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: mistral-1p
|
| 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 |
+
# mistral-1p
|
| 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: nan
|
| 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: 1
|
| 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: 4
|
| 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 |
+
| 0.7291 | 1.0 | 650 | nan |
|
| 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:f88c8b6a4c3e751a8a9701f48913c2ad34e9090a200570df41c8bba6647e50eb
|
| 3 |
size 31516744
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.7519041672119727,
|
| 4 |
+
"train_runtime": 26444.6436,
|
| 5 |
+
"train_samples": 41573,
|
| 6 |
+
"train_samples_per_second": 1.572,
|
| 7 |
+
"train_steps_per_second": 0.025
|
| 8 |
+
}
|
runs/May08_05-14-33_ip-172-31-69-60.ec2.internal/events.out.tfevents.1715145498.ip-172-31-69-60.ec2.internal.39500.0
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 sha256:3c3c881cc14f2d5654a036a68996a4bf456b91fd3e3c66d60a82e3a0625fb426
|
| 3 |
+
size 32816
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.7519041672119727,
|
| 4 |
+
"train_runtime": 26444.6436,
|
| 5 |
+
"train_samples": 41573,
|
| 6 |
+
"train_samples_per_second": 1.572,
|
| 7 |
+
"train_steps_per_second": 0.025
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,955 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 650,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"grad_norm": 0.22638954581615983,
|
| 14 |
+
"learning_rate": 3.0769230769230774e-06,
|
| 15 |
+
"loss": 0.8364,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.01,
|
| 20 |
+
"grad_norm": 0.1813039257679487,
|
| 21 |
+
"learning_rate": 1.5384615384615387e-05,
|
| 22 |
+
"loss": 0.8034,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.02,
|
| 27 |
+
"grad_norm": 0.17727989080166365,
|
| 28 |
+
"learning_rate": 3.0769230769230774e-05,
|
| 29 |
+
"loss": 0.7942,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.02,
|
| 34 |
+
"grad_norm": 0.16805037708786894,
|
| 35 |
+
"learning_rate": 4.615384615384616e-05,
|
| 36 |
+
"loss": 0.8146,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.03,
|
| 41 |
+
"grad_norm": 0.21617629507877206,
|
| 42 |
+
"learning_rate": 6.153846153846155e-05,
|
| 43 |
+
"loss": 0.7828,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.04,
|
| 48 |
+
"grad_norm": 0.20939368966196042,
|
| 49 |
+
"learning_rate": 7.692307692307693e-05,
|
| 50 |
+
"loss": 0.7701,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.05,
|
| 55 |
+
"grad_norm": 0.1980708158646925,
|
| 56 |
+
"learning_rate": 9.230769230769232e-05,
|
| 57 |
+
"loss": 0.8039,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.05,
|
| 62 |
+
"grad_norm": 0.1727912158397291,
|
| 63 |
+
"learning_rate": 0.0001076923076923077,
|
| 64 |
+
"loss": 0.7828,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.06,
|
| 69 |
+
"grad_norm": 0.18556767932502666,
|
| 70 |
+
"learning_rate": 0.0001230769230769231,
|
| 71 |
+
"loss": 0.7467,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.07,
|
| 76 |
+
"grad_norm": 0.2557061081364788,
|
| 77 |
+
"learning_rate": 0.00013846153846153847,
|
| 78 |
+
"loss": 0.7449,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.08,
|
| 83 |
+
"grad_norm": 0.19745764432673993,
|
| 84 |
+
"learning_rate": 0.00015384615384615385,
|
| 85 |
+
"loss": 0.7572,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.08,
|
| 90 |
+
"grad_norm": 0.20505129132890218,
|
| 91 |
+
"learning_rate": 0.00016923076923076923,
|
| 92 |
+
"loss": 0.7751,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.09,
|
| 97 |
+
"grad_norm": 0.20649448170626705,
|
| 98 |
+
"learning_rate": 0.00018461538461538463,
|
| 99 |
+
"loss": 0.7602,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.1,
|
| 104 |
+
"grad_norm": 0.18752216144043785,
|
| 105 |
+
"learning_rate": 0.0002,
|
| 106 |
+
"loss": 0.8063,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.11,
|
| 111 |
+
"grad_norm": 0.22508963348939887,
|
| 112 |
+
"learning_rate": 0.00019996395276708856,
|
| 113 |
+
"loss": 0.7611,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.12,
|
| 118 |
+
"grad_norm": 0.18833225533556988,
|
| 119 |
+
"learning_rate": 0.00019985583705641418,
|
| 120 |
+
"loss": 0.7542,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.12,
|
| 125 |
+
"grad_norm": 0.18925044414460548,
|
| 126 |
+
"learning_rate": 0.00019967573081342103,
|
| 127 |
+
"loss": 0.7973,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.13,
|
| 132 |
+
"grad_norm": 0.19417928462178893,
|
| 133 |
+
"learning_rate": 0.0001994237638847428,
|
| 134 |
+
"loss": 0.7084,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.14,
|
| 139 |
+
"grad_norm": 0.20495423399654503,
|
| 140 |
+
"learning_rate": 0.00019910011792459087,
|
| 141 |
+
"loss": 0.7428,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.15,
|
| 146 |
+
"grad_norm": 0.19400035198889168,
|
| 147 |
+
"learning_rate": 0.00019870502626379127,
|
| 148 |
+
"loss": 0.7826,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.15,
|
| 153 |
+
"grad_norm": 0.18597079746230874,
|
| 154 |
+
"learning_rate": 0.00019823877374156647,
|
| 155 |
+
"loss": 0.7836,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.16,
|
| 160 |
+
"grad_norm": 0.18679845602710174,
|
| 161 |
+
"learning_rate": 0.00019770169650018172,
|
| 162 |
+
"loss": 0.765,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.17,
|
| 167 |
+
"grad_norm": 0.18479380410859886,
|
| 168 |
+
"learning_rate": 0.0001970941817426052,
|
| 169 |
+
"loss": 0.7534,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.18,
|
| 174 |
+
"grad_norm": 0.18138845502090514,
|
| 175 |
+
"learning_rate": 0.00019641666745335624,
|
| 176 |
+
"loss": 0.7577,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.18,
|
| 181 |
+
"grad_norm": 0.17448186193560006,
|
| 182 |
+
"learning_rate": 0.00019566964208274254,
|
| 183 |
+
"loss": 0.7799,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.19,
|
| 188 |
+
"grad_norm": 0.19208143444574954,
|
| 189 |
+
"learning_rate": 0.00019485364419471454,
|
| 190 |
+
"loss": 0.7689,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.2,
|
| 195 |
+
"grad_norm": 0.1622511683293268,
|
| 196 |
+
"learning_rate": 0.00019396926207859084,
|
| 197 |
+
"loss": 0.7375,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.21,
|
| 202 |
+
"grad_norm": 0.18313460619011496,
|
| 203 |
+
"learning_rate": 0.00019301713332493386,
|
| 204 |
+
"loss": 0.7385,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.22,
|
| 209 |
+
"grad_norm": 0.17951515004814617,
|
| 210 |
+
"learning_rate": 0.00019199794436588243,
|
| 211 |
+
"loss": 0.7399,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.22,
|
| 216 |
+
"grad_norm": 0.17473307701756932,
|
| 217 |
+
"learning_rate": 0.0001909124299802724,
|
| 218 |
+
"loss": 0.7594,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.23,
|
| 223 |
+
"grad_norm": 0.16310885248098056,
|
| 224 |
+
"learning_rate": 0.0001897613727639014,
|
| 225 |
+
"loss": 0.7178,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.24,
|
| 230 |
+
"grad_norm": 0.1895983902895304,
|
| 231 |
+
"learning_rate": 0.000188545602565321,
|
| 232 |
+
"loss": 0.7259,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.25,
|
| 237 |
+
"grad_norm": 0.17011783213385412,
|
| 238 |
+
"learning_rate": 0.00018726599588756145,
|
| 239 |
+
"loss": 0.7663,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.25,
|
| 244 |
+
"grad_norm": 0.19740064630501092,
|
| 245 |
+
"learning_rate": 0.0001859234752562217,
|
| 246 |
+
"loss": 0.7835,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.26,
|
| 251 |
+
"grad_norm": 0.176460816673931,
|
| 252 |
+
"learning_rate": 0.0001845190085543795,
|
| 253 |
+
"loss": 0.7742,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.27,
|
| 258 |
+
"grad_norm": 0.1776861592924501,
|
| 259 |
+
"learning_rate": 0.00018305360832480117,
|
| 260 |
+
"loss": 0.7483,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.28,
|
| 265 |
+
"grad_norm": 0.18361359295861726,
|
| 266 |
+
"learning_rate": 0.00018152833103995443,
|
| 267 |
+
"loss": 0.767,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.28,
|
| 272 |
+
"grad_norm": 0.17604664269508136,
|
| 273 |
+
"learning_rate": 0.00017994427634035015,
|
| 274 |
+
"loss": 0.76,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.29,
|
| 279 |
+
"grad_norm": 0.18343023724564714,
|
| 280 |
+
"learning_rate": 0.00017830258624176225,
|
| 281 |
+
"loss": 0.7665,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.3,
|
| 286 |
+
"grad_norm": 0.17483015598221394,
|
| 287 |
+
"learning_rate": 0.0001766044443118978,
|
| 288 |
+
"loss": 0.7239,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.31,
|
| 293 |
+
"grad_norm": 0.1778755737742503,
|
| 294 |
+
"learning_rate": 0.00017485107481711012,
|
| 295 |
+
"loss": 0.7617,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.32,
|
| 300 |
+
"grad_norm": 0.17763024228280486,
|
| 301 |
+
"learning_rate": 0.00017304374183977033,
|
| 302 |
+
"loss": 0.7664,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.32,
|
| 307 |
+
"grad_norm": 0.17405205010652272,
|
| 308 |
+
"learning_rate": 0.00017118374836693406,
|
| 309 |
+
"loss": 0.7568,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.33,
|
| 314 |
+
"grad_norm": 0.20068956314633762,
|
| 315 |
+
"learning_rate": 0.00016927243535095997,
|
| 316 |
+
"loss": 0.7614,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.34,
|
| 321 |
+
"grad_norm": 0.17815075790056695,
|
| 322 |
+
"learning_rate": 0.00016731118074275704,
|
| 323 |
+
"loss": 0.7445,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.35,
|
| 328 |
+
"grad_norm": 0.1732484639432504,
|
| 329 |
+
"learning_rate": 0.0001653013984983585,
|
| 330 |
+
"loss": 0.7413,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.35,
|
| 335 |
+
"grad_norm": 0.16182846941484944,
|
| 336 |
+
"learning_rate": 0.00016324453755953773,
|
| 337 |
+
"loss": 0.7411,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.36,
|
| 342 |
+
"grad_norm": 0.18502931691402047,
|
| 343 |
+
"learning_rate": 0.00016114208080920123,
|
| 344 |
+
"loss": 0.7567,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.37,
|
| 349 |
+
"grad_norm": 0.19284513271580453,
|
| 350 |
+
"learning_rate": 0.00015899554400231232,
|
| 351 |
+
"loss": 0.7611,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.38,
|
| 356 |
+
"grad_norm": 0.18204918517543528,
|
| 357 |
+
"learning_rate": 0.00015680647467311557,
|
| 358 |
+
"loss": 0.7637,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.38,
|
| 363 |
+
"grad_norm": 0.18152147568265412,
|
| 364 |
+
"learning_rate": 0.00015457645101945046,
|
| 365 |
+
"loss": 0.7613,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.39,
|
| 370 |
+
"grad_norm": 0.17373412443807332,
|
| 371 |
+
"learning_rate": 0.00015230708076495775,
|
| 372 |
+
"loss": 0.734,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.4,
|
| 377 |
+
"grad_norm": 0.20935352135186272,
|
| 378 |
+
"learning_rate": 0.00015000000000000001,
|
| 379 |
+
"loss": 0.7503,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.41,
|
| 384 |
+
"grad_norm": 0.19127094935614322,
|
| 385 |
+
"learning_rate": 0.0001476568720021308,
|
| 386 |
+
"loss": 0.7649,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.42,
|
| 391 |
+
"grad_norm": 0.18459794613971947,
|
| 392 |
+
"learning_rate": 0.00014527938603696376,
|
| 393 |
+
"loss": 0.7582,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.42,
|
| 398 |
+
"grad_norm": 0.16739519013438775,
|
| 399 |
+
"learning_rate": 0.00014286925614030542,
|
| 400 |
+
"loss": 0.7028,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.43,
|
| 405 |
+
"grad_norm": 0.17618630132316776,
|
| 406 |
+
"learning_rate": 0.0001404282198824305,
|
| 407 |
+
"loss": 0.7759,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.44,
|
| 412 |
+
"grad_norm": 0.1742265666097768,
|
| 413 |
+
"learning_rate": 0.00013795803711538966,
|
| 414 |
+
"loss": 0.7499,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.45,
|
| 419 |
+
"grad_norm": 0.16927687855060541,
|
| 420 |
+
"learning_rate": 0.00013546048870425356,
|
| 421 |
+
"loss": 0.7785,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.45,
|
| 426 |
+
"grad_norm": 0.16526453726289647,
|
| 427 |
+
"learning_rate": 0.00013293737524320797,
|
| 428 |
+
"loss": 0.707,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.46,
|
| 433 |
+
"grad_norm": 0.16424167922354121,
|
| 434 |
+
"learning_rate": 0.0001303905157574247,
|
| 435 |
+
"loss": 0.7736,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.47,
|
| 440 |
+
"grad_norm": 0.1689166927092904,
|
| 441 |
+
"learning_rate": 0.0001278217463916453,
|
| 442 |
+
"loss": 0.7376,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.48,
|
| 447 |
+
"grad_norm": 0.17538502991890237,
|
| 448 |
+
"learning_rate": 0.00012523291908642217,
|
| 449 |
+
"loss": 0.7561,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.48,
|
| 454 |
+
"grad_norm": 0.16834661737082066,
|
| 455 |
+
"learning_rate": 0.00012262590024297225,
|
| 456 |
+
"loss": 0.7879,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.49,
|
| 461 |
+
"grad_norm": 0.18075535513747248,
|
| 462 |
+
"learning_rate": 0.00012000256937760445,
|
| 463 |
+
"loss": 0.76,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.5,
|
| 468 |
+
"grad_norm": 0.18435217046485927,
|
| 469 |
+
"learning_rate": 0.00011736481776669306,
|
| 470 |
+
"loss": 0.7634,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.51,
|
| 475 |
+
"grad_norm": 0.19534270424648292,
|
| 476 |
+
"learning_rate": 0.00011471454708317162,
|
| 477 |
+
"loss": 0.7289,
|
| 478 |
+
"step": 330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.52,
|
| 482 |
+
"grad_norm": 0.16179391514607225,
|
| 483 |
+
"learning_rate": 0.0001120536680255323,
|
| 484 |
+
"loss": 0.7757,
|
| 485 |
+
"step": 335
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.52,
|
| 489 |
+
"grad_norm": 0.16984696045342035,
|
| 490 |
+
"learning_rate": 0.00010938409894031794,
|
| 491 |
+
"loss": 0.7728,
|
| 492 |
+
"step": 340
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.53,
|
| 496 |
+
"grad_norm": 0.17164253966708626,
|
| 497 |
+
"learning_rate": 0.00010670776443910024,
|
| 498 |
+
"loss": 0.7567,
|
| 499 |
+
"step": 345
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.54,
|
| 503 |
+
"grad_norm": 0.1762947619639153,
|
| 504 |
+
"learning_rate": 0.00010402659401094152,
|
| 505 |
+
"loss": 0.7622,
|
| 506 |
+
"step": 350
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.55,
|
| 510 |
+
"grad_norm": 0.1643638219047145,
|
| 511 |
+
"learning_rate": 0.00010134252063133975,
|
| 512 |
+
"loss": 0.7445,
|
| 513 |
+
"step": 355
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.55,
|
| 517 |
+
"grad_norm": 0.18083244859851283,
|
| 518 |
+
"learning_rate": 9.865747936866027e-05,
|
| 519 |
+
"loss": 0.7267,
|
| 520 |
+
"step": 360
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.56,
|
| 524 |
+
"grad_norm": 0.17258431530932208,
|
| 525 |
+
"learning_rate": 9.597340598905852e-05,
|
| 526 |
+
"loss": 0.7365,
|
| 527 |
+
"step": 365
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.57,
|
| 531 |
+
"grad_norm": 0.16200859086797756,
|
| 532 |
+
"learning_rate": 9.329223556089975e-05,
|
| 533 |
+
"loss": 0.7387,
|
| 534 |
+
"step": 370
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.58,
|
| 538 |
+
"grad_norm": 0.16774671238035113,
|
| 539 |
+
"learning_rate": 9.061590105968208e-05,
|
| 540 |
+
"loss": 0.7318,
|
| 541 |
+
"step": 375
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.58,
|
| 545 |
+
"grad_norm": 0.1692828345651934,
|
| 546 |
+
"learning_rate": 8.79463319744677e-05,
|
| 547 |
+
"loss": 0.7896,
|
| 548 |
+
"step": 380
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.59,
|
| 552 |
+
"grad_norm": 0.15934964070723345,
|
| 553 |
+
"learning_rate": 8.528545291682838e-05,
|
| 554 |
+
"loss": 0.6854,
|
| 555 |
+
"step": 385
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.6,
|
| 559 |
+
"grad_norm": 0.1550634713902335,
|
| 560 |
+
"learning_rate": 8.263518223330697e-05,
|
| 561 |
+
"loss": 0.7837,
|
| 562 |
+
"step": 390
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.61,
|
| 566 |
+
"grad_norm": 0.1607860378586748,
|
| 567 |
+
"learning_rate": 7.999743062239557e-05,
|
| 568 |
+
"loss": 0.7537,
|
| 569 |
+
"step": 395
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.62,
|
| 573 |
+
"grad_norm": 0.16982363325460645,
|
| 574 |
+
"learning_rate": 7.73740997570278e-05,
|
| 575 |
+
"loss": 0.7476,
|
| 576 |
+
"step": 400
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.62,
|
| 580 |
+
"grad_norm": 0.1787899661184355,
|
| 581 |
+
"learning_rate": 7.476708091357782e-05,
|
| 582 |
+
"loss": 0.7292,
|
| 583 |
+
"step": 405
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.63,
|
| 587 |
+
"grad_norm": 0.17032167101003257,
|
| 588 |
+
"learning_rate": 7.217825360835473e-05,
|
| 589 |
+
"loss": 0.7481,
|
| 590 |
+
"step": 410
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.64,
|
| 594 |
+
"grad_norm": 0.1808269404462512,
|
| 595 |
+
"learning_rate": 6.960948424257532e-05,
|
| 596 |
+
"loss": 0.7367,
|
| 597 |
+
"step": 415
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.65,
|
| 601 |
+
"grad_norm": 0.17901906299647485,
|
| 602 |
+
"learning_rate": 6.706262475679205e-05,
|
| 603 |
+
"loss": 0.7605,
|
| 604 |
+
"step": 420
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.65,
|
| 608 |
+
"grad_norm": 0.18834056302806162,
|
| 609 |
+
"learning_rate": 6.453951129574644e-05,
|
| 610 |
+
"loss": 0.788,
|
| 611 |
+
"step": 425
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.66,
|
| 615 |
+
"grad_norm": 0.18253089327197253,
|
| 616 |
+
"learning_rate": 6.204196288461037e-05,
|
| 617 |
+
"loss": 0.7485,
|
| 618 |
+
"step": 430
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.67,
|
| 622 |
+
"grad_norm": 0.1896961988867079,
|
| 623 |
+
"learning_rate": 5.957178011756952e-05,
|
| 624 |
+
"loss": 0.7462,
|
| 625 |
+
"step": 435
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.68,
|
| 629 |
+
"grad_norm": 0.18760202699871834,
|
| 630 |
+
"learning_rate": 5.713074385969457e-05,
|
| 631 |
+
"loss": 0.756,
|
| 632 |
+
"step": 440
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.68,
|
| 636 |
+
"grad_norm": 0.1773529126283878,
|
| 637 |
+
"learning_rate": 5.472061396303629e-05,
|
| 638 |
+
"loss": 0.7426,
|
| 639 |
+
"step": 445
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.69,
|
| 643 |
+
"grad_norm": 0.1669653708836188,
|
| 644 |
+
"learning_rate": 5.234312799786921e-05,
|
| 645 |
+
"loss": 0.7214,
|
| 646 |
+
"step": 450
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.7,
|
| 650 |
+
"grad_norm": 0.16724226423303531,
|
| 651 |
+
"learning_rate": 5.000000000000002e-05,
|
| 652 |
+
"loss": 0.7554,
|
| 653 |
+
"step": 455
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.71,
|
| 657 |
+
"grad_norm": 0.1605488611045014,
|
| 658 |
+
"learning_rate": 4.7692919235042255e-05,
|
| 659 |
+
"loss": 0.7395,
|
| 660 |
+
"step": 460
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.72,
|
| 664 |
+
"grad_norm": 0.1724230273686043,
|
| 665 |
+
"learning_rate": 4.542354898054953e-05,
|
| 666 |
+
"loss": 0.6914,
|
| 667 |
+
"step": 465
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.72,
|
| 671 |
+
"grad_norm": 0.18876308185046786,
|
| 672 |
+
"learning_rate": 4.3193525326884435e-05,
|
| 673 |
+
"loss": 0.774,
|
| 674 |
+
"step": 470
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.73,
|
| 678 |
+
"grad_norm": 0.15832807229666745,
|
| 679 |
+
"learning_rate": 4.100445599768774e-05,
|
| 680 |
+
"loss": 0.7285,
|
| 681 |
+
"step": 475
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.74,
|
| 685 |
+
"grad_norm": 0.20134778903646663,
|
| 686 |
+
"learning_rate": 3.885791919079878e-05,
|
| 687 |
+
"loss": 0.7513,
|
| 688 |
+
"step": 480
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.75,
|
| 692 |
+
"grad_norm": 0.17746064473235634,
|
| 693 |
+
"learning_rate": 3.675546244046228e-05,
|
| 694 |
+
"loss": 0.7175,
|
| 695 |
+
"step": 485
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.75,
|
| 699 |
+
"grad_norm": 0.17200683319654153,
|
| 700 |
+
"learning_rate": 3.469860150164152e-05,
|
| 701 |
+
"loss": 0.7321,
|
| 702 |
+
"step": 490
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.76,
|
| 706 |
+
"grad_norm": 0.15989134079339526,
|
| 707 |
+
"learning_rate": 3.268881925724297e-05,
|
| 708 |
+
"loss": 0.7379,
|
| 709 |
+
"step": 495
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.77,
|
| 713 |
+
"grad_norm": 0.15850580729842006,
|
| 714 |
+
"learning_rate": 3.072756464904006e-05,
|
| 715 |
+
"loss": 0.7376,
|
| 716 |
+
"step": 500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.78,
|
| 720 |
+
"grad_norm": 0.18738024330457914,
|
| 721 |
+
"learning_rate": 2.881625163306596e-05,
|
| 722 |
+
"loss": 0.7471,
|
| 723 |
+
"step": 505
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.78,
|
| 727 |
+
"grad_norm": 0.1666154545377965,
|
| 728 |
+
"learning_rate": 2.6956258160229695e-05,
|
| 729 |
+
"loss": 0.7281,
|
| 730 |
+
"step": 510
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.79,
|
| 734 |
+
"grad_norm": 0.1876771320924796,
|
| 735 |
+
"learning_rate": 2.514892518288988e-05,
|
| 736 |
+
"loss": 0.7482,
|
| 737 |
+
"step": 515
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.8,
|
| 741 |
+
"grad_norm": 0.16905049400258154,
|
| 742 |
+
"learning_rate": 2.339555568810221e-05,
|
| 743 |
+
"loss": 0.749,
|
| 744 |
+
"step": 520
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.81,
|
| 748 |
+
"grad_norm": 0.18106716736760403,
|
| 749 |
+
"learning_rate": 2.1697413758237784e-05,
|
| 750 |
+
"loss": 0.7601,
|
| 751 |
+
"step": 525
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.82,
|
| 755 |
+
"grad_norm": 0.1616487448106075,
|
| 756 |
+
"learning_rate": 2.0055723659649904e-05,
|
| 757 |
+
"loss": 0.7509,
|
| 758 |
+
"step": 530
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.82,
|
| 762 |
+
"grad_norm": 0.16890169036482472,
|
| 763 |
+
"learning_rate": 1.8471668960045574e-05,
|
| 764 |
+
"loss": 0.7066,
|
| 765 |
+
"step": 535
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.83,
|
| 769 |
+
"grad_norm": 0.1632645450151788,
|
| 770 |
+
"learning_rate": 1.6946391675198836e-05,
|
| 771 |
+
"loss": 0.7396,
|
| 772 |
+
"step": 540
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.84,
|
| 776 |
+
"grad_norm": 0.18148424988604053,
|
| 777 |
+
"learning_rate": 1.5480991445620542e-05,
|
| 778 |
+
"loss": 0.7602,
|
| 779 |
+
"step": 545
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.85,
|
| 783 |
+
"grad_norm": 0.16966068643276655,
|
| 784 |
+
"learning_rate": 1.4076524743778319e-05,
|
| 785 |
+
"loss": 0.7002,
|
| 786 |
+
"step": 550
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.85,
|
| 790 |
+
"grad_norm": 0.16674840971276483,
|
| 791 |
+
"learning_rate": 1.2734004112438568e-05,
|
| 792 |
+
"loss": 0.7596,
|
| 793 |
+
"step": 555
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.86,
|
| 797 |
+
"grad_norm": 0.16780234279195239,
|
| 798 |
+
"learning_rate": 1.1454397434679021e-05,
|
| 799 |
+
"loss": 0.7404,
|
| 800 |
+
"step": 560
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.87,
|
| 804 |
+
"grad_norm": 0.1688456301085619,
|
| 805 |
+
"learning_rate": 1.0238627236098619e-05,
|
| 806 |
+
"loss": 0.742,
|
| 807 |
+
"step": 565
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.88,
|
| 811 |
+
"grad_norm": 0.16354206297853066,
|
| 812 |
+
"learning_rate": 9.08757001972762e-06,
|
| 813 |
+
"loss": 0.7227,
|
| 814 |
+
"step": 570
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.88,
|
| 818 |
+
"grad_norm": 0.17015103460312153,
|
| 819 |
+
"learning_rate": 8.002055634117578e-06,
|
| 820 |
+
"loss": 0.7265,
|
| 821 |
+
"step": 575
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.89,
|
| 825 |
+
"grad_norm": 0.17411041321482185,
|
| 826 |
+
"learning_rate": 6.9828666750661795e-06,
|
| 827 |
+
"loss": 0.7408,
|
| 828 |
+
"step": 580
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.9,
|
| 832 |
+
"grad_norm": 0.15987450052661933,
|
| 833 |
+
"learning_rate": 6.030737921409169e-06,
|
| 834 |
+
"loss": 0.7541,
|
| 835 |
+
"step": 585
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.91,
|
| 839 |
+
"grad_norm": 0.16461391402486866,
|
| 840 |
+
"learning_rate": 5.146355805285452e-06,
|
| 841 |
+
"loss": 0.7288,
|
| 842 |
+
"step": 590
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.92,
|
| 846 |
+
"grad_norm": 0.17493762678626293,
|
| 847 |
+
"learning_rate": 4.3303579172574885e-06,
|
| 848 |
+
"loss": 0.7451,
|
| 849 |
+
"step": 595
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.92,
|
| 853 |
+
"grad_norm": 0.16247847988130878,
|
| 854 |
+
"learning_rate": 3.5833325466437694e-06,
|
| 855 |
+
"loss": 0.7299,
|
| 856 |
+
"step": 600
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.93,
|
| 860 |
+
"grad_norm": 0.1643216040963927,
|
| 861 |
+
"learning_rate": 2.905818257394799e-06,
|
| 862 |
+
"loss": 0.7473,
|
| 863 |
+
"step": 605
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.94,
|
| 867 |
+
"grad_norm": 0.16603719389852187,
|
| 868 |
+
"learning_rate": 2.2983034998182997e-06,
|
| 869 |
+
"loss": 0.7345,
|
| 870 |
+
"step": 610
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.95,
|
| 874 |
+
"grad_norm": 0.1905014253547241,
|
| 875 |
+
"learning_rate": 1.7612262584335237e-06,
|
| 876 |
+
"loss": 0.7193,
|
| 877 |
+
"step": 615
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.95,
|
| 881 |
+
"grad_norm": 0.17400163902350113,
|
| 882 |
+
"learning_rate": 1.2949737362087156e-06,
|
| 883 |
+
"loss": 0.7942,
|
| 884 |
+
"step": 620
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.96,
|
| 888 |
+
"grad_norm": 0.17549556714092185,
|
| 889 |
+
"learning_rate": 8.998820754091531e-07,
|
| 890 |
+
"loss": 0.7735,
|
| 891 |
+
"step": 625
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.97,
|
| 895 |
+
"grad_norm": 0.17592545054253697,
|
| 896 |
+
"learning_rate": 5.762361152572115e-07,
|
| 897 |
+
"loss": 0.7364,
|
| 898 |
+
"step": 630
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.98,
|
| 902 |
+
"grad_norm": 0.18023784894742628,
|
| 903 |
+
"learning_rate": 3.2426918657900704e-07,
|
| 904 |
+
"loss": 0.7338,
|
| 905 |
+
"step": 635
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.98,
|
| 909 |
+
"grad_norm": 0.17195796913696132,
|
| 910 |
+
"learning_rate": 1.4416294358582384e-07,
|
| 911 |
+
"loss": 0.7572,
|
| 912 |
+
"step": 640
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.99,
|
| 916 |
+
"grad_norm": 0.17111312234723997,
|
| 917 |
+
"learning_rate": 3.60472329114625e-08,
|
| 918 |
+
"loss": 0.7365,
|
| 919 |
+
"step": 645
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.0,
|
| 923 |
+
"grad_norm": 0.18043206582301746,
|
| 924 |
+
"learning_rate": 0.0,
|
| 925 |
+
"loss": 0.7291,
|
| 926 |
+
"step": 650
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.0,
|
| 930 |
+
"eval_loss": NaN,
|
| 931 |
+
"eval_runtime": 2999.5091,
|
| 932 |
+
"eval_samples_per_second": 1.541,
|
| 933 |
+
"eval_steps_per_second": 0.385,
|
| 934 |
+
"step": 650
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.0,
|
| 938 |
+
"step": 650,
|
| 939 |
+
"total_flos": 7820976031531008.0,
|
| 940 |
+
"train_loss": 0.7519041672119727,
|
| 941 |
+
"train_runtime": 26444.6436,
|
| 942 |
+
"train_samples_per_second": 1.572,
|
| 943 |
+
"train_steps_per_second": 0.025
|
| 944 |
+
}
|
| 945 |
+
],
|
| 946 |
+
"logging_steps": 5,
|
| 947 |
+
"max_steps": 650,
|
| 948 |
+
"num_input_tokens_seen": 0,
|
| 949 |
+
"num_train_epochs": 1,
|
| 950 |
+
"save_steps": 100,
|
| 951 |
+
"total_flos": 7820976031531008.0,
|
| 952 |
+
"train_batch_size": 8,
|
| 953 |
+
"trial_name": null,
|
| 954 |
+
"trial_params": null
|
| 955 |
+
}
|