
| 930 |
+
"learning_rate": 9.951111337532205e-05,
|
| 931 |
+
"loss": 1.0914,
|
| 932 |
+
"step": 1250
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 0.46,
|
| 936 |
+
"grad_norm": 0.2706618309020996,
|
| 937 |
+
"learning_rate": 9.950314493005408e-05,
|
| 938 |
+
"loss": 1.0714,
|
| 939 |
+
"step": 1260
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.46,
|
| 943 |
+
"grad_norm": 0.23367558419704437,
|
| 944 |
+
"learning_rate": 9.949511239339831e-05,
|
| 945 |
+
"loss": 1.0224,
|
| 946 |
+
"step": 1270
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.46,
|
| 950 |
+
"grad_norm": 0.30005407333374023,
|
| 951 |
+
"learning_rate": 9.948701577575439e-05,
|
| 952 |
+
"loss": 1.0152,
|
| 953 |
+
"step": 1280
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.47,
|
| 957 |
+
"grad_norm": 0.3130083382129669,
|
| 958 |
+
"learning_rate": 9.947885508760496e-05,
|
| 959 |
+
"loss": 0.8988,
|
| 960 |
+
"step": 1290
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.47,
|
| 964 |
+
"grad_norm": 0.23657679557800293,
|
| 965 |
+
"learning_rate": 9.94706303395156e-05,
|
| 966 |
+
"loss": 1.0242,
|
| 967 |
+
"step": 1300
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 0.47,
|
| 971 |
+
"grad_norm": 0.40966659784317017,
|
| 972 |
+
"learning_rate": 9.946234154213487e-05,
|
| 973 |
+
"loss": 1.0145,
|
| 974 |
+
"step": 1310
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 0.48,
|
| 978 |
+
"grad_norm": 0.35292962193489075,
|
| 979 |
+
"learning_rate": 9.94539887061942e-05,
|
| 980 |
+
"loss": 1.0197,
|
| 981 |
+
"step": 1320
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.48,
|
| 985 |
+
"grad_norm": 0.38793638348579407,
|
| 986 |
+
"learning_rate": 9.944557184250794e-05,
|
| 987 |
+
"loss": 1.0273,
|
| 988 |
+
"step": 1330
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 0.48,
|
| 992 |
+
"grad_norm": 0.27373677492141724,
|
| 993 |
+
"learning_rate": 9.943709096197335e-05,
|
| 994 |
+
"loss": 0.9561,
|
| 995 |
+
"step": 1340
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 0.49,
|
| 999 |
+
"grad_norm": 0.24536257982254028,
|
| 1000 |
+
"learning_rate": 9.942854607557057e-05,
|
| 1001 |
+
"loss": 0.9678,
|
| 1002 |
+
"step": 1350
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 0.49,
|
| 1006 |
+
"grad_norm": 0.4609609842300415,
|
| 1007 |
+
"learning_rate": 9.941993719436262e-05,
|
| 1008 |
+
"loss": 1.0429,
|
| 1009 |
+
"step": 1360
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.5,
|
| 1013 |
+
"grad_norm": 0.27118805050849915,
|
| 1014 |
+
"learning_rate": 9.941126432949535e-05,
|
| 1015 |
+
"loss": 1.0506,
|
| 1016 |
+
"step": 1370
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 0.5,
|
| 1020 |
+
"grad_norm": 0.27538400888442993,
|
| 1021 |
+
"learning_rate": 9.940252749219746e-05,
|
| 1022 |
+
"loss": 1.0326,
|
| 1023 |
+
"step": 1380
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.5,
|
| 1027 |
+
"grad_norm": 0.2451954036951065,
|
| 1028 |
+
"learning_rate": 9.939372669378048e-05,
|
| 1029 |
+
"loss": 1.0413,
|
| 1030 |
+
"step": 1390
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 0.51,
|
| 1034 |
+
"grad_norm": 0.2622232437133789,
|
| 1035 |
+
"learning_rate": 9.938486194563875e-05,
|
| 1036 |
+
"loss": 1.0051,
|
| 1037 |
+
"step": 1400
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 0.51,
|
| 1041 |
+
"eval_loss": 1.011703372001648,
|
| 1042 |
+
"eval_runtime": 124.6726,
|
| 1043 |
+
"eval_samples_per_second": 62.572,
|
| 1044 |
+
"eval_steps_per_second": 3.914,
|
| 1045 |
+
"step": 1400
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.51,
|
| 1049 |
+
"grad_norm": 0.2616746425628662,
|
| 1050 |
+
"learning_rate": 9.937593325924937e-05,
|
| 1051 |
+
"loss": 1.0277,
|
| 1052 |
+
"step": 1410
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.51,
|
| 1056 |
+
"grad_norm": 0.2952045202255249,
|
| 1057 |
+
"learning_rate": 9.936694064617227e-05,
|
| 1058 |
+
"loss": 0.9802,
|
| 1059 |
+
"step": 1420
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.52,
|
| 1063 |
+
"grad_norm": 0.2611790895462036,
|
| 1064 |
+
"learning_rate": 9.935788411805011e-05,
|
| 1065 |
+
"loss": 0.9811,
|
| 1066 |
+
"step": 1430
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.52,
|
| 1070 |
+
"grad_norm": 0.3291374742984772,
|
| 1071 |
+
"learning_rate": 9.934876368660836e-05,
|
| 1072 |
+
"loss": 0.9972,
|
| 1073 |
+
"step": 1440
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.52,
|
| 1077 |
+
"grad_norm": 0.32888704538345337,
|
| 1078 |
+
"learning_rate": 9.933957936365515e-05,
|
| 1079 |
+
"loss": 1.1006,
|
| 1080 |
+
"step": 1450
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.53,
|
| 1084 |
+
"grad_norm": 0.20011785626411438,
|
| 1085 |
+
"learning_rate": 9.933033116108134e-05,
|
| 1086 |
+
"loss": 1.0139,
|
| 1087 |
+
"step": 1460
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.53,
|
| 1091 |
+
"grad_norm": 0.3157961666584015,
|
| 1092 |
+
"learning_rate": 9.932101909086056e-05,
|
| 1093 |
+
"loss": 0.993,
|
| 1094 |
+
"step": 1470
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.54,
|
| 1098 |
+
"grad_norm": 0.22981207072734833,
|
| 1099 |
+
"learning_rate": 9.931164316504904e-05,
|
| 1100 |
+
"loss": 1.0539,
|
| 1101 |
+
"step": 1480
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.54,
|
| 1105 |
+
"grad_norm": 0.23787029087543488,
|
| 1106 |
+
"learning_rate": 9.930220339578576e-05,
|
| 1107 |
+
"loss": 0.9599,
|
| 1108 |
+
"step": 1490
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.54,
|
| 1112 |
+
"grad_norm": 0.2633046507835388,
|
| 1113 |
+
"learning_rate": 9.929269979529232e-05,
|
| 1114 |
+
"loss": 0.9813,
|
| 1115 |
+
"step": 1500
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.55,
|
| 1119 |
+
"grad_norm": 0.2666633725166321,
|
| 1120 |
+
"learning_rate": 9.928313237587296e-05,
|
| 1121 |
+
"loss": 0.9637,
|
| 1122 |
+
"step": 1510
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.55,
|
| 1126 |
+
"grad_norm": 0.26092538237571716,
|
| 1127 |
+
"learning_rate": 9.927350114991456e-05,
|
| 1128 |
+
"loss": 1.0375,
|
| 1129 |
+
"step": 1520
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.55,
|
| 1133 |
+
"grad_norm": 0.2837240397930145,
|
| 1134 |
+
"learning_rate": 9.92638061298866e-05,
|
| 1135 |
+
"loss": 1.0053,
|
| 1136 |
+
"step": 1530
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.56,
|
| 1140 |
+
"grad_norm": 0.2586491107940674,
|
| 1141 |
+
"learning_rate": 9.925404732834117e-05,
|
| 1142 |
+
"loss": 1.0631,
|
| 1143 |
+
"step": 1540
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.56,
|
| 1147 |
+
"grad_norm": 0.43321874737739563,
|
| 1148 |
+
"learning_rate": 9.924422475791288e-05,
|
| 1149 |
+
"loss": 1.0134,
|
| 1150 |
+
"step": 1550
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.56,
|
| 1154 |
+
"grad_norm": 0.19062629342079163,
|
| 1155 |
+
"learning_rate": 9.923433843131901e-05,
|
| 1156 |
+
"loss": 0.9989,
|
| 1157 |
+
"step": 1560
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.57,
|
| 1161 |
+
"grad_norm": 0.34545308351516724,
|
| 1162 |
+
"learning_rate": 9.922438836135928e-05,
|
| 1163 |
+
"loss": 1.0896,
|
| 1164 |
+
"step": 1570
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.57,
|
| 1168 |
+
"grad_norm": 0.2846600115299225,
|
| 1169 |
+
"learning_rate": 9.921437456091596e-05,
|
| 1170 |
+
"loss": 0.9954,
|
| 1171 |
+
"step": 1580
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.58,
|
| 1175 |
+
"grad_norm": 0.25403323769569397,
|
| 1176 |
+
"learning_rate": 9.920429704295391e-05,
|
| 1177 |
+
"loss": 0.9937,
|
| 1178 |
+
"step": 1590
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.58,
|
| 1182 |
+
"grad_norm": 0.23549498617649078,
|
| 1183 |
+
"learning_rate": 9.919415582052036e-05,
|
| 1184 |
+
"loss": 1.0469,
|
| 1185 |
+
"step": 1600
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.58,
|
| 1189 |
+
"eval_loss": 1.0105613470077515,
|
| 1190 |
+
"eval_runtime": 124.7139,
|
| 1191 |
+
"eval_samples_per_second": 62.551,
|
| 1192 |
+
"eval_steps_per_second": 3.913,
|
| 1193 |
+
"step": 1600
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.58,
|
| 1197 |
+
"grad_norm": 0.21466514468193054,
|
| 1198 |
+
"learning_rate": 9.918395090674514e-05,
|
| 1199 |
+
"loss": 1.0408,
|
| 1200 |
+
"step": 1610
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.59,
|
| 1204 |
+
"grad_norm": 0.21247586607933044,
|
| 1205 |
+
"learning_rate": 9.917368231484045e-05,
|
| 1206 |
+
"loss": 0.9893,
|
| 1207 |
+
"step": 1620
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.59,
|
| 1211 |
+
"grad_norm": 0.26590731739997864,
|
| 1212 |
+
"learning_rate": 9.916335005810095e-05,
|
| 1213 |
+
"loss": 1.0563,
|
| 1214 |
+
"step": 1630
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.59,
|
| 1218 |
+
"grad_norm": 0.2346472591161728,
|
| 1219 |
+
"learning_rate": 9.91529541499038e-05,
|
| 1220 |
+
"loss": 1.0061,
|
| 1221 |
+
"step": 1640
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.6,
|
| 1225 |
+
"grad_norm": 0.27766481041908264,
|
| 1226 |
+
"learning_rate": 9.914249460370846e-05,
|
| 1227 |
+
"loss": 0.9639,
|
| 1228 |
+
"step": 1650
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.6,
|
| 1232 |
+
"grad_norm": 0.24883978068828583,
|
| 1233 |
+
"learning_rate": 9.913197143305684e-05,
|
| 1234 |
+
"loss": 1.0289,
|
| 1235 |
+
"step": 1660
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.6,
|
| 1239 |
+
"grad_norm": 0.2379382699728012,
|
| 1240 |
+
"learning_rate": 9.912138465157325e-05,
|
| 1241 |
+
"loss": 1.0154,
|
| 1242 |
+
"step": 1670
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.61,
|
| 1246 |
+
"grad_norm": 0.17160119116306305,
|
| 1247 |
+
"learning_rate": 9.91107342729643e-05,
|
| 1248 |
+
"loss": 1.0002,
|
| 1249 |
+
"step": 1680
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.61,
|
| 1253 |
+
"grad_norm": 0.2804344892501831,
|
| 1254 |
+
"learning_rate": 9.910002031101895e-05,
|
| 1255 |
+
"loss": 0.9887,
|
| 1256 |
+
"step": 1690
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.62,
|
| 1260 |
+
"grad_norm": 0.2296508252620697,
|
| 1261 |
+
"learning_rate": 9.908924277960854e-05,
|
| 1262 |
+
"loss": 1.0703,
|
| 1263 |
+
"step": 1700
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.62,
|
| 1267 |
+
"grad_norm": 0.22265523672103882,
|
| 1268 |
+
"learning_rate": 9.907840169268662e-05,
|
| 1269 |
+
"loss": 0.9495,
|
| 1270 |
+
"step": 1710
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.62,
|
| 1274 |
+
"grad_norm": 0.3383825123310089,
|
| 1275 |
+
"learning_rate": 9.90674970642891e-05,
|
| 1276 |
+
"loss": 0.9878,
|
| 1277 |
+
"step": 1720
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.63,
|
| 1281 |
+
"grad_norm": 0.2603285312652588,
|
| 1282 |
+
"learning_rate": 9.905652890853411e-05,
|
| 1283 |
+
"loss": 1.0351,
|
| 1284 |
+
"step": 1730
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.63,
|
| 1288 |
+
"grad_norm": 0.27001509070396423,
|
| 1289 |
+
"learning_rate": 9.904549723962206e-05,
|
| 1290 |
+
"loss": 1.0528,
|
| 1291 |
+
"step": 1740
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.63,
|
| 1295 |
+
"grad_norm": 0.34035804867744446,
|
| 1296 |
+
"learning_rate": 9.903440207183558e-05,
|
| 1297 |
+
"loss": 1.0159,
|
| 1298 |
+
"step": 1750
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.64,
|
| 1302 |
+
"grad_norm": 0.3518404960632324,
|
| 1303 |
+
"learning_rate": 9.90232434195395e-05,
|
| 1304 |
+
"loss": 0.9879,
|
| 1305 |
+
"step": 1760
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.64,
|
| 1309 |
+
"grad_norm": 0.24958577752113342,
|
| 1310 |
+
"learning_rate": 9.901202129718086e-05,
|
| 1311 |
+
"loss": 1.0221,
|
| 1312 |
+
"step": 1770
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.64,
|
| 1316 |
+
"grad_norm": 0.23898568749427795,
|
| 1317 |
+
"learning_rate": 9.900073571928886e-05,
|
| 1318 |
+
"loss": 1.037,
|
| 1319 |
+
"step": 1780
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.65,
|
| 1323 |
+
"grad_norm": 0.22275009751319885,
|
| 1324 |
+
"learning_rate": 9.898938670047486e-05,
|
| 1325 |
+
"loss": 1.0008,
|
| 1326 |
+
"step": 1790
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.65,
|
| 1330 |
+
"grad_norm": 0.2770971655845642,
|
| 1331 |
+
"learning_rate": 9.897797425543236e-05,
|
| 1332 |
+
"loss": 0.9994,
|
| 1333 |
+
"step": 1800
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.65,
|
| 1337 |
+
"eval_loss": 1.0094062089920044,
|
| 1338 |
+
"eval_runtime": 124.6598,
|
| 1339 |
+
"eval_samples_per_second": 62.578,
|
| 1340 |
+
"eval_steps_per_second": 3.915,
|
| 1341 |
+
"step": 1800
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 0.66,
|
| 1345 |
+
"grad_norm": 0.2470710575580597,
|
| 1346 |
+
"learning_rate": 9.896649839893699e-05,
|
| 1347 |
+
"loss": 1.0093,
|
| 1348 |
+
"step": 1810
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 0.66,
|
| 1352 |
+
"grad_norm": 0.31282275915145874,
|
| 1353 |
+
"learning_rate": 9.895495914584643e-05,
|
| 1354 |
+
"loss": 1.0124,
|
| 1355 |
+
"step": 1820
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 0.66,
|
| 1359 |
+
"grad_norm": 0.2757389545440674,
|
| 1360 |
+
"learning_rate": 9.894335651110051e-05,
|
| 1361 |
+
"loss": 1.0197,
|
| 1362 |
+
"step": 1830
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 0.67,
|
| 1366 |
+
"grad_norm": 0.3123573362827301,
|
| 1367 |
+
"learning_rate": 9.893169050972106e-05,
|
| 1368 |
+
"loss": 0.9469,
|
| 1369 |
+
"step": 1840
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 0.67,
|
| 1373 |
+
"grad_norm": 0.4073740839958191,
|
| 1374 |
+
"learning_rate": 9.8919961156812e-05,
|
| 1375 |
+
"loss": 1.0153,
|
| 1376 |
+
"step": 1850
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 0.67,
|
| 1380 |
+
"grad_norm": 0.24388962984085083,
|
| 1381 |
+
"learning_rate": 9.89081684675592e-05,
|
| 1382 |
+
"loss": 1.0124,
|
| 1383 |
+
"step": 1860
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 0.68,
|
| 1387 |
+
"grad_norm": 0.27508777379989624,
|
| 1388 |
+
"learning_rate": 9.88963124572306e-05,
|
| 1389 |
+
"loss": 0.96,
|
| 1390 |
+
"step": 1870
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 0.68,
|
| 1394 |
+
"grad_norm": 0.2843553125858307,
|
| 1395 |
+
"learning_rate": 9.88843931411761e-05,
|
| 1396 |
+
"loss": 1.0448,
|
| 1397 |
+
"step": 1880
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 0.68,
|
| 1401 |
+
"grad_norm": 0.25155389308929443,
|
| 1402 |
+
"learning_rate": 9.887241053482757e-05,
|
| 1403 |
+
"loss": 1.0362,
|
| 1404 |
+
"step": 1890
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 0.69,
|
| 1408 |
+
"grad_norm": 0.21977895498275757,
|
| 1409 |
+
"learning_rate": 9.886036465369877e-05,
|
| 1410 |
+
"loss": 1.0658,
|
| 1411 |
+
"step": 1900
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 0.69,
|
| 1415 |
+
"grad_norm": 0.22326160967350006,
|
| 1416 |
+
"learning_rate": 9.884825551338546e-05,
|
| 1417 |
+
"loss": 1.0068,
|
| 1418 |
+
"step": 1910
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 0.69,
|
| 1422 |
+
"grad_norm": 0.3339684307575226,
|
| 1423 |
+
"learning_rate": 9.883608312956524e-05,
|
| 1424 |
+
"loss": 1.0147,
|
| 1425 |
+
"step": 1920
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 0.7,
|
| 1429 |
+
"grad_norm": 0.26512840390205383,
|
| 1430 |
+
"learning_rate": 9.882384751799762e-05,
|
| 1431 |
+
"loss": 0.9421,
|
| 1432 |
+
"step": 1930
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"epoch": 0.7,
|
| 1436 |
+
"grad_norm": 0.313123881816864,
|
| 1437 |
+
"learning_rate": 9.881154869452395e-05,
|
| 1438 |
+
"loss": 1.0032,
|
| 1439 |
+
"step": 1940
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 0.71,
|
| 1443 |
+
"grad_norm": 0.3562926948070526,
|
| 1444 |
+
"learning_rate": 9.879918667506748e-05,
|
| 1445 |
+
"loss": 1.0491,
|
| 1446 |
+
"step": 1950
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 0.71,
|
| 1450 |
+
"grad_norm": 0.373032808303833,
|
| 1451 |
+
"learning_rate": 9.87867614756332e-05,
|
| 1452 |
+
"loss": 0.9823,
|
| 1453 |
+
"step": 1960
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 0.71,
|
| 1457 |
+
"grad_norm": 0.2701728641986847,
|
| 1458 |
+
"learning_rate": 9.87742731123079e-05,
|
| 1459 |
+
"loss": 1.0326,
|
| 1460 |
+
"step": 1970
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 0.72,
|
| 1464 |
+
"grad_norm": 0.4167492687702179,
|
| 1465 |
+
"learning_rate": 9.876172160126024e-05,
|
| 1466 |
+
"loss": 1.0256,
|
| 1467 |
+
"step": 1980
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 0.72,
|
| 1471 |
+
"grad_norm": 0.2636062800884247,
|
| 1472 |
+
"learning_rate": 9.874910695874053e-05,
|
| 1473 |
+
"loss": 1.0301,
|
| 1474 |
+
"step": 1990
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 0.72,
|
| 1478 |
+
"grad_norm": 0.27048760652542114,
|
| 1479 |
+
"learning_rate": 9.873642920108091e-05,
|
| 1480 |
+
"loss": 1.0141,
|
| 1481 |
+
"step": 2000
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 0.72,
|
| 1485 |
+
"eval_loss": 1.0082145929336548,
|
| 1486 |
+
"eval_runtime": 124.7209,
|
| 1487 |
+
"eval_samples_per_second": 62.548,
|
| 1488 |
+
"eval_steps_per_second": 3.913,
|
| 1489 |
+
"step": 2000
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"epoch": 0.73,
|
| 1493 |
+
"grad_norm": 0.26596397161483765,
|
| 1494 |
+
"learning_rate": 9.872368834469514e-05,
|
| 1495 |
+
"loss": 0.9554,
|
| 1496 |
+
"step": 2010
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 0.73,
|
| 1500 |
+
"grad_norm": 0.3881726861000061,
|
| 1501 |
+
"learning_rate": 9.871088440607874e-05,
|
| 1502 |
+
"loss": 1.0374,
|
| 1503 |
+
"step": 2020
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 0.73,
|
| 1507 |
+
"grad_norm": 0.345869243144989,
|
| 1508 |
+
"learning_rate": 9.869801740180889e-05,
|
| 1509 |
+
"loss": 1.01,
|
| 1510 |
+
"step": 2030
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"epoch": 0.74,
|
| 1514 |
+
"grad_norm": 0.3740908205509186,
|
| 1515 |
+
"learning_rate": 9.86850873485444e-05,
|
| 1516 |
+
"loss": 1.0244,
|
| 1517 |
+
"step": 2040
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 0.74,
|
| 1521 |
+
"grad_norm": 0.3265666663646698,
|
| 1522 |
+
"learning_rate": 9.867209426302572e-05,
|
| 1523 |
+
"loss": 0.9303,
|
| 1524 |
+
"step": 2050
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 0.75,
|
| 1528 |
+
"grad_norm": 0.381783664226532,
|
| 1529 |
+
"learning_rate": 9.865903816207493e-05,
|
| 1530 |
+
"loss": 1.0851,
|
| 1531 |
+
"step": 2060
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 0.75,
|
| 1535 |
+
"grad_norm": 0.30846527218818665,
|
| 1536 |
+
"learning_rate": 9.864591906259568e-05,
|
| 1537 |
+
"loss": 1.0042,
|
| 1538 |
+
"step": 2070
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 0.75,
|
| 1542 |
+
"grad_norm": 0.36899617314338684,
|
| 1543 |
+
"learning_rate": 9.863273698157315e-05,
|
| 1544 |
+
"loss": 0.9866,
|
| 1545 |
+
"step": 2080
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 0.76,
|
| 1549 |
+
"grad_norm": 0.25415265560150146,
|
| 1550 |
+
"learning_rate": 9.861949193607411e-05,
|
| 1551 |
+
"loss": 1.056,
|
| 1552 |
+
"step": 2090
|
| 1553 |
+
},
|
| 1554 |
+
{
|
| 1555 |
+
"epoch": 0.76,
|
| 1556 |
+
"grad_norm": 0.3369081914424896,
|
| 1557 |
+
"learning_rate": 9.860618394324682e-05,
|
| 1558 |
+
"loss": 0.9988,
|
| 1559 |
+
"step": 2100
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 0.76,
|
| 1563 |
+
"grad_norm": 0.19644911587238312,
|
| 1564 |
+
"learning_rate": 9.859281302032106e-05,
|
| 1565 |
+
"loss": 0.9562,
|
| 1566 |
+
"step": 2110
|
| 1567 |
+
},
|
| 1568 |
+
{
|
| 1569 |
+
"epoch": 0.77,
|
| 1570 |
+
"grad_norm": 0.3449130356311798,
|
| 1571 |
+
"learning_rate": 9.857937918460808e-05,
|
| 1572 |
+
"loss": 1.0325,
|
| 1573 |
+
"step": 2120
|
| 1574 |
+
},
|
| 1575 |
+
{
|
| 1576 |
+
"epoch": 0.77,
|
| 1577 |
+
"grad_norm": 0.2639143764972687,
|
| 1578 |
+
"learning_rate": 9.856588245350056e-05,
|
| 1579 |
+
"loss": 1.0458,
|
| 1580 |
+
"step": 2130
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 0.77,
|
| 1584 |
+
"grad_norm": 0.2752164602279663,
|
| 1585 |
+
"learning_rate": 9.855232284447262e-05,
|
| 1586 |
+
"loss": 1.089,
|
| 1587 |
+
"step": 2140
|
| 1588 |
+
},
|
| 1589 |
+
{
|
| 1590 |
+
"epoch": 0.78,
|
| 1591 |
+
"grad_norm": 0.31700417399406433,
|
| 1592 |
+
"learning_rate": 9.853870037507983e-05,
|
| 1593 |
+
"loss": 1.0398,
|
| 1594 |
+
"step": 2150
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"epoch": 0.78,
|
| 1598 |
+
"grad_norm": 0.24685466289520264,
|
| 1599 |
+
"learning_rate": 9.852501506295907e-05,
|
| 1600 |
+
"loss": 1.0038,
|
| 1601 |
+
"step": 2160
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"epoch": 0.79,
|
| 1605 |
+
"grad_norm": 0.28860118985176086,
|
| 1606 |
+
"learning_rate": 9.851126692582864e-05,
|
| 1607 |
+
"loss": 1.0343,
|
| 1608 |
+
"step": 2170
|
| 1609 |
+
},
|
| 1610 |
+
{
|
| 1611 |
+
"epoch": 0.79,
|
| 1612 |
+
"grad_norm": 0.2774854898452759,
|
| 1613 |
+
"learning_rate": 9.849745598148817e-05,
|
| 1614 |
+
"loss": 0.9986,
|
| 1615 |
+
"step": 2180
|
| 1616 |
+
},
|
| 1617 |
+
{
|
| 1618 |
+
"epoch": 0.79,
|
| 1619 |
+
"grad_norm": 0.28867611289024353,
|
| 1620 |
+
"learning_rate": 9.848358224781857e-05,
|
| 1621 |
+
"loss": 1.035,
|
| 1622 |
+
"step": 2190
|
| 1623 |
+
},
|
| 1624 |
+
{
|
| 1625 |
+
"epoch": 0.8,
|
| 1626 |
+
"grad_norm": 0.2703929841518402,
|
| 1627 |
+
"learning_rate": 9.84696457427821e-05,
|
| 1628 |
+
"loss": 1.0891,
|
| 1629 |
+
"step": 2200
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 0.8,
|
| 1633 |
+
"eval_loss": 1.0072919130325317,
|
| 1634 |
+
"eval_runtime": 125.0779,
|
| 1635 |
+
"eval_samples_per_second": 62.369,
|
| 1636 |
+
"eval_steps_per_second": 3.902,
|
| 1637 |
+
"step": 2200
|
| 1638 |
+
},
|
| 1639 |
+
{
|
| 1640 |
+
"epoch": 0.8,
|
| 1641 |
+
"grad_norm": 0.3247489035129547,
|
| 1642 |
+
"learning_rate": 9.845564648442222e-05,
|
| 1643 |
+
"loss": 1.0259,
|
| 1644 |
+
"step": 2210
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 0.8,
|
| 1648 |
+
"grad_norm": 0.2535197138786316,
|
| 1649 |
+
"learning_rate": 9.844158449086371e-05,
|
| 1650 |
+
"loss": 1.0457,
|
| 1651 |
+
"step": 2220
|
| 1652 |
+
},
|
| 1653 |
+
{
|
| 1654 |
+
"epoch": 0.81,
|
| 1655 |
+
"grad_norm": 0.26780492067337036,
|
| 1656 |
+
"learning_rate": 9.842745978031253e-05,
|
| 1657 |
+
"loss": 0.9869,
|
| 1658 |
+
"step": 2230
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 0.81,
|
| 1662 |
+
"grad_norm": 0.29711589217185974,
|
| 1663 |
+
"learning_rate": 9.841327237105585e-05,
|
| 1664 |
+
"loss": 1.0158,
|
| 1665 |
+
"step": 2240
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 0.81,
|
| 1669 |
+
"grad_norm": 0.239434614777565,
|
| 1670 |
+
"learning_rate": 9.8399022281462e-05,
|
| 1671 |
+
"loss": 0.997,
|
| 1672 |
+
"step": 2250
|
| 1673 |
+
},
|
| 1674 |
+
{
|
| 1675 |
+
"epoch": 0.82,
|
| 1676 |
+
"grad_norm": 0.2368830293416977,
|
| 1677 |
+
"learning_rate": 9.838470952998049e-05,
|
| 1678 |
+
"loss": 1.0148,
|
| 1679 |
+
"step": 2260
|
| 1680 |
+
},
|
| 1681 |
+
{
|
| 1682 |
+
"epoch": 0.82,
|
| 1683 |
+
"grad_norm": 0.2554934322834015,
|
| 1684 |
+
"learning_rate": 9.837033413514191e-05,
|
| 1685 |
+
"loss": 0.9787,
|
| 1686 |
+
"step": 2270
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 0.83,
|
| 1690 |
+
"grad_norm": 0.2310570627450943,
|
| 1691 |
+
"learning_rate": 9.835589611555805e-05,
|
| 1692 |
+
"loss": 0.9656,
|
| 1693 |
+
"step": 2280
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 0.83,
|
| 1697 |
+
"grad_norm": 0.22654668986797333,
|
| 1698 |
+
"learning_rate": 9.834139548992165e-05,
|
| 1699 |
+
"loss": 0.9837,
|
| 1700 |
+
"step": 2290
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 0.83,
|
| 1704 |
+
"grad_norm": 0.25957950949668884,
|
| 1705 |
+
"learning_rate": 9.832683227700661e-05,
|
| 1706 |
+
"loss": 1.0513,
|
| 1707 |
+
"step": 2300
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 0.84,
|
| 1711 |
+
"grad_norm": 0.20669637620449066,
|
| 1712 |
+
"learning_rate": 9.831220649566782e-05,
|
| 1713 |
+
"loss": 0.9649,
|
| 1714 |
+
"step": 2310
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 0.84,
|
| 1718 |
+
"grad_norm": 0.24330663681030273,
|
| 1719 |
+
"learning_rate": 9.829751816484116e-05,
|
| 1720 |
+
"loss": 1.0208,
|
| 1721 |
+
"step": 2320
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 0.84,
|
| 1725 |
+
"grad_norm": 0.28211724758148193,
|
| 1726 |
+
"learning_rate": 9.828276730354353e-05,
|
| 1727 |
+
"loss": 0.9512,
|
| 1728 |
+
"step": 2330
|
| 1729 |
+
},
|
| 1730 |
+
{
|
| 1731 |
+
"epoch": 0.85,
|
| 1732 |
+
"grad_norm": 0.23784276843070984,
|
| 1733 |
+
"learning_rate": 9.826795393087278e-05,
|
| 1734 |
+
"loss": 0.976,
|
| 1735 |
+
"step": 2340
|
| 1736 |
+
},
|
| 1737 |
+
{
|
| 1738 |
+
"epoch": 0.85,
|
| 1739 |
+
"grad_norm": 0.2881389260292053,
|
| 1740 |
+
"learning_rate": 9.825307806600765e-05,
|
| 1741 |
+
"loss": 1.0036,
|
| 1742 |
+
"step": 2350
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 0.85,
|
| 1746 |
+
"grad_norm": 0.27906882762908936,
|
| 1747 |
+
"learning_rate": 9.823813972820786e-05,
|
| 1748 |
+
"loss": 1.0555,
|
| 1749 |
+
"step": 2360
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 0.86,
|
| 1753 |
+
"grad_norm": 0.25142115354537964,
|
| 1754 |
+
"learning_rate": 9.822313893681397e-05,
|
| 1755 |
+
"loss": 1.0483,
|
| 1756 |
+
"step": 2370
|
| 1757 |
+
},
|
| 1758 |
+
{
|
| 1759 |
+
"epoch": 0.86,
|
| 1760 |
+
"grad_norm": 0.244681715965271,
|
| 1761 |
+
"learning_rate": 9.820807571124738e-05,
|
| 1762 |
+
"loss": 1.0102,
|
| 1763 |
+
"step": 2380
|
| 1764 |
+
},
|
| 1765 |
+
{
|
| 1766 |
+
"epoch": 0.87,
|
| 1767 |
+
"grad_norm": 0.3696367144584656,
|
| 1768 |
+
"learning_rate": 9.819295007101035e-05,
|
| 1769 |
+
"loss": 1.0626,
|
| 1770 |
+
"step": 2390
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"epoch": 0.87,
|
| 1774 |
+
"grad_norm": 0.26112619042396545,
|
| 1775 |
+
"learning_rate": 9.817776203568596e-05,
|
| 1776 |
+
"loss": 1.0141,
|
| 1777 |
+
"step": 2400
|
| 1778 |
+
},
|
| 1779 |
+
{
|
| 1780 |
+
"epoch": 0.87,
|
| 1781 |
+
"eval_loss": 1.0063296556472778,
|
| 1782 |
+
"eval_runtime": 125.7335,
|
| 1783 |
+
"eval_samples_per_second": 62.044,
|
| 1784 |
+
"eval_steps_per_second": 3.881,
|
| 1785 |
+
"step": 2400
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 0.87,
|
| 1789 |
+
"grad_norm": 0.25221410393714905,
|
| 1790 |
+
"learning_rate": 9.816251162493804e-05,
|
| 1791 |
+
"loss": 1.0222,
|
| 1792 |
+
"step": 2410
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"epoch": 0.88,
|
| 1796 |
+
"grad_norm": 0.19672074913978577,
|
| 1797 |
+
"learning_rate": 9.814719885851121e-05,
|
| 1798 |
+
"loss": 0.9891,
|
| 1799 |
+
"step": 2420
|
| 1800 |
+
},
|
| 1801 |
+
{
|
| 1802 |
+
"epoch": 0.88,
|
| 1803 |
+
"grad_norm": 0.3084292411804199,
|
| 1804 |
+
"learning_rate": 9.81318237562308e-05,
|
| 1805 |
+
"loss": 0.9785,
|
| 1806 |
+
"step": 2430
|
| 1807 |
+
},
|
| 1808 |
+
{
|
| 1809 |
+
"epoch": 0.88,
|
| 1810 |
+
"grad_norm": 0.3434545397758484,
|
| 1811 |
+
"learning_rate": 9.811638633800287e-05,
|
| 1812 |
+
"loss": 0.9357,
|
| 1813 |
+
"step": 2440
|
| 1814 |
+
},
|
| 1815 |
+
{
|
| 1816 |
+
"epoch": 0.89,
|
| 1817 |
+
"grad_norm": 0.23335447907447815,
|
| 1818 |
+
"learning_rate": 9.81008866238141e-05,
|
| 1819 |
+
"loss": 1.0485,
|
| 1820 |
+
"step": 2450
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"epoch": 0.89,
|
| 1824 |
+
"grad_norm": 0.2942172586917877,
|
| 1825 |
+
"learning_rate": 9.808532463373188e-05,
|
| 1826 |
+
"loss": 1.0138,
|
| 1827 |
+
"step": 2460
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"epoch": 0.89,
|
| 1831 |
+
"grad_norm": 0.22536420822143555,
|
| 1832 |
+
"learning_rate": 9.806970038790423e-05,
|
| 1833 |
+
"loss": 1.0421,
|
| 1834 |
+
"step": 2470
|
| 1835 |
+
},
|
| 1836 |
+
{
|
| 1837 |
+
"epoch": 0.9,
|
| 1838 |
+
"grad_norm": 0.30886924266815186,
|
| 1839 |
+
"learning_rate": 9.805401390655975e-05,
|
| 1840 |
+
"loss": 0.9926,
|
| 1841 |
+
"step": 2480
|
| 1842 |
+
},
|
| 1843 |
+
{
|
| 1844 |
+
"epoch": 0.9,
|
| 1845 |
+
"grad_norm": 0.34105512499809265,
|
| 1846 |
+
"learning_rate": 9.803826521000761e-05,
|
| 1847 |
+
"loss": 1.0013,
|
| 1848 |
+
"step": 2490
|
| 1849 |
+
},
|
| 1850 |
+
{
|
| 1851 |
+
"epoch": 0.9,
|
| 1852 |
+
"grad_norm": 0.261643648147583,
|
| 1853 |
+
"learning_rate": 9.802245431863757e-05,
|
| 1854 |
+
"loss": 0.9937,
|
| 1855 |
+
"step": 2500
|
| 1856 |
+
},
|
| 1857 |
+
{
|
| 1858 |
+
"epoch": 0.91,
|
| 1859 |
+
"grad_norm": 0.3864617347717285,
|
| 1860 |
+
"learning_rate": 9.800658125291984e-05,
|
| 1861 |
+
"loss": 0.9986,
|
| 1862 |
+
"step": 2510
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"epoch": 0.91,
|
| 1866 |
+
"grad_norm": 0.31850436329841614,
|
| 1867 |
+
"learning_rate": 9.79906460334052e-05,
|
| 1868 |
+
"loss": 0.9984,
|
| 1869 |
+
"step": 2520
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 0.92,
|
| 1873 |
+
"grad_norm": 0.25421255826950073,
|
| 1874 |
+
"learning_rate": 9.797464868072488e-05,
|
| 1875 |
+
"loss": 1.0273,
|
| 1876 |
+
"step": 2530
|
| 1877 |
+
},
|
| 1878 |
+
{
|
| 1879 |
+
"epoch": 0.92,
|
| 1880 |
+
"grad_norm": 0.34440311789512634,
|
| 1881 |
+
"learning_rate": 9.795858921559052e-05,
|
| 1882 |
+
"loss": 1.0346,
|
| 1883 |
+
"step": 2540
|
| 1884 |
+
},
|
| 1885 |
+
{
|
| 1886 |
+
"epoch": 0.92,
|
| 1887 |
+
"grad_norm": 0.33147209882736206,
|
| 1888 |
+
"learning_rate": 9.79424676587942e-05,
|
| 1889 |
+
"loss": 1.0691,
|
| 1890 |
+
"step": 2550
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"epoch": 0.93,
|
| 1894 |
+
"grad_norm": 0.2778458893299103,
|
| 1895 |
+
"learning_rate": 9.792628403120842e-05,
|
| 1896 |
+
"loss": 1.009,
|
| 1897 |
+
"step": 2560
|
| 1898 |
+
},
|
| 1899 |
+
{
|
| 1900 |
+
"epoch": 0.93,
|
| 1901 |
+
"grad_norm": 0.29282572865486145,
|
| 1902 |
+
"learning_rate": 9.791003835378598e-05,
|
| 1903 |
+
"loss": 1.0015,
|
| 1904 |
+
"step": 2570
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 0.93,
|
| 1908 |
+
"grad_norm": 0.25391730666160583,
|
| 1909 |
+
"learning_rate": 9.789373064756008e-05,
|
| 1910 |
+
"loss": 1.0177,
|
| 1911 |
+
"step": 2580
|
| 1912 |
+
},
|
| 1913 |
+
{
|
| 1914 |
+
"epoch": 0.94,
|
| 1915 |
+
"grad_norm": 0.23779381811618805,
|
| 1916 |
+
"learning_rate": 9.787736093364416e-05,
|
| 1917 |
+
"loss": 1.0935,
|
| 1918 |
+
"step": 2590
|
| 1919 |
+
},
|
| 1920 |
+
{
|
| 1921 |
+
"epoch": 0.94,
|
| 1922 |
+
"grad_norm": 0.2965840995311737,
|
| 1923 |
+
"learning_rate": 9.786092923323203e-05,
|
| 1924 |
+
"loss": 1.0002,
|
| 1925 |
+
"step": 2600
|
| 1926 |
+
},
|
| 1927 |
+
{
|
| 1928 |
+
"epoch": 0.94,
|
| 1929 |
+
"eval_loss": 1.005922555923462,
|
| 1930 |
+
"eval_runtime": 125.0587,
|
| 1931 |
+
"eval_samples_per_second": 62.379,
|
| 1932 |
+
"eval_steps_per_second": 3.902,
|
| 1933 |
+
"step": 2600
|
| 1934 |
+
},
|
| 1935 |
+
{
|
| 1936 |
+
"epoch": 0.94,
|
| 1937 |
+
"grad_norm": 0.23760788142681122,
|
| 1938 |
+
"learning_rate": 9.784443556759766e-05,
|
| 1939 |
+
"loss": 1.0305,
|
| 1940 |
+
"step": 2610
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 0.95,
|
| 1944 |
+
"grad_norm": 0.22895409166812897,
|
| 1945 |
+
"learning_rate": 9.78278799580953e-05,
|
| 1946 |
+
"loss": 1.0427,
|
| 1947 |
+
"step": 2620
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 0.95,
|
| 1951 |
+
"grad_norm": 0.36007368564605713,
|
| 1952 |
+
"learning_rate": 9.781126242615939e-05,
|
| 1953 |
+
"loss": 1.0059,
|
| 1954 |
+
"step": 2630
|
| 1955 |
+
},
|
| 1956 |
+
{
|
| 1957 |
+
"epoch": 0.96,
|
| 1958 |
+
"grad_norm": 0.2813151776790619,
|
| 1959 |
+
"learning_rate": 9.779458299330452e-05,
|
| 1960 |
+
"loss": 1.0418,
|
| 1961 |
+
"step": 2640
|
| 1962 |
+
},
|
| 1963 |
+
{
|
| 1964 |
+
"epoch": 0.96,
|
| 1965 |
+
"grad_norm": 0.27038782835006714,
|
| 1966 |
+
"learning_rate": 9.777784168112545e-05,
|
| 1967 |
+
"loss": 1.0092,
|
| 1968 |
+
"step": 2650
|
| 1969 |
+
},
|
| 1970 |
+
{
|
| 1971 |
+
"epoch": 0.96,
|
| 1972 |
+
"grad_norm": 0.22898097336292267,
|
| 1973 |
+
"learning_rate": 9.776103851129706e-05,
|
| 1974 |
+
"loss": 0.9883,
|
| 1975 |
+
"step": 2660
|
| 1976 |
+
},
|
| 1977 |
+
{
|
| 1978 |
+
"epoch": 0.97,
|
| 1979 |
+
"grad_norm": 0.2213810682296753,
|
| 1980 |
+
"learning_rate": 9.774417350557428e-05,
|
| 1981 |
+
"loss": 1.0753,
|
| 1982 |
+
"step": 2670
|
| 1983 |
+
},
|
| 1984 |
+
{
|
| 1985 |
+
"epoch": 0.97,
|
| 1986 |
+
"grad_norm": 0.22410623729228973,
|
| 1987 |
+
"learning_rate": 9.772724668579212e-05,
|
| 1988 |
+
"loss": 1.0524,
|
| 1989 |
+
"step": 2680
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 0.97,
|
| 1993 |
+
"grad_norm": 0.3005650043487549,
|
| 1994 |
+
"learning_rate": 9.771025807386562e-05,
|
| 1995 |
+
"loss": 1.0562,
|
| 1996 |
+
"step": 2690
|
| 1997 |
+
},
|
| 1998 |
+
{
|
| 1999 |
+
"epoch": 0.98,
|
| 2000 |
+
"grad_norm": 0.3941683769226074,
|
| 2001 |
+
"learning_rate": 9.769320769178983e-05,
|
| 2002 |
+
"loss": 0.9925,
|
| 2003 |
+
"step": 2700
|
| 2004 |
+
},
|
| 2005 |
+
{
|
| 2006 |
+
"epoch": 0.98,
|
| 2007 |
+
"grad_norm": 0.2829142212867737,
|
| 2008 |
+
"learning_rate": 9.767609556163977e-05,
|
| 2009 |
+
"loss": 1.014,
|
| 2010 |
+
"step": 2710
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"epoch": 0.98,
|
| 2014 |
+
"grad_norm": 0.29680418968200684,
|
| 2015 |
+
"learning_rate": 9.765892170557038e-05,
|
| 2016 |
+
"loss": 0.9677,
|
| 2017 |
+
"step": 2720
|
| 2018 |
+
},
|
| 2019 |
+
{
|
| 2020 |
+
"epoch": 0.99,
|
| 2021 |
+
"grad_norm": 0.22002767026424408,
|
| 2022 |
+
"learning_rate": 9.764168614581655e-05,
|
| 2023 |
+
"loss": 0.9954,
|
| 2024 |
+
"step": 2730
|
| 2025 |
+
},
|
| 2026 |
+
{
|
| 2027 |
+
"epoch": 0.99,
|
| 2028 |
+
"grad_norm": 0.2758820354938507,
|
| 2029 |
+
"learning_rate": 9.762438890469304e-05,
|
| 2030 |
+
"loss": 1.0029,
|
| 2031 |
+
"step": 2740
|
| 2032 |
+
},
|
| 2033 |
+
{
|
| 2034 |
+
"epoch": 1.0,
|
| 2035 |
+
"grad_norm": 0.2981850802898407,
|
| 2036 |
+
"learning_rate": 9.760703000459446e-05,
|
| 2037 |
+
"loss": 1.0555,
|
| 2038 |
+
"step": 2750
|
| 2039 |
+
},
|
| 2040 |
+
{
|
| 2041 |
+
"epoch": 1.0,
|
| 2042 |
+
"grad_norm": 0.22340857982635498,
|
| 2043 |
+
"learning_rate": 9.758960946799528e-05,
|
| 2044 |
+
"loss": 1.0394,
|
| 2045 |
+
"step": 2760
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 1.0,
|
| 2049 |
+
"grad_norm": 0.19991633296012878,
|
| 2050 |
+
"learning_rate": 9.757212731744974e-05,
|
| 2051 |
+
"loss": 0.9325,
|
| 2052 |
+
"step": 2770
|
| 2053 |
+
},
|
| 2054 |
+
{
|
| 2055 |
+
"epoch": 1.01,
|
| 2056 |
+
"grad_norm": 0.30030888319015503,
|
| 2057 |
+
"learning_rate": 9.755458357559186e-05,
|
| 2058 |
+
"loss": 0.9711,
|
| 2059 |
+
"step": 2780
|
| 2060 |
+
},
|
| 2061 |
+
{
|
| 2062 |
+
"epoch": 1.01,
|
| 2063 |
+
"grad_norm": 0.3804832696914673,
|
| 2064 |
+
"learning_rate": 9.753697826513541e-05,
|
| 2065 |
+
"loss": 0.9651,
|
| 2066 |
+
"step": 2790
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 1.01,
|
| 2070 |
+
"grad_norm": 0.46047547459602356,
|
| 2071 |
+
"learning_rate": 9.751931140887387e-05,
|
| 2072 |
+
"loss": 0.9686,
|
| 2073 |
+
"step": 2800
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 1.01,
|
| 2077 |
+
"eval_loss": 1.0086077451705933,
|
| 2078 |
+
"eval_runtime": 124.6354,
|
| 2079 |
+
"eval_samples_per_second": 62.591,
|
| 2080 |
+
"eval_steps_per_second": 3.915,
|
| 2081 |
+
"step": 2800
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 1.02,
|
| 2085 |
+
"grad_norm": 0.30646952986717224,
|
| 2086 |
+
"learning_rate": 9.750158302968039e-05,
|
| 2087 |
+
"loss": 0.9267,
|
| 2088 |
+
"step": 2810
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 1.02,
|
| 2092 |
+
"grad_norm": 0.3007545471191406,
|
| 2093 |
+
"learning_rate": 9.748379315050778e-05,
|
| 2094 |
+
"loss": 1.0193,
|
| 2095 |
+
"step": 2820
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 1.02,
|
| 2099 |
+
"grad_norm": 0.2814784049987793,
|
| 2100 |
+
"learning_rate": 9.74659417943885e-05,
|
| 2101 |
+
"loss": 0.8893,
|
| 2102 |
+
"step": 2830
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 1.03,
|
| 2106 |
+
"grad_norm": 0.2728348970413208,
|
| 2107 |
+
"learning_rate": 9.744802898443456e-05,
|
| 2108 |
+
"loss": 0.937,
|
| 2109 |
+
"step": 2840
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 1.03,
|
| 2113 |
+
"grad_norm": 0.2994844913482666,
|
| 2114 |
+
"learning_rate": 9.743005474383755e-05,
|
| 2115 |
+
"loss": 0.949,
|
| 2116 |
+
"step": 2850
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 1.04,
|
| 2120 |
+
"grad_norm": 0.43111738562583923,
|
| 2121 |
+
"learning_rate": 9.741201909586861e-05,
|
| 2122 |
+
"loss": 0.9897,
|
| 2123 |
+
"step": 2860
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 1.04,
|
| 2127 |
+
"grad_norm": 0.29551658034324646,
|
| 2128 |
+
"learning_rate": 9.739392206387838e-05,
|
| 2129 |
+
"loss": 0.9393,
|
| 2130 |
+
"step": 2870
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 1.04,
|
| 2134 |
+
"grad_norm": 0.40380623936653137,
|
| 2135 |
+
"learning_rate": 9.737576367129694e-05,
|
| 2136 |
+
"loss": 0.9365,
|
| 2137 |
+
"step": 2880
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 1.05,
|
| 2141 |
+
"grad_norm": 0.2757427394390106,
|
| 2142 |
+
"learning_rate": 9.735754394163386e-05,
|
| 2143 |
+
"loss": 1.0074,
|
| 2144 |
+
"step": 2890
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 1.05,
|
| 2148 |
+
"grad_norm": 0.35594430565834045,
|
| 2149 |
+
"learning_rate": 9.73392628984781e-05,
|
| 2150 |
+
"loss": 0.9682,
|
| 2151 |
+
"step": 2900
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 1.05,
|
| 2155 |
+
"grad_norm": 0.32288888096809387,
|
| 2156 |
+
"learning_rate": 9.732092056549799e-05,
|
| 2157 |
+
"loss": 0.9753,
|
| 2158 |
+
"step": 2910
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 1.06,
|
| 2162 |
+
"grad_norm": 0.3491690158843994,
|
| 2163 |
+
"learning_rate": 9.730251696644122e-05,
|
| 2164 |
+
"loss": 0.926,
|
| 2165 |
+
"step": 2920
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 1.06,
|
| 2169 |
+
"grad_norm": 0.41806405782699585,
|
| 2170 |
+
"learning_rate": 9.728405212513483e-05,
|
| 2171 |
+
"loss": 0.9993,
|
| 2172 |
+
"step": 2930
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 1.06,
|
| 2176 |
+
"grad_norm": 0.4885188043117523,
|
| 2177 |
+
"learning_rate": 9.726552606548512e-05,
|
| 2178 |
+
"loss": 0.9879,
|
| 2179 |
+
"step": 2940
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 1.07,
|
| 2183 |
+
"grad_norm": 0.41796302795410156,
|
| 2184 |
+
"learning_rate": 9.724693881147761e-05,
|
| 2185 |
+
"loss": 0.9626,
|
| 2186 |
+
"step": 2950
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 1.07,
|
| 2190 |
+
"grad_norm": 0.39677631855010986,
|
| 2191 |
+
"learning_rate": 9.722829038717717e-05,
|
| 2192 |
+
"loss": 0.9767,
|
| 2193 |
+
"step": 2960
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 1.07,
|
| 2197 |
+
"grad_norm": 0.5329232215881348,
|
| 2198 |
+
"learning_rate": 9.720958081672773e-05,
|
| 2199 |
+
"loss": 0.9357,
|
| 2200 |
+
"step": 2970
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 1.08,
|
| 2204 |
+
"grad_norm": 0.4468931257724762,
|
| 2205 |
+
"learning_rate": 9.719081012435247e-05,
|
| 2206 |
+
"loss": 0.9705,
|
| 2207 |
+
"step": 2980
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 1.08,
|
| 2211 |
+
"grad_norm": 0.4029316306114197,
|
| 2212 |
+
"learning_rate": 9.717197833435367e-05,
|
| 2213 |
+
"loss": 0.9727,
|
| 2214 |
+
"step": 2990
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 1.09,
|
| 2218 |
+
"grad_norm": 0.37598028779029846,
|
| 2219 |
+
"learning_rate": 9.715308547111273e-05,
|
| 2220 |
+
"loss": 0.9767,
|
| 2221 |
+
"step": 3000
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 1.09,
|
| 2225 |
+
"eval_loss": 1.014098048210144,
|
| 2226 |
+
"eval_runtime": 125.4232,
|
| 2227 |
+
"eval_samples_per_second": 62.197,
|
| 2228 |
+
"eval_steps_per_second": 3.891,
|
| 2229 |
+
"step": 3000
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 1.09,
|
| 2233 |
+
"grad_norm": 0.3833357095718384,
|
| 2234 |
+
"learning_rate": 9.713413155909009e-05,
|
| 2235 |
+
"loss": 0.9605,
|
| 2236 |
+
"step": 3010
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 1.09,
|
| 2240 |
+
"grad_norm": 0.4391871988773346,
|
| 2241 |
+
"learning_rate": 9.711511662282527e-05,
|
| 2242 |
+
"loss": 0.9611,
|
| 2243 |
+
"step": 3020
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 1.1,
|
| 2247 |
+
"grad_norm": 0.39860454201698303,
|
| 2248 |
+
"learning_rate": 9.709604068693679e-05,
|
| 2249 |
+
"loss": 0.9222,
|
| 2250 |
+
"step": 3030
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 1.1,
|
| 2254 |
+
"grad_norm": 0.33882561326026917,
|
| 2255 |
+
"learning_rate": 9.707690377612211e-05,
|
| 2256 |
+
"loss": 0.9369,
|
| 2257 |
+
"step": 3040
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 1.1,
|
| 2261 |
+
"grad_norm": 0.3763039708137512,
|
| 2262 |
+
"learning_rate": 9.705770591515768e-05,
|
| 2263 |
+
"loss": 0.8864,
|
| 2264 |
+
"step": 3050
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 1.11,
|
| 2268 |
+
"grad_norm": 0.3221600353717804,
|
| 2269 |
+
"learning_rate": 9.703844712889884e-05,
|
| 2270 |
+
"loss": 0.9753,
|
| 2271 |
+
"step": 3060
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 1.11,
|
| 2275 |
+
"grad_norm": 0.3342023491859436,
|
| 2276 |
+
"learning_rate": 9.701912744227979e-05,
|
| 2277 |
+
"loss": 0.9233,
|
| 2278 |
+
"step": 3070
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 1.11,
|
| 2282 |
+
"grad_norm": 0.4082651734352112,
|
| 2283 |
+
"learning_rate": 9.699974688031363e-05,
|
| 2284 |
+
"loss": 0.987,
|
| 2285 |
+
"step": 3080
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 1.12,
|
| 2289 |
+
"grad_norm": 0.4198564291000366,
|
| 2290 |
+
"learning_rate": 9.69803054680922e-05,
|
| 2291 |
+
"loss": 0.8833,
|
| 2292 |
+
"step": 3090
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 1.12,
|
| 2296 |
+
"grad_norm": 0.3833492398262024,
|
| 2297 |
+
"learning_rate": 9.696080323078621e-05,
|
| 2298 |
+
"loss": 0.9894,
|
| 2299 |
+
"step": 3100
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 1.13,
|
| 2303 |
+
"grad_norm": 0.35935208201408386,
|
| 2304 |
+
"learning_rate": 9.694124019364505e-05,
|
| 2305 |
+
"loss": 0.9417,
|
| 2306 |
+
"step": 3110
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 1.13,
|
| 2310 |
+
"grad_norm": 0.3433043658733368,
|
| 2311 |
+
"learning_rate": 9.692161638199686e-05,
|
| 2312 |
+
"loss": 0.9251,
|
| 2313 |
+
"step": 3120
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 1.13,
|
| 2317 |
+
"grad_norm": 0.30163127183914185,
|
| 2318 |
+
"learning_rate": 9.690193182124844e-05,
|
| 2319 |
+
"loss": 0.9447,
|
| 2320 |
+
"step": 3130
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 1.14,
|
| 2324 |
+
"grad_norm": 0.4361821711063385,
|
| 2325 |
+
"learning_rate": 9.68821865368853e-05,
|
| 2326 |
+
"loss": 0.9984,
|
| 2327 |
+
"step": 3140
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 1.14,
|
| 2331 |
+
"grad_norm": 0.4263075888156891,
|
| 2332 |
+
"learning_rate": 9.686238055447148e-05,
|
| 2333 |
+
"loss": 0.9422,
|
| 2334 |
+
"step": 3150
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 1.14,
|
| 2338 |
+
"grad_norm": 0.33963072299957275,
|
| 2339 |
+
"learning_rate": 9.684251389964967e-05,
|
| 2340 |
+
"loss": 0.9199,
|
| 2341 |
+
"step": 3160
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 1.15,
|
| 2345 |
+
"grad_norm": 0.41040754318237305,
|
| 2346 |
+
"learning_rate": 9.68225865981411e-05,
|
| 2347 |
+
"loss": 0.9249,
|
| 2348 |
+
"step": 3170
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 1.15,
|
| 2352 |
+
"grad_norm": 0.3697950839996338,
|
| 2353 |
+
"learning_rate": 9.680259867574552e-05,
|
| 2354 |
+
"loss": 0.947,
|
| 2355 |
+
"step": 3180
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 1.15,
|
| 2359 |
+
"grad_norm": 0.3211696743965149,
|
| 2360 |
+
"learning_rate": 9.678255015834112e-05,
|
| 2361 |
+
"loss": 0.9956,
|
| 2362 |
+
"step": 3190
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 1.16,
|
| 2366 |
+
"grad_norm": 0.4463675022125244,
|
| 2367 |
+
"learning_rate": 9.676244107188463e-05,
|
| 2368 |
+
"loss": 0.9494,
|
| 2369 |
+
"step": 3200
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 1.16,
|
| 2373 |
+
"eval_loss": 1.0160499811172485,
|
| 2374 |
+
"eval_runtime": 124.6588,
|
| 2375 |
+
"eval_samples_per_second": 62.579,
|
| 2376 |
+
"eval_steps_per_second": 3.915,
|
| 2377 |
+
"step": 3200
|
| 2378 |
+
},
|
| 2379 |
+
{
|
| 2380 |
+
"epoch": 1.16,
|
| 2381 |
+
"step": 3200,
|
| 2382 |
+
"total_flos": 8.146148608211681e+17,
|
| 2383 |
+
"train_loss": 1.015018144249916,
|
| 2384 |
+
"train_runtime": 4695.8401,
|
| 2385 |
+
"train_samples_per_second": 94.128,
|
| 2386 |
+
"train_steps_per_second": 5.884
|
| 2387 |
+
}
|
| 2388 |
+
],
|
| 2389 |
+
"logging_steps": 10,
|
| 2390 |
+
"max_steps": 27630,
|
| 2391 |
+
"num_input_tokens_seen": 0,
|
| 2392 |
+
"num_train_epochs": 10,
|
| 2393 |
+
"save_steps": 1000,
|
| 2394 |
+
"total_flos": 8.146148608211681e+17,
|
| 2395 |
+
"train_batch_size": 8,
|
| 2396 |
+
"trial_name": null,
|
| 2397 |
+
"trial_params": null
|
| 2398 |
+
}
|
llama2_13b_peft/alpaca/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee00a18a03b57747a77ea7ce888e4df0481f3a55be563ee85ba65d3e1221563f
|
| 3 |
+
size 5048
|
llama2_13b_peft/alpaca/training_eval_loss.png
ADDED
|
llama2_13b_peft/alpaca/training_loss.png
ADDED
|
llama2_13b_peft/cnn_dailymail/README.md
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- llama-factory
|
| 6 |
+
- lora
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: /data1/model/llama2/meta-llama/Llama2-13b
|
| 9 |
+
model-index:
|
| 10 |
+
- name: cnn_dailymail_no_sys
|
| 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 |
+
# cnn_dailymail_no_sys
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [/data1/model/llama2/meta-llama/Llama2-13b](https://huggingface.co//data1/model/llama2/meta-llama/Llama2-13b) on the cnn_dailymail_no_sys dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.9911
|
| 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: 0.0001
|
| 41 |
+
- train_batch_size: 8
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- num_devices: 3
|
| 46 |
+
- total_train_batch_size: 24
|
| 47 |
+
- total_eval_batch_size: 24
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: cosine
|
| 50 |
+
- lr_scheduler_warmup_steps: 20
|
| 51 |
+
- num_epochs: 10.0
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 57 |
+
| 1.0297 | 0.14 | 50 | 1.0376 |
|
| 58 |
+
| 1.0043 | 0.28 | 100 | 1.0226 |
|
| 59 |
+
| 1.0241 | 0.42 | 150 | 1.0131 |
|
| 60 |
+
| 1.0134 | 0.56 | 200 | 1.0083 |
|
| 61 |
+
| 1.0284 | 0.7 | 250 | 1.0041 |
|
| 62 |
+
| 1.0126 | 0.85 | 300 | 0.9974 |
|
| 63 |
+
| 0.9779 | 0.99 | 350 | 0.9922 |
|
| 64 |
+
| 0.9239 | 1.13 | 400 | 0.9984 |
|
| 65 |
+
| 0.9456 | 1.27 | 450 | 0.9971 |
|
| 66 |
+
| 0.9064 | 1.41 | 500 | 0.9911 |
|
| 67 |
+
| 0.9238 | 1.55 | 550 | 0.9884 |
|
| 68 |
+
| 0.9053 | 1.69 | 600 | 0.9863 |
|
| 69 |
+
| 0.9066 | 1.83 | 650 | 0.9829 |
|
| 70 |
+
| 0.932 | 1.97 | 700 | 0.9802 |
|
| 71 |
+
| 0.7339 | 2.11 | 750 | 1.0370 |
|
| 72 |
+
| 0.7678 | 2.25 | 800 | 1.0321 |
|
| 73 |
+
| 0.7538 | 2.39 | 850 | 1.0240 |
|
| 74 |
+
|
| 75 |
+
|
| 76 |
+
### Framework versions
|
| 77 |
+
|
| 78 |
+
- PEFT 0.9.0
|
| 79 |
+
- Transformers 4.38.2
|
| 80 |
+
- Pytorch 2.2.1
|
| 81 |
+
- Datasets 2.18.0
|
| 82 |
+
- Tokenizers 0.15.2
|
llama2_13b_peft/cnn_dailymail/adapter_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "/data1/model/llama2/meta-llama/Llama2-13b",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 16,
|
| 13 |
+
"lora_dropout": 0.0,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 8,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"o_proj",
|
| 23 |
+
"up_proj",
|
| 24 |
+
"v_proj",
|
| 25 |
+
"k_proj",
|
| 26 |
+
"down_proj",
|
| 27 |
+
"q_proj",
|
| 28 |
+
"gate_proj"
|
| 29 |
+
],
|
| 30 |
+
"task_type": "CAUSAL_LM",
|
| 31 |
+
"use_dora": false,
|
| 32 |
+
"use_rslora": false
|
| 33 |
+
}
|
llama2_13b_peft/cnn_dailymail/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91b54b9ab362c86ed5fa1b8aceba1d8f17d63dbc2ab01d716dab026362e2c096
|
| 3 |
+
size 125248064
|
llama2_13b_peft/cnn_dailymail/all_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.39,
|
| 3 |
+
"eval_loss": 0.9910521507263184,
|
| 4 |
+
"eval_runtime": 121.9871,
|
| 5 |
+
"eval_samples_per_second": 12.296,
|
| 6 |
+
"eval_steps_per_second": 0.516,
|
| 7 |
+
"train_loss": 0.943028081445133,
|
| 8 |
+
"train_runtime": 7174.3764,
|
| 9 |
+
"train_samples_per_second": 11.848,
|
| 10 |
+
"train_steps_per_second": 0.495
|
| 11 |
+
}
|
llama2_13b_peft/cnn_dailymail/eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.39,
|
| 3 |
+
"eval_loss": 0.9910521507263184,
|
| 4 |
+
"eval_runtime": 121.9871,
|
| 5 |
+
"eval_samples_per_second": 12.296,
|
| 6 |
+
"eval_steps_per_second": 0.516
|
| 7 |
+
}
|
llama2_13b_peft/cnn_dailymail/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
llama2_13b_peft/cnn_dailymail/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
llama2_13b_peft/cnn_dailymail/tokenizer_config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content + '\\n' }}{% endif %}{% endfor %}",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"legacy": true,
|
| 36 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
+
"pad_token": "</s>",
|
| 38 |
+
"padding_side": "right",
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"spaces_between_special_tokens": false,
|
| 41 |
+
"split_special_tokens": false,
|
| 42 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 43 |
+
"unk_token": "<unk>",
|
| 44 |
+
"use_default_system_prompt": false
|
| 45 |
+
}
|
llama2_13b_peft/cnn_dailymail/train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.39,
|
| 3 |
+
"train_loss": 0.943028081445133,
|
| 4 |
+
"train_runtime": 7174.3764,
|
| 5 |
+
"train_samples_per_second": 11.848,
|
| 6 |
+
"train_steps_per_second": 0.495
|
| 7 |
+
}
|
llama2_13b_peft/cnn_dailymail/trainer_log.jsonl
ADDED
|
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 10, "total_steps": 3550, "loss": 1.6246, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5e-05, "epoch": 0.03, "percentage": 0.28, "elapsed_time": "0:01:01", "remaining_time": "6:03:32"}
|
| 2 |
+
{"current_steps": 20, "total_steps": 3550, "loss": 1.3935, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001, "epoch": 0.06, "percentage": 0.56, "elapsed_time": "0:01:58", "remaining_time": "5:47:35"}
|
| 3 |
+
{"current_steps": 30, "total_steps": 3550, "loss": 1.1048, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.999801989839055e-05, "epoch": 0.08, "percentage": 0.85, "elapsed_time": "0:02:57", "remaining_time": "5:47:59"}
|
| 4 |
+
{"current_steps": 40, "total_steps": 3550, "loss": 1.0825, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.999207975039429e-05, "epoch": 0.11, "percentage": 1.13, "elapsed_time": "0:03:56", "remaining_time": "5:45:24"}
|
| 5 |
+
{"current_steps": 50, "total_steps": 3550, "loss": 1.0297, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.998218002649506e-05, "epoch": 0.14, "percentage": 1.41, "elapsed_time": "0:04:57", "remaining_time": "5:47:02"}
|
| 6 |
+
{"current_steps": 50, "total_steps": 3550, "loss": null, "eval_loss": 1.0375804901123047, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.14, "percentage": 1.41, "elapsed_time": "0:04:57", "remaining_time": "5:47:02"}
|
| 7 |
+
{"current_steps": 60, "total_steps": 3550, "loss": 1.0166, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.996832151079127e-05, "epoch": 0.17, "percentage": 1.69, "elapsed_time": "0:07:55", "remaining_time": "7:40:39"}
|
| 8 |
+
{"current_steps": 70, "total_steps": 3550, "loss": 1.0402, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.995050530093367e-05, "epoch": 0.2, "percentage": 1.97, "elapsed_time": "0:09:00", "remaining_time": "7:27:41"}
|
| 9 |
+
{"current_steps": 80, "total_steps": 3550, "loss": 1.0182, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.992873280803849e-05, "epoch": 0.23, "percentage": 2.25, "elapsed_time": "0:10:01", "remaining_time": "7:15:05"}
|
| 10 |
+
{"current_steps": 90, "total_steps": 3550, "loss": 1.0422, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.990300575657565e-05, "epoch": 0.25, "percentage": 2.54, "elapsed_time": "0:11:00", "remaining_time": "7:03:17"}
|
| 11 |
+
{"current_steps": 100, "total_steps": 3550, "loss": 1.0043, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.987332618423221e-05, "epoch": 0.28, "percentage": 2.82, "elapsed_time": "0:12:00", "remaining_time": "6:54:04"}
|
| 12 |
+
{"current_steps": 100, "total_steps": 3550, "loss": null, "eval_loss": 1.022628903388977, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.28, "percentage": 2.82, "elapsed_time": "0:12:00", "remaining_time": "6:54:04"}
|
| 13 |
+
{"current_steps": 110, "total_steps": 3550, "loss": 1.0384, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.983969644175091e-05, "epoch": 0.31, "percentage": 3.1, "elapsed_time": "0:14:59", "remaining_time": "7:48:47"}
|
| 14 |
+
{"current_steps": 120, "total_steps": 3550, "loss": 1.0326, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.980211919274407e-05, "epoch": 0.34, "percentage": 3.38, "elapsed_time": "0:15:57", "remaining_time": "7:36:06"}
|
| 15 |
+
{"current_steps": 130, "total_steps": 3550, "loss": 1.0133, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.976059741348251e-05, "epoch": 0.37, "percentage": 3.66, "elapsed_time": "0:17:01", "remaining_time": "7:27:54"}
|
| 16 |
+
{"current_steps": 140, "total_steps": 3550, "loss": 1.0129, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.971513439265991e-05, "epoch": 0.39, "percentage": 3.94, "elapsed_time": "0:18:05", "remaining_time": "7:20:33"}
|
| 17 |
+
{"current_steps": 150, "total_steps": 3550, "loss": 1.0241, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.96657337311323e-05, "epoch": 0.42, "percentage": 4.23, "elapsed_time": "0:19:07", "remaining_time": "7:13:40"}
|
| 18 |
+
{"current_steps": 150, "total_steps": 3550, "loss": null, "eval_loss": 1.0130971670150757, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.42, "percentage": 4.23, "elapsed_time": "0:19:07", "remaining_time": "7:13:40"}
|
| 19 |
+
{"current_steps": 160, "total_steps": 3550, "loss": 1.038, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.961239934163289e-05, "epoch": 0.45, "percentage": 4.51, "elapsed_time": "0:22:08", "remaining_time": "7:49:07"}
|
| 20 |
+
{"current_steps": 170, "total_steps": 3550, "loss": 1.0083, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.955513544846205e-05, "epoch": 0.48, "percentage": 4.79, "elapsed_time": "0:23:08", "remaining_time": "7:40:05"}
|
| 21 |
+
{"current_steps": 180, "total_steps": 3550, "loss": 0.9988, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.949394658715288e-05, "epoch": 0.51, "percentage": 5.07, "elapsed_time": "0:24:05", "remaining_time": "7:30:54"}
|
| 22 |
+
{"current_steps": 190, "total_steps": 3550, "loss": 1.0344, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.942883760411188e-05, "epoch": 0.54, "percentage": 5.35, "elapsed_time": "0:25:02", "remaining_time": "7:22:49"}
|
| 23 |
+
{"current_steps": 200, "total_steps": 3550, "loss": 1.0134, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.935981365623516e-05, "epoch": 0.56, "percentage": 5.63, "elapsed_time": "0:26:03", "remaining_time": "7:16:33"}
|
| 24 |
+
{"current_steps": 200, "total_steps": 3550, "loss": null, "eval_loss": 1.0082659721374512, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.56, "percentage": 5.63, "elapsed_time": "0:26:03", "remaining_time": "7:16:33"}
|
| 25 |
+
{"current_steps": 210, "total_steps": 3550, "loss": 1.0259, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.928688021049992e-05, "epoch": 0.59, "percentage": 5.92, "elapsed_time": "0:29:03", "remaining_time": "7:42:13"}
|
| 26 |
+
{"current_steps": 220, "total_steps": 3550, "loss": 1.0102, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.921004304353147e-05, "epoch": 0.62, "percentage": 6.2, "elapsed_time": "0:30:04", "remaining_time": "7:35:16"}
|
| 27 |
+
{"current_steps": 230, "total_steps": 3550, "loss": 0.9969, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.912930824114576e-05, "epoch": 0.65, "percentage": 6.48, "elapsed_time": "0:31:04", "remaining_time": "7:28:27"}
|
| 28 |
+
{"current_steps": 240, "total_steps": 3550, "loss": 0.9626, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.904468219786727e-05, "epoch": 0.68, "percentage": 6.76, "elapsed_time": "0:32:01", "remaining_time": "7:21:37"}
|
| 29 |
+
{"current_steps": 250, "total_steps": 3550, "loss": 1.0284, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.895617161642256e-05, "epoch": 0.7, "percentage": 7.04, "elapsed_time": "0:33:04", "remaining_time": "7:16:40"}
|
| 30 |
+
{"current_steps": 250, "total_steps": 3550, "loss": null, "eval_loss": 1.0040661096572876, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.7, "percentage": 7.04, "elapsed_time": "0:33:04", "remaining_time": "7:16:40"}
|
| 31 |
+
{"current_steps": 260, "total_steps": 3550, "loss": 0.9762, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.886378350720943e-05, "epoch": 0.73, "percentage": 7.32, "elapsed_time": "0:36:06", "remaining_time": "7:36:48"}
|
| 32 |
+
{"current_steps": 270, "total_steps": 3550, "loss": 1.0387, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.876752518774166e-05, "epoch": 0.76, "percentage": 7.61, "elapsed_time": "0:37:07", "remaining_time": "7:30:56"}
|
| 33 |
+
{"current_steps": 280, "total_steps": 3550, "loss": 0.9725, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.866740428206934e-05, "epoch": 0.79, "percentage": 7.89, "elapsed_time": "0:38:09", "remaining_time": "7:25:39"}
|
| 34 |
+
{"current_steps": 290, "total_steps": 3550, "loss": 1.0357, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.856342872017515e-05, "epoch": 0.82, "percentage": 8.17, "elapsed_time": "0:39:08", "remaining_time": "7:19:59"}
|
| 35 |
+
{"current_steps": 300, "total_steps": 3550, "loss": 1.0126, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.845560673734617e-05, "epoch": 0.85, "percentage": 8.45, "elapsed_time": "0:40:10", "remaining_time": "7:15:13"}
|
| 36 |
+
{"current_steps": 300, "total_steps": 3550, "loss": null, "eval_loss": 0.9973611831665039, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.85, "percentage": 8.45, "elapsed_time": "0:40:10", "remaining_time": "7:15:13"}
|
| 37 |
+
{"current_steps": 310, "total_steps": 3550, "loss": 0.9815, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.834394687352169e-05, "epoch": 0.87, "percentage": 8.73, "elapsed_time": "0:43:10", "remaining_time": "7:31:17"}
|
| 38 |
+
{"current_steps": 320, "total_steps": 3550, "loss": 0.9906, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.822845797261675e-05, "epoch": 0.9, "percentage": 9.01, "elapsed_time": "0:44:14", "remaining_time": "7:26:36"}
|
| 39 |
+
{"current_steps": 330, "total_steps": 3550, "loss": 1.0014, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.810914918182169e-05, "epoch": 0.93, "percentage": 9.3, "elapsed_time": "0:45:12", "remaining_time": "7:21:05"}
|
| 40 |
+
{"current_steps": 340, "total_steps": 3550, "loss": 0.9813, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.798602995087763e-05, "epoch": 0.96, "percentage": 9.58, "elapsed_time": "0:46:11", "remaining_time": "7:16:08"}
|
| 41 |
+
{"current_steps": 350, "total_steps": 3550, "loss": 0.9779, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.785911003132811e-05, "epoch": 0.99, "percentage": 9.86, "elapsed_time": "0:47:10", "remaining_time": "7:11:22"}
|
| 42 |
+
{"current_steps": 350, "total_steps": 3550, "loss": null, "eval_loss": 0.9921852350234985, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.99, "percentage": 9.86, "elapsed_time": "0:47:10", "remaining_time": "7:11:22"}
|
| 43 |
+
{"current_steps": 360, "total_steps": 3550, "loss": 0.9616, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.772839947574657e-05, "epoch": 1.01, "percentage": 10.14, "elapsed_time": "0:50:18", "remaining_time": "7:25:47"}
|
| 44 |
+
{"current_steps": 370, "total_steps": 3550, "loss": 0.9413, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.75939086369403e-05, "epoch": 1.04, "percentage": 10.42, "elapsed_time": "0:51:20", "remaining_time": "7:21:17"}
|
| 45 |
+
{"current_steps": 380, "total_steps": 3550, "loss": 0.9512, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.745564816713034e-05, "epoch": 1.07, "percentage": 10.7, "elapsed_time": "0:52:19", "remaining_time": "7:16:26"}
|
| 46 |
+
{"current_steps": 390, "total_steps": 3550, "loss": 0.935, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.731362901710783e-05, "epoch": 1.1, "percentage": 10.99, "elapsed_time": "0:53:21", "remaining_time": "7:12:20"}
|
| 47 |
+
{"current_steps": 400, "total_steps": 3550, "loss": 0.9239, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.71678624353667e-05, "epoch": 1.13, "percentage": 11.27, "elapsed_time": "0:54:19", "remaining_time": "7:07:51"}
|
| 48 |
+
{"current_steps": 400, "total_steps": 3550, "loss": null, "eval_loss": 0.9983939528465271, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.13, "percentage": 11.27, "elapsed_time": "0:54:19", "remaining_time": "7:07:51"}
|
| 49 |
+
{"current_steps": 410, "total_steps": 3550, "loss": 0.9265, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.701835996721265e-05, "epoch": 1.15, "percentage": 11.55, "elapsed_time": "0:57:22", "remaining_time": "7:19:28"}
|
| 50 |
+
{"current_steps": 420, "total_steps": 3550, "loss": 0.9361, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.686513345384882e-05, "epoch": 1.18, "percentage": 11.83, "elapsed_time": "0:58:29", "remaining_time": "7:15:52"}
|
| 51 |
+
{"current_steps": 430, "total_steps": 3550, "loss": 0.9043, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.67081950314378e-05, "epoch": 1.21, "percentage": 12.11, "elapsed_time": "0:59:24", "remaining_time": "7:11:01"}
|
| 52 |
+
{"current_steps": 440, "total_steps": 3550, "loss": 0.9006, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.654755713014052e-05, "epoch": 1.24, "percentage": 12.39, "elapsed_time": "1:00:21", "remaining_time": "7:06:36"}
|
| 53 |
+
{"current_steps": 450, "total_steps": 3550, "loss": 0.9456, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.638323247313166e-05, "epoch": 1.27, "percentage": 12.68, "elapsed_time": "1:01:20", "remaining_time": "7:02:31"}
|
| 54 |
+
{"current_steps": 450, "total_steps": 3550, "loss": null, "eval_loss": 0.9970971345901489, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.27, "percentage": 12.68, "elapsed_time": "1:01:20", "remaining_time": "7:02:31"}
|
| 55 |
+
{"current_steps": 460, "total_steps": 3550, "loss": 0.8814, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.621523407559193e-05, "epoch": 1.3, "percentage": 12.96, "elapsed_time": "1:04:20", "remaining_time": "7:12:11"}
|
| 56 |
+
{"current_steps": 470, "total_steps": 3550, "loss": 0.9459, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.604357524367722e-05, "epoch": 1.32, "percentage": 13.24, "elapsed_time": "1:05:22", "remaining_time": "7:08:22"}
|
| 57 |
+
{"current_steps": 480, "total_steps": 3550, "loss": 0.8911, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.586826957346473e-05, "epoch": 1.35, "percentage": 13.52, "elapsed_time": "1:06:21", "remaining_time": "7:04:26"}
|
| 58 |
+
{"current_steps": 490, "total_steps": 3550, "loss": 0.9142, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.568933094987601e-05, "epoch": 1.38, "percentage": 13.8, "elapsed_time": "1:07:16", "remaining_time": "7:00:07"}
|
| 59 |
+
{"current_steps": 500, "total_steps": 3550, "loss": 0.9064, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.550677354557734e-05, "epoch": 1.41, "percentage": 14.08, "elapsed_time": "1:08:15", "remaining_time": "6:56:20"}
|
| 60 |
+
{"current_steps": 500, "total_steps": 3550, "loss": null, "eval_loss": 0.9910521507263184, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.41, "percentage": 14.08, "elapsed_time": "1:08:15", "remaining_time": "6:56:20"}
|
| 61 |
+
{"current_steps": 510, "total_steps": 3550, "loss": 0.9389, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.532061181985714e-05, "epoch": 1.44, "percentage": 14.37, "elapsed_time": "1:11:14", "remaining_time": "7:04:37"}
|
| 62 |
+
{"current_steps": 520, "total_steps": 3550, "loss": 0.8996, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.513086051748068e-05, "epoch": 1.46, "percentage": 14.65, "elapsed_time": "1:12:16", "remaining_time": "7:01:07"}
|
| 63 |
+
{"current_steps": 530, "total_steps": 3550, "loss": 0.929, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.493753466752235e-05, "epoch": 1.49, "percentage": 14.93, "elapsed_time": "1:13:14", "remaining_time": "6:57:19"}
|
| 64 |
+
{"current_steps": 540, "total_steps": 3550, "loss": 0.9307, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.474064958217523e-05, "epoch": 1.52, "percentage": 15.21, "elapsed_time": "1:14:12", "remaining_time": "6:53:38"}
|
| 65 |
+
{"current_steps": 550, "total_steps": 3550, "loss": 0.9238, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.454022085553828e-05, "epoch": 1.55, "percentage": 15.49, "elapsed_time": "1:15:12", "remaining_time": "6:50:12"}
|
| 66 |
+
{"current_steps": 550, "total_steps": 3550, "loss": null, "eval_loss": 0.9884344935417175, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.55, "percentage": 15.49, "elapsed_time": "1:15:12", "remaining_time": "6:50:12"}
|
| 67 |
+
{"current_steps": 560, "total_steps": 3550, "loss": 0.9161, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.433626436238128e-05, "epoch": 1.58, "percentage": 15.77, "elapsed_time": "1:18:16", "remaining_time": "6:57:56"}
|
| 68 |
+
{"current_steps": 570, "total_steps": 3550, "loss": 0.8969, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.412879625688742e-05, "epoch": 1.61, "percentage": 16.06, "elapsed_time": "1:19:18", "remaining_time": "6:54:40"}
|
| 69 |
+
{"current_steps": 580, "total_steps": 3550, "loss": 0.9393, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.391783297137391e-05, "epoch": 1.63, "percentage": 16.34, "elapsed_time": "1:20:21", "remaining_time": "6:51:29"}
|
| 70 |
+
{"current_steps": 590, "total_steps": 3550, "loss": 0.9139, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.370339121499038e-05, "epoch": 1.66, "percentage": 16.62, "elapsed_time": "1:21:24", "remaining_time": "6:48:25"}
|
| 71 |
+
{"current_steps": 600, "total_steps": 3550, "loss": 0.9053, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.348548797239551e-05, "epoch": 1.69, "percentage": 16.9, "elapsed_time": "1:22:23", "remaining_time": "6:45:04"}
|
| 72 |
+
{"current_steps": 600, "total_steps": 3550, "loss": null, "eval_loss": 0.9863258600234985, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.69, "percentage": 16.9, "elapsed_time": "1:22:23", "remaining_time": "6:45:04"}
|
| 73 |
+
{"current_steps": 610, "total_steps": 3550, "loss": 0.9176, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.326414050241175e-05, "epoch": 1.72, "percentage": 17.18, "elapsed_time": "1:25:27", "remaining_time": "6:51:54"}
|
| 74 |
+
{"current_steps": 620, "total_steps": 3550, "loss": 0.9378, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.30393663366584e-05, "epoch": 1.75, "percentage": 17.46, "elapsed_time": "1:26:23", "remaining_time": "6:48:16"}
|
| 75 |
+
{"current_steps": 630, "total_steps": 3550, "loss": 0.9158, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.28111832781629e-05, "epoch": 1.77, "percentage": 17.75, "elapsed_time": "1:27:20", "remaining_time": "6:44:47"}
|
| 76 |
+
{"current_steps": 640, "total_steps": 3550, "loss": 0.9385, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.257960939995093e-05, "epoch": 1.8, "percentage": 18.03, "elapsed_time": "1:28:18", "remaining_time": "6:41:30"}
|
| 77 |
+
{"current_steps": 650, "total_steps": 3550, "loss": 0.9066, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.234466304361487e-05, "epoch": 1.83, "percentage": 18.31, "elapsed_time": "1:29:20", "remaining_time": "6:38:34"}
|
| 78 |
+
{"current_steps": 650, "total_steps": 3550, "loss": null, "eval_loss": 0.9829334616661072, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.83, "percentage": 18.31, "elapsed_time": "1:29:20", "remaining_time": "6:38:34"}
|
| 79 |
+
{"current_steps": 660, "total_steps": 3550, "loss": 0.9185, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.2106362817861e-05, "epoch": 1.86, "percentage": 18.59, "elapsed_time": "1:32:21", "remaining_time": "6:44:22"}
|
| 80 |
+
{"current_steps": 670, "total_steps": 3550, "loss": 0.9425, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.186472759703579e-05, "epoch": 1.89, "percentage": 18.87, "elapsed_time": "1:33:18", "remaining_time": "6:41:06"}
|
| 81 |
+
{"current_steps": 680, "total_steps": 3550, "loss": 0.9143, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.161977651963081e-05, "epoch": 1.92, "percentage": 19.15, "elapsed_time": "1:34:21", "remaining_time": "6:38:14"}
|
| 82 |
+
{"current_steps": 690, "total_steps": 3550, "loss": 0.8889, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.137152898676698e-05, "epoch": 1.94, "percentage": 19.44, "elapsed_time": "1:35:26", "remaining_time": "6:35:36"}
|
| 83 |
+
{"current_steps": 700, "total_steps": 3550, "loss": 0.932, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.112000466065784e-05, "epoch": 1.97, "percentage": 19.72, "elapsed_time": "1:36:24", "remaining_time": "6:32:33"}
|
| 84 |
+
{"current_steps": 700, "total_steps": 3550, "loss": null, "eval_loss": 0.9802341461181641, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.97, "percentage": 19.72, "elapsed_time": "1:36:24", "remaining_time": "6:32:33"}
|
| 85 |
+
{"current_steps": 710, "total_steps": 3550, "loss": 0.9121, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.086522346305233e-05, "epoch": 2.0, "percentage": 20.0, "elapsed_time": "1:39:23", "remaining_time": "6:37:33"}
|
| 86 |
+
{"current_steps": 720, "total_steps": 3550, "loss": 0.7502, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.060720557365683e-05, "epoch": 2.03, "percentage": 20.28, "elapsed_time": "1:40:28", "remaining_time": "6:34:54"}
|
| 87 |
+
{"current_steps": 730, "total_steps": 3550, "loss": 0.7308, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.034597142853684e-05, "epoch": 2.06, "percentage": 20.56, "elapsed_time": "1:41:28", "remaining_time": "6:31:59"}
|
| 88 |
+
{"current_steps": 740, "total_steps": 3550, "loss": 0.7424, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.008154171849844e-05, "epoch": 2.08, "percentage": 20.85, "elapsed_time": "1:42:26", "remaining_time": "6:29:00"}
|
| 89 |
+
{"current_steps": 750, "total_steps": 3550, "loss": 0.7339, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.981393738744939e-05, "epoch": 2.11, "percentage": 21.13, "elapsed_time": "1:43:27", "remaining_time": "6:26:13"}
|
| 90 |
+
{"current_steps": 750, "total_steps": 3550, "loss": null, "eval_loss": 1.0370149612426758, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.11, "percentage": 21.13, "elapsed_time": "1:43:27", "remaining_time": "6:26:13"}
|
| 91 |
+
{"current_steps": 760, "total_steps": 3550, "loss": 0.704, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.954317963074034e-05, "epoch": 2.14, "percentage": 21.41, "elapsed_time": "1:46:29", "remaining_time": "6:30:54"}
|
| 92 |
+
{"current_steps": 770, "total_steps": 3550, "loss": 0.7179, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.926928989348612e-05, "epoch": 2.17, "percentage": 21.69, "elapsed_time": "1:47:30", "remaining_time": "6:28:10"}
|
| 93 |
+
{"current_steps": 780, "total_steps": 3550, "loss": 0.7156, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.899228986886709e-05, "epoch": 2.2, "percentage": 21.97, "elapsed_time": "1:48:24", "remaining_time": "6:25:00"}
|
| 94 |
+
{"current_steps": 790, "total_steps": 3550, "loss": 0.7577, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.871220149641101e-05, "epoch": 2.23, "percentage": 22.25, "elapsed_time": "1:49:27", "remaining_time": "6:22:24"}
|
| 95 |
+
{"current_steps": 800, "total_steps": 3550, "loss": 0.7678, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.842904696025542e-05, "epoch": 2.25, "percentage": 22.54, "elapsed_time": "1:50:31", "remaining_time": "6:19:54"}
|
| 96 |
+
{"current_steps": 800, "total_steps": 3550, "loss": null, "eval_loss": 1.032098650932312, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.25, "percentage": 22.54, "elapsed_time": "1:50:31", "remaining_time": "6:19:54"}
|
| 97 |
+
{"current_steps": 810, "total_steps": 3550, "loss": 0.7659, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.814284868739038e-05, "epoch": 2.28, "percentage": 22.82, "elapsed_time": "1:53:31", "remaining_time": "6:24:02"}
|
| 98 |
+
{"current_steps": 820, "total_steps": 3550, "loss": 0.7443, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.785362934588233e-05, "epoch": 2.31, "percentage": 23.1, "elapsed_time": "1:54:29", "remaining_time": "6:21:11"}
|
| 99 |
+
{"current_steps": 830, "total_steps": 3550, "loss": 0.7736, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.756141184307864e-05, "epoch": 2.34, "percentage": 23.38, "elapsed_time": "1:55:29", "remaining_time": "6:18:28"}
|
| 100 |
+
{"current_steps": 840, "total_steps": 3550, "loss": 0.7527, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.726621932379319e-05, "epoch": 2.37, "percentage": 23.66, "elapsed_time": "1:56:28", "remaining_time": "6:15:47"}
|
| 101 |
+
{"current_steps": 850, "total_steps": 3550, "loss": 0.7538, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.696807516847328e-05, "epoch": 2.39, "percentage": 23.94, "elapsed_time": "1:57:27", "remaining_time": "6:13:06"}
|
| 102 |
+
{"current_steps": 850, "total_steps": 3550, "loss": null, "eval_loss": 1.0239675045013428, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.39, "percentage": 23.94, "elapsed_time": "1:57:27", "remaining_time": "6:13:06"}
|
| 103 |
+
{"current_steps": 850, "total_steps": 3550, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.39, "percentage": 23.94, "elapsed_time": "1:57:27", "remaining_time": "6:13:06"}
|
| 104 |
+
{"current_steps": 63, "total_steps": 63, "loss": null, "eval_loss": 0.9910521507263184, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.39, "percentage": 100.0, "elapsed_time": "2:01:44", "remaining_time": "0:00:00"}
|
llama2_13b_peft/cnn_dailymail/trainer_state.json
ADDED
|
@@ -0,0 +1,761 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9910521507263184,
|
| 3 |
+
"best_model_checkpoint": "ckpt/llama2_13b_fuze15_no_sys/cnn_dailymail_no_sys/checkpoint-500",
|
| 4 |
+
"epoch": 2.3943661971830985,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 850,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"grad_norm": 0.47264495491981506,
|
| 14 |
+
"learning_rate": 5e-05,
|
| 15 |
+
"loss": 1.6246,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06,
|
| 20 |
+
"grad_norm": 0.349923312664032,
|
| 21 |
+
"learning_rate": 0.0001,
|
| 22 |
+
"loss": 1.3935,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.08,
|
| 27 |
+
"grad_norm": 0.3155190348625183,
|
| 28 |
+
"learning_rate": 9.999801989839055e-05,
|
| 29 |
+
"loss": 1.1048,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.11,
|
| 34 |
+
"grad_norm": 0.2674517333507538,
|
| 35 |
+
"learning_rate": 9.999207975039429e-05,
|
| 36 |
+
"loss": 1.0825,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.14,
|
| 41 |
+
"grad_norm": 0.2541864216327667,
|
| 42 |
+
"learning_rate": 9.998218002649506e-05,
|
| 43 |
+
"loss": 1.0297,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.14,
|
| 48 |
+
"eval_loss": 1.0375804901123047,
|
| 49 |
+
"eval_runtime": 122.2414,
|
| 50 |
+
"eval_samples_per_second": 12.271,
|
| 51 |
+
"eval_steps_per_second": 0.515,
|
| 52 |
+
"step": 50
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.17,
|
| 56 |
+
"grad_norm": 0.253811776638031,
|
| 57 |
+
"learning_rate": 9.996832151079127e-05,
|
| 58 |
+
"loss": 1.0166,
|
| 59 |
+
"step": 60
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.2,
|
| 63 |
+
"grad_norm": 0.2265736311674118,
|
| 64 |
+
"learning_rate": 9.995050530093367e-05,
|
| 65 |
+
"loss": 1.0402,
|
| 66 |
+
"step": 70
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.23,
|
| 70 |
+
"grad_norm": 0.37545114755630493,
|
| 71 |
+
"learning_rate": 9.992873280803849e-05,
|
| 72 |
+
"loss": 1.0182,
|
| 73 |
+
"step": 80
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.25,
|
| 77 |
+
"grad_norm": 0.2609192132949829,
|
| 78 |
+
"learning_rate": 9.990300575657565e-05,
|
| 79 |
+
"loss": 1.0422,
|
| 80 |
+
"step": 90
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.28,
|
| 84 |
+
"grad_norm": 0.28785914182662964,
|
| 85 |
+
"learning_rate": 9.987332618423221e-05,
|
| 86 |
+
"loss": 1.0043,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.28,
|
| 91 |
+
"eval_loss": 1.022628903388977,
|
| 92 |
+
"eval_runtime": 122.0796,
|
| 93 |
+
"eval_samples_per_second": 12.287,
|
| 94 |
+
"eval_steps_per_second": 0.516,
|
| 95 |
+
"step": 100
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.31,
|
| 99 |
+
"grad_norm": 0.26292186975479126,
|
| 100 |
+
"learning_rate": 9.983969644175091e-05,
|
| 101 |
+
"loss": 1.0384,
|
| 102 |
+
"step": 110
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.34,
|
| 106 |
+
"grad_norm": 0.2501932382583618,
|
| 107 |
+
"learning_rate": 9.980211919274407e-05,
|
| 108 |
+
"loss": 1.0326,
|
| 109 |
+
"step": 120
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.37,
|
| 113 |
+
"grad_norm": 0.2618853449821472,
|
| 114 |
+
"learning_rate": 9.976059741348251e-05,
|
| 115 |
+
"loss": 1.0133,
|
| 116 |
+
"step": 130
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.39,
|
| 120 |
+
"grad_norm": 0.27294716238975525,
|
| 121 |
+
"learning_rate": 9.971513439265991e-05,
|
| 122 |
+
"loss": 1.0129,
|
| 123 |
+
"step": 140
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.42,
|
| 127 |
+
"grad_norm": 0.27111512422561646,
|
| 128 |
+
"learning_rate": 9.96657337311323e-05,
|
| 129 |
+
"loss": 1.0241,
|
| 130 |
+
"step": 150
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.42,
|
| 134 |
+
"eval_loss": 1.0130971670150757,
|
| 135 |
+
"eval_runtime": 122.2912,
|
| 136 |
+
"eval_samples_per_second": 12.266,
|
| 137 |
+
"eval_steps_per_second": 0.515,
|
| 138 |
+
"step": 150
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.45,
|
| 142 |
+
"grad_norm": 0.30171358585357666,
|
| 143 |
+
"learning_rate": 9.961239934163289e-05,
|
| 144 |
+
"loss": 1.038,
|
| 145 |
+
"step": 160
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.48,
|
| 149 |
+
"grad_norm": 0.2853068709373474,
|
| 150 |
+
"learning_rate": 9.955513544846205e-05,
|
| 151 |
+
"loss": 1.0083,
|
| 152 |
+
"step": 170
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.51,
|
| 156 |
+
"grad_norm": 0.3023884892463684,
|
| 157 |
+
"learning_rate": 9.949394658715288e-05,
|
| 158 |
+
"loss": 0.9988,
|
| 159 |
+
"step": 180
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.54,
|
| 163 |
+
"grad_norm": 0.3108798563480377,
|
| 164 |
+
"learning_rate": 9.942883760411188e-05,
|
| 165 |
+
"loss": 1.0344,
|
| 166 |
+
"step": 190
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.56,
|
| 170 |
+
"grad_norm": 0.2736767530441284,
|
| 171 |
+
"learning_rate": 9.935981365623516e-05,
|
| 172 |
+
"loss": 1.0134,
|
| 173 |
+
"step": 200
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.56,
|
| 177 |
+
"eval_loss": 1.0082659721374512,
|
| 178 |
+
"eval_runtime": 122.0985,
|
| 179 |
+
"eval_samples_per_second": 12.285,
|
| 180 |
+
"eval_steps_per_second": 0.516,
|
| 181 |
+
"step": 200
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.59,
|
| 185 |
+
"grad_norm": 0.2804129123687744,
|
| 186 |
+
"learning_rate": 9.928688021049992e-05,
|
| 187 |
+
"loss": 1.0259,
|
| 188 |
+
"step": 210
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.62,
|
| 192 |
+
"grad_norm": 0.29631489515304565,
|
| 193 |
+
"learning_rate": 9.921004304353147e-05,
|
| 194 |
+
"loss": 1.0102,
|
| 195 |
+
"step": 220
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.65,
|
| 199 |
+
"grad_norm": 0.28678563237190247,
|
| 200 |
+
"learning_rate": 9.912930824114576e-05,
|
| 201 |
+
"loss": 0.9969,
|
| 202 |
+
"step": 230
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.68,
|
| 206 |
+
"grad_norm": 0.35824358463287354,
|
| 207 |
+
"learning_rate": 9.904468219786727e-05,
|
| 208 |
+
"loss": 0.9626,
|
| 209 |
+
"step": 240
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.7,
|
| 213 |
+
"grad_norm": 0.26744136214256287,
|
| 214 |
+
"learning_rate": 9.895617161642256e-05,
|
| 215 |
+
"loss": 1.0284,
|
| 216 |
+
"step": 250
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.7,
|
| 220 |
+
"eval_loss": 1.0040661096572876,
|
| 221 |
+
"eval_runtime": 122.3546,
|
| 222 |
+
"eval_samples_per_second": 12.259,
|
| 223 |
+
"eval_steps_per_second": 0.515,
|
| 224 |
+
"step": 250
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.73,
|
| 228 |
+
"grad_norm": 0.29996350407600403,
|
| 229 |
+
"learning_rate": 9.886378350720943e-05,
|
| 230 |
+
"loss": 0.9762,
|
| 231 |
+
"step": 260
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.76,
|
| 235 |
+
"grad_norm": 0.2882774770259857,
|
| 236 |
+
"learning_rate": 9.876752518774166e-05,
|
| 237 |
+
"loss": 1.0387,
|
| 238 |
+
"step": 270
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.79,
|
| 242 |
+
"grad_norm": 0.3027604818344116,
|
| 243 |
+
"learning_rate": 9.866740428206934e-05,
|
| 244 |
+
"loss": 0.9725,
|
| 245 |
+
"step": 280
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.82,
|
| 249 |
+
"grad_norm": 0.29195544123649597,
|
| 250 |
+
"learning_rate": 9.856342872017515e-05,
|
| 251 |
+
"loss": 1.0357,
|
| 252 |
+
"step": 290
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.85,
|
| 256 |
+
"grad_norm": 0.3052995800971985,
|
| 257 |
+
"learning_rate": 9.845560673734617e-05,
|
| 258 |
+
"loss": 1.0126,
|
| 259 |
+
"step": 300
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.85,
|
| 263 |
+
"eval_loss": 0.9973611831665039,
|
| 264 |
+
"eval_runtime": 122.3104,
|
| 265 |
+
"eval_samples_per_second": 12.264,
|
| 266 |
+
"eval_steps_per_second": 0.515,
|
| 267 |
+
"step": 300
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.87,
|
| 271 |
+
"grad_norm": 0.316039115190506,
|
| 272 |
+
"learning_rate": 9.834394687352169e-05,
|
| 273 |
+
"loss": 0.9815,
|
| 274 |
+
"step": 310
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.9,
|
| 278 |
+
"grad_norm": 0.3242320120334625,
|
| 279 |
+
"learning_rate": 9.822845797261675e-05,
|
| 280 |
+
"loss": 0.9906,
|
| 281 |
+
"step": 320
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.93,
|
| 285 |
+
"grad_norm": 0.29159247875213623,
|
| 286 |
+
"learning_rate": 9.810914918182169e-05,
|
| 287 |
+
"loss": 1.0014,
|
| 288 |
+
"step": 330
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.96,
|
| 292 |
+
"grad_norm": 0.33583688735961914,
|
| 293 |
+
"learning_rate": 9.798602995087763e-05,
|
| 294 |
+
"loss": 0.9813,
|
| 295 |
+
"step": 340
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.99,
|
| 299 |
+
"grad_norm": 0.29560449719429016,
|
| 300 |
+
"learning_rate": 9.785911003132811e-05,
|
| 301 |
+
"loss": 0.9779,
|
| 302 |
+
"step": 350
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.99,
|
| 306 |
+
"eval_loss": 0.9921852350234985,
|
| 307 |
+
"eval_runtime": 122.2577,
|
| 308 |
+
"eval_samples_per_second": 12.269,
|
| 309 |
+
"eval_steps_per_second": 0.515,
|
| 310 |
+
"step": 350
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.01,
|
| 314 |
+
"grad_norm": 0.3149906098842621,
|
| 315 |
+
"learning_rate": 9.772839947574657e-05,
|
| 316 |
+
"loss": 0.9616,
|
| 317 |
+
"step": 360
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.04,
|
| 321 |
+
"grad_norm": 0.3386111259460449,
|
| 322 |
+
"learning_rate": 9.75939086369403e-05,
|
| 323 |
+
"loss": 0.9413,
|
| 324 |
+
"step": 370
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.07,
|
| 328 |
+
"grad_norm": 0.39352336525917053,
|
| 329 |
+
"learning_rate": 9.745564816713034e-05,
|
| 330 |
+
"loss": 0.9512,
|
| 331 |
+
"step": 380
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.1,
|
| 335 |
+
"grad_norm": 0.3844590187072754,
|
| 336 |
+
"learning_rate": 9.731362901710783e-05,
|
| 337 |
+
"loss": 0.935,
|
| 338 |
+
"step": 390
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.13,
|
| 342 |
+
"grad_norm": 0.4934450387954712,
|
| 343 |
+
"learning_rate": 9.71678624353667e-05,
|
| 344 |
+
"loss": 0.9239,
|
| 345 |
+
"step": 400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.13,
|
| 349 |
+
"eval_loss": 0.9983939528465271,
|
| 350 |
+
"eval_runtime": 122.3109,
|
| 351 |
+
"eval_samples_per_second": 12.264,
|
| 352 |
+
"eval_steps_per_second": 0.515,
|
| 353 |
+
"step": 400
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.15,
|
| 357 |
+
"grad_norm": 0.4922298192977905,
|
| 358 |
+
"learning_rate": 9.701835996721265e-05,
|
| 359 |
+
"loss": 0.9265,
|
| 360 |
+
"step": 410
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.18,
|
| 364 |
+
"grad_norm": 0.5618098974227905,
|
| 365 |
+
"learning_rate": 9.686513345384882e-05,
|
| 366 |
+
"loss": 0.9361,
|
| 367 |
+
"step": 420
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.21,
|
| 371 |
+
"grad_norm": 0.5378989577293396,
|
| 372 |
+
"learning_rate": 9.67081950314378e-05,
|
| 373 |
+
"loss": 0.9043,
|
| 374 |
+
"step": 430
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.24,
|
| 378 |
+
"grad_norm": 0.5351877808570862,
|
| 379 |
+
"learning_rate": 9.654755713014052e-05,
|
| 380 |
+
"loss": 0.9006,
|
| 381 |
+
"step": 440
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.27,
|
| 385 |
+
"grad_norm": 0.6081934571266174,
|
| 386 |
+
"learning_rate": 9.638323247313166e-05,
|
| 387 |
+
"loss": 0.9456,
|
| 388 |
+
"step": 450
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.27,
|
| 392 |
+
"eval_loss": 0.9970971345901489,
|
| 393 |
+
"eval_runtime": 122.1402,
|
| 394 |
+
"eval_samples_per_second": 12.281,
|
| 395 |
+
"eval_steps_per_second": 0.516,
|
| 396 |
+
"step": 450
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.3,
|
| 400 |
+
"grad_norm": 0.5924888253211975,
|
| 401 |
+
"learning_rate": 9.621523407559193e-05,
|
| 402 |
+
"loss": 0.8814,
|
| 403 |
+
"step": 460
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 1.32,
|
| 407 |
+
"grad_norm": 0.5622063279151917,
|
| 408 |
+
"learning_rate": 9.604357524367722e-05,
|
| 409 |
+
"loss": 0.9459,
|
| 410 |
+
"step": 470
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.35,
|
| 414 |
+
"grad_norm": 0.6370586156845093,
|
| 415 |
+
"learning_rate": 9.586826957346473e-05,
|
| 416 |
+
"loss": 0.8911,
|
| 417 |
+
"step": 480
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.38,
|
| 421 |
+
"grad_norm": 0.5782639384269714,
|
| 422 |
+
"learning_rate": 9.568933094987601e-05,
|
| 423 |
+
"loss": 0.9142,
|
| 424 |
+
"step": 490
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 1.41,
|
| 428 |
+
"grad_norm": 0.5522053837776184,
|
| 429 |
+
"learning_rate": 9.550677354557734e-05,
|
| 430 |
+
"loss": 0.9064,
|
| 431 |
+
"step": 500
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 1.41,
|
| 435 |
+
"eval_loss": 0.9910521507263184,
|
| 436 |
+
"eval_runtime": 122.2738,
|
| 437 |
+
"eval_samples_per_second": 12.268,
|
| 438 |
+
"eval_steps_per_second": 0.515,
|
| 439 |
+
"step": 500
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 1.44,
|
| 443 |
+
"grad_norm": 0.5490506887435913,
|
| 444 |
+
"learning_rate": 9.532061181985714e-05,
|
| 445 |
+
"loss": 0.9389,
|
| 446 |
+
"step": 510
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.46,
|
| 450 |
+
"grad_norm": 0.6112892627716064,
|
| 451 |
+
"learning_rate": 9.513086051748068e-05,
|
| 452 |
+
"loss": 0.8996,
|
| 453 |
+
"step": 520
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.49,
|
| 457 |
+
"grad_norm": 0.6104739308357239,
|
| 458 |
+
"learning_rate": 9.493753466752235e-05,
|
| 459 |
+
"loss": 0.929,
|
| 460 |
+
"step": 530
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 1.52,
|
| 464 |
+
"grad_norm": 0.5805090665817261,
|
| 465 |
+
"learning_rate": 9.474064958217523e-05,
|
| 466 |
+
"loss": 0.9307,
|
| 467 |
+
"step": 540
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 1.55,
|
| 471 |
+
"grad_norm": 0.5656021237373352,
|
| 472 |
+
"learning_rate": 9.454022085553828e-05,
|
| 473 |
+
"loss": 0.9238,
|
| 474 |
+
"step": 550
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.55,
|
| 478 |
+
"eval_loss": 0.9884344935417175,
|
| 479 |
+
"eval_runtime": 122.2227,
|
| 480 |
+
"eval_samples_per_second": 12.273,
|
| 481 |
+
"eval_steps_per_second": 0.515,
|
| 482 |
+
"step": 550
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 1.58,
|
| 486 |
+
"grad_norm": 0.6901003122329712,
|
| 487 |
+
"learning_rate": 9.433626436238128e-05,
|
| 488 |
+
"loss": 0.9161,
|
| 489 |
+
"step": 560
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.61,
|
| 493 |
+
"grad_norm": 0.5691778063774109,
|
| 494 |
+
"learning_rate": 9.412879625688742e-05,
|
| 495 |
+
"loss": 0.8969,
|
| 496 |
+
"step": 570
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 1.63,
|
| 500 |
+
"grad_norm": 0.5715755820274353,
|
| 501 |
+
"learning_rate": 9.391783297137391e-05,
|
| 502 |
+
"loss": 0.9393,
|
| 503 |
+
"step": 580
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 1.66,
|
| 507 |
+
"grad_norm": 0.616493284702301,
|
| 508 |
+
"learning_rate": 9.370339121499038e-05,
|
| 509 |
+
"loss": 0.9139,
|
| 510 |
+
"step": 590
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 1.69,
|
| 514 |
+
"grad_norm": 0.6331434845924377,
|
| 515 |
+
"learning_rate": 9.348548797239551e-05,
|
| 516 |
+
"loss": 0.9053,
|
| 517 |
+
"step": 600
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 1.69,
|
| 521 |
+
"eval_loss": 0.9863258600234985,
|
| 522 |
+
"eval_runtime": 122.2709,
|
| 523 |
+
"eval_samples_per_second": 12.268,
|
| 524 |
+
"eval_steps_per_second": 0.515,
|
| 525 |
+
"step": 600
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 1.72,
|
| 529 |
+
"grad_norm": 0.5978617668151855,
|
| 530 |
+
"learning_rate": 9.326414050241175e-05,
|
| 531 |
+
"loss": 0.9176,
|
| 532 |
+
"step": 610
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 1.75,
|
| 536 |
+
"grad_norm": 0.6102743744850159,
|
| 537 |
+
"learning_rate": 9.30393663366584e-05,
|
| 538 |
+
"loss": 0.9378,
|
| 539 |
+
"step": 620
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 1.77,
|
| 543 |
+
"grad_norm": 0.6495214104652405,
|
| 544 |
+
"learning_rate": 9.28111832781629e-05,
|
| 545 |
+
"loss": 0.9158,
|
| 546 |
+
"step": 630
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 1.8,
|
| 550 |
+
"grad_norm": 0.6791807413101196,
|
| 551 |
+
"learning_rate": 9.257960939995093e-05,
|
| 552 |
+
"loss": 0.9385,
|
| 553 |
+
"step": 640
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 1.83,
|
| 557 |
+
"grad_norm": 0.6373294591903687,
|
| 558 |
+
"learning_rate": 9.234466304361487e-05,
|
| 559 |
+
"loss": 0.9066,
|
| 560 |
+
"step": 650
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.83,
|
| 564 |
+
"eval_loss": 0.9829334616661072,
|
| 565 |
+
"eval_runtime": 122.4062,
|
| 566 |
+
"eval_samples_per_second": 12.254,
|
| 567 |
+
"eval_steps_per_second": 0.515,
|
| 568 |
+
"step": 650
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.86,
|
| 572 |
+
"grad_norm": 0.6747245788574219,
|
| 573 |
+
"learning_rate": 9.2106362817861e-05,
|
| 574 |
+
"loss": 0.9185,
|
| 575 |
+
"step": 660
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 1.89,
|
| 579 |
+
"grad_norm": 0.6707281470298767,
|
| 580 |
+
"learning_rate": 9.186472759703579e-05,
|
| 581 |
+
"loss": 0.9425,
|
| 582 |
+
"step": 670
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 1.92,
|
| 586 |
+
"grad_norm": 0.6029950976371765,
|
| 587 |
+
"learning_rate": 9.161977651963081e-05,
|
| 588 |
+
"loss": 0.9143,
|
| 589 |
+
"step": 680
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 1.94,
|
| 593 |
+
"grad_norm": 0.6832878589630127,
|
| 594 |
+
"learning_rate": 9.137152898676698e-05,
|
| 595 |
+
"loss": 0.8889,
|
| 596 |
+
"step": 690
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 1.97,
|
| 600 |
+
"grad_norm": 0.6552910804748535,
|
| 601 |
+
"learning_rate": 9.112000466065784e-05,
|
| 602 |
+
"loss": 0.932,
|
| 603 |
+
"step": 700
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.97,
|
| 607 |
+
"eval_loss": 0.9802341461181641,
|
| 608 |
+
"eval_runtime": 122.2282,
|
| 609 |
+
"eval_samples_per_second": 12.272,
|
| 610 |
+
"eval_steps_per_second": 0.515,
|
| 611 |
+
"step": 700
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 2.0,
|
| 615 |
+
"grad_norm": 0.5472111701965332,
|
| 616 |
+
"learning_rate": 9.086522346305233e-05,
|
| 617 |
+
"loss": 0.9121,
|
| 618 |
+
"step": 710
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 2.03,
|
| 622 |
+
"grad_norm": 0.8331531286239624,
|
| 623 |
+
"learning_rate": 9.060720557365683e-05,
|
| 624 |
+
"loss": 0.7502,
|
| 625 |
+
"step": 720
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 2.06,
|
| 629 |
+
"grad_norm": 0.7888972163200378,
|
| 630 |
+
"learning_rate": 9.034597142853684e-05,
|
| 631 |
+
"loss": 0.7308,
|
| 632 |
+
"step": 730
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 2.08,
|
| 636 |
+
"grad_norm": 1.116204023361206,
|
| 637 |
+
"learning_rate": 9.008154171849844e-05,
|
| 638 |
+
"loss": 0.7424,
|
| 639 |
+
"step": 740
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 2.11,
|
| 643 |
+
"grad_norm": 1.0302730798721313,
|
| 644 |
+
"learning_rate": 8.981393738744939e-05,
|
| 645 |
+
"loss": 0.7339,
|
| 646 |
+
"step": 750
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 2.11,
|
| 650 |
+
"eval_loss": 1.0370149612426758,
|
| 651 |
+
"eval_runtime": 122.3036,
|
| 652 |
+
"eval_samples_per_second": 12.265,
|
| 653 |
+
"eval_steps_per_second": 0.515,
|
| 654 |
+
"step": 750
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 2.14,
|
| 658 |
+
"grad_norm": 0.8039250373840332,
|
| 659 |
+
"learning_rate": 8.954317963074034e-05,
|
| 660 |
+
"loss": 0.704,
|
| 661 |
+
"step": 760
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 2.17,
|
| 665 |
+
"grad_norm": 0.9725390076637268,
|
| 666 |
+
"learning_rate": 8.926928989348612e-05,
|
| 667 |
+
"loss": 0.7179,
|
| 668 |
+
"step": 770
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 2.2,
|
| 672 |
+
"grad_norm": 1.0024648904800415,
|
| 673 |
+
"learning_rate": 8.899228986886709e-05,
|
| 674 |
+
"loss": 0.7156,
|
| 675 |
+
"step": 780
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 2.23,
|
| 679 |
+
"grad_norm": 1.0251855850219727,
|
| 680 |
+
"learning_rate": 8.871220149641101e-05,
|
| 681 |
+
"loss": 0.7577,
|
| 682 |
+
"step": 790
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 2.25,
|
| 686 |
+
"grad_norm": 1.0738469362258911,
|
| 687 |
+
"learning_rate": 8.842904696025542e-05,
|
| 688 |
+
"loss": 0.7678,
|
| 689 |
+
"step": 800
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 2.25,
|
| 693 |
+
"eval_loss": 1.032098650932312,
|
| 694 |
+
"eval_runtime": 122.3453,
|
| 695 |
+
"eval_samples_per_second": 12.26,
|
| 696 |
+
"eval_steps_per_second": 0.515,
|
| 697 |
+
"step": 800
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.28,
|
| 701 |
+
"grad_norm": 0.9893040060997009,
|
| 702 |
+
"learning_rate": 8.814284868739038e-05,
|
| 703 |
+
"loss": 0.7659,
|
| 704 |
+
"step": 810
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.31,
|
| 708 |
+
"grad_norm": 1.0190677642822266,
|
| 709 |
+
"learning_rate": 8.785362934588233e-05,
|
| 710 |
+
"loss": 0.7443,
|
| 711 |
+
"step": 820
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.34,
|
| 715 |
+
"grad_norm": 0.9342036247253418,
|
| 716 |
+
"learning_rate": 8.756141184307864e-05,
|
| 717 |
+
"loss": 0.7736,
|
| 718 |
+
"step": 830
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.37,
|
| 722 |
+
"grad_norm": 0.9595410823822021,
|
| 723 |
+
"learning_rate": 8.726621932379319e-05,
|
| 724 |
+
"loss": 0.7527,
|
| 725 |
+
"step": 840
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 2.39,
|
| 729 |
+
"grad_norm": 1.057177186012268,
|
| 730 |
+
"learning_rate": 8.696807516847328e-05,
|
| 731 |
+
"loss": 0.7538,
|
| 732 |
+
"step": 850
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 2.39,
|
| 736 |
+
"eval_loss": 1.0239675045013428,
|
| 737 |
+
"eval_runtime": 122.2319,
|
| 738 |
+
"eval_samples_per_second": 12.272,
|
| 739 |
+
"eval_steps_per_second": 0.515,
|
| 740 |
+
"step": 850
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 2.39,
|
| 744 |
+
"step": 850,
|
| 745 |
+
"total_flos": 2.7031368943670395e+18,
|
| 746 |
+
"train_loss": 0.943028081445133,
|
| 747 |
+
"train_runtime": 7174.3764,
|
| 748 |
+
"train_samples_per_second": 11.848,
|
| 749 |
+
"train_steps_per_second": 0.495
|
| 750 |
+
}
|
| 751 |
+
],
|
| 752 |
+
"logging_steps": 10,
|
| 753 |
+
"max_steps": 3550,
|
| 754 |
+
"num_input_tokens_seen": 0,
|
| 755 |
+
"num_train_epochs": 10,
|
| 756 |
+
"save_steps": 500,
|
| 757 |
+
"total_flos": 2.7031368943670395e+18,
|
| 758 |
+
"train_batch_size": 8,
|
| 759 |
+
"trial_name": null,
|
| 760 |
+
"trial_params": null
|
| 761 |
+
}
|
llama2_13b_peft/cnn_dailymail/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98b719af2fd3d7324911d57e3cefb5f31c9c0c5b7c26baed7a0a99cadff76d55
|
| 3 |
+
size 5112
|
llama2_13b_peft/cnn_dailymail/training_eval_loss.png
ADDED
|
llama2_13b_peft/cnn_dailymail/training_loss.png
ADDED
|
llama2_13b_peft/contextual_parametric_knowledge_conflicts/README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- llama-factory
|
| 6 |
+
- lora
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: /data1/model/llama2/meta-llama/Llama2-13b
|
| 9 |
+
model-index:
|
| 10 |
+
- name: contextual_parametric_knowledge_conflicts_no_sys
|
| 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 |
+
# contextual_parametric_knowledge_conflicts_no_sys
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [/data1/model/llama2/meta-llama/Llama2-13b](https://huggingface.co//data1/model/llama2/meta-llama/Llama2-13b) on the contextual_parametric_knowledge_conflicts_no_sys dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.0000
|
| 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: 0.0001
|
| 41 |
+
- train_batch_size: 8
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- num_devices: 4
|
| 46 |
+
- total_train_batch_size: 32
|
| 47 |
+
- total_eval_batch_size: 32
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: cosine
|
| 50 |
+
- lr_scheduler_warmup_steps: 20
|
| 51 |
+
- num_epochs: 10.0
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 57 |
+
| 0.0098 | 0.13 | 50 | 0.0022 |
|
| 58 |
+
| 0.0023 | 0.27 | 100 | 0.0005 |
|
| 59 |
+
| 0.0002 | 0.4 | 150 | 0.0001 |
|
| 60 |
+
| 0.0 | 0.54 | 200 | 0.0000 |
|
| 61 |
+
| 0.0 | 0.67 | 250 | 0.0000 |
|
| 62 |
+
| 0.0006 | 0.8 | 300 | 0.0001 |
|
| 63 |
+
| 0.0 | 0.94 | 350 | 0.0000 |
|
| 64 |
+
| 0.0 | 1.07 | 400 | 0.0001 |
|
| 65 |
+
| 0.0 | 1.21 | 450 | 0.0000 |
|
| 66 |
+
| 0.0 | 1.34 | 500 | 0.0000 |
|
| 67 |
+
| 0.0 | 1.47 | 550 | 0.0000 |
|
| 68 |
+
| 0.0 | 1.61 | 600 | 0.0000 |
|
| 69 |
+
| 0.0 | 1.74 | 650 | 0.0000 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- PEFT 0.9.0
|
| 75 |
+
- Transformers 4.38.2
|
| 76 |
+
- Pytorch 2.2.1
|
| 77 |
+
- Datasets 2.18.0
|
| 78 |
+
- Tokenizers 0.15.2
|
llama2_13b_peft/contextual_parametric_knowledge_conflicts/adapter_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "/data1/model/llama2/meta-llama/Llama2-13b",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 16,
|
| 13 |
+
"lora_dropout": 0.0,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 8,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"up_proj",
|
| 23 |
+
"q_proj",
|
| 24 |
+
"down_proj",
|
| 25 |
+
"gate_proj",
|
| 26 |
+
"o_proj",
|
| 27 |
+
"v_proj",
|
| 28 |
+
"k_proj"
|
| 29 |
+
],
|
| 30 |
+
"task_type": "CAUSAL_LM",
|
| 31 |
+
"use_dora": false,
|
| 32 |
+
"use_rslora": false
|
| 33 |
+
}
|
llama2_13b_peft/contextual_parametric_knowledge_conflicts/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ff9f6f4864adea593d264b78cd225dd6a9a69e45ec9624910470fe96c5b9aa0
|
| 3 |
+
size 125248064
|
llama2_13b_peft/contextual_parametric_knowledge_conflicts/all_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.74,
|
| 3 |
+
"eval_loss": 4.564080882119015e-05,
|
| 4 |
+
"eval_runtime": 36.4056,
|
| 5 |
+
"eval_samples_per_second": 57.793,
|
| 6 |
+
"eval_steps_per_second": 1.813,
|
| 7 |
+
"train_loss": 0.0704553289199248,
|
| 8 |
+
"train_runtime": 1752.1107,
|
| 9 |
+
"train_samples_per_second": 68.027,
|
| 10 |
+
"train_steps_per_second": 2.129
|
| 11 |
+
}
|
llama2_13b_peft/contextual_parametric_knowledge_conflicts/eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.74,
|
| 3 |
+
"eval_loss": 4.564080882119015e-05,
|
| 4 |
+
"eval_runtime": 36.4056,
|
| 5 |
+
"eval_samples_per_second": 57.793,
|
| 6 |
+
"eval_steps_per_second": 1.813
|
| 7 |
+
}
|
llama2_13b_peft/contextual_parametric_knowledge_conflicts/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
llama2_13b_peft/contextual_parametric_knowledge_conflicts/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
llama2_13b_peft/contextual_parametric_knowledge_conflicts/tokenizer_config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content + '\\n' }}{% endif %}{% endfor %}",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"legacy": true,
|
| 36 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
+
"pad_token": "</s>",
|
| 38 |
+
"padding_side": "right",
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"spaces_between_special_tokens": false,
|
| 41 |
+
"split_special_tokens": false,
|
| 42 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 43 |
+
"unk_token": "<unk>",
|
| 44 |
+
"use_default_system_prompt": false
|
| 45 |
+
}
|