Bram Vanroy
commited on
Commit
•
517adfd
1
Parent(s):
d9d7ad2
init adapters
Browse files- README.md +79 -0
- adapter_config.json +22 -0
- adapter_model.bin +3 -0
- all_results.json +14 -0
- eval_results.json +9 -0
- info.txt +4 -0
- special_tokens_map.json +17 -0
- tokenizer.json +0 -0
- tokenizer_config.json +7 -0
- train_results.json +8 -0
- trainer_state.json +2073 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- BramVanroy/alpaca-dolly-dutch
|
| 7 |
+
model-index:
|
| 8 |
+
- name: 2e-4lr+512tbs+5ep+32a+4r-v2
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# 2e-4lr+512tbs+5ep+32a+4r-v2
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [tiiuae/falcon-40b](https://huggingface.co/tiiuae/falcon-40b) on the BramVanroy/alpaca-dolly-dutch dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.9154
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 0.0002
|
| 39 |
+
- train_batch_size: 8
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- num_devices: 16
|
| 44 |
+
- gradient_accumulation_steps: 4
|
| 45 |
+
- total_train_batch_size: 512
|
| 46 |
+
- total_eval_batch_size: 128
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- lr_scheduler_warmup_steps: 150
|
| 50 |
+
- num_epochs: 5
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 56 |
+
| 1.1656 | 0.16 | 20 | 1.0107 |
|
| 57 |
+
| 0.9778 | 0.32 | 40 | 0.9711 |
|
| 58 |
+
| 1.0424 | 0.49 | 60 | 0.9512 |
|
| 59 |
+
| 0.9858 | 0.65 | 80 | 0.9415 |
|
| 60 |
+
| 0.9457 | 0.81 | 100 | 0.9341 |
|
| 61 |
+
| 1.0584 | 0.97 | 120 | 0.9277 |
|
| 62 |
+
| 1.0284 | 1.14 | 140 | 0.9372 |
|
| 63 |
+
| 0.8781 | 1.3 | 160 | 0.9295 |
|
| 64 |
+
| 0.9531 | 1.46 | 180 | 0.9267 |
|
| 65 |
+
| 0.9496 | 1.62 | 200 | 0.9226 |
|
| 66 |
+
| 0.9178 | 1.78 | 220 | 0.9192 |
|
| 67 |
+
| 1.0763 | 1.95 | 240 | 0.9154 |
|
| 68 |
+
| 0.9561 | 2.11 | 260 | 0.9423 |
|
| 69 |
+
| 0.7991 | 2.27 | 280 | 0.9368 |
|
| 70 |
+
| 0.8503 | 2.43 | 300 | 0.9363 |
|
| 71 |
+
| 0.8749 | 2.6 | 320 | 0.9299 |
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
### Framework versions
|
| 75 |
+
|
| 76 |
+
- Transformers 4.30.1
|
| 77 |
+
- Pytorch 2.0.1+cu117
|
| 78 |
+
- Datasets 2.13.1
|
| 79 |
+
- Tokenizers 0.13.3
|
adapter_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "tiiuae/falcon-40b",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"fan_in_fan_out": false,
|
| 5 |
+
"inference_mode": true,
|
| 6 |
+
"init_lora_weights": true,
|
| 7 |
+
"layers_pattern": null,
|
| 8 |
+
"layers_to_transform": null,
|
| 9 |
+
"lora_alpha": 32,
|
| 10 |
+
"lora_dropout": 0.1,
|
| 11 |
+
"modules_to_save": null,
|
| 12 |
+
"peft_type": "LORA",
|
| 13 |
+
"r": 4,
|
| 14 |
+
"revision": null,
|
| 15 |
+
"target_modules": [
|
| 16 |
+
"query_key_value",
|
| 17 |
+
"dense",
|
| 18 |
+
"dense_h_to_4h",
|
| 19 |
+
"dense_4h_to_h"
|
| 20 |
+
],
|
| 21 |
+
"task_type": "CAUSAL_LM"
|
| 22 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:987670579cbb7749ef24514721dab6a9e950722b238123ab455708dd05931a72
|
| 3 |
+
size 55621053
|
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.6,
|
| 3 |
+
"eval_loss": 0.9153895974159241,
|
| 4 |
+
"eval_runtime": 108.0996,
|
| 5 |
+
"eval_samples": 3332,
|
| 6 |
+
"eval_samples_per_second": 30.823,
|
| 7 |
+
"eval_steps_per_second": 0.25,
|
| 8 |
+
"perplexity": 2.497748178603731,
|
| 9 |
+
"train_loss": 0.9615403175354004,
|
| 10 |
+
"train_runtime": 23129.1803,
|
| 11 |
+
"train_samples": 63101,
|
| 12 |
+
"train_samples_per_second": 13.641,
|
| 13 |
+
"train_steps_per_second": 0.027
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.6,
|
| 3 |
+
"eval_loss": 0.9153895974159241,
|
| 4 |
+
"eval_runtime": 108.0996,
|
| 5 |
+
"eval_samples": 3332,
|
| 6 |
+
"eval_samples_per_second": 30.823,
|
| 7 |
+
"eval_steps_per_second": 0.25,
|
| 8 |
+
"perplexity": 2.497748178603731
|
| 9 |
+
}
|
info.txt
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
CMD: -n 4 -g 4 -o falcon-40b-ft-alpaca-dolly-dutch/2e-4lr+512tbs+5ep+32a+4r-v2 -t 80 -p falcon-40b-ft-alpaca-dolly-dutch -e --learning_rate 2e-4 --model_name_or_path tiiuae/falcon-40b --per_device_train_batch_size 8 --per_device_eval_batch_size 8 --gradient_accumulation_steps 4 --save_total_limit 3 --lora_alpha 32 --lora_r 4 -i Hyperparameters were taken from LoRA paper. See Table 11.
|
| 2 |
+
|
| 3 |
+
INFO: Hyperparameters were taken from LoRA paper. See Table 11.
|
| 4 |
+
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
">>TITLE<<",
|
| 4 |
+
">>ABSTRACT<<",
|
| 5 |
+
">>INTRODUCTION<<",
|
| 6 |
+
">>SUMMARY<<",
|
| 7 |
+
">>COMMENT<<",
|
| 8 |
+
">>ANSWER<<",
|
| 9 |
+
">>QUESTION<<",
|
| 10 |
+
">>DOMAIN<<",
|
| 11 |
+
">>PREFIX<<",
|
| 12 |
+
">>SUFFIX<<",
|
| 13 |
+
">>MIDDLE<<"
|
| 14 |
+
],
|
| 15 |
+
"eos_token": "<|endoftext|>",
|
| 16 |
+
"pad_token": "<|endoftext|>"
|
| 17 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
+
"eos_token": "<|endoftext|>",
|
| 5 |
+
"model_max_length": 2048,
|
| 6 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.6,
|
| 3 |
+
"train_loss": 0.9615403175354004,
|
| 4 |
+
"train_runtime": 23129.1803,
|
| 5 |
+
"train_samples": 63101,
|
| 6 |
+
"train_samples_per_second": 13.641,
|
| 7 |
+
"train_steps_per_second": 0.027
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2073 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9153895974159241,
|
| 3 |
+
"best_model_checkpoint": "/dodrio/scratch/projects/2023_005/llm-finetuning/instruct-tuning/results/falcon-40b-ft-alpaca-dolly-dutch/2e-4lr+512tbs+5ep+32a+4r-v2/checkpoint-240",
|
| 4 |
+
"epoch": 2.5963488843813387,
|
| 5 |
+
"global_step": 320,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.01,
|
| 12 |
+
"learning_rate": 0.0,
|
| 13 |
+
"loss": 1.3493,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.02,
|
| 18 |
+
"learning_rate": 2.7667037805630792e-05,
|
| 19 |
+
"loss": 1.1896,
|
| 20 |
+
"step": 2
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.02,
|
| 24 |
+
"learning_rate": 4.3851217427959356e-05,
|
| 25 |
+
"loss": 1.1459,
|
| 26 |
+
"step": 3
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.03,
|
| 30 |
+
"learning_rate": 5.5334075611261585e-05,
|
| 31 |
+
"loss": 1.2258,
|
| 32 |
+
"step": 4
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.04,
|
| 36 |
+
"learning_rate": 6.424087238320494e-05,
|
| 37 |
+
"loss": 1.246,
|
| 38 |
+
"step": 5
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.05,
|
| 42 |
+
"learning_rate": 7.151825523359015e-05,
|
| 43 |
+
"loss": 1.1355,
|
| 44 |
+
"step": 6
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.06,
|
| 48 |
+
"learning_rate": 7.767119476239142e-05,
|
| 49 |
+
"loss": 1.2275,
|
| 50 |
+
"step": 7
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.06,
|
| 54 |
+
"learning_rate": 8.300111341689237e-05,
|
| 55 |
+
"loss": 1.137,
|
| 56 |
+
"step": 8
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.07,
|
| 60 |
+
"learning_rate": 8.770243485591871e-05,
|
| 61 |
+
"loss": 1.103,
|
| 62 |
+
"step": 9
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.08,
|
| 66 |
+
"learning_rate": 9.190791018883575e-05,
|
| 67 |
+
"loss": 1.1777,
|
| 68 |
+
"step": 10
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.09,
|
| 72 |
+
"learning_rate": 9.571222537883264e-05,
|
| 73 |
+
"loss": 1.1354,
|
| 74 |
+
"step": 11
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.1,
|
| 78 |
+
"learning_rate": 9.918529303922093e-05,
|
| 79 |
+
"loss": 1.0573,
|
| 80 |
+
"step": 12
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.11,
|
| 84 |
+
"learning_rate": 0.00010238020557926735,
|
| 85 |
+
"loss": 1.1057,
|
| 86 |
+
"step": 13
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.11,
|
| 90 |
+
"learning_rate": 0.0001053382325680222,
|
| 91 |
+
"loss": 1.1141,
|
| 92 |
+
"step": 14
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.12,
|
| 96 |
+
"learning_rate": 0.0001080920898111643,
|
| 97 |
+
"loss": 1.0665,
|
| 98 |
+
"step": 15
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.13,
|
| 102 |
+
"learning_rate": 0.00011066815122252317,
|
| 103 |
+
"loss": 1.1191,
|
| 104 |
+
"step": 16
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.14,
|
| 108 |
+
"learning_rate": 0.0001130879889579842,
|
| 109 |
+
"loss": 1.1608,
|
| 110 |
+
"step": 17
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.15,
|
| 114 |
+
"learning_rate": 0.0001153694726615495,
|
| 115 |
+
"loss": 1.0334,
|
| 116 |
+
"step": 18
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.15,
|
| 120 |
+
"learning_rate": 0.00011752757111002288,
|
| 121 |
+
"loss": 1.0872,
|
| 122 |
+
"step": 19
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.16,
|
| 126 |
+
"learning_rate": 0.00011957494799446651,
|
| 127 |
+
"loss": 1.1656,
|
| 128 |
+
"step": 20
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.16,
|
| 132 |
+
"eval_loss": 1.0107293128967285,
|
| 133 |
+
"eval_runtime": 104.5604,
|
| 134 |
+
"eval_samples_per_second": 31.867,
|
| 135 |
+
"eval_steps_per_second": 0.258,
|
| 136 |
+
"step": 20
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.17,
|
| 140 |
+
"learning_rate": 0.00012152241219035079,
|
| 141 |
+
"loss": 1.0628,
|
| 142 |
+
"step": 21
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.18,
|
| 146 |
+
"learning_rate": 0.00012337926318446344,
|
| 147 |
+
"loss": 1.0393,
|
| 148 |
+
"step": 22
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.19,
|
| 152 |
+
"learning_rate": 0.00012515355965434256,
|
| 153 |
+
"loss": 1.1608,
|
| 154 |
+
"step": 23
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.19,
|
| 158 |
+
"learning_rate": 0.00012685233084485173,
|
| 159 |
+
"loss": 1.0166,
|
| 160 |
+
"step": 24
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.2,
|
| 164 |
+
"learning_rate": 0.00012848174476640987,
|
| 165 |
+
"loss": 1.0257,
|
| 166 |
+
"step": 25
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.21,
|
| 170 |
+
"learning_rate": 0.00013004724338489814,
|
| 171 |
+
"loss": 1.1549,
|
| 172 |
+
"step": 26
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.22,
|
| 176 |
+
"learning_rate": 0.00013155365228387805,
|
| 177 |
+
"loss": 1.0424,
|
| 178 |
+
"step": 27
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.23,
|
| 182 |
+
"learning_rate": 0.000133005270373653,
|
| 183 |
+
"loss": 1.0365,
|
| 184 |
+
"step": 28
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.24,
|
| 188 |
+
"learning_rate": 0.00013440594385123045,
|
| 189 |
+
"loss": 1.1665,
|
| 190 |
+
"step": 29
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.24,
|
| 194 |
+
"learning_rate": 0.0001357591276167951,
|
| 195 |
+
"loss": 1.0571,
|
| 196 |
+
"step": 30
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.25,
|
| 200 |
+
"learning_rate": 0.00013706793661599027,
|
| 201 |
+
"loss": 0.9924,
|
| 202 |
+
"step": 31
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.26,
|
| 206 |
+
"learning_rate": 0.00013833518902815398,
|
| 207 |
+
"loss": 1.1116,
|
| 208 |
+
"step": 32
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.27,
|
| 212 |
+
"learning_rate": 0.00013956344280679199,
|
| 213 |
+
"loss": 1.0776,
|
| 214 |
+
"step": 33
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.28,
|
| 218 |
+
"learning_rate": 0.000140755026763615,
|
| 219 |
+
"loss": 0.9747,
|
| 220 |
+
"step": 34
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.28,
|
| 224 |
+
"learning_rate": 0.00014191206714559635,
|
| 225 |
+
"loss": 1.0629,
|
| 226 |
+
"step": 35
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.29,
|
| 230 |
+
"learning_rate": 0.0001430365104671803,
|
| 231 |
+
"loss": 1.092,
|
| 232 |
+
"step": 36
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.3,
|
| 236 |
+
"learning_rate": 0.00014413014321352675,
|
| 237 |
+
"loss": 0.9619,
|
| 238 |
+
"step": 37
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.31,
|
| 242 |
+
"learning_rate": 0.00014519460891565368,
|
| 243 |
+
"loss": 1.0927,
|
| 244 |
+
"step": 38
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.32,
|
| 248 |
+
"learning_rate": 0.0001462314230072267,
|
| 249 |
+
"loss": 1.0615,
|
| 250 |
+
"step": 39
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.32,
|
| 254 |
+
"learning_rate": 0.0001472419858000973,
|
| 255 |
+
"loss": 0.9778,
|
| 256 |
+
"step": 40
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.32,
|
| 260 |
+
"eval_loss": 0.9711087346076965,
|
| 261 |
+
"eval_runtime": 105.6416,
|
| 262 |
+
"eval_samples_per_second": 31.541,
|
| 263 |
+
"eval_steps_per_second": 0.256,
|
| 264 |
+
"step": 40
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.33,
|
| 268 |
+
"learning_rate": 0.00014822759385740156,
|
| 269 |
+
"loss": 1.0388,
|
| 270 |
+
"step": 41
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.34,
|
| 274 |
+
"learning_rate": 0.00014918944999598157,
|
| 275 |
+
"loss": 1.1334,
|
| 276 |
+
"step": 42
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.35,
|
| 280 |
+
"learning_rate": 0.00015012867211170486,
|
| 281 |
+
"loss": 0.9814,
|
| 282 |
+
"step": 43
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.36,
|
| 286 |
+
"learning_rate": 0.00015104630099009423,
|
| 287 |
+
"loss": 1.0085,
|
| 288 |
+
"step": 44
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.37,
|
| 292 |
+
"learning_rate": 0.00015194330723912363,
|
| 293 |
+
"loss": 1.067,
|
| 294 |
+
"step": 45
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.37,
|
| 298 |
+
"learning_rate": 0.00015282059745997336,
|
| 299 |
+
"loss": 1.0041,
|
| 300 |
+
"step": 46
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.38,
|
| 304 |
+
"learning_rate": 0.00015367901975410053,
|
| 305 |
+
"loss": 0.957,
|
| 306 |
+
"step": 47
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.39,
|
| 310 |
+
"learning_rate": 0.00015451936865048253,
|
| 311 |
+
"loss": 1.1281,
|
| 312 |
+
"step": 48
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.4,
|
| 316 |
+
"learning_rate": 0.00015534238952478284,
|
| 317 |
+
"loss": 1.0121,
|
| 318 |
+
"step": 49
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.41,
|
| 322 |
+
"learning_rate": 0.00015614878257204067,
|
| 323 |
+
"loss": 0.9725,
|
| 324 |
+
"step": 50
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.41,
|
| 328 |
+
"learning_rate": 0.00015693920638594356,
|
| 329 |
+
"loss": 1.0977,
|
| 330 |
+
"step": 51
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.42,
|
| 334 |
+
"learning_rate": 0.00015771428119052897,
|
| 335 |
+
"loss": 0.9913,
|
| 336 |
+
"step": 52
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 0.43,
|
| 340 |
+
"learning_rate": 0.00015847459176404594,
|
| 341 |
+
"loss": 0.9657,
|
| 342 |
+
"step": 53
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.44,
|
| 346 |
+
"learning_rate": 0.00015922069008950885,
|
| 347 |
+
"loss": 1.0791,
|
| 348 |
+
"step": 54
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 0.45,
|
| 352 |
+
"learning_rate": 0.00015995309776203757,
|
| 353 |
+
"loss": 1.0275,
|
| 354 |
+
"step": 55
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.45,
|
| 358 |
+
"learning_rate": 0.00016067230817928382,
|
| 359 |
+
"loss": 0.9755,
|
| 360 |
+
"step": 56
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.46,
|
| 364 |
+
"learning_rate": 0.00016137878853798225,
|
| 365 |
+
"loss": 1.0315,
|
| 366 |
+
"step": 57
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.47,
|
| 370 |
+
"learning_rate": 0.00016207298165686122,
|
| 371 |
+
"loss": 1.03,
|
| 372 |
+
"step": 58
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 0.48,
|
| 376 |
+
"learning_rate": 0.0001627553076437253,
|
| 377 |
+
"loss": 0.9478,
|
| 378 |
+
"step": 59
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.49,
|
| 382 |
+
"learning_rate": 0.00016342616542242586,
|
| 383 |
+
"loss": 1.0424,
|
| 384 |
+
"step": 60
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.49,
|
| 388 |
+
"eval_loss": 0.9511741995811462,
|
| 389 |
+
"eval_runtime": 105.0633,
|
| 390 |
+
"eval_samples_per_second": 31.714,
|
| 391 |
+
"eval_steps_per_second": 0.257,
|
| 392 |
+
"step": 60
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.49,
|
| 396 |
+
"learning_rate": 0.0001640859341336185,
|
| 397 |
+
"loss": 1.0543,
|
| 398 |
+
"step": 61
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.5,
|
| 402 |
+
"learning_rate": 0.00016473497442162107,
|
| 403 |
+
"loss": 0.9464,
|
| 404 |
+
"step": 62
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.51,
|
| 408 |
+
"learning_rate": 0.00016537362961831014,
|
| 409 |
+
"loss": 1.0091,
|
| 410 |
+
"step": 63
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.52,
|
| 414 |
+
"learning_rate": 0.00016600222683378475,
|
| 415 |
+
"loss": 1.1283,
|
| 416 |
+
"step": 64
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.53,
|
| 420 |
+
"learning_rate": 0.0001666210779624723,
|
| 421 |
+
"loss": 0.9776,
|
| 422 |
+
"step": 65
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.54,
|
| 426 |
+
"learning_rate": 0.00016723048061242278,
|
| 427 |
+
"loss": 1.0544,
|
| 428 |
+
"step": 66
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.54,
|
| 432 |
+
"learning_rate": 0.00016783071896472347,
|
| 433 |
+
"loss": 1.0389,
|
| 434 |
+
"step": 67
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.55,
|
| 438 |
+
"learning_rate": 0.0001684220645692458,
|
| 439 |
+
"loss": 0.9661,
|
| 440 |
+
"step": 68
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 0.56,
|
| 444 |
+
"learning_rate": 0.00016900477708230193,
|
| 445 |
+
"loss": 0.9977,
|
| 446 |
+
"step": 69
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.57,
|
| 450 |
+
"learning_rate": 0.00016957910495122718,
|
| 451 |
+
"loss": 1.1473,
|
| 452 |
+
"step": 70
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.58,
|
| 456 |
+
"learning_rate": 0.00017014528605040512,
|
| 457 |
+
"loss": 0.9642,
|
| 458 |
+
"step": 71
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.58,
|
| 462 |
+
"learning_rate": 0.0001707035482728111,
|
| 463 |
+
"loss": 0.9816,
|
| 464 |
+
"step": 72
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.59,
|
| 468 |
+
"learning_rate": 0.00017125411008075538,
|
| 469 |
+
"loss": 1.0252,
|
| 470 |
+
"step": 73
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.6,
|
| 474 |
+
"learning_rate": 0.00017179718101915754,
|
| 475 |
+
"loss": 0.931,
|
| 476 |
+
"step": 74
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 0.61,
|
| 480 |
+
"learning_rate": 0.00017233296219436924,
|
| 481 |
+
"loss": 0.9844,
|
| 482 |
+
"step": 75
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.62,
|
| 486 |
+
"learning_rate": 0.0001728616467212845,
|
| 487 |
+
"loss": 1.1343,
|
| 488 |
+
"step": 76
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.62,
|
| 492 |
+
"learning_rate": 0.00017338342014122407,
|
| 493 |
+
"loss": 0.9936,
|
| 494 |
+
"step": 77
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.63,
|
| 498 |
+
"learning_rate": 0.0001738984608128575,
|
| 499 |
+
"loss": 0.9236,
|
| 500 |
+
"step": 78
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.64,
|
| 504 |
+
"learning_rate": 0.0001744069402782235,
|
| 505 |
+
"loss": 1.0555,
|
| 506 |
+
"step": 79
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.65,
|
| 510 |
+
"learning_rate": 0.0001749090236057281,
|
| 511 |
+
"loss": 0.9858,
|
| 512 |
+
"step": 80
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 0.65,
|
| 516 |
+
"eval_loss": 0.9414578080177307,
|
| 517 |
+
"eval_runtime": 104.7003,
|
| 518 |
+
"eval_samples_per_second": 31.824,
|
| 519 |
+
"eval_steps_per_second": 0.258,
|
| 520 |
+
"step": 80
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.66,
|
| 524 |
+
"learning_rate": 0.00017540486971183742,
|
| 525 |
+
"loss": 0.9318,
|
| 526 |
+
"step": 81
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.67,
|
| 530 |
+
"learning_rate": 0.00017589463166303238,
|
| 531 |
+
"loss": 1.0657,
|
| 532 |
+
"step": 82
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.67,
|
| 536 |
+
"learning_rate": 0.00017637845695946241,
|
| 537 |
+
"loss": 0.999,
|
| 538 |
+
"step": 83
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 0.68,
|
| 542 |
+
"learning_rate": 0.00017685648780161234,
|
| 543 |
+
"loss": 0.9757,
|
| 544 |
+
"step": 84
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.69,
|
| 548 |
+
"learning_rate": 0.00017732886134118916,
|
| 549 |
+
"loss": 1.0634,
|
| 550 |
+
"step": 85
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.7,
|
| 554 |
+
"learning_rate": 0.00017779570991733563,
|
| 555 |
+
"loss": 1.0504,
|
| 556 |
+
"step": 86
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.71,
|
| 560 |
+
"learning_rate": 0.0001782571612791898,
|
| 561 |
+
"loss": 0.9327,
|
| 562 |
+
"step": 87
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.71,
|
| 566 |
+
"learning_rate": 0.00017871333879572503,
|
| 567 |
+
"loss": 1.0454,
|
| 568 |
+
"step": 88
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 0.72,
|
| 572 |
+
"learning_rate": 0.00017916436165373454,
|
| 573 |
+
"loss": 1.0217,
|
| 574 |
+
"step": 89
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 0.73,
|
| 578 |
+
"learning_rate": 0.00017961034504475446,
|
| 579 |
+
"loss": 0.9515,
|
| 580 |
+
"step": 90
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 0.74,
|
| 584 |
+
"learning_rate": 0.00018005140034165878,
|
| 585 |
+
"loss": 1.0084,
|
| 586 |
+
"step": 91
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.75,
|
| 590 |
+
"learning_rate": 0.00018048763526560415,
|
| 591 |
+
"loss": 1.0499,
|
| 592 |
+
"step": 92
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.75,
|
| 596 |
+
"learning_rate": 0.00018091915404394964,
|
| 597 |
+
"loss": 0.991,
|
| 598 |
+
"step": 93
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.76,
|
| 602 |
+
"learning_rate": 0.00018134605755973132,
|
| 603 |
+
"loss": 1.0103,
|
| 604 |
+
"step": 94
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.77,
|
| 608 |
+
"learning_rate": 0.00018176844349322783,
|
| 609 |
+
"loss": 1.0429,
|
| 610 |
+
"step": 95
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.78,
|
| 614 |
+
"learning_rate": 0.00018218640645611332,
|
| 615 |
+
"loss": 0.9532,
|
| 616 |
+
"step": 96
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 0.79,
|
| 620 |
+
"learning_rate": 0.00018260003811865945,
|
| 621 |
+
"loss": 0.9993,
|
| 622 |
+
"step": 97
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 0.8,
|
| 626 |
+
"learning_rate": 0.00018300942733041366,
|
| 627 |
+
"loss": 1.1194,
|
| 628 |
+
"step": 98
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 0.8,
|
| 632 |
+
"learning_rate": 0.00018341466023475133,
|
| 633 |
+
"loss": 0.9519,
|
| 634 |
+
"step": 99
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.81,
|
| 638 |
+
"learning_rate": 0.0001838158203776715,
|
| 639 |
+
"loss": 0.9457,
|
| 640 |
+
"step": 100
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.81,
|
| 644 |
+
"eval_loss": 0.9341189861297607,
|
| 645 |
+
"eval_runtime": 105.432,
|
| 646 |
+
"eval_samples_per_second": 31.603,
|
| 647 |
+
"eval_steps_per_second": 0.256,
|
| 648 |
+
"step": 100
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.82,
|
| 652 |
+
"learning_rate": 0.000184212988811179,
|
| 653 |
+
"loss": 1.1073,
|
| 654 |
+
"step": 101
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.83,
|
| 658 |
+
"learning_rate": 0.00018460624419157432,
|
| 659 |
+
"loss": 0.9791,
|
| 660 |
+
"step": 102
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.84,
|
| 664 |
+
"learning_rate": 0.00018499566287294834,
|
| 665 |
+
"loss": 0.9439,
|
| 666 |
+
"step": 103
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 0.84,
|
| 670 |
+
"learning_rate": 0.00018538131899615973,
|
| 671 |
+
"loss": 1.0692,
|
| 672 |
+
"step": 104
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 0.85,
|
| 676 |
+
"learning_rate": 0.0001857632845735557,
|
| 677 |
+
"loss": 1.0314,
|
| 678 |
+
"step": 105
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 0.86,
|
| 682 |
+
"learning_rate": 0.00018614162956967674,
|
| 683 |
+
"loss": 0.9366,
|
| 684 |
+
"step": 106
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.87,
|
| 688 |
+
"learning_rate": 0.00018651642197817242,
|
| 689 |
+
"loss": 1.0502,
|
| 690 |
+
"step": 107
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.88,
|
| 694 |
+
"learning_rate": 0.00018688772789513967,
|
| 695 |
+
"loss": 1.0201,
|
| 696 |
+
"step": 108
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.88,
|
| 700 |
+
"learning_rate": 0.00018725561158908094,
|
| 701 |
+
"loss": 0.9718,
|
| 702 |
+
"step": 109
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.89,
|
| 706 |
+
"learning_rate": 0.0001876201355676684,
|
| 707 |
+
"loss": 0.9949,
|
| 708 |
+
"step": 110
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 0.9,
|
| 712 |
+
"learning_rate": 0.0001879813606414861,
|
| 713 |
+
"loss": 0.9924,
|
| 714 |
+
"step": 111
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.91,
|
| 718 |
+
"learning_rate": 0.0001883393459849146,
|
| 719 |
+
"loss": 0.9327,
|
| 720 |
+
"step": 112
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.92,
|
| 724 |
+
"learning_rate": 0.0001886941491943088,
|
| 725 |
+
"loss": 0.9908,
|
| 726 |
+
"step": 113
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 0.92,
|
| 730 |
+
"learning_rate": 0.00018904582634361305,
|
| 731 |
+
"loss": 1.0408,
|
| 732 |
+
"step": 114
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.93,
|
| 736 |
+
"learning_rate": 0.00018939443203754748,
|
| 737 |
+
"loss": 0.9303,
|
| 738 |
+
"step": 115
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.94,
|
| 742 |
+
"learning_rate": 0.000189740019462492,
|
| 743 |
+
"loss": 1.0056,
|
| 744 |
+
"step": 116
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.95,
|
| 748 |
+
"learning_rate": 0.00019008264043518606,
|
| 749 |
+
"loss": 1.0623,
|
| 750 |
+
"step": 117
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 0.96,
|
| 754 |
+
"learning_rate": 0.0001904223454493561,
|
| 755 |
+
"loss": 0.9385,
|
| 756 |
+
"step": 118
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 0.97,
|
| 760 |
+
"learning_rate": 0.00019075918372037564,
|
| 761 |
+
"loss": 0.9983,
|
| 762 |
+
"step": 119
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.97,
|
| 766 |
+
"learning_rate": 0.00019109320322805665,
|
| 767 |
+
"loss": 1.0584,
|
| 768 |
+
"step": 120
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.97,
|
| 772 |
+
"eval_loss": 0.9276898503303528,
|
| 773 |
+
"eval_runtime": 104.6096,
|
| 774 |
+
"eval_samples_per_second": 31.852,
|
| 775 |
+
"eval_steps_per_second": 0.258,
|
| 776 |
+
"step": 120
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.98,
|
| 780 |
+
"learning_rate": 0.00019142445075766529,
|
| 781 |
+
"loss": 0.928,
|
| 782 |
+
"step": 121
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.99,
|
| 786 |
+
"learning_rate": 0.0001917529719392493,
|
| 787 |
+
"loss": 0.9414,
|
| 788 |
+
"step": 122
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 1.0,
|
| 792 |
+
"learning_rate": 0.0001920788112853609,
|
| 793 |
+
"loss": 1.0277,
|
| 794 |
+
"step": 123
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.01,
|
| 798 |
+
"learning_rate": 0.00019240201222725186,
|
| 799 |
+
"loss": 1.0717,
|
| 800 |
+
"step": 124
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.01,
|
| 804 |
+
"learning_rate": 0.00019272261714961485,
|
| 805 |
+
"loss": 0.9567,
|
| 806 |
+
"step": 125
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 1.02,
|
| 810 |
+
"learning_rate": 0.0001930406674239409,
|
| 811 |
+
"loss": 0.8984,
|
| 812 |
+
"step": 126
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 1.03,
|
| 816 |
+
"learning_rate": 0.0001933562034405585,
|
| 817 |
+
"loss": 0.9453,
|
| 818 |
+
"step": 127
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 1.04,
|
| 822 |
+
"learning_rate": 0.00019366926463941554,
|
| 823 |
+
"loss": 0.9943,
|
| 824 |
+
"step": 128
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 1.05,
|
| 828 |
+
"learning_rate": 0.0001939798895396642,
|
| 829 |
+
"loss": 0.8644,
|
| 830 |
+
"step": 129
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 1.05,
|
| 834 |
+
"learning_rate": 0.0001942881157681031,
|
| 835 |
+
"loss": 0.968,
|
| 836 |
+
"step": 130
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.06,
|
| 840 |
+
"learning_rate": 0.00019459398008652982,
|
| 841 |
+
"loss": 1.0798,
|
| 842 |
+
"step": 131
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.07,
|
| 846 |
+
"learning_rate": 0.00019489751841805358,
|
| 847 |
+
"loss": 0.9165,
|
| 848 |
+
"step": 132
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 1.08,
|
| 852 |
+
"learning_rate": 0.0001951987658724143,
|
| 853 |
+
"loss": 0.9391,
|
| 854 |
+
"step": 133
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 1.09,
|
| 858 |
+
"learning_rate": 0.00019549775677035427,
|
| 859 |
+
"loss": 1.0106,
|
| 860 |
+
"step": 134
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 1.1,
|
| 864 |
+
"learning_rate": 0.000195794524667083,
|
| 865 |
+
"loss": 0.8805,
|
| 866 |
+
"step": 135
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 1.1,
|
| 870 |
+
"learning_rate": 0.0001960891023748766,
|
| 871 |
+
"loss": 0.935,
|
| 872 |
+
"step": 136
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 1.11,
|
| 876 |
+
"learning_rate": 0.00019638152198484917,
|
| 877 |
+
"loss": 1.0291,
|
| 878 |
+
"step": 137
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.12,
|
| 882 |
+
"learning_rate": 0.00019667181488793273,
|
| 883 |
+
"loss": 0.8887,
|
| 884 |
+
"step": 138
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 1.13,
|
| 888 |
+
"learning_rate": 0.00019696001179509912,
|
| 889 |
+
"loss": 0.8827,
|
| 890 |
+
"step": 139
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 1.14,
|
| 894 |
+
"learning_rate": 0.00019724614275685795,
|
| 895 |
+
"loss": 1.0284,
|
| 896 |
+
"step": 140
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 1.14,
|
| 900 |
+
"eval_loss": 0.9371529817581177,
|
| 901 |
+
"eval_runtime": 104.4681,
|
| 902 |
+
"eval_samples_per_second": 31.895,
|
| 903 |
+
"eval_steps_per_second": 0.258,
|
| 904 |
+
"step": 140
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 1.14,
|
| 908 |
+
"learning_rate": 0.0001975302371820599,
|
| 909 |
+
"loss": 0.8687,
|
| 910 |
+
"step": 141
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 1.15,
|
| 914 |
+
"learning_rate": 0.0001978123238560359,
|
| 915 |
+
"loss": 0.8771,
|
| 916 |
+
"step": 142
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 1.16,
|
| 920 |
+
"learning_rate": 0.00019809243095809996,
|
| 921 |
+
"loss": 1.0197,
|
| 922 |
+
"step": 143
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 1.17,
|
| 926 |
+
"learning_rate": 0.00019837058607844187,
|
| 927 |
+
"loss": 0.8979,
|
| 928 |
+
"step": 144
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 1.18,
|
| 932 |
+
"learning_rate": 0.00019864681623443537,
|
| 933 |
+
"loss": 0.9128,
|
| 934 |
+
"step": 145
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.18,
|
| 938 |
+
"learning_rate": 0.00019892114788638618,
|
| 939 |
+
"loss": 1.0225,
|
| 940 |
+
"step": 146
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.19,
|
| 944 |
+
"learning_rate": 0.00019919360695274218,
|
| 945 |
+
"loss": 0.9081,
|
| 946 |
+
"step": 147
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 1.2,
|
| 950 |
+
"learning_rate": 0.00019946421882478829,
|
| 951 |
+
"loss": 0.8753,
|
| 952 |
+
"step": 148
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 1.21,
|
| 956 |
+
"learning_rate": 0.00019973300838084634,
|
| 957 |
+
"loss": 0.9424,
|
| 958 |
+
"step": 149
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 1.22,
|
| 962 |
+
"learning_rate": 0.0002,
|
| 963 |
+
"loss": 0.9569,
|
| 964 |
+
"step": 150
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 1.23,
|
| 968 |
+
"learning_rate": 0.0002,
|
| 969 |
+
"loss": 0.8741,
|
| 970 |
+
"step": 151
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 1.23,
|
| 974 |
+
"learning_rate": 0.0002,
|
| 975 |
+
"loss": 0.9871,
|
| 976 |
+
"step": 152
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.24,
|
| 980 |
+
"learning_rate": 0.0002,
|
| 981 |
+
"loss": 1.0033,
|
| 982 |
+
"step": 153
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 1.25,
|
| 986 |
+
"learning_rate": 0.0002,
|
| 987 |
+
"loss": 0.8893,
|
| 988 |
+
"step": 154
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 1.26,
|
| 992 |
+
"learning_rate": 0.0002,
|
| 993 |
+
"loss": 0.9914,
|
| 994 |
+
"step": 155
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 1.27,
|
| 998 |
+
"learning_rate": 0.0002,
|
| 999 |
+
"loss": 0.9987,
|
| 1000 |
+
"step": 156
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 1.27,
|
| 1004 |
+
"learning_rate": 0.0002,
|
| 1005 |
+
"loss": 0.8921,
|
| 1006 |
+
"step": 157
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 1.28,
|
| 1010 |
+
"learning_rate": 0.0002,
|
| 1011 |
+
"loss": 0.9267,
|
| 1012 |
+
"step": 158
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 1.29,
|
| 1016 |
+
"learning_rate": 0.0002,
|
| 1017 |
+
"loss": 1.0002,
|
| 1018 |
+
"step": 159
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.3,
|
| 1022 |
+
"learning_rate": 0.0002,
|
| 1023 |
+
"loss": 0.8781,
|
| 1024 |
+
"step": 160
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 1.3,
|
| 1028 |
+
"eval_loss": 0.9295092821121216,
|
| 1029 |
+
"eval_runtime": 103.7825,
|
| 1030 |
+
"eval_samples_per_second": 32.106,
|
| 1031 |
+
"eval_steps_per_second": 0.26,
|
| 1032 |
+
"step": 160
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.31,
|
| 1036 |
+
"learning_rate": 0.0002,
|
| 1037 |
+
"loss": 0.9044,
|
| 1038 |
+
"step": 161
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 1.31,
|
| 1042 |
+
"learning_rate": 0.0002,
|
| 1043 |
+
"loss": 1.0411,
|
| 1044 |
+
"step": 162
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 1.32,
|
| 1048 |
+
"learning_rate": 0.0002,
|
| 1049 |
+
"loss": 0.8899,
|
| 1050 |
+
"step": 163
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 1.33,
|
| 1054 |
+
"learning_rate": 0.0002,
|
| 1055 |
+
"loss": 0.9184,
|
| 1056 |
+
"step": 164
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 1.34,
|
| 1060 |
+
"learning_rate": 0.0002,
|
| 1061 |
+
"loss": 1.0897,
|
| 1062 |
+
"step": 165
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 1.35,
|
| 1066 |
+
"learning_rate": 0.0002,
|
| 1067 |
+
"loss": 0.8789,
|
| 1068 |
+
"step": 166
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 1.35,
|
| 1072 |
+
"learning_rate": 0.0002,
|
| 1073 |
+
"loss": 0.8745,
|
| 1074 |
+
"step": 167
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.36,
|
| 1078 |
+
"learning_rate": 0.0002,
|
| 1079 |
+
"loss": 1.0253,
|
| 1080 |
+
"step": 168
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 1.37,
|
| 1084 |
+
"learning_rate": 0.0002,
|
| 1085 |
+
"loss": 0.9096,
|
| 1086 |
+
"step": 169
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 1.38,
|
| 1090 |
+
"learning_rate": 0.0002,
|
| 1091 |
+
"loss": 0.8611,
|
| 1092 |
+
"step": 170
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 1.39,
|
| 1096 |
+
"learning_rate": 0.0002,
|
| 1097 |
+
"loss": 1.0522,
|
| 1098 |
+
"step": 171
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 1.4,
|
| 1102 |
+
"learning_rate": 0.0002,
|
| 1103 |
+
"loss": 0.9484,
|
| 1104 |
+
"step": 172
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 1.4,
|
| 1108 |
+
"learning_rate": 0.0002,
|
| 1109 |
+
"loss": 0.8581,
|
| 1110 |
+
"step": 173
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 1.41,
|
| 1114 |
+
"learning_rate": 0.0002,
|
| 1115 |
+
"loss": 0.9673,
|
| 1116 |
+
"step": 174
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.42,
|
| 1120 |
+
"learning_rate": 0.0002,
|
| 1121 |
+
"loss": 0.8891,
|
| 1122 |
+
"step": 175
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.43,
|
| 1126 |
+
"learning_rate": 0.0002,
|
| 1127 |
+
"loss": 0.8821,
|
| 1128 |
+
"step": 176
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 1.44,
|
| 1132 |
+
"learning_rate": 0.0002,
|
| 1133 |
+
"loss": 0.9771,
|
| 1134 |
+
"step": 177
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 1.44,
|
| 1138 |
+
"learning_rate": 0.0002,
|
| 1139 |
+
"loss": 0.974,
|
| 1140 |
+
"step": 178
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 1.45,
|
| 1144 |
+
"learning_rate": 0.0002,
|
| 1145 |
+
"loss": 0.8719,
|
| 1146 |
+
"step": 179
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 1.46,
|
| 1150 |
+
"learning_rate": 0.0002,
|
| 1151 |
+
"loss": 0.9531,
|
| 1152 |
+
"step": 180
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 1.46,
|
| 1156 |
+
"eval_loss": 0.926723837852478,
|
| 1157 |
+
"eval_runtime": 104.5098,
|
| 1158 |
+
"eval_samples_per_second": 31.882,
|
| 1159 |
+
"eval_steps_per_second": 0.258,
|
| 1160 |
+
"step": 180
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 1.47,
|
| 1164 |
+
"learning_rate": 0.0002,
|
| 1165 |
+
"loss": 0.9568,
|
| 1166 |
+
"step": 181
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 1.48,
|
| 1170 |
+
"learning_rate": 0.0002,
|
| 1171 |
+
"loss": 0.8702,
|
| 1172 |
+
"step": 182
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.48,
|
| 1176 |
+
"learning_rate": 0.0002,
|
| 1177 |
+
"loss": 0.98,
|
| 1178 |
+
"step": 183
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.49,
|
| 1182 |
+
"learning_rate": 0.0002,
|
| 1183 |
+
"loss": 0.9709,
|
| 1184 |
+
"step": 184
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 1.5,
|
| 1188 |
+
"learning_rate": 0.0002,
|
| 1189 |
+
"loss": 0.8892,
|
| 1190 |
+
"step": 185
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 1.51,
|
| 1194 |
+
"learning_rate": 0.0002,
|
| 1195 |
+
"loss": 0.8827,
|
| 1196 |
+
"step": 186
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 1.52,
|
| 1200 |
+
"learning_rate": 0.0002,
|
| 1201 |
+
"loss": 0.9874,
|
| 1202 |
+
"step": 187
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 1.53,
|
| 1206 |
+
"learning_rate": 0.0002,
|
| 1207 |
+
"loss": 0.8684,
|
| 1208 |
+
"step": 188
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 1.53,
|
| 1212 |
+
"learning_rate": 0.0002,
|
| 1213 |
+
"loss": 0.8632,
|
| 1214 |
+
"step": 189
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.54,
|
| 1218 |
+
"learning_rate": 0.0002,
|
| 1219 |
+
"loss": 1.0162,
|
| 1220 |
+
"step": 190
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.55,
|
| 1224 |
+
"learning_rate": 0.0002,
|
| 1225 |
+
"loss": 0.9045,
|
| 1226 |
+
"step": 191
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 1.56,
|
| 1230 |
+
"learning_rate": 0.0002,
|
| 1231 |
+
"loss": 0.9085,
|
| 1232 |
+
"step": 192
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 1.57,
|
| 1236 |
+
"learning_rate": 0.0002,
|
| 1237 |
+
"loss": 1.0432,
|
| 1238 |
+
"step": 193
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 1.57,
|
| 1242 |
+
"learning_rate": 0.0002,
|
| 1243 |
+
"loss": 0.8893,
|
| 1244 |
+
"step": 194
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 1.58,
|
| 1248 |
+
"learning_rate": 0.0002,
|
| 1249 |
+
"loss": 0.9048,
|
| 1250 |
+
"step": 195
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 1.59,
|
| 1254 |
+
"learning_rate": 0.0002,
|
| 1255 |
+
"loss": 0.9976,
|
| 1256 |
+
"step": 196
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.6,
|
| 1260 |
+
"learning_rate": 0.0002,
|
| 1261 |
+
"loss": 0.9437,
|
| 1262 |
+
"step": 197
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.61,
|
| 1266 |
+
"learning_rate": 0.0002,
|
| 1267 |
+
"loss": 0.8922,
|
| 1268 |
+
"step": 198
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 1.61,
|
| 1272 |
+
"learning_rate": 0.0002,
|
| 1273 |
+
"loss": 1.0123,
|
| 1274 |
+
"step": 199
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 1.62,
|
| 1278 |
+
"learning_rate": 0.0002,
|
| 1279 |
+
"loss": 0.9496,
|
| 1280 |
+
"step": 200
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 1.62,
|
| 1284 |
+
"eval_loss": 0.9225737452507019,
|
| 1285 |
+
"eval_runtime": 104.9516,
|
| 1286 |
+
"eval_samples_per_second": 31.748,
|
| 1287 |
+
"eval_steps_per_second": 0.257,
|
| 1288 |
+
"step": 200
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 1.63,
|
| 1292 |
+
"learning_rate": 0.0002,
|
| 1293 |
+
"loss": 0.88,
|
| 1294 |
+
"step": 201
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 1.64,
|
| 1298 |
+
"learning_rate": 0.0002,
|
| 1299 |
+
"loss": 0.9854,
|
| 1300 |
+
"step": 202
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 1.65,
|
| 1304 |
+
"learning_rate": 0.0002,
|
| 1305 |
+
"loss": 0.9728,
|
| 1306 |
+
"step": 203
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 1.66,
|
| 1310 |
+
"learning_rate": 0.0002,
|
| 1311 |
+
"loss": 0.8941,
|
| 1312 |
+
"step": 204
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.66,
|
| 1316 |
+
"learning_rate": 0.0002,
|
| 1317 |
+
"loss": 0.9427,
|
| 1318 |
+
"step": 205
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 1.67,
|
| 1322 |
+
"learning_rate": 0.0002,
|
| 1323 |
+
"loss": 0.9838,
|
| 1324 |
+
"step": 206
|
| 1325 |
+
},
|
| 1326 |
+
{
|
| 1327 |
+
"epoch": 1.68,
|
| 1328 |
+
"learning_rate": 0.0002,
|
| 1329 |
+
"loss": 0.8835,
|
| 1330 |
+
"step": 207
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 1.69,
|
| 1334 |
+
"learning_rate": 0.0002,
|
| 1335 |
+
"loss": 0.9632,
|
| 1336 |
+
"step": 208
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 1.7,
|
| 1340 |
+
"learning_rate": 0.0002,
|
| 1341 |
+
"loss": 1.063,
|
| 1342 |
+
"step": 209
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 1.7,
|
| 1346 |
+
"learning_rate": 0.0002,
|
| 1347 |
+
"loss": 0.8781,
|
| 1348 |
+
"step": 210
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 1.71,
|
| 1352 |
+
"learning_rate": 0.0002,
|
| 1353 |
+
"loss": 0.9306,
|
| 1354 |
+
"step": 211
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.72,
|
| 1358 |
+
"learning_rate": 0.0002,
|
| 1359 |
+
"loss": 1.0085,
|
| 1360 |
+
"step": 212
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 1.73,
|
| 1364 |
+
"learning_rate": 0.0002,
|
| 1365 |
+
"loss": 0.8721,
|
| 1366 |
+
"step": 213
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 1.74,
|
| 1370 |
+
"learning_rate": 0.0002,
|
| 1371 |
+
"loss": 0.9305,
|
| 1372 |
+
"step": 214
|
| 1373 |
+
},
|
| 1374 |
+
{
|
| 1375 |
+
"epoch": 1.74,
|
| 1376 |
+
"learning_rate": 0.0002,
|
| 1377 |
+
"loss": 1.0009,
|
| 1378 |
+
"step": 215
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 1.75,
|
| 1382 |
+
"learning_rate": 0.0002,
|
| 1383 |
+
"loss": 0.8773,
|
| 1384 |
+
"step": 216
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 1.76,
|
| 1388 |
+
"learning_rate": 0.0002,
|
| 1389 |
+
"loss": 0.8806,
|
| 1390 |
+
"step": 217
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 1.77,
|
| 1394 |
+
"learning_rate": 0.0002,
|
| 1395 |
+
"loss": 1.0875,
|
| 1396 |
+
"step": 218
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 1.78,
|
| 1400 |
+
"learning_rate": 0.0002,
|
| 1401 |
+
"loss": 0.9055,
|
| 1402 |
+
"step": 219
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 1.78,
|
| 1406 |
+
"learning_rate": 0.0002,
|
| 1407 |
+
"loss": 0.9178,
|
| 1408 |
+
"step": 220
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 1.78,
|
| 1412 |
+
"eval_loss": 0.9191879630088806,
|
| 1413 |
+
"eval_runtime": 104.0108,
|
| 1414 |
+
"eval_samples_per_second": 32.035,
|
| 1415 |
+
"eval_steps_per_second": 0.26,
|
| 1416 |
+
"step": 220
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 1.79,
|
| 1420 |
+
"learning_rate": 0.0002,
|
| 1421 |
+
"loss": 1.0323,
|
| 1422 |
+
"step": 221
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 1.8,
|
| 1426 |
+
"learning_rate": 0.0002,
|
| 1427 |
+
"loss": 0.9546,
|
| 1428 |
+
"step": 222
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 1.81,
|
| 1432 |
+
"learning_rate": 0.0002,
|
| 1433 |
+
"loss": 0.9247,
|
| 1434 |
+
"step": 223
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 1.82,
|
| 1438 |
+
"learning_rate": 0.0002,
|
| 1439 |
+
"loss": 0.9444,
|
| 1440 |
+
"step": 224
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 1.83,
|
| 1444 |
+
"learning_rate": 0.0002,
|
| 1445 |
+
"loss": 0.9241,
|
| 1446 |
+
"step": 225
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 1.83,
|
| 1450 |
+
"learning_rate": 0.0002,
|
| 1451 |
+
"loss": 0.8956,
|
| 1452 |
+
"step": 226
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 1.84,
|
| 1456 |
+
"learning_rate": 0.0002,
|
| 1457 |
+
"loss": 0.9338,
|
| 1458 |
+
"step": 227
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 1.85,
|
| 1462 |
+
"learning_rate": 0.0002,
|
| 1463 |
+
"loss": 0.995,
|
| 1464 |
+
"step": 228
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 1.86,
|
| 1468 |
+
"learning_rate": 0.0002,
|
| 1469 |
+
"loss": 0.8993,
|
| 1470 |
+
"step": 229
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 1.87,
|
| 1474 |
+
"learning_rate": 0.0002,
|
| 1475 |
+
"loss": 0.9504,
|
| 1476 |
+
"step": 230
|
| 1477 |
+
},
|
| 1478 |
+
{
|
| 1479 |
+
"epoch": 1.87,
|
| 1480 |
+
"learning_rate": 0.0002,
|
| 1481 |
+
"loss": 0.9759,
|
| 1482 |
+
"step": 231
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 1.88,
|
| 1486 |
+
"learning_rate": 0.0002,
|
| 1487 |
+
"loss": 0.8997,
|
| 1488 |
+
"step": 232
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 1.89,
|
| 1492 |
+
"learning_rate": 0.0002,
|
| 1493 |
+
"loss": 0.9527,
|
| 1494 |
+
"step": 233
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 1.9,
|
| 1498 |
+
"learning_rate": 0.0002,
|
| 1499 |
+
"loss": 1.0184,
|
| 1500 |
+
"step": 234
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 1.91,
|
| 1504 |
+
"learning_rate": 0.0002,
|
| 1505 |
+
"loss": 0.899,
|
| 1506 |
+
"step": 235
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 1.91,
|
| 1510 |
+
"learning_rate": 0.0002,
|
| 1511 |
+
"loss": 0.9286,
|
| 1512 |
+
"step": 236
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 1.92,
|
| 1516 |
+
"learning_rate": 0.0002,
|
| 1517 |
+
"loss": 1.026,
|
| 1518 |
+
"step": 237
|
| 1519 |
+
},
|
| 1520 |
+
{
|
| 1521 |
+
"epoch": 1.93,
|
| 1522 |
+
"learning_rate": 0.0002,
|
| 1523 |
+
"loss": 0.8862,
|
| 1524 |
+
"step": 238
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 1.94,
|
| 1528 |
+
"learning_rate": 0.0002,
|
| 1529 |
+
"loss": 0.9016,
|
| 1530 |
+
"step": 239
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 1.95,
|
| 1534 |
+
"learning_rate": 0.0002,
|
| 1535 |
+
"loss": 1.0763,
|
| 1536 |
+
"step": 240
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 1.95,
|
| 1540 |
+
"eval_loss": 0.9153895974159241,
|
| 1541 |
+
"eval_runtime": 103.9918,
|
| 1542 |
+
"eval_samples_per_second": 32.041,
|
| 1543 |
+
"eval_steps_per_second": 0.26,
|
| 1544 |
+
"step": 240
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 1.96,
|
| 1548 |
+
"learning_rate": 0.0002,
|
| 1549 |
+
"loss": 0.8882,
|
| 1550 |
+
"step": 241
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 1.96,
|
| 1554 |
+
"learning_rate": 0.0002,
|
| 1555 |
+
"loss": 0.8924,
|
| 1556 |
+
"step": 242
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 1.97,
|
| 1560 |
+
"learning_rate": 0.0002,
|
| 1561 |
+
"loss": 1.0703,
|
| 1562 |
+
"step": 243
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 1.98,
|
| 1566 |
+
"learning_rate": 0.0002,
|
| 1567 |
+
"loss": 0.8981,
|
| 1568 |
+
"step": 244
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 1.99,
|
| 1572 |
+
"learning_rate": 0.0002,
|
| 1573 |
+
"loss": 0.9054,
|
| 1574 |
+
"step": 245
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 2.0,
|
| 1578 |
+
"learning_rate": 0.0002,
|
| 1579 |
+
"loss": 0.9789,
|
| 1580 |
+
"step": 246
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 2.0,
|
| 1584 |
+
"learning_rate": 0.0002,
|
| 1585 |
+
"loss": 0.9292,
|
| 1586 |
+
"step": 247
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 2.01,
|
| 1590 |
+
"learning_rate": 0.0002,
|
| 1591 |
+
"loss": 0.8948,
|
| 1592 |
+
"step": 248
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 2.02,
|
| 1596 |
+
"learning_rate": 0.0002,
|
| 1597 |
+
"loss": 0.7865,
|
| 1598 |
+
"step": 249
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 2.03,
|
| 1602 |
+
"learning_rate": 0.0002,
|
| 1603 |
+
"loss": 0.8547,
|
| 1604 |
+
"step": 250
|
| 1605 |
+
},
|
| 1606 |
+
{
|
| 1607 |
+
"epoch": 2.04,
|
| 1608 |
+
"learning_rate": 0.0002,
|
| 1609 |
+
"loss": 0.9293,
|
| 1610 |
+
"step": 251
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 2.04,
|
| 1614 |
+
"learning_rate": 0.0002,
|
| 1615 |
+
"loss": 0.7914,
|
| 1616 |
+
"step": 252
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 2.05,
|
| 1620 |
+
"learning_rate": 0.0002,
|
| 1621 |
+
"loss": 0.8331,
|
| 1622 |
+
"step": 253
|
| 1623 |
+
},
|
| 1624 |
+
{
|
| 1625 |
+
"epoch": 2.06,
|
| 1626 |
+
"learning_rate": 0.0002,
|
| 1627 |
+
"loss": 0.9477,
|
| 1628 |
+
"step": 254
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 2.07,
|
| 1632 |
+
"learning_rate": 0.0002,
|
| 1633 |
+
"loss": 0.8101,
|
| 1634 |
+
"step": 255
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 2.08,
|
| 1638 |
+
"learning_rate": 0.0002,
|
| 1639 |
+
"loss": 0.8236,
|
| 1640 |
+
"step": 256
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 2.09,
|
| 1644 |
+
"learning_rate": 0.0002,
|
| 1645 |
+
"loss": 0.93,
|
| 1646 |
+
"step": 257
|
| 1647 |
+
},
|
| 1648 |
+
{
|
| 1649 |
+
"epoch": 2.09,
|
| 1650 |
+
"learning_rate": 0.0002,
|
| 1651 |
+
"loss": 0.8066,
|
| 1652 |
+
"step": 258
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 2.1,
|
| 1656 |
+
"learning_rate": 0.0002,
|
| 1657 |
+
"loss": 0.7846,
|
| 1658 |
+
"step": 259
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 2.11,
|
| 1662 |
+
"learning_rate": 0.0002,
|
| 1663 |
+
"loss": 0.9561,
|
| 1664 |
+
"step": 260
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 2.11,
|
| 1668 |
+
"eval_loss": 0.9422550201416016,
|
| 1669 |
+
"eval_runtime": 104.5769,
|
| 1670 |
+
"eval_samples_per_second": 31.862,
|
| 1671 |
+
"eval_steps_per_second": 0.258,
|
| 1672 |
+
"step": 260
|
| 1673 |
+
},
|
| 1674 |
+
{
|
| 1675 |
+
"epoch": 2.12,
|
| 1676 |
+
"learning_rate": 0.0002,
|
| 1677 |
+
"loss": 0.8292,
|
| 1678 |
+
"step": 261
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 2.13,
|
| 1682 |
+
"learning_rate": 0.0002,
|
| 1683 |
+
"loss": 0.7639,
|
| 1684 |
+
"step": 262
|
| 1685 |
+
},
|
| 1686 |
+
{
|
| 1687 |
+
"epoch": 2.13,
|
| 1688 |
+
"learning_rate": 0.0002,
|
| 1689 |
+
"loss": 0.895,
|
| 1690 |
+
"step": 263
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 2.14,
|
| 1694 |
+
"learning_rate": 0.0002,
|
| 1695 |
+
"loss": 0.8531,
|
| 1696 |
+
"step": 264
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 2.15,
|
| 1700 |
+
"learning_rate": 0.0002,
|
| 1701 |
+
"loss": 0.7822,
|
| 1702 |
+
"step": 265
|
| 1703 |
+
},
|
| 1704 |
+
{
|
| 1705 |
+
"epoch": 2.16,
|
| 1706 |
+
"learning_rate": 0.0002,
|
| 1707 |
+
"loss": 0.9096,
|
| 1708 |
+
"step": 266
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 2.17,
|
| 1712 |
+
"learning_rate": 0.0002,
|
| 1713 |
+
"loss": 0.8751,
|
| 1714 |
+
"step": 267
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 2.17,
|
| 1718 |
+
"learning_rate": 0.0002,
|
| 1719 |
+
"loss": 0.7933,
|
| 1720 |
+
"step": 268
|
| 1721 |
+
},
|
| 1722 |
+
{
|
| 1723 |
+
"epoch": 2.18,
|
| 1724 |
+
"learning_rate": 0.0002,
|
| 1725 |
+
"loss": 0.8531,
|
| 1726 |
+
"step": 269
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 2.19,
|
| 1730 |
+
"learning_rate": 0.0002,
|
| 1731 |
+
"loss": 0.8781,
|
| 1732 |
+
"step": 270
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 2.2,
|
| 1736 |
+
"learning_rate": 0.0002,
|
| 1737 |
+
"loss": 0.7974,
|
| 1738 |
+
"step": 271
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 2.21,
|
| 1742 |
+
"learning_rate": 0.0002,
|
| 1743 |
+
"loss": 0.8571,
|
| 1744 |
+
"step": 272
|
| 1745 |
+
},
|
| 1746 |
+
{
|
| 1747 |
+
"epoch": 2.22,
|
| 1748 |
+
"learning_rate": 0.0002,
|
| 1749 |
+
"loss": 0.893,
|
| 1750 |
+
"step": 273
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 2.22,
|
| 1754 |
+
"learning_rate": 0.0002,
|
| 1755 |
+
"loss": 0.7881,
|
| 1756 |
+
"step": 274
|
| 1757 |
+
},
|
| 1758 |
+
{
|
| 1759 |
+
"epoch": 2.23,
|
| 1760 |
+
"learning_rate": 0.0002,
|
| 1761 |
+
"loss": 0.8831,
|
| 1762 |
+
"step": 275
|
| 1763 |
+
},
|
| 1764 |
+
{
|
| 1765 |
+
"epoch": 2.24,
|
| 1766 |
+
"learning_rate": 0.0002,
|
| 1767 |
+
"loss": 0.9272,
|
| 1768 |
+
"step": 276
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"epoch": 2.25,
|
| 1772 |
+
"learning_rate": 0.0002,
|
| 1773 |
+
"loss": 0.7924,
|
| 1774 |
+
"step": 277
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 2.26,
|
| 1778 |
+
"learning_rate": 0.0002,
|
| 1779 |
+
"loss": 0.8152,
|
| 1780 |
+
"step": 278
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 2.26,
|
| 1784 |
+
"learning_rate": 0.0002,
|
| 1785 |
+
"loss": 0.9071,
|
| 1786 |
+
"step": 279
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 2.27,
|
| 1790 |
+
"learning_rate": 0.0002,
|
| 1791 |
+
"loss": 0.7991,
|
| 1792 |
+
"step": 280
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"epoch": 2.27,
|
| 1796 |
+
"eval_loss": 0.9367637634277344,
|
| 1797 |
+
"eval_runtime": 104.4183,
|
| 1798 |
+
"eval_samples_per_second": 31.91,
|
| 1799 |
+
"eval_steps_per_second": 0.259,
|
| 1800 |
+
"step": 280
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 2.28,
|
| 1804 |
+
"learning_rate": 0.0002,
|
| 1805 |
+
"loss": 0.8638,
|
| 1806 |
+
"step": 281
|
| 1807 |
+
},
|
| 1808 |
+
{
|
| 1809 |
+
"epoch": 2.29,
|
| 1810 |
+
"learning_rate": 0.0002,
|
| 1811 |
+
"loss": 0.9924,
|
| 1812 |
+
"step": 282
|
| 1813 |
+
},
|
| 1814 |
+
{
|
| 1815 |
+
"epoch": 2.3,
|
| 1816 |
+
"learning_rate": 0.0002,
|
| 1817 |
+
"loss": 0.8228,
|
| 1818 |
+
"step": 283
|
| 1819 |
+
},
|
| 1820 |
+
{
|
| 1821 |
+
"epoch": 2.3,
|
| 1822 |
+
"learning_rate": 0.0002,
|
| 1823 |
+
"loss": 0.8012,
|
| 1824 |
+
"step": 284
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 2.31,
|
| 1828 |
+
"learning_rate": 0.0002,
|
| 1829 |
+
"loss": 0.9366,
|
| 1830 |
+
"step": 285
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 2.32,
|
| 1834 |
+
"learning_rate": 0.0002,
|
| 1835 |
+
"loss": 0.8264,
|
| 1836 |
+
"step": 286
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 2.33,
|
| 1840 |
+
"learning_rate": 0.0002,
|
| 1841 |
+
"loss": 0.7954,
|
| 1842 |
+
"step": 287
|
| 1843 |
+
},
|
| 1844 |
+
{
|
| 1845 |
+
"epoch": 2.34,
|
| 1846 |
+
"learning_rate": 0.0002,
|
| 1847 |
+
"loss": 0.9375,
|
| 1848 |
+
"step": 288
|
| 1849 |
+
},
|
| 1850 |
+
{
|
| 1851 |
+
"epoch": 2.34,
|
| 1852 |
+
"learning_rate": 0.0002,
|
| 1853 |
+
"loss": 0.8495,
|
| 1854 |
+
"step": 289
|
| 1855 |
+
},
|
| 1856 |
+
{
|
| 1857 |
+
"epoch": 2.35,
|
| 1858 |
+
"learning_rate": 0.0002,
|
| 1859 |
+
"loss": 0.8029,
|
| 1860 |
+
"step": 290
|
| 1861 |
+
},
|
| 1862 |
+
{
|
| 1863 |
+
"epoch": 2.36,
|
| 1864 |
+
"learning_rate": 0.0002,
|
| 1865 |
+
"loss": 0.9309,
|
| 1866 |
+
"step": 291
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 2.37,
|
| 1870 |
+
"learning_rate": 0.0002,
|
| 1871 |
+
"loss": 0.895,
|
| 1872 |
+
"step": 292
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 2.38,
|
| 1876 |
+
"learning_rate": 0.0002,
|
| 1877 |
+
"loss": 0.7859,
|
| 1878 |
+
"step": 293
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 2.39,
|
| 1882 |
+
"learning_rate": 0.0002,
|
| 1883 |
+
"loss": 0.9474,
|
| 1884 |
+
"step": 294
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 2.39,
|
| 1888 |
+
"learning_rate": 0.0002,
|
| 1889 |
+
"loss": 0.8534,
|
| 1890 |
+
"step": 295
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"epoch": 2.4,
|
| 1894 |
+
"learning_rate": 0.0002,
|
| 1895 |
+
"loss": 0.8233,
|
| 1896 |
+
"step": 296
|
| 1897 |
+
},
|
| 1898 |
+
{
|
| 1899 |
+
"epoch": 2.41,
|
| 1900 |
+
"learning_rate": 0.0002,
|
| 1901 |
+
"loss": 0.85,
|
| 1902 |
+
"step": 297
|
| 1903 |
+
},
|
| 1904 |
+
{
|
| 1905 |
+
"epoch": 2.42,
|
| 1906 |
+
"learning_rate": 0.0002,
|
| 1907 |
+
"loss": 0.9265,
|
| 1908 |
+
"step": 298
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 2.43,
|
| 1912 |
+
"learning_rate": 0.0002,
|
| 1913 |
+
"loss": 0.8192,
|
| 1914 |
+
"step": 299
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 2.43,
|
| 1918 |
+
"learning_rate": 0.0002,
|
| 1919 |
+
"loss": 0.8503,
|
| 1920 |
+
"step": 300
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 2.43,
|
| 1924 |
+
"eval_loss": 0.9363464117050171,
|
| 1925 |
+
"eval_runtime": 104.4808,
|
| 1926 |
+
"eval_samples_per_second": 31.891,
|
| 1927 |
+
"eval_steps_per_second": 0.258,
|
| 1928 |
+
"step": 300
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 2.44,
|
| 1932 |
+
"learning_rate": 0.0002,
|
| 1933 |
+
"loss": 0.9259,
|
| 1934 |
+
"step": 301
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 2.45,
|
| 1938 |
+
"learning_rate": 0.0002,
|
| 1939 |
+
"loss": 0.8339,
|
| 1940 |
+
"step": 302
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 2.46,
|
| 1944 |
+
"learning_rate": 0.0002,
|
| 1945 |
+
"loss": 0.8471,
|
| 1946 |
+
"step": 303
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 2.47,
|
| 1950 |
+
"learning_rate": 0.0002,
|
| 1951 |
+
"loss": 0.9809,
|
| 1952 |
+
"step": 304
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 2.47,
|
| 1956 |
+
"learning_rate": 0.0002,
|
| 1957 |
+
"loss": 0.8134,
|
| 1958 |
+
"step": 305
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 2.48,
|
| 1962 |
+
"learning_rate": 0.0002,
|
| 1963 |
+
"loss": 0.8459,
|
| 1964 |
+
"step": 306
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 2.49,
|
| 1968 |
+
"learning_rate": 0.0002,
|
| 1969 |
+
"loss": 0.9366,
|
| 1970 |
+
"step": 307
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 2.5,
|
| 1974 |
+
"learning_rate": 0.0002,
|
| 1975 |
+
"loss": 0.8253,
|
| 1976 |
+
"step": 308
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 2.51,
|
| 1980 |
+
"learning_rate": 0.0002,
|
| 1981 |
+
"loss": 0.786,
|
| 1982 |
+
"step": 309
|
| 1983 |
+
},
|
| 1984 |
+
{
|
| 1985 |
+
"epoch": 2.52,
|
| 1986 |
+
"learning_rate": 0.0002,
|
| 1987 |
+
"loss": 0.9092,
|
| 1988 |
+
"step": 310
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 2.52,
|
| 1992 |
+
"learning_rate": 0.0002,
|
| 1993 |
+
"loss": 0.8864,
|
| 1994 |
+
"step": 311
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 2.53,
|
| 1998 |
+
"learning_rate": 0.0002,
|
| 1999 |
+
"loss": 0.8244,
|
| 2000 |
+
"step": 312
|
| 2001 |
+
},
|
| 2002 |
+
{
|
| 2003 |
+
"epoch": 2.54,
|
| 2004 |
+
"learning_rate": 0.0002,
|
| 2005 |
+
"loss": 0.9474,
|
| 2006 |
+
"step": 313
|
| 2007 |
+
},
|
| 2008 |
+
{
|
| 2009 |
+
"epoch": 2.55,
|
| 2010 |
+
"learning_rate": 0.0002,
|
| 2011 |
+
"loss": 0.818,
|
| 2012 |
+
"step": 314
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 2.56,
|
| 2016 |
+
"learning_rate": 0.0002,
|
| 2017 |
+
"loss": 0.8447,
|
| 2018 |
+
"step": 315
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 2.56,
|
| 2022 |
+
"learning_rate": 0.0002,
|
| 2023 |
+
"loss": 0.9267,
|
| 2024 |
+
"step": 316
|
| 2025 |
+
},
|
| 2026 |
+
{
|
| 2027 |
+
"epoch": 2.57,
|
| 2028 |
+
"learning_rate": 0.0002,
|
| 2029 |
+
"loss": 0.8774,
|
| 2030 |
+
"step": 317
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 2.58,
|
| 2034 |
+
"learning_rate": 0.0002,
|
| 2035 |
+
"loss": 0.8042,
|
| 2036 |
+
"step": 318
|
| 2037 |
+
},
|
| 2038 |
+
{
|
| 2039 |
+
"epoch": 2.59,
|
| 2040 |
+
"learning_rate": 0.0002,
|
| 2041 |
+
"loss": 0.8845,
|
| 2042 |
+
"step": 319
|
| 2043 |
+
},
|
| 2044 |
+
{
|
| 2045 |
+
"epoch": 2.6,
|
| 2046 |
+
"learning_rate": 0.0002,
|
| 2047 |
+
"loss": 0.8749,
|
| 2048 |
+
"step": 320
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 2.6,
|
| 2052 |
+
"eval_loss": 0.9298563003540039,
|
| 2053 |
+
"eval_runtime": 104.4409,
|
| 2054 |
+
"eval_samples_per_second": 31.903,
|
| 2055 |
+
"eval_steps_per_second": 0.259,
|
| 2056 |
+
"step": 320
|
| 2057 |
+
},
|
| 2058 |
+
{
|
| 2059 |
+
"epoch": 2.6,
|
| 2060 |
+
"step": 320,
|
| 2061 |
+
"total_flos": 1.8893507662761165e+19,
|
| 2062 |
+
"train_loss": 0.9615403175354004,
|
| 2063 |
+
"train_runtime": 23129.1803,
|
| 2064 |
+
"train_samples_per_second": 13.641,
|
| 2065 |
+
"train_steps_per_second": 0.027
|
| 2066 |
+
}
|
| 2067 |
+
],
|
| 2068 |
+
"max_steps": 615,
|
| 2069 |
+
"num_train_epochs": 5,
|
| 2070 |
+
"total_flos": 1.8893507662761165e+19,
|
| 2071 |
+
"trial_name": null,
|
| 2072 |
+
"trial_params": null
|
| 2073 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68e717ecf488cca439e51599d2fda491e398706ab72775dee6d1bae3477460f5
|
| 3 |
+
size 5627
|