Model save
Browse files- README.md +69 -0
- adapter_model.safetensors +1 -1
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +1046 -0
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-Instruct-v0.2
|
| 9 |
+
model-index:
|
| 10 |
+
- name: Mistral-7B-Instruct-v0.2-multilingual-deita-10k-v0-sft-v0.1
|
| 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-7B-Instruct-v0.2-multilingual-deita-10k-v0-sft-v0.1
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.6609
|
| 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: 4
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- num_devices: 4
|
| 46 |
+
- gradient_accumulation_steps: 2
|
| 47 |
+
- total_train_batch_size: 32
|
| 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 |
+
| 0.8266 | 0.2861 | 200 | 0.6874 |
|
| 59 |
+
| 0.7478 | 0.5722 | 400 | 0.6693 |
|
| 60 |
+
| 0.7963 | 0.8584 | 600 | 0.6609 |
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
### Framework versions
|
| 64 |
+
|
| 65 |
+
- PEFT 0.7.1
|
| 66 |
+
- Transformers 4.41.2
|
| 67 |
+
- Pytorch 2.3.0+cu121
|
| 68 |
+
- Datasets 2.20.0
|
| 69 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 83946192
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:941201da74138fab79808af623a62a24a05e29e66c5c6bee7fc1b18eddf11494
|
| 3 |
size 83946192
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 1.493876632190976e+16,
|
| 4 |
+
"train_loss": 0.7242236417932743,
|
| 5 |
+
"train_runtime": 29465.3177,
|
| 6 |
+
"train_samples": 22361,
|
| 7 |
+
"train_samples_per_second": 0.759,
|
| 8 |
+
"train_steps_per_second": 0.024
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 1.493876632190976e+16,
|
| 4 |
+
"train_loss": 0.7242236417932743,
|
| 5 |
+
"train_runtime": 29465.3177,
|
| 6 |
+
"train_samples": 22361,
|
| 7 |
+
"train_samples_per_second": 0.759,
|
| 8 |
+
"train_steps_per_second": 0.024
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1046 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 699,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.001430615164520744,
|
| 13 |
+
"grad_norm": 0.7870709777607977,
|
| 14 |
+
"learning_rate": 2.8571428571428573e-06,
|
| 15 |
+
"loss": 0.9791,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.00715307582260372,
|
| 20 |
+
"grad_norm": 0.673048592872478,
|
| 21 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 22 |
+
"loss": 0.9655,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.01430615164520744,
|
| 27 |
+
"grad_norm": 0.6751613698851058,
|
| 28 |
+
"learning_rate": 2.857142857142857e-05,
|
| 29 |
+
"loss": 1.0427,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.02145922746781116,
|
| 34 |
+
"grad_norm": 0.37361113910805865,
|
| 35 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 36 |
+
"loss": 1.0165,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02861230329041488,
|
| 41 |
+
"grad_norm": 0.25425037309567433,
|
| 42 |
+
"learning_rate": 5.714285714285714e-05,
|
| 43 |
+
"loss": 0.7928,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0357653791130186,
|
| 48 |
+
"grad_norm": 0.47123658085709424,
|
| 49 |
+
"learning_rate": 7.142857142857143e-05,
|
| 50 |
+
"loss": 0.9567,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.04291845493562232,
|
| 55 |
+
"grad_norm": 0.19886770818499985,
|
| 56 |
+
"learning_rate": 8.571428571428571e-05,
|
| 57 |
+
"loss": 0.7555,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.05007153075822604,
|
| 62 |
+
"grad_norm": 0.18492536060018994,
|
| 63 |
+
"learning_rate": 0.0001,
|
| 64 |
+
"loss": 0.8203,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.05722460658082976,
|
| 69 |
+
"grad_norm": 0.11579635774128288,
|
| 70 |
+
"learning_rate": 0.00011428571428571428,
|
| 71 |
+
"loss": 0.8403,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.06437768240343347,
|
| 76 |
+
"grad_norm": 0.14426080380091869,
|
| 77 |
+
"learning_rate": 0.00012857142857142858,
|
| 78 |
+
"loss": 0.765,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.0715307582260372,
|
| 83 |
+
"grad_norm": 0.3962935654200976,
|
| 84 |
+
"learning_rate": 0.00014285714285714287,
|
| 85 |
+
"loss": 0.9031,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.07868383404864092,
|
| 90 |
+
"grad_norm": 0.1122336069942178,
|
| 91 |
+
"learning_rate": 0.00015714285714285716,
|
| 92 |
+
"loss": 0.7221,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.08583690987124463,
|
| 97 |
+
"grad_norm": 0.14487919195639437,
|
| 98 |
+
"learning_rate": 0.00017142857142857143,
|
| 99 |
+
"loss": 0.8207,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.09298998569384835,
|
| 104 |
+
"grad_norm": 0.10991881963153113,
|
| 105 |
+
"learning_rate": 0.00018571428571428572,
|
| 106 |
+
"loss": 0.7837,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.10014306151645208,
|
| 111 |
+
"grad_norm": 0.12479037045363885,
|
| 112 |
+
"learning_rate": 0.0002,
|
| 113 |
+
"loss": 0.6984,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.1072961373390558,
|
| 118 |
+
"grad_norm": 0.3825157581902254,
|
| 119 |
+
"learning_rate": 0.00019996881929740885,
|
| 120 |
+
"loss": 0.8457,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.11444921316165951,
|
| 125 |
+
"grad_norm": 0.10204843755668831,
|
| 126 |
+
"learning_rate": 0.00019987529663435965,
|
| 127 |
+
"loss": 0.6723,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.12160228898426323,
|
| 132 |
+
"grad_norm": 0.1556108526142336,
|
| 133 |
+
"learning_rate": 0.00019971949033289923,
|
| 134 |
+
"loss": 0.787,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.12875536480686695,
|
| 139 |
+
"grad_norm": 0.1089156658349774,
|
| 140 |
+
"learning_rate": 0.00019950149755602656,
|
| 141 |
+
"loss": 0.7182,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.13590844062947066,
|
| 146 |
+
"grad_norm": 0.11809573830330126,
|
| 147 |
+
"learning_rate": 0.00019922145424710051,
|
| 148 |
+
"loss": 0.7088,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.1430615164520744,
|
| 153 |
+
"grad_norm": 0.4570754502103615,
|
| 154 |
+
"learning_rate": 0.00019887953504506362,
|
| 155 |
+
"loss": 0.8189,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.15021459227467812,
|
| 160 |
+
"grad_norm": 0.10840048416131945,
|
| 161 |
+
"learning_rate": 0.00019847595317553488,
|
| 162 |
+
"loss": 0.6759,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.15736766809728184,
|
| 167 |
+
"grad_norm": 0.1381325645315335,
|
| 168 |
+
"learning_rate": 0.0001980109603178392,
|
| 169 |
+
"loss": 0.768,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.16452074391988555,
|
| 174 |
+
"grad_norm": 0.1017001439638063,
|
| 175 |
+
"learning_rate": 0.0001974848464480566,
|
| 176 |
+
"loss": 0.7698,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.17167381974248927,
|
| 181 |
+
"grad_norm": 0.13205919198629731,
|
| 182 |
+
"learning_rate": 0.00019689793965818917,
|
| 183 |
+
"loss": 0.6944,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.17882689556509299,
|
| 188 |
+
"grad_norm": 0.48394521253305983,
|
| 189 |
+
"learning_rate": 0.00019625060595155816,
|
| 190 |
+
"loss": 0.8363,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.1859799713876967,
|
| 195 |
+
"grad_norm": 0.14521632085748434,
|
| 196 |
+
"learning_rate": 0.00019554324901455928,
|
| 197 |
+
"loss": 0.662,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.19313304721030042,
|
| 202 |
+
"grad_norm": 0.1689121199898348,
|
| 203 |
+
"learning_rate": 0.00019477630996491804,
|
| 204 |
+
"loss": 0.7749,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.20028612303290416,
|
| 209 |
+
"grad_norm": 0.10646210944295648,
|
| 210 |
+
"learning_rate": 0.00019395026707660275,
|
| 211 |
+
"loss": 0.7846,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.20743919885550788,
|
| 216 |
+
"grad_norm": 0.11099677119841628,
|
| 217 |
+
"learning_rate": 0.00019306563548156594,
|
| 218 |
+
"loss": 0.6496,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.2145922746781116,
|
| 223 |
+
"grad_norm": 0.4940715196481721,
|
| 224 |
+
"learning_rate": 0.00019212296684850095,
|
| 225 |
+
"loss": 0.7797,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.2217453505007153,
|
| 230 |
+
"grad_norm": 0.10857780176447043,
|
| 231 |
+
"learning_rate": 0.0001911228490388136,
|
| 232 |
+
"loss": 0.6568,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.22889842632331903,
|
| 237 |
+
"grad_norm": 0.1558194607792288,
|
| 238 |
+
"learning_rate": 0.00019006590574002346,
|
| 239 |
+
"loss": 0.7589,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.23605150214592274,
|
| 244 |
+
"grad_norm": 0.11205216199084236,
|
| 245 |
+
"learning_rate": 0.00018895279607682365,
|
| 246 |
+
"loss": 0.7432,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.24320457796852646,
|
| 251 |
+
"grad_norm": 0.10598348111600908,
|
| 252 |
+
"learning_rate": 0.00018778421420004136,
|
| 253 |
+
"loss": 0.6713,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.2503576537911302,
|
| 258 |
+
"grad_norm": 0.37721971351878564,
|
| 259 |
+
"learning_rate": 0.00018656088885375568,
|
| 260 |
+
"loss": 0.7928,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.2575107296137339,
|
| 265 |
+
"grad_norm": 0.11245600928935082,
|
| 266 |
+
"learning_rate": 0.00018528358292084246,
|
| 267 |
+
"loss": 0.6346,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.2646638054363376,
|
| 272 |
+
"grad_norm": 0.1620137549427017,
|
| 273 |
+
"learning_rate": 0.00018395309294723,
|
| 274 |
+
"loss": 0.757,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.2718168812589413,
|
| 279 |
+
"grad_norm": 0.09949111843144275,
|
| 280 |
+
"learning_rate": 0.00018257024864516162,
|
| 281 |
+
"loss": 0.7145,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.27896995708154504,
|
| 286 |
+
"grad_norm": 0.12215913633341108,
|
| 287 |
+
"learning_rate": 0.00018113591237577556,
|
| 288 |
+
"loss": 0.6667,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.2861230329041488,
|
| 293 |
+
"grad_norm": 0.5598361803307672,
|
| 294 |
+
"learning_rate": 0.00017965097861132447,
|
| 295 |
+
"loss": 0.8266,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.2861230329041488,
|
| 300 |
+
"eval_loss": 0.68742835521698,
|
| 301 |
+
"eval_runtime": 974.2638,
|
| 302 |
+
"eval_samples_per_second": 2.053,
|
| 303 |
+
"eval_steps_per_second": 0.128,
|
| 304 |
+
"step": 200
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.2932761087267525,
|
| 308 |
+
"grad_norm": 0.1103365072886984,
|
| 309 |
+
"learning_rate": 0.00017811637337736988,
|
| 310 |
+
"loss": 0.6201,
|
| 311 |
+
"step": 205
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.30042918454935624,
|
| 315 |
+
"grad_norm": 0.18081388953274952,
|
| 316 |
+
"learning_rate": 0.00017653305367529968,
|
| 317 |
+
"loss": 0.7519,
|
| 318 |
+
"step": 210
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.30758226037195996,
|
| 322 |
+
"grad_norm": 0.0979269774081774,
|
| 323 |
+
"learning_rate": 0.00017490200688552866,
|
| 324 |
+
"loss": 0.7811,
|
| 325 |
+
"step": 215
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.3147353361945637,
|
| 329 |
+
"grad_norm": 0.1178423488937459,
|
| 330 |
+
"learning_rate": 0.00017322425015175403,
|
| 331 |
+
"loss": 0.6599,
|
| 332 |
+
"step": 220
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.3218884120171674,
|
| 336 |
+
"grad_norm": 0.38638772763542717,
|
| 337 |
+
"learning_rate": 0.00017150082974665053,
|
| 338 |
+
"loss": 0.7658,
|
| 339 |
+
"step": 225
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.3290414878397711,
|
| 343 |
+
"grad_norm": 0.10912001826583005,
|
| 344 |
+
"learning_rate": 0.00016973282041940005,
|
| 345 |
+
"loss": 0.6353,
|
| 346 |
+
"step": 230
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.3361945636623748,
|
| 350 |
+
"grad_norm": 0.13882513170563118,
|
| 351 |
+
"learning_rate": 0.00016792132472546274,
|
| 352 |
+
"loss": 0.778,
|
| 353 |
+
"step": 235
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.34334763948497854,
|
| 357 |
+
"grad_norm": 0.10083866344440855,
|
| 358 |
+
"learning_rate": 0.00016606747233900815,
|
| 359 |
+
"loss": 0.7229,
|
| 360 |
+
"step": 240
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.35050071530758226,
|
| 364 |
+
"grad_norm": 0.1254352004833624,
|
| 365 |
+
"learning_rate": 0.00016417241934843456,
|
| 366 |
+
"loss": 0.7063,
|
| 367 |
+
"step": 245
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.35765379113018597,
|
| 371 |
+
"grad_norm": 0.46499091728878567,
|
| 372 |
+
"learning_rate": 0.00016223734753541575,
|
| 373 |
+
"loss": 0.7838,
|
| 374 |
+
"step": 250
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.3648068669527897,
|
| 378 |
+
"grad_norm": 0.1078358562936522,
|
| 379 |
+
"learning_rate": 0.00016026346363792567,
|
| 380 |
+
"loss": 0.6502,
|
| 381 |
+
"step": 255
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.3719599427753934,
|
| 385 |
+
"grad_norm": 0.14916467905079567,
|
| 386 |
+
"learning_rate": 0.0001582519985976994,
|
| 387 |
+
"loss": 0.7599,
|
| 388 |
+
"step": 260
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.3791130185979971,
|
| 392 |
+
"grad_norm": 0.10034285034077563,
|
| 393 |
+
"learning_rate": 0.00015620420679260085,
|
| 394 |
+
"loss": 0.7457,
|
| 395 |
+
"step": 265
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.38626609442060084,
|
| 399 |
+
"grad_norm": 0.1178480592114291,
|
| 400 |
+
"learning_rate": 0.00015412136525437485,
|
| 401 |
+
"loss": 0.6755,
|
| 402 |
+
"step": 270
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.39341917024320455,
|
| 406 |
+
"grad_norm": 0.4121462451204322,
|
| 407 |
+
"learning_rate": 0.00015200477287227236,
|
| 408 |
+
"loss": 0.8288,
|
| 409 |
+
"step": 275
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.4005722460658083,
|
| 413 |
+
"grad_norm": 0.10328930758167154,
|
| 414 |
+
"learning_rate": 0.00014985574958304484,
|
| 415 |
+
"loss": 0.624,
|
| 416 |
+
"step": 280
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.40772532188841204,
|
| 420 |
+
"grad_norm": 0.13717935978977466,
|
| 421 |
+
"learning_rate": 0.00014767563554781316,
|
| 422 |
+
"loss": 0.732,
|
| 423 |
+
"step": 285
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.41487839771101576,
|
| 427 |
+
"grad_norm": 0.09128697749820436,
|
| 428 |
+
"learning_rate": 0.00014546579031632427,
|
| 429 |
+
"loss": 0.7197,
|
| 430 |
+
"step": 290
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.4220314735336195,
|
| 434 |
+
"grad_norm": 0.12086812939243298,
|
| 435 |
+
"learning_rate": 0.00014322759197911685,
|
| 436 |
+
"loss": 0.6709,
|
| 437 |
+
"step": 295
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.4291845493562232,
|
| 441 |
+
"grad_norm": 0.40143408299485855,
|
| 442 |
+
"learning_rate": 0.00014096243630812478,
|
| 443 |
+
"loss": 0.815,
|
| 444 |
+
"step": 300
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.4363376251788269,
|
| 448 |
+
"grad_norm": 0.09924403899475973,
|
| 449 |
+
"learning_rate": 0.00013867173588625405,
|
| 450 |
+
"loss": 0.6408,
|
| 451 |
+
"step": 305
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.4434907010014306,
|
| 455 |
+
"grad_norm": 0.13959887072890406,
|
| 456 |
+
"learning_rate": 0.0001363569192264762,
|
| 457 |
+
"loss": 0.731,
|
| 458 |
+
"step": 310
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.45064377682403434,
|
| 462 |
+
"grad_norm": 0.09921104913462633,
|
| 463 |
+
"learning_rate": 0.0001340194298809878,
|
| 464 |
+
"loss": 0.7096,
|
| 465 |
+
"step": 315
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.45779685264663805,
|
| 469 |
+
"grad_norm": 0.11089054056325505,
|
| 470 |
+
"learning_rate": 0.00013166072554099056,
|
| 471 |
+
"loss": 0.6672,
|
| 472 |
+
"step": 320
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.46494992846924177,
|
| 476 |
+
"grad_norm": 0.4230116831435091,
|
| 477 |
+
"learning_rate": 0.00012928227712765504,
|
| 478 |
+
"loss": 0.7871,
|
| 479 |
+
"step": 325
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.4721030042918455,
|
| 483 |
+
"grad_norm": 0.09737599815254978,
|
| 484 |
+
"learning_rate": 0.00012688556787483334,
|
| 485 |
+
"loss": 0.6405,
|
| 486 |
+
"step": 330
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.4792560801144492,
|
| 490 |
+
"grad_norm": 0.14484542924430074,
|
| 491 |
+
"learning_rate": 0.00012447209240409364,
|
| 492 |
+
"loss": 0.7468,
|
| 493 |
+
"step": 335
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.4864091559370529,
|
| 497 |
+
"grad_norm": 0.08987261375789386,
|
| 498 |
+
"learning_rate": 0.00012204335579265323,
|
| 499 |
+
"loss": 0.7169,
|
| 500 |
+
"step": 340
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.49356223175965663,
|
| 504 |
+
"grad_norm": 0.10881204819795895,
|
| 505 |
+
"learning_rate": 0.00011960087263479119,
|
| 506 |
+
"loss": 0.6587,
|
| 507 |
+
"step": 345
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.5007153075822603,
|
| 511 |
+
"grad_norm": 0.49675617394166816,
|
| 512 |
+
"learning_rate": 0.0001171461660973261,
|
| 513 |
+
"loss": 0.779,
|
| 514 |
+
"step": 350
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.5078683834048641,
|
| 518 |
+
"grad_norm": 0.10435791237431437,
|
| 519 |
+
"learning_rate": 0.00011468076696974778,
|
| 520 |
+
"loss": 0.6392,
|
| 521 |
+
"step": 355
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.5150214592274678,
|
| 525 |
+
"grad_norm": 0.14338822382120334,
|
| 526 |
+
"learning_rate": 0.00011220621270959564,
|
| 527 |
+
"loss": 0.746,
|
| 528 |
+
"step": 360
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.5221745350500715,
|
| 532 |
+
"grad_norm": 0.09020136891885296,
|
| 533 |
+
"learning_rate": 0.00010972404648367822,
|
| 534 |
+
"loss": 0.7134,
|
| 535 |
+
"step": 365
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.5293276108726752,
|
| 539 |
+
"grad_norm": 0.11624451016773857,
|
| 540 |
+
"learning_rate": 0.00010723581620573299,
|
| 541 |
+
"loss": 0.6715,
|
| 542 |
+
"step": 370
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.5364806866952789,
|
| 546 |
+
"grad_norm": 0.5023243515754996,
|
| 547 |
+
"learning_rate": 0.00010474307357112547,
|
| 548 |
+
"loss": 0.7996,
|
| 549 |
+
"step": 375
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.5436337625178826,
|
| 553 |
+
"grad_norm": 0.10482971216811227,
|
| 554 |
+
"learning_rate": 0.00010224737308919014,
|
| 555 |
+
"loss": 0.6509,
|
| 556 |
+
"step": 380
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.5507868383404864,
|
| 560 |
+
"grad_norm": 0.15040978772920802,
|
| 561 |
+
"learning_rate": 9.975027111381675e-05,
|
| 562 |
+
"loss": 0.7435,
|
| 563 |
+
"step": 385
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.5579399141630901,
|
| 567 |
+
"grad_norm": 0.09272976728170695,
|
| 568 |
+
"learning_rate": 9.72533248728859e-05,
|
| 569 |
+
"loss": 0.6922,
|
| 570 |
+
"step": 390
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.5650929899856938,
|
| 574 |
+
"grad_norm": 0.1221214527065867,
|
| 575 |
+
"learning_rate": 9.475809149716011e-05,
|
| 576 |
+
"loss": 0.6814,
|
| 577 |
+
"step": 395
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.5722460658082976,
|
| 581 |
+
"grad_norm": 0.5036832457140492,
|
| 582 |
+
"learning_rate": 9.226612704923507e-05,
|
| 583 |
+
"loss": 0.7478,
|
| 584 |
+
"step": 400
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.5722460658082976,
|
| 588 |
+
"eval_loss": 0.6692562103271484,
|
| 589 |
+
"eval_runtime": 972.3875,
|
| 590 |
+
"eval_samples_per_second": 2.057,
|
| 591 |
+
"eval_steps_per_second": 0.129,
|
| 592 |
+
"step": 400
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.5793991416309013,
|
| 596 |
+
"grad_norm": 0.09390195648925902,
|
| 597 |
+
"learning_rate": 8.977898555315713e-05,
|
| 598 |
+
"loss": 0.6167,
|
| 599 |
+
"step": 405
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.586552217453505,
|
| 603 |
+
"grad_norm": 0.14219781785034696,
|
| 604 |
+
"learning_rate": 8.729821802531212e-05,
|
| 605 |
+
"loss": 0.73,
|
| 606 |
+
"step": 410
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.5937052932761088,
|
| 610 |
+
"grad_norm": 0.09671061747598036,
|
| 611 |
+
"learning_rate": 8.482537150718975e-05,
|
| 612 |
+
"loss": 0.7244,
|
| 613 |
+
"step": 415
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.6008583690987125,
|
| 617 |
+
"grad_norm": 0.11955392967058884,
|
| 618 |
+
"learning_rate": 8.23619881006267e-05,
|
| 619 |
+
"loss": 0.6769,
|
| 620 |
+
"step": 420
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.6080114449213162,
|
| 624 |
+
"grad_norm": 0.4189202491522242,
|
| 625 |
+
"learning_rate": 7.99096040061303e-05,
|
| 626 |
+
"loss": 0.7751,
|
| 627 |
+
"step": 425
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.6151645207439199,
|
| 631 |
+
"grad_norm": 0.09721911498914373,
|
| 632 |
+
"learning_rate": 7.746974856488238e-05,
|
| 633 |
+
"loss": 0.6233,
|
| 634 |
+
"step": 430
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.6223175965665236,
|
| 638 |
+
"grad_norm": 0.13846978267168025,
|
| 639 |
+
"learning_rate": 7.50439433050205e-05,
|
| 640 |
+
"loss": 0.7407,
|
| 641 |
+
"step": 435
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.6294706723891274,
|
| 645 |
+
"grad_norm": 0.08838254367219467,
|
| 646 |
+
"learning_rate": 7.263370099279172e-05,
|
| 647 |
+
"loss": 0.7088,
|
| 648 |
+
"step": 440
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.6366237482117311,
|
| 652 |
+
"grad_norm": 0.11873577831994696,
|
| 653 |
+
"learning_rate": 7.024052468917022e-05,
|
| 654 |
+
"loss": 0.6736,
|
| 655 |
+
"step": 445
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.6437768240343348,
|
| 659 |
+
"grad_norm": 0.33813588083054347,
|
| 660 |
+
"learning_rate": 6.786590681252744e-05,
|
| 661 |
+
"loss": 0.7469,
|
| 662 |
+
"step": 450
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.6509298998569385,
|
| 666 |
+
"grad_norm": 0.1035926098875485,
|
| 667 |
+
"learning_rate": 6.551132820793902e-05,
|
| 668 |
+
"loss": 0.6177,
|
| 669 |
+
"step": 455
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.6580829756795422,
|
| 673 |
+
"grad_norm": 0.13996128874715752,
|
| 674 |
+
"learning_rate": 6.31782572237088e-05,
|
| 675 |
+
"loss": 0.7217,
|
| 676 |
+
"step": 460
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.6652360515021459,
|
| 680 |
+
"grad_norm": 0.09586075004988552,
|
| 681 |
+
"learning_rate": 6.08681487956865e-05,
|
| 682 |
+
"loss": 0.6931,
|
| 683 |
+
"step": 465
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.6723891273247496,
|
| 687 |
+
"grad_norm": 0.11431458069436656,
|
| 688 |
+
"learning_rate": 5.858244353994906e-05,
|
| 689 |
+
"loss": 0.6904,
|
| 690 |
+
"step": 470
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.6795422031473534,
|
| 694 |
+
"grad_norm": 0.36826661059200655,
|
| 695 |
+
"learning_rate": 5.632256685441229e-05,
|
| 696 |
+
"loss": 0.7614,
|
| 697 |
+
"step": 475
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.6866952789699571,
|
| 701 |
+
"grad_norm": 0.09520510613886908,
|
| 702 |
+
"learning_rate": 5.408992802993269e-05,
|
| 703 |
+
"loss": 0.6571,
|
| 704 |
+
"step": 480
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.6938483547925608,
|
| 708 |
+
"grad_norm": 0.15384325014915562,
|
| 709 |
+
"learning_rate": 5.188591937145386e-05,
|
| 710 |
+
"loss": 0.7585,
|
| 711 |
+
"step": 485
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.7010014306151645,
|
| 715 |
+
"grad_norm": 0.0899989739652617,
|
| 716 |
+
"learning_rate": 4.971191532974552e-05,
|
| 717 |
+
"loss": 0.7155,
|
| 718 |
+
"step": 490
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.7081545064377682,
|
| 722 |
+
"grad_norm": 0.10977217448571064,
|
| 723 |
+
"learning_rate": 4.756927164427685e-05,
|
| 724 |
+
"loss": 0.6359,
|
| 725 |
+
"step": 495
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.7153075822603719,
|
| 729 |
+
"grad_norm": 0.4092589446417867,
|
| 730 |
+
"learning_rate": 4.5459324497758104e-05,
|
| 731 |
+
"loss": 0.7788,
|
| 732 |
+
"step": 500
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.7224606580829757,
|
| 736 |
+
"grad_norm": 0.09127215016969027,
|
| 737 |
+
"learning_rate": 4.338338968287853e-05,
|
| 738 |
+
"loss": 0.6295,
|
| 739 |
+
"step": 505
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 0.7296137339055794,
|
| 743 |
+
"grad_norm": 0.15013590282846936,
|
| 744 |
+
"learning_rate": 4.134276178175927e-05,
|
| 745 |
+
"loss": 0.7025,
|
| 746 |
+
"step": 510
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.7367668097281831,
|
| 750 |
+
"grad_norm": 0.0899908161380569,
|
| 751 |
+
"learning_rate": 3.933871335863408e-05,
|
| 752 |
+
"loss": 0.67,
|
| 753 |
+
"step": 515
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.7439198855507868,
|
| 757 |
+
"grad_norm": 0.11465342107800292,
|
| 758 |
+
"learning_rate": 3.737249416626014e-05,
|
| 759 |
+
"loss": 0.6392,
|
| 760 |
+
"step": 520
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.7510729613733905,
|
| 764 |
+
"grad_norm": 0.4280343702289959,
|
| 765 |
+
"learning_rate": 3.544533036655476e-05,
|
| 766 |
+
"loss": 0.786,
|
| 767 |
+
"step": 525
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.7582260371959942,
|
| 771 |
+
"grad_norm": 0.10266949219770882,
|
| 772 |
+
"learning_rate": 3.355842376594357e-05,
|
| 773 |
+
"loss": 0.6068,
|
| 774 |
+
"step": 530
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.765379113018598,
|
| 778 |
+
"grad_norm": 0.14253463950155285,
|
| 779 |
+
"learning_rate": 3.171295106589726e-05,
|
| 780 |
+
"loss": 0.7457,
|
| 781 |
+
"step": 535
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 0.7725321888412017,
|
| 785 |
+
"grad_norm": 0.09202889667099431,
|
| 786 |
+
"learning_rate": 2.9910063129123755e-05,
|
| 787 |
+
"loss": 0.682,
|
| 788 |
+
"step": 540
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.7796852646638054,
|
| 792 |
+
"grad_norm": 0.11296926525170213,
|
| 793 |
+
"learning_rate": 2.8150884261874366e-05,
|
| 794 |
+
"loss": 0.6397,
|
| 795 |
+
"step": 545
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.7868383404864091,
|
| 799 |
+
"grad_norm": 0.509027438656149,
|
| 800 |
+
"learning_rate": 2.6436511512810325e-05,
|
| 801 |
+
"loss": 0.7777,
|
| 802 |
+
"step": 550
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.7939914163090128,
|
| 806 |
+
"grad_norm": 0.09297223864460286,
|
| 807 |
+
"learning_rate": 2.4768013988868065e-05,
|
| 808 |
+
"loss": 0.6147,
|
| 809 |
+
"step": 555
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.8011444921316166,
|
| 813 |
+
"grad_norm": 0.1399057626649613,
|
| 814 |
+
"learning_rate": 2.3146432188548917e-05,
|
| 815 |
+
"loss": 0.7012,
|
| 816 |
+
"step": 560
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 0.8082975679542204,
|
| 820 |
+
"grad_norm": 0.09185298523651206,
|
| 821 |
+
"learning_rate": 2.157277735304971e-05,
|
| 822 |
+
"loss": 0.7267,
|
| 823 |
+
"step": 565
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 0.8154506437768241,
|
| 827 |
+
"grad_norm": 0.1123786553918693,
|
| 828 |
+
"learning_rate": 2.0048030835638644e-05,
|
| 829 |
+
"loss": 0.6257,
|
| 830 |
+
"step": 570
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.8226037195994278,
|
| 834 |
+
"grad_norm": 0.37210838744162594,
|
| 835 |
+
"learning_rate": 1.8573143489669385e-05,
|
| 836 |
+
"loss": 0.7216,
|
| 837 |
+
"step": 575
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.8297567954220315,
|
| 841 |
+
"grad_norm": 0.10101729128186683,
|
| 842 |
+
"learning_rate": 1.7149035075615794e-05,
|
| 843 |
+
"loss": 0.6183,
|
| 844 |
+
"step": 580
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 0.8369098712446352,
|
| 848 |
+
"grad_norm": 0.15231579242566323,
|
| 849 |
+
"learning_rate": 1.5776593687496167e-05,
|
| 850 |
+
"loss": 0.7182,
|
| 851 |
+
"step": 585
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 0.844062947067239,
|
| 855 |
+
"grad_norm": 0.08888363881120907,
|
| 856 |
+
"learning_rate": 1.44566751990454e-05,
|
| 857 |
+
"loss": 0.6994,
|
| 858 |
+
"step": 590
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.8512160228898427,
|
| 862 |
+
"grad_norm": 0.11401883397158272,
|
| 863 |
+
"learning_rate": 1.3190102729980226e-05,
|
| 864 |
+
"loss": 0.6824,
|
| 865 |
+
"step": 595
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.8583690987124464,
|
| 869 |
+
"grad_norm": 0.4299251120038569,
|
| 870 |
+
"learning_rate": 1.1977666132689947e-05,
|
| 871 |
+
"loss": 0.7963,
|
| 872 |
+
"step": 600
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 0.8583690987124464,
|
| 876 |
+
"eval_loss": 0.660947322845459,
|
| 877 |
+
"eval_runtime": 974.2409,
|
| 878 |
+
"eval_samples_per_second": 2.053,
|
| 879 |
+
"eval_steps_per_second": 0.128,
|
| 880 |
+
"step": 600
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.8655221745350501,
|
| 884 |
+
"grad_norm": 0.09507686854622492,
|
| 885 |
+
"learning_rate": 1.0820121499673618e-05,
|
| 886 |
+
"loss": 0.6198,
|
| 887 |
+
"step": 605
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.8726752503576538,
|
| 891 |
+
"grad_norm": 0.1446777341342134,
|
| 892 |
+
"learning_rate": 9.71819069202996e-06,
|
| 893 |
+
"loss": 0.6841,
|
| 894 |
+
"step": 610
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.8798283261802575,
|
| 898 |
+
"grad_norm": 0.09274602760519131,
|
| 899 |
+
"learning_rate": 8.672560889294812e-06,
|
| 900 |
+
"loss": 0.6759,
|
| 901 |
+
"step": 615
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.8869814020028612,
|
| 905 |
+
"grad_norm": 0.13384317589987976,
|
| 906 |
+
"learning_rate": 7.683884160906118e-06,
|
| 907 |
+
"loss": 0.6853,
|
| 908 |
+
"step": 620
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.894134477825465,
|
| 912 |
+
"grad_norm": 0.5618493715100463,
|
| 913 |
+
"learning_rate": 6.75277705956443e-06,
|
| 914 |
+
"loss": 0.76,
|
| 915 |
+
"step": 625
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.9012875536480687,
|
| 919 |
+
"grad_norm": 0.08834479759548475,
|
| 920 |
+
"learning_rate": 5.879820236741884e-06,
|
| 921 |
+
"loss": 0.6058,
|
| 922 |
+
"step": 630
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.9084406294706724,
|
| 926 |
+
"grad_norm": 0.13992620759849517,
|
| 927 |
+
"learning_rate": 5.065558080579835e-06,
|
| 928 |
+
"loss": 0.7586,
|
| 929 |
+
"step": 635
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.9155937052932761,
|
| 933 |
+
"grad_norm": 0.09567272654127822,
|
| 934 |
+
"learning_rate": 4.310498376400751e-06,
|
| 935 |
+
"loss": 0.7173,
|
| 936 |
+
"step": 640
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.9227467811158798,
|
| 940 |
+
"grad_norm": 0.112867269041588,
|
| 941 |
+
"learning_rate": 3.615111990046094e-06,
|
| 942 |
+
"loss": 0.6469,
|
| 943 |
+
"step": 645
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.9298998569384835,
|
| 947 |
+
"grad_norm": 0.4489160430511751,
|
| 948 |
+
"learning_rate": 2.979832574237884e-06,
|
| 949 |
+
"loss": 0.7839,
|
| 950 |
+
"step": 650
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.9370529327610873,
|
| 954 |
+
"grad_norm": 0.09860092960999309,
|
| 955 |
+
"learning_rate": 2.4050562981465906e-06,
|
| 956 |
+
"loss": 0.6202,
|
| 957 |
+
"step": 655
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.944206008583691,
|
| 961 |
+
"grad_norm": 0.14952199122077578,
|
| 962 |
+
"learning_rate": 1.8911416003346893e-06,
|
| 963 |
+
"loss": 0.7517,
|
| 964 |
+
"step": 660
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.9513590844062947,
|
| 968 |
+
"grad_norm": 0.09034770607257726,
|
| 969 |
+
"learning_rate": 1.4384089652291543e-06,
|
| 970 |
+
"loss": 0.722,
|
| 971 |
+
"step": 665
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.9585121602288984,
|
| 975 |
+
"grad_norm": 0.12043580567803806,
|
| 976 |
+
"learning_rate": 1.0471407232629626e-06,
|
| 977 |
+
"loss": 0.6474,
|
| 978 |
+
"step": 670
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.9656652360515021,
|
| 982 |
+
"grad_norm": 0.3910952273479509,
|
| 983 |
+
"learning_rate": 7.175808748098311e-07,
|
| 984 |
+
"loss": 0.7645,
|
| 985 |
+
"step": 675
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.9728183118741058,
|
| 989 |
+
"grad_norm": 0.09625514486008946,
|
| 990 |
+
"learning_rate": 4.4993493802217847e-07,
|
| 991 |
+
"loss": 0.6296,
|
| 992 |
+
"step": 680
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.9799713876967096,
|
| 996 |
+
"grad_norm": 0.14269654608023083,
|
| 997 |
+
"learning_rate": 2.443698206670897e-07,
|
| 998 |
+
"loss": 0.7063,
|
| 999 |
+
"step": 685
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.9871244635193133,
|
| 1003 |
+
"grad_norm": 0.09242040569454475,
|
| 1004 |
+
"learning_rate": 1.0101371604032128e-07,
|
| 1005 |
+
"loss": 0.7074,
|
| 1006 |
+
"step": 690
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.994277539341917,
|
| 1010 |
+
"grad_norm": 0.12417081551389351,
|
| 1011 |
+
"learning_rate": 1.99560230231266e-08,
|
| 1012 |
+
"loss": 0.6753,
|
| 1013 |
+
"step": 695
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 1.0,
|
| 1017 |
+
"step": 699,
|
| 1018 |
+
"total_flos": 1.493876632190976e+16,
|
| 1019 |
+
"train_loss": 0.7242236417932743,
|
| 1020 |
+
"train_runtime": 29465.3177,
|
| 1021 |
+
"train_samples_per_second": 0.759,
|
| 1022 |
+
"train_steps_per_second": 0.024
|
| 1023 |
+
}
|
| 1024 |
+
],
|
| 1025 |
+
"logging_steps": 5,
|
| 1026 |
+
"max_steps": 699,
|
| 1027 |
+
"num_input_tokens_seen": 0,
|
| 1028 |
+
"num_train_epochs": 1,
|
| 1029 |
+
"save_steps": 200,
|
| 1030 |
+
"stateful_callbacks": {
|
| 1031 |
+
"TrainerControl": {
|
| 1032 |
+
"args": {
|
| 1033 |
+
"should_epoch_stop": false,
|
| 1034 |
+
"should_evaluate": false,
|
| 1035 |
+
"should_log": false,
|
| 1036 |
+
"should_save": true,
|
| 1037 |
+
"should_training_stop": false
|
| 1038 |
+
},
|
| 1039 |
+
"attributes": {}
|
| 1040 |
+
}
|
| 1041 |
+
},
|
| 1042 |
+
"total_flos": 1.493876632190976e+16,
|
| 1043 |
+
"train_batch_size": 4,
|
| 1044 |
+
"trial_name": null,
|
| 1045 |
+
"trial_params": null
|
| 1046 |
+
}
|