Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: mistralai/Mistral-7B-v0.1
|
| 9 |
+
model-index:
|
| 10 |
+
- name: zephyr-7b-sft-qlora-50p
|
| 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-50p
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.9261
|
| 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: 8
|
| 42 |
+
- eval_batch_size: 4
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- num_devices: 4
|
| 46 |
+
- gradient_accumulation_steps: 2
|
| 47 |
+
- total_train_batch_size: 64
|
| 48 |
+
- total_eval_batch_size: 16
|
| 49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
+
- lr_scheduler_type: cosine
|
| 51 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 52 |
+
- num_epochs: 1
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 57 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 58 |
+
| 0.6774 | 1.0 | 812 | 0.9261 |
|
| 59 |
+
|
| 60 |
+
|
| 61 |
+
### Framework versions
|
| 62 |
+
|
| 63 |
+
- PEFT 0.7.1
|
| 64 |
+
- Transformers 4.39.0.dev0
|
| 65 |
+
- Pytorch 2.2.2+cu121
|
| 66 |
+
- Datasets 2.14.6
|
| 67 |
+
- 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 31516744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a2fb1f5fe0bb9d33de166d72f05689aad2ae6f4817b72b25c11657f34e8337b
|
| 3 |
size 31516744
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.7061199183240899,
|
| 4 |
+
"train_runtime": 29649.4111,
|
| 5 |
+
"train_samples": 51965,
|
| 6 |
+
"train_samples_per_second": 1.753,
|
| 7 |
+
"train_steps_per_second": 0.027
|
| 8 |
+
}
|
runs/May04_05-18-00_ip-172-31-69-60.ec2.internal/events.out.tfevents.1714800161.ip-172-31-69-60.ec2.internal.42244.0
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:fc30cca49b9258c77b50fad09437c4f678e56381ce72400c45125064402b31d8
|
| 3 |
+
size 39620
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.7061199183240899,
|
| 4 |
+
"train_runtime": 29649.4111,
|
| 5 |
+
"train_samples": 51965,
|
| 6 |
+
"train_samples_per_second": 1.753,
|
| 7 |
+
"train_steps_per_second": 0.027
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1179 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 812,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"grad_norm": 0.22422564560903913,
|
| 14 |
+
"learning_rate": 2.4390243902439027e-06,
|
| 15 |
+
"loss": 0.8165,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.01,
|
| 20 |
+
"grad_norm": 0.24393612584966326,
|
| 21 |
+
"learning_rate": 1.2195121951219513e-05,
|
| 22 |
+
"loss": 0.8171,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.01,
|
| 27 |
+
"grad_norm": 0.32976460652590056,
|
| 28 |
+
"learning_rate": 2.4390243902439026e-05,
|
| 29 |
+
"loss": 0.8001,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.02,
|
| 34 |
+
"grad_norm": 0.22143488102760825,
|
| 35 |
+
"learning_rate": 3.6585365853658535e-05,
|
| 36 |
+
"loss": 0.7749,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"grad_norm": 0.27241208120124494,
|
| 42 |
+
"learning_rate": 4.878048780487805e-05,
|
| 43 |
+
"loss": 0.7399,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.03,
|
| 48 |
+
"grad_norm": 0.22476497302964527,
|
| 49 |
+
"learning_rate": 6.097560975609756e-05,
|
| 50 |
+
"loss": 0.765,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.04,
|
| 55 |
+
"grad_norm": 0.23267051655279075,
|
| 56 |
+
"learning_rate": 7.317073170731707e-05,
|
| 57 |
+
"loss": 0.7434,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.04,
|
| 62 |
+
"grad_norm": 0.22352973519663066,
|
| 63 |
+
"learning_rate": 8.53658536585366e-05,
|
| 64 |
+
"loss": 0.7884,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.05,
|
| 69 |
+
"grad_norm": 0.23366158183718752,
|
| 70 |
+
"learning_rate": 9.75609756097561e-05,
|
| 71 |
+
"loss": 0.767,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.06,
|
| 76 |
+
"grad_norm": 0.21853843372631854,
|
| 77 |
+
"learning_rate": 0.00010975609756097563,
|
| 78 |
+
"loss": 0.76,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.06,
|
| 83 |
+
"grad_norm": 0.1997879106921521,
|
| 84 |
+
"learning_rate": 0.00012195121951219512,
|
| 85 |
+
"loss": 0.7516,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.07,
|
| 90 |
+
"grad_norm": 0.2251793056206077,
|
| 91 |
+
"learning_rate": 0.00013414634146341464,
|
| 92 |
+
"loss": 0.7173,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.07,
|
| 97 |
+
"grad_norm": 0.21081648300798228,
|
| 98 |
+
"learning_rate": 0.00014634146341463414,
|
| 99 |
+
"loss": 0.7528,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.08,
|
| 104 |
+
"grad_norm": 0.23666214760062876,
|
| 105 |
+
"learning_rate": 0.00015853658536585366,
|
| 106 |
+
"loss": 0.7404,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.09,
|
| 111 |
+
"grad_norm": 0.23722379969745064,
|
| 112 |
+
"learning_rate": 0.0001707317073170732,
|
| 113 |
+
"loss": 0.7612,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.09,
|
| 118 |
+
"grad_norm": 0.24333660134577043,
|
| 119 |
+
"learning_rate": 0.0001829268292682927,
|
| 120 |
+
"loss": 0.717,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.1,
|
| 125 |
+
"grad_norm": 0.24793258937714172,
|
| 126 |
+
"learning_rate": 0.0001951219512195122,
|
| 127 |
+
"loss": 0.7233,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.1,
|
| 132 |
+
"grad_norm": 0.21823934898390882,
|
| 133 |
+
"learning_rate": 0.0001999916658654738,
|
| 134 |
+
"loss": 0.7168,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.11,
|
| 139 |
+
"grad_norm": 0.2468304527466075,
|
| 140 |
+
"learning_rate": 0.0001999407400739705,
|
| 141 |
+
"loss": 0.7519,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.12,
|
| 146 |
+
"grad_norm": 0.2481744524594569,
|
| 147 |
+
"learning_rate": 0.00019984354211555644,
|
| 148 |
+
"loss": 0.7212,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.12,
|
| 153 |
+
"grad_norm": 0.22553056449126135,
|
| 154 |
+
"learning_rate": 0.00019970011699250152,
|
| 155 |
+
"loss": 0.7351,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.13,
|
| 160 |
+
"grad_norm": 0.20832972377638914,
|
| 161 |
+
"learning_rate": 0.00019951053111006976,
|
| 162 |
+
"loss": 0.7611,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.14,
|
| 167 |
+
"grad_norm": 0.2276942421072934,
|
| 168 |
+
"learning_rate": 0.00019927487224577402,
|
| 169 |
+
"loss": 0.7373,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.14,
|
| 174 |
+
"grad_norm": 0.22785202882473857,
|
| 175 |
+
"learning_rate": 0.0001989932495087353,
|
| 176 |
+
"loss": 0.7777,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.15,
|
| 181 |
+
"grad_norm": 0.23403114621707224,
|
| 182 |
+
"learning_rate": 0.0001986657932891657,
|
| 183 |
+
"loss": 0.7814,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.15,
|
| 188 |
+
"grad_norm": 0.21032447129887216,
|
| 189 |
+
"learning_rate": 0.0001982926551979982,
|
| 190 |
+
"loss": 0.7601,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.16,
|
| 195 |
+
"grad_norm": 0.21778287055015214,
|
| 196 |
+
"learning_rate": 0.00019787400799669154,
|
| 197 |
+
"loss": 0.7465,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.17,
|
| 202 |
+
"grad_norm": 0.23068074124934998,
|
| 203 |
+
"learning_rate": 0.00019741004551724207,
|
| 204 |
+
"loss": 0.7671,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.17,
|
| 209 |
+
"grad_norm": 0.21498665804807518,
|
| 210 |
+
"learning_rate": 0.00019690098257244064,
|
| 211 |
+
"loss": 0.7448,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.18,
|
| 216 |
+
"grad_norm": 0.2217460126233852,
|
| 217 |
+
"learning_rate": 0.00019634705485641488,
|
| 218 |
+
"loss": 0.7508,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.18,
|
| 223 |
+
"grad_norm": 0.22491198578150204,
|
| 224 |
+
"learning_rate": 0.00019574851883550395,
|
| 225 |
+
"loss": 0.7528,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.19,
|
| 230 |
+
"grad_norm": 0.21656015924096556,
|
| 231 |
+
"learning_rate": 0.00019510565162951537,
|
| 232 |
+
"loss": 0.7528,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.2,
|
| 237 |
+
"grad_norm": 0.21231516089906458,
|
| 238 |
+
"learning_rate": 0.00019441875088341997,
|
| 239 |
+
"loss": 0.7334,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.2,
|
| 244 |
+
"grad_norm": 0.20043526486232421,
|
| 245 |
+
"learning_rate": 0.00019368813462954316,
|
| 246 |
+
"loss": 0.7092,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.21,
|
| 251 |
+
"grad_norm": 0.2066905562271494,
|
| 252 |
+
"learning_rate": 0.00019291414114031743,
|
| 253 |
+
"loss": 0.69,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.22,
|
| 258 |
+
"grad_norm": 0.2409977578699428,
|
| 259 |
+
"learning_rate": 0.00019209712877166349,
|
| 260 |
+
"loss": 0.7274,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.22,
|
| 265 |
+
"grad_norm": 0.21478894589801012,
|
| 266 |
+
"learning_rate": 0.00019123747579707275,
|
| 267 |
+
"loss": 0.702,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.23,
|
| 272 |
+
"grad_norm": 0.21830847034248066,
|
| 273 |
+
"learning_rate": 0.00019033558023246844,
|
| 274 |
+
"loss": 0.7474,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.23,
|
| 279 |
+
"grad_norm": 0.22565415608082542,
|
| 280 |
+
"learning_rate": 0.0001893918596519257,
|
| 281 |
+
"loss": 0.7263,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.24,
|
| 286 |
+
"grad_norm": 0.22451701734198667,
|
| 287 |
+
"learning_rate": 0.00018840675099433636,
|
| 288 |
+
"loss": 0.7376,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.25,
|
| 293 |
+
"grad_norm": 0.22016338896296778,
|
| 294 |
+
"learning_rate": 0.00018738071036110808,
|
| 295 |
+
"loss": 0.6939,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.25,
|
| 300 |
+
"grad_norm": 0.20607069335042727,
|
| 301 |
+
"learning_rate": 0.00018631421280499116,
|
| 302 |
+
"loss": 0.7351,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.26,
|
| 307 |
+
"grad_norm": 0.20601552052171884,
|
| 308 |
+
"learning_rate": 0.00018520775211013093,
|
| 309 |
+
"loss": 0.7082,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.26,
|
| 314 |
+
"grad_norm": 0.21774646892016394,
|
| 315 |
+
"learning_rate": 0.00018406184056344782,
|
| 316 |
+
"loss": 0.745,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.27,
|
| 321 |
+
"grad_norm": 0.23099746146509867,
|
| 322 |
+
"learning_rate": 0.00018287700871745036,
|
| 323 |
+
"loss": 0.7707,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.28,
|
| 328 |
+
"grad_norm": 0.2225513878139953,
|
| 329 |
+
"learning_rate": 0.0001816538051445916,
|
| 330 |
+
"loss": 0.72,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.28,
|
| 335 |
+
"grad_norm": 0.2810648109589189,
|
| 336 |
+
"learning_rate": 0.00018039279618328212,
|
| 337 |
+
"loss": 0.7159,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.29,
|
| 342 |
+
"grad_norm": 0.23360820743854752,
|
| 343 |
+
"learning_rate": 0.00017909456567567772,
|
| 344 |
+
"loss": 0.7916,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.3,
|
| 349 |
+
"grad_norm": 0.2346981575638156,
|
| 350 |
+
"learning_rate": 0.0001777597146973627,
|
| 351 |
+
"loss": 0.7543,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.3,
|
| 356 |
+
"grad_norm": 0.22472791649678256,
|
| 357 |
+
"learning_rate": 0.00017638886127905427,
|
| 358 |
+
"loss": 0.7145,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.31,
|
| 363 |
+
"grad_norm": 0.2330382456080435,
|
| 364 |
+
"learning_rate": 0.00017498264012045687,
|
| 365 |
+
"loss": 0.6951,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.31,
|
| 370 |
+
"grad_norm": 0.28462945710570964,
|
| 371 |
+
"learning_rate": 0.00017354170229639856,
|
| 372 |
+
"loss": 0.7218,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.32,
|
| 377 |
+
"grad_norm": 0.23120564986808903,
|
| 378 |
+
"learning_rate": 0.00017206671495538612,
|
| 379 |
+
"loss": 0.6954,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.33,
|
| 384 |
+
"grad_norm": 0.21787726424323484,
|
| 385 |
+
"learning_rate": 0.0001705583610107178,
|
| 386 |
+
"loss": 0.6993,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.33,
|
| 391 |
+
"grad_norm": 0.22337741579847503,
|
| 392 |
+
"learning_rate": 0.0001690173388242972,
|
| 393 |
+
"loss": 0.7742,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.34,
|
| 398 |
+
"grad_norm": 0.2418352997312942,
|
| 399 |
+
"learning_rate": 0.00016744436188329456,
|
| 400 |
+
"loss": 0.7385,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.34,
|
| 405 |
+
"grad_norm": 0.25104847122600993,
|
| 406 |
+
"learning_rate": 0.0001658401584698049,
|
| 407 |
+
"loss": 0.7142,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.35,
|
| 412 |
+
"grad_norm": 0.21545698908596508,
|
| 413 |
+
"learning_rate": 0.00016420547132365635,
|
| 414 |
+
"loss": 0.7043,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.36,
|
| 419 |
+
"grad_norm": 0.24534521084917407,
|
| 420 |
+
"learning_rate": 0.00016254105729852464,
|
| 421 |
+
"loss": 0.6988,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.36,
|
| 426 |
+
"grad_norm": 0.24621959592804224,
|
| 427 |
+
"learning_rate": 0.00016084768701151263,
|
| 428 |
+
"loss": 0.701,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.37,
|
| 433 |
+
"grad_norm": 0.2441445089915858,
|
| 434 |
+
"learning_rate": 0.00015912614448635782,
|
| 435 |
+
"loss": 0.713,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.38,
|
| 440 |
+
"grad_norm": 0.23144503509205255,
|
| 441 |
+
"learning_rate": 0.00015737722679043248,
|
| 442 |
+
"loss": 0.7185,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.38,
|
| 447 |
+
"grad_norm": 0.23779196053246493,
|
| 448 |
+
"learning_rate": 0.00015560174366570446,
|
| 449 |
+
"loss": 0.6585,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.39,
|
| 454 |
+
"grad_norm": 0.23922306500283833,
|
| 455 |
+
"learning_rate": 0.00015380051715382996,
|
| 456 |
+
"loss": 0.7025,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.39,
|
| 461 |
+
"grad_norm": 0.25732276520746106,
|
| 462 |
+
"learning_rate": 0.0001519743812155516,
|
| 463 |
+
"loss": 0.6496,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.4,
|
| 468 |
+
"grad_norm": 0.25676931335616193,
|
| 469 |
+
"learning_rate": 0.00015012418134457755,
|
| 470 |
+
"loss": 0.6946,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.41,
|
| 475 |
+
"grad_norm": 0.25925282419918827,
|
| 476 |
+
"learning_rate": 0.00014825077417612186,
|
| 477 |
+
"loss": 0.7309,
|
| 478 |
+
"step": 330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.41,
|
| 482 |
+
"grad_norm": 0.25723625109413206,
|
| 483 |
+
"learning_rate": 0.0001463550270902851,
|
| 484 |
+
"loss": 0.6929,
|
| 485 |
+
"step": 335
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.42,
|
| 489 |
+
"grad_norm": 0.2758091340120669,
|
| 490 |
+
"learning_rate": 0.00014443781781046136,
|
| 491 |
+
"loss": 0.7016,
|
| 492 |
+
"step": 340
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.42,
|
| 496 |
+
"grad_norm": 0.2368505670464136,
|
| 497 |
+
"learning_rate": 0.0001425000339969554,
|
| 498 |
+
"loss": 0.703,
|
| 499 |
+
"step": 345
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.43,
|
| 503 |
+
"grad_norm": 0.23084399243795903,
|
| 504 |
+
"learning_rate": 0.00014054257283599973,
|
| 505 |
+
"loss": 0.7102,
|
| 506 |
+
"step": 350
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.44,
|
| 510 |
+
"grad_norm": 0.2503463601524904,
|
| 511 |
+
"learning_rate": 0.0001385663406243607,
|
| 512 |
+
"loss": 0.7278,
|
| 513 |
+
"step": 355
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.44,
|
| 517 |
+
"grad_norm": 0.22226083699821775,
|
| 518 |
+
"learning_rate": 0.00013657225234972695,
|
| 519 |
+
"loss": 0.6753,
|
| 520 |
+
"step": 360
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.45,
|
| 524 |
+
"grad_norm": 0.26300812718557964,
|
| 525 |
+
"learning_rate": 0.00013456123126707334,
|
| 526 |
+
"loss": 0.6871,
|
| 527 |
+
"step": 365
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.46,
|
| 531 |
+
"grad_norm": 0.257794988184064,
|
| 532 |
+
"learning_rate": 0.00013253420847119803,
|
| 533 |
+
"loss": 0.737,
|
| 534 |
+
"step": 370
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.46,
|
| 538 |
+
"grad_norm": 0.23283253484592037,
|
| 539 |
+
"learning_rate": 0.0001304921224656289,
|
| 540 |
+
"loss": 0.6948,
|
| 541 |
+
"step": 375
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.47,
|
| 545 |
+
"grad_norm": 0.2489222484332262,
|
| 546 |
+
"learning_rate": 0.0001284359187281004,
|
| 547 |
+
"loss": 0.6807,
|
| 548 |
+
"step": 380
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.47,
|
| 552 |
+
"grad_norm": 0.24773496287366326,
|
| 553 |
+
"learning_rate": 0.00012636654927280073,
|
| 554 |
+
"loss": 0.7322,
|
| 555 |
+
"step": 385
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.48,
|
| 559 |
+
"grad_norm": 0.25284782064647693,
|
| 560 |
+
"learning_rate": 0.0001242849722095936,
|
| 561 |
+
"loss": 0.7038,
|
| 562 |
+
"step": 390
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.49,
|
| 566 |
+
"grad_norm": 0.2640705980904302,
|
| 567 |
+
"learning_rate": 0.00012219215130041656,
|
| 568 |
+
"loss": 0.6818,
|
| 569 |
+
"step": 395
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.49,
|
| 573 |
+
"grad_norm": 0.244353569188838,
|
| 574 |
+
"learning_rate": 0.00012008905551306356,
|
| 575 |
+
"loss": 0.6888,
|
| 576 |
+
"step": 400
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.5,
|
| 580 |
+
"grad_norm": 0.2582385397817055,
|
| 581 |
+
"learning_rate": 0.00011797665857255621,
|
| 582 |
+
"loss": 0.7347,
|
| 583 |
+
"step": 405
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.5,
|
| 587 |
+
"grad_norm": 0.2657939654189472,
|
| 588 |
+
"learning_rate": 0.00011585593851031347,
|
| 589 |
+
"loss": 0.7292,
|
| 590 |
+
"step": 410
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.51,
|
| 594 |
+
"grad_norm": 0.2412402754418769,
|
| 595 |
+
"learning_rate": 0.00011372787721132648,
|
| 596 |
+
"loss": 0.6793,
|
| 597 |
+
"step": 415
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.52,
|
| 601 |
+
"grad_norm": 0.25269309847633625,
|
| 602 |
+
"learning_rate": 0.00011159345995955006,
|
| 603 |
+
"loss": 0.6811,
|
| 604 |
+
"step": 420
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.52,
|
| 608 |
+
"grad_norm": 0.3555199335436584,
|
| 609 |
+
"learning_rate": 0.00010945367498171993,
|
| 610 |
+
"loss": 0.6632,
|
| 611 |
+
"step": 425
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.53,
|
| 615 |
+
"grad_norm": 0.2807299993278487,
|
| 616 |
+
"learning_rate": 0.00010730951298980776,
|
| 617 |
+
"loss": 0.7121,
|
| 618 |
+
"step": 430
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.54,
|
| 622 |
+
"grad_norm": 0.2676168527706757,
|
| 623 |
+
"learning_rate": 0.00010516196672232539,
|
| 624 |
+
"loss": 0.6897,
|
| 625 |
+
"step": 435
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.54,
|
| 629 |
+
"grad_norm": 0.2696033985636684,
|
| 630 |
+
"learning_rate": 0.00010301203048469083,
|
| 631 |
+
"loss": 0.7149,
|
| 632 |
+
"step": 440
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.55,
|
| 636 |
+
"grad_norm": 0.264343040293582,
|
| 637 |
+
"learning_rate": 0.00010086069968886885,
|
| 638 |
+
"loss": 0.697,
|
| 639 |
+
"step": 445
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.55,
|
| 643 |
+
"grad_norm": 0.24941452883154777,
|
| 644 |
+
"learning_rate": 9.870897039249911e-05,
|
| 645 |
+
"loss": 0.6739,
|
| 646 |
+
"step": 450
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.56,
|
| 650 |
+
"grad_norm": 0.27184754304212144,
|
| 651 |
+
"learning_rate": 9.655783883772545e-05,
|
| 652 |
+
"loss": 0.6771,
|
| 653 |
+
"step": 455
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.57,
|
| 657 |
+
"grad_norm": 0.25069232194770324,
|
| 658 |
+
"learning_rate": 9.440830098993969e-05,
|
| 659 |
+
"loss": 0.6628,
|
| 660 |
+
"step": 460
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.57,
|
| 664 |
+
"grad_norm": 0.26945962491120906,
|
| 665 |
+
"learning_rate": 9.22613520766537e-05,
|
| 666 |
+
"loss": 0.6501,
|
| 667 |
+
"step": 465
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.58,
|
| 671 |
+
"grad_norm": 0.27595385280343615,
|
| 672 |
+
"learning_rate": 9.011798612671286e-05,
|
| 673 |
+
"loss": 0.6923,
|
| 674 |
+
"step": 470
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.58,
|
| 678 |
+
"grad_norm": 0.23254427170051437,
|
| 679 |
+
"learning_rate": 8.797919551006475e-05,
|
| 680 |
+
"loss": 0.6687,
|
| 681 |
+
"step": 475
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.59,
|
| 685 |
+
"grad_norm": 0.2700843553748168,
|
| 686 |
+
"learning_rate": 8.58459704782957e-05,
|
| 687 |
+
"loss": 0.6922,
|
| 688 |
+
"step": 480
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.6,
|
| 692 |
+
"grad_norm": 0.29075126290562925,
|
| 693 |
+
"learning_rate": 8.371929870614833e-05,
|
| 694 |
+
"loss": 0.6838,
|
| 695 |
+
"step": 485
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.6,
|
| 699 |
+
"grad_norm": 0.2582533489019304,
|
| 700 |
+
"learning_rate": 8.160016483423199e-05,
|
| 701 |
+
"loss": 0.709,
|
| 702 |
+
"step": 490
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.61,
|
| 706 |
+
"grad_norm": 0.24306629955384693,
|
| 707 |
+
"learning_rate": 7.948955001313811e-05,
|
| 708 |
+
"loss": 0.6644,
|
| 709 |
+
"step": 495
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.62,
|
| 713 |
+
"grad_norm": 0.2792860639380007,
|
| 714 |
+
"learning_rate": 7.738843144917119e-05,
|
| 715 |
+
"loss": 0.7122,
|
| 716 |
+
"step": 500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.62,
|
| 720 |
+
"grad_norm": 0.2717162268363558,
|
| 721 |
+
"learning_rate": 7.529778195190645e-05,
|
| 722 |
+
"loss": 0.7235,
|
| 723 |
+
"step": 505
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.63,
|
| 727 |
+
"grad_norm": 0.284678632001059,
|
| 728 |
+
"learning_rate": 7.321856948378259e-05,
|
| 729 |
+
"loss": 0.6916,
|
| 730 |
+
"step": 510
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.63,
|
| 734 |
+
"grad_norm": 0.26262649770739277,
|
| 735 |
+
"learning_rate": 7.115175671193913e-05,
|
| 736 |
+
"loss": 0.6741,
|
| 737 |
+
"step": 515
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.64,
|
| 741 |
+
"grad_norm": 0.2529748057506211,
|
| 742 |
+
"learning_rate": 6.909830056250527e-05,
|
| 743 |
+
"loss": 0.7025,
|
| 744 |
+
"step": 520
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.65,
|
| 748 |
+
"grad_norm": 0.28817490304932813,
|
| 749 |
+
"learning_rate": 6.7059151777547e-05,
|
| 750 |
+
"loss": 0.7071,
|
| 751 |
+
"step": 525
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.65,
|
| 755 |
+
"grad_norm": 0.28586738996038136,
|
| 756 |
+
"learning_rate": 6.503525447487715e-05,
|
| 757 |
+
"loss": 0.7223,
|
| 758 |
+
"step": 530
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.66,
|
| 762 |
+
"grad_norm": 0.27355383837426006,
|
| 763 |
+
"learning_rate": 6.30275457109327e-05,
|
| 764 |
+
"loss": 0.6878,
|
| 765 |
+
"step": 535
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.67,
|
| 769 |
+
"grad_norm": 0.2696146366032459,
|
| 770 |
+
"learning_rate": 6.103695504692122e-05,
|
| 771 |
+
"loss": 0.666,
|
| 772 |
+
"step": 540
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.67,
|
| 776 |
+
"grad_norm": 0.293084107951244,
|
| 777 |
+
"learning_rate": 5.906440411843787e-05,
|
| 778 |
+
"loss": 0.7165,
|
| 779 |
+
"step": 545
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.68,
|
| 783 |
+
"grad_norm": 0.2744477897912315,
|
| 784 |
+
"learning_rate": 5.7110806208751655e-05,
|
| 785 |
+
"loss": 0.6791,
|
| 786 |
+
"step": 550
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.68,
|
| 790 |
+
"grad_norm": 0.2719074571288193,
|
| 791 |
+
"learning_rate": 5.5177065825958966e-05,
|
| 792 |
+
"loss": 0.7183,
|
| 793 |
+
"step": 555
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.69,
|
| 797 |
+
"grad_norm": 0.29658031172179306,
|
| 798 |
+
"learning_rate": 5.326407828419979e-05,
|
| 799 |
+
"loss": 0.6741,
|
| 800 |
+
"step": 560
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.7,
|
| 804 |
+
"grad_norm": 0.25304272831172997,
|
| 805 |
+
"learning_rate": 5.137272928913097e-05,
|
| 806 |
+
"loss": 0.68,
|
| 807 |
+
"step": 565
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.7,
|
| 811 |
+
"grad_norm": 0.2676461633502972,
|
| 812 |
+
"learning_rate": 4.9503894527847964e-05,
|
| 813 |
+
"loss": 0.6593,
|
| 814 |
+
"step": 570
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.71,
|
| 818 |
+
"grad_norm": 0.31247663625681804,
|
| 819 |
+
"learning_rate": 4.765843926344501e-05,
|
| 820 |
+
"loss": 0.6863,
|
| 821 |
+
"step": 575
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.71,
|
| 825 |
+
"grad_norm": 0.2955325664002294,
|
| 826 |
+
"learning_rate": 4.583721793440188e-05,
|
| 827 |
+
"loss": 0.6728,
|
| 828 |
+
"step": 580
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.72,
|
| 832 |
+
"grad_norm": 0.2807174542636257,
|
| 833 |
+
"learning_rate": 4.4041073758982335e-05,
|
| 834 |
+
"loss": 0.6913,
|
| 835 |
+
"step": 585
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.73,
|
| 839 |
+
"grad_norm": 0.2989395763460932,
|
| 840 |
+
"learning_rate": 4.227083834482728e-05,
|
| 841 |
+
"loss": 0.6085,
|
| 842 |
+
"step": 590
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.73,
|
| 846 |
+
"grad_norm": 0.2636409419874345,
|
| 847 |
+
"learning_rate": 4.052733130392367e-05,
|
| 848 |
+
"loss": 0.676,
|
| 849 |
+
"step": 595
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.74,
|
| 853 |
+
"grad_norm": 0.2735419958012749,
|
| 854 |
+
"learning_rate": 3.881135987312757e-05,
|
| 855 |
+
"loss": 0.697,
|
| 856 |
+
"step": 600
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.75,
|
| 860 |
+
"grad_norm": 0.29812585759610105,
|
| 861 |
+
"learning_rate": 3.712371854041654e-05,
|
| 862 |
+
"loss": 0.6788,
|
| 863 |
+
"step": 605
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.75,
|
| 867 |
+
"grad_norm": 0.2858805204008935,
|
| 868 |
+
"learning_rate": 3.546518867704499e-05,
|
| 869 |
+
"loss": 0.6891,
|
| 870 |
+
"step": 610
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.76,
|
| 874 |
+
"grad_norm": 0.2711930626215174,
|
| 875 |
+
"learning_rate": 3.383653817577216e-05,
|
| 876 |
+
"loss": 0.6626,
|
| 877 |
+
"step": 615
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.76,
|
| 881 |
+
"grad_norm": 0.30583390146359735,
|
| 882 |
+
"learning_rate": 3.223852109533112e-05,
|
| 883 |
+
"loss": 0.6977,
|
| 884 |
+
"step": 620
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.77,
|
| 888 |
+
"grad_norm": 0.31918222012772746,
|
| 889 |
+
"learning_rate": 3.0671877311302244e-05,
|
| 890 |
+
"loss": 0.6546,
|
| 891 |
+
"step": 625
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.78,
|
| 895 |
+
"grad_norm": 0.27113125300550006,
|
| 896 |
+
"learning_rate": 2.9137332173554043e-05,
|
| 897 |
+
"loss": 0.6718,
|
| 898 |
+
"step": 630
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.78,
|
| 902 |
+
"grad_norm": 0.2933116316225334,
|
| 903 |
+
"learning_rate": 2.763559617040876e-05,
|
| 904 |
+
"loss": 0.677,
|
| 905 |
+
"step": 635
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.79,
|
| 909 |
+
"grad_norm": 0.3236593994578141,
|
| 910 |
+
"learning_rate": 2.616736459968936e-05,
|
| 911 |
+
"loss": 0.6685,
|
| 912 |
+
"step": 640
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.79,
|
| 916 |
+
"grad_norm": 0.30406592976690633,
|
| 917 |
+
"learning_rate": 2.473331724679917e-05,
|
| 918 |
+
"loss": 0.6746,
|
| 919 |
+
"step": 645
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.8,
|
| 923 |
+
"grad_norm": 0.27899362724771787,
|
| 924 |
+
"learning_rate": 2.33341180699841e-05,
|
| 925 |
+
"loss": 0.6667,
|
| 926 |
+
"step": 650
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.81,
|
| 930 |
+
"grad_norm": 0.2954598561484786,
|
| 931 |
+
"learning_rate": 2.1970414892922442e-05,
|
| 932 |
+
"loss": 0.7175,
|
| 933 |
+
"step": 655
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.81,
|
| 937 |
+
"grad_norm": 0.3100581301740447,
|
| 938 |
+
"learning_rate": 2.0642839104785272e-05,
|
| 939 |
+
"loss": 0.6979,
|
| 940 |
+
"step": 660
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.82,
|
| 944 |
+
"grad_norm": 0.2759099798186259,
|
| 945 |
+
"learning_rate": 1.9352005367905536e-05,
|
| 946 |
+
"loss": 0.7098,
|
| 947 |
+
"step": 665
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.83,
|
| 951 |
+
"grad_norm": 0.30931195338097267,
|
| 952 |
+
"learning_rate": 1.8098511333192024e-05,
|
| 953 |
+
"loss": 0.6593,
|
| 954 |
+
"step": 670
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.83,
|
| 958 |
+
"grad_norm": 0.32368942926694433,
|
| 959 |
+
"learning_rate": 1.6882937363419203e-05,
|
| 960 |
+
"loss": 0.6869,
|
| 961 |
+
"step": 675
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.84,
|
| 965 |
+
"grad_norm": 0.2776307386865438,
|
| 966 |
+
"learning_rate": 1.570584626452173e-05,
|
| 967 |
+
"loss": 0.6717,
|
| 968 |
+
"step": 680
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.84,
|
| 972 |
+
"grad_norm": 0.30301564173702233,
|
| 973 |
+
"learning_rate": 1.4567783025017301e-05,
|
| 974 |
+
"loss": 0.6681,
|
| 975 |
+
"step": 685
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.85,
|
| 979 |
+
"grad_norm": 0.31904417802084467,
|
| 980 |
+
"learning_rate": 1.3469274563679402e-05,
|
| 981 |
+
"loss": 0.6851,
|
| 982 |
+
"step": 690
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.86,
|
| 986 |
+
"grad_norm": 0.2774036633854793,
|
| 987 |
+
"learning_rate": 1.2410829485575704e-05,
|
| 988 |
+
"loss": 0.7023,
|
| 989 |
+
"step": 695
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.86,
|
| 993 |
+
"grad_norm": 0.2965220463492153,
|
| 994 |
+
"learning_rate": 1.1392937846586215e-05,
|
| 995 |
+
"loss": 0.6565,
|
| 996 |
+
"step": 700
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.87,
|
| 1000 |
+
"grad_norm": 0.32675908474718157,
|
| 1001 |
+
"learning_rate": 1.0416070926509113e-05,
|
| 1002 |
+
"loss": 0.6487,
|
| 1003 |
+
"step": 705
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.87,
|
| 1007 |
+
"grad_norm": 0.3090900072007822,
|
| 1008 |
+
"learning_rate": 9.48068101086026e-06,
|
| 1009 |
+
"loss": 0.6976,
|
| 1010 |
+
"step": 710
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.88,
|
| 1014 |
+
"grad_norm": 0.309037705156712,
|
| 1015 |
+
"learning_rate": 8.58720118146662e-06,
|
| 1016 |
+
"loss": 0.66,
|
| 1017 |
+
"step": 715
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.89,
|
| 1021 |
+
"grad_norm": 0.3087738006371124,
|
| 1022 |
+
"learning_rate": 7.736045115951251e-06,
|
| 1023 |
+
"loss": 0.7067,
|
| 1024 |
+
"step": 720
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.89,
|
| 1028 |
+
"grad_norm": 0.3443047214751086,
|
| 1029 |
+
"learning_rate": 6.927606896202066e-06,
|
| 1030 |
+
"loss": 0.6968,
|
| 1031 |
+
"step": 725
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.9,
|
| 1035 |
+
"grad_norm": 0.30866169616965344,
|
| 1036 |
+
"learning_rate": 6.16226082591359e-06,
|
| 1037 |
+
"loss": 0.6595,
|
| 1038 |
+
"step": 730
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.91,
|
| 1042 |
+
"grad_norm": 0.26453835920017715,
|
| 1043 |
+
"learning_rate": 5.440361257285742e-06,
|
| 1044 |
+
"loss": 0.6873,
|
| 1045 |
+
"step": 735
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.91,
|
| 1049 |
+
"grad_norm": 0.2870240594644306,
|
| 1050 |
+
"learning_rate": 4.762242426960262e-06,
|
| 1051 |
+
"loss": 0.6897,
|
| 1052 |
+
"step": 740
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.92,
|
| 1056 |
+
"grad_norm": 0.31907803929807727,
|
| 1057 |
+
"learning_rate": 4.128218301270359e-06,
|
| 1058 |
+
"loss": 0.7062,
|
| 1059 |
+
"step": 745
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.92,
|
| 1063 |
+
"grad_norm": 0.3461230801807586,
|
| 1064 |
+
"learning_rate": 3.5385824308756587e-06,
|
| 1065 |
+
"loss": 0.6506,
|
| 1066 |
+
"step": 750
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.93,
|
| 1070 |
+
"grad_norm": 0.2982663104307397,
|
| 1071 |
+
"learning_rate": 2.9936078148492973e-06,
|
| 1072 |
+
"loss": 0.6722,
|
| 1073 |
+
"step": 755
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.94,
|
| 1077 |
+
"grad_norm": 0.27990503389995286,
|
| 1078 |
+
"learning_rate": 2.493546774280531e-06,
|
| 1079 |
+
"loss": 0.7049,
|
| 1080 |
+
"step": 760
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.94,
|
| 1084 |
+
"grad_norm": 0.3112912132178525,
|
| 1085 |
+
"learning_rate": 2.0386308354509942e-06,
|
| 1086 |
+
"loss": 0.7125,
|
| 1087 |
+
"step": 765
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.95,
|
| 1091 |
+
"grad_norm": 0.31758074243604545,
|
| 1092 |
+
"learning_rate": 1.6290706226390285e-06,
|
| 1093 |
+
"loss": 0.6857,
|
| 1094 |
+
"step": 770
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.95,
|
| 1098 |
+
"grad_norm": 0.3210813944651733,
|
| 1099 |
+
"learning_rate": 1.2650557606013635e-06,
|
| 1100 |
+
"loss": 0.6829,
|
| 1101 |
+
"step": 775
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.96,
|
| 1105 |
+
"grad_norm": 0.2880839335185284,
|
| 1106 |
+
"learning_rate": 9.46754786777726e-07,
|
| 1107 |
+
"loss": 0.7146,
|
| 1108 |
+
"step": 780
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.97,
|
| 1112 |
+
"grad_norm": 0.29564960884643837,
|
| 1113 |
+
"learning_rate": 6.74315073258569e-07,
|
| 1114 |
+
"loss": 0.7101,
|
| 1115 |
+
"step": 785
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.97,
|
| 1119 |
+
"grad_norm": 0.29256820612374973,
|
| 1120 |
+
"learning_rate": 4.4786275855247527e-07,
|
| 1121 |
+
"loss": 0.6478,
|
| 1122 |
+
"step": 790
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.98,
|
| 1126 |
+
"grad_norm": 0.33071981852297627,
|
| 1127 |
+
"learning_rate": 2.675026891844512e-07,
|
| 1128 |
+
"loss": 0.672,
|
| 1129 |
+
"step": 795
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.99,
|
| 1133 |
+
"grad_norm": 0.329286091376579,
|
| 1134 |
+
"learning_rate": 1.333183711524133e-07,
|
| 1135 |
+
"loss": 0.6438,
|
| 1136 |
+
"step": 800
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.99,
|
| 1140 |
+
"grad_norm": 0.3104373424505981,
|
| 1141 |
+
"learning_rate": 4.5371931264270864e-08,
|
| 1142 |
+
"loss": 0.6555,
|
| 1143 |
+
"step": 805
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.0,
|
| 1147 |
+
"grad_norm": 0.2971195933385636,
|
| 1148 |
+
"learning_rate": 3.7040883734462683e-09,
|
| 1149 |
+
"loss": 0.6774,
|
| 1150 |
+
"step": 810
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.0,
|
| 1154 |
+
"eval_loss": 0.926139771938324,
|
| 1155 |
+
"eval_runtime": 459.5724,
|
| 1156 |
+
"eval_samples_per_second": 5.026,
|
| 1157 |
+
"eval_steps_per_second": 0.316,
|
| 1158 |
+
"step": 812
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.0,
|
| 1162 |
+
"step": 812,
|
| 1163 |
+
"total_flos": 9607955794100224.0,
|
| 1164 |
+
"train_loss": 0.7061199183240899,
|
| 1165 |
+
"train_runtime": 29649.4111,
|
| 1166 |
+
"train_samples_per_second": 1.753,
|
| 1167 |
+
"train_steps_per_second": 0.027
|
| 1168 |
+
}
|
| 1169 |
+
],
|
| 1170 |
+
"logging_steps": 5,
|
| 1171 |
+
"max_steps": 812,
|
| 1172 |
+
"num_input_tokens_seen": 0,
|
| 1173 |
+
"num_train_epochs": 1,
|
| 1174 |
+
"save_steps": 100,
|
| 1175 |
+
"total_flos": 9607955794100224.0,
|
| 1176 |
+
"train_batch_size": 8,
|
| 1177 |
+
"trial_name": null,
|
| 1178 |
+
"trial_params": null
|
| 1179 |
+
}
|