Model save
Browse files- README.md +69 -0
- adapter_model.safetensors +1 -1
- all_results.json +9 -0
- runs/May24_21-35-04_5c31577a2818/events.out.tfevents.1716586512.5c31577a2818.5087.0 +2 -2
- train_results.json +9 -0
- trainer_state.json +1151 -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 |
+
datasets:
|
| 10 |
+
- generator
|
| 11 |
+
model-index:
|
| 12 |
+
- name: zilo-instruct-v2-sft-qlora
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# zilo-instruct-v2-sft-qlora
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.3868
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 0.0002
|
| 43 |
+
- train_batch_size: 4
|
| 44 |
+
- eval_batch_size: 8
|
| 45 |
+
- seed: 42
|
| 46 |
+
- distributed_type: multi-GPU
|
| 47 |
+
- gradient_accumulation_steps: 2
|
| 48 |
+
- total_train_batch_size: 8
|
| 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: 3
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 57 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 58 |
+
| 0.4177 | 0.9981 | 257 | 0.4282 |
|
| 59 |
+
| 0.361 | 2.0 | 515 | 0.3842 |
|
| 60 |
+
| 0.3036 | 2.9942 | 771 | 0.3868 |
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
### Framework versions
|
| 64 |
+
|
| 65 |
+
- PEFT 0.11.1
|
| 66 |
+
- Transformers 4.41.1
|
| 67 |
+
- Pytorch 2.3.0+cu121
|
| 68 |
+
- Datasets 2.19.1
|
| 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 sha256:48e515a18fbb96311c5276c4c0ff67a67f5c27ea691bcc1d42227e9512ed81c2
|
| 3 |
size 83946192
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.994174757281553,
|
| 3 |
+
"total_flos": 5.421128640186286e+17,
|
| 4 |
+
"train_loss": 0.2601610358741651,
|
| 5 |
+
"train_runtime": 3322.581,
|
| 6 |
+
"train_samples": 29084,
|
| 7 |
+
"train_samples_per_second": 1.86,
|
| 8 |
+
"train_steps_per_second": 0.232
|
| 9 |
+
}
|
runs/May24_21-35-04_5c31577a2818/events.out.tfevents.1716586512.5c31577a2818.5087.0
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 sha256:60b6a6e3d891315421f8e3c0d8e0af039adb6c7b2a52bc3c6f31c0990ebf1467
|
| 3 |
+
size 30637
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.994174757281553,
|
| 3 |
+
"total_flos": 5.421128640186286e+17,
|
| 4 |
+
"train_loss": 0.2601610358741651,
|
| 5 |
+
"train_runtime": 3322.581,
|
| 6 |
+
"train_samples": 29084,
|
| 7 |
+
"train_samples_per_second": 1.86,
|
| 8 |
+
"train_steps_per_second": 0.232
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1151 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.994174757281553,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 771,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.003883495145631068,
|
| 13 |
+
"grad_norm": 2.65625,
|
| 14 |
+
"learning_rate": 2.564102564102564e-06,
|
| 15 |
+
"loss": 1.8569,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.019417475728155338,
|
| 20 |
+
"grad_norm": 2.609375,
|
| 21 |
+
"learning_rate": 1.282051282051282e-05,
|
| 22 |
+
"loss": 1.8227,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.038834951456310676,
|
| 27 |
+
"grad_norm": 2.09375,
|
| 28 |
+
"learning_rate": 2.564102564102564e-05,
|
| 29 |
+
"loss": 1.6509,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.05825242718446602,
|
| 34 |
+
"grad_norm": 1.21875,
|
| 35 |
+
"learning_rate": 3.846153846153846e-05,
|
| 36 |
+
"loss": 1.3453,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.07766990291262135,
|
| 41 |
+
"grad_norm": 0.94921875,
|
| 42 |
+
"learning_rate": 5.128205128205128e-05,
|
| 43 |
+
"loss": 1.1542,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0970873786407767,
|
| 48 |
+
"grad_norm": 0.5546875,
|
| 49 |
+
"learning_rate": 6.410256410256412e-05,
|
| 50 |
+
"loss": 1.0378,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.11650485436893204,
|
| 55 |
+
"grad_norm": 0.51171875,
|
| 56 |
+
"learning_rate": 7.692307692307693e-05,
|
| 57 |
+
"loss": 0.9156,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.13592233009708737,
|
| 62 |
+
"grad_norm": 0.423828125,
|
| 63 |
+
"learning_rate": 8.974358974358975e-05,
|
| 64 |
+
"loss": 0.7894,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.1553398058252427,
|
| 69 |
+
"grad_norm": 0.333984375,
|
| 70 |
+
"learning_rate": 0.00010256410256410256,
|
| 71 |
+
"loss": 0.7181,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.17475728155339806,
|
| 76 |
+
"grad_norm": 0.353515625,
|
| 77 |
+
"learning_rate": 0.00011538461538461538,
|
| 78 |
+
"loss": 0.6847,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.1941747572815534,
|
| 83 |
+
"grad_norm": 0.392578125,
|
| 84 |
+
"learning_rate": 0.00012820512820512823,
|
| 85 |
+
"loss": 0.6471,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.21359223300970873,
|
| 90 |
+
"grad_norm": 0.345703125,
|
| 91 |
+
"learning_rate": 0.00014102564102564104,
|
| 92 |
+
"loss": 0.6139,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.23300970873786409,
|
| 97 |
+
"grad_norm": 0.3671875,
|
| 98 |
+
"learning_rate": 0.00015384615384615385,
|
| 99 |
+
"loss": 0.6034,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.2524271844660194,
|
| 104 |
+
"grad_norm": 0.376953125,
|
| 105 |
+
"learning_rate": 0.0001666666666666667,
|
| 106 |
+
"loss": 0.563,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.27184466019417475,
|
| 111 |
+
"grad_norm": 0.396484375,
|
| 112 |
+
"learning_rate": 0.0001794871794871795,
|
| 113 |
+
"loss": 0.5629,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.2912621359223301,
|
| 118 |
+
"grad_norm": 0.365234375,
|
| 119 |
+
"learning_rate": 0.00019230769230769233,
|
| 120 |
+
"loss": 0.5443,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.3106796116504854,
|
| 125 |
+
"grad_norm": 0.34375,
|
| 126 |
+
"learning_rate": 0.0001999958898251569,
|
| 127 |
+
"loss": 0.5345,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.3300970873786408,
|
| 132 |
+
"grad_norm": 0.33203125,
|
| 133 |
+
"learning_rate": 0.00019994965423831854,
|
| 134 |
+
"loss": 0.5196,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.34951456310679613,
|
| 139 |
+
"grad_norm": 0.330078125,
|
| 140 |
+
"learning_rate": 0.00019985206917896563,
|
| 141 |
+
"loss": 0.5243,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.36893203883495146,
|
| 146 |
+
"grad_norm": 0.3203125,
|
| 147 |
+
"learning_rate": 0.00019970318478175218,
|
| 148 |
+
"loss": 0.5218,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.3883495145631068,
|
| 153 |
+
"grad_norm": 0.28515625,
|
| 154 |
+
"learning_rate": 0.00019950307753654017,
|
| 155 |
+
"loss": 0.5253,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.4077669902912621,
|
| 160 |
+
"grad_norm": 0.326171875,
|
| 161 |
+
"learning_rate": 0.00019925185024910277,
|
| 162 |
+
"loss": 0.5084,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.42718446601941745,
|
| 167 |
+
"grad_norm": 0.376953125,
|
| 168 |
+
"learning_rate": 0.00019894963198830768,
|
| 169 |
+
"loss": 0.48,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.44660194174757284,
|
| 174 |
+
"grad_norm": 0.287109375,
|
| 175 |
+
"learning_rate": 0.00019859657801980733,
|
| 176 |
+
"loss": 0.4837,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.46601941747572817,
|
| 181 |
+
"grad_norm": 0.29296875,
|
| 182 |
+
"learning_rate": 0.00019819286972627066,
|
| 183 |
+
"loss": 0.4751,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.4854368932038835,
|
| 188 |
+
"grad_norm": 0.28125,
|
| 189 |
+
"learning_rate": 0.00019773871451419736,
|
| 190 |
+
"loss": 0.4962,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.5048543689320388,
|
| 195 |
+
"grad_norm": 0.30859375,
|
| 196 |
+
"learning_rate": 0.00019723434570736181,
|
| 197 |
+
"loss": 0.5064,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.5242718446601942,
|
| 202 |
+
"grad_norm": 0.283203125,
|
| 203 |
+
"learning_rate": 0.00019668002242694238,
|
| 204 |
+
"loss": 0.4812,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.5436893203883495,
|
| 209 |
+
"grad_norm": 0.3671875,
|
| 210 |
+
"learning_rate": 0.00019607602945839698,
|
| 211 |
+
"loss": 0.4815,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.5631067961165048,
|
| 216 |
+
"grad_norm": 0.267578125,
|
| 217 |
+
"learning_rate": 0.00019542267710515368,
|
| 218 |
+
"loss": 0.4763,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.5825242718446602,
|
| 223 |
+
"grad_norm": 0.287109375,
|
| 224 |
+
"learning_rate": 0.000194720301029191,
|
| 225 |
+
"loss": 0.4682,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.6019417475728155,
|
| 230 |
+
"grad_norm": 0.298828125,
|
| 231 |
+
"learning_rate": 0.00019396926207859084,
|
| 232 |
+
"loss": 0.4604,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.6213592233009708,
|
| 237 |
+
"grad_norm": 0.26953125,
|
| 238 |
+
"learning_rate": 0.00019316994610215116,
|
| 239 |
+
"loss": 0.4866,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.6407766990291263,
|
| 244 |
+
"grad_norm": 0.271484375,
|
| 245 |
+
"learning_rate": 0.00019232276375115515,
|
| 246 |
+
"loss": 0.4898,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.6601941747572816,
|
| 251 |
+
"grad_norm": 0.2578125,
|
| 252 |
+
"learning_rate": 0.00019142815026839755,
|
| 253 |
+
"loss": 0.4908,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.6796116504854369,
|
| 258 |
+
"grad_norm": 0.28515625,
|
| 259 |
+
"learning_rate": 0.0001904865652645773,
|
| 260 |
+
"loss": 0.4566,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.6990291262135923,
|
| 265 |
+
"grad_norm": 0.27734375,
|
| 266 |
+
"learning_rate": 0.000189498492482171,
|
| 267 |
+
"loss": 0.45,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.7184466019417476,
|
| 272 |
+
"grad_norm": 0.259765625,
|
| 273 |
+
"learning_rate": 0.00018846443954690848,
|
| 274 |
+
"loss": 0.4646,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.7378640776699029,
|
| 279 |
+
"grad_norm": 0.275390625,
|
| 280 |
+
"learning_rate": 0.00018738493770697852,
|
| 281 |
+
"loss": 0.4625,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.7572815533980582,
|
| 286 |
+
"grad_norm": 0.26171875,
|
| 287 |
+
"learning_rate": 0.00018626054156009806,
|
| 288 |
+
"loss": 0.4452,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.7766990291262136,
|
| 293 |
+
"grad_norm": 0.29296875,
|
| 294 |
+
"learning_rate": 0.00018509182876858611,
|
| 295 |
+
"loss": 0.4535,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.7961165048543689,
|
| 300 |
+
"grad_norm": 0.25390625,
|
| 301 |
+
"learning_rate": 0.00018387939976258734,
|
| 302 |
+
"loss": 0.4393,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.8155339805825242,
|
| 307 |
+
"grad_norm": 0.263671875,
|
| 308 |
+
"learning_rate": 0.0001826238774315995,
|
| 309 |
+
"loss": 0.4391,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.8349514563106796,
|
| 314 |
+
"grad_norm": 0.271484375,
|
| 315 |
+
"learning_rate": 0.00018132590680446147,
|
| 316 |
+
"loss": 0.443,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.8543689320388349,
|
| 321 |
+
"grad_norm": 0.279296875,
|
| 322 |
+
"learning_rate": 0.00017998615471796775,
|
| 323 |
+
"loss": 0.4527,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.8737864077669902,
|
| 328 |
+
"grad_norm": 0.265625,
|
| 329 |
+
"learning_rate": 0.00017860530947427875,
|
| 330 |
+
"loss": 0.4416,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.8932038834951457,
|
| 335 |
+
"grad_norm": 0.2890625,
|
| 336 |
+
"learning_rate": 0.00017718408048730317,
|
| 337 |
+
"loss": 0.4506,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.912621359223301,
|
| 342 |
+
"grad_norm": 0.298828125,
|
| 343 |
+
"learning_rate": 0.00017572319791823424,
|
| 344 |
+
"loss": 0.4538,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.9320388349514563,
|
| 349 |
+
"grad_norm": 0.263671875,
|
| 350 |
+
"learning_rate": 0.000174223412300427,
|
| 351 |
+
"loss": 0.4467,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.9514563106796117,
|
| 356 |
+
"grad_norm": 0.26953125,
|
| 357 |
+
"learning_rate": 0.00017268549415380916,
|
| 358 |
+
"loss": 0.4425,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.970873786407767,
|
| 363 |
+
"grad_norm": 0.267578125,
|
| 364 |
+
"learning_rate": 0.00017111023358902392,
|
| 365 |
+
"loss": 0.4389,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.9902912621359223,
|
| 370 |
+
"grad_norm": 0.251953125,
|
| 371 |
+
"learning_rate": 0.00016949843990150796,
|
| 372 |
+
"loss": 0.4177,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.9980582524271845,
|
| 377 |
+
"eval_loss": 0.4281997084617615,
|
| 378 |
+
"eval_runtime": 22.0587,
|
| 379 |
+
"eval_samples_per_second": 4.987,
|
| 380 |
+
"eval_steps_per_second": 0.635,
|
| 381 |
+
"step": 257
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.0097087378640777,
|
| 385 |
+
"grad_norm": 0.236328125,
|
| 386 |
+
"learning_rate": 0.00016785094115571322,
|
| 387 |
+
"loss": 0.4083,
|
| 388 |
+
"step": 260
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.029126213592233,
|
| 392 |
+
"grad_norm": 0.275390625,
|
| 393 |
+
"learning_rate": 0.00016616858375968595,
|
| 394 |
+
"loss": 0.4012,
|
| 395 |
+
"step": 265
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.0485436893203883,
|
| 399 |
+
"grad_norm": 0.28515625,
|
| 400 |
+
"learning_rate": 0.00016445223203022166,
|
| 401 |
+
"loss": 0.3935,
|
| 402 |
+
"step": 270
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.0679611650485437,
|
| 406 |
+
"grad_norm": 0.279296875,
|
| 407 |
+
"learning_rate": 0.00016270276774881954,
|
| 408 |
+
"loss": 0.3972,
|
| 409 |
+
"step": 275
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.087378640776699,
|
| 413 |
+
"grad_norm": 0.267578125,
|
| 414 |
+
"learning_rate": 0.00016092108970866423,
|
| 415 |
+
"loss": 0.4004,
|
| 416 |
+
"step": 280
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.1067961165048543,
|
| 420 |
+
"grad_norm": 0.279296875,
|
| 421 |
+
"learning_rate": 0.00015910811325286768,
|
| 422 |
+
"loss": 0.3941,
|
| 423 |
+
"step": 285
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.1262135922330097,
|
| 427 |
+
"grad_norm": 0.271484375,
|
| 428 |
+
"learning_rate": 0.00015726476980420864,
|
| 429 |
+
"loss": 0.3877,
|
| 430 |
+
"step": 290
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.145631067961165,
|
| 434 |
+
"grad_norm": 0.287109375,
|
| 435 |
+
"learning_rate": 0.00015539200638661104,
|
| 436 |
+
"loss": 0.3819,
|
| 437 |
+
"step": 295
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.1650485436893203,
|
| 441 |
+
"grad_norm": 0.291015625,
|
| 442 |
+
"learning_rate": 0.00015349078513860726,
|
| 443 |
+
"loss": 0.3816,
|
| 444 |
+
"step": 300
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.1844660194174756,
|
| 448 |
+
"grad_norm": 0.318359375,
|
| 449 |
+
"learning_rate": 0.00015156208281903613,
|
| 450 |
+
"loss": 0.3953,
|
| 451 |
+
"step": 305
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.203883495145631,
|
| 455 |
+
"grad_norm": 0.296875,
|
| 456 |
+
"learning_rate": 0.0001496068903052299,
|
| 457 |
+
"loss": 0.3905,
|
| 458 |
+
"step": 310
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.2233009708737863,
|
| 462 |
+
"grad_norm": 0.2734375,
|
| 463 |
+
"learning_rate": 0.0001476262120839475,
|
| 464 |
+
"loss": 0.3763,
|
| 465 |
+
"step": 315
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.2427184466019416,
|
| 469 |
+
"grad_norm": 0.3125,
|
| 470 |
+
"learning_rate": 0.0001456210657353163,
|
| 471 |
+
"loss": 0.3792,
|
| 472 |
+
"step": 320
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.262135922330097,
|
| 476 |
+
"grad_norm": 0.29296875,
|
| 477 |
+
"learning_rate": 0.00014359248141004668,
|
| 478 |
+
"loss": 0.3794,
|
| 479 |
+
"step": 325
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.2815533980582523,
|
| 483 |
+
"grad_norm": 0.294921875,
|
| 484 |
+
"learning_rate": 0.00014154150130018866,
|
| 485 |
+
"loss": 0.3756,
|
| 486 |
+
"step": 330
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.3009708737864076,
|
| 490 |
+
"grad_norm": 0.287109375,
|
| 491 |
+
"learning_rate": 0.00013946917910370233,
|
| 492 |
+
"loss": 0.3876,
|
| 493 |
+
"step": 335
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.3203883495145632,
|
| 497 |
+
"grad_norm": 0.306640625,
|
| 498 |
+
"learning_rate": 0.00013737657948311683,
|
| 499 |
+
"loss": 0.3819,
|
| 500 |
+
"step": 340
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.3398058252427185,
|
| 504 |
+
"grad_norm": 0.26171875,
|
| 505 |
+
"learning_rate": 0.00013526477751855644,
|
| 506 |
+
"loss": 0.3925,
|
| 507 |
+
"step": 345
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.3592233009708738,
|
| 511 |
+
"grad_norm": 0.287109375,
|
| 512 |
+
"learning_rate": 0.00013313485815541454,
|
| 513 |
+
"loss": 0.3915,
|
| 514 |
+
"step": 350
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.3786407766990292,
|
| 518 |
+
"grad_norm": 0.28515625,
|
| 519 |
+
"learning_rate": 0.00013098791564695927,
|
| 520 |
+
"loss": 0.3902,
|
| 521 |
+
"step": 355
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.3980582524271845,
|
| 525 |
+
"grad_norm": 0.2890625,
|
| 526 |
+
"learning_rate": 0.0001288250529921571,
|
| 527 |
+
"loss": 0.3864,
|
| 528 |
+
"step": 360
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.4174757281553398,
|
| 532 |
+
"grad_norm": 0.27734375,
|
| 533 |
+
"learning_rate": 0.00012664738136900348,
|
| 534 |
+
"loss": 0.3778,
|
| 535 |
+
"step": 365
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.4368932038834952,
|
| 539 |
+
"grad_norm": 0.2890625,
|
| 540 |
+
"learning_rate": 0.0001244560195636515,
|
| 541 |
+
"loss": 0.3732,
|
| 542 |
+
"step": 370
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.4563106796116505,
|
| 546 |
+
"grad_norm": 0.318359375,
|
| 547 |
+
"learning_rate": 0.00012225209339563145,
|
| 548 |
+
"loss": 0.3856,
|
| 549 |
+
"step": 375
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.4757281553398058,
|
| 553 |
+
"grad_norm": 0.265625,
|
| 554 |
+
"learning_rate": 0.00012003673513945746,
|
| 555 |
+
"loss": 0.3745,
|
| 556 |
+
"step": 380
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.4951456310679612,
|
| 560 |
+
"grad_norm": 0.306640625,
|
| 561 |
+
"learning_rate": 0.0001178110829429175,
|
| 562 |
+
"loss": 0.3657,
|
| 563 |
+
"step": 385
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.5145631067961165,
|
| 567 |
+
"grad_norm": 0.25390625,
|
| 568 |
+
"learning_rate": 0.0001155762802423463,
|
| 569 |
+
"loss": 0.3728,
|
| 570 |
+
"step": 390
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.5339805825242718,
|
| 574 |
+
"grad_norm": 0.265625,
|
| 575 |
+
"learning_rate": 0.0001133334751751809,
|
| 576 |
+
"loss": 0.3849,
|
| 577 |
+
"step": 395
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.5533980582524272,
|
| 581 |
+
"grad_norm": 0.291015625,
|
| 582 |
+
"learning_rate": 0.00011108381999010111,
|
| 583 |
+
"loss": 0.3979,
|
| 584 |
+
"step": 400
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.5728155339805825,
|
| 588 |
+
"grad_norm": 0.26171875,
|
| 589 |
+
"learning_rate": 0.00010882847045505808,
|
| 590 |
+
"loss": 0.3819,
|
| 591 |
+
"step": 405
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.5922330097087378,
|
| 595 |
+
"grad_norm": 0.2578125,
|
| 596 |
+
"learning_rate": 0.00010656858526349449,
|
| 597 |
+
"loss": 0.3704,
|
| 598 |
+
"step": 410
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.6116504854368932,
|
| 602 |
+
"grad_norm": 0.26171875,
|
| 603 |
+
"learning_rate": 0.00010430532543906179,
|
| 604 |
+
"loss": 0.3702,
|
| 605 |
+
"step": 415
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.6310679611650487,
|
| 609 |
+
"grad_norm": 0.283203125,
|
| 610 |
+
"learning_rate": 0.00010203985373914056,
|
| 611 |
+
"loss": 0.373,
|
| 612 |
+
"step": 420
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.650485436893204,
|
| 616 |
+
"grad_norm": 0.279296875,
|
| 617 |
+
"learning_rate": 9.977333405746979e-05,
|
| 618 |
+
"loss": 0.366,
|
| 619 |
+
"step": 425
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.6699029126213594,
|
| 623 |
+
"grad_norm": 0.30859375,
|
| 624 |
+
"learning_rate": 9.750693082619273e-05,
|
| 625 |
+
"loss": 0.3555,
|
| 626 |
+
"step": 430
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.6893203883495147,
|
| 630 |
+
"grad_norm": 0.279296875,
|
| 631 |
+
"learning_rate": 9.524180841762577e-05,
|
| 632 |
+
"loss": 0.3793,
|
| 633 |
+
"step": 435
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.70873786407767,
|
| 637 |
+
"grad_norm": 0.25390625,
|
| 638 |
+
"learning_rate": 9.297913054605838e-05,
|
| 639 |
+
"loss": 0.3692,
|
| 640 |
+
"step": 440
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.7281553398058254,
|
| 644 |
+
"grad_norm": 0.27734375,
|
| 645 |
+
"learning_rate": 9.072005966989084e-05,
|
| 646 |
+
"loss": 0.3655,
|
| 647 |
+
"step": 445
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.7475728155339807,
|
| 651 |
+
"grad_norm": 0.265625,
|
| 652 |
+
"learning_rate": 8.846575639441732e-05,
|
| 653 |
+
"loss": 0.3791,
|
| 654 |
+
"step": 450
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.766990291262136,
|
| 658 |
+
"grad_norm": 0.29296875,
|
| 659 |
+
"learning_rate": 8.621737887556114e-05,
|
| 660 |
+
"loss": 0.3661,
|
| 661 |
+
"step": 455
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.7864077669902914,
|
| 665 |
+
"grad_norm": 0.2890625,
|
| 666 |
+
"learning_rate": 8.397608222486805e-05,
|
| 667 |
+
"loss": 0.3611,
|
| 668 |
+
"step": 460
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.8058252427184467,
|
| 672 |
+
"grad_norm": 0.291015625,
|
| 673 |
+
"learning_rate": 8.174301791606385e-05,
|
| 674 |
+
"loss": 0.3611,
|
| 675 |
+
"step": 465
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.825242718446602,
|
| 679 |
+
"grad_norm": 0.279296875,
|
| 680 |
+
"learning_rate": 7.951933319348095e-05,
|
| 681 |
+
"loss": 0.3493,
|
| 682 |
+
"step": 470
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.8446601941747574,
|
| 686 |
+
"grad_norm": 0.2578125,
|
| 687 |
+
"learning_rate": 7.730617048265761e-05,
|
| 688 |
+
"loss": 0.3655,
|
| 689 |
+
"step": 475
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.8640776699029127,
|
| 693 |
+
"grad_norm": 0.318359375,
|
| 694 |
+
"learning_rate": 7.510466680341301e-05,
|
| 695 |
+
"loss": 0.3527,
|
| 696 |
+
"step": 480
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.883495145631068,
|
| 700 |
+
"grad_norm": 0.298828125,
|
| 701 |
+
"learning_rate": 7.291595318569951e-05,
|
| 702 |
+
"loss": 0.3528,
|
| 703 |
+
"step": 485
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.9029126213592233,
|
| 707 |
+
"grad_norm": 0.30078125,
|
| 708 |
+
"learning_rate": 7.074115408853203e-05,
|
| 709 |
+
"loss": 0.3784,
|
| 710 |
+
"step": 490
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.9223300970873787,
|
| 714 |
+
"grad_norm": 0.27734375,
|
| 715 |
+
"learning_rate": 6.858138682229376e-05,
|
| 716 |
+
"loss": 0.3571,
|
| 717 |
+
"step": 495
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.941747572815534,
|
| 721 |
+
"grad_norm": 0.265625,
|
| 722 |
+
"learning_rate": 6.643776097471377e-05,
|
| 723 |
+
"loss": 0.3658,
|
| 724 |
+
"step": 500
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.9611650485436893,
|
| 728 |
+
"grad_norm": 0.275390625,
|
| 729 |
+
"learning_rate": 6.431137784081282e-05,
|
| 730 |
+
"loss": 0.3567,
|
| 731 |
+
"step": 505
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.9805825242718447,
|
| 735 |
+
"grad_norm": 0.29296875,
|
| 736 |
+
"learning_rate": 6.220332985710936e-05,
|
| 737 |
+
"loss": 0.3526,
|
| 738 |
+
"step": 510
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 2.0,
|
| 742 |
+
"grad_norm": 0.30078125,
|
| 743 |
+
"learning_rate": 6.011470004037636e-05,
|
| 744 |
+
"loss": 0.361,
|
| 745 |
+
"step": 515
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 2.0,
|
| 749 |
+
"eval_loss": 0.38420218229293823,
|
| 750 |
+
"eval_runtime": 22.0532,
|
| 751 |
+
"eval_samples_per_second": 4.988,
|
| 752 |
+
"eval_steps_per_second": 0.635,
|
| 753 |
+
"step": 515
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 2.0194174757281553,
|
| 757 |
+
"grad_norm": 0.2421875,
|
| 758 |
+
"learning_rate": 5.804656143123801e-05,
|
| 759 |
+
"loss": 0.308,
|
| 760 |
+
"step": 520
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 2.0388349514563107,
|
| 764 |
+
"grad_norm": 0.283203125,
|
| 765 |
+
"learning_rate": 5.599997654289129e-05,
|
| 766 |
+
"loss": 0.3136,
|
| 767 |
+
"step": 525
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 2.058252427184466,
|
| 771 |
+
"grad_norm": 0.3046875,
|
| 772 |
+
"learning_rate": 5.397599681523643e-05,
|
| 773 |
+
"loss": 0.3037,
|
| 774 |
+
"step": 530
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 2.0776699029126213,
|
| 778 |
+
"grad_norm": 0.298828125,
|
| 779 |
+
"learning_rate": 5.1975662074695865e-05,
|
| 780 |
+
"loss": 0.3098,
|
| 781 |
+
"step": 535
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 2.0970873786407767,
|
| 785 |
+
"grad_norm": 0.28125,
|
| 786 |
+
"learning_rate": 5.000000000000002e-05,
|
| 787 |
+
"loss": 0.3111,
|
| 788 |
+
"step": 540
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 2.116504854368932,
|
| 792 |
+
"grad_norm": 0.294921875,
|
| 793 |
+
"learning_rate": 4.8050025594214e-05,
|
| 794 |
+
"loss": 0.3083,
|
| 795 |
+
"step": 545
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 2.1359223300970873,
|
| 799 |
+
"grad_norm": 0.29296875,
|
| 800 |
+
"learning_rate": 4.6126740663276166e-05,
|
| 801 |
+
"loss": 0.3133,
|
| 802 |
+
"step": 550
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 2.1553398058252426,
|
| 806 |
+
"grad_norm": 0.29296875,
|
| 807 |
+
"learning_rate": 4.423113330131707e-05,
|
| 808 |
+
"loss": 0.3076,
|
| 809 |
+
"step": 555
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 2.174757281553398,
|
| 813 |
+
"grad_norm": 0.29296875,
|
| 814 |
+
"learning_rate": 4.236417738302257e-05,
|
| 815 |
+
"loss": 0.2981,
|
| 816 |
+
"step": 560
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 2.1941747572815533,
|
| 820 |
+
"grad_norm": 0.314453125,
|
| 821 |
+
"learning_rate": 4.052683206330267e-05,
|
| 822 |
+
"loss": 0.312,
|
| 823 |
+
"step": 565
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 2.2135922330097086,
|
| 827 |
+
"grad_norm": 0.298828125,
|
| 828 |
+
"learning_rate": 3.872004128452231e-05,
|
| 829 |
+
"loss": 0.2942,
|
| 830 |
+
"step": 570
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 2.233009708737864,
|
| 834 |
+
"grad_norm": 0.314453125,
|
| 835 |
+
"learning_rate": 3.694473329154778e-05,
|
| 836 |
+
"loss": 0.3205,
|
| 837 |
+
"step": 575
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 2.2524271844660193,
|
| 841 |
+
"grad_norm": 0.3359375,
|
| 842 |
+
"learning_rate": 3.5201820154857755e-05,
|
| 843 |
+
"loss": 0.322,
|
| 844 |
+
"step": 580
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 2.2718446601941746,
|
| 848 |
+
"grad_norm": 0.296875,
|
| 849 |
+
"learning_rate": 3.3492197301964145e-05,
|
| 850 |
+
"loss": 0.2931,
|
| 851 |
+
"step": 585
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 2.29126213592233,
|
| 855 |
+
"grad_norm": 0.33203125,
|
| 856 |
+
"learning_rate": 3.18167430573831e-05,
|
| 857 |
+
"loss": 0.3107,
|
| 858 |
+
"step": 590
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 2.3106796116504853,
|
| 862 |
+
"grad_norm": 0.302734375,
|
| 863 |
+
"learning_rate": 3.0176318191392726e-05,
|
| 864 |
+
"loss": 0.3065,
|
| 865 |
+
"step": 595
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 2.3300970873786406,
|
| 869 |
+
"grad_norm": 0.3203125,
|
| 870 |
+
"learning_rate": 2.8571765477809643e-05,
|
| 871 |
+
"loss": 0.3031,
|
| 872 |
+
"step": 600
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 2.349514563106796,
|
| 876 |
+
"grad_norm": 0.3125,
|
| 877 |
+
"learning_rate": 2.7003909261010928e-05,
|
| 878 |
+
"loss": 0.2894,
|
| 879 |
+
"step": 605
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 2.3689320388349513,
|
| 883 |
+
"grad_norm": 0.314453125,
|
| 884 |
+
"learning_rate": 2.5473555032424533e-05,
|
| 885 |
+
"loss": 0.3136,
|
| 886 |
+
"step": 610
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 2.3883495145631066,
|
| 890 |
+
"grad_norm": 0.33984375,
|
| 891 |
+
"learning_rate": 2.3981489016705205e-05,
|
| 892 |
+
"loss": 0.3078,
|
| 893 |
+
"step": 615
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 2.407766990291262,
|
| 897 |
+
"grad_norm": 0.322265625,
|
| 898 |
+
"learning_rate": 2.2528477767808963e-05,
|
| 899 |
+
"loss": 0.3094,
|
| 900 |
+
"step": 620
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 2.4271844660194173,
|
| 904 |
+
"grad_norm": 0.31640625,
|
| 905 |
+
"learning_rate": 2.1115267775173532e-05,
|
| 906 |
+
"loss": 0.2985,
|
| 907 |
+
"step": 625
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 2.4466019417475726,
|
| 911 |
+
"grad_norm": 0.322265625,
|
| 912 |
+
"learning_rate": 1.9742585080206755e-05,
|
| 913 |
+
"loss": 0.3191,
|
| 914 |
+
"step": 630
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 2.466019417475728,
|
| 918 |
+
"grad_norm": 0.3203125,
|
| 919 |
+
"learning_rate": 1.8411134903280303e-05,
|
| 920 |
+
"loss": 0.3117,
|
| 921 |
+
"step": 635
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 2.4854368932038833,
|
| 925 |
+
"grad_norm": 0.306640625,
|
| 926 |
+
"learning_rate": 1.7121601281420495e-05,
|
| 927 |
+
"loss": 0.3086,
|
| 928 |
+
"step": 640
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 2.5048543689320386,
|
| 932 |
+
"grad_norm": 0.33203125,
|
| 933 |
+
"learning_rate": 1.587464671688187e-05,
|
| 934 |
+
"loss": 0.3072,
|
| 935 |
+
"step": 645
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 2.524271844660194,
|
| 939 |
+
"grad_norm": 0.306640625,
|
| 940 |
+
"learning_rate": 1.467091183678444e-05,
|
| 941 |
+
"loss": 0.3044,
|
| 942 |
+
"step": 650
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 2.5436893203883493,
|
| 946 |
+
"grad_norm": 0.298828125,
|
| 947 |
+
"learning_rate": 1.3511015063989274e-05,
|
| 948 |
+
"loss": 0.3081,
|
| 949 |
+
"step": 655
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 2.5631067961165046,
|
| 953 |
+
"grad_norm": 0.275390625,
|
| 954 |
+
"learning_rate": 1.2395552299381741e-05,
|
| 955 |
+
"loss": 0.3005,
|
| 956 |
+
"step": 660
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 2.58252427184466,
|
| 960 |
+
"grad_norm": 0.3125,
|
| 961 |
+
"learning_rate": 1.1325096615725427e-05,
|
| 962 |
+
"loss": 0.3034,
|
| 963 |
+
"step": 665
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 2.6019417475728153,
|
| 967 |
+
"grad_norm": 0.3125,
|
| 968 |
+
"learning_rate": 1.030019796324404e-05,
|
| 969 |
+
"loss": 0.3075,
|
| 970 |
+
"step": 670
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 2.6213592233009706,
|
| 974 |
+
"grad_norm": 0.3125,
|
| 975 |
+
"learning_rate": 9.321382887082563e-06,
|
| 976 |
+
"loss": 0.3084,
|
| 977 |
+
"step": 675
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 2.6407766990291264,
|
| 981 |
+
"grad_norm": 0.3203125,
|
| 982 |
+
"learning_rate": 8.38915425679304e-06,
|
| 983 |
+
"loss": 0.3064,
|
| 984 |
+
"step": 680
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 2.6601941747572817,
|
| 988 |
+
"grad_norm": 0.310546875,
|
| 989 |
+
"learning_rate": 7.503991007983524e-06,
|
| 990 |
+
"loss": 0.3087,
|
| 991 |
+
"step": 685
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 2.679611650485437,
|
| 995 |
+
"grad_norm": 0.3359375,
|
| 996 |
+
"learning_rate": 6.666347896263325e-06,
|
| 997 |
+
"loss": 0.3129,
|
| 998 |
+
"step": 690
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 2.6990291262135924,
|
| 1002 |
+
"grad_norm": 0.291015625,
|
| 1003 |
+
"learning_rate": 5.876655263610842e-06,
|
| 1004 |
+
"loss": 0.2897,
|
| 1005 |
+
"step": 695
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 2.7184466019417477,
|
| 1009 |
+
"grad_norm": 0.31640625,
|
| 1010 |
+
"learning_rate": 5.1353188172838074e-06,
|
| 1011 |
+
"loss": 0.3033,
|
| 1012 |
+
"step": 700
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 2.737864077669903,
|
| 1016 |
+
"grad_norm": 0.30859375,
|
| 1017 |
+
"learning_rate": 4.442719421385922e-06,
|
| 1018 |
+
"loss": 0.2994,
|
| 1019 |
+
"step": 705
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 2.7572815533980584,
|
| 1023 |
+
"grad_norm": 0.330078125,
|
| 1024 |
+
"learning_rate": 3.7992129011965803e-06,
|
| 1025 |
+
"loss": 0.3152,
|
| 1026 |
+
"step": 710
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 2.7766990291262137,
|
| 1030 |
+
"grad_norm": 0.314453125,
|
| 1031 |
+
"learning_rate": 3.2051298603643753e-06,
|
| 1032 |
+
"loss": 0.3101,
|
| 1033 |
+
"step": 715
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 2.796116504854369,
|
| 1037 |
+
"grad_norm": 0.30859375,
|
| 1038 |
+
"learning_rate": 2.6607755110584887e-06,
|
| 1039 |
+
"loss": 0.3125,
|
| 1040 |
+
"step": 720
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 2.8155339805825244,
|
| 1044 |
+
"grad_norm": 0.291015625,
|
| 1045 |
+
"learning_rate": 2.1664295171648364e-06,
|
| 1046 |
+
"loss": 0.3024,
|
| 1047 |
+
"step": 725
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 2.8349514563106797,
|
| 1051 |
+
"grad_norm": 0.31640625,
|
| 1052 |
+
"learning_rate": 1.7223458506077316e-06,
|
| 1053 |
+
"loss": 0.2913,
|
| 1054 |
+
"step": 730
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 2.854368932038835,
|
| 1058 |
+
"grad_norm": 0.3046875,
|
| 1059 |
+
"learning_rate": 1.3287526608711131e-06,
|
| 1060 |
+
"loss": 0.2968,
|
| 1061 |
+
"step": 735
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 2.8737864077669903,
|
| 1065 |
+
"grad_norm": 0.3203125,
|
| 1066 |
+
"learning_rate": 9.85852157785816e-07,
|
| 1067 |
+
"loss": 0.3033,
|
| 1068 |
+
"step": 740
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 2.8932038834951457,
|
| 1072 |
+
"grad_norm": 0.310546875,
|
| 1073 |
+
"learning_rate": 6.938205076436832e-07,
|
| 1074 |
+
"loss": 0.2991,
|
| 1075 |
+
"step": 745
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 2.912621359223301,
|
| 1079 |
+
"grad_norm": 0.328125,
|
| 1080 |
+
"learning_rate": 4.5280774269154115e-07,
|
| 1081 |
+
"loss": 0.3003,
|
| 1082 |
+
"step": 750
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 2.9320388349514563,
|
| 1086 |
+
"grad_norm": 0.2890625,
|
| 1087 |
+
"learning_rate": 2.629376840515452e-07,
|
| 1088 |
+
"loss": 0.2999,
|
| 1089 |
+
"step": 755
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 2.9514563106796117,
|
| 1093 |
+
"grad_norm": 0.32421875,
|
| 1094 |
+
"learning_rate": 1.2430787810776555e-07,
|
| 1095 |
+
"loss": 0.3023,
|
| 1096 |
+
"step": 760
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 2.970873786407767,
|
| 1100 |
+
"grad_norm": 0.326171875,
|
| 1101 |
+
"learning_rate": 3.6989546391297256e-08,
|
| 1102 |
+
"loss": 0.3106,
|
| 1103 |
+
"step": 765
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 2.9902912621359223,
|
| 1107 |
+
"grad_norm": 0.318359375,
|
| 1108 |
+
"learning_rate": 1.0275489900624102e-09,
|
| 1109 |
+
"loss": 0.3036,
|
| 1110 |
+
"step": 770
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 2.994174757281553,
|
| 1114 |
+
"eval_loss": 0.38681623339653015,
|
| 1115 |
+
"eval_runtime": 22.0402,
|
| 1116 |
+
"eval_samples_per_second": 4.991,
|
| 1117 |
+
"eval_steps_per_second": 0.635,
|
| 1118 |
+
"step": 771
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 2.994174757281553,
|
| 1122 |
+
"step": 771,
|
| 1123 |
+
"total_flos": 5.421128640186286e+17,
|
| 1124 |
+
"train_loss": 0.2601610358741651,
|
| 1125 |
+
"train_runtime": 3322.581,
|
| 1126 |
+
"train_samples_per_second": 1.86,
|
| 1127 |
+
"train_steps_per_second": 0.232
|
| 1128 |
+
}
|
| 1129 |
+
],
|
| 1130 |
+
"logging_steps": 5,
|
| 1131 |
+
"max_steps": 771,
|
| 1132 |
+
"num_input_tokens_seen": 0,
|
| 1133 |
+
"num_train_epochs": 3,
|
| 1134 |
+
"save_steps": 100,
|
| 1135 |
+
"stateful_callbacks": {
|
| 1136 |
+
"TrainerControl": {
|
| 1137 |
+
"args": {
|
| 1138 |
+
"should_epoch_stop": false,
|
| 1139 |
+
"should_evaluate": false,
|
| 1140 |
+
"should_log": false,
|
| 1141 |
+
"should_save": true,
|
| 1142 |
+
"should_training_stop": false
|
| 1143 |
+
},
|
| 1144 |
+
"attributes": {}
|
| 1145 |
+
}
|
| 1146 |
+
},
|
| 1147 |
+
"total_flos": 5.421128640186286e+17,
|
| 1148 |
+
"train_batch_size": 4,
|
| 1149 |
+
"trial_name": null,
|
| 1150 |
+
"trial_params": null
|
| 1151 |
+
}
|