Model save
Browse files- README.md +65 -0
- adapter_model.safetensors +1 -1
- all_results.json +13 -0
- eval_results.json +8 -0
- runs/Mar21_17-44-48_586cb8b6da8c/events.out.tfevents.1711043107.586cb8b6da8c.31404.0 +2 -2
- runs/Mar21_17-44-48_586cb8b6da8c/events.out.tfevents.1711043821.586cb8b6da8c.31404.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +1460 -0
README.md
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: alignment-handbook/zephyr-7b-sft-full
|
| 9 |
+
model-index:
|
| 10 |
+
- name: zephyr-7b-sft-qlora-mctaco
|
| 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 |
+
# zephyr-7b-sft-qlora-mctaco
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.1047
|
| 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: 0.0002
|
| 41 |
+
- train_batch_size: 4
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- gradient_accumulation_steps: 2
|
| 46 |
+
- total_train_batch_size: 8
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
+
- num_epochs: 1
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 56 |
+
| 0.1162 | 1.0 | 1180 | 0.1047 |
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
### Framework versions
|
| 60 |
+
|
| 61 |
+
- PEFT 0.7.1
|
| 62 |
+
- Transformers 4.36.2
|
| 63 |
+
- Pytorch 2.1.2+cu121
|
| 64 |
+
- Datasets 2.14.6
|
| 65 |
+
- Tokenizers 0.15.2
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 42002584
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88c62429e7c76c30146c5f07e6c76102d01108c5aa50c5a1abb1be7aafed373c
|
| 3 |
size 42002584
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 0.10465715825557709,
|
| 4 |
+
"eval_runtime": 0.1011,
|
| 5 |
+
"eval_samples": 5,
|
| 6 |
+
"eval_samples_per_second": 49.464,
|
| 7 |
+
"eval_steps_per_second": 9.893,
|
| 8 |
+
"train_loss": 0.2257307288000139,
|
| 9 |
+
"train_runtime": 713.6543,
|
| 10 |
+
"train_samples": 9442,
|
| 11 |
+
"train_samples_per_second": 13.23,
|
| 12 |
+
"train_steps_per_second": 1.653
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 0.10465715825557709,
|
| 4 |
+
"eval_runtime": 0.1011,
|
| 5 |
+
"eval_samples": 5,
|
| 6 |
+
"eval_samples_per_second": 49.464,
|
| 7 |
+
"eval_steps_per_second": 9.893
|
| 8 |
+
}
|
runs/Mar21_17-44-48_586cb8b6da8c/events.out.tfevents.1711043107.586cb8b6da8c.31404.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97ec31001f08721ce117c992593a4cb51cecde3ec9edc8f0bbab8fc3e8e4c6f9
|
| 3 |
+
size 42228
|
runs/Mar21_17-44-48_586cb8b6da8c/events.out.tfevents.1711043821.586cb8b6da8c.31404.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6e5a1ee936517e7417f425c65d1900cdf1c6a0da96fe72c1ae5e4de6905b324
|
| 3 |
+
size 359
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.2257307288000139,
|
| 4 |
+
"train_runtime": 713.6543,
|
| 5 |
+
"train_samples": 9442,
|
| 6 |
+
"train_samples_per_second": 13.23,
|
| 7 |
+
"train_steps_per_second": 1.653
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1460 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9995764506565015,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1180,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 1.6949152542372882e-06,
|
| 14 |
+
"loss": 1.9981,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.0,
|
| 19 |
+
"learning_rate": 8.47457627118644e-06,
|
| 20 |
+
"loss": 2.0358,
|
| 21 |
+
"step": 5
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 1.694915254237288e-05,
|
| 26 |
+
"loss": 1.9674,
|
| 27 |
+
"step": 10
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.01,
|
| 31 |
+
"learning_rate": 2.5423728813559322e-05,
|
| 32 |
+
"loss": 1.6753,
|
| 33 |
+
"step": 15
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.02,
|
| 37 |
+
"learning_rate": 3.389830508474576e-05,
|
| 38 |
+
"loss": 1.277,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.02,
|
| 43 |
+
"learning_rate": 4.2372881355932206e-05,
|
| 44 |
+
"loss": 0.9453,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.03,
|
| 49 |
+
"learning_rate": 5.0847457627118643e-05,
|
| 50 |
+
"loss": 0.7953,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03,
|
| 55 |
+
"learning_rate": 5.932203389830509e-05,
|
| 56 |
+
"loss": 0.7426,
|
| 57 |
+
"step": 35
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.03,
|
| 61 |
+
"learning_rate": 6.779661016949152e-05,
|
| 62 |
+
"loss": 0.6909,
|
| 63 |
+
"step": 40
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.04,
|
| 67 |
+
"learning_rate": 7.627118644067796e-05,
|
| 68 |
+
"loss": 0.723,
|
| 69 |
+
"step": 45
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.04,
|
| 73 |
+
"learning_rate": 8.474576271186441e-05,
|
| 74 |
+
"loss": 0.6646,
|
| 75 |
+
"step": 50
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.05,
|
| 79 |
+
"learning_rate": 9.322033898305085e-05,
|
| 80 |
+
"loss": 0.6685,
|
| 81 |
+
"step": 55
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.05,
|
| 85 |
+
"learning_rate": 0.00010169491525423729,
|
| 86 |
+
"loss": 0.6565,
|
| 87 |
+
"step": 60
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.06,
|
| 91 |
+
"learning_rate": 0.00011016949152542372,
|
| 92 |
+
"loss": 0.6032,
|
| 93 |
+
"step": 65
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.06,
|
| 97 |
+
"learning_rate": 0.00011864406779661017,
|
| 98 |
+
"loss": 0.6357,
|
| 99 |
+
"step": 70
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.06,
|
| 103 |
+
"learning_rate": 0.0001271186440677966,
|
| 104 |
+
"loss": 0.641,
|
| 105 |
+
"step": 75
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.07,
|
| 109 |
+
"learning_rate": 0.00013559322033898305,
|
| 110 |
+
"loss": 0.581,
|
| 111 |
+
"step": 80
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.07,
|
| 115 |
+
"learning_rate": 0.00014406779661016949,
|
| 116 |
+
"loss": 0.5263,
|
| 117 |
+
"step": 85
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.08,
|
| 121 |
+
"learning_rate": 0.00015254237288135592,
|
| 122 |
+
"loss": 0.5573,
|
| 123 |
+
"step": 90
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.08,
|
| 127 |
+
"learning_rate": 0.00016101694915254236,
|
| 128 |
+
"loss": 0.4486,
|
| 129 |
+
"step": 95
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.08,
|
| 133 |
+
"learning_rate": 0.00016949152542372882,
|
| 134 |
+
"loss": 0.4374,
|
| 135 |
+
"step": 100
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.09,
|
| 139 |
+
"learning_rate": 0.00017796610169491526,
|
| 140 |
+
"loss": 0.4425,
|
| 141 |
+
"step": 105
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.09,
|
| 145 |
+
"learning_rate": 0.0001864406779661017,
|
| 146 |
+
"loss": 0.4849,
|
| 147 |
+
"step": 110
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.1,
|
| 151 |
+
"learning_rate": 0.00019491525423728814,
|
| 152 |
+
"loss": 0.3484,
|
| 153 |
+
"step": 115
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.1,
|
| 157 |
+
"learning_rate": 0.00019999824983320177,
|
| 158 |
+
"loss": 0.3903,
|
| 159 |
+
"step": 120
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.11,
|
| 163 |
+
"learning_rate": 0.00019997856116026692,
|
| 164 |
+
"loss": 0.3913,
|
| 165 |
+
"step": 125
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.11,
|
| 169 |
+
"learning_rate": 0.00019993700042749937,
|
| 170 |
+
"loss": 0.3313,
|
| 171 |
+
"step": 130
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.11,
|
| 175 |
+
"learning_rate": 0.00019987357672703672,
|
| 176 |
+
"loss": 0.3447,
|
| 177 |
+
"step": 135
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.12,
|
| 181 |
+
"learning_rate": 0.0001997883039339234,
|
| 182 |
+
"loss": 0.3978,
|
| 183 |
+
"step": 140
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.12,
|
| 187 |
+
"learning_rate": 0.000199681200703075,
|
| 188 |
+
"loss": 0.3689,
|
| 189 |
+
"step": 145
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.13,
|
| 193 |
+
"learning_rate": 0.0001995522904651977,
|
| 194 |
+
"loss": 0.3055,
|
| 195 |
+
"step": 150
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.13,
|
| 199 |
+
"learning_rate": 0.00019940160142166172,
|
| 200 |
+
"loss": 0.3499,
|
| 201 |
+
"step": 155
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.14,
|
| 205 |
+
"learning_rate": 0.00019922916653833248,
|
| 206 |
+
"loss": 0.3107,
|
| 207 |
+
"step": 160
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.14,
|
| 211 |
+
"learning_rate": 0.00019903502353835813,
|
| 212 |
+
"loss": 0.313,
|
| 213 |
+
"step": 165
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.14,
|
| 217 |
+
"learning_rate": 0.00019881921489391737,
|
| 218 |
+
"loss": 0.3267,
|
| 219 |
+
"step": 170
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.15,
|
| 223 |
+
"learning_rate": 0.00019858178781692774,
|
| 224 |
+
"loss": 0.3396,
|
| 225 |
+
"step": 175
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.15,
|
| 229 |
+
"learning_rate": 0.00019832279424871719,
|
| 230 |
+
"loss": 0.3315,
|
| 231 |
+
"step": 180
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.16,
|
| 235 |
+
"learning_rate": 0.00019804229084866102,
|
| 236 |
+
"loss": 0.2894,
|
| 237 |
+
"step": 185
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.16,
|
| 241 |
+
"learning_rate": 0.00019774033898178667,
|
| 242 |
+
"loss": 0.2326,
|
| 243 |
+
"step": 190
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.17,
|
| 247 |
+
"learning_rate": 0.00019741700470534906,
|
| 248 |
+
"loss": 0.2904,
|
| 249 |
+
"step": 195
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.17,
|
| 253 |
+
"learning_rate": 0.00019707235875437933,
|
| 254 |
+
"loss": 0.2489,
|
| 255 |
+
"step": 200
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.17,
|
| 259 |
+
"learning_rate": 0.00019670647652621041,
|
| 260 |
+
"loss": 0.231,
|
| 261 |
+
"step": 205
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.18,
|
| 265 |
+
"learning_rate": 0.00019631943806398252,
|
| 266 |
+
"loss": 0.2691,
|
| 267 |
+
"step": 210
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.18,
|
| 271 |
+
"learning_rate": 0.0001959113280391322,
|
| 272 |
+
"loss": 0.3092,
|
| 273 |
+
"step": 215
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.19,
|
| 277 |
+
"learning_rate": 0.0001954822357328692,
|
| 278 |
+
"loss": 0.2461,
|
| 279 |
+
"step": 220
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.19,
|
| 283 |
+
"learning_rate": 0.0001950322550166444,
|
| 284 |
+
"loss": 0.2451,
|
| 285 |
+
"step": 225
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.19,
|
| 289 |
+
"learning_rate": 0.00019456148433161387,
|
| 290 |
+
"loss": 0.2183,
|
| 291 |
+
"step": 230
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.2,
|
| 295 |
+
"learning_rate": 0.00019407002666710336,
|
| 296 |
+
"loss": 0.2332,
|
| 297 |
+
"step": 235
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.2,
|
| 301 |
+
"learning_rate": 0.00019355798953807715,
|
| 302 |
+
"loss": 0.2203,
|
| 303 |
+
"step": 240
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.21,
|
| 307 |
+
"learning_rate": 0.00019302548496161765,
|
| 308 |
+
"loss": 0.2358,
|
| 309 |
+
"step": 245
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.21,
|
| 313 |
+
"learning_rate": 0.0001924726294324196,
|
| 314 |
+
"loss": 0.2191,
|
| 315 |
+
"step": 250
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.22,
|
| 319 |
+
"learning_rate": 0.00019189954389730468,
|
| 320 |
+
"loss": 0.2226,
|
| 321 |
+
"step": 255
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.22,
|
| 325 |
+
"learning_rate": 0.00019130635372876246,
|
| 326 |
+
"loss": 0.2194,
|
| 327 |
+
"step": 260
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.22,
|
| 331 |
+
"learning_rate": 0.00019069318869752283,
|
| 332 |
+
"loss": 0.1904,
|
| 333 |
+
"step": 265
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.23,
|
| 337 |
+
"learning_rate": 0.00019006018294416647,
|
| 338 |
+
"loss": 0.2449,
|
| 339 |
+
"step": 270
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.23,
|
| 343 |
+
"learning_rate": 0.00018940747494977932,
|
| 344 |
+
"loss": 0.2084,
|
| 345 |
+
"step": 275
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.24,
|
| 349 |
+
"learning_rate": 0.00018873520750565718,
|
| 350 |
+
"loss": 0.2174,
|
| 351 |
+
"step": 280
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.24,
|
| 355 |
+
"learning_rate": 0.00018804352768206782,
|
| 356 |
+
"loss": 0.2243,
|
| 357 |
+
"step": 285
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.25,
|
| 361 |
+
"learning_rate": 0.00018733258679607672,
|
| 362 |
+
"loss": 0.1996,
|
| 363 |
+
"step": 290
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.25,
|
| 367 |
+
"learning_rate": 0.00018660254037844388,
|
| 368 |
+
"loss": 0.2254,
|
| 369 |
+
"step": 295
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.25,
|
| 373 |
+
"learning_rate": 0.00018585354813959858,
|
| 374 |
+
"loss": 0.2027,
|
| 375 |
+
"step": 300
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.26,
|
| 379 |
+
"learning_rate": 0.00018508577393470013,
|
| 380 |
+
"loss": 0.2096,
|
| 381 |
+
"step": 305
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.26,
|
| 385 |
+
"learning_rate": 0.00018429938572779152,
|
| 386 |
+
"loss": 0.1661,
|
| 387 |
+
"step": 310
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.27,
|
| 391 |
+
"learning_rate": 0.00018349455555505446,
|
| 392 |
+
"loss": 0.2263,
|
| 393 |
+
"step": 315
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.27,
|
| 397 |
+
"learning_rate": 0.00018267145948717338,
|
| 398 |
+
"loss": 0.1851,
|
| 399 |
+
"step": 320
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.28,
|
| 403 |
+
"learning_rate": 0.0001818302775908169,
|
| 404 |
+
"loss": 0.1796,
|
| 405 |
+
"step": 325
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.28,
|
| 409 |
+
"learning_rate": 0.00018097119388924525,
|
| 410 |
+
"loss": 0.1906,
|
| 411 |
+
"step": 330
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.28,
|
| 415 |
+
"learning_rate": 0.0001800943963220516,
|
| 416 |
+
"loss": 0.1766,
|
| 417 |
+
"step": 335
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.29,
|
| 421 |
+
"learning_rate": 0.0001792000767040474,
|
| 422 |
+
"loss": 0.1615,
|
| 423 |
+
"step": 340
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.29,
|
| 427 |
+
"learning_rate": 0.00017828843068329924,
|
| 428 |
+
"loss": 0.1624,
|
| 429 |
+
"step": 345
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.3,
|
| 433 |
+
"learning_rate": 0.00017735965769832753,
|
| 434 |
+
"loss": 0.1694,
|
| 435 |
+
"step": 350
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.3,
|
| 439 |
+
"learning_rate": 0.00017641396093447592,
|
| 440 |
+
"loss": 0.18,
|
| 441 |
+
"step": 355
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.3,
|
| 445 |
+
"learning_rate": 0.00017545154727946065,
|
| 446 |
+
"loss": 0.1672,
|
| 447 |
+
"step": 360
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.31,
|
| 451 |
+
"learning_rate": 0.00017447262727811062,
|
| 452 |
+
"loss": 0.1708,
|
| 453 |
+
"step": 365
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.31,
|
| 457 |
+
"learning_rate": 0.00017347741508630672,
|
| 458 |
+
"loss": 0.1739,
|
| 459 |
+
"step": 370
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.32,
|
| 463 |
+
"learning_rate": 0.00017246612842413173,
|
| 464 |
+
"loss": 0.1595,
|
| 465 |
+
"step": 375
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.32,
|
| 469 |
+
"learning_rate": 0.00017143898852824003,
|
| 470 |
+
"loss": 0.1739,
|
| 471 |
+
"step": 380
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.33,
|
| 475 |
+
"learning_rate": 0.0001703962201034583,
|
| 476 |
+
"loss": 0.1701,
|
| 477 |
+
"step": 385
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.33,
|
| 481 |
+
"learning_rate": 0.00016933805127362743,
|
| 482 |
+
"loss": 0.1549,
|
| 483 |
+
"step": 390
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.33,
|
| 487 |
+
"learning_rate": 0.00016826471353169646,
|
| 488 |
+
"loss": 0.1693,
|
| 489 |
+
"step": 395
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.34,
|
| 493 |
+
"learning_rate": 0.0001671764416890793,
|
| 494 |
+
"loss": 0.1541,
|
| 495 |
+
"step": 400
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.34,
|
| 499 |
+
"learning_rate": 0.00016607347382428578,
|
| 500 |
+
"loss": 0.1554,
|
| 501 |
+
"step": 405
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.35,
|
| 505 |
+
"learning_rate": 0.0001649560512308378,
|
| 506 |
+
"loss": 0.1635,
|
| 507 |
+
"step": 410
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.35,
|
| 511 |
+
"learning_rate": 0.00016382441836448202,
|
| 512 |
+
"loss": 0.1499,
|
| 513 |
+
"step": 415
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.36,
|
| 517 |
+
"learning_rate": 0.00016267882278971101,
|
| 518 |
+
"loss": 0.1501,
|
| 519 |
+
"step": 420
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.36,
|
| 523 |
+
"learning_rate": 0.0001615195151256042,
|
| 524 |
+
"loss": 0.1634,
|
| 525 |
+
"step": 425
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.36,
|
| 529 |
+
"learning_rate": 0.0001603467489910004,
|
| 530 |
+
"loss": 0.1623,
|
| 531 |
+
"step": 430
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.37,
|
| 535 |
+
"learning_rate": 0.00015916078094901445,
|
| 536 |
+
"loss": 0.1666,
|
| 537 |
+
"step": 435
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.37,
|
| 541 |
+
"learning_rate": 0.00015796187045090943,
|
| 542 |
+
"loss": 0.1718,
|
| 543 |
+
"step": 440
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.38,
|
| 547 |
+
"learning_rate": 0.0001567502797793372,
|
| 548 |
+
"loss": 0.162,
|
| 549 |
+
"step": 445
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.38,
|
| 553 |
+
"learning_rate": 0.0001555262739909594,
|
| 554 |
+
"loss": 0.166,
|
| 555 |
+
"step": 450
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.39,
|
| 559 |
+
"learning_rate": 0.00015429012085846182,
|
| 560 |
+
"loss": 0.1682,
|
| 561 |
+
"step": 455
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.39,
|
| 565 |
+
"learning_rate": 0.00015304209081197425,
|
| 566 |
+
"loss": 0.172,
|
| 567 |
+
"step": 460
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.39,
|
| 571 |
+
"learning_rate": 0.00015178245687990938,
|
| 572 |
+
"loss": 0.1414,
|
| 573 |
+
"step": 465
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.4,
|
| 577 |
+
"learning_rate": 0.00015051149462923285,
|
| 578 |
+
"loss": 0.1778,
|
| 579 |
+
"step": 470
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.4,
|
| 583 |
+
"learning_rate": 0.00014922948210517822,
|
| 584 |
+
"loss": 0.1411,
|
| 585 |
+
"step": 475
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.41,
|
| 589 |
+
"learning_rate": 0.00014793669977041977,
|
| 590 |
+
"loss": 0.156,
|
| 591 |
+
"step": 480
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.41,
|
| 595 |
+
"learning_rate": 0.00014663343044371633,
|
| 596 |
+
"loss": 0.1383,
|
| 597 |
+
"step": 485
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.42,
|
| 601 |
+
"learning_rate": 0.00014531995923803973,
|
| 602 |
+
"loss": 0.1653,
|
| 603 |
+
"step": 490
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.42,
|
| 607 |
+
"learning_rate": 0.00014399657349820134,
|
| 608 |
+
"loss": 0.1507,
|
| 609 |
+
"step": 495
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.42,
|
| 613 |
+
"learning_rate": 0.00014266356273799044,
|
| 614 |
+
"loss": 0.1413,
|
| 615 |
+
"step": 500
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.43,
|
| 619 |
+
"learning_rate": 0.00014132121857683783,
|
| 620 |
+
"loss": 0.1659,
|
| 621 |
+
"step": 505
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.43,
|
| 625 |
+
"learning_rate": 0.0001399698346760192,
|
| 626 |
+
"loss": 0.1468,
|
| 627 |
+
"step": 510
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.44,
|
| 631 |
+
"learning_rate": 0.00013860970667441147,
|
| 632 |
+
"loss": 0.1211,
|
| 633 |
+
"step": 515
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.44,
|
| 637 |
+
"learning_rate": 0.0001372411321238166,
|
| 638 |
+
"loss": 0.1353,
|
| 639 |
+
"step": 520
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.44,
|
| 643 |
+
"learning_rate": 0.00013586441042386693,
|
| 644 |
+
"loss": 0.1566,
|
| 645 |
+
"step": 525
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.45,
|
| 649 |
+
"learning_rate": 0.00013447984275652636,
|
| 650 |
+
"loss": 0.1449,
|
| 651 |
+
"step": 530
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.45,
|
| 655 |
+
"learning_rate": 0.0001330877320202014,
|
| 656 |
+
"loss": 0.1635,
|
| 657 |
+
"step": 535
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.46,
|
| 661 |
+
"learning_rate": 0.0001316883827634769,
|
| 662 |
+
"loss": 0.135,
|
| 663 |
+
"step": 540
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.46,
|
| 667 |
+
"learning_rate": 0.00013028210111849076,
|
| 668 |
+
"loss": 0.1441,
|
| 669 |
+
"step": 545
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.47,
|
| 673 |
+
"learning_rate": 0.0001288691947339621,
|
| 674 |
+
"loss": 0.1637,
|
| 675 |
+
"step": 550
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.47,
|
| 679 |
+
"learning_rate": 0.00012744997270788775,
|
| 680 |
+
"loss": 0.1479,
|
| 681 |
+
"step": 555
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.47,
|
| 685 |
+
"learning_rate": 0.00012602474551992165,
|
| 686 |
+
"loss": 0.1404,
|
| 687 |
+
"step": 560
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.48,
|
| 691 |
+
"learning_rate": 0.00012459382496345198,
|
| 692 |
+
"loss": 0.1442,
|
| 693 |
+
"step": 565
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.48,
|
| 697 |
+
"learning_rate": 0.00012315752407739093,
|
| 698 |
+
"loss": 0.1464,
|
| 699 |
+
"step": 570
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.49,
|
| 703 |
+
"learning_rate": 0.0001217161570776919,
|
| 704 |
+
"loss": 0.1337,
|
| 705 |
+
"step": 575
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.49,
|
| 709 |
+
"learning_rate": 0.00012027003928860937,
|
| 710 |
+
"loss": 0.1497,
|
| 711 |
+
"step": 580
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.5,
|
| 715 |
+
"learning_rate": 0.00011881948707371608,
|
| 716 |
+
"loss": 0.1451,
|
| 717 |
+
"step": 585
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.5,
|
| 721 |
+
"learning_rate": 0.00011736481776669306,
|
| 722 |
+
"loss": 0.1421,
|
| 723 |
+
"step": 590
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.5,
|
| 727 |
+
"learning_rate": 0.00011590634960190721,
|
| 728 |
+
"loss": 0.1286,
|
| 729 |
+
"step": 595
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.51,
|
| 733 |
+
"learning_rate": 0.00011444440164479215,
|
| 734 |
+
"loss": 0.1421,
|
| 735 |
+
"step": 600
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.51,
|
| 739 |
+
"learning_rate": 0.00011297929372204692,
|
| 740 |
+
"loss": 0.1374,
|
| 741 |
+
"step": 605
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.52,
|
| 745 |
+
"learning_rate": 0.00011151134635166829,
|
| 746 |
+
"loss": 0.1502,
|
| 747 |
+
"step": 610
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.52,
|
| 751 |
+
"learning_rate": 0.000110040880672832,
|
| 752 |
+
"loss": 0.159,
|
| 753 |
+
"step": 615
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.53,
|
| 757 |
+
"learning_rate": 0.00010856821837563769,
|
| 758 |
+
"loss": 0.1316,
|
| 759 |
+
"step": 620
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.53,
|
| 763 |
+
"learning_rate": 0.00010709368163073386,
|
| 764 |
+
"loss": 0.1271,
|
| 765 |
+
"step": 625
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.53,
|
| 769 |
+
"learning_rate": 0.00010561759301883714,
|
| 770 |
+
"loss": 0.1289,
|
| 771 |
+
"step": 630
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.54,
|
| 775 |
+
"learning_rate": 0.00010414027546016222,
|
| 776 |
+
"loss": 0.146,
|
| 777 |
+
"step": 635
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.54,
|
| 781 |
+
"learning_rate": 0.00010266205214377748,
|
| 782 |
+
"loss": 0.1417,
|
| 783 |
+
"step": 640
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.55,
|
| 787 |
+
"learning_rate": 0.00010118324645690161,
|
| 788 |
+
"loss": 0.1563,
|
| 789 |
+
"step": 645
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.55,
|
| 793 |
+
"learning_rate": 9.970418191415703e-05,
|
| 794 |
+
"loss": 0.1432,
|
| 795 |
+
"step": 650
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.55,
|
| 799 |
+
"learning_rate": 9.822518208679542e-05,
|
| 800 |
+
"loss": 0.1336,
|
| 801 |
+
"step": 655
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.56,
|
| 805 |
+
"learning_rate": 9.674657053191079e-05,
|
| 806 |
+
"loss": 0.1216,
|
| 807 |
+
"step": 660
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.56,
|
| 811 |
+
"learning_rate": 9.526867072165581e-05,
|
| 812 |
+
"loss": 0.1379,
|
| 813 |
+
"step": 665
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.57,
|
| 817 |
+
"learning_rate": 9.379180597247661e-05,
|
| 818 |
+
"loss": 0.1471,
|
| 819 |
+
"step": 670
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.57,
|
| 823 |
+
"learning_rate": 9.231629937438142e-05,
|
| 824 |
+
"loss": 0.1385,
|
| 825 |
+
"step": 675
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.58,
|
| 829 |
+
"learning_rate": 9.084247372025937e-05,
|
| 830 |
+
"loss": 0.1532,
|
| 831 |
+
"step": 680
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.58,
|
| 835 |
+
"learning_rate": 8.937065143526347e-05,
|
| 836 |
+
"loss": 0.1337,
|
| 837 |
+
"step": 685
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.58,
|
| 841 |
+
"learning_rate": 8.790115450627485e-05,
|
| 842 |
+
"loss": 0.1539,
|
| 843 |
+
"step": 690
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.59,
|
| 847 |
+
"learning_rate": 8.64343044114622e-05,
|
| 848 |
+
"loss": 0.1218,
|
| 849 |
+
"step": 695
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.59,
|
| 853 |
+
"learning_rate": 8.497042204995299e-05,
|
| 854 |
+
"loss": 0.1282,
|
| 855 |
+
"step": 700
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.6,
|
| 859 |
+
"learning_rate": 8.350982767163104e-05,
|
| 860 |
+
"loss": 0.1215,
|
| 861 |
+
"step": 705
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.6,
|
| 865 |
+
"learning_rate": 8.205284080707634e-05,
|
| 866 |
+
"loss": 0.129,
|
| 867 |
+
"step": 710
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.61,
|
| 871 |
+
"learning_rate": 8.059978019766219e-05,
|
| 872 |
+
"loss": 0.1435,
|
| 873 |
+
"step": 715
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.61,
|
| 877 |
+
"learning_rate": 7.915096372582466e-05,
|
| 878 |
+
"loss": 0.1378,
|
| 879 |
+
"step": 720
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.61,
|
| 883 |
+
"learning_rate": 7.770670834552074e-05,
|
| 884 |
+
"loss": 0.1361,
|
| 885 |
+
"step": 725
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.62,
|
| 889 |
+
"learning_rate": 7.626733001288851e-05,
|
| 890 |
+
"loss": 0.127,
|
| 891 |
+
"step": 730
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.62,
|
| 895 |
+
"learning_rate": 7.483314361712685e-05,
|
| 896 |
+
"loss": 0.1344,
|
| 897 |
+
"step": 735
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.63,
|
| 901 |
+
"learning_rate": 7.340446291160732e-05,
|
| 902 |
+
"loss": 0.1439,
|
| 903 |
+
"step": 740
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.63,
|
| 907 |
+
"learning_rate": 7.198160044523554e-05,
|
| 908 |
+
"loss": 0.1239,
|
| 909 |
+
"step": 745
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.64,
|
| 913 |
+
"learning_rate": 7.056486749407551e-05,
|
| 914 |
+
"loss": 0.135,
|
| 915 |
+
"step": 750
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.64,
|
| 919 |
+
"learning_rate": 6.915457399325242e-05,
|
| 920 |
+
"loss": 0.1532,
|
| 921 |
+
"step": 755
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.64,
|
| 925 |
+
"learning_rate": 6.775102846914911e-05,
|
| 926 |
+
"loss": 0.1206,
|
| 927 |
+
"step": 760
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.65,
|
| 931 |
+
"learning_rate": 6.635453797191034e-05,
|
| 932 |
+
"loss": 0.1312,
|
| 933 |
+
"step": 765
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.65,
|
| 937 |
+
"learning_rate": 6.496540800827036e-05,
|
| 938 |
+
"loss": 0.1366,
|
| 939 |
+
"step": 770
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.66,
|
| 943 |
+
"learning_rate": 6.358394247471778e-05,
|
| 944 |
+
"loss": 0.1473,
|
| 945 |
+
"step": 775
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.66,
|
| 949 |
+
"learning_rate": 6.221044359101317e-05,
|
| 950 |
+
"loss": 0.13,
|
| 951 |
+
"step": 780
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 0.66,
|
| 955 |
+
"learning_rate": 6.084521183407286e-05,
|
| 956 |
+
"loss": 0.1126,
|
| 957 |
+
"step": 785
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.67,
|
| 961 |
+
"learning_rate": 5.9488545872234645e-05,
|
| 962 |
+
"loss": 0.1235,
|
| 963 |
+
"step": 790
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.67,
|
| 967 |
+
"learning_rate": 5.8140742499918756e-05,
|
| 968 |
+
"loss": 0.1425,
|
| 969 |
+
"step": 795
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.68,
|
| 973 |
+
"learning_rate": 5.680209657269871e-05,
|
| 974 |
+
"loss": 0.1386,
|
| 975 |
+
"step": 800
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.68,
|
| 979 |
+
"learning_rate": 5.547290094279687e-05,
|
| 980 |
+
"loss": 0.1325,
|
| 981 |
+
"step": 805
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.69,
|
| 985 |
+
"learning_rate": 5.4153446395017537e-05,
|
| 986 |
+
"loss": 0.1237,
|
| 987 |
+
"step": 810
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 0.69,
|
| 991 |
+
"learning_rate": 5.2844021583132983e-05,
|
| 992 |
+
"loss": 0.126,
|
| 993 |
+
"step": 815
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 0.69,
|
| 997 |
+
"learning_rate": 5.1544912966734994e-05,
|
| 998 |
+
"loss": 0.1205,
|
| 999 |
+
"step": 820
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.7,
|
| 1003 |
+
"learning_rate": 5.025640474856732e-05,
|
| 1004 |
+
"loss": 0.1358,
|
| 1005 |
+
"step": 825
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.7,
|
| 1009 |
+
"learning_rate": 4.897877881235091e-05,
|
| 1010 |
+
"loss": 0.1269,
|
| 1011 |
+
"step": 830
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.71,
|
| 1015 |
+
"learning_rate": 4.771231466111725e-05,
|
| 1016 |
+
"loss": 0.1173,
|
| 1017 |
+
"step": 835
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.71,
|
| 1021 |
+
"learning_rate": 4.645728935606194e-05,
|
| 1022 |
+
"loss": 0.1261,
|
| 1023 |
+
"step": 840
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.72,
|
| 1027 |
+
"learning_rate": 4.5213977455932785e-05,
|
| 1028 |
+
"loss": 0.1302,
|
| 1029 |
+
"step": 845
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.72,
|
| 1033 |
+
"learning_rate": 4.398265095696539e-05,
|
| 1034 |
+
"loss": 0.1237,
|
| 1035 |
+
"step": 850
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.72,
|
| 1039 |
+
"learning_rate": 4.2763579233379025e-05,
|
| 1040 |
+
"loss": 0.1214,
|
| 1041 |
+
"step": 855
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.73,
|
| 1045 |
+
"learning_rate": 4.155702897844641e-05,
|
| 1046 |
+
"loss": 0.1409,
|
| 1047 |
+
"step": 860
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 0.73,
|
| 1051 |
+
"learning_rate": 4.036326414614985e-05,
|
| 1052 |
+
"loss": 0.1182,
|
| 1053 |
+
"step": 865
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.74,
|
| 1057 |
+
"learning_rate": 3.918254589343683e-05,
|
| 1058 |
+
"loss": 0.138,
|
| 1059 |
+
"step": 870
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.74,
|
| 1063 |
+
"learning_rate": 3.8015132523087116e-05,
|
| 1064 |
+
"loss": 0.1221,
|
| 1065 |
+
"step": 875
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.75,
|
| 1069 |
+
"learning_rate": 3.686127942720463e-05,
|
| 1070 |
+
"loss": 0.1381,
|
| 1071 |
+
"step": 880
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 0.75,
|
| 1075 |
+
"learning_rate": 3.5721239031346066e-05,
|
| 1076 |
+
"loss": 0.1386,
|
| 1077 |
+
"step": 885
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 0.75,
|
| 1081 |
+
"learning_rate": 3.459526073929818e-05,
|
| 1082 |
+
"loss": 0.1145,
|
| 1083 |
+
"step": 890
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.76,
|
| 1087 |
+
"learning_rate": 3.3483590878516435e-05,
|
| 1088 |
+
"loss": 0.1108,
|
| 1089 |
+
"step": 895
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.76,
|
| 1093 |
+
"learning_rate": 3.2386472646236566e-05,
|
| 1094 |
+
"loss": 0.1218,
|
| 1095 |
+
"step": 900
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.77,
|
| 1099 |
+
"learning_rate": 3.1304146056271024e-05,
|
| 1100 |
+
"loss": 0.1142,
|
| 1101 |
+
"step": 905
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.77,
|
| 1105 |
+
"learning_rate": 3.0236847886501542e-05,
|
| 1106 |
+
"loss": 0.128,
|
| 1107 |
+
"step": 910
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 0.78,
|
| 1111 |
+
"learning_rate": 2.9184811627079987e-05,
|
| 1112 |
+
"loss": 0.1268,
|
| 1113 |
+
"step": 915
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 0.78,
|
| 1117 |
+
"learning_rate": 2.814826742934823e-05,
|
| 1118 |
+
"loss": 0.1271,
|
| 1119 |
+
"step": 920
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.78,
|
| 1123 |
+
"learning_rate": 2.7127442055488615e-05,
|
| 1124 |
+
"loss": 0.1205,
|
| 1125 |
+
"step": 925
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.79,
|
| 1129 |
+
"learning_rate": 2.6122558828915646e-05,
|
| 1130 |
+
"loss": 0.1196,
|
| 1131 |
+
"step": 930
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 0.79,
|
| 1135 |
+
"learning_rate": 2.5133837585420084e-05,
|
| 1136 |
+
"loss": 0.1305,
|
| 1137 |
+
"step": 935
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.8,
|
| 1141 |
+
"learning_rate": 2.4161494625076165e-05,
|
| 1142 |
+
"loss": 0.1213,
|
| 1143 |
+
"step": 940
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.8,
|
| 1147 |
+
"learning_rate": 2.3205742664922004e-05,
|
| 1148 |
+
"loss": 0.1308,
|
| 1149 |
+
"step": 945
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 0.8,
|
| 1153 |
+
"learning_rate": 2.2266790792424097e-05,
|
| 1154 |
+
"loss": 0.1229,
|
| 1155 |
+
"step": 950
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 0.81,
|
| 1159 |
+
"learning_rate": 2.1344844419735755e-05,
|
| 1160 |
+
"loss": 0.1212,
|
| 1161 |
+
"step": 955
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.81,
|
| 1165 |
+
"learning_rate": 2.0440105238759687e-05,
|
| 1166 |
+
"loss": 0.138,
|
| 1167 |
+
"step": 960
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 0.82,
|
| 1171 |
+
"learning_rate": 1.9552771177024242e-05,
|
| 1172 |
+
"loss": 0.119,
|
| 1173 |
+
"step": 965
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 0.82,
|
| 1177 |
+
"learning_rate": 1.868303635438332e-05,
|
| 1178 |
+
"loss": 0.118,
|
| 1179 |
+
"step": 970
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.83,
|
| 1183 |
+
"learning_rate": 1.7831091040549397e-05,
|
| 1184 |
+
"loss": 0.1286,
|
| 1185 |
+
"step": 975
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.83,
|
| 1189 |
+
"learning_rate": 1.6997121613468458e-05,
|
| 1190 |
+
"loss": 0.1292,
|
| 1191 |
+
"step": 980
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 0.83,
|
| 1195 |
+
"learning_rate": 1.6181310518546856e-05,
|
| 1196 |
+
"loss": 0.1232,
|
| 1197 |
+
"step": 985
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 0.84,
|
| 1201 |
+
"learning_rate": 1.5383836228737814e-05,
|
| 1202 |
+
"loss": 0.1282,
|
| 1203 |
+
"step": 990
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.84,
|
| 1207 |
+
"learning_rate": 1.4604873205497727e-05,
|
| 1208 |
+
"loss": 0.1235,
|
| 1209 |
+
"step": 995
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 0.85,
|
| 1213 |
+
"learning_rate": 1.3844591860619383e-05,
|
| 1214 |
+
"loss": 0.1266,
|
| 1215 |
+
"step": 1000
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 0.85,
|
| 1219 |
+
"learning_rate": 1.3103158518951618e-05,
|
| 1220 |
+
"loss": 0.1248,
|
| 1221 |
+
"step": 1005
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.86,
|
| 1225 |
+
"learning_rate": 1.2380735382012576e-05,
|
| 1226 |
+
"loss": 0.1321,
|
| 1227 |
+
"step": 1010
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.86,
|
| 1231 |
+
"learning_rate": 1.1677480492505588e-05,
|
| 1232 |
+
"loss": 0.1261,
|
| 1233 |
+
"step": 1015
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 0.86,
|
| 1237 |
+
"learning_rate": 1.0993547699744366e-05,
|
| 1238 |
+
"loss": 0.1274,
|
| 1239 |
+
"step": 1020
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 0.87,
|
| 1243 |
+
"learning_rate": 1.0329086625995843e-05,
|
| 1244 |
+
"loss": 0.1243,
|
| 1245 |
+
"step": 1025
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.87,
|
| 1249 |
+
"learning_rate": 9.684242633747642e-06,
|
| 1250 |
+
"loss": 0.1493,
|
| 1251 |
+
"step": 1030
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 0.88,
|
| 1255 |
+
"learning_rate": 9.059156793907541e-06,
|
| 1256 |
+
"loss": 0.1342,
|
| 1257 |
+
"step": 1035
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 0.88,
|
| 1261 |
+
"learning_rate": 8.453965854941748e-06,
|
| 1262 |
+
"loss": 0.1203,
|
| 1263 |
+
"step": 1040
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.89,
|
| 1267 |
+
"learning_rate": 7.868802212958703e-06,
|
| 1268 |
+
"loss": 0.1182,
|
| 1269 |
+
"step": 1045
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.89,
|
| 1273 |
+
"learning_rate": 7.3037938827451805e-06,
|
| 1274 |
+
"loss": 0.1373,
|
| 1275 |
+
"step": 1050
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 0.89,
|
| 1279 |
+
"learning_rate": 6.759064469760823e-06,
|
| 1280 |
+
"loss": 0.135,
|
| 1281 |
+
"step": 1055
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 0.9,
|
| 1285 |
+
"learning_rate": 6.234733143097216e-06,
|
| 1286 |
+
"loss": 0.1093,
|
| 1287 |
+
"step": 1060
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.9,
|
| 1291 |
+
"learning_rate": 5.730914609407634e-06,
|
| 1292 |
+
"loss": 0.1354,
|
| 1293 |
+
"step": 1065
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 0.91,
|
| 1297 |
+
"learning_rate": 5.247719087812897e-06,
|
| 1298 |
+
"loss": 0.1156,
|
| 1299 |
+
"step": 1070
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 0.91,
|
| 1303 |
+
"learning_rate": 4.785252285789077e-06,
|
| 1304 |
+
"loss": 0.1157,
|
| 1305 |
+
"step": 1075
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.91,
|
| 1309 |
+
"learning_rate": 4.3436153760420654e-06,
|
| 1310 |
+
"loss": 0.1402,
|
| 1311 |
+
"step": 1080
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.92,
|
| 1315 |
+
"learning_rate": 3.922904974374309e-06,
|
| 1316 |
+
"loss": 0.1291,
|
| 1317 |
+
"step": 1085
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 0.92,
|
| 1321 |
+
"learning_rate": 3.5232131185484076e-06,
|
| 1322 |
+
"loss": 0.1371,
|
| 1323 |
+
"step": 1090
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 0.93,
|
| 1327 |
+
"learning_rate": 3.1446272481522543e-06,
|
| 1328 |
+
"loss": 0.1198,
|
| 1329 |
+
"step": 1095
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.93,
|
| 1333 |
+
"learning_rate": 2.78723018547008e-06,
|
| 1334 |
+
"loss": 0.1456,
|
| 1335 |
+
"step": 1100
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 0.94,
|
| 1339 |
+
"learning_rate": 2.451100117363603e-06,
|
| 1340 |
+
"loss": 0.1208,
|
| 1341 |
+
"step": 1105
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 0.94,
|
| 1345 |
+
"learning_rate": 2.1363105781673888e-06,
|
| 1346 |
+
"loss": 0.1089,
|
| 1347 |
+
"step": 1110
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.94,
|
| 1351 |
+
"learning_rate": 1.842930433601775e-06,
|
| 1352 |
+
"loss": 0.1166,
|
| 1353 |
+
"step": 1115
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.95,
|
| 1357 |
+
"learning_rate": 1.5710238657074217e-06,
|
| 1358 |
+
"loss": 0.1258,
|
| 1359 |
+
"step": 1120
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 0.95,
|
| 1363 |
+
"learning_rate": 1.3206503588042762e-06,
|
| 1364 |
+
"loss": 0.1338,
|
| 1365 |
+
"step": 1125
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 0.96,
|
| 1369 |
+
"learning_rate": 1.0918646864784166e-06,
|
| 1370 |
+
"loss": 0.1282,
|
| 1371 |
+
"step": 1130
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.96,
|
| 1375 |
+
"learning_rate": 8.847168995992916e-07,
|
| 1376 |
+
"loss": 0.1266,
|
| 1377 |
+
"step": 1135
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 0.97,
|
| 1381 |
+
"learning_rate": 6.992523153702691e-07,
|
| 1382 |
+
"loss": 0.1218,
|
| 1383 |
+
"step": 1140
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 0.97,
|
| 1387 |
+
"learning_rate": 5.35511507414721e-07,
|
| 1388 |
+
"loss": 0.1172,
|
| 1389 |
+
"step": 1145
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.97,
|
| 1393 |
+
"learning_rate": 3.9353029689974674e-07,
|
| 1394 |
+
"loss": 0.1367,
|
| 1395 |
+
"step": 1150
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.98,
|
| 1399 |
+
"learning_rate": 2.733397446997632e-07,
|
| 1400 |
+
"loss": 0.1164,
|
| 1401 |
+
"step": 1155
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 0.98,
|
| 1405 |
+
"learning_rate": 1.7496614460135176e-07,
|
| 1406 |
+
"loss": 0.1091,
|
| 1407 |
+
"step": 1160
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 0.99,
|
| 1411 |
+
"learning_rate": 9.843101755101502e-08,
|
| 1412 |
+
"loss": 0.1402,
|
| 1413 |
+
"step": 1165
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.99,
|
| 1417 |
+
"learning_rate": 4.375110694713191e-08,
|
| 1418 |
+
"loss": 0.1242,
|
| 1419 |
+
"step": 1170
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 1.0,
|
| 1423 |
+
"learning_rate": 1.0938374977020882e-08,
|
| 1424 |
+
"loss": 0.122,
|
| 1425 |
+
"step": 1175
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 1.0,
|
| 1429 |
+
"learning_rate": 0.0,
|
| 1430 |
+
"loss": 0.1162,
|
| 1431 |
+
"step": 1180
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.0,
|
| 1435 |
+
"eval_loss": 0.10465715825557709,
|
| 1436 |
+
"eval_runtime": 0.1015,
|
| 1437 |
+
"eval_samples_per_second": 49.268,
|
| 1438 |
+
"eval_steps_per_second": 9.854,
|
| 1439 |
+
"step": 1180
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 1.0,
|
| 1443 |
+
"step": 1180,
|
| 1444 |
+
"total_flos": 6.174977435684045e+16,
|
| 1445 |
+
"train_loss": 0.2257307288000139,
|
| 1446 |
+
"train_runtime": 713.6543,
|
| 1447 |
+
"train_samples_per_second": 13.23,
|
| 1448 |
+
"train_steps_per_second": 1.653
|
| 1449 |
+
}
|
| 1450 |
+
],
|
| 1451 |
+
"logging_steps": 5,
|
| 1452 |
+
"max_steps": 1180,
|
| 1453 |
+
"num_input_tokens_seen": 0,
|
| 1454 |
+
"num_train_epochs": 1,
|
| 1455 |
+
"save_steps": 500,
|
| 1456 |
+
"total_flos": 6.174977435684045e+16,
|
| 1457 |
+
"train_batch_size": 4,
|
| 1458 |
+
"trial_name": null,
|
| 1459 |
+
"trial_params": null
|
| 1460 |
+
}
|