Model save
Browse files- README.md +78 -0
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +3182 -0
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: llama3.2
|
| 4 |
+
base_model: meta-llama/Llama-3.2-3B
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
datasets:
|
| 10 |
+
- generator
|
| 11 |
+
model-index:
|
| 12 |
+
- name: llama3-3b-summarize-gpt4o-128k
|
| 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 |
+
# llama3-3b-summarize-gpt4o-128k
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [meta-llama/Llama-3.2-3B](https://huggingface.co/meta-llama/Llama-3.2-3B) on the generator dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 2.5189
|
| 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: 2
|
| 45 |
+
- seed: 42
|
| 46 |
+
- distributed_type: multi-GPU
|
| 47 |
+
- num_devices: 8
|
| 48 |
+
- gradient_accumulation_steps: 2
|
| 49 |
+
- total_train_batch_size: 64
|
| 50 |
+
- total_eval_batch_size: 16
|
| 51 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 52 |
+
- lr_scheduler_type: cosine
|
| 53 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 54 |
+
- num_epochs: 10
|
| 55 |
+
|
| 56 |
+
### Training results
|
| 57 |
+
|
| 58 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 59 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 60 |
+
| 1.5142 | 1.0 | 219 | 2.4458 |
|
| 61 |
+
| 1.4574 | 2.0 | 438 | 2.4565 |
|
| 62 |
+
| 1.4298 | 3.0 | 657 | 2.4537 |
|
| 63 |
+
| 1.3972 | 4.0 | 876 | 2.4622 |
|
| 64 |
+
| 1.3868 | 5.0 | 1095 | 2.4810 |
|
| 65 |
+
| 1.3692 | 6.0 | 1314 | 2.5001 |
|
| 66 |
+
| 1.3509 | 7.0 | 1533 | 2.5038 |
|
| 67 |
+
| 1.3413 | 8.0 | 1752 | 2.5123 |
|
| 68 |
+
| 1.3562 | 9.0 | 1971 | 2.5176 |
|
| 69 |
+
| 1.3538 | 9.9565 | 2180 | 2.5189 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- PEFT 0.15.1
|
| 75 |
+
- Transformers 4.50.3
|
| 76 |
+
- Pytorch 2.6.0+cu124
|
| 77 |
+
- Datasets 3.5.0
|
| 78 |
+
- Tokenizers 0.21.1
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.956521739130435,
|
| 3 |
+
"total_flos": 2.4191218891641324e+18,
|
| 4 |
+
"train_loss": 1.418152675716155,
|
| 5 |
+
"train_runtime": 3547.1741,
|
| 6 |
+
"train_samples": 129221,
|
| 7 |
+
"train_samples_per_second": 39.395,
|
| 8 |
+
"train_steps_per_second": 0.615
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.956521739130435,
|
| 3 |
+
"total_flos": 2.4191218891641324e+18,
|
| 4 |
+
"train_loss": 1.418152675716155,
|
| 5 |
+
"train_runtime": 3547.1741,
|
| 6 |
+
"train_samples": 129221,
|
| 7 |
+
"train_samples_per_second": 39.395,
|
| 8 |
+
"train_steps_per_second": 0.615
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3182 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 9.956521739130435,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2180,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.004576659038901602,
|
| 14 |
+
"grad_norm": 0.795125424861908,
|
| 15 |
+
"learning_rate": 9.174311926605506e-07,
|
| 16 |
+
"loss": 2.0857,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.02288329519450801,
|
| 21 |
+
"grad_norm": 0.7591376900672913,
|
| 22 |
+
"learning_rate": 4.587155963302753e-06,
|
| 23 |
+
"loss": 2.0888,
|
| 24 |
+
"step": 5
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.04576659038901602,
|
| 28 |
+
"grad_norm": 0.7638061046600342,
|
| 29 |
+
"learning_rate": 9.174311926605506e-06,
|
| 30 |
+
"loss": 2.0744,
|
| 31 |
+
"step": 10
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.06864988558352403,
|
| 35 |
+
"grad_norm": 0.6205304265022278,
|
| 36 |
+
"learning_rate": 1.3761467889908258e-05,
|
| 37 |
+
"loss": 2.0578,
|
| 38 |
+
"step": 15
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.09153318077803203,
|
| 42 |
+
"grad_norm": 0.40848588943481445,
|
| 43 |
+
"learning_rate": 1.834862385321101e-05,
|
| 44 |
+
"loss": 2.0541,
|
| 45 |
+
"step": 20
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.11441647597254005,
|
| 49 |
+
"grad_norm": 0.35839515924453735,
|
| 50 |
+
"learning_rate": 2.2935779816513765e-05,
|
| 51 |
+
"loss": 2.0396,
|
| 52 |
+
"step": 25
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.13729977116704806,
|
| 56 |
+
"grad_norm": 0.3498051166534424,
|
| 57 |
+
"learning_rate": 2.7522935779816515e-05,
|
| 58 |
+
"loss": 2.0186,
|
| 59 |
+
"step": 30
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.16018306636155608,
|
| 63 |
+
"grad_norm": 0.34915778040885925,
|
| 64 |
+
"learning_rate": 3.211009174311927e-05,
|
| 65 |
+
"loss": 1.9692,
|
| 66 |
+
"step": 35
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.18306636155606407,
|
| 70 |
+
"grad_norm": 0.2829169034957886,
|
| 71 |
+
"learning_rate": 3.669724770642202e-05,
|
| 72 |
+
"loss": 1.9478,
|
| 73 |
+
"step": 40
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.20594965675057209,
|
| 77 |
+
"grad_norm": 0.29471325874328613,
|
| 78 |
+
"learning_rate": 4.1284403669724776e-05,
|
| 79 |
+
"loss": 1.9081,
|
| 80 |
+
"step": 45
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.2288329519450801,
|
| 84 |
+
"grad_norm": 0.26286041736602783,
|
| 85 |
+
"learning_rate": 4.587155963302753e-05,
|
| 86 |
+
"loss": 1.8852,
|
| 87 |
+
"step": 50
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.2517162471395881,
|
| 91 |
+
"grad_norm": 0.253055214881897,
|
| 92 |
+
"learning_rate": 5.0458715596330276e-05,
|
| 93 |
+
"loss": 1.8466,
|
| 94 |
+
"step": 55
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.2745995423340961,
|
| 98 |
+
"grad_norm": 0.25780022144317627,
|
| 99 |
+
"learning_rate": 5.504587155963303e-05,
|
| 100 |
+
"loss": 1.7978,
|
| 101 |
+
"step": 60
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.2974828375286041,
|
| 105 |
+
"grad_norm": 0.22376658022403717,
|
| 106 |
+
"learning_rate": 5.9633027522935784e-05,
|
| 107 |
+
"loss": 1.7513,
|
| 108 |
+
"step": 65
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.32036613272311215,
|
| 112 |
+
"grad_norm": 0.20868130028247833,
|
| 113 |
+
"learning_rate": 6.422018348623854e-05,
|
| 114 |
+
"loss": 1.7581,
|
| 115 |
+
"step": 70
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.34324942791762014,
|
| 119 |
+
"grad_norm": 0.20019210875034332,
|
| 120 |
+
"learning_rate": 6.880733944954129e-05,
|
| 121 |
+
"loss": 1.7225,
|
| 122 |
+
"step": 75
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.36613272311212813,
|
| 126 |
+
"grad_norm": 0.20799387991428375,
|
| 127 |
+
"learning_rate": 7.339449541284404e-05,
|
| 128 |
+
"loss": 1.7073,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.3890160183066362,
|
| 133 |
+
"grad_norm": 0.19921623170375824,
|
| 134 |
+
"learning_rate": 7.79816513761468e-05,
|
| 135 |
+
"loss": 1.698,
|
| 136 |
+
"step": 85
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.41189931350114417,
|
| 140 |
+
"grad_norm": 0.19697250425815582,
|
| 141 |
+
"learning_rate": 8.256880733944955e-05,
|
| 142 |
+
"loss": 1.6806,
|
| 143 |
+
"step": 90
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.43478260869565216,
|
| 147 |
+
"grad_norm": 0.21829445660114288,
|
| 148 |
+
"learning_rate": 8.715596330275229e-05,
|
| 149 |
+
"loss": 1.661,
|
| 150 |
+
"step": 95
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.4576659038901602,
|
| 154 |
+
"grad_norm": 0.20831452310085297,
|
| 155 |
+
"learning_rate": 9.174311926605506e-05,
|
| 156 |
+
"loss": 1.6499,
|
| 157 |
+
"step": 100
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.4805491990846682,
|
| 161 |
+
"grad_norm": 0.2224440723657608,
|
| 162 |
+
"learning_rate": 9.63302752293578e-05,
|
| 163 |
+
"loss": 1.6504,
|
| 164 |
+
"step": 105
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.5034324942791762,
|
| 168 |
+
"grad_norm": 0.22193986177444458,
|
| 169 |
+
"learning_rate": 0.00010091743119266055,
|
| 170 |
+
"loss": 1.6399,
|
| 171 |
+
"step": 110
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.5263157894736842,
|
| 175 |
+
"grad_norm": 0.2367602288722992,
|
| 176 |
+
"learning_rate": 0.00010550458715596329,
|
| 177 |
+
"loss": 1.6236,
|
| 178 |
+
"step": 115
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.5491990846681922,
|
| 182 |
+
"grad_norm": 0.2362162321805954,
|
| 183 |
+
"learning_rate": 0.00011009174311926606,
|
| 184 |
+
"loss": 1.6227,
|
| 185 |
+
"step": 120
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.5720823798627003,
|
| 189 |
+
"grad_norm": 0.24902412295341492,
|
| 190 |
+
"learning_rate": 0.00011467889908256881,
|
| 191 |
+
"loss": 1.5984,
|
| 192 |
+
"step": 125
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.5949656750572082,
|
| 196 |
+
"grad_norm": 0.2517242431640625,
|
| 197 |
+
"learning_rate": 0.00011926605504587157,
|
| 198 |
+
"loss": 1.6003,
|
| 199 |
+
"step": 130
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.6178489702517163,
|
| 203 |
+
"grad_norm": 0.2526886463165283,
|
| 204 |
+
"learning_rate": 0.00012385321100917432,
|
| 205 |
+
"loss": 1.5961,
|
| 206 |
+
"step": 135
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.6407322654462243,
|
| 210 |
+
"grad_norm": 0.2544921338558197,
|
| 211 |
+
"learning_rate": 0.00012844036697247707,
|
| 212 |
+
"loss": 1.5782,
|
| 213 |
+
"step": 140
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.6636155606407322,
|
| 217 |
+
"grad_norm": 0.2370745986700058,
|
| 218 |
+
"learning_rate": 0.00013302752293577983,
|
| 219 |
+
"loss": 1.5817,
|
| 220 |
+
"step": 145
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.6864988558352403,
|
| 224 |
+
"grad_norm": 0.2654547095298767,
|
| 225 |
+
"learning_rate": 0.00013761467889908258,
|
| 226 |
+
"loss": 1.5683,
|
| 227 |
+
"step": 150
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.7093821510297483,
|
| 231 |
+
"grad_norm": 0.251737505197525,
|
| 232 |
+
"learning_rate": 0.0001422018348623853,
|
| 233 |
+
"loss": 1.5683,
|
| 234 |
+
"step": 155
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.7322654462242563,
|
| 238 |
+
"grad_norm": 0.27123987674713135,
|
| 239 |
+
"learning_rate": 0.0001467889908256881,
|
| 240 |
+
"loss": 1.5492,
|
| 241 |
+
"step": 160
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.7551487414187643,
|
| 245 |
+
"grad_norm": 0.2787420451641083,
|
| 246 |
+
"learning_rate": 0.00015137614678899084,
|
| 247 |
+
"loss": 1.5573,
|
| 248 |
+
"step": 165
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.7780320366132724,
|
| 252 |
+
"grad_norm": 0.3056250810623169,
|
| 253 |
+
"learning_rate": 0.0001559633027522936,
|
| 254 |
+
"loss": 1.5535,
|
| 255 |
+
"step": 170
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.8009153318077803,
|
| 259 |
+
"grad_norm": 0.4223385751247406,
|
| 260 |
+
"learning_rate": 0.00016055045871559632,
|
| 261 |
+
"loss": 1.5624,
|
| 262 |
+
"step": 175
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.8237986270022883,
|
| 266 |
+
"grad_norm": 0.3226919174194336,
|
| 267 |
+
"learning_rate": 0.0001651376146788991,
|
| 268 |
+
"loss": 1.5548,
|
| 269 |
+
"step": 180
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.8466819221967964,
|
| 273 |
+
"grad_norm": 0.42250385880470276,
|
| 274 |
+
"learning_rate": 0.00016972477064220186,
|
| 275 |
+
"loss": 1.5403,
|
| 276 |
+
"step": 185
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.8695652173913043,
|
| 280 |
+
"grad_norm": 0.29832813143730164,
|
| 281 |
+
"learning_rate": 0.00017431192660550458,
|
| 282 |
+
"loss": 1.5406,
|
| 283 |
+
"step": 190
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.8924485125858124,
|
| 287 |
+
"grad_norm": 0.318697988986969,
|
| 288 |
+
"learning_rate": 0.00017889908256880734,
|
| 289 |
+
"loss": 1.5423,
|
| 290 |
+
"step": 195
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.9153318077803204,
|
| 294 |
+
"grad_norm": 0.30288153886795044,
|
| 295 |
+
"learning_rate": 0.00018348623853211012,
|
| 296 |
+
"loss": 1.5432,
|
| 297 |
+
"step": 200
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.9382151029748284,
|
| 301 |
+
"grad_norm": 0.26959261298179626,
|
| 302 |
+
"learning_rate": 0.00018807339449541284,
|
| 303 |
+
"loss": 1.5264,
|
| 304 |
+
"step": 205
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.9610983981693364,
|
| 308 |
+
"grad_norm": 0.27854207158088684,
|
| 309 |
+
"learning_rate": 0.0001926605504587156,
|
| 310 |
+
"loss": 1.5328,
|
| 311 |
+
"step": 210
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.9839816933638444,
|
| 315 |
+
"grad_norm": 0.26367124915122986,
|
| 316 |
+
"learning_rate": 0.00019724770642201835,
|
| 317 |
+
"loss": 1.5142,
|
| 318 |
+
"step": 215
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.0,
|
| 322 |
+
"eval_loss": 2.4457786083221436,
|
| 323 |
+
"eval_runtime": 0.158,
|
| 324 |
+
"eval_samples_per_second": 63.273,
|
| 325 |
+
"eval_steps_per_second": 6.327,
|
| 326 |
+
"step": 219
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.0045766590389016,
|
| 330 |
+
"grad_norm": 0.24696815013885498,
|
| 331 |
+
"learning_rate": 0.00019999948721966259,
|
| 332 |
+
"loss": 1.5267,
|
| 333 |
+
"step": 220
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.0274599542334095,
|
| 337 |
+
"grad_norm": 0.2515549063682556,
|
| 338 |
+
"learning_rate": 0.0001999937185012612,
|
| 339 |
+
"loss": 1.5197,
|
| 340 |
+
"step": 225
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 1.0503432494279177,
|
| 344 |
+
"grad_norm": 0.26250341534614563,
|
| 345 |
+
"learning_rate": 0.00019998154046002822,
|
| 346 |
+
"loss": 1.4932,
|
| 347 |
+
"step": 230
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 1.0732265446224256,
|
| 351 |
+
"grad_norm": 0.2599635422229767,
|
| 352 |
+
"learning_rate": 0.00019996295387654262,
|
| 353 |
+
"loss": 1.5057,
|
| 354 |
+
"step": 235
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.0961098398169336,
|
| 358 |
+
"grad_norm": 0.2875217795372009,
|
| 359 |
+
"learning_rate": 0.0001999379599421534,
|
| 360 |
+
"loss": 1.5123,
|
| 361 |
+
"step": 240
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.1189931350114417,
|
| 365 |
+
"grad_norm": 0.2571655511856079,
|
| 366 |
+
"learning_rate": 0.00019990656025890315,
|
| 367 |
+
"loss": 1.5125,
|
| 368 |
+
"step": 245
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 1.1418764302059496,
|
| 372 |
+
"grad_norm": 0.2501162588596344,
|
| 373 |
+
"learning_rate": 0.00019986875683942535,
|
| 374 |
+
"loss": 1.5125,
|
| 375 |
+
"step": 250
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.1647597254004576,
|
| 379 |
+
"grad_norm": 0.2591252028942108,
|
| 380 |
+
"learning_rate": 0.00019982455210681537,
|
| 381 |
+
"loss": 1.491,
|
| 382 |
+
"step": 255
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 1.1876430205949657,
|
| 386 |
+
"grad_norm": 0.2666991055011749,
|
| 387 |
+
"learning_rate": 0.00019977394889447524,
|
| 388 |
+
"loss": 1.4931,
|
| 389 |
+
"step": 260
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.2105263157894737,
|
| 393 |
+
"grad_norm": 0.3265208601951599,
|
| 394 |
+
"learning_rate": 0.00019971695044593196,
|
| 395 |
+
"loss": 1.5088,
|
| 396 |
+
"step": 265
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.2334096109839816,
|
| 400 |
+
"grad_norm": 0.3080615699291229,
|
| 401 |
+
"learning_rate": 0.00019965356041462955,
|
| 402 |
+
"loss": 1.4943,
|
| 403 |
+
"step": 270
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 1.2562929061784898,
|
| 407 |
+
"grad_norm": 0.2847588062286377,
|
| 408 |
+
"learning_rate": 0.00019958378286369502,
|
| 409 |
+
"loss": 1.4829,
|
| 410 |
+
"step": 275
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.2791762013729977,
|
| 414 |
+
"grad_norm": 0.2870901823043823,
|
| 415 |
+
"learning_rate": 0.00019950762226567781,
|
| 416 |
+
"loss": 1.4841,
|
| 417 |
+
"step": 280
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.3020594965675056,
|
| 421 |
+
"grad_norm": 0.27676528692245483,
|
| 422 |
+
"learning_rate": 0.00019942508350226314,
|
| 423 |
+
"loss": 1.4901,
|
| 424 |
+
"step": 285
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 1.3249427917620138,
|
| 428 |
+
"grad_norm": 0.26728203892707825,
|
| 429 |
+
"learning_rate": 0.00019933617186395917,
|
| 430 |
+
"loss": 1.4743,
|
| 431 |
+
"step": 290
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 1.3478260869565217,
|
| 435 |
+
"grad_norm": 0.2857504189014435,
|
| 436 |
+
"learning_rate": 0.0001992408930497578,
|
| 437 |
+
"loss": 1.4919,
|
| 438 |
+
"step": 295
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 1.3707093821510297,
|
| 442 |
+
"grad_norm": 0.36729517579078674,
|
| 443 |
+
"learning_rate": 0.00019913925316676945,
|
| 444 |
+
"loss": 1.4872,
|
| 445 |
+
"step": 300
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 1.3935926773455378,
|
| 449 |
+
"grad_norm": 0.2691424489021301,
|
| 450 |
+
"learning_rate": 0.0001990312587298316,
|
| 451 |
+
"loss": 1.4785,
|
| 452 |
+
"step": 305
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.4164759725400458,
|
| 456 |
+
"grad_norm": 0.3448796570301056,
|
| 457 |
+
"learning_rate": 0.00019891691666109113,
|
| 458 |
+
"loss": 1.4857,
|
| 459 |
+
"step": 310
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.4393592677345537,
|
| 463 |
+
"grad_norm": 0.29720258712768555,
|
| 464 |
+
"learning_rate": 0.0001987962342895607,
|
| 465 |
+
"loss": 1.4844,
|
| 466 |
+
"step": 315
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.4622425629290619,
|
| 470 |
+
"grad_norm": 0.25346481800079346,
|
| 471 |
+
"learning_rate": 0.00019866921935064906,
|
| 472 |
+
"loss": 1.4822,
|
| 473 |
+
"step": 320
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 1.4851258581235698,
|
| 477 |
+
"grad_norm": 0.2484666258096695,
|
| 478 |
+
"learning_rate": 0.0001985358799856651,
|
| 479 |
+
"loss": 1.4804,
|
| 480 |
+
"step": 325
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 1.5080091533180777,
|
| 484 |
+
"grad_norm": 0.2337537705898285,
|
| 485 |
+
"learning_rate": 0.00019839622474129596,
|
| 486 |
+
"loss": 1.4762,
|
| 487 |
+
"step": 330
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 1.5308924485125859,
|
| 491 |
+
"grad_norm": 0.26846134662628174,
|
| 492 |
+
"learning_rate": 0.00019825026256905948,
|
| 493 |
+
"loss": 1.4656,
|
| 494 |
+
"step": 335
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.5537757437070938,
|
| 498 |
+
"grad_norm": 0.239125594496727,
|
| 499 |
+
"learning_rate": 0.00019809800282473013,
|
| 500 |
+
"loss": 1.4802,
|
| 501 |
+
"step": 340
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.5766590389016018,
|
| 505 |
+
"grad_norm": 0.2293742597103119,
|
| 506 |
+
"learning_rate": 0.00019793945526773947,
|
| 507 |
+
"loss": 1.4603,
|
| 508 |
+
"step": 345
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 1.59954233409611,
|
| 512 |
+
"grad_norm": 0.2655136287212372,
|
| 513 |
+
"learning_rate": 0.0001977746300605507,
|
| 514 |
+
"loss": 1.4783,
|
| 515 |
+
"step": 350
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.6224256292906178,
|
| 519 |
+
"grad_norm": 0.25485122203826904,
|
| 520 |
+
"learning_rate": 0.00019760353776800704,
|
| 521 |
+
"loss": 1.4755,
|
| 522 |
+
"step": 355
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 1.6453089244851258,
|
| 526 |
+
"grad_norm": 0.2485138326883316,
|
| 527 |
+
"learning_rate": 0.00019742618935665476,
|
| 528 |
+
"loss": 1.464,
|
| 529 |
+
"step": 360
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 1.668192219679634,
|
| 533 |
+
"grad_norm": 0.23952895402908325,
|
| 534 |
+
"learning_rate": 0.0001972425961940401,
|
| 535 |
+
"loss": 1.4652,
|
| 536 |
+
"step": 365
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 1.6910755148741419,
|
| 540 |
+
"grad_norm": 0.22710928320884705,
|
| 541 |
+
"learning_rate": 0.00019705277004798073,
|
| 542 |
+
"loss": 1.4585,
|
| 543 |
+
"step": 370
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 1.7139588100686498,
|
| 547 |
+
"grad_norm": 0.2363155037164688,
|
| 548 |
+
"learning_rate": 0.00019685672308581152,
|
| 549 |
+
"loss": 1.4725,
|
| 550 |
+
"step": 375
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 1.736842105263158,
|
| 554 |
+
"grad_norm": 0.23678353428840637,
|
| 555 |
+
"learning_rate": 0.0001966544678736044,
|
| 556 |
+
"loss": 1.4654,
|
| 557 |
+
"step": 380
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 1.759725400457666,
|
| 561 |
+
"grad_norm": 0.24644772708415985,
|
| 562 |
+
"learning_rate": 0.00019644601737536338,
|
| 563 |
+
"loss": 1.4473,
|
| 564 |
+
"step": 385
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 1.7826086956521738,
|
| 568 |
+
"grad_norm": 0.24988573789596558,
|
| 569 |
+
"learning_rate": 0.00019623138495219292,
|
| 570 |
+
"loss": 1.4658,
|
| 571 |
+
"step": 390
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 1.805491990846682,
|
| 575 |
+
"grad_norm": 0.2501707971096039,
|
| 576 |
+
"learning_rate": 0.00019601058436144225,
|
| 577 |
+
"loss": 1.4631,
|
| 578 |
+
"step": 395
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 1.82837528604119,
|
| 582 |
+
"grad_norm": 0.22899797558784485,
|
| 583 |
+
"learning_rate": 0.00019578362975582292,
|
| 584 |
+
"loss": 1.4663,
|
| 585 |
+
"step": 400
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 1.8512585812356979,
|
| 589 |
+
"grad_norm": 0.2957789897918701,
|
| 590 |
+
"learning_rate": 0.0001955505356825021,
|
| 591 |
+
"loss": 1.4649,
|
| 592 |
+
"step": 405
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 1.874141876430206,
|
| 596 |
+
"grad_norm": 0.26199233531951904,
|
| 597 |
+
"learning_rate": 0.00019531131708217005,
|
| 598 |
+
"loss": 1.4568,
|
| 599 |
+
"step": 410
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 1.897025171624714,
|
| 603 |
+
"grad_norm": 0.2635655403137207,
|
| 604 |
+
"learning_rate": 0.00019506598928808216,
|
| 605 |
+
"loss": 1.4748,
|
| 606 |
+
"step": 415
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 1.919908466819222,
|
| 610 |
+
"grad_norm": 0.23314692080020905,
|
| 611 |
+
"learning_rate": 0.0001948145680250766,
|
| 612 |
+
"loss": 1.4615,
|
| 613 |
+
"step": 420
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 1.94279176201373,
|
| 617 |
+
"grad_norm": 0.24421729147434235,
|
| 618 |
+
"learning_rate": 0.000194557069408566,
|
| 619 |
+
"loss": 1.463,
|
| 620 |
+
"step": 425
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 1.965675057208238,
|
| 624 |
+
"grad_norm": 0.2970636188983917,
|
| 625 |
+
"learning_rate": 0.00019429350994350483,
|
| 626 |
+
"loss": 1.4702,
|
| 627 |
+
"step": 430
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 1.988558352402746,
|
| 631 |
+
"grad_norm": 0.2254825085401535,
|
| 632 |
+
"learning_rate": 0.0001940239065233311,
|
| 633 |
+
"loss": 1.4574,
|
| 634 |
+
"step": 435
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.0,
|
| 638 |
+
"eval_loss": 2.456493854522705,
|
| 639 |
+
"eval_runtime": 0.1591,
|
| 640 |
+
"eval_samples_per_second": 62.851,
|
| 641 |
+
"eval_steps_per_second": 6.285,
|
| 642 |
+
"step": 438
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 2.009153318077803,
|
| 646 |
+
"grad_norm": 0.2410830557346344,
|
| 647 |
+
"learning_rate": 0.00019374827642888398,
|
| 648 |
+
"loss": 1.4467,
|
| 649 |
+
"step": 440
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 2.0320366132723113,
|
| 653 |
+
"grad_norm": 0.3021443784236908,
|
| 654 |
+
"learning_rate": 0.00019346663732729572,
|
| 655 |
+
"loss": 1.4415,
|
| 656 |
+
"step": 445
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 2.054919908466819,
|
| 660 |
+
"grad_norm": 0.2840650975704193,
|
| 661 |
+
"learning_rate": 0.0001931790072708596,
|
| 662 |
+
"loss": 1.4438,
|
| 663 |
+
"step": 450
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 2.077803203661327,
|
| 667 |
+
"grad_norm": 0.25511375069618225,
|
| 668 |
+
"learning_rate": 0.0001928854046958725,
|
| 669 |
+
"loss": 1.4412,
|
| 670 |
+
"step": 455
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 2.1006864988558354,
|
| 674 |
+
"grad_norm": 0.25664883852005005,
|
| 675 |
+
"learning_rate": 0.00019258584842145343,
|
| 676 |
+
"loss": 1.4476,
|
| 677 |
+
"step": 460
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 2.123569794050343,
|
| 681 |
+
"grad_norm": 0.29023540019989014,
|
| 682 |
+
"learning_rate": 0.00019228035764833718,
|
| 683 |
+
"loss": 1.4393,
|
| 684 |
+
"step": 465
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 2.1464530892448512,
|
| 688 |
+
"grad_norm": 0.23540236055850983,
|
| 689 |
+
"learning_rate": 0.00019196895195764362,
|
| 690 |
+
"loss": 1.45,
|
| 691 |
+
"step": 470
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 2.1693363844393594,
|
| 695 |
+
"grad_norm": 0.23571573197841644,
|
| 696 |
+
"learning_rate": 0.0001916516513096226,
|
| 697 |
+
"loss": 1.4292,
|
| 698 |
+
"step": 475
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 2.192219679633867,
|
| 702 |
+
"grad_norm": 0.22221675515174866,
|
| 703 |
+
"learning_rate": 0.0001913284760423745,
|
| 704 |
+
"loss": 1.4385,
|
| 705 |
+
"step": 480
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 2.2151029748283753,
|
| 709 |
+
"grad_norm": 0.24515533447265625,
|
| 710 |
+
"learning_rate": 0.00019099944687054672,
|
| 711 |
+
"loss": 1.438,
|
| 712 |
+
"step": 485
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 2.2379862700228834,
|
| 716 |
+
"grad_norm": 0.22849489748477936,
|
| 717 |
+
"learning_rate": 0.00019066458488400584,
|
| 718 |
+
"loss": 1.4365,
|
| 719 |
+
"step": 490
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 2.260869565217391,
|
| 723 |
+
"grad_norm": 0.23650361597537994,
|
| 724 |
+
"learning_rate": 0.0001903239115464859,
|
| 725 |
+
"loss": 1.4421,
|
| 726 |
+
"step": 495
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 2.2837528604118993,
|
| 730 |
+
"grad_norm": 0.2418275624513626,
|
| 731 |
+
"learning_rate": 0.00018997744869421246,
|
| 732 |
+
"loss": 1.4275,
|
| 733 |
+
"step": 500
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 2.3066361556064074,
|
| 737 |
+
"grad_norm": 0.2576926350593567,
|
| 738 |
+
"learning_rate": 0.00018962521853450323,
|
| 739 |
+
"loss": 1.4315,
|
| 740 |
+
"step": 505
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 2.329519450800915,
|
| 744 |
+
"grad_norm": 0.26270532608032227,
|
| 745 |
+
"learning_rate": 0.00018926724364434446,
|
| 746 |
+
"loss": 1.4386,
|
| 747 |
+
"step": 510
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 2.3524027459954233,
|
| 751 |
+
"grad_norm": 0.2584366798400879,
|
| 752 |
+
"learning_rate": 0.00018890354696894375,
|
| 753 |
+
"loss": 1.4288,
|
| 754 |
+
"step": 515
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 2.3752860411899315,
|
| 758 |
+
"grad_norm": 0.2276887744665146,
|
| 759 |
+
"learning_rate": 0.0001885341518202595,
|
| 760 |
+
"loss": 1.4331,
|
| 761 |
+
"step": 520
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 2.398169336384439,
|
| 765 |
+
"grad_norm": 0.25574877858161926,
|
| 766 |
+
"learning_rate": 0.00018815908187550667,
|
| 767 |
+
"loss": 1.4343,
|
| 768 |
+
"step": 525
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 2.4210526315789473,
|
| 772 |
+
"grad_norm": 0.2539375424385071,
|
| 773 |
+
"learning_rate": 0.00018777836117563892,
|
| 774 |
+
"loss": 1.4283,
|
| 775 |
+
"step": 530
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 2.4439359267734555,
|
| 779 |
+
"grad_norm": 0.23258014023303986,
|
| 780 |
+
"learning_rate": 0.0001873920141238079,
|
| 781 |
+
"loss": 1.4333,
|
| 782 |
+
"step": 535
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 2.466819221967963,
|
| 786 |
+
"grad_norm": 0.24933487176895142,
|
| 787 |
+
"learning_rate": 0.00018700006548379898,
|
| 788 |
+
"loss": 1.4245,
|
| 789 |
+
"step": 540
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 2.4897025171624714,
|
| 793 |
+
"grad_norm": 0.2398696094751358,
|
| 794 |
+
"learning_rate": 0.00018660254037844388,
|
| 795 |
+
"loss": 1.4373,
|
| 796 |
+
"step": 545
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 2.5125858123569795,
|
| 800 |
+
"grad_norm": 0.2470606118440628,
|
| 801 |
+
"learning_rate": 0.0001861994642880105,
|
| 802 |
+
"loss": 1.4316,
|
| 803 |
+
"step": 550
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 2.5354691075514877,
|
| 807 |
+
"grad_norm": 0.2763492166996002,
|
| 808 |
+
"learning_rate": 0.0001857908630485696,
|
| 809 |
+
"loss": 1.4229,
|
| 810 |
+
"step": 555
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 2.5583524027459954,
|
| 814 |
+
"grad_norm": 0.25183382630348206,
|
| 815 |
+
"learning_rate": 0.00018537676285033887,
|
| 816 |
+
"loss": 1.4235,
|
| 817 |
+
"step": 560
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 2.5812356979405036,
|
| 821 |
+
"grad_norm": 0.25710180401802063,
|
| 822 |
+
"learning_rate": 0.00018495719023600414,
|
| 823 |
+
"loss": 1.4203,
|
| 824 |
+
"step": 565
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 2.6041189931350113,
|
| 828 |
+
"grad_norm": 0.22346384823322296,
|
| 829 |
+
"learning_rate": 0.0001845321720990181,
|
| 830 |
+
"loss": 1.4274,
|
| 831 |
+
"step": 570
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 2.6270022883295194,
|
| 835 |
+
"grad_norm": 0.2290782779455185,
|
| 836 |
+
"learning_rate": 0.00018410173568187647,
|
| 837 |
+
"loss": 1.4304,
|
| 838 |
+
"step": 575
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 2.6498855835240276,
|
| 842 |
+
"grad_norm": 0.25173699855804443,
|
| 843 |
+
"learning_rate": 0.00018366590857437184,
|
| 844 |
+
"loss": 1.4331,
|
| 845 |
+
"step": 580
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 2.6727688787185357,
|
| 849 |
+
"grad_norm": 0.2373346984386444,
|
| 850 |
+
"learning_rate": 0.00018322471871182528,
|
| 851 |
+
"loss": 1.4257,
|
| 852 |
+
"step": 585
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 2.6956521739130435,
|
| 856 |
+
"grad_norm": 0.2577199339866638,
|
| 857 |
+
"learning_rate": 0.00018277819437329576,
|
| 858 |
+
"loss": 1.4382,
|
| 859 |
+
"step": 590
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 2.7185354691075516,
|
| 863 |
+
"grad_norm": 0.23805540800094604,
|
| 864 |
+
"learning_rate": 0.00018232636417976744,
|
| 865 |
+
"loss": 1.4365,
|
| 866 |
+
"step": 595
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 2.7414187643020593,
|
| 870 |
+
"grad_norm": 0.25108346343040466,
|
| 871 |
+
"learning_rate": 0.00018186925709231532,
|
| 872 |
+
"loss": 1.424,
|
| 873 |
+
"step": 600
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 2.7643020594965675,
|
| 877 |
+
"grad_norm": 0.25178954005241394,
|
| 878 |
+
"learning_rate": 0.00018140690241024872,
|
| 879 |
+
"loss": 1.429,
|
| 880 |
+
"step": 605
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 2.7871853546910756,
|
| 884 |
+
"grad_norm": 0.2157055288553238,
|
| 885 |
+
"learning_rate": 0.0001809393297692334,
|
| 886 |
+
"loss": 1.4257,
|
| 887 |
+
"step": 610
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 2.8100686498855834,
|
| 891 |
+
"grad_norm": 0.22406814992427826,
|
| 892 |
+
"learning_rate": 0.00018046656913939195,
|
| 893 |
+
"loss": 1.4248,
|
| 894 |
+
"step": 615
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 2.8329519450800915,
|
| 898 |
+
"grad_norm": 0.22442927956581116,
|
| 899 |
+
"learning_rate": 0.0001799886508233829,
|
| 900 |
+
"loss": 1.4292,
|
| 901 |
+
"step": 620
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 2.8558352402745997,
|
| 905 |
+
"grad_norm": 0.22204960882663727,
|
| 906 |
+
"learning_rate": 0.00017950560545445813,
|
| 907 |
+
"loss": 1.4399,
|
| 908 |
+
"step": 625
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 2.8787185354691074,
|
| 912 |
+
"grad_norm": 0.2269710898399353,
|
| 913 |
+
"learning_rate": 0.0001790174639944997,
|
| 914 |
+
"loss": 1.4248,
|
| 915 |
+
"step": 630
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 2.9016018306636155,
|
| 919 |
+
"grad_norm": 0.23222693800926208,
|
| 920 |
+
"learning_rate": 0.000178524257732035,
|
| 921 |
+
"loss": 1.4261,
|
| 922 |
+
"step": 635
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 2.9244851258581237,
|
| 926 |
+
"grad_norm": 0.21854890882968903,
|
| 927 |
+
"learning_rate": 0.00017802601828023138,
|
| 928 |
+
"loss": 1.4172,
|
| 929 |
+
"step": 640
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 2.9473684210526314,
|
| 933 |
+
"grad_norm": 0.2316950112581253,
|
| 934 |
+
"learning_rate": 0.0001775227775748699,
|
| 935 |
+
"loss": 1.4156,
|
| 936 |
+
"step": 645
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 2.9702517162471396,
|
| 940 |
+
"grad_norm": 0.21298670768737793,
|
| 941 |
+
"learning_rate": 0.00017701456787229804,
|
| 942 |
+
"loss": 1.4288,
|
| 943 |
+
"step": 650
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 2.9931350114416477,
|
| 947 |
+
"grad_norm": 0.21937227249145508,
|
| 948 |
+
"learning_rate": 0.00017650142174736262,
|
| 949 |
+
"loss": 1.4298,
|
| 950 |
+
"step": 655
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 3.0,
|
| 954 |
+
"eval_loss": 2.4537367820739746,
|
| 955 |
+
"eval_runtime": 0.1693,
|
| 956 |
+
"eval_samples_per_second": 59.08,
|
| 957 |
+
"eval_steps_per_second": 5.908,
|
| 958 |
+
"step": 657
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 3.013729977116705,
|
| 962 |
+
"grad_norm": 0.22709442675113678,
|
| 963 |
+
"learning_rate": 0.0001759833720913214,
|
| 964 |
+
"loss": 1.4058,
|
| 965 |
+
"step": 660
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 3.0366132723112127,
|
| 969 |
+
"grad_norm": 0.21663448214530945,
|
| 970 |
+
"learning_rate": 0.00017546045210973507,
|
| 971 |
+
"loss": 1.4108,
|
| 972 |
+
"step": 665
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 3.059496567505721,
|
| 976 |
+
"grad_norm": 0.21900029480457306,
|
| 977 |
+
"learning_rate": 0.00017493269532033883,
|
| 978 |
+
"loss": 1.41,
|
| 979 |
+
"step": 670
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 3.082379862700229,
|
| 983 |
+
"grad_norm": 0.23556417226791382,
|
| 984 |
+
"learning_rate": 0.00017440013555089393,
|
| 985 |
+
"loss": 1.4084,
|
| 986 |
+
"step": 675
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 3.1052631578947367,
|
| 990 |
+
"grad_norm": 0.26198992133140564,
|
| 991 |
+
"learning_rate": 0.0001738628069370195,
|
| 992 |
+
"loss": 1.4108,
|
| 993 |
+
"step": 680
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 3.128146453089245,
|
| 997 |
+
"grad_norm": 0.2543962299823761,
|
| 998 |
+
"learning_rate": 0.00017332074392000454,
|
| 999 |
+
"loss": 1.4124,
|
| 1000 |
+
"step": 685
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 3.151029748283753,
|
| 1004 |
+
"grad_norm": 0.23739871382713318,
|
| 1005 |
+
"learning_rate": 0.00017277398124460023,
|
| 1006 |
+
"loss": 1.4048,
|
| 1007 |
+
"step": 690
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 3.1739130434782608,
|
| 1011 |
+
"grad_norm": 0.23524770140647888,
|
| 1012 |
+
"learning_rate": 0.00017222255395679296,
|
| 1013 |
+
"loss": 1.4184,
|
| 1014 |
+
"step": 695
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 3.196796338672769,
|
| 1018 |
+
"grad_norm": 0.2273031771183014,
|
| 1019 |
+
"learning_rate": 0.000171666497401558,
|
| 1020 |
+
"loss": 1.4122,
|
| 1021 |
+
"step": 700
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 3.219679633867277,
|
| 1025 |
+
"grad_norm": 0.23595724999904633,
|
| 1026 |
+
"learning_rate": 0.00017110584722059393,
|
| 1027 |
+
"loss": 1.407,
|
| 1028 |
+
"step": 705
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 3.242562929061785,
|
| 1032 |
+
"grad_norm": 0.21827439963817596,
|
| 1033 |
+
"learning_rate": 0.0001705406393500381,
|
| 1034 |
+
"loss": 1.4027,
|
| 1035 |
+
"step": 710
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 3.265446224256293,
|
| 1039 |
+
"grad_norm": 0.22116319835186005,
|
| 1040 |
+
"learning_rate": 0.00016997091001816336,
|
| 1041 |
+
"loss": 1.4049,
|
| 1042 |
+
"step": 715
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 3.288329519450801,
|
| 1046 |
+
"grad_norm": 0.23044751584529877,
|
| 1047 |
+
"learning_rate": 0.00016939669574305566,
|
| 1048 |
+
"loss": 1.4095,
|
| 1049 |
+
"step": 720
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 3.311212814645309,
|
| 1053 |
+
"grad_norm": 0.22559754550457,
|
| 1054 |
+
"learning_rate": 0.00016881803333027362,
|
| 1055 |
+
"loss": 1.3991,
|
| 1056 |
+
"step": 725
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 3.334096109839817,
|
| 1060 |
+
"grad_norm": 0.2260756939649582,
|
| 1061 |
+
"learning_rate": 0.0001682349598704892,
|
| 1062 |
+
"loss": 1.4123,
|
| 1063 |
+
"step": 730
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 3.356979405034325,
|
| 1067 |
+
"grad_norm": 0.2145521193742752,
|
| 1068 |
+
"learning_rate": 0.00016764751273711044,
|
| 1069 |
+
"loss": 1.4119,
|
| 1070 |
+
"step": 735
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 3.379862700228833,
|
| 1074 |
+
"grad_norm": 0.23654837906360626,
|
| 1075 |
+
"learning_rate": 0.00016705572958388576,
|
| 1076 |
+
"loss": 1.4024,
|
| 1077 |
+
"step": 740
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 3.402745995423341,
|
| 1081 |
+
"grad_norm": 0.21862386167049408,
|
| 1082 |
+
"learning_rate": 0.0001664596483424906,
|
| 1083 |
+
"loss": 1.4104,
|
| 1084 |
+
"step": 745
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 3.425629290617849,
|
| 1088 |
+
"grad_norm": 0.2240535169839859,
|
| 1089 |
+
"learning_rate": 0.00016585930722009601,
|
| 1090 |
+
"loss": 1.4012,
|
| 1091 |
+
"step": 750
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 3.448512585812357,
|
| 1095 |
+
"grad_norm": 0.23204627633094788,
|
| 1096 |
+
"learning_rate": 0.00016525474469691984,
|
| 1097 |
+
"loss": 1.4044,
|
| 1098 |
+
"step": 755
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 3.471395881006865,
|
| 1102 |
+
"grad_norm": 0.23645585775375366,
|
| 1103 |
+
"learning_rate": 0.00016464599952375998,
|
| 1104 |
+
"loss": 1.4135,
|
| 1105 |
+
"step": 760
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 3.494279176201373,
|
| 1109 |
+
"grad_norm": 0.2199520468711853,
|
| 1110 |
+
"learning_rate": 0.00016403311071951082,
|
| 1111 |
+
"loss": 1.413,
|
| 1112 |
+
"step": 765
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 3.517162471395881,
|
| 1116 |
+
"grad_norm": 0.23638251423835754,
|
| 1117 |
+
"learning_rate": 0.000163416117568662,
|
| 1118 |
+
"loss": 1.4101,
|
| 1119 |
+
"step": 770
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 3.540045766590389,
|
| 1123 |
+
"grad_norm": 0.2419108748435974,
|
| 1124 |
+
"learning_rate": 0.00016279505961878064,
|
| 1125 |
+
"loss": 1.399,
|
| 1126 |
+
"step": 775
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 3.5629290617848968,
|
| 1130 |
+
"grad_norm": 0.23601311445236206,
|
| 1131 |
+
"learning_rate": 0.0001621699766779763,
|
| 1132 |
+
"loss": 1.4084,
|
| 1133 |
+
"step": 780
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 3.585812356979405,
|
| 1137 |
+
"grad_norm": 0.24460086226463318,
|
| 1138 |
+
"learning_rate": 0.0001615409088123493,
|
| 1139 |
+
"loss": 1.4144,
|
| 1140 |
+
"step": 785
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 3.608695652173913,
|
| 1144 |
+
"grad_norm": 0.21848763525485992,
|
| 1145 |
+
"learning_rate": 0.00016090789634342278,
|
| 1146 |
+
"loss": 1.3929,
|
| 1147 |
+
"step": 790
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 3.6315789473684212,
|
| 1151 |
+
"grad_norm": 0.22614765167236328,
|
| 1152 |
+
"learning_rate": 0.00016027097984555816,
|
| 1153 |
+
"loss": 1.399,
|
| 1154 |
+
"step": 795
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 3.654462242562929,
|
| 1158 |
+
"grad_norm": 0.22731591761112213,
|
| 1159 |
+
"learning_rate": 0.00015963020014335438,
|
| 1160 |
+
"loss": 1.3998,
|
| 1161 |
+
"step": 800
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 3.677345537757437,
|
| 1165 |
+
"grad_norm": 0.21770906448364258,
|
| 1166 |
+
"learning_rate": 0.00015898559830903106,
|
| 1167 |
+
"loss": 1.4064,
|
| 1168 |
+
"step": 805
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 3.700228832951945,
|
| 1172 |
+
"grad_norm": 0.25158295035362244,
|
| 1173 |
+
"learning_rate": 0.0001583372156597961,
|
| 1174 |
+
"loss": 1.4046,
|
| 1175 |
+
"step": 810
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 3.723112128146453,
|
| 1179 |
+
"grad_norm": 0.23650844395160675,
|
| 1180 |
+
"learning_rate": 0.00015768509375519726,
|
| 1181 |
+
"loss": 1.3942,
|
| 1182 |
+
"step": 815
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 3.745995423340961,
|
| 1186 |
+
"grad_norm": 0.22743116319179535,
|
| 1187 |
+
"learning_rate": 0.00015702927439445826,
|
| 1188 |
+
"loss": 1.4022,
|
| 1189 |
+
"step": 820
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 3.7688787185354693,
|
| 1193 |
+
"grad_norm": 0.23518233001232147,
|
| 1194 |
+
"learning_rate": 0.0001563697996137997,
|
| 1195 |
+
"loss": 1.3986,
|
| 1196 |
+
"step": 825
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 3.791762013729977,
|
| 1200 |
+
"grad_norm": 0.22372908890247345,
|
| 1201 |
+
"learning_rate": 0.00015570671168374438,
|
| 1202 |
+
"loss": 1.3937,
|
| 1203 |
+
"step": 830
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 3.814645308924485,
|
| 1207 |
+
"grad_norm": 0.2474096119403839,
|
| 1208 |
+
"learning_rate": 0.00015504005310640822,
|
| 1209 |
+
"loss": 1.3984,
|
| 1210 |
+
"step": 835
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 3.837528604118993,
|
| 1214 |
+
"grad_norm": 0.23158776760101318,
|
| 1215 |
+
"learning_rate": 0.00015436986661277577,
|
| 1216 |
+
"loss": 1.3972,
|
| 1217 |
+
"step": 840
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 3.860411899313501,
|
| 1221 |
+
"grad_norm": 0.239366814494133,
|
| 1222 |
+
"learning_rate": 0.0001536961951599613,
|
| 1223 |
+
"loss": 1.4023,
|
| 1224 |
+
"step": 845
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 3.883295194508009,
|
| 1228 |
+
"grad_norm": 0.26158976554870605,
|
| 1229 |
+
"learning_rate": 0.0001530190819284555,
|
| 1230 |
+
"loss": 1.3918,
|
| 1231 |
+
"step": 850
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 3.9061784897025174,
|
| 1235 |
+
"grad_norm": 0.2554950416088104,
|
| 1236 |
+
"learning_rate": 0.00015233857031935749,
|
| 1237 |
+
"loss": 1.3927,
|
| 1238 |
+
"step": 855
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 3.929061784897025,
|
| 1242 |
+
"grad_norm": 0.23338022828102112,
|
| 1243 |
+
"learning_rate": 0.00015165470395159313,
|
| 1244 |
+
"loss": 1.3929,
|
| 1245 |
+
"step": 860
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 3.9519450800915332,
|
| 1249 |
+
"grad_norm": 0.2260856032371521,
|
| 1250 |
+
"learning_rate": 0.00015096752665911913,
|
| 1251 |
+
"loss": 1.4055,
|
| 1252 |
+
"step": 865
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 3.974828375286041,
|
| 1256 |
+
"grad_norm": 0.2310597449541092,
|
| 1257 |
+
"learning_rate": 0.0001502770824881133,
|
| 1258 |
+
"loss": 1.3984,
|
| 1259 |
+
"step": 870
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 3.997711670480549,
|
| 1263 |
+
"grad_norm": 0.22370661795139313,
|
| 1264 |
+
"learning_rate": 0.00014958341569415147,
|
| 1265 |
+
"loss": 1.3972,
|
| 1266 |
+
"step": 875
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 4.0,
|
| 1270 |
+
"eval_loss": 2.462189197540283,
|
| 1271 |
+
"eval_runtime": 0.1584,
|
| 1272 |
+
"eval_samples_per_second": 63.121,
|
| 1273 |
+
"eval_steps_per_second": 6.312,
|
| 1274 |
+
"step": 876
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 4.018306636155606,
|
| 1278 |
+
"grad_norm": 0.24240370094776154,
|
| 1279 |
+
"learning_rate": 0.00014888657073937076,
|
| 1280 |
+
"loss": 1.3961,
|
| 1281 |
+
"step": 880
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 4.0411899313501145,
|
| 1285 |
+
"grad_norm": 0.22996193170547485,
|
| 1286 |
+
"learning_rate": 0.0001481865922896196,
|
| 1287 |
+
"loss": 1.3808,
|
| 1288 |
+
"step": 885
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 4.064073226544623,
|
| 1292 |
+
"grad_norm": 0.21983887255191803,
|
| 1293 |
+
"learning_rate": 0.00014748352521159493,
|
| 1294 |
+
"loss": 1.3764,
|
| 1295 |
+
"step": 890
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 4.086956521739131,
|
| 1299 |
+
"grad_norm": 0.23078066110610962,
|
| 1300 |
+
"learning_rate": 0.00014677741456996617,
|
| 1301 |
+
"loss": 1.3826,
|
| 1302 |
+
"step": 895
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 4.109839816933638,
|
| 1306 |
+
"grad_norm": 0.2580978274345398,
|
| 1307 |
+
"learning_rate": 0.0001460683056244869,
|
| 1308 |
+
"loss": 1.3816,
|
| 1309 |
+
"step": 900
|
| 1310 |
+
},
|
| 1311 |
+
{
|
| 1312 |
+
"epoch": 4.132723112128146,
|
| 1313 |
+
"grad_norm": 0.22216792404651642,
|
| 1314 |
+
"learning_rate": 0.00014535624382709382,
|
| 1315 |
+
"loss": 1.3767,
|
| 1316 |
+
"step": 905
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 4.155606407322654,
|
| 1320 |
+
"grad_norm": 0.21901686489582062,
|
| 1321 |
+
"learning_rate": 0.00014464127481899312,
|
| 1322 |
+
"loss": 1.3951,
|
| 1323 |
+
"step": 910
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 4.178489702517163,
|
| 1327 |
+
"grad_norm": 0.22333645820617676,
|
| 1328 |
+
"learning_rate": 0.0001439234444277354,
|
| 1329 |
+
"loss": 1.3946,
|
| 1330 |
+
"step": 915
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 4.201372997711671,
|
| 1334 |
+
"grad_norm": 0.2606089413166046,
|
| 1335 |
+
"learning_rate": 0.00014320279866427796,
|
| 1336 |
+
"loss": 1.3836,
|
| 1337 |
+
"step": 920
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 4.224256292906179,
|
| 1341 |
+
"grad_norm": 0.2596084475517273,
|
| 1342 |
+
"learning_rate": 0.00014247938372003582,
|
| 1343 |
+
"loss": 1.3849,
|
| 1344 |
+
"step": 925
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 4.247139588100686,
|
| 1348 |
+
"grad_norm": 0.2835715115070343,
|
| 1349 |
+
"learning_rate": 0.00014175324596392075,
|
| 1350 |
+
"loss": 1.386,
|
| 1351 |
+
"step": 930
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 4.270022883295194,
|
| 1355 |
+
"grad_norm": 0.2396639585494995,
|
| 1356 |
+
"learning_rate": 0.0001410244319393694,
|
| 1357 |
+
"loss": 1.3848,
|
| 1358 |
+
"step": 935
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 4.2929061784897025,
|
| 1362 |
+
"grad_norm": 0.22530311346054077,
|
| 1363 |
+
"learning_rate": 0.00014029298836135988,
|
| 1364 |
+
"loss": 1.3839,
|
| 1365 |
+
"step": 940
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 4.315789473684211,
|
| 1369 |
+
"grad_norm": 0.23546090722084045,
|
| 1370 |
+
"learning_rate": 0.0001395589621134174,
|
| 1371 |
+
"loss": 1.3948,
|
| 1372 |
+
"step": 945
|
| 1373 |
+
},
|
| 1374 |
+
{
|
| 1375 |
+
"epoch": 4.338672768878719,
|
| 1376 |
+
"grad_norm": 0.24042978882789612,
|
| 1377 |
+
"learning_rate": 0.00013882240024460927,
|
| 1378 |
+
"loss": 1.3891,
|
| 1379 |
+
"step": 950
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 4.361556064073227,
|
| 1383 |
+
"grad_norm": 0.26460978388786316,
|
| 1384 |
+
"learning_rate": 0.00013808334996652904,
|
| 1385 |
+
"loss": 1.3821,
|
| 1386 |
+
"step": 955
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 4.384439359267734,
|
| 1390 |
+
"grad_norm": 0.2298058718442917,
|
| 1391 |
+
"learning_rate": 0.0001373418586502706,
|
| 1392 |
+
"loss": 1.3796,
|
| 1393 |
+
"step": 960
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"epoch": 4.407322654462242,
|
| 1397 |
+
"grad_norm": 0.21995796263217926,
|
| 1398 |
+
"learning_rate": 0.0001365979738233916,
|
| 1399 |
+
"loss": 1.3892,
|
| 1400 |
+
"step": 965
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 4.4302059496567505,
|
| 1404 |
+
"grad_norm": 0.22304576635360718,
|
| 1405 |
+
"learning_rate": 0.0001358517431668672,
|
| 1406 |
+
"loss": 1.3731,
|
| 1407 |
+
"step": 970
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 4.453089244851259,
|
| 1411 |
+
"grad_norm": 0.2750610411167145,
|
| 1412 |
+
"learning_rate": 0.0001351032145120337,
|
| 1413 |
+
"loss": 1.3732,
|
| 1414 |
+
"step": 975
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 4.475972540045767,
|
| 1418 |
+
"grad_norm": 0.24216437339782715,
|
| 1419 |
+
"learning_rate": 0.00013435243583752294,
|
| 1420 |
+
"loss": 1.3955,
|
| 1421 |
+
"step": 980
|
| 1422 |
+
},
|
| 1423 |
+
{
|
| 1424 |
+
"epoch": 4.498855835240275,
|
| 1425 |
+
"grad_norm": 0.23672589659690857,
|
| 1426 |
+
"learning_rate": 0.00013359945526618668,
|
| 1427 |
+
"loss": 1.3859,
|
| 1428 |
+
"step": 985
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 4.521739130434782,
|
| 1432 |
+
"grad_norm": 0.21664075553417206,
|
| 1433 |
+
"learning_rate": 0.00013284432106201233,
|
| 1434 |
+
"loss": 1.3885,
|
| 1435 |
+
"step": 990
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 4.54462242562929,
|
| 1439 |
+
"grad_norm": 0.22267000377178192,
|
| 1440 |
+
"learning_rate": 0.00013208708162702922,
|
| 1441 |
+
"loss": 1.3811,
|
| 1442 |
+
"step": 995
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 4.567505720823799,
|
| 1446 |
+
"grad_norm": 0.23190075159072876,
|
| 1447 |
+
"learning_rate": 0.00013132778549820618,
|
| 1448 |
+
"loss": 1.3813,
|
| 1449 |
+
"step": 1000
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 4.590389016018307,
|
| 1453 |
+
"grad_norm": 0.21617767214775085,
|
| 1454 |
+
"learning_rate": 0.0001305664813443405,
|
| 1455 |
+
"loss": 1.3821,
|
| 1456 |
+
"step": 1005
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 4.613272311212815,
|
| 1460 |
+
"grad_norm": 0.22316230833530426,
|
| 1461 |
+
"learning_rate": 0.00012980321796293836,
|
| 1462 |
+
"loss": 1.3854,
|
| 1463 |
+
"step": 1010
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 4.636155606407323,
|
| 1467 |
+
"grad_norm": 0.22770841419696808,
|
| 1468 |
+
"learning_rate": 0.00012903804427708704,
|
| 1469 |
+
"loss": 1.392,
|
| 1470 |
+
"step": 1015
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 4.65903890160183,
|
| 1474 |
+
"grad_norm": 0.25319135189056396,
|
| 1475 |
+
"learning_rate": 0.00012827100933231905,
|
| 1476 |
+
"loss": 1.384,
|
| 1477 |
+
"step": 1020
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 4.6819221967963385,
|
| 1481 |
+
"grad_norm": 0.24790321290493011,
|
| 1482 |
+
"learning_rate": 0.0001275021622934685,
|
| 1483 |
+
"loss": 1.3817,
|
| 1484 |
+
"step": 1025
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 4.704805491990847,
|
| 1488 |
+
"grad_norm": 0.24224399030208588,
|
| 1489 |
+
"learning_rate": 0.00012673155244151985,
|
| 1490 |
+
"loss": 1.3869,
|
| 1491 |
+
"step": 1030
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 4.727688787185355,
|
| 1495 |
+
"grad_norm": 0.2306058555841446,
|
| 1496 |
+
"learning_rate": 0.0001259592291704489,
|
| 1497 |
+
"loss": 1.3816,
|
| 1498 |
+
"step": 1035
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 4.750572082379863,
|
| 1502 |
+
"grad_norm": 0.2296520620584488,
|
| 1503 |
+
"learning_rate": 0.000125185241984057,
|
| 1504 |
+
"loss": 1.3855,
|
| 1505 |
+
"step": 1040
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 4.77345537757437,
|
| 1509 |
+
"grad_norm": 0.22120504081249237,
|
| 1510 |
+
"learning_rate": 0.00012440964049279787,
|
| 1511 |
+
"loss": 1.3839,
|
| 1512 |
+
"step": 1045
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 4.796338672768878,
|
| 1516 |
+
"grad_norm": 0.23121312260627747,
|
| 1517 |
+
"learning_rate": 0.00012363247441059776,
|
| 1518 |
+
"loss": 1.3816,
|
| 1519 |
+
"step": 1050
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 4.8192219679633865,
|
| 1523 |
+
"grad_norm": 0.22182002663612366,
|
| 1524 |
+
"learning_rate": 0.00012285379355166893,
|
| 1525 |
+
"loss": 1.3808,
|
| 1526 |
+
"step": 1055
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 4.842105263157895,
|
| 1530 |
+
"grad_norm": 0.22699835896492004,
|
| 1531 |
+
"learning_rate": 0.00012207364782731655,
|
| 1532 |
+
"loss": 1.3829,
|
| 1533 |
+
"step": 1060
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 4.864988558352403,
|
| 1537 |
+
"grad_norm": 0.24495604634284973,
|
| 1538 |
+
"learning_rate": 0.00012129208724273984,
|
| 1539 |
+
"loss": 1.3827,
|
| 1540 |
+
"step": 1065
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 4.887871853546911,
|
| 1544 |
+
"grad_norm": 0.235788956284523,
|
| 1545 |
+
"learning_rate": 0.00012050916189382646,
|
| 1546 |
+
"loss": 1.3898,
|
| 1547 |
+
"step": 1070
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 4.910755148741419,
|
| 1551 |
+
"grad_norm": 0.24433469772338867,
|
| 1552 |
+
"learning_rate": 0.00011972492196394187,
|
| 1553 |
+
"loss": 1.3913,
|
| 1554 |
+
"step": 1075
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 4.933638443935926,
|
| 1558 |
+
"grad_norm": 0.2331000417470932,
|
| 1559 |
+
"learning_rate": 0.00011893941772071249,
|
| 1560 |
+
"loss": 1.3906,
|
| 1561 |
+
"step": 1080
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 4.956521739130435,
|
| 1565 |
+
"grad_norm": 0.22595056891441345,
|
| 1566 |
+
"learning_rate": 0.0001181526995128038,
|
| 1567 |
+
"loss": 1.3981,
|
| 1568 |
+
"step": 1085
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 4.979405034324943,
|
| 1572 |
+
"grad_norm": 0.22172114253044128,
|
| 1573 |
+
"learning_rate": 0.00011736481776669306,
|
| 1574 |
+
"loss": 1.3895,
|
| 1575 |
+
"step": 1090
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 5.0,
|
| 1579 |
+
"grad_norm": 0.3044658601284027,
|
| 1580 |
+
"learning_rate": 0.0001165758229834371,
|
| 1581 |
+
"loss": 1.3868,
|
| 1582 |
+
"step": 1095
|
| 1583 |
+
},
|
| 1584 |
+
{
|
| 1585 |
+
"epoch": 5.0,
|
| 1586 |
+
"eval_loss": 2.481019973754883,
|
| 1587 |
+
"eval_runtime": 0.1574,
|
| 1588 |
+
"eval_samples_per_second": 63.534,
|
| 1589 |
+
"eval_steps_per_second": 6.353,
|
| 1590 |
+
"step": 1095
|
| 1591 |
+
},
|
| 1592 |
+
{
|
| 1593 |
+
"epoch": 5.022883295194508,
|
| 1594 |
+
"grad_norm": 0.24489176273345947,
|
| 1595 |
+
"learning_rate": 0.0001157857657354354,
|
| 1596 |
+
"loss": 1.376,
|
| 1597 |
+
"step": 1100
|
| 1598 |
+
},
|
| 1599 |
+
{
|
| 1600 |
+
"epoch": 5.045766590389016,
|
| 1601 |
+
"grad_norm": 0.2253871113061905,
|
| 1602 |
+
"learning_rate": 0.00011499469666318858,
|
| 1603 |
+
"loss": 1.3759,
|
| 1604 |
+
"step": 1105
|
| 1605 |
+
},
|
| 1606 |
+
{
|
| 1607 |
+
"epoch": 5.068649885583524,
|
| 1608 |
+
"grad_norm": 0.235123872756958,
|
| 1609 |
+
"learning_rate": 0.00011420266647205231,
|
| 1610 |
+
"loss": 1.3774,
|
| 1611 |
+
"step": 1110
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 5.091533180778032,
|
| 1615 |
+
"grad_norm": 0.2346729189157486,
|
| 1616 |
+
"learning_rate": 0.00011340972592898744,
|
| 1617 |
+
"loss": 1.3556,
|
| 1618 |
+
"step": 1115
|
| 1619 |
+
},
|
| 1620 |
+
{
|
| 1621 |
+
"epoch": 5.11441647597254,
|
| 1622 |
+
"grad_norm": 0.2369905263185501,
|
| 1623 |
+
"learning_rate": 0.00011261592585930576,
|
| 1624 |
+
"loss": 1.3714,
|
| 1625 |
+
"step": 1120
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 5.137299771167048,
|
| 1629 |
+
"grad_norm": 0.2265693098306656,
|
| 1630 |
+
"learning_rate": 0.00011182131714341247,
|
| 1631 |
+
"loss": 1.37,
|
| 1632 |
+
"step": 1125
|
| 1633 |
+
},
|
| 1634 |
+
{
|
| 1635 |
+
"epoch": 5.160183066361556,
|
| 1636 |
+
"grad_norm": 0.21262961626052856,
|
| 1637 |
+
"learning_rate": 0.00011102595071354472,
|
| 1638 |
+
"loss": 1.3639,
|
| 1639 |
+
"step": 1130
|
| 1640 |
+
},
|
| 1641 |
+
{
|
| 1642 |
+
"epoch": 5.183066361556064,
|
| 1643 |
+
"grad_norm": 0.2247275561094284,
|
| 1644 |
+
"learning_rate": 0.00011022987755050704,
|
| 1645 |
+
"loss": 1.3649,
|
| 1646 |
+
"step": 1135
|
| 1647 |
+
},
|
| 1648 |
+
{
|
| 1649 |
+
"epoch": 5.2059496567505725,
|
| 1650 |
+
"grad_norm": 0.22549380362033844,
|
| 1651 |
+
"learning_rate": 0.00010943314868040364,
|
| 1652 |
+
"loss": 1.3542,
|
| 1653 |
+
"step": 1140
|
| 1654 |
+
},
|
| 1655 |
+
{
|
| 1656 |
+
"epoch": 5.22883295194508,
|
| 1657 |
+
"grad_norm": 0.2336389124393463,
|
| 1658 |
+
"learning_rate": 0.00010863581517136776,
|
| 1659 |
+
"loss": 1.3659,
|
| 1660 |
+
"step": 1145
|
| 1661 |
+
},
|
| 1662 |
+
{
|
| 1663 |
+
"epoch": 5.251716247139588,
|
| 1664 |
+
"grad_norm": 0.24654635787010193,
|
| 1665 |
+
"learning_rate": 0.00010783792813028827,
|
| 1666 |
+
"loss": 1.3742,
|
| 1667 |
+
"step": 1150
|
| 1668 |
+
},
|
| 1669 |
+
{
|
| 1670 |
+
"epoch": 5.274599542334096,
|
| 1671 |
+
"grad_norm": 0.22848239541053772,
|
| 1672 |
+
"learning_rate": 0.00010703953869953403,
|
| 1673 |
+
"loss": 1.3783,
|
| 1674 |
+
"step": 1155
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 5.297482837528604,
|
| 1678 |
+
"grad_norm": 0.241807758808136,
|
| 1679 |
+
"learning_rate": 0.00010624069805367559,
|
| 1680 |
+
"loss": 1.3731,
|
| 1681 |
+
"step": 1160
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 5.320366132723112,
|
| 1685 |
+
"grad_norm": 0.23657450079917908,
|
| 1686 |
+
"learning_rate": 0.00010544145739620519,
|
| 1687 |
+
"loss": 1.3674,
|
| 1688 |
+
"step": 1165
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 5.34324942791762,
|
| 1692 |
+
"grad_norm": 0.2408100813627243,
|
| 1693 |
+
"learning_rate": 0.00010464186795625482,
|
| 1694 |
+
"loss": 1.3732,
|
| 1695 |
+
"step": 1170
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 5.366132723112128,
|
| 1699 |
+
"grad_norm": 0.23080427944660187,
|
| 1700 |
+
"learning_rate": 0.00010384198098531225,
|
| 1701 |
+
"loss": 1.3912,
|
| 1702 |
+
"step": 1175
|
| 1703 |
+
},
|
| 1704 |
+
{
|
| 1705 |
+
"epoch": 5.389016018306636,
|
| 1706 |
+
"grad_norm": 0.23397450149059296,
|
| 1707 |
+
"learning_rate": 0.00010304184775393642,
|
| 1708 |
+
"loss": 1.381,
|
| 1709 |
+
"step": 1180
|
| 1710 |
+
},
|
| 1711 |
+
{
|
| 1712 |
+
"epoch": 5.411899313501144,
|
| 1713 |
+
"grad_norm": 0.2350955307483673,
|
| 1714 |
+
"learning_rate": 0.00010224151954847064,
|
| 1715 |
+
"loss": 1.3768,
|
| 1716 |
+
"step": 1185
|
| 1717 |
+
},
|
| 1718 |
+
{
|
| 1719 |
+
"epoch": 5.434782608695652,
|
| 1720 |
+
"grad_norm": 0.23939336836338043,
|
| 1721 |
+
"learning_rate": 0.00010144104766775572,
|
| 1722 |
+
"loss": 1.3731,
|
| 1723 |
+
"step": 1190
|
| 1724 |
+
},
|
| 1725 |
+
{
|
| 1726 |
+
"epoch": 5.4576659038901605,
|
| 1727 |
+
"grad_norm": 0.23009169101715088,
|
| 1728 |
+
"learning_rate": 0.0001006404834198416,
|
| 1729 |
+
"loss": 1.3715,
|
| 1730 |
+
"step": 1195
|
| 1731 |
+
},
|
| 1732 |
+
{
|
| 1733 |
+
"epoch": 5.480549199084669,
|
| 1734 |
+
"grad_norm": 0.2236054390668869,
|
| 1735 |
+
"learning_rate": 9.983987811869862e-05,
|
| 1736 |
+
"loss": 1.3737,
|
| 1737 |
+
"step": 1200
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 5.503432494279176,
|
| 1741 |
+
"grad_norm": 0.23314499855041504,
|
| 1742 |
+
"learning_rate": 9.903928308092865e-05,
|
| 1743 |
+
"loss": 1.369,
|
| 1744 |
+
"step": 1205
|
| 1745 |
+
},
|
| 1746 |
+
{
|
| 1747 |
+
"epoch": 5.526315789473684,
|
| 1748 |
+
"grad_norm": 0.22338473796844482,
|
| 1749 |
+
"learning_rate": 9.823874962247564e-05,
|
| 1750 |
+
"loss": 1.3717,
|
| 1751 |
+
"step": 1210
|
| 1752 |
+
},
|
| 1753 |
+
{
|
| 1754 |
+
"epoch": 5.549199084668192,
|
| 1755 |
+
"grad_norm": 0.22037141025066376,
|
| 1756 |
+
"learning_rate": 9.743832905533644e-05,
|
| 1757 |
+
"loss": 1.3789,
|
| 1758 |
+
"step": 1215
|
| 1759 |
+
},
|
| 1760 |
+
{
|
| 1761 |
+
"epoch": 5.5720823798627,
|
| 1762 |
+
"grad_norm": 0.2261509895324707,
|
| 1763 |
+
"learning_rate": 9.663807268427198e-05,
|
| 1764 |
+
"loss": 1.3741,
|
| 1765 |
+
"step": 1220
|
| 1766 |
+
},
|
| 1767 |
+
{
|
| 1768 |
+
"epoch": 5.5949656750572085,
|
| 1769 |
+
"grad_norm": 0.2503112256526947,
|
| 1770 |
+
"learning_rate": 9.583803180351852e-05,
|
| 1771 |
+
"loss": 1.3805,
|
| 1772 |
+
"step": 1225
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 5.617848970251716,
|
| 1776 |
+
"grad_norm": 0.22896412014961243,
|
| 1777 |
+
"learning_rate": 9.503825769350017e-05,
|
| 1778 |
+
"loss": 1.3583,
|
| 1779 |
+
"step": 1230
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 5.640732265446224,
|
| 1783 |
+
"grad_norm": 0.2552075982093811,
|
| 1784 |
+
"learning_rate": 9.423880161754158e-05,
|
| 1785 |
+
"loss": 1.3767,
|
| 1786 |
+
"step": 1235
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 5.663615560640732,
|
| 1790 |
+
"grad_norm": 0.23098088800907135,
|
| 1791 |
+
"learning_rate": 9.343971481858246e-05,
|
| 1792 |
+
"loss": 1.3719,
|
| 1793 |
+
"step": 1240
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 5.68649885583524,
|
| 1797 |
+
"grad_norm": 0.23425135016441345,
|
| 1798 |
+
"learning_rate": 9.264104851589273e-05,
|
| 1799 |
+
"loss": 1.3678,
|
| 1800 |
+
"step": 1245
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 5.709382151029748,
|
| 1804 |
+
"grad_norm": 0.229757159948349,
|
| 1805 |
+
"learning_rate": 9.184285390178978e-05,
|
| 1806 |
+
"loss": 1.3652,
|
| 1807 |
+
"step": 1250
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 5.732265446224257,
|
| 1811 |
+
"grad_norm": 0.22069285809993744,
|
| 1812 |
+
"learning_rate": 9.104518213835692e-05,
|
| 1813 |
+
"loss": 1.3628,
|
| 1814 |
+
"step": 1255
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 5.755148741418765,
|
| 1818 |
+
"grad_norm": 0.23451228439807892,
|
| 1819 |
+
"learning_rate": 9.024808435416434e-05,
|
| 1820 |
+
"loss": 1.3658,
|
| 1821 |
+
"step": 1260
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 5.778032036613272,
|
| 1825 |
+
"grad_norm": 0.2394520491361618,
|
| 1826 |
+
"learning_rate": 8.945161164099157e-05,
|
| 1827 |
+
"loss": 1.3775,
|
| 1828 |
+
"step": 1265
|
| 1829 |
+
},
|
| 1830 |
+
{
|
| 1831 |
+
"epoch": 5.80091533180778,
|
| 1832 |
+
"grad_norm": 0.23245683312416077,
|
| 1833 |
+
"learning_rate": 8.865581505055291e-05,
|
| 1834 |
+
"loss": 1.372,
|
| 1835 |
+
"step": 1270
|
| 1836 |
+
},
|
| 1837 |
+
{
|
| 1838 |
+
"epoch": 5.823798627002288,
|
| 1839 |
+
"grad_norm": 0.23066289722919464,
|
| 1840 |
+
"learning_rate": 8.7860745591225e-05,
|
| 1841 |
+
"loss": 1.3739,
|
| 1842 |
+
"step": 1275
|
| 1843 |
+
},
|
| 1844 |
+
{
|
| 1845 |
+
"epoch": 5.8466819221967965,
|
| 1846 |
+
"grad_norm": 0.23424118757247925,
|
| 1847 |
+
"learning_rate": 8.706645422477739e-05,
|
| 1848 |
+
"loss": 1.3597,
|
| 1849 |
+
"step": 1280
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 5.869565217391305,
|
| 1853 |
+
"grad_norm": 0.2321302741765976,
|
| 1854 |
+
"learning_rate": 8.627299186310603e-05,
|
| 1855 |
+
"loss": 1.3732,
|
| 1856 |
+
"step": 1285
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 5.892448512585812,
|
| 1860 |
+
"grad_norm": 0.2273801863193512,
|
| 1861 |
+
"learning_rate": 8.548040936496989e-05,
|
| 1862 |
+
"loss": 1.3685,
|
| 1863 |
+
"step": 1290
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 5.91533180778032,
|
| 1867 |
+
"grad_norm": 0.2422792911529541,
|
| 1868 |
+
"learning_rate": 8.468875753273115e-05,
|
| 1869 |
+
"loss": 1.372,
|
| 1870 |
+
"step": 1295
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"epoch": 5.938215102974828,
|
| 1874 |
+
"grad_norm": 0.22604131698608398,
|
| 1875 |
+
"learning_rate": 8.389808710909881e-05,
|
| 1876 |
+
"loss": 1.3676,
|
| 1877 |
+
"step": 1300
|
| 1878 |
+
},
|
| 1879 |
+
{
|
| 1880 |
+
"epoch": 5.961098398169336,
|
| 1881 |
+
"grad_norm": 0.24549026787281036,
|
| 1882 |
+
"learning_rate": 8.310844877387637e-05,
|
| 1883 |
+
"loss": 1.358,
|
| 1884 |
+
"step": 1305
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 5.983981693363845,
|
| 1888 |
+
"grad_norm": 0.23445729911327362,
|
| 1889 |
+
"learning_rate": 8.231989314071317e-05,
|
| 1890 |
+
"loss": 1.3692,
|
| 1891 |
+
"step": 1310
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 6.0,
|
| 1895 |
+
"eval_loss": 2.5001282691955566,
|
| 1896 |
+
"eval_runtime": 0.1605,
|
| 1897 |
+
"eval_samples_per_second": 62.3,
|
| 1898 |
+
"eval_steps_per_second": 6.23,
|
| 1899 |
+
"step": 1314
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 6.004576659038902,
|
| 1903 |
+
"grad_norm": 0.2388521283864975,
|
| 1904 |
+
"learning_rate": 8.153247075386043e-05,
|
| 1905 |
+
"loss": 1.3541,
|
| 1906 |
+
"step": 1315
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 6.02745995423341,
|
| 1910 |
+
"grad_norm": 0.23299774527549744,
|
| 1911 |
+
"learning_rate": 8.07462320849313e-05,
|
| 1912 |
+
"loss": 1.3572,
|
| 1913 |
+
"step": 1320
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 6.050343249427917,
|
| 1917 |
+
"grad_norm": 0.23086461424827576,
|
| 1918 |
+
"learning_rate": 7.996122752966595e-05,
|
| 1919 |
+
"loss": 1.3568,
|
| 1920 |
+
"step": 1325
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 6.073226544622425,
|
| 1924 |
+
"grad_norm": 0.23091675341129303,
|
| 1925 |
+
"learning_rate": 7.917750740470117e-05,
|
| 1926 |
+
"loss": 1.3618,
|
| 1927 |
+
"step": 1330
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 6.0961098398169336,
|
| 1931 |
+
"grad_norm": 0.23161986470222473,
|
| 1932 |
+
"learning_rate": 7.839512194434531e-05,
|
| 1933 |
+
"loss": 1.363,
|
| 1934 |
+
"step": 1335
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 6.118993135011442,
|
| 1938 |
+
"grad_norm": 0.23545809090137482,
|
| 1939 |
+
"learning_rate": 7.761412129735852e-05,
|
| 1940 |
+
"loss": 1.3609,
|
| 1941 |
+
"step": 1340
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 6.14187643020595,
|
| 1945 |
+
"grad_norm": 0.23319639265537262,
|
| 1946 |
+
"learning_rate": 7.683455552373799e-05,
|
| 1947 |
+
"loss": 1.365,
|
| 1948 |
+
"step": 1345
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 6.164759725400458,
|
| 1952 |
+
"grad_norm": 0.23536434769630432,
|
| 1953 |
+
"learning_rate": 7.605647459150961e-05,
|
| 1954 |
+
"loss": 1.3673,
|
| 1955 |
+
"step": 1350
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 6.187643020594965,
|
| 1959 |
+
"grad_norm": 0.2269584983587265,
|
| 1960 |
+
"learning_rate": 7.527992837352501e-05,
|
| 1961 |
+
"loss": 1.3635,
|
| 1962 |
+
"step": 1355
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 6.2105263157894735,
|
| 1966 |
+
"grad_norm": 0.22587326169013977,
|
| 1967 |
+
"learning_rate": 7.450496664426477e-05,
|
| 1968 |
+
"loss": 1.3595,
|
| 1969 |
+
"step": 1360
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 6.233409610983982,
|
| 1973 |
+
"grad_norm": 0.22287671267986298,
|
| 1974 |
+
"learning_rate": 7.37316390766482e-05,
|
| 1975 |
+
"loss": 1.3752,
|
| 1976 |
+
"step": 1365
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 6.25629290617849,
|
| 1980 |
+
"grad_norm": 0.23099535703659058,
|
| 1981 |
+
"learning_rate": 7.295999523884921e-05,
|
| 1982 |
+
"loss": 1.3613,
|
| 1983 |
+
"step": 1370
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 6.279176201372998,
|
| 1987 |
+
"grad_norm": 0.22423085570335388,
|
| 1988 |
+
"learning_rate": 7.219008459111937e-05,
|
| 1989 |
+
"loss": 1.3658,
|
| 1990 |
+
"step": 1375
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 6.302059496567506,
|
| 1994 |
+
"grad_norm": 0.23212574422359467,
|
| 1995 |
+
"learning_rate": 7.142195648261747e-05,
|
| 1996 |
+
"loss": 1.361,
|
| 1997 |
+
"step": 1380
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 6.324942791762013,
|
| 2001 |
+
"grad_norm": 0.22750739753246307,
|
| 2002 |
+
"learning_rate": 7.065566014824643e-05,
|
| 2003 |
+
"loss": 1.3602,
|
| 2004 |
+
"step": 1385
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 6.3478260869565215,
|
| 2008 |
+
"grad_norm": 0.2309405356645584,
|
| 2009 |
+
"learning_rate": 6.989124470549745e-05,
|
| 2010 |
+
"loss": 1.366,
|
| 2011 |
+
"step": 1390
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 6.37070938215103,
|
| 2015 |
+
"grad_norm": 0.24688778817653656,
|
| 2016 |
+
"learning_rate": 6.912875915130183e-05,
|
| 2017 |
+
"loss": 1.3645,
|
| 2018 |
+
"step": 1395
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 6.393592677345538,
|
| 2022 |
+
"grad_norm": 0.23304879665374756,
|
| 2023 |
+
"learning_rate": 6.83682523588902e-05,
|
| 2024 |
+
"loss": 1.3519,
|
| 2025 |
+
"step": 1400
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 6.416475972540046,
|
| 2029 |
+
"grad_norm": 0.2324698269367218,
|
| 2030 |
+
"learning_rate": 6.760977307466008e-05,
|
| 2031 |
+
"loss": 1.358,
|
| 2032 |
+
"step": 1405
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 6.439359267734554,
|
| 2036 |
+
"grad_norm": 0.23698380589485168,
|
| 2037 |
+
"learning_rate": 6.685336991505122e-05,
|
| 2038 |
+
"loss": 1.3569,
|
| 2039 |
+
"step": 1410
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 6.462242562929061,
|
| 2043 |
+
"grad_norm": 0.2366679459810257,
|
| 2044 |
+
"learning_rate": 6.609909136342955e-05,
|
| 2045 |
+
"loss": 1.3538,
|
| 2046 |
+
"step": 1415
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 6.48512585812357,
|
| 2050 |
+
"grad_norm": 0.2314102202653885,
|
| 2051 |
+
"learning_rate": 6.534698576697939e-05,
|
| 2052 |
+
"loss": 1.3607,
|
| 2053 |
+
"step": 1420
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 6.508009153318078,
|
| 2057 |
+
"grad_norm": 0.2393520474433899,
|
| 2058 |
+
"learning_rate": 6.459710133360464e-05,
|
| 2059 |
+
"loss": 1.3649,
|
| 2060 |
+
"step": 1425
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 6.530892448512586,
|
| 2064 |
+
"grad_norm": 0.23024214804172516,
|
| 2065 |
+
"learning_rate": 6.384948612883873e-05,
|
| 2066 |
+
"loss": 1.367,
|
| 2067 |
+
"step": 1430
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 6.553775743707094,
|
| 2071 |
+
"grad_norm": 0.23126175999641418,
|
| 2072 |
+
"learning_rate": 6.310418807276375e-05,
|
| 2073 |
+
"loss": 1.3623,
|
| 2074 |
+
"step": 1435
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 6.576659038901602,
|
| 2078 |
+
"grad_norm": 0.2327370047569275,
|
| 2079 |
+
"learning_rate": 6.2361254936939e-05,
|
| 2080 |
+
"loss": 1.3532,
|
| 2081 |
+
"step": 1440
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 6.5995423340961095,
|
| 2085 |
+
"grad_norm": 0.22811928391456604,
|
| 2086 |
+
"learning_rate": 6.162073434133876e-05,
|
| 2087 |
+
"loss": 1.3662,
|
| 2088 |
+
"step": 1445
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 6.622425629290618,
|
| 2092 |
+
"grad_norm": 0.25274351239204407,
|
| 2093 |
+
"learning_rate": 6.088267375130023e-05,
|
| 2094 |
+
"loss": 1.3537,
|
| 2095 |
+
"step": 1450
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 6.645308924485126,
|
| 2099 |
+
"grad_norm": 0.24889418482780457,
|
| 2100 |
+
"learning_rate": 6.01471204744809e-05,
|
| 2101 |
+
"loss": 1.3598,
|
| 2102 |
+
"step": 1455
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 6.668192219679634,
|
| 2106 |
+
"grad_norm": 0.23805195093154907,
|
| 2107 |
+
"learning_rate": 5.941412165782645e-05,
|
| 2108 |
+
"loss": 1.3525,
|
| 2109 |
+
"step": 1460
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 6.691075514874142,
|
| 2113 |
+
"grad_norm": 0.2376497983932495,
|
| 2114 |
+
"learning_rate": 5.868372428454861e-05,
|
| 2115 |
+
"loss": 1.3662,
|
| 2116 |
+
"step": 1465
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 6.71395881006865,
|
| 2120 |
+
"grad_norm": 0.24028287827968597,
|
| 2121 |
+
"learning_rate": 5.79559751711138e-05,
|
| 2122 |
+
"loss": 1.3524,
|
| 2123 |
+
"step": 1470
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 6.7368421052631575,
|
| 2127 |
+
"grad_norm": 0.23552508652210236,
|
| 2128 |
+
"learning_rate": 5.72309209642422e-05,
|
| 2129 |
+
"loss": 1.3435,
|
| 2130 |
+
"step": 1475
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 6.759725400457666,
|
| 2134 |
+
"grad_norm": 0.23250797390937805,
|
| 2135 |
+
"learning_rate": 5.650860813791785e-05,
|
| 2136 |
+
"loss": 1.3576,
|
| 2137 |
+
"step": 1480
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 6.782608695652174,
|
| 2141 |
+
"grad_norm": 0.23260493576526642,
|
| 2142 |
+
"learning_rate": 5.5789082990409945e-05,
|
| 2143 |
+
"loss": 1.3648,
|
| 2144 |
+
"step": 1485
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 6.805491990846682,
|
| 2148 |
+
"grad_norm": 0.23065823316574097,
|
| 2149 |
+
"learning_rate": 5.507239164130501e-05,
|
| 2150 |
+
"loss": 1.3553,
|
| 2151 |
+
"step": 1490
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 6.82837528604119,
|
| 2155 |
+
"grad_norm": 0.22898992896080017,
|
| 2156 |
+
"learning_rate": 5.4358580028550896e-05,
|
| 2157 |
+
"loss": 1.357,
|
| 2158 |
+
"step": 1495
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 6.851258581235698,
|
| 2162 |
+
"grad_norm": 0.24019262194633484,
|
| 2163 |
+
"learning_rate": 5.364769390551225e-05,
|
| 2164 |
+
"loss": 1.3561,
|
| 2165 |
+
"step": 1500
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 6.874141876430206,
|
| 2169 |
+
"grad_norm": 0.24061718583106995,
|
| 2170 |
+
"learning_rate": 5.293977883803797e-05,
|
| 2171 |
+
"loss": 1.3654,
|
| 2172 |
+
"step": 1505
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 6.897025171624714,
|
| 2176 |
+
"grad_norm": 0.2238311618566513,
|
| 2177 |
+
"learning_rate": 5.2234880201540284e-05,
|
| 2178 |
+
"loss": 1.3542,
|
| 2179 |
+
"step": 1510
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 6.919908466819222,
|
| 2183 |
+
"grad_norm": 0.22695277631282806,
|
| 2184 |
+
"learning_rate": 5.1533043178086536e-05,
|
| 2185 |
+
"loss": 1.354,
|
| 2186 |
+
"step": 1515
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 6.94279176201373,
|
| 2190 |
+
"grad_norm": 0.22949448227882385,
|
| 2191 |
+
"learning_rate": 5.0834312753503124e-05,
|
| 2192 |
+
"loss": 1.3613,
|
| 2193 |
+
"step": 1520
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 6.965675057208238,
|
| 2197 |
+
"grad_norm": 0.23366492986679077,
|
| 2198 |
+
"learning_rate": 5.0138733714492e-05,
|
| 2199 |
+
"loss": 1.3497,
|
| 2200 |
+
"step": 1525
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 6.988558352402746,
|
| 2204 |
+
"grad_norm": 0.2318800687789917,
|
| 2205 |
+
"learning_rate": 4.9446350645759885e-05,
|
| 2206 |
+
"loss": 1.3509,
|
| 2207 |
+
"step": 1530
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 7.0,
|
| 2211 |
+
"eval_loss": 2.50384783744812,
|
| 2212 |
+
"eval_runtime": 0.1625,
|
| 2213 |
+
"eval_samples_per_second": 61.536,
|
| 2214 |
+
"eval_steps_per_second": 6.154,
|
| 2215 |
+
"step": 1533
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 7.009153318077804,
|
| 2219 |
+
"grad_norm": 0.24519094824790955,
|
| 2220 |
+
"learning_rate": 4.8757207927160584e-05,
|
| 2221 |
+
"loss": 1.3595,
|
| 2222 |
+
"step": 1535
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 7.032036613272311,
|
| 2226 |
+
"grad_norm": 0.23380842804908752,
|
| 2227 |
+
"learning_rate": 4.807134973085036e-05,
|
| 2228 |
+
"loss": 1.3402,
|
| 2229 |
+
"step": 1540
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 7.054919908466819,
|
| 2233 |
+
"grad_norm": 0.23818600177764893,
|
| 2234 |
+
"learning_rate": 4.738882001845668e-05,
|
| 2235 |
+
"loss": 1.3542,
|
| 2236 |
+
"step": 1545
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 7.077803203661327,
|
| 2240 |
+
"grad_norm": 0.2337319701910019,
|
| 2241 |
+
"learning_rate": 4.6709662538260267e-05,
|
| 2242 |
+
"loss": 1.3603,
|
| 2243 |
+
"step": 1550
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 7.100686498855835,
|
| 2247 |
+
"grad_norm": 0.23182658851146698,
|
| 2248 |
+
"learning_rate": 4.603392082239102e-05,
|
| 2249 |
+
"loss": 1.3513,
|
| 2250 |
+
"step": 1555
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 7.1235697940503435,
|
| 2254 |
+
"grad_norm": 0.22734318673610687,
|
| 2255 |
+
"learning_rate": 4.53616381840377e-05,
|
| 2256 |
+
"loss": 1.3515,
|
| 2257 |
+
"step": 1560
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 7.146453089244852,
|
| 2261 |
+
"grad_norm": 0.2282598614692688,
|
| 2262 |
+
"learning_rate": 4.469285771467181e-05,
|
| 2263 |
+
"loss": 1.3529,
|
| 2264 |
+
"step": 1565
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 7.169336384439359,
|
| 2268 |
+
"grad_norm": 0.23265138268470764,
|
| 2269 |
+
"learning_rate": 4.402762228128531e-05,
|
| 2270 |
+
"loss": 1.3513,
|
| 2271 |
+
"step": 1570
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 7.192219679633867,
|
| 2275 |
+
"grad_norm": 0.23814916610717773,
|
| 2276 |
+
"learning_rate": 4.336597452364309e-05,
|
| 2277 |
+
"loss": 1.3459,
|
| 2278 |
+
"step": 1575
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 7.215102974828375,
|
| 2282 |
+
"grad_norm": 0.23314997553825378,
|
| 2283 |
+
"learning_rate": 4.2707956851550016e-05,
|
| 2284 |
+
"loss": 1.351,
|
| 2285 |
+
"step": 1580
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 7.237986270022883,
|
| 2289 |
+
"grad_norm": 0.2370002567768097,
|
| 2290 |
+
"learning_rate": 4.205361144213227e-05,
|
| 2291 |
+
"loss": 1.3552,
|
| 2292 |
+
"step": 1585
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 7.260869565217392,
|
| 2296 |
+
"grad_norm": 0.2338656485080719,
|
| 2297 |
+
"learning_rate": 4.140298023713416e-05,
|
| 2298 |
+
"loss": 1.3598,
|
| 2299 |
+
"step": 1590
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 7.2837528604119,
|
| 2303 |
+
"grad_norm": 0.2293270081281662,
|
| 2304 |
+
"learning_rate": 4.075610494022964e-05,
|
| 2305 |
+
"loss": 1.3565,
|
| 2306 |
+
"step": 1595
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 7.306636155606407,
|
| 2310 |
+
"grad_norm": 0.23523476719856262,
|
| 2311 |
+
"learning_rate": 4.011302701434937e-05,
|
| 2312 |
+
"loss": 1.3545,
|
| 2313 |
+
"step": 1600
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 7.329519450800915,
|
| 2317 |
+
"grad_norm": 0.22826853394508362,
|
| 2318 |
+
"learning_rate": 3.947378767902284e-05,
|
| 2319 |
+
"loss": 1.3411,
|
| 2320 |
+
"step": 1605
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 7.352402745995423,
|
| 2324 |
+
"grad_norm": 0.24477452039718628,
|
| 2325 |
+
"learning_rate": 3.8838427907736476e-05,
|
| 2326 |
+
"loss": 1.3482,
|
| 2327 |
+
"step": 1610
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 7.3752860411899315,
|
| 2331 |
+
"grad_norm": 0.23173397779464722,
|
| 2332 |
+
"learning_rate": 3.8206988425307246e-05,
|
| 2333 |
+
"loss": 1.3602,
|
| 2334 |
+
"step": 1615
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 7.39816933638444,
|
| 2338 |
+
"grad_norm": 0.2321847528219223,
|
| 2339 |
+
"learning_rate": 3.757950970527249e-05,
|
| 2340 |
+
"loss": 1.3572,
|
| 2341 |
+
"step": 1620
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 7.421052631578947,
|
| 2345 |
+
"grad_norm": 0.2273811548948288,
|
| 2346 |
+
"learning_rate": 3.695603196729543e-05,
|
| 2347 |
+
"loss": 1.3575,
|
| 2348 |
+
"step": 1625
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 7.443935926773455,
|
| 2352 |
+
"grad_norm": 0.22913090884685516,
|
| 2353 |
+
"learning_rate": 3.633659517458736e-05,
|
| 2354 |
+
"loss": 1.3566,
|
| 2355 |
+
"step": 1630
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 7.466819221967963,
|
| 2359 |
+
"grad_norm": 0.23222309350967407,
|
| 2360 |
+
"learning_rate": 3.5721239031346066e-05,
|
| 2361 |
+
"loss": 1.3461,
|
| 2362 |
+
"step": 1635
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 7.489702517162471,
|
| 2366 |
+
"grad_norm": 0.2386443018913269,
|
| 2367 |
+
"learning_rate": 3.5110002980210975e-05,
|
| 2368 |
+
"loss": 1.3335,
|
| 2369 |
+
"step": 1640
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 7.5125858123569795,
|
| 2373 |
+
"grad_norm": 0.23243063688278198,
|
| 2374 |
+
"learning_rate": 3.450292619973483e-05,
|
| 2375 |
+
"loss": 1.3497,
|
| 2376 |
+
"step": 1645
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 7.535469107551488,
|
| 2380 |
+
"grad_norm": 0.22777137160301208,
|
| 2381 |
+
"learning_rate": 3.3900047601872596e-05,
|
| 2382 |
+
"loss": 1.3526,
|
| 2383 |
+
"step": 1650
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 7.558352402745996,
|
| 2387 |
+
"grad_norm": 0.23459511995315552,
|
| 2388 |
+
"learning_rate": 3.3301405829487195e-05,
|
| 2389 |
+
"loss": 1.3484,
|
| 2390 |
+
"step": 1655
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 7.581235697940503,
|
| 2394 |
+
"grad_norm": 0.22907888889312744,
|
| 2395 |
+
"learning_rate": 3.270703925387279e-05,
|
| 2396 |
+
"loss": 1.3529,
|
| 2397 |
+
"step": 1660
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 7.604118993135011,
|
| 2401 |
+
"grad_norm": 0.22607311606407166,
|
| 2402 |
+
"learning_rate": 3.2116985972295076e-05,
|
| 2403 |
+
"loss": 1.3557,
|
| 2404 |
+
"step": 1665
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 7.627002288329519,
|
| 2408 |
+
"grad_norm": 0.2280961275100708,
|
| 2409 |
+
"learning_rate": 3.153128380554941e-05,
|
| 2410 |
+
"loss": 1.3485,
|
| 2411 |
+
"step": 1670
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 7.649885583524028,
|
| 2415 |
+
"grad_norm": 0.22796593606472015,
|
| 2416 |
+
"learning_rate": 3.094997029553673e-05,
|
| 2417 |
+
"loss": 1.3524,
|
| 2418 |
+
"step": 1675
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 7.672768878718536,
|
| 2422 |
+
"grad_norm": 0.22574880719184875,
|
| 2423 |
+
"learning_rate": 3.037308270285709e-05,
|
| 2424 |
+
"loss": 1.3415,
|
| 2425 |
+
"step": 1680
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 7.695652173913043,
|
| 2429 |
+
"grad_norm": 0.22538483142852783,
|
| 2430 |
+
"learning_rate": 2.9800658004421366e-05,
|
| 2431 |
+
"loss": 1.3584,
|
| 2432 |
+
"step": 1685
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 7.718535469107551,
|
| 2436 |
+
"grad_norm": 0.22863738238811493,
|
| 2437 |
+
"learning_rate": 2.923273289108115e-05,
|
| 2438 |
+
"loss": 1.3555,
|
| 2439 |
+
"step": 1690
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 7.741418764302059,
|
| 2443 |
+
"grad_norm": 0.23403213918209076,
|
| 2444 |
+
"learning_rate": 2.8669343765277078e-05,
|
| 2445 |
+
"loss": 1.3455,
|
| 2446 |
+
"step": 1695
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 7.7643020594965675,
|
| 2450 |
+
"grad_norm": 0.23343510925769806,
|
| 2451 |
+
"learning_rate": 2.8110526738705344e-05,
|
| 2452 |
+
"loss": 1.3472,
|
| 2453 |
+
"step": 1700
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 7.787185354691076,
|
| 2457 |
+
"grad_norm": 0.2283450961112976,
|
| 2458 |
+
"learning_rate": 2.755631763000318e-05,
|
| 2459 |
+
"loss": 1.3594,
|
| 2460 |
+
"step": 1705
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 7.810068649885584,
|
| 2464 |
+
"grad_norm": 0.2360517978668213,
|
| 2465 |
+
"learning_rate": 2.7006751962452882e-05,
|
| 2466 |
+
"loss": 1.347,
|
| 2467 |
+
"step": 1710
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 7.832951945080092,
|
| 2471 |
+
"grad_norm": 0.2376154214143753,
|
| 2472 |
+
"learning_rate": 2.6461864961704975e-05,
|
| 2473 |
+
"loss": 1.3532,
|
| 2474 |
+
"step": 1715
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 7.855835240274599,
|
| 2478 |
+
"grad_norm": 0.23671028017997742,
|
| 2479 |
+
"learning_rate": 2.592169155352031e-05,
|
| 2480 |
+
"loss": 1.3589,
|
| 2481 |
+
"step": 1720
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 7.878718535469107,
|
| 2485 |
+
"grad_norm": 0.23020578920841217,
|
| 2486 |
+
"learning_rate": 2.538626636153131e-05,
|
| 2487 |
+
"loss": 1.3527,
|
| 2488 |
+
"step": 1725
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 7.9016018306636155,
|
| 2492 |
+
"grad_norm": 0.2411489188671112,
|
| 2493 |
+
"learning_rate": 2.485562370502279e-05,
|
| 2494 |
+
"loss": 1.3508,
|
| 2495 |
+
"step": 1730
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 7.924485125858124,
|
| 2499 |
+
"grad_norm": 0.23260930180549622,
|
| 2500 |
+
"learning_rate": 2.4329797596732252e-05,
|
| 2501 |
+
"loss": 1.3446,
|
| 2502 |
+
"step": 1735
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 7.947368421052632,
|
| 2506 |
+
"grad_norm": 0.23165710270404816,
|
| 2507 |
+
"learning_rate": 2.3808821740669606e-05,
|
| 2508 |
+
"loss": 1.357,
|
| 2509 |
+
"step": 1740
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 7.970251716247139,
|
| 2513 |
+
"grad_norm": 0.240895077586174,
|
| 2514 |
+
"learning_rate": 2.3292729529956935e-05,
|
| 2515 |
+
"loss": 1.3631,
|
| 2516 |
+
"step": 1745
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 7.993135011441647,
|
| 2520 |
+
"grad_norm": 0.2322818636894226,
|
| 2521 |
+
"learning_rate": 2.2781554044688015e-05,
|
| 2522 |
+
"loss": 1.3413,
|
| 2523 |
+
"step": 1750
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 8.0,
|
| 2527 |
+
"eval_loss": 2.5123343467712402,
|
| 2528 |
+
"eval_runtime": 0.1598,
|
| 2529 |
+
"eval_samples_per_second": 62.575,
|
| 2530 |
+
"eval_steps_per_second": 6.258,
|
| 2531 |
+
"step": 1752
|
| 2532 |
+
},
|
| 2533 |
+
{
|
| 2534 |
+
"epoch": 8.013729977116705,
|
| 2535 |
+
"grad_norm": 0.22951894998550415,
|
| 2536 |
+
"learning_rate": 2.227532804980813e-05,
|
| 2537 |
+
"loss": 1.3476,
|
| 2538 |
+
"step": 1755
|
| 2539 |
+
},
|
| 2540 |
+
{
|
| 2541 |
+
"epoch": 8.036613272311213,
|
| 2542 |
+
"grad_norm": 0.23239345848560333,
|
| 2543 |
+
"learning_rate": 2.1774083993013718e-05,
|
| 2544 |
+
"loss": 1.344,
|
| 2545 |
+
"step": 1760
|
| 2546 |
+
},
|
| 2547 |
+
{
|
| 2548 |
+
"epoch": 8.05949656750572,
|
| 2549 |
+
"grad_norm": 0.23161360621452332,
|
| 2550 |
+
"learning_rate": 2.1277854002672683e-05,
|
| 2551 |
+
"loss": 1.3465,
|
| 2552 |
+
"step": 1765
|
| 2553 |
+
},
|
| 2554 |
+
{
|
| 2555 |
+
"epoch": 8.082379862700229,
|
| 2556 |
+
"grad_norm": 0.24183310568332672,
|
| 2557 |
+
"learning_rate": 2.078666988576504e-05,
|
| 2558 |
+
"loss": 1.3395,
|
| 2559 |
+
"step": 1770
|
| 2560 |
+
},
|
| 2561 |
+
{
|
| 2562 |
+
"epoch": 8.105263157894736,
|
| 2563 |
+
"grad_norm": 0.23045741021633148,
|
| 2564 |
+
"learning_rate": 2.030056312584424e-05,
|
| 2565 |
+
"loss": 1.3489,
|
| 2566 |
+
"step": 1775
|
| 2567 |
+
},
|
| 2568 |
+
{
|
| 2569 |
+
"epoch": 8.128146453089245,
|
| 2570 |
+
"grad_norm": 0.23021478950977325,
|
| 2571 |
+
"learning_rate": 1.9819564881018983e-05,
|
| 2572 |
+
"loss": 1.3461,
|
| 2573 |
+
"step": 1780
|
| 2574 |
+
},
|
| 2575 |
+
{
|
| 2576 |
+
"epoch": 8.151029748283753,
|
| 2577 |
+
"grad_norm": 0.22722554206848145,
|
| 2578 |
+
"learning_rate": 1.934370598195622e-05,
|
| 2579 |
+
"loss": 1.344,
|
| 2580 |
+
"step": 1785
|
| 2581 |
+
},
|
| 2582 |
+
{
|
| 2583 |
+
"epoch": 8.173913043478262,
|
| 2584 |
+
"grad_norm": 0.23223134875297546,
|
| 2585 |
+
"learning_rate": 1.887301692990494e-05,
|
| 2586 |
+
"loss": 1.3585,
|
| 2587 |
+
"step": 1790
|
| 2588 |
+
},
|
| 2589 |
+
{
|
| 2590 |
+
"epoch": 8.196796338672769,
|
| 2591 |
+
"grad_norm": 0.2324499934911728,
|
| 2592 |
+
"learning_rate": 1.8407527894741184e-05,
|
| 2593 |
+
"loss": 1.3466,
|
| 2594 |
+
"step": 1795
|
| 2595 |
+
},
|
| 2596 |
+
{
|
| 2597 |
+
"epoch": 8.219679633867276,
|
| 2598 |
+
"grad_norm": 0.23666158318519592,
|
| 2599 |
+
"learning_rate": 1.7947268713034127e-05,
|
| 2600 |
+
"loss": 1.3353,
|
| 2601 |
+
"step": 1800
|
| 2602 |
+
},
|
| 2603 |
+
{
|
| 2604 |
+
"epoch": 8.242562929061785,
|
| 2605 |
+
"grad_norm": 0.2395636886358261,
|
| 2606 |
+
"learning_rate": 1.7492268886133676e-05,
|
| 2607 |
+
"loss": 1.3312,
|
| 2608 |
+
"step": 1805
|
| 2609 |
+
},
|
| 2610 |
+
{
|
| 2611 |
+
"epoch": 8.265446224256292,
|
| 2612 |
+
"grad_norm": 0.23455668985843658,
|
| 2613 |
+
"learning_rate": 1.7042557578279626e-05,
|
| 2614 |
+
"loss": 1.3536,
|
| 2615 |
+
"step": 1810
|
| 2616 |
+
},
|
| 2617 |
+
{
|
| 2618 |
+
"epoch": 8.288329519450802,
|
| 2619 |
+
"grad_norm": 0.24188482761383057,
|
| 2620 |
+
"learning_rate": 1.6598163614732154e-05,
|
| 2621 |
+
"loss": 1.3592,
|
| 2622 |
+
"step": 1815
|
| 2623 |
+
},
|
| 2624 |
+
{
|
| 2625 |
+
"epoch": 8.311212814645309,
|
| 2626 |
+
"grad_norm": 0.23694472014904022,
|
| 2627 |
+
"learning_rate": 1.6159115479924257e-05,
|
| 2628 |
+
"loss": 1.3485,
|
| 2629 |
+
"step": 1820
|
| 2630 |
+
},
|
| 2631 |
+
{
|
| 2632 |
+
"epoch": 8.334096109839816,
|
| 2633 |
+
"grad_norm": 0.2400536835193634,
|
| 2634 |
+
"learning_rate": 1.5725441315636002e-05,
|
| 2635 |
+
"loss": 1.3387,
|
| 2636 |
+
"step": 1825
|
| 2637 |
+
},
|
| 2638 |
+
{
|
| 2639 |
+
"epoch": 8.356979405034325,
|
| 2640 |
+
"grad_norm": 0.2341165691614151,
|
| 2641 |
+
"learning_rate": 1.529716891919074e-05,
|
| 2642 |
+
"loss": 1.3429,
|
| 2643 |
+
"step": 1830
|
| 2644 |
+
},
|
| 2645 |
+
{
|
| 2646 |
+
"epoch": 8.379862700228832,
|
| 2647 |
+
"grad_norm": 0.23209024965763092,
|
| 2648 |
+
"learning_rate": 1.4874325741673278e-05,
|
| 2649 |
+
"loss": 1.3537,
|
| 2650 |
+
"step": 1835
|
| 2651 |
+
},
|
| 2652 |
+
{
|
| 2653 |
+
"epoch": 8.402745995423341,
|
| 2654 |
+
"grad_norm": 0.2267337441444397,
|
| 2655 |
+
"learning_rate": 1.4456938886170412e-05,
|
| 2656 |
+
"loss": 1.3432,
|
| 2657 |
+
"step": 1840
|
| 2658 |
+
},
|
| 2659 |
+
{
|
| 2660 |
+
"epoch": 8.425629290617849,
|
| 2661 |
+
"grad_norm": 0.22982369363307953,
|
| 2662 |
+
"learning_rate": 1.4045035106033655e-05,
|
| 2663 |
+
"loss": 1.3401,
|
| 2664 |
+
"step": 1845
|
| 2665 |
+
},
|
| 2666 |
+
{
|
| 2667 |
+
"epoch": 8.448512585812358,
|
| 2668 |
+
"grad_norm": 0.23104478418827057,
|
| 2669 |
+
"learning_rate": 1.3638640803164516e-05,
|
| 2670 |
+
"loss": 1.3481,
|
| 2671 |
+
"step": 1850
|
| 2672 |
+
},
|
| 2673 |
+
{
|
| 2674 |
+
"epoch": 8.471395881006865,
|
| 2675 |
+
"grad_norm": 0.22922466695308685,
|
| 2676 |
+
"learning_rate": 1.3237782026322055e-05,
|
| 2677 |
+
"loss": 1.3548,
|
| 2678 |
+
"step": 1855
|
| 2679 |
+
},
|
| 2680 |
+
{
|
| 2681 |
+
"epoch": 8.494279176201372,
|
| 2682 |
+
"grad_norm": 0.2303161472082138,
|
| 2683 |
+
"learning_rate": 1.2842484469453365e-05,
|
| 2684 |
+
"loss": 1.3461,
|
| 2685 |
+
"step": 1860
|
| 2686 |
+
},
|
| 2687 |
+
{
|
| 2688 |
+
"epoch": 8.517162471395881,
|
| 2689 |
+
"grad_norm": 0.23580402135849,
|
| 2690 |
+
"learning_rate": 1.2452773470046541e-05,
|
| 2691 |
+
"loss": 1.3517,
|
| 2692 |
+
"step": 1865
|
| 2693 |
+
},
|
| 2694 |
+
{
|
| 2695 |
+
"epoch": 8.540045766590389,
|
| 2696 |
+
"grad_norm": 0.2284560203552246,
|
| 2697 |
+
"learning_rate": 1.2068674007506786e-05,
|
| 2698 |
+
"loss": 1.34,
|
| 2699 |
+
"step": 1870
|
| 2700 |
+
},
|
| 2701 |
+
{
|
| 2702 |
+
"epoch": 8.562929061784898,
|
| 2703 |
+
"grad_norm": 0.23408174514770508,
|
| 2704 |
+
"learning_rate": 1.1690210701555104e-05,
|
| 2705 |
+
"loss": 1.3382,
|
| 2706 |
+
"step": 1875
|
| 2707 |
+
},
|
| 2708 |
+
{
|
| 2709 |
+
"epoch": 8.585812356979405,
|
| 2710 |
+
"grad_norm": 0.22775082290172577,
|
| 2711 |
+
"learning_rate": 1.1317407810650372e-05,
|
| 2712 |
+
"loss": 1.3533,
|
| 2713 |
+
"step": 1880
|
| 2714 |
+
},
|
| 2715 |
+
{
|
| 2716 |
+
"epoch": 8.608695652173914,
|
| 2717 |
+
"grad_norm": 0.23187576234340668,
|
| 2718 |
+
"learning_rate": 1.0950289230434374e-05,
|
| 2719 |
+
"loss": 1.342,
|
| 2720 |
+
"step": 1885
|
| 2721 |
+
},
|
| 2722 |
+
{
|
| 2723 |
+
"epoch": 8.631578947368421,
|
| 2724 |
+
"grad_norm": 0.23138730227947235,
|
| 2725 |
+
"learning_rate": 1.058887849220026e-05,
|
| 2726 |
+
"loss": 1.3571,
|
| 2727 |
+
"step": 1890
|
| 2728 |
+
},
|
| 2729 |
+
{
|
| 2730 |
+
"epoch": 8.654462242562929,
|
| 2731 |
+
"grad_norm": 0.2307848185300827,
|
| 2732 |
+
"learning_rate": 1.02331987613841e-05,
|
| 2733 |
+
"loss": 1.3525,
|
| 2734 |
+
"step": 1895
|
| 2735 |
+
},
|
| 2736 |
+
{
|
| 2737 |
+
"epoch": 8.677345537757438,
|
| 2738 |
+
"grad_norm": 0.2283322662115097,
|
| 2739 |
+
"learning_rate": 9.883272836080116e-06,
|
| 2740 |
+
"loss": 1.3472,
|
| 2741 |
+
"step": 1900
|
| 2742 |
+
},
|
| 2743 |
+
{
|
| 2744 |
+
"epoch": 8.700228832951945,
|
| 2745 |
+
"grad_norm": 0.22654347121715546,
|
| 2746 |
+
"learning_rate": 9.539123145579476e-06,
|
| 2747 |
+
"loss": 1.3477,
|
| 2748 |
+
"step": 1905
|
| 2749 |
+
},
|
| 2750 |
+
{
|
| 2751 |
+
"epoch": 8.723112128146454,
|
| 2752 |
+
"grad_norm": 0.23034285008907318,
|
| 2753 |
+
"learning_rate": 9.200771748932513e-06,
|
| 2754 |
+
"loss": 1.345,
|
| 2755 |
+
"step": 1910
|
| 2756 |
+
},
|
| 2757 |
+
{
|
| 2758 |
+
"epoch": 8.745995423340961,
|
| 2759 |
+
"grad_norm": 0.23074457049369812,
|
| 2760 |
+
"learning_rate": 8.868240333534815e-06,
|
| 2761 |
+
"loss": 1.3389,
|
| 2762 |
+
"step": 1915
|
| 2763 |
+
},
|
| 2764 |
+
{
|
| 2765 |
+
"epoch": 8.768878718535468,
|
| 2766 |
+
"grad_norm": 0.22868825495243073,
|
| 2767 |
+
"learning_rate": 8.541550213737171e-06,
|
| 2768 |
+
"loss": 1.3417,
|
| 2769 |
+
"step": 1920
|
| 2770 |
+
},
|
| 2771 |
+
{
|
| 2772 |
+
"epoch": 8.791762013729977,
|
| 2773 |
+
"grad_norm": 0.22654058039188385,
|
| 2774 |
+
"learning_rate": 8.220722329479346e-06,
|
| 2775 |
+
"loss": 1.3458,
|
| 2776 |
+
"step": 1925
|
| 2777 |
+
},
|
| 2778 |
+
{
|
| 2779 |
+
"epoch": 8.814645308924485,
|
| 2780 |
+
"grad_norm": 0.22552727162837982,
|
| 2781 |
+
"learning_rate": 7.905777244947954e-06,
|
| 2782 |
+
"loss": 1.3444,
|
| 2783 |
+
"step": 1930
|
| 2784 |
+
},
|
| 2785 |
+
{
|
| 2786 |
+
"epoch": 8.837528604118994,
|
| 2787 |
+
"grad_norm": 0.22772538661956787,
|
| 2788 |
+
"learning_rate": 7.5967351472582275e-06,
|
| 2789 |
+
"loss": 1.355,
|
| 2790 |
+
"step": 1935
|
| 2791 |
+
},
|
| 2792 |
+
{
|
| 2793 |
+
"epoch": 8.860411899313501,
|
| 2794 |
+
"grad_norm": 0.2261328399181366,
|
| 2795 |
+
"learning_rate": 7.293615845160196e-06,
|
| 2796 |
+
"loss": 1.3314,
|
| 2797 |
+
"step": 1940
|
| 2798 |
+
},
|
| 2799 |
+
{
|
| 2800 |
+
"epoch": 8.883295194508008,
|
| 2801 |
+
"grad_norm": 0.23299558460712433,
|
| 2802 |
+
"learning_rate": 6.99643876776891e-06,
|
| 2803 |
+
"loss": 1.3461,
|
| 2804 |
+
"step": 1945
|
| 2805 |
+
},
|
| 2806 |
+
{
|
| 2807 |
+
"epoch": 8.906178489702517,
|
| 2808 |
+
"grad_norm": 0.22399510443210602,
|
| 2809 |
+
"learning_rate": 6.705222963319191e-06,
|
| 2810 |
+
"loss": 1.3412,
|
| 2811 |
+
"step": 1950
|
| 2812 |
+
},
|
| 2813 |
+
{
|
| 2814 |
+
"epoch": 8.929061784897025,
|
| 2815 |
+
"grad_norm": 0.22913098335266113,
|
| 2816 |
+
"learning_rate": 6.419987097944579e-06,
|
| 2817 |
+
"loss": 1.3519,
|
| 2818 |
+
"step": 1955
|
| 2819 |
+
},
|
| 2820 |
+
{
|
| 2821 |
+
"epoch": 8.951945080091534,
|
| 2822 |
+
"grad_norm": 0.22438156604766846,
|
| 2823 |
+
"learning_rate": 6.140749454480932e-06,
|
| 2824 |
+
"loss": 1.3513,
|
| 2825 |
+
"step": 1960
|
| 2826 |
+
},
|
| 2827 |
+
{
|
| 2828 |
+
"epoch": 8.974828375286041,
|
| 2829 |
+
"grad_norm": 0.23290272057056427,
|
| 2830 |
+
"learning_rate": 5.867527931294614e-06,
|
| 2831 |
+
"loss": 1.3495,
|
| 2832 |
+
"step": 1965
|
| 2833 |
+
},
|
| 2834 |
+
{
|
| 2835 |
+
"epoch": 8.99771167048055,
|
| 2836 |
+
"grad_norm": 0.2285740226507187,
|
| 2837 |
+
"learning_rate": 5.6003400411351325e-06,
|
| 2838 |
+
"loss": 1.3562,
|
| 2839 |
+
"step": 1970
|
| 2840 |
+
},
|
| 2841 |
+
{
|
| 2842 |
+
"epoch": 9.0,
|
| 2843 |
+
"eval_loss": 2.517554998397827,
|
| 2844 |
+
"eval_runtime": 0.1572,
|
| 2845 |
+
"eval_samples_per_second": 63.605,
|
| 2846 |
+
"eval_steps_per_second": 6.36,
|
| 2847 |
+
"step": 1971
|
| 2848 |
+
},
|
| 2849 |
+
{
|
| 2850 |
+
"epoch": 9.018306636155607,
|
| 2851 |
+
"grad_norm": 0.22652767598628998,
|
| 2852 |
+
"learning_rate": 5.339202910012708e-06,
|
| 2853 |
+
"loss": 1.3499,
|
| 2854 |
+
"step": 1975
|
| 2855 |
+
},
|
| 2856 |
+
{
|
| 2857 |
+
"epoch": 9.041189931350115,
|
| 2858 |
+
"grad_norm": 0.2265496850013733,
|
| 2859 |
+
"learning_rate": 5.0841332761005e-06,
|
| 2860 |
+
"loss": 1.3514,
|
| 2861 |
+
"step": 1980
|
| 2862 |
+
},
|
| 2863 |
+
{
|
| 2864 |
+
"epoch": 9.064073226544622,
|
| 2865 |
+
"grad_norm": 0.22489045560359955,
|
| 2866 |
+
"learning_rate": 4.835147488661795e-06,
|
| 2867 |
+
"loss": 1.3402,
|
| 2868 |
+
"step": 1985
|
| 2869 |
+
},
|
| 2870 |
+
{
|
| 2871 |
+
"epoch": 9.08695652173913,
|
| 2872 |
+
"grad_norm": 0.23145288228988647,
|
| 2873 |
+
"learning_rate": 4.592261507001993e-06,
|
| 2874 |
+
"loss": 1.343,
|
| 2875 |
+
"step": 1990
|
| 2876 |
+
},
|
| 2877 |
+
{
|
| 2878 |
+
"epoch": 9.109839816933638,
|
| 2879 |
+
"grad_norm": 0.228094220161438,
|
| 2880 |
+
"learning_rate": 4.355490899445691e-06,
|
| 2881 |
+
"loss": 1.3422,
|
| 2882 |
+
"step": 1995
|
| 2883 |
+
},
|
| 2884 |
+
{
|
| 2885 |
+
"epoch": 9.132723112128147,
|
| 2886 |
+
"grad_norm": 0.23417501151561737,
|
| 2887 |
+
"learning_rate": 4.124850842338779e-06,
|
| 2888 |
+
"loss": 1.3512,
|
| 2889 |
+
"step": 2000
|
| 2890 |
+
},
|
| 2891 |
+
{
|
| 2892 |
+
"epoch": 9.155606407322654,
|
| 2893 |
+
"grad_norm": 0.2259424477815628,
|
| 2894 |
+
"learning_rate": 3.900356119075743e-06,
|
| 2895 |
+
"loss": 1.3428,
|
| 2896 |
+
"step": 2005
|
| 2897 |
+
},
|
| 2898 |
+
{
|
| 2899 |
+
"epoch": 9.178489702517162,
|
| 2900 |
+
"grad_norm": 0.22936026751995087,
|
| 2901 |
+
"learning_rate": 3.6820211191520125e-06,
|
| 2902 |
+
"loss": 1.343,
|
| 2903 |
+
"step": 2010
|
| 2904 |
+
},
|
| 2905 |
+
{
|
| 2906 |
+
"epoch": 9.20137299771167,
|
| 2907 |
+
"grad_norm": 0.2265051156282425,
|
| 2908 |
+
"learning_rate": 3.469859837241651e-06,
|
| 2909 |
+
"loss": 1.3517,
|
| 2910 |
+
"step": 2015
|
| 2911 |
+
},
|
| 2912 |
+
{
|
| 2913 |
+
"epoch": 9.224256292906178,
|
| 2914 |
+
"grad_norm": 0.22797267138957977,
|
| 2915 |
+
"learning_rate": 3.263885872300343e-06,
|
| 2916 |
+
"loss": 1.3497,
|
| 2917 |
+
"step": 2020
|
| 2918 |
+
},
|
| 2919 |
+
{
|
| 2920 |
+
"epoch": 9.247139588100687,
|
| 2921 |
+
"grad_norm": 0.2263391762971878,
|
| 2922 |
+
"learning_rate": 3.064112426693799e-06,
|
| 2923 |
+
"loss": 1.3381,
|
| 2924 |
+
"step": 2025
|
| 2925 |
+
},
|
| 2926 |
+
{
|
| 2927 |
+
"epoch": 9.270022883295194,
|
| 2928 |
+
"grad_norm": 0.23144488036632538,
|
| 2929 |
+
"learning_rate": 2.8705523053513816e-06,
|
| 2930 |
+
"loss": 1.3453,
|
| 2931 |
+
"step": 2030
|
| 2932 |
+
},
|
| 2933 |
+
{
|
| 2934 |
+
"epoch": 9.292906178489703,
|
| 2935 |
+
"grad_norm": 0.2310468852519989,
|
| 2936 |
+
"learning_rate": 2.6832179149454793e-06,
|
| 2937 |
+
"loss": 1.338,
|
| 2938 |
+
"step": 2035
|
| 2939 |
+
},
|
| 2940 |
+
{
|
| 2941 |
+
"epoch": 9.31578947368421,
|
| 2942 |
+
"grad_norm": 0.2297661006450653,
|
| 2943 |
+
"learning_rate": 2.502121263096224e-06,
|
| 2944 |
+
"loss": 1.3424,
|
| 2945 |
+
"step": 2040
|
| 2946 |
+
},
|
| 2947 |
+
{
|
| 2948 |
+
"epoch": 9.338672768878718,
|
| 2949 |
+
"grad_norm": 0.23045673966407776,
|
| 2950 |
+
"learning_rate": 2.3272739576017945e-06,
|
| 2951 |
+
"loss": 1.3525,
|
| 2952 |
+
"step": 2045
|
| 2953 |
+
},
|
| 2954 |
+
{
|
| 2955 |
+
"epoch": 9.361556064073227,
|
| 2956 |
+
"grad_norm": 0.22856095433235168,
|
| 2957 |
+
"learning_rate": 2.1586872056944428e-06,
|
| 2958 |
+
"loss": 1.3441,
|
| 2959 |
+
"step": 2050
|
| 2960 |
+
},
|
| 2961 |
+
{
|
| 2962 |
+
"epoch": 9.384439359267734,
|
| 2963 |
+
"grad_norm": 0.23274967074394226,
|
| 2964 |
+
"learning_rate": 1.996371813322129e-06,
|
| 2965 |
+
"loss": 1.355,
|
| 2966 |
+
"step": 2055
|
| 2967 |
+
},
|
| 2968 |
+
{
|
| 2969 |
+
"epoch": 9.407322654462243,
|
| 2970 |
+
"grad_norm": 0.22686432301998138,
|
| 2971 |
+
"learning_rate": 1.840338184455881e-06,
|
| 2972 |
+
"loss": 1.341,
|
| 2973 |
+
"step": 2060
|
| 2974 |
+
},
|
| 2975 |
+
{
|
| 2976 |
+
"epoch": 9.43020594965675,
|
| 2977 |
+
"grad_norm": 0.22302532196044922,
|
| 2978 |
+
"learning_rate": 1.6905963204229436e-06,
|
| 2979 |
+
"loss": 1.3573,
|
| 2980 |
+
"step": 2065
|
| 2981 |
+
},
|
| 2982 |
+
{
|
| 2983 |
+
"epoch": 9.453089244851258,
|
| 2984 |
+
"grad_norm": 0.2239583283662796,
|
| 2985 |
+
"learning_rate": 1.5471558192656777e-06,
|
| 2986 |
+
"loss": 1.3357,
|
| 2987 |
+
"step": 2070
|
| 2988 |
+
},
|
| 2989 |
+
{
|
| 2990 |
+
"epoch": 9.475972540045767,
|
| 2991 |
+
"grad_norm": 0.22839844226837158,
|
| 2992 |
+
"learning_rate": 1.4100258751264195e-06,
|
| 2993 |
+
"loss": 1.3387,
|
| 2994 |
+
"step": 2075
|
| 2995 |
+
},
|
| 2996 |
+
{
|
| 2997 |
+
"epoch": 9.498855835240274,
|
| 2998 |
+
"grad_norm": 0.22954653203487396,
|
| 2999 |
+
"learning_rate": 1.2792152776580968e-06,
|
| 3000 |
+
"loss": 1.3428,
|
| 3001 |
+
"step": 2080
|
| 3002 |
+
},
|
| 3003 |
+
{
|
| 3004 |
+
"epoch": 9.521739130434783,
|
| 3005 |
+
"grad_norm": 0.22747966647148132,
|
| 3006 |
+
"learning_rate": 1.1547324114608904e-06,
|
| 3007 |
+
"loss": 1.3396,
|
| 3008 |
+
"step": 2085
|
| 3009 |
+
},
|
| 3010 |
+
{
|
| 3011 |
+
"epoch": 9.54462242562929,
|
| 3012 |
+
"grad_norm": 0.2284754067659378,
|
| 3013 |
+
"learning_rate": 1.036585255544764e-06,
|
| 3014 |
+
"loss": 1.3472,
|
| 3015 |
+
"step": 2090
|
| 3016 |
+
},
|
| 3017 |
+
{
|
| 3018 |
+
"epoch": 9.5675057208238,
|
| 3019 |
+
"grad_norm": 0.22196947038173676,
|
| 3020 |
+
"learning_rate": 9.247813828180407e-07,
|
| 3021 |
+
"loss": 1.3454,
|
| 3022 |
+
"step": 2095
|
| 3023 |
+
},
|
| 3024 |
+
{
|
| 3025 |
+
"epoch": 9.590389016018307,
|
| 3026 |
+
"grad_norm": 0.22999419271945953,
|
| 3027 |
+
"learning_rate": 8.193279596020121e-07,
|
| 3028 |
+
"loss": 1.3431,
|
| 3029 |
+
"step": 2100
|
| 3030 |
+
},
|
| 3031 |
+
{
|
| 3032 |
+
"epoch": 9.613272311212814,
|
| 3033 |
+
"grad_norm": 0.23028169572353363,
|
| 3034 |
+
"learning_rate": 7.202317451716067e-07,
|
| 3035 |
+
"loss": 1.3277,
|
| 3036 |
+
"step": 2105
|
| 3037 |
+
},
|
| 3038 |
+
{
|
| 3039 |
+
"epoch": 9.636155606407323,
|
| 3040 |
+
"grad_norm": 0.22792372107505798,
|
| 3041 |
+
"learning_rate": 6.274990913221035e-07,
|
| 3042 |
+
"loss": 1.3374,
|
| 3043 |
+
"step": 2110
|
| 3044 |
+
},
|
| 3045 |
+
{
|
| 3046 |
+
"epoch": 9.65903890160183,
|
| 3047 |
+
"grad_norm": 0.22512663900852203,
|
| 3048 |
+
"learning_rate": 5.411359419620232e-07,
|
| 3049 |
+
"loss": 1.3503,
|
| 3050 |
+
"step": 2115
|
| 3051 |
+
},
|
| 3052 |
+
{
|
| 3053 |
+
"epoch": 9.68192219679634,
|
| 3054 |
+
"grad_norm": 0.22875413298606873,
|
| 3055 |
+
"learning_rate": 4.6114783273213393e-07,
|
| 3056 |
+
"loss": 1.3451,
|
| 3057 |
+
"step": 2120
|
| 3058 |
+
},
|
| 3059 |
+
{
|
| 3060 |
+
"epoch": 9.704805491990847,
|
| 3061 |
+
"grad_norm": 0.22629615664482117,
|
| 3062 |
+
"learning_rate": 3.8753989065064557e-07,
|
| 3063 |
+
"loss": 1.3315,
|
| 3064 |
+
"step": 2125
|
| 3065 |
+
},
|
| 3066 |
+
{
|
| 3067 |
+
"epoch": 9.727688787185354,
|
| 3068 |
+
"grad_norm": 0.22211916744709015,
|
| 3069 |
+
"learning_rate": 3.203168337845508e-07,
|
| 3070 |
+
"loss": 1.35,
|
| 3071 |
+
"step": 2130
|
| 3072 |
+
},
|
| 3073 |
+
{
|
| 3074 |
+
"epoch": 9.750572082379863,
|
| 3075 |
+
"grad_norm": 0.22795149683952332,
|
| 3076 |
+
"learning_rate": 2.594829709472446e-07,
|
| 3077 |
+
"loss": 1.3314,
|
| 3078 |
+
"step": 2135
|
| 3079 |
+
},
|
| 3080 |
+
{
|
| 3081 |
+
"epoch": 9.77345537757437,
|
| 3082 |
+
"grad_norm": 0.231648787856102,
|
| 3083 |
+
"learning_rate": 2.05042201422323e-07,
|
| 3084 |
+
"loss": 1.3568,
|
| 3085 |
+
"step": 2140
|
| 3086 |
+
},
|
| 3087 |
+
{
|
| 3088 |
+
"epoch": 9.79633867276888,
|
| 3089 |
+
"grad_norm": 0.22703665494918823,
|
| 3090 |
+
"learning_rate": 1.5699801471364962e-07,
|
| 3091 |
+
"loss": 1.3411,
|
| 3092 |
+
"step": 2145
|
| 3093 |
+
},
|
| 3094 |
+
{
|
| 3095 |
+
"epoch": 9.819221967963387,
|
| 3096 |
+
"grad_norm": 0.2311718612909317,
|
| 3097 |
+
"learning_rate": 1.1535349032167908e-07,
|
| 3098 |
+
"loss": 1.3456,
|
| 3099 |
+
"step": 2150
|
| 3100 |
+
},
|
| 3101 |
+
{
|
| 3102 |
+
"epoch": 9.842105263157894,
|
| 3103 |
+
"grad_norm": 0.2319943606853485,
|
| 3104 |
+
"learning_rate": 8.011129754611491e-08,
|
| 3105 |
+
"loss": 1.3507,
|
| 3106 |
+
"step": 2155
|
| 3107 |
+
},
|
| 3108 |
+
{
|
| 3109 |
+
"epoch": 9.864988558352403,
|
| 3110 |
+
"grad_norm": 0.2376013547182083,
|
| 3111 |
+
"learning_rate": 5.127369531473525e-08,
|
| 3112 |
+
"loss": 1.3372,
|
| 3113 |
+
"step": 2160
|
| 3114 |
+
},
|
| 3115 |
+
{
|
| 3116 |
+
"epoch": 9.88787185354691,
|
| 3117 |
+
"grad_norm": 0.2285187989473343,
|
| 3118 |
+
"learning_rate": 2.884253203869758e-08,
|
| 3119 |
+
"loss": 1.3469,
|
| 3120 |
+
"step": 2165
|
| 3121 |
+
},
|
| 3122 |
+
{
|
| 3123 |
+
"epoch": 9.91075514874142,
|
| 3124 |
+
"grad_norm": 0.22958822548389435,
|
| 3125 |
+
"learning_rate": 1.2819245493955744e-08,
|
| 3126 |
+
"loss": 1.3467,
|
| 3127 |
+
"step": 2170
|
| 3128 |
+
},
|
| 3129 |
+
{
|
| 3130 |
+
"epoch": 9.933638443935926,
|
| 3131 |
+
"grad_norm": 0.22622478008270264,
|
| 3132 |
+
"learning_rate": 3.2048627292113887e-09,
|
| 3133 |
+
"loss": 1.3452,
|
| 3134 |
+
"step": 2175
|
| 3135 |
+
},
|
| 3136 |
+
{
|
| 3137 |
+
"epoch": 9.956521739130435,
|
| 3138 |
+
"grad_norm": 0.2237871289253235,
|
| 3139 |
+
"learning_rate": 0.0,
|
| 3140 |
+
"loss": 1.3538,
|
| 3141 |
+
"step": 2180
|
| 3142 |
+
},
|
| 3143 |
+
{
|
| 3144 |
+
"epoch": 9.956521739130435,
|
| 3145 |
+
"eval_loss": 2.5189335346221924,
|
| 3146 |
+
"eval_runtime": 0.1831,
|
| 3147 |
+
"eval_samples_per_second": 54.615,
|
| 3148 |
+
"eval_steps_per_second": 5.461,
|
| 3149 |
+
"step": 2180
|
| 3150 |
+
},
|
| 3151 |
+
{
|
| 3152 |
+
"epoch": 9.956521739130435,
|
| 3153 |
+
"step": 2180,
|
| 3154 |
+
"total_flos": 2.4191218891641324e+18,
|
| 3155 |
+
"train_loss": 1.418152675716155,
|
| 3156 |
+
"train_runtime": 3547.1741,
|
| 3157 |
+
"train_samples_per_second": 39.395,
|
| 3158 |
+
"train_steps_per_second": 0.615
|
| 3159 |
+
}
|
| 3160 |
+
],
|
| 3161 |
+
"logging_steps": 5,
|
| 3162 |
+
"max_steps": 2180,
|
| 3163 |
+
"num_input_tokens_seen": 0,
|
| 3164 |
+
"num_train_epochs": 10,
|
| 3165 |
+
"save_steps": 100,
|
| 3166 |
+
"stateful_callbacks": {
|
| 3167 |
+
"TrainerControl": {
|
| 3168 |
+
"args": {
|
| 3169 |
+
"should_epoch_stop": false,
|
| 3170 |
+
"should_evaluate": false,
|
| 3171 |
+
"should_log": false,
|
| 3172 |
+
"should_save": true,
|
| 3173 |
+
"should_training_stop": true
|
| 3174 |
+
},
|
| 3175 |
+
"attributes": {}
|
| 3176 |
+
}
|
| 3177 |
+
},
|
| 3178 |
+
"total_flos": 2.4191218891641324e+18,
|
| 3179 |
+
"train_batch_size": 4,
|
| 3180 |
+
"trial_name": null,
|
| 3181 |
+
"trial_params": null
|
| 3182 |
+
}
|