Model save
Browse files- README.md +60 -0
- all_results.json +9 -0
- generation_config.json +6 -0
- runs/Sep27_19-58-10_COE-CS-sv003/events.out.tfevents.1727467471.COE-CS-sv003.928272.0 +2 -2
- train_results.json +9 -0
- trainer_state.json +3444 -0
README.md
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: preference_p0.1_seed42_level2_styledirtybatch16_reverse
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# preference_p0.1_seed42_level2_styledirtybatch16_reverse
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the None dataset.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 1e-05
|
| 39 |
+
- train_batch_size: 4
|
| 40 |
+
- eval_batch_size: 1
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- num_devices: 4
|
| 44 |
+
- total_train_batch_size: 16
|
| 45 |
+
- total_eval_batch_size: 4
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: cosine
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
+
- num_epochs: 1
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
### Framework versions
|
| 56 |
+
|
| 57 |
+
- Transformers 4.45.1
|
| 58 |
+
- Pytorch 2.4.1+cu121
|
| 59 |
+
- Datasets 3.0.1
|
| 60 |
+
- Tokenizers 0.20.0
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 253558763028480.0,
|
| 4 |
+
"train_loss": 0.530042272082643,
|
| 5 |
+
"train_runtime": 21564.4437,
|
| 6 |
+
"train_samples": 98881,
|
| 7 |
+
"train_samples_per_second": 1.797,
|
| 8 |
+
"train_steps_per_second": 0.112
|
| 9 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.45.1"
|
| 6 |
+
}
|
runs/Sep27_19-58-10_COE-CS-sv003/events.out.tfevents.1727467471.COE-CS-sv003.928272.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8ac824a8ba915e5bb0ad51c2841cca89705035efe4a512475ffc884d892dcdd
|
| 3 |
+
size 108645
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 253558763028480.0,
|
| 4 |
+
"train_loss": 0.530042272082643,
|
| 5 |
+
"train_runtime": 21564.4437,
|
| 6 |
+
"train_samples": 98881,
|
| 7 |
+
"train_samples_per_second": 1.797,
|
| 8 |
+
"train_steps_per_second": 0.112
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3444 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2422,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.00041288191577208916,
|
| 13 |
+
"grad_norm": 24.94086805103786,
|
| 14 |
+
"learning_rate": 4.1152263374485605e-08,
|
| 15 |
+
"loss": 1.4345,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.002064409578860446,
|
| 20 |
+
"grad_norm": 24.898038168161193,
|
| 21 |
+
"learning_rate": 2.05761316872428e-07,
|
| 22 |
+
"loss": 1.4101,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.004128819157720892,
|
| 27 |
+
"grad_norm": 15.938300194174698,
|
| 28 |
+
"learning_rate": 4.11522633744856e-07,
|
| 29 |
+
"loss": 1.3943,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.006193228736581338,
|
| 34 |
+
"grad_norm": 8.846886408597587,
|
| 35 |
+
"learning_rate": 6.17283950617284e-07,
|
| 36 |
+
"loss": 1.2771,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.008257638315441783,
|
| 41 |
+
"grad_norm": 9.948610282503696,
|
| 42 |
+
"learning_rate": 8.23045267489712e-07,
|
| 43 |
+
"loss": 1.1572,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.01032204789430223,
|
| 48 |
+
"grad_norm": 4.744946112205854,
|
| 49 |
+
"learning_rate": 1.02880658436214e-06,
|
| 50 |
+
"loss": 1.0575,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.012386457473162676,
|
| 55 |
+
"grad_norm": 3.3793530185545926,
|
| 56 |
+
"learning_rate": 1.234567901234568e-06,
|
| 57 |
+
"loss": 0.9708,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.014450867052023121,
|
| 62 |
+
"grad_norm": 3.4379702794812124,
|
| 63 |
+
"learning_rate": 1.440329218106996e-06,
|
| 64 |
+
"loss": 0.9668,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.016515276630883566,
|
| 69 |
+
"grad_norm": 3.110466178670075,
|
| 70 |
+
"learning_rate": 1.646090534979424e-06,
|
| 71 |
+
"loss": 0.9508,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.018579686209744012,
|
| 76 |
+
"grad_norm": 3.0934122499344614,
|
| 77 |
+
"learning_rate": 1.8518518518518519e-06,
|
| 78 |
+
"loss": 0.9496,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.02064409578860446,
|
| 83 |
+
"grad_norm": 3.2046299727793572,
|
| 84 |
+
"learning_rate": 2.05761316872428e-06,
|
| 85 |
+
"loss": 0.9256,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.022708505367464906,
|
| 90 |
+
"grad_norm": 2.9857050496874358,
|
| 91 |
+
"learning_rate": 2.263374485596708e-06,
|
| 92 |
+
"loss": 0.9146,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.02477291494632535,
|
| 97 |
+
"grad_norm": 3.010697976532333,
|
| 98 |
+
"learning_rate": 2.469135802469136e-06,
|
| 99 |
+
"loss": 0.9185,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.026837324525185797,
|
| 104 |
+
"grad_norm": 2.9986835294430274,
|
| 105 |
+
"learning_rate": 2.674897119341564e-06,
|
| 106 |
+
"loss": 0.9008,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.028901734104046242,
|
| 111 |
+
"grad_norm": 3.2527007862069186,
|
| 112 |
+
"learning_rate": 2.880658436213992e-06,
|
| 113 |
+
"loss": 0.8855,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.030966143682906688,
|
| 118 |
+
"grad_norm": 3.2007644630686833,
|
| 119 |
+
"learning_rate": 3.08641975308642e-06,
|
| 120 |
+
"loss": 0.8783,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.03303055326176713,
|
| 125 |
+
"grad_norm": 3.196196143650837,
|
| 126 |
+
"learning_rate": 3.292181069958848e-06,
|
| 127 |
+
"loss": 0.8775,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.03509496284062758,
|
| 132 |
+
"grad_norm": 3.004102067065696,
|
| 133 |
+
"learning_rate": 3.4979423868312762e-06,
|
| 134 |
+
"loss": 0.8808,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.037159372419488024,
|
| 139 |
+
"grad_norm": 3.118135767316795,
|
| 140 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 141 |
+
"loss": 0.8775,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.03922378199834847,
|
| 146 |
+
"grad_norm": 3.0856528450327354,
|
| 147 |
+
"learning_rate": 3.909465020576132e-06,
|
| 148 |
+
"loss": 0.8634,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.04128819157720892,
|
| 153 |
+
"grad_norm": 2.9700335979493167,
|
| 154 |
+
"learning_rate": 4.11522633744856e-06,
|
| 155 |
+
"loss": 0.872,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.04335260115606936,
|
| 160 |
+
"grad_norm": 3.1350056589977533,
|
| 161 |
+
"learning_rate": 4.3209876543209875e-06,
|
| 162 |
+
"loss": 0.8706,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.04541701073492981,
|
| 167 |
+
"grad_norm": 3.2497160658033852,
|
| 168 |
+
"learning_rate": 4.526748971193416e-06,
|
| 169 |
+
"loss": 0.8539,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.047481420313790254,
|
| 174 |
+
"grad_norm": 3.382546616433861,
|
| 175 |
+
"learning_rate": 4.732510288065844e-06,
|
| 176 |
+
"loss": 0.8573,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.0495458298926507,
|
| 181 |
+
"grad_norm": 3.1741955682207124,
|
| 182 |
+
"learning_rate": 4.938271604938272e-06,
|
| 183 |
+
"loss": 0.8433,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.051610239471511145,
|
| 188 |
+
"grad_norm": 3.13507489217465,
|
| 189 |
+
"learning_rate": 5.1440329218107e-06,
|
| 190 |
+
"loss": 0.8546,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.053674649050371594,
|
| 195 |
+
"grad_norm": 3.182938519722128,
|
| 196 |
+
"learning_rate": 5.349794238683128e-06,
|
| 197 |
+
"loss": 0.8505,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.05573905862923204,
|
| 202 |
+
"grad_norm": 3.3061978280140916,
|
| 203 |
+
"learning_rate": 5.555555555555557e-06,
|
| 204 |
+
"loss": 0.8596,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.057803468208092484,
|
| 209 |
+
"grad_norm": 3.172304485577032,
|
| 210 |
+
"learning_rate": 5.761316872427984e-06,
|
| 211 |
+
"loss": 0.8454,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.05986787778695293,
|
| 216 |
+
"grad_norm": 3.222279073856588,
|
| 217 |
+
"learning_rate": 5.967078189300412e-06,
|
| 218 |
+
"loss": 0.8552,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.061932287365813375,
|
| 223 |
+
"grad_norm": 3.026540545603275,
|
| 224 |
+
"learning_rate": 6.17283950617284e-06,
|
| 225 |
+
"loss": 0.8365,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.06399669694467382,
|
| 230 |
+
"grad_norm": 3.1724013332685304,
|
| 231 |
+
"learning_rate": 6.3786008230452675e-06,
|
| 232 |
+
"loss": 0.8397,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.06606110652353427,
|
| 237 |
+
"grad_norm": 3.4516704362207222,
|
| 238 |
+
"learning_rate": 6.584362139917696e-06,
|
| 239 |
+
"loss": 0.8346,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.06812551610239471,
|
| 244 |
+
"grad_norm": 3.1199583778413285,
|
| 245 |
+
"learning_rate": 6.790123456790124e-06,
|
| 246 |
+
"loss": 0.8296,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.07018992568125516,
|
| 251 |
+
"grad_norm": 3.448087429701013,
|
| 252 |
+
"learning_rate": 6.9958847736625525e-06,
|
| 253 |
+
"loss": 0.8384,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.07225433526011561,
|
| 258 |
+
"grad_norm": 3.072968814322973,
|
| 259 |
+
"learning_rate": 7.201646090534981e-06,
|
| 260 |
+
"loss": 0.846,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.07431874483897605,
|
| 265 |
+
"grad_norm": 3.1647169459938076,
|
| 266 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 267 |
+
"loss": 0.8256,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.0763831544178365,
|
| 272 |
+
"grad_norm": 3.105263189462399,
|
| 273 |
+
"learning_rate": 7.613168724279836e-06,
|
| 274 |
+
"loss": 0.8011,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.07844756399669695,
|
| 279 |
+
"grad_norm": 2.9946543968073294,
|
| 280 |
+
"learning_rate": 7.818930041152263e-06,
|
| 281 |
+
"loss": 0.8214,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.0805119735755574,
|
| 286 |
+
"grad_norm": 3.25501723509638,
|
| 287 |
+
"learning_rate": 8.024691358024692e-06,
|
| 288 |
+
"loss": 0.8201,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.08257638315441784,
|
| 293 |
+
"grad_norm": 3.0087568189695237,
|
| 294 |
+
"learning_rate": 8.23045267489712e-06,
|
| 295 |
+
"loss": 0.8139,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.08464079273327828,
|
| 300 |
+
"grad_norm": 3.0911976211351817,
|
| 301 |
+
"learning_rate": 8.43621399176955e-06,
|
| 302 |
+
"loss": 0.8242,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.08670520231213873,
|
| 307 |
+
"grad_norm": 3.310286578361364,
|
| 308 |
+
"learning_rate": 8.641975308641975e-06,
|
| 309 |
+
"loss": 0.8364,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.08876961189099918,
|
| 314 |
+
"grad_norm": 2.986473336622259,
|
| 315 |
+
"learning_rate": 8.847736625514404e-06,
|
| 316 |
+
"loss": 0.8316,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.09083402146985962,
|
| 321 |
+
"grad_norm": 3.102015428130825,
|
| 322 |
+
"learning_rate": 9.053497942386832e-06,
|
| 323 |
+
"loss": 0.8128,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.09289843104872006,
|
| 328 |
+
"grad_norm": 2.906374211555821,
|
| 329 |
+
"learning_rate": 9.25925925925926e-06,
|
| 330 |
+
"loss": 0.7945,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.09496284062758051,
|
| 335 |
+
"grad_norm": 3.0506200713500826,
|
| 336 |
+
"learning_rate": 9.465020576131688e-06,
|
| 337 |
+
"loss": 0.8158,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.09702725020644096,
|
| 342 |
+
"grad_norm": 3.0384361806454017,
|
| 343 |
+
"learning_rate": 9.670781893004116e-06,
|
| 344 |
+
"loss": 0.8228,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.0990916597853014,
|
| 349 |
+
"grad_norm": 3.100843008960617,
|
| 350 |
+
"learning_rate": 9.876543209876543e-06,
|
| 351 |
+
"loss": 0.8099,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.10115606936416185,
|
| 356 |
+
"grad_norm": 2.935521796714598,
|
| 357 |
+
"learning_rate": 9.999979213327006e-06,
|
| 358 |
+
"loss": 0.8108,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.10322047894302229,
|
| 363 |
+
"grad_norm": 3.361172390200279,
|
| 364 |
+
"learning_rate": 9.999745365240722e-06,
|
| 365 |
+
"loss": 0.7923,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.10528488852188274,
|
| 370 |
+
"grad_norm": 2.915556545903911,
|
| 371 |
+
"learning_rate": 9.999251697919687e-06,
|
| 372 |
+
"loss": 0.8045,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.10734929810074319,
|
| 377 |
+
"grad_norm": 3.212286307862521,
|
| 378 |
+
"learning_rate": 9.998498237018056e-06,
|
| 379 |
+
"loss": 0.8112,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.10941370767960364,
|
| 384 |
+
"grad_norm": 3.191428090938715,
|
| 385 |
+
"learning_rate": 9.997485021690553e-06,
|
| 386 |
+
"loss": 0.8001,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.11147811725846409,
|
| 391 |
+
"grad_norm": 2.838764527991799,
|
| 392 |
+
"learning_rate": 9.996212104590426e-06,
|
| 393 |
+
"loss": 0.8074,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.11354252683732452,
|
| 398 |
+
"grad_norm": 2.9644134550569943,
|
| 399 |
+
"learning_rate": 9.994679551866712e-06,
|
| 400 |
+
"loss": 0.8033,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.11560693641618497,
|
| 405 |
+
"grad_norm": 3.118728479888768,
|
| 406 |
+
"learning_rate": 9.992887443160804e-06,
|
| 407 |
+
"loss": 0.7905,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.11767134599504542,
|
| 412 |
+
"grad_norm": 2.8425828854985737,
|
| 413 |
+
"learning_rate": 9.990835871602305e-06,
|
| 414 |
+
"loss": 0.7987,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.11973575557390587,
|
| 419 |
+
"grad_norm": 3.091935940986862,
|
| 420 |
+
"learning_rate": 9.988524943804196e-06,
|
| 421 |
+
"loss": 0.7919,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.12180016515276632,
|
| 426 |
+
"grad_norm": 2.9471270363090976,
|
| 427 |
+
"learning_rate": 9.985954779857292e-06,
|
| 428 |
+
"loss": 0.7885,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.12386457473162675,
|
| 433 |
+
"grad_norm": 2.761224162387467,
|
| 434 |
+
"learning_rate": 9.983125513324e-06,
|
| 435 |
+
"loss": 0.784,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.1259289843104872,
|
| 440 |
+
"grad_norm": 2.779726805954528,
|
| 441 |
+
"learning_rate": 9.98003729123138e-06,
|
| 442 |
+
"loss": 0.7762,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.12799339388934763,
|
| 447 |
+
"grad_norm": 2.8806127663541625,
|
| 448 |
+
"learning_rate": 9.976690274063507e-06,
|
| 449 |
+
"loss": 0.7995,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.13005780346820808,
|
| 454 |
+
"grad_norm": 3.0861309652893163,
|
| 455 |
+
"learning_rate": 9.973084635753125e-06,
|
| 456 |
+
"loss": 0.8002,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.13212221304706853,
|
| 461 |
+
"grad_norm": 2.886159344081087,
|
| 462 |
+
"learning_rate": 9.969220563672614e-06,
|
| 463 |
+
"loss": 0.7742,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.13418662262592898,
|
| 468 |
+
"grad_norm": 2.9262415184999835,
|
| 469 |
+
"learning_rate": 9.965098258624253e-06,
|
| 470 |
+
"loss": 0.7807,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.13625103220478943,
|
| 475 |
+
"grad_norm": 2.9922747460068324,
|
| 476 |
+
"learning_rate": 9.960717934829777e-06,
|
| 477 |
+
"loss": 0.7582,
|
| 478 |
+
"step": 330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.13831544178364988,
|
| 482 |
+
"grad_norm": 2.9066701618612596,
|
| 483 |
+
"learning_rate": 9.956079819919254e-06,
|
| 484 |
+
"loss": 0.7849,
|
| 485 |
+
"step": 335
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.14037985136251033,
|
| 489 |
+
"grad_norm": 2.9577891790066766,
|
| 490 |
+
"learning_rate": 9.951184154919253e-06,
|
| 491 |
+
"loss": 0.7676,
|
| 492 |
+
"step": 340
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.14244426094137078,
|
| 496 |
+
"grad_norm": 2.7242674149455923,
|
| 497 |
+
"learning_rate": 9.946031194240317e-06,
|
| 498 |
+
"loss": 0.7613,
|
| 499 |
+
"step": 345
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.14450867052023122,
|
| 503 |
+
"grad_norm": 2.738187421683147,
|
| 504 |
+
"learning_rate": 9.940621205663745e-06,
|
| 505 |
+
"loss": 0.7476,
|
| 506 |
+
"step": 350
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.14657308009909165,
|
| 510 |
+
"grad_norm": 2.959447667783807,
|
| 511 |
+
"learning_rate": 9.934954470327671e-06,
|
| 512 |
+
"loss": 0.757,
|
| 513 |
+
"step": 355
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.1486374896779521,
|
| 517 |
+
"grad_norm": 2.9344152274329693,
|
| 518 |
+
"learning_rate": 9.92903128271246e-06,
|
| 519 |
+
"loss": 0.7559,
|
| 520 |
+
"step": 360
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.15070189925681254,
|
| 524 |
+
"grad_norm": 3.0358566235662554,
|
| 525 |
+
"learning_rate": 9.9228519506254e-06,
|
| 526 |
+
"loss": 0.7671,
|
| 527 |
+
"step": 365
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.152766308835673,
|
| 531 |
+
"grad_norm": 2.917481842444454,
|
| 532 |
+
"learning_rate": 9.916416795184716e-06,
|
| 533 |
+
"loss": 0.7423,
|
| 534 |
+
"step": 370
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.15483071841453344,
|
| 538 |
+
"grad_norm": 2.858632389269523,
|
| 539 |
+
"learning_rate": 9.90972615080287e-06,
|
| 540 |
+
"loss": 0.7625,
|
| 541 |
+
"step": 375
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.1568951279933939,
|
| 545 |
+
"grad_norm": 2.7940389389869997,
|
| 546 |
+
"learning_rate": 9.902780365169186e-06,
|
| 547 |
+
"loss": 0.7344,
|
| 548 |
+
"step": 380
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.15895953757225434,
|
| 552 |
+
"grad_norm": 2.966296190863466,
|
| 553 |
+
"learning_rate": 9.895579799231791e-06,
|
| 554 |
+
"loss": 0.7431,
|
| 555 |
+
"step": 385
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.1610239471511148,
|
| 559 |
+
"grad_norm": 2.734933032890328,
|
| 560 |
+
"learning_rate": 9.888124827178847e-06,
|
| 561 |
+
"loss": 0.7543,
|
| 562 |
+
"step": 390
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.16308835672997524,
|
| 566 |
+
"grad_norm": 3.0106930594709183,
|
| 567 |
+
"learning_rate": 9.880415836419108e-06,
|
| 568 |
+
"loss": 0.7322,
|
| 569 |
+
"step": 395
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.16515276630883569,
|
| 573 |
+
"grad_norm": 3.1160711879023277,
|
| 574 |
+
"learning_rate": 9.872453227561795e-06,
|
| 575 |
+
"loss": 0.7217,
|
| 576 |
+
"step": 400
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.1672171758876961,
|
| 580 |
+
"grad_norm": 3.025574483100628,
|
| 581 |
+
"learning_rate": 9.864237414395768e-06,
|
| 582 |
+
"loss": 0.7234,
|
| 583 |
+
"step": 405
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.16928158546655656,
|
| 587 |
+
"grad_norm": 3.0800133917199024,
|
| 588 |
+
"learning_rate": 9.855768823868026e-06,
|
| 589 |
+
"loss": 0.7451,
|
| 590 |
+
"step": 410
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.171345995045417,
|
| 594 |
+
"grad_norm": 2.878566581474389,
|
| 595 |
+
"learning_rate": 9.847047896061526e-06,
|
| 596 |
+
"loss": 0.7479,
|
| 597 |
+
"step": 415
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.17341040462427745,
|
| 601 |
+
"grad_norm": 3.168491396422218,
|
| 602 |
+
"learning_rate": 9.838075084172303e-06,
|
| 603 |
+
"loss": 0.7258,
|
| 604 |
+
"step": 420
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.1754748142031379,
|
| 608 |
+
"grad_norm": 2.815061772988165,
|
| 609 |
+
"learning_rate": 9.828850854485929e-06,
|
| 610 |
+
"loss": 0.7055,
|
| 611 |
+
"step": 425
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.17753922378199835,
|
| 615 |
+
"grad_norm": 2.6873037207867356,
|
| 616 |
+
"learning_rate": 9.819375686353277e-06,
|
| 617 |
+
"loss": 0.7253,
|
| 618 |
+
"step": 430
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.1796036333608588,
|
| 622 |
+
"grad_norm": 2.8648079803750077,
|
| 623 |
+
"learning_rate": 9.809650072165606e-06,
|
| 624 |
+
"loss": 0.7218,
|
| 625 |
+
"step": 435
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.18166804293971925,
|
| 629 |
+
"grad_norm": 2.6485478231791446,
|
| 630 |
+
"learning_rate": 9.799674517328985e-06,
|
| 631 |
+
"loss": 0.7211,
|
| 632 |
+
"step": 440
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.1837324525185797,
|
| 636 |
+
"grad_norm": 2.9086971891718365,
|
| 637 |
+
"learning_rate": 9.78944954023802e-06,
|
| 638 |
+
"loss": 0.7113,
|
| 639 |
+
"step": 445
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.18579686209744012,
|
| 643 |
+
"grad_norm": 2.777331603392391,
|
| 644 |
+
"learning_rate": 9.778975672248909e-06,
|
| 645 |
+
"loss": 0.7236,
|
| 646 |
+
"step": 450
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.18786127167630057,
|
| 650 |
+
"grad_norm": 2.896862579927988,
|
| 651 |
+
"learning_rate": 9.768253457651853e-06,
|
| 652 |
+
"loss": 0.7239,
|
| 653 |
+
"step": 455
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.18992568125516102,
|
| 657 |
+
"grad_norm": 2.788383349290103,
|
| 658 |
+
"learning_rate": 9.757283453642741e-06,
|
| 659 |
+
"loss": 0.7083,
|
| 660 |
+
"step": 460
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.19199009083402147,
|
| 664 |
+
"grad_norm": 2.7799217861819816,
|
| 665 |
+
"learning_rate": 9.746066230294216e-06,
|
| 666 |
+
"loss": 0.7008,
|
| 667 |
+
"step": 465
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.19405450041288191,
|
| 671 |
+
"grad_norm": 3.0828748770941603,
|
| 672 |
+
"learning_rate": 9.734602370526042e-06,
|
| 673 |
+
"loss": 0.6949,
|
| 674 |
+
"step": 470
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.19611890999174236,
|
| 678 |
+
"grad_norm": 2.8583233928158145,
|
| 679 |
+
"learning_rate": 9.722892470074811e-06,
|
| 680 |
+
"loss": 0.6923,
|
| 681 |
+
"step": 475
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.1981833195706028,
|
| 685 |
+
"grad_norm": 2.850888921108626,
|
| 686 |
+
"learning_rate": 9.710937137462992e-06,
|
| 687 |
+
"loss": 0.7056,
|
| 688 |
+
"step": 480
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.20024772914946326,
|
| 692 |
+
"grad_norm": 2.8804381008997697,
|
| 693 |
+
"learning_rate": 9.698736993967295e-06,
|
| 694 |
+
"loss": 0.7134,
|
| 695 |
+
"step": 485
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.2023121387283237,
|
| 699 |
+
"grad_norm": 2.5675849510127473,
|
| 700 |
+
"learning_rate": 9.686292673586397e-06,
|
| 701 |
+
"loss": 0.6854,
|
| 702 |
+
"step": 490
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.20437654830718416,
|
| 706 |
+
"grad_norm": 2.752726728070582,
|
| 707 |
+
"learning_rate": 9.673604823007994e-06,
|
| 708 |
+
"loss": 0.6944,
|
| 709 |
+
"step": 495
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.20644095788604458,
|
| 713 |
+
"grad_norm": 2.8340105200706507,
|
| 714 |
+
"learning_rate": 9.660674101575188e-06,
|
| 715 |
+
"loss": 0.6959,
|
| 716 |
+
"step": 500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.20850536746490503,
|
| 720 |
+
"grad_norm": 2.6749836979567325,
|
| 721 |
+
"learning_rate": 9.647501181252228e-06,
|
| 722 |
+
"loss": 0.7181,
|
| 723 |
+
"step": 505
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.21056977704376548,
|
| 727 |
+
"grad_norm": 2.871887495235821,
|
| 728 |
+
"learning_rate": 9.634086746589597e-06,
|
| 729 |
+
"loss": 0.6855,
|
| 730 |
+
"step": 510
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.21263418662262593,
|
| 734 |
+
"grad_norm": 3.022510499989922,
|
| 735 |
+
"learning_rate": 9.62043149468842e-06,
|
| 736 |
+
"loss": 0.6786,
|
| 737 |
+
"step": 515
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.21469859620148637,
|
| 741 |
+
"grad_norm": 2.798631786402729,
|
| 742 |
+
"learning_rate": 9.60653613516426e-06,
|
| 743 |
+
"loss": 0.6878,
|
| 744 |
+
"step": 520
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.21676300578034682,
|
| 748 |
+
"grad_norm": 2.7665584034808557,
|
| 749 |
+
"learning_rate": 9.592401390110224e-06,
|
| 750 |
+
"loss": 0.6689,
|
| 751 |
+
"step": 525
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.21882741535920727,
|
| 755 |
+
"grad_norm": 2.6972597849127995,
|
| 756 |
+
"learning_rate": 9.578027994059448e-06,
|
| 757 |
+
"loss": 0.6938,
|
| 758 |
+
"step": 530
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.22089182493806772,
|
| 762 |
+
"grad_norm": 2.876624388604322,
|
| 763 |
+
"learning_rate": 9.563416693946927e-06,
|
| 764 |
+
"loss": 0.6831,
|
| 765 |
+
"step": 535
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.22295623451692817,
|
| 769 |
+
"grad_norm": 2.760614779991045,
|
| 770 |
+
"learning_rate": 9.548568249070688e-06,
|
| 771 |
+
"loss": 0.6721,
|
| 772 |
+
"step": 540
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.2250206440957886,
|
| 776 |
+
"grad_norm": 2.711332679097759,
|
| 777 |
+
"learning_rate": 9.533483431052347e-06,
|
| 778 |
+
"loss": 0.6734,
|
| 779 |
+
"step": 545
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.22708505367464904,
|
| 783 |
+
"grad_norm": 2.9419038213760573,
|
| 784 |
+
"learning_rate": 9.518163023797001e-06,
|
| 785 |
+
"loss": 0.6826,
|
| 786 |
+
"step": 550
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.2291494632535095,
|
| 790 |
+
"grad_norm": 2.708449916455307,
|
| 791 |
+
"learning_rate": 9.502607823452492e-06,
|
| 792 |
+
"loss": 0.6909,
|
| 793 |
+
"step": 555
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.23121387283236994,
|
| 797 |
+
"grad_norm": 2.6744723555279712,
|
| 798 |
+
"learning_rate": 9.486818638368037e-06,
|
| 799 |
+
"loss": 0.6727,
|
| 800 |
+
"step": 560
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.2332782824112304,
|
| 804 |
+
"grad_norm": 2.740519766192663,
|
| 805 |
+
"learning_rate": 9.47079628905222e-06,
|
| 806 |
+
"loss": 0.6643,
|
| 807 |
+
"step": 565
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.23534269199009084,
|
| 811 |
+
"grad_norm": 2.6127044855477544,
|
| 812 |
+
"learning_rate": 9.45454160813035e-06,
|
| 813 |
+
"loss": 0.641,
|
| 814 |
+
"step": 570
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.23740710156895128,
|
| 818 |
+
"grad_norm": 2.5898360039465547,
|
| 819 |
+
"learning_rate": 9.438055440301198e-06,
|
| 820 |
+
"loss": 0.654,
|
| 821 |
+
"step": 575
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.23947151114781173,
|
| 825 |
+
"grad_norm": 2.594315428105211,
|
| 826 |
+
"learning_rate": 9.421338642293096e-06,
|
| 827 |
+
"loss": 0.6612,
|
| 828 |
+
"step": 580
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.24153592072667218,
|
| 832 |
+
"grad_norm": 2.675279309210325,
|
| 833 |
+
"learning_rate": 9.404392082819418e-06,
|
| 834 |
+
"loss": 0.6835,
|
| 835 |
+
"step": 585
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.24360033030553263,
|
| 839 |
+
"grad_norm": 2.720481221371884,
|
| 840 |
+
"learning_rate": 9.387216642533436e-06,
|
| 841 |
+
"loss": 0.638,
|
| 842 |
+
"step": 590
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.24566473988439305,
|
| 846 |
+
"grad_norm": 2.7274539164197567,
|
| 847 |
+
"learning_rate": 9.369813213982557e-06,
|
| 848 |
+
"loss": 0.6742,
|
| 849 |
+
"step": 595
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.2477291494632535,
|
| 853 |
+
"grad_norm": 2.881159963630694,
|
| 854 |
+
"learning_rate": 9.352182701561932e-06,
|
| 855 |
+
"loss": 0.643,
|
| 856 |
+
"step": 600
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.24979355904211395,
|
| 860 |
+
"grad_norm": 2.672785271513205,
|
| 861 |
+
"learning_rate": 9.334326021467473e-06,
|
| 862 |
+
"loss": 0.6518,
|
| 863 |
+
"step": 605
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.2518579686209744,
|
| 867 |
+
"grad_norm": 2.6806455710314365,
|
| 868 |
+
"learning_rate": 9.316244101648229e-06,
|
| 869 |
+
"loss": 0.644,
|
| 870 |
+
"step": 610
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.2539223781998348,
|
| 874 |
+
"grad_norm": 2.5531072290720296,
|
| 875 |
+
"learning_rate": 9.297937881758165e-06,
|
| 876 |
+
"loss": 0.6738,
|
| 877 |
+
"step": 615
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.25598678777869527,
|
| 881 |
+
"grad_norm": 2.8562519058356335,
|
| 882 |
+
"learning_rate": 9.279408313107342e-06,
|
| 883 |
+
"loss": 0.6497,
|
| 884 |
+
"step": 620
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.2580511973575557,
|
| 888 |
+
"grad_norm": 2.9118129566241273,
|
| 889 |
+
"learning_rate": 9.260656358612461e-06,
|
| 890 |
+
"loss": 0.6544,
|
| 891 |
+
"step": 625
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.26011560693641617,
|
| 895 |
+
"grad_norm": 2.6582669873812117,
|
| 896 |
+
"learning_rate": 9.241682992746847e-06,
|
| 897 |
+
"loss": 0.6492,
|
| 898 |
+
"step": 630
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.2621800165152766,
|
| 902 |
+
"grad_norm": 3.135088950824475,
|
| 903 |
+
"learning_rate": 9.222489201489792e-06,
|
| 904 |
+
"loss": 0.6324,
|
| 905 |
+
"step": 635
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.26424442609413706,
|
| 909 |
+
"grad_norm": 2.5674033607777282,
|
| 910 |
+
"learning_rate": 9.203075982275323e-06,
|
| 911 |
+
"loss": 0.6461,
|
| 912 |
+
"step": 640
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.2663088356729975,
|
| 916 |
+
"grad_norm": 2.615329482313224,
|
| 917 |
+
"learning_rate": 9.18344434394037e-06,
|
| 918 |
+
"loss": 0.6322,
|
| 919 |
+
"step": 645
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.26837324525185796,
|
| 923 |
+
"grad_norm": 2.6662637432037144,
|
| 924 |
+
"learning_rate": 9.163595306672337e-06,
|
| 925 |
+
"loss": 0.6245,
|
| 926 |
+
"step": 650
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.2704376548307184,
|
| 930 |
+
"grad_norm": 2.788831071229617,
|
| 931 |
+
"learning_rate": 9.143529901956089e-06,
|
| 932 |
+
"loss": 0.6395,
|
| 933 |
+
"step": 655
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.27250206440957886,
|
| 937 |
+
"grad_norm": 2.7354638041171344,
|
| 938 |
+
"learning_rate": 9.12324917252035e-06,
|
| 939 |
+
"loss": 0.6239,
|
| 940 |
+
"step": 660
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.2745664739884393,
|
| 944 |
+
"grad_norm": 2.6074213157412682,
|
| 945 |
+
"learning_rate": 9.102754172283513e-06,
|
| 946 |
+
"loss": 0.6146,
|
| 947 |
+
"step": 665
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.27663088356729976,
|
| 951 |
+
"grad_norm": 2.6642140176865485,
|
| 952 |
+
"learning_rate": 9.082045966298871e-06,
|
| 953 |
+
"loss": 0.6207,
|
| 954 |
+
"step": 670
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.2786952931461602,
|
| 958 |
+
"grad_norm": 2.7423993871208547,
|
| 959 |
+
"learning_rate": 9.061125630699276e-06,
|
| 960 |
+
"loss": 0.6244,
|
| 961 |
+
"step": 675
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.28075970272502065,
|
| 965 |
+
"grad_norm": 2.639661943202539,
|
| 966 |
+
"learning_rate": 9.039994252641214e-06,
|
| 967 |
+
"loss": 0.6212,
|
| 968 |
+
"step": 680
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.2828241123038811,
|
| 972 |
+
"grad_norm": 2.7917609886441443,
|
| 973 |
+
"learning_rate": 9.018652930248299e-06,
|
| 974 |
+
"loss": 0.6279,
|
| 975 |
+
"step": 685
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.28488852188274155,
|
| 979 |
+
"grad_norm": 2.629871903545716,
|
| 980 |
+
"learning_rate": 8.997102772554226e-06,
|
| 981 |
+
"loss": 0.6229,
|
| 982 |
+
"step": 690
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.286952931461602,
|
| 986 |
+
"grad_norm": 2.625664182045412,
|
| 987 |
+
"learning_rate": 8.975344899445119e-06,
|
| 988 |
+
"loss": 0.6177,
|
| 989 |
+
"step": 695
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.28901734104046245,
|
| 993 |
+
"grad_norm": 2.80144553747866,
|
| 994 |
+
"learning_rate": 8.953380441601352e-06,
|
| 995 |
+
"loss": 0.6225,
|
| 996 |
+
"step": 700
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.2910817506193229,
|
| 1000 |
+
"grad_norm": 2.672640679384628,
|
| 1001 |
+
"learning_rate": 8.931210540438778e-06,
|
| 1002 |
+
"loss": 0.6169,
|
| 1003 |
+
"step": 705
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.2931461601981833,
|
| 1007 |
+
"grad_norm": 2.709692648262891,
|
| 1008 |
+
"learning_rate": 8.908836348049421e-06,
|
| 1009 |
+
"loss": 0.6198,
|
| 1010 |
+
"step": 710
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.29521056977704374,
|
| 1014 |
+
"grad_norm": 2.681528317767069,
|
| 1015 |
+
"learning_rate": 8.886259027141603e-06,
|
| 1016 |
+
"loss": 0.6149,
|
| 1017 |
+
"step": 715
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.2972749793559042,
|
| 1021 |
+
"grad_norm": 3.03293644975451,
|
| 1022 |
+
"learning_rate": 8.863479750979523e-06,
|
| 1023 |
+
"loss": 0.6048,
|
| 1024 |
+
"step": 720
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.29933938893476464,
|
| 1028 |
+
"grad_norm": 2.670868153191048,
|
| 1029 |
+
"learning_rate": 8.840499703322286e-06,
|
| 1030 |
+
"loss": 0.6244,
|
| 1031 |
+
"step": 725
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.3014037985136251,
|
| 1035 |
+
"grad_norm": 2.7608395704880646,
|
| 1036 |
+
"learning_rate": 8.817320078362388e-06,
|
| 1037 |
+
"loss": 0.6035,
|
| 1038 |
+
"step": 730
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.30346820809248554,
|
| 1042 |
+
"grad_norm": 2.62588384982977,
|
| 1043 |
+
"learning_rate": 8.793942080663658e-06,
|
| 1044 |
+
"loss": 0.6172,
|
| 1045 |
+
"step": 735
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.305532617671346,
|
| 1049 |
+
"grad_norm": 2.5889068256927006,
|
| 1050 |
+
"learning_rate": 8.77036692509866e-06,
|
| 1051 |
+
"loss": 0.6128,
|
| 1052 |
+
"step": 740
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.30759702725020643,
|
| 1056 |
+
"grad_norm": 2.8092080143766216,
|
| 1057 |
+
"learning_rate": 8.746595836785561e-06,
|
| 1058 |
+
"loss": 0.6218,
|
| 1059 |
+
"step": 745
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.3096614368290669,
|
| 1063 |
+
"grad_norm": 2.6419072436310205,
|
| 1064 |
+
"learning_rate": 8.722630051024467e-06,
|
| 1065 |
+
"loss": 0.5877,
|
| 1066 |
+
"step": 750
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.31172584640792733,
|
| 1070 |
+
"grad_norm": 2.4997349328580363,
|
| 1071 |
+
"learning_rate": 8.698470813233223e-06,
|
| 1072 |
+
"loss": 0.6091,
|
| 1073 |
+
"step": 755
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.3137902559867878,
|
| 1077 |
+
"grad_norm": 2.6466710278909074,
|
| 1078 |
+
"learning_rate": 8.674119378882707e-06,
|
| 1079 |
+
"loss": 0.6087,
|
| 1080 |
+
"step": 760
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.31585466556564823,
|
| 1084 |
+
"grad_norm": 2.9297154437714363,
|
| 1085 |
+
"learning_rate": 8.649577013431569e-06,
|
| 1086 |
+
"loss": 0.592,
|
| 1087 |
+
"step": 765
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.3179190751445087,
|
| 1091 |
+
"grad_norm": 2.549997409403058,
|
| 1092 |
+
"learning_rate": 8.624844992260483e-06,
|
| 1093 |
+
"loss": 0.6023,
|
| 1094 |
+
"step": 770
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.3199834847233691,
|
| 1098 |
+
"grad_norm": 2.7080008761741827,
|
| 1099 |
+
"learning_rate": 8.599924600605865e-06,
|
| 1100 |
+
"loss": 0.6087,
|
| 1101 |
+
"step": 775
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.3220478943022296,
|
| 1105 |
+
"grad_norm": 2.567143331934158,
|
| 1106 |
+
"learning_rate": 8.574817133493085e-06,
|
| 1107 |
+
"loss": 0.5847,
|
| 1108 |
+
"step": 780
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.32411230388109,
|
| 1112 |
+
"grad_norm": 3.0113192932757418,
|
| 1113 |
+
"learning_rate": 8.549523895669167e-06,
|
| 1114 |
+
"loss": 0.5908,
|
| 1115 |
+
"step": 785
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.3261767134599505,
|
| 1119 |
+
"grad_norm": 2.7819521209578206,
|
| 1120 |
+
"learning_rate": 8.52404620153499e-06,
|
| 1121 |
+
"loss": 0.5953,
|
| 1122 |
+
"step": 790
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.3282411230388109,
|
| 1126 |
+
"grad_norm": 2.747216748021648,
|
| 1127 |
+
"learning_rate": 8.498385375076979e-06,
|
| 1128 |
+
"loss": 0.6114,
|
| 1129 |
+
"step": 795
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.33030553261767137,
|
| 1133 |
+
"grad_norm": 2.8476886670194523,
|
| 1134 |
+
"learning_rate": 8.472542749798302e-06,
|
| 1135 |
+
"loss": 0.5923,
|
| 1136 |
+
"step": 800
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.33236994219653176,
|
| 1140 |
+
"grad_norm": 3.078148326221217,
|
| 1141 |
+
"learning_rate": 8.44651966864958e-06,
|
| 1142 |
+
"loss": 0.5854,
|
| 1143 |
+
"step": 805
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.3344343517753922,
|
| 1147 |
+
"grad_norm": 2.7069355571781553,
|
| 1148 |
+
"learning_rate": 8.420317483959086e-06,
|
| 1149 |
+
"loss": 0.5963,
|
| 1150 |
+
"step": 810
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.33649876135425266,
|
| 1154 |
+
"grad_norm": 2.651998023029158,
|
| 1155 |
+
"learning_rate": 8.39393755736248e-06,
|
| 1156 |
+
"loss": 0.578,
|
| 1157 |
+
"step": 815
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.3385631709331131,
|
| 1161 |
+
"grad_norm": 2.6251615353567117,
|
| 1162 |
+
"learning_rate": 8.367381259732042e-06,
|
| 1163 |
+
"loss": 0.587,
|
| 1164 |
+
"step": 820
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.34062758051197356,
|
| 1168 |
+
"grad_norm": 2.5308341360997595,
|
| 1169 |
+
"learning_rate": 8.340649971105444e-06,
|
| 1170 |
+
"loss": 0.5732,
|
| 1171 |
+
"step": 825
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.342691990090834,
|
| 1175 |
+
"grad_norm": 2.823077213728183,
|
| 1176 |
+
"learning_rate": 8.313745080614017e-06,
|
| 1177 |
+
"loss": 0.5672,
|
| 1178 |
+
"step": 830
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.34475639966969446,
|
| 1182 |
+
"grad_norm": 2.659469137057744,
|
| 1183 |
+
"learning_rate": 8.286667986410578e-06,
|
| 1184 |
+
"loss": 0.5858,
|
| 1185 |
+
"step": 835
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.3468208092485549,
|
| 1189 |
+
"grad_norm": 2.845018948853141,
|
| 1190 |
+
"learning_rate": 8.259420095596766e-06,
|
| 1191 |
+
"loss": 0.5662,
|
| 1192 |
+
"step": 840
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.34888521882741536,
|
| 1196 |
+
"grad_norm": 2.6028478895400116,
|
| 1197 |
+
"learning_rate": 8.232002824149917e-06,
|
| 1198 |
+
"loss": 0.5606,
|
| 1199 |
+
"step": 845
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.3509496284062758,
|
| 1203 |
+
"grad_norm": 2.664709732227379,
|
| 1204 |
+
"learning_rate": 8.204417596849492e-06,
|
| 1205 |
+
"loss": 0.5807,
|
| 1206 |
+
"step": 850
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.35301403798513625,
|
| 1210 |
+
"grad_norm": 2.6109659834823478,
|
| 1211 |
+
"learning_rate": 8.176665847203023e-06,
|
| 1212 |
+
"loss": 0.5678,
|
| 1213 |
+
"step": 855
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.3550784475639967,
|
| 1217 |
+
"grad_norm": 2.576771155175357,
|
| 1218 |
+
"learning_rate": 8.148749017371627e-06,
|
| 1219 |
+
"loss": 0.5656,
|
| 1220 |
+
"step": 860
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.35714285714285715,
|
| 1224 |
+
"grad_norm": 2.6688801593883817,
|
| 1225 |
+
"learning_rate": 8.120668558095056e-06,
|
| 1226 |
+
"loss": 0.5749,
|
| 1227 |
+
"step": 865
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.3592072667217176,
|
| 1231 |
+
"grad_norm": 2.801881409304358,
|
| 1232 |
+
"learning_rate": 8.092425928616317e-06,
|
| 1233 |
+
"loss": 0.5603,
|
| 1234 |
+
"step": 870
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.36127167630057805,
|
| 1238 |
+
"grad_norm": 2.7158675577145512,
|
| 1239 |
+
"learning_rate": 8.064022596605825e-06,
|
| 1240 |
+
"loss": 0.5878,
|
| 1241 |
+
"step": 875
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.3633360858794385,
|
| 1245 |
+
"grad_norm": 2.7112475864205208,
|
| 1246 |
+
"learning_rate": 8.03546003808515e-06,
|
| 1247 |
+
"loss": 0.5697,
|
| 1248 |
+
"step": 880
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.36540049545829895,
|
| 1252 |
+
"grad_norm": 2.757081302105068,
|
| 1253 |
+
"learning_rate": 8.006739737350303e-06,
|
| 1254 |
+
"loss": 0.5549,
|
| 1255 |
+
"step": 885
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.3674649050371594,
|
| 1259 |
+
"grad_norm": 2.6798695533176,
|
| 1260 |
+
"learning_rate": 7.977863186894598e-06,
|
| 1261 |
+
"loss": 0.5621,
|
| 1262 |
+
"step": 890
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.36952931461601984,
|
| 1266 |
+
"grad_norm": 2.901794116790705,
|
| 1267 |
+
"learning_rate": 7.948831887331113e-06,
|
| 1268 |
+
"loss": 0.5531,
|
| 1269 |
+
"step": 895
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.37159372419488024,
|
| 1273 |
+
"grad_norm": 2.6209628611019333,
|
| 1274 |
+
"learning_rate": 7.91964734731468e-06,
|
| 1275 |
+
"loss": 0.5529,
|
| 1276 |
+
"step": 900
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.3736581337737407,
|
| 1280 |
+
"grad_norm": 2.631776999408232,
|
| 1281 |
+
"learning_rate": 7.890311083463511e-06,
|
| 1282 |
+
"loss": 0.5341,
|
| 1283 |
+
"step": 905
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.37572254335260113,
|
| 1287 |
+
"grad_norm": 2.6460839052940424,
|
| 1288 |
+
"learning_rate": 7.860824620280367e-06,
|
| 1289 |
+
"loss": 0.5589,
|
| 1290 |
+
"step": 910
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.3777869529314616,
|
| 1294 |
+
"grad_norm": 2.7027858769480604,
|
| 1295 |
+
"learning_rate": 7.831189490073343e-06,
|
| 1296 |
+
"loss": 0.5662,
|
| 1297 |
+
"step": 915
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.37985136251032203,
|
| 1301 |
+
"grad_norm": 2.686204866691535,
|
| 1302 |
+
"learning_rate": 7.80140723287624e-06,
|
| 1303 |
+
"loss": 0.5557,
|
| 1304 |
+
"step": 920
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.3819157720891825,
|
| 1308 |
+
"grad_norm": 2.537669294604416,
|
| 1309 |
+
"learning_rate": 7.771479396368533e-06,
|
| 1310 |
+
"loss": 0.5392,
|
| 1311 |
+
"step": 925
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.38398018166804293,
|
| 1315 |
+
"grad_norm": 2.634245727933428,
|
| 1316 |
+
"learning_rate": 7.741407535794939e-06,
|
| 1317 |
+
"loss": 0.5476,
|
| 1318 |
+
"step": 930
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.3860445912469034,
|
| 1322 |
+
"grad_norm": 2.63998365984595,
|
| 1323 |
+
"learning_rate": 7.711193213884602e-06,
|
| 1324 |
+
"loss": 0.5411,
|
| 1325 |
+
"step": 935
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.38810900082576383,
|
| 1329 |
+
"grad_norm": 2.5066641406139163,
|
| 1330 |
+
"learning_rate": 7.680838000769889e-06,
|
| 1331 |
+
"loss": 0.5436,
|
| 1332 |
+
"step": 940
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.3901734104046243,
|
| 1336 |
+
"grad_norm": 2.4698510563626384,
|
| 1337 |
+
"learning_rate": 7.650343473904776e-06,
|
| 1338 |
+
"loss": 0.536,
|
| 1339 |
+
"step": 945
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.3922378199834847,
|
| 1343 |
+
"grad_norm": 2.5102808206533753,
|
| 1344 |
+
"learning_rate": 7.619711217982899e-06,
|
| 1345 |
+
"loss": 0.5391,
|
| 1346 |
+
"step": 950
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.3943022295623452,
|
| 1350 |
+
"grad_norm": 2.648139467398325,
|
| 1351 |
+
"learning_rate": 7.5889428248551854e-06,
|
| 1352 |
+
"loss": 0.5368,
|
| 1353 |
+
"step": 955
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.3963666391412056,
|
| 1357 |
+
"grad_norm": 2.6648738415553765,
|
| 1358 |
+
"learning_rate": 7.558039893447131e-06,
|
| 1359 |
+
"loss": 0.5496,
|
| 1360 |
+
"step": 960
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.39843104872006607,
|
| 1364 |
+
"grad_norm": 2.6157509498551526,
|
| 1365 |
+
"learning_rate": 7.527004029675722e-06,
|
| 1366 |
+
"loss": 0.5318,
|
| 1367 |
+
"step": 965
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.4004954582989265,
|
| 1371 |
+
"grad_norm": 2.5975829607560574,
|
| 1372 |
+
"learning_rate": 7.495836846365965e-06,
|
| 1373 |
+
"loss": 0.5352,
|
| 1374 |
+
"step": 970
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.40255986787778697,
|
| 1378 |
+
"grad_norm": 2.92450937390704,
|
| 1379 |
+
"learning_rate": 7.464539963167091e-06,
|
| 1380 |
+
"loss": 0.5177,
|
| 1381 |
+
"step": 975
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.4046242774566474,
|
| 1385 |
+
"grad_norm": 2.7355952122295264,
|
| 1386 |
+
"learning_rate": 7.433115006468373e-06,
|
| 1387 |
+
"loss": 0.5322,
|
| 1388 |
+
"step": 980
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.40668868703550787,
|
| 1392 |
+
"grad_norm": 2.5829736114469184,
|
| 1393 |
+
"learning_rate": 7.40156360931462e-06,
|
| 1394 |
+
"loss": 0.5298,
|
| 1395 |
+
"step": 985
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.4087530966143683,
|
| 1399 |
+
"grad_norm": 2.705958846647064,
|
| 1400 |
+
"learning_rate": 7.369887411321305e-06,
|
| 1401 |
+
"loss": 0.5477,
|
| 1402 |
+
"step": 990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.4108175061932287,
|
| 1406 |
+
"grad_norm": 2.4846959730474145,
|
| 1407 |
+
"learning_rate": 7.338088058589362e-06,
|
| 1408 |
+
"loss": 0.5324,
|
| 1409 |
+
"step": 995
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.41288191577208916,
|
| 1413 |
+
"grad_norm": 2.5252160694956762,
|
| 1414 |
+
"learning_rate": 7.306167203619647e-06,
|
| 1415 |
+
"loss": 0.5335,
|
| 1416 |
+
"step": 1000
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.4149463253509496,
|
| 1420 |
+
"grad_norm": 2.509240890701763,
|
| 1421 |
+
"learning_rate": 7.27412650522706e-06,
|
| 1422 |
+
"loss": 0.5219,
|
| 1423 |
+
"step": 1005
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.41701073492981006,
|
| 1427 |
+
"grad_norm": 2.567378202198639,
|
| 1428 |
+
"learning_rate": 7.241967628454345e-06,
|
| 1429 |
+
"loss": 0.5142,
|
| 1430 |
+
"step": 1010
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.4190751445086705,
|
| 1434 |
+
"grad_norm": 2.479116521394592,
|
| 1435 |
+
"learning_rate": 7.20969224448556e-06,
|
| 1436 |
+
"loss": 0.5198,
|
| 1437 |
+
"step": 1015
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.42113955408753095,
|
| 1441 |
+
"grad_norm": 2.456783739959803,
|
| 1442 |
+
"learning_rate": 7.1773020305592355e-06,
|
| 1443 |
+
"loss": 0.5141,
|
| 1444 |
+
"step": 1020
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.4232039636663914,
|
| 1448 |
+
"grad_norm": 2.6855797799019356,
|
| 1449 |
+
"learning_rate": 7.1447986698812115e-06,
|
| 1450 |
+
"loss": 0.5307,
|
| 1451 |
+
"step": 1025
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.42526837324525185,
|
| 1455 |
+
"grad_norm": 2.5323199215752203,
|
| 1456 |
+
"learning_rate": 7.112183851537166e-06,
|
| 1457 |
+
"loss": 0.5256,
|
| 1458 |
+
"step": 1030
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.4273327828241123,
|
| 1462 |
+
"grad_norm": 2.735418738176186,
|
| 1463 |
+
"learning_rate": 7.079459270404842e-06,
|
| 1464 |
+
"loss": 0.5112,
|
| 1465 |
+
"step": 1035
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.42939719240297275,
|
| 1469 |
+
"grad_norm": 2.6703449875287735,
|
| 1470 |
+
"learning_rate": 7.046626627065974e-06,
|
| 1471 |
+
"loss": 0.5099,
|
| 1472 |
+
"step": 1040
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.4314616019818332,
|
| 1476 |
+
"grad_norm": 2.4631394786044747,
|
| 1477 |
+
"learning_rate": 7.013687627717905e-06,
|
| 1478 |
+
"loss": 0.4978,
|
| 1479 |
+
"step": 1045
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.43352601156069365,
|
| 1483 |
+
"grad_norm": 2.8328555379260196,
|
| 1484 |
+
"learning_rate": 6.980643984084927e-06,
|
| 1485 |
+
"loss": 0.5179,
|
| 1486 |
+
"step": 1050
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.4355904211395541,
|
| 1490 |
+
"grad_norm": 2.504430665948721,
|
| 1491 |
+
"learning_rate": 6.947497413329333e-06,
|
| 1492 |
+
"loss": 0.5199,
|
| 1493 |
+
"step": 1055
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.43765483071841454,
|
| 1497 |
+
"grad_norm": 2.5711442943268663,
|
| 1498 |
+
"learning_rate": 6.914249637962174e-06,
|
| 1499 |
+
"loss": 0.5133,
|
| 1500 |
+
"step": 1060
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.439719240297275,
|
| 1504 |
+
"grad_norm": 2.5576807334846747,
|
| 1505 |
+
"learning_rate": 6.880902385753749e-06,
|
| 1506 |
+
"loss": 0.51,
|
| 1507 |
+
"step": 1065
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.44178364987613544,
|
| 1511 |
+
"grad_norm": 2.4378114750971833,
|
| 1512 |
+
"learning_rate": 6.847457389643823e-06,
|
| 1513 |
+
"loss": 0.4966,
|
| 1514 |
+
"step": 1070
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.4438480594549959,
|
| 1518 |
+
"grad_norm": 2.57922332477375,
|
| 1519 |
+
"learning_rate": 6.8139163876515694e-06,
|
| 1520 |
+
"loss": 0.5018,
|
| 1521 |
+
"step": 1075
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.44591246903385634,
|
| 1525 |
+
"grad_norm": 2.4923563722799145,
|
| 1526 |
+
"learning_rate": 6.780281122785243e-06,
|
| 1527 |
+
"loss": 0.5089,
|
| 1528 |
+
"step": 1080
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.4479768786127168,
|
| 1532 |
+
"grad_norm": 2.380488675820629,
|
| 1533 |
+
"learning_rate": 6.74655334295162e-06,
|
| 1534 |
+
"loss": 0.4969,
|
| 1535 |
+
"step": 1085
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.4500412881915772,
|
| 1539 |
+
"grad_norm": 2.622744707083321,
|
| 1540 |
+
"learning_rate": 6.712734800865146e-06,
|
| 1541 |
+
"loss": 0.5006,
|
| 1542 |
+
"step": 1090
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.45210569777043763,
|
| 1546 |
+
"grad_norm": 2.5279298037448514,
|
| 1547 |
+
"learning_rate": 6.67882725395687e-06,
|
| 1548 |
+
"loss": 0.4919,
|
| 1549 |
+
"step": 1095
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.4541701073492981,
|
| 1553 |
+
"grad_norm": 2.5696353167432076,
|
| 1554 |
+
"learning_rate": 6.644832464283105e-06,
|
| 1555 |
+
"loss": 0.5006,
|
| 1556 |
+
"step": 1100
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.45623451692815853,
|
| 1560 |
+
"grad_norm": 2.6472120693562675,
|
| 1561 |
+
"learning_rate": 6.6107521984338654e-06,
|
| 1562 |
+
"loss": 0.5222,
|
| 1563 |
+
"step": 1105
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.458298926507019,
|
| 1567 |
+
"grad_norm": 2.5641259833492915,
|
| 1568 |
+
"learning_rate": 6.576588227441063e-06,
|
| 1569 |
+
"loss": 0.5021,
|
| 1570 |
+
"step": 1110
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.4603633360858794,
|
| 1574 |
+
"grad_norm": 2.508674684822535,
|
| 1575 |
+
"learning_rate": 6.5423423266864715e-06,
|
| 1576 |
+
"loss": 0.5019,
|
| 1577 |
+
"step": 1115
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.4624277456647399,
|
| 1581 |
+
"grad_norm": 2.5803067400324546,
|
| 1582 |
+
"learning_rate": 6.508016275809472e-06,
|
| 1583 |
+
"loss": 0.5116,
|
| 1584 |
+
"step": 1120
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.4644921552436003,
|
| 1588 |
+
"grad_norm": 2.4783246238450296,
|
| 1589 |
+
"learning_rate": 6.473611858614557e-06,
|
| 1590 |
+
"loss": 0.4939,
|
| 1591 |
+
"step": 1125
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.4665565648224608,
|
| 1595 |
+
"grad_norm": 2.3961470840043986,
|
| 1596 |
+
"learning_rate": 6.439130862978653e-06,
|
| 1597 |
+
"loss": 0.4964,
|
| 1598 |
+
"step": 1130
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.4686209744013212,
|
| 1602 |
+
"grad_norm": 2.523268688947089,
|
| 1603 |
+
"learning_rate": 6.4045750807581875e-06,
|
| 1604 |
+
"loss": 0.4878,
|
| 1605 |
+
"step": 1135
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.47068538398018167,
|
| 1609 |
+
"grad_norm": 2.464908065215536,
|
| 1610 |
+
"learning_rate": 6.369946307695994e-06,
|
| 1611 |
+
"loss": 0.5004,
|
| 1612 |
+
"step": 1140
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.4727497935590421,
|
| 1616 |
+
"grad_norm": 2.4978854529114556,
|
| 1617 |
+
"learning_rate": 6.335246343327983e-06,
|
| 1618 |
+
"loss": 0.4928,
|
| 1619 |
+
"step": 1145
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.47481420313790257,
|
| 1623 |
+
"grad_norm": 2.5910220265362405,
|
| 1624 |
+
"learning_rate": 6.300476990889622e-06,
|
| 1625 |
+
"loss": 0.4859,
|
| 1626 |
+
"step": 1150
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.476878612716763,
|
| 1630 |
+
"grad_norm": 2.6474515998209314,
|
| 1631 |
+
"learning_rate": 6.2656400572222374e-06,
|
| 1632 |
+
"loss": 0.4968,
|
| 1633 |
+
"step": 1155
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.47894302229562347,
|
| 1637 |
+
"grad_norm": 2.5111508875593627,
|
| 1638 |
+
"learning_rate": 6.230737352679115e-06,
|
| 1639 |
+
"loss": 0.4825,
|
| 1640 |
+
"step": 1160
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.4810074318744839,
|
| 1644 |
+
"grad_norm": 2.6001140755401067,
|
| 1645 |
+
"learning_rate": 6.1957706910314195e-06,
|
| 1646 |
+
"loss": 0.4903,
|
| 1647 |
+
"step": 1165
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.48307184145334436,
|
| 1651 |
+
"grad_norm": 2.4405093084108853,
|
| 1652 |
+
"learning_rate": 6.160741889373948e-06,
|
| 1653 |
+
"loss": 0.4738,
|
| 1654 |
+
"step": 1170
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.4851362510322048,
|
| 1658 |
+
"grad_norm": 2.6122999506914817,
|
| 1659 |
+
"learning_rate": 6.12565276803069e-06,
|
| 1660 |
+
"loss": 0.4851,
|
| 1661 |
+
"step": 1175
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.48720066061106526,
|
| 1665 |
+
"grad_norm": 2.5491172182391284,
|
| 1666 |
+
"learning_rate": 6.090505150460239e-06,
|
| 1667 |
+
"loss": 0.4969,
|
| 1668 |
+
"step": 1180
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.48926507018992565,
|
| 1672 |
+
"grad_norm": 2.5615374385855256,
|
| 1673 |
+
"learning_rate": 6.055300863161035e-06,
|
| 1674 |
+
"loss": 0.4778,
|
| 1675 |
+
"step": 1185
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.4913294797687861,
|
| 1679 |
+
"grad_norm": 2.4469903993231514,
|
| 1680 |
+
"learning_rate": 6.020041735576444e-06,
|
| 1681 |
+
"loss": 0.4787,
|
| 1682 |
+
"step": 1190
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.49339388934764655,
|
| 1686 |
+
"grad_norm": 2.4860974782023346,
|
| 1687 |
+
"learning_rate": 5.9847295999996835e-06,
|
| 1688 |
+
"loss": 0.4914,
|
| 1689 |
+
"step": 1195
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.495458298926507,
|
| 1693 |
+
"grad_norm": 2.4900103589842395,
|
| 1694 |
+
"learning_rate": 5.949366291478621e-06,
|
| 1695 |
+
"loss": 0.4906,
|
| 1696 |
+
"step": 1200
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.49752270850536745,
|
| 1700 |
+
"grad_norm": 2.5283147963068964,
|
| 1701 |
+
"learning_rate": 5.9139536477203945e-06,
|
| 1702 |
+
"loss": 0.4759,
|
| 1703 |
+
"step": 1205
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.4995871180842279,
|
| 1707 |
+
"grad_norm": 2.573137486004109,
|
| 1708 |
+
"learning_rate": 5.878493508995924e-06,
|
| 1709 |
+
"loss": 0.4768,
|
| 1710 |
+
"step": 1210
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.5016515276630884,
|
| 1714 |
+
"grad_norm": 2.579476813837634,
|
| 1715 |
+
"learning_rate": 5.842987718044275e-06,
|
| 1716 |
+
"loss": 0.4679,
|
| 1717 |
+
"step": 1215
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.5037159372419489,
|
| 1721 |
+
"grad_norm": 2.497492462831134,
|
| 1722 |
+
"learning_rate": 5.807438119976904e-06,
|
| 1723 |
+
"loss": 0.4698,
|
| 1724 |
+
"step": 1220
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.5057803468208093,
|
| 1728 |
+
"grad_norm": 2.590655156263669,
|
| 1729 |
+
"learning_rate": 5.771846562181761e-06,
|
| 1730 |
+
"loss": 0.4728,
|
| 1731 |
+
"step": 1225
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.5078447563996696,
|
| 1735 |
+
"grad_norm": 2.5177297962486493,
|
| 1736 |
+
"learning_rate": 5.736214894227304e-06,
|
| 1737 |
+
"loss": 0.473,
|
| 1738 |
+
"step": 1230
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.5099091659785301,
|
| 1742 |
+
"grad_norm": 2.6021365054723775,
|
| 1743 |
+
"learning_rate": 5.700544967766373e-06,
|
| 1744 |
+
"loss": 0.4753,
|
| 1745 |
+
"step": 1235
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.5119735755573905,
|
| 1749 |
+
"grad_norm": 2.604951347166713,
|
| 1750 |
+
"learning_rate": 5.6648386364399645e-06,
|
| 1751 |
+
"loss": 0.47,
|
| 1752 |
+
"step": 1240
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 0.514037985136251,
|
| 1756 |
+
"grad_norm": 2.4157020679627794,
|
| 1757 |
+
"learning_rate": 5.629097755780913e-06,
|
| 1758 |
+
"loss": 0.4711,
|
| 1759 |
+
"step": 1245
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.5161023947151114,
|
| 1763 |
+
"grad_norm": 2.3659395254457167,
|
| 1764 |
+
"learning_rate": 5.59332418311746e-06,
|
| 1765 |
+
"loss": 0.4773,
|
| 1766 |
+
"step": 1250
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 0.5181668042939719,
|
| 1770 |
+
"grad_norm": 2.499361991412955,
|
| 1771 |
+
"learning_rate": 5.557519777476733e-06,
|
| 1772 |
+
"loss": 0.4527,
|
| 1773 |
+
"step": 1255
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.5202312138728323,
|
| 1777 |
+
"grad_norm": 2.5585105365426513,
|
| 1778 |
+
"learning_rate": 5.521686399488145e-06,
|
| 1779 |
+
"loss": 0.4573,
|
| 1780 |
+
"step": 1260
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 0.5222956234516928,
|
| 1784 |
+
"grad_norm": 2.4814508055210567,
|
| 1785 |
+
"learning_rate": 5.485825911286697e-06,
|
| 1786 |
+
"loss": 0.4691,
|
| 1787 |
+
"step": 1265
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.5243600330305532,
|
| 1791 |
+
"grad_norm": 2.6081291748684716,
|
| 1792 |
+
"learning_rate": 5.449940176416213e-06,
|
| 1793 |
+
"loss": 0.4526,
|
| 1794 |
+
"step": 1270
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 0.5264244426094137,
|
| 1798 |
+
"grad_norm": 2.587126119981003,
|
| 1799 |
+
"learning_rate": 5.414031059732502e-06,
|
| 1800 |
+
"loss": 0.4605,
|
| 1801 |
+
"step": 1275
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.5284888521882741,
|
| 1805 |
+
"grad_norm": 2.5458768564010765,
|
| 1806 |
+
"learning_rate": 5.378100427306439e-06,
|
| 1807 |
+
"loss": 0.4467,
|
| 1808 |
+
"step": 1280
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 0.5305532617671346,
|
| 1812 |
+
"grad_norm": 2.422344978356131,
|
| 1813 |
+
"learning_rate": 5.3421501463269976e-06,
|
| 1814 |
+
"loss": 0.4563,
|
| 1815 |
+
"step": 1285
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.532617671345995,
|
| 1819 |
+
"grad_norm": 2.481246363328885,
|
| 1820 |
+
"learning_rate": 5.30618208500422e-06,
|
| 1821 |
+
"loss": 0.4496,
|
| 1822 |
+
"step": 1290
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 0.5346820809248555,
|
| 1826 |
+
"grad_norm": 2.5964265890691274,
|
| 1827 |
+
"learning_rate": 5.270198112472128e-06,
|
| 1828 |
+
"loss": 0.4487,
|
| 1829 |
+
"step": 1295
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.5367464905037159,
|
| 1833 |
+
"grad_norm": 2.375375823310664,
|
| 1834 |
+
"learning_rate": 5.234200098691597e-06,
|
| 1835 |
+
"loss": 0.4492,
|
| 1836 |
+
"step": 1300
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 0.5388109000825764,
|
| 1840 |
+
"grad_norm": 2.482312531712164,
|
| 1841 |
+
"learning_rate": 5.19818991435317e-06,
|
| 1842 |
+
"loss": 0.4524,
|
| 1843 |
+
"step": 1305
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.5408753096614368,
|
| 1847 |
+
"grad_norm": 2.6268917122173154,
|
| 1848 |
+
"learning_rate": 5.162169430779861e-06,
|
| 1849 |
+
"loss": 0.4343,
|
| 1850 |
+
"step": 1310
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.5429397192402973,
|
| 1854 |
+
"grad_norm": 2.543083790336233,
|
| 1855 |
+
"learning_rate": 5.126140519829888e-06,
|
| 1856 |
+
"loss": 0.4738,
|
| 1857 |
+
"step": 1315
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.5450041288191577,
|
| 1861 |
+
"grad_norm": 2.4547121862030865,
|
| 1862 |
+
"learning_rate": 5.090105053799418e-06,
|
| 1863 |
+
"loss": 0.4604,
|
| 1864 |
+
"step": 1320
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 0.5470685383980182,
|
| 1868 |
+
"grad_norm": 2.5806078709462295,
|
| 1869 |
+
"learning_rate": 5.054064905325262e-06,
|
| 1870 |
+
"loss": 0.4571,
|
| 1871 |
+
"step": 1325
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.5491329479768786,
|
| 1875 |
+
"grad_norm": 2.538503365518751,
|
| 1876 |
+
"learning_rate": 5.018021947287556e-06,
|
| 1877 |
+
"loss": 0.4432,
|
| 1878 |
+
"step": 1330
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 0.5511973575557391,
|
| 1882 |
+
"grad_norm": 2.4205037183193157,
|
| 1883 |
+
"learning_rate": 4.981978052712446e-06,
|
| 1884 |
+
"loss": 0.4545,
|
| 1885 |
+
"step": 1335
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.5532617671345995,
|
| 1889 |
+
"grad_norm": 2.5910957054221817,
|
| 1890 |
+
"learning_rate": 4.9459350946747405e-06,
|
| 1891 |
+
"loss": 0.4584,
|
| 1892 |
+
"step": 1340
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 0.55532617671346,
|
| 1896 |
+
"grad_norm": 2.423593643872453,
|
| 1897 |
+
"learning_rate": 4.909894946200583e-06,
|
| 1898 |
+
"loss": 0.454,
|
| 1899 |
+
"step": 1345
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.5573905862923204,
|
| 1903 |
+
"grad_norm": 2.491439793223575,
|
| 1904 |
+
"learning_rate": 4.873859480170113e-06,
|
| 1905 |
+
"loss": 0.4535,
|
| 1906 |
+
"step": 1350
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 0.5594549958711809,
|
| 1910 |
+
"grad_norm": 2.6251023268801106,
|
| 1911 |
+
"learning_rate": 4.83783056922014e-06,
|
| 1912 |
+
"loss": 0.4475,
|
| 1913 |
+
"step": 1355
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.5615194054500413,
|
| 1917 |
+
"grad_norm": 2.379012672081149,
|
| 1918 |
+
"learning_rate": 4.801810085646831e-06,
|
| 1919 |
+
"loss": 0.4427,
|
| 1920 |
+
"step": 1360
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 0.5635838150289018,
|
| 1924 |
+
"grad_norm": 2.438307211574731,
|
| 1925 |
+
"learning_rate": 4.765799901308405e-06,
|
| 1926 |
+
"loss": 0.4392,
|
| 1927 |
+
"step": 1365
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.5656482246077622,
|
| 1931 |
+
"grad_norm": 2.4743966890129534,
|
| 1932 |
+
"learning_rate": 4.729801887527872e-06,
|
| 1933 |
+
"loss": 0.4376,
|
| 1934 |
+
"step": 1370
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 0.5677126341866227,
|
| 1938 |
+
"grad_norm": 2.4438402043185636,
|
| 1939 |
+
"learning_rate": 4.6938179149957815e-06,
|
| 1940 |
+
"loss": 0.4448,
|
| 1941 |
+
"step": 1375
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.5697770437654831,
|
| 1945 |
+
"grad_norm": 2.3233363056641587,
|
| 1946 |
+
"learning_rate": 4.657849853673004e-06,
|
| 1947 |
+
"loss": 0.4332,
|
| 1948 |
+
"step": 1380
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 0.5718414533443436,
|
| 1952 |
+
"grad_norm": 2.3513159156694536,
|
| 1953 |
+
"learning_rate": 4.621899572693564e-06,
|
| 1954 |
+
"loss": 0.4286,
|
| 1955 |
+
"step": 1385
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.573905862923204,
|
| 1959 |
+
"grad_norm": 2.452790907750448,
|
| 1960 |
+
"learning_rate": 4.585968940267499e-06,
|
| 1961 |
+
"loss": 0.4329,
|
| 1962 |
+
"step": 1390
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 0.5759702725020645,
|
| 1966 |
+
"grad_norm": 2.4876165011978544,
|
| 1967 |
+
"learning_rate": 4.550059823583788e-06,
|
| 1968 |
+
"loss": 0.4368,
|
| 1969 |
+
"step": 1395
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.5780346820809249,
|
| 1973 |
+
"grad_norm": 2.4110190508295926,
|
| 1974 |
+
"learning_rate": 4.514174088713305e-06,
|
| 1975 |
+
"loss": 0.4294,
|
| 1976 |
+
"step": 1400
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 0.5800990916597853,
|
| 1980 |
+
"grad_norm": 2.4790636104654724,
|
| 1981 |
+
"learning_rate": 4.478313600511856e-06,
|
| 1982 |
+
"loss": 0.438,
|
| 1983 |
+
"step": 1405
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.5821635012386458,
|
| 1987 |
+
"grad_norm": 2.5304633815274062,
|
| 1988 |
+
"learning_rate": 4.442480222523269e-06,
|
| 1989 |
+
"loss": 0.4383,
|
| 1990 |
+
"step": 1410
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 0.5842279108175062,
|
| 1994 |
+
"grad_norm": 2.365309103378621,
|
| 1995 |
+
"learning_rate": 4.4066758168825414e-06,
|
| 1996 |
+
"loss": 0.4383,
|
| 1997 |
+
"step": 1415
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.5862923203963666,
|
| 2001 |
+
"grad_norm": 2.4670833952729687,
|
| 2002 |
+
"learning_rate": 4.370902244219088e-06,
|
| 2003 |
+
"loss": 0.4389,
|
| 2004 |
+
"step": 1420
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 0.588356729975227,
|
| 2008 |
+
"grad_norm": 2.3390938676909734,
|
| 2009 |
+
"learning_rate": 4.335161363560037e-06,
|
| 2010 |
+
"loss": 0.4291,
|
| 2011 |
+
"step": 1425
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.5904211395540875,
|
| 2015 |
+
"grad_norm": 2.362644766829775,
|
| 2016 |
+
"learning_rate": 4.299455032233631e-06,
|
| 2017 |
+
"loss": 0.4288,
|
| 2018 |
+
"step": 1430
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 0.5924855491329479,
|
| 2022 |
+
"grad_norm": 2.445730007800526,
|
| 2023 |
+
"learning_rate": 4.263785105772696e-06,
|
| 2024 |
+
"loss": 0.4335,
|
| 2025 |
+
"step": 1435
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.5945499587118084,
|
| 2029 |
+
"grad_norm": 2.303973634970439,
|
| 2030 |
+
"learning_rate": 4.22815343781824e-06,
|
| 2031 |
+
"loss": 0.4366,
|
| 2032 |
+
"step": 1440
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 0.5966143682906688,
|
| 2036 |
+
"grad_norm": 2.391887494831502,
|
| 2037 |
+
"learning_rate": 4.192561880023099e-06,
|
| 2038 |
+
"loss": 0.4261,
|
| 2039 |
+
"step": 1445
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.5986787778695293,
|
| 2043 |
+
"grad_norm": 2.293302291662098,
|
| 2044 |
+
"learning_rate": 4.157012281955726e-06,
|
| 2045 |
+
"loss": 0.424,
|
| 2046 |
+
"step": 1450
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 0.6007431874483897,
|
| 2050 |
+
"grad_norm": 2.3712447663578655,
|
| 2051 |
+
"learning_rate": 4.1215064910040795e-06,
|
| 2052 |
+
"loss": 0.4314,
|
| 2053 |
+
"step": 1455
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.6028075970272502,
|
| 2057 |
+
"grad_norm": 2.381812200033987,
|
| 2058 |
+
"learning_rate": 4.086046352279606e-06,
|
| 2059 |
+
"loss": 0.4227,
|
| 2060 |
+
"step": 1460
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 0.6048720066061106,
|
| 2064 |
+
"grad_norm": 2.4743735981326114,
|
| 2065 |
+
"learning_rate": 4.050633708521381e-06,
|
| 2066 |
+
"loss": 0.4158,
|
| 2067 |
+
"step": 1465
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.6069364161849711,
|
| 2071 |
+
"grad_norm": 2.396322395044398,
|
| 2072 |
+
"learning_rate": 4.015270400000317e-06,
|
| 2073 |
+
"loss": 0.42,
|
| 2074 |
+
"step": 1470
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 0.6090008257638315,
|
| 2078 |
+
"grad_norm": 2.565114051952279,
|
| 2079 |
+
"learning_rate": 3.979958264423558e-06,
|
| 2080 |
+
"loss": 0.4155,
|
| 2081 |
+
"step": 1475
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.611065235342692,
|
| 2085 |
+
"grad_norm": 2.4934554445972954,
|
| 2086 |
+
"learning_rate": 3.944699136838965e-06,
|
| 2087 |
+
"loss": 0.4126,
|
| 2088 |
+
"step": 1480
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 0.6131296449215524,
|
| 2092 |
+
"grad_norm": 2.4162398419293187,
|
| 2093 |
+
"learning_rate": 3.909494849539761e-06,
|
| 2094 |
+
"loss": 0.4213,
|
| 2095 |
+
"step": 1485
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.6151940545004129,
|
| 2099 |
+
"grad_norm": 2.464180248251729,
|
| 2100 |
+
"learning_rate": 3.874347231969312e-06,
|
| 2101 |
+
"loss": 0.4235,
|
| 2102 |
+
"step": 1490
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 0.6172584640792733,
|
| 2106 |
+
"grad_norm": 2.4941582294474434,
|
| 2107 |
+
"learning_rate": 3.839258110626053e-06,
|
| 2108 |
+
"loss": 0.4307,
|
| 2109 |
+
"step": 1495
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.6193228736581338,
|
| 2113 |
+
"grad_norm": 2.276754213405921,
|
| 2114 |
+
"learning_rate": 3.8042293089685813e-06,
|
| 2115 |
+
"loss": 0.4065,
|
| 2116 |
+
"step": 1500
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.6213872832369942,
|
| 2120 |
+
"grad_norm": 2.324659425092549,
|
| 2121 |
+
"learning_rate": 3.769262647320886e-06,
|
| 2122 |
+
"loss": 0.4179,
|
| 2123 |
+
"step": 1505
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.6234516928158547,
|
| 2127 |
+
"grad_norm": 2.3013999943076815,
|
| 2128 |
+
"learning_rate": 3.7343599427777634e-06,
|
| 2129 |
+
"loss": 0.4157,
|
| 2130 |
+
"step": 1510
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 0.6255161023947151,
|
| 2134 |
+
"grad_norm": 2.3853366654087633,
|
| 2135 |
+
"learning_rate": 3.69952300911038e-06,
|
| 2136 |
+
"loss": 0.4087,
|
| 2137 |
+
"step": 1515
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.6275805119735756,
|
| 2141 |
+
"grad_norm": 2.3274220274703206,
|
| 2142 |
+
"learning_rate": 3.6647536566720186e-06,
|
| 2143 |
+
"loss": 0.4203,
|
| 2144 |
+
"step": 1520
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.629644921552436,
|
| 2148 |
+
"grad_norm": 2.4392433402643947,
|
| 2149 |
+
"learning_rate": 3.630053692304005e-06,
|
| 2150 |
+
"loss": 0.4091,
|
| 2151 |
+
"step": 1525
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.6317093311312965,
|
| 2155 |
+
"grad_norm": 2.4428540121878894,
|
| 2156 |
+
"learning_rate": 3.5954249192418133e-06,
|
| 2157 |
+
"loss": 0.4255,
|
| 2158 |
+
"step": 1530
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 0.6337737407101569,
|
| 2162 |
+
"grad_norm": 2.3810770043048692,
|
| 2163 |
+
"learning_rate": 3.560869137021349e-06,
|
| 2164 |
+
"loss": 0.4103,
|
| 2165 |
+
"step": 1535
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.6358381502890174,
|
| 2169 |
+
"grad_norm": 2.301863999851205,
|
| 2170 |
+
"learning_rate": 3.526388141385444e-06,
|
| 2171 |
+
"loss": 0.4155,
|
| 2172 |
+
"step": 1540
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 0.6379025598678778,
|
| 2176 |
+
"grad_norm": 2.400363519907276,
|
| 2177 |
+
"learning_rate": 3.4919837241905308e-06,
|
| 2178 |
+
"loss": 0.4224,
|
| 2179 |
+
"step": 1545
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.6399669694467383,
|
| 2183 |
+
"grad_norm": 2.477498090820749,
|
| 2184 |
+
"learning_rate": 3.4576576733135284e-06,
|
| 2185 |
+
"loss": 0.3938,
|
| 2186 |
+
"step": 1550
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.6420313790255987,
|
| 2190 |
+
"grad_norm": 2.707387721012179,
|
| 2191 |
+
"learning_rate": 3.4234117725589385e-06,
|
| 2192 |
+
"loss": 0.4111,
|
| 2193 |
+
"step": 1555
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.6440957886044592,
|
| 2197 |
+
"grad_norm": 2.341459106750255,
|
| 2198 |
+
"learning_rate": 3.3892478015661362e-06,
|
| 2199 |
+
"loss": 0.4139,
|
| 2200 |
+
"step": 1560
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 0.6461601981833196,
|
| 2204 |
+
"grad_norm": 2.4202740830209137,
|
| 2205 |
+
"learning_rate": 3.355167535716897e-06,
|
| 2206 |
+
"loss": 0.4127,
|
| 2207 |
+
"step": 1565
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.64822460776218,
|
| 2211 |
+
"grad_norm": 2.3816575196973577,
|
| 2212 |
+
"learning_rate": 3.321172746043131e-06,
|
| 2213 |
+
"loss": 0.4002,
|
| 2214 |
+
"step": 1570
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 0.6502890173410405,
|
| 2218 |
+
"grad_norm": 2.454435864594131,
|
| 2219 |
+
"learning_rate": 3.2872651991348548e-06,
|
| 2220 |
+
"loss": 0.403,
|
| 2221 |
+
"step": 1575
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.652353426919901,
|
| 2225 |
+
"grad_norm": 2.591163202406022,
|
| 2226 |
+
"learning_rate": 3.253446657048382e-06,
|
| 2227 |
+
"loss": 0.4072,
|
| 2228 |
+
"step": 1580
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 0.6544178364987614,
|
| 2232 |
+
"grad_norm": 2.4282921305894676,
|
| 2233 |
+
"learning_rate": 3.2197188772147593e-06,
|
| 2234 |
+
"loss": 0.3869,
|
| 2235 |
+
"step": 1585
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.6564822460776218,
|
| 2239 |
+
"grad_norm": 2.4682745998960827,
|
| 2240 |
+
"learning_rate": 3.186083612348434e-06,
|
| 2241 |
+
"loss": 0.4028,
|
| 2242 |
+
"step": 1590
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 0.6585466556564823,
|
| 2246 |
+
"grad_norm": 2.376999029803135,
|
| 2247 |
+
"learning_rate": 3.1525426103561774e-06,
|
| 2248 |
+
"loss": 0.4064,
|
| 2249 |
+
"step": 1595
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.6606110652353427,
|
| 2253 |
+
"grad_norm": 2.370838413822066,
|
| 2254 |
+
"learning_rate": 3.119097614246252e-06,
|
| 2255 |
+
"loss": 0.3978,
|
| 2256 |
+
"step": 1600
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 0.6626754748142032,
|
| 2260 |
+
"grad_norm": 2.362260369144417,
|
| 2261 |
+
"learning_rate": 3.0857503620378284e-06,
|
| 2262 |
+
"loss": 0.3905,
|
| 2263 |
+
"step": 1605
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.6647398843930635,
|
| 2267 |
+
"grad_norm": 2.421231306606393,
|
| 2268 |
+
"learning_rate": 3.052502586670669e-06,
|
| 2269 |
+
"loss": 0.4053,
|
| 2270 |
+
"step": 1610
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 0.666804293971924,
|
| 2274 |
+
"grad_norm": 2.395970410200359,
|
| 2275 |
+
"learning_rate": 3.0193560159150747e-06,
|
| 2276 |
+
"loss": 0.3943,
|
| 2277 |
+
"step": 1615
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.6688687035507844,
|
| 2281 |
+
"grad_norm": 2.5057121725436917,
|
| 2282 |
+
"learning_rate": 2.986312372282097e-06,
|
| 2283 |
+
"loss": 0.4182,
|
| 2284 |
+
"step": 1620
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 0.6709331131296449,
|
| 2288 |
+
"grad_norm": 2.3776161687385207,
|
| 2289 |
+
"learning_rate": 2.9533733729340274e-06,
|
| 2290 |
+
"loss": 0.4077,
|
| 2291 |
+
"step": 1625
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.6729975227085053,
|
| 2295 |
+
"grad_norm": 2.5915693629163217,
|
| 2296 |
+
"learning_rate": 2.920540729595159e-06,
|
| 2297 |
+
"loss": 0.4085,
|
| 2298 |
+
"step": 1630
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 0.6750619322873658,
|
| 2302 |
+
"grad_norm": 2.443160283840937,
|
| 2303 |
+
"learning_rate": 2.8878161484628364e-06,
|
| 2304 |
+
"loss": 0.4028,
|
| 2305 |
+
"step": 1635
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.6771263418662262,
|
| 2309 |
+
"grad_norm": 2.420398270818125,
|
| 2310 |
+
"learning_rate": 2.8552013301187898e-06,
|
| 2311 |
+
"loss": 0.3972,
|
| 2312 |
+
"step": 1640
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 0.6791907514450867,
|
| 2316 |
+
"grad_norm": 2.4196367974051265,
|
| 2317 |
+
"learning_rate": 2.8226979694407657e-06,
|
| 2318 |
+
"loss": 0.4067,
|
| 2319 |
+
"step": 1645
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.6812551610239471,
|
| 2323 |
+
"grad_norm": 2.438274119472032,
|
| 2324 |
+
"learning_rate": 2.790307755514442e-06,
|
| 2325 |
+
"loss": 0.4032,
|
| 2326 |
+
"step": 1650
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 0.6833195706028076,
|
| 2330 |
+
"grad_norm": 3.0023110501423944,
|
| 2331 |
+
"learning_rate": 2.7580323715456564e-06,
|
| 2332 |
+
"loss": 0.4121,
|
| 2333 |
+
"step": 1655
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 0.685383980181668,
|
| 2337 |
+
"grad_norm": 2.3597852522402474,
|
| 2338 |
+
"learning_rate": 2.7258734947729428e-06,
|
| 2339 |
+
"loss": 0.3938,
|
| 2340 |
+
"step": 1660
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 0.6874483897605285,
|
| 2344 |
+
"grad_norm": 2.4413156249499854,
|
| 2345 |
+
"learning_rate": 2.6938327963803545e-06,
|
| 2346 |
+
"loss": 0.3925,
|
| 2347 |
+
"step": 1665
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 0.6895127993393889,
|
| 2351 |
+
"grad_norm": 2.441149846551036,
|
| 2352 |
+
"learning_rate": 2.6619119414106385e-06,
|
| 2353 |
+
"loss": 0.3902,
|
| 2354 |
+
"step": 1670
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 0.6915772089182494,
|
| 2358 |
+
"grad_norm": 2.4274483132890685,
|
| 2359 |
+
"learning_rate": 2.6301125886786965e-06,
|
| 2360 |
+
"loss": 0.3933,
|
| 2361 |
+
"step": 1675
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 0.6936416184971098,
|
| 2365 |
+
"grad_norm": 2.514301355730002,
|
| 2366 |
+
"learning_rate": 2.5984363906853814e-06,
|
| 2367 |
+
"loss": 0.3847,
|
| 2368 |
+
"step": 1680
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 0.6957060280759703,
|
| 2372 |
+
"grad_norm": 2.23025942549343,
|
| 2373 |
+
"learning_rate": 2.566884993531628e-06,
|
| 2374 |
+
"loss": 0.3868,
|
| 2375 |
+
"step": 1685
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 0.6977704376548307,
|
| 2379 |
+
"grad_norm": 2.3910909958649764,
|
| 2380 |
+
"learning_rate": 2.5354600368329108e-06,
|
| 2381 |
+
"loss": 0.379,
|
| 2382 |
+
"step": 1690
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 0.6998348472336912,
|
| 2386 |
+
"grad_norm": 2.5413951969823554,
|
| 2387 |
+
"learning_rate": 2.5041631536340374e-06,
|
| 2388 |
+
"loss": 0.3909,
|
| 2389 |
+
"step": 1695
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 0.7018992568125516,
|
| 2393 |
+
"grad_norm": 2.360003867942285,
|
| 2394 |
+
"learning_rate": 2.472995970324282e-06,
|
| 2395 |
+
"loss": 0.3888,
|
| 2396 |
+
"step": 1700
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 0.7039636663914121,
|
| 2400 |
+
"grad_norm": 2.4621248065886516,
|
| 2401 |
+
"learning_rate": 2.4419601065528703e-06,
|
| 2402 |
+
"loss": 0.3803,
|
| 2403 |
+
"step": 1705
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 0.7060280759702725,
|
| 2407 |
+
"grad_norm": 2.4221633580536865,
|
| 2408 |
+
"learning_rate": 2.4110571751448154e-06,
|
| 2409 |
+
"loss": 0.3804,
|
| 2410 |
+
"step": 1710
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 0.708092485549133,
|
| 2414 |
+
"grad_norm": 2.3044799343595685,
|
| 2415 |
+
"learning_rate": 2.3802887820171012e-06,
|
| 2416 |
+
"loss": 0.3709,
|
| 2417 |
+
"step": 1715
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.7101568951279934,
|
| 2421 |
+
"grad_norm": 2.3101555840305585,
|
| 2422 |
+
"learning_rate": 2.349656526095224e-06,
|
| 2423 |
+
"loss": 0.382,
|
| 2424 |
+
"step": 1720
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 0.7122213047068539,
|
| 2428 |
+
"grad_norm": 2.439524803446898,
|
| 2429 |
+
"learning_rate": 2.3191619992301144e-06,
|
| 2430 |
+
"loss": 0.3969,
|
| 2431 |
+
"step": 1725
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.7142857142857143,
|
| 2435 |
+
"grad_norm": 2.3771584605894174,
|
| 2436 |
+
"learning_rate": 2.2888067861153983e-06,
|
| 2437 |
+
"loss": 0.3792,
|
| 2438 |
+
"step": 1730
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 0.7163501238645748,
|
| 2442 |
+
"grad_norm": 2.5666012183468587,
|
| 2443 |
+
"learning_rate": 2.2585924642050638e-06,
|
| 2444 |
+
"loss": 0.3802,
|
| 2445 |
+
"step": 1735
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 0.7184145334434352,
|
| 2449 |
+
"grad_norm": 2.3145141740784307,
|
| 2450 |
+
"learning_rate": 2.2285206036314684e-06,
|
| 2451 |
+
"loss": 0.3835,
|
| 2452 |
+
"step": 1740
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 0.7204789430222956,
|
| 2456 |
+
"grad_norm": 2.520653602273766,
|
| 2457 |
+
"learning_rate": 2.1985927671237605e-06,
|
| 2458 |
+
"loss": 0.3766,
|
| 2459 |
+
"step": 1745
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 0.7225433526011561,
|
| 2463 |
+
"grad_norm": 2.470460484865602,
|
| 2464 |
+
"learning_rate": 2.168810509926659e-06,
|
| 2465 |
+
"loss": 0.3897,
|
| 2466 |
+
"step": 1750
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 0.7246077621800165,
|
| 2470 |
+
"grad_norm": 2.408249418201136,
|
| 2471 |
+
"learning_rate": 2.1391753797196328e-06,
|
| 2472 |
+
"loss": 0.3952,
|
| 2473 |
+
"step": 1755
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 0.726672171758877,
|
| 2477 |
+
"grad_norm": 2.4402970653227247,
|
| 2478 |
+
"learning_rate": 2.1096889165364894e-06,
|
| 2479 |
+
"loss": 0.375,
|
| 2480 |
+
"step": 1760
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 0.7287365813377374,
|
| 2484 |
+
"grad_norm": 2.4710285995197188,
|
| 2485 |
+
"learning_rate": 2.0803526526853206e-06,
|
| 2486 |
+
"loss": 0.3748,
|
| 2487 |
+
"step": 1765
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 0.7308009909165979,
|
| 2491 |
+
"grad_norm": 2.2841746369286633,
|
| 2492 |
+
"learning_rate": 2.0511681126688883e-06,
|
| 2493 |
+
"loss": 0.3799,
|
| 2494 |
+
"step": 1770
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 0.7328654004954583,
|
| 2498 |
+
"grad_norm": 2.46102171882109,
|
| 2499 |
+
"learning_rate": 2.022136813105401e-06,
|
| 2500 |
+
"loss": 0.3729,
|
| 2501 |
+
"step": 1775
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 0.7349298100743188,
|
| 2505 |
+
"grad_norm": 2.2829340264643156,
|
| 2506 |
+
"learning_rate": 1.9932602626496994e-06,
|
| 2507 |
+
"loss": 0.3722,
|
| 2508 |
+
"step": 1780
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 0.7369942196531792,
|
| 2512 |
+
"grad_norm": 2.4439441720908,
|
| 2513 |
+
"learning_rate": 1.9645399619148515e-06,
|
| 2514 |
+
"loss": 0.3774,
|
| 2515 |
+
"step": 1785
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 0.7390586292320397,
|
| 2519 |
+
"grad_norm": 2.363486720634483,
|
| 2520 |
+
"learning_rate": 1.9359774033941757e-06,
|
| 2521 |
+
"loss": 0.3775,
|
| 2522 |
+
"step": 1790
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 0.7411230388109001,
|
| 2526 |
+
"grad_norm": 2.2893262909558065,
|
| 2527 |
+
"learning_rate": 1.9075740713836854e-06,
|
| 2528 |
+
"loss": 0.3851,
|
| 2529 |
+
"step": 1795
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 0.7431874483897605,
|
| 2533 |
+
"grad_norm": 2.381579584567696,
|
| 2534 |
+
"learning_rate": 1.8793314419049446e-06,
|
| 2535 |
+
"loss": 0.3736,
|
| 2536 |
+
"step": 1800
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 0.7452518579686209,
|
| 2540 |
+
"grad_norm": 2.3588892144435714,
|
| 2541 |
+
"learning_rate": 1.8512509826283752e-06,
|
| 2542 |
+
"loss": 0.3647,
|
| 2543 |
+
"step": 1805
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 0.7473162675474814,
|
| 2547 |
+
"grad_norm": 2.468444814623241,
|
| 2548 |
+
"learning_rate": 1.8233341527969777e-06,
|
| 2549 |
+
"loss": 0.3731,
|
| 2550 |
+
"step": 1810
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 0.7493806771263418,
|
| 2554 |
+
"grad_norm": 2.4216200751888217,
|
| 2555 |
+
"learning_rate": 1.7955824031505097e-06,
|
| 2556 |
+
"loss": 0.3741,
|
| 2557 |
+
"step": 1815
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 0.7514450867052023,
|
| 2561 |
+
"grad_norm": 2.3925423466955884,
|
| 2562 |
+
"learning_rate": 1.7679971758500836e-06,
|
| 2563 |
+
"loss": 0.3652,
|
| 2564 |
+
"step": 1820
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 0.7535094962840627,
|
| 2568 |
+
"grad_norm": 2.386508421187067,
|
| 2569 |
+
"learning_rate": 1.7405799044032356e-06,
|
| 2570 |
+
"loss": 0.3685,
|
| 2571 |
+
"step": 1825
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 0.7555739058629232,
|
| 2575 |
+
"grad_norm": 2.439989821363405,
|
| 2576 |
+
"learning_rate": 1.7133320135894233e-06,
|
| 2577 |
+
"loss": 0.3653,
|
| 2578 |
+
"step": 1830
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 0.7576383154417836,
|
| 2582 |
+
"grad_norm": 2.3039350711469186,
|
| 2583 |
+
"learning_rate": 1.686254919385985e-06,
|
| 2584 |
+
"loss": 0.3783,
|
| 2585 |
+
"step": 1835
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 0.7597027250206441,
|
| 2589 |
+
"grad_norm": 2.216200410510777,
|
| 2590 |
+
"learning_rate": 1.6593500288945574e-06,
|
| 2591 |
+
"loss": 0.3646,
|
| 2592 |
+
"step": 1840
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 0.7617671345995045,
|
| 2596 |
+
"grad_norm": 2.4989495842816405,
|
| 2597 |
+
"learning_rate": 1.6326187402679577e-06,
|
| 2598 |
+
"loss": 0.3741,
|
| 2599 |
+
"step": 1845
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 0.763831544178365,
|
| 2603 |
+
"grad_norm": 2.4154932431289673,
|
| 2604 |
+
"learning_rate": 1.6060624426375222e-06,
|
| 2605 |
+
"loss": 0.3698,
|
| 2606 |
+
"step": 1850
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 0.7658959537572254,
|
| 2610 |
+
"grad_norm": 2.473649546182009,
|
| 2611 |
+
"learning_rate": 1.5796825160409168e-06,
|
| 2612 |
+
"loss": 0.3672,
|
| 2613 |
+
"step": 1855
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 0.7679603633360859,
|
| 2617 |
+
"grad_norm": 2.355038901564694,
|
| 2618 |
+
"learning_rate": 1.5534803313504215e-06,
|
| 2619 |
+
"loss": 0.3566,
|
| 2620 |
+
"step": 1860
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 0.7700247729149463,
|
| 2624 |
+
"grad_norm": 2.3588413583977625,
|
| 2625 |
+
"learning_rate": 1.5274572502016982e-06,
|
| 2626 |
+
"loss": 0.3711,
|
| 2627 |
+
"step": 1865
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 0.7720891824938068,
|
| 2631 |
+
"grad_norm": 2.401065534914905,
|
| 2632 |
+
"learning_rate": 1.5016146249230229e-06,
|
| 2633 |
+
"loss": 0.3736,
|
| 2634 |
+
"step": 1870
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 0.7741535920726672,
|
| 2638 |
+
"grad_norm": 2.342195370497388,
|
| 2639 |
+
"learning_rate": 1.4759537984650114e-06,
|
| 2640 |
+
"loss": 0.3626,
|
| 2641 |
+
"step": 1875
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 0.7762180016515277,
|
| 2645 |
+
"grad_norm": 2.3601036223952634,
|
| 2646 |
+
"learning_rate": 1.4504761043308346e-06,
|
| 2647 |
+
"loss": 0.3534,
|
| 2648 |
+
"step": 1880
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 0.7782824112303881,
|
| 2652 |
+
"grad_norm": 2.3058771526048405,
|
| 2653 |
+
"learning_rate": 1.425182866506918e-06,
|
| 2654 |
+
"loss": 0.3633,
|
| 2655 |
+
"step": 1885
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 0.7803468208092486,
|
| 2659 |
+
"grad_norm": 2.308152081660379,
|
| 2660 |
+
"learning_rate": 1.4000753993941369e-06,
|
| 2661 |
+
"loss": 0.3723,
|
| 2662 |
+
"step": 1890
|
| 2663 |
+
},
|
| 2664 |
+
{
|
| 2665 |
+
"epoch": 0.782411230388109,
|
| 2666 |
+
"grad_norm": 2.4604302877257664,
|
| 2667 |
+
"learning_rate": 1.3751550077395181e-06,
|
| 2668 |
+
"loss": 0.3523,
|
| 2669 |
+
"step": 1895
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 0.7844756399669695,
|
| 2673 |
+
"grad_norm": 2.551739458655361,
|
| 2674 |
+
"learning_rate": 1.3504229865684326e-06,
|
| 2675 |
+
"loss": 0.3706,
|
| 2676 |
+
"step": 1900
|
| 2677 |
+
},
|
| 2678 |
+
{
|
| 2679 |
+
"epoch": 0.7865400495458299,
|
| 2680 |
+
"grad_norm": 2.4143979686568104,
|
| 2681 |
+
"learning_rate": 1.3258806211172954e-06,
|
| 2682 |
+
"loss": 0.3588,
|
| 2683 |
+
"step": 1905
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 0.7886044591246903,
|
| 2687 |
+
"grad_norm": 2.364426767604513,
|
| 2688 |
+
"learning_rate": 1.3015291867667757e-06,
|
| 2689 |
+
"loss": 0.3508,
|
| 2690 |
+
"step": 1910
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 0.7906688687035508,
|
| 2694 |
+
"grad_norm": 2.3233651206895147,
|
| 2695 |
+
"learning_rate": 1.2773699489755343e-06,
|
| 2696 |
+
"loss": 0.3571,
|
| 2697 |
+
"step": 1915
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 0.7927332782824112,
|
| 2701 |
+
"grad_norm": 2.3196733264987675,
|
| 2702 |
+
"learning_rate": 1.2534041632144407e-06,
|
| 2703 |
+
"loss": 0.3405,
|
| 2704 |
+
"step": 1920
|
| 2705 |
+
},
|
| 2706 |
+
{
|
| 2707 |
+
"epoch": 0.7947976878612717,
|
| 2708 |
+
"grad_norm": 2.347467115991222,
|
| 2709 |
+
"learning_rate": 1.2296330749013408e-06,
|
| 2710 |
+
"loss": 0.3502,
|
| 2711 |
+
"step": 1925
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 0.7968620974401321,
|
| 2715 |
+
"grad_norm": 2.3004029534314174,
|
| 2716 |
+
"learning_rate": 1.2060579193363431e-06,
|
| 2717 |
+
"loss": 0.3564,
|
| 2718 |
+
"step": 1930
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 0.7989265070189926,
|
| 2722 |
+
"grad_norm": 2.5374233309055083,
|
| 2723 |
+
"learning_rate": 1.1826799216376128e-06,
|
| 2724 |
+
"loss": 0.3778,
|
| 2725 |
+
"step": 1935
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 0.800990916597853,
|
| 2729 |
+
"grad_norm": 2.4431483706896007,
|
| 2730 |
+
"learning_rate": 1.1595002966777152e-06,
|
| 2731 |
+
"loss": 0.356,
|
| 2732 |
+
"step": 1940
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 0.8030553261767135,
|
| 2736 |
+
"grad_norm": 2.35423434746266,
|
| 2737 |
+
"learning_rate": 1.136520249020478e-06,
|
| 2738 |
+
"loss": 0.3491,
|
| 2739 |
+
"step": 1945
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 0.8051197357555739,
|
| 2743 |
+
"grad_norm": 2.3767268596250672,
|
| 2744 |
+
"learning_rate": 1.113740972858398e-06,
|
| 2745 |
+
"loss": 0.348,
|
| 2746 |
+
"step": 1950
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 0.8071841453344344,
|
| 2750 |
+
"grad_norm": 2.4631890684934965,
|
| 2751 |
+
"learning_rate": 1.0911636519505791e-06,
|
| 2752 |
+
"loss": 0.3671,
|
| 2753 |
+
"step": 1955
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 0.8092485549132948,
|
| 2757 |
+
"grad_norm": 2.201423417502954,
|
| 2758 |
+
"learning_rate": 1.068789459561223e-06,
|
| 2759 |
+
"loss": 0.3459,
|
| 2760 |
+
"step": 1960
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 0.8113129644921553,
|
| 2764 |
+
"grad_norm": 2.36077824921438,
|
| 2765 |
+
"learning_rate": 1.0466195583986487e-06,
|
| 2766 |
+
"loss": 0.3639,
|
| 2767 |
+
"step": 1965
|
| 2768 |
+
},
|
| 2769 |
+
{
|
| 2770 |
+
"epoch": 0.8133773740710157,
|
| 2771 |
+
"grad_norm": 2.354003763601073,
|
| 2772 |
+
"learning_rate": 1.024655100554882e-06,
|
| 2773 |
+
"loss": 0.3643,
|
| 2774 |
+
"step": 1970
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 0.8154417836498762,
|
| 2778 |
+
"grad_norm": 2.4101822702917004,
|
| 2779 |
+
"learning_rate": 1.002897227445777e-06,
|
| 2780 |
+
"loss": 0.3617,
|
| 2781 |
+
"step": 1975
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 0.8175061932287366,
|
| 2785 |
+
"grad_norm": 2.4833584786174163,
|
| 2786 |
+
"learning_rate": 9.813470697517009e-07,
|
| 2787 |
+
"loss": 0.3501,
|
| 2788 |
+
"step": 1980
|
| 2789 |
+
},
|
| 2790 |
+
{
|
| 2791 |
+
"epoch": 0.8195706028075971,
|
| 2792 |
+
"grad_norm": 2.3627937000377393,
|
| 2793 |
+
"learning_rate": 9.600057473587876e-07,
|
| 2794 |
+
"loss": 0.3671,
|
| 2795 |
+
"step": 1985
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 0.8216350123864574,
|
| 2799 |
+
"grad_norm": 2.415763997145714,
|
| 2800 |
+
"learning_rate": 9.388743693007247e-07,
|
| 2801 |
+
"loss": 0.3541,
|
| 2802 |
+
"step": 1990
|
| 2803 |
+
},
|
| 2804 |
+
{
|
| 2805 |
+
"epoch": 0.8236994219653179,
|
| 2806 |
+
"grad_norm": 2.4671751077694406,
|
| 2807 |
+
"learning_rate": 9.1795403370113e-07,
|
| 2808 |
+
"loss": 0.3535,
|
| 2809 |
+
"step": 1995
|
| 2810 |
+
},
|
| 2811 |
+
{
|
| 2812 |
+
"epoch": 0.8257638315441783,
|
| 2813 |
+
"grad_norm": 2.3775799288896287,
|
| 2814 |
+
"learning_rate": 8.972458277164886e-07,
|
| 2815 |
+
"loss": 0.3516,
|
| 2816 |
+
"step": 2000
|
| 2817 |
+
},
|
| 2818 |
+
{
|
| 2819 |
+
"epoch": 0.8278282411230388,
|
| 2820 |
+
"grad_norm": 2.2938470233646604,
|
| 2821 |
+
"learning_rate": 8.76750827479651e-07,
|
| 2822 |
+
"loss": 0.3398,
|
| 2823 |
+
"step": 2005
|
| 2824 |
+
},
|
| 2825 |
+
{
|
| 2826 |
+
"epoch": 0.8298926507018992,
|
| 2827 |
+
"grad_norm": 2.2933382256010497,
|
| 2828 |
+
"learning_rate": 8.564700980439122e-07,
|
| 2829 |
+
"loss": 0.3608,
|
| 2830 |
+
"step": 2010
|
| 2831 |
+
},
|
| 2832 |
+
{
|
| 2833 |
+
"epoch": 0.8319570602807597,
|
| 2834 |
+
"grad_norm": 2.3382609787220785,
|
| 2835 |
+
"learning_rate": 8.364046933276642e-07,
|
| 2836 |
+
"loss": 0.3666,
|
| 2837 |
+
"step": 2015
|
| 2838 |
+
},
|
| 2839 |
+
{
|
| 2840 |
+
"epoch": 0.8340214698596201,
|
| 2841 |
+
"grad_norm": 2.44152050789561,
|
| 2842 |
+
"learning_rate": 8.165556560596316e-07,
|
| 2843 |
+
"loss": 0.3485,
|
| 2844 |
+
"step": 2020
|
| 2845 |
+
},
|
| 2846 |
+
{
|
| 2847 |
+
"epoch": 0.8360858794384806,
|
| 2848 |
+
"grad_norm": 2.3858823443159034,
|
| 2849 |
+
"learning_rate": 7.969240177246779e-07,
|
| 2850 |
+
"loss": 0.3547,
|
| 2851 |
+
"step": 2025
|
| 2852 |
+
},
|
| 2853 |
+
{
|
| 2854 |
+
"epoch": 0.838150289017341,
|
| 2855 |
+
"grad_norm": 2.453983334202833,
|
| 2856 |
+
"learning_rate": 7.775107985102087e-07,
|
| 2857 |
+
"loss": 0.3651,
|
| 2858 |
+
"step": 2030
|
| 2859 |
+
},
|
| 2860 |
+
{
|
| 2861 |
+
"epoch": 0.8402146985962015,
|
| 2862 |
+
"grad_norm": 2.5029504947887875,
|
| 2863 |
+
"learning_rate": 7.583170072531543e-07,
|
| 2864 |
+
"loss": 0.3509,
|
| 2865 |
+
"step": 2035
|
| 2866 |
+
},
|
| 2867 |
+
{
|
| 2868 |
+
"epoch": 0.8422791081750619,
|
| 2869 |
+
"grad_norm": 2.482629951124892,
|
| 2870 |
+
"learning_rate": 7.393436413875411e-07,
|
| 2871 |
+
"loss": 0.3476,
|
| 2872 |
+
"step": 2040
|
| 2873 |
+
},
|
| 2874 |
+
{
|
| 2875 |
+
"epoch": 0.8443435177539224,
|
| 2876 |
+
"grad_norm": 2.283216056409345,
|
| 2877 |
+
"learning_rate": 7.205916868926604e-07,
|
| 2878 |
+
"loss": 0.3526,
|
| 2879 |
+
"step": 2045
|
| 2880 |
+
},
|
| 2881 |
+
{
|
| 2882 |
+
"epoch": 0.8464079273327828,
|
| 2883 |
+
"grad_norm": 2.3590631737094845,
|
| 2884 |
+
"learning_rate": 7.020621182418347e-07,
|
| 2885 |
+
"loss": 0.34,
|
| 2886 |
+
"step": 2050
|
| 2887 |
+
},
|
| 2888 |
+
{
|
| 2889 |
+
"epoch": 0.8484723369116433,
|
| 2890 |
+
"grad_norm": 2.6201296500024553,
|
| 2891 |
+
"learning_rate": 6.837558983517723e-07,
|
| 2892 |
+
"loss": 0.3535,
|
| 2893 |
+
"step": 2055
|
| 2894 |
+
},
|
| 2895 |
+
{
|
| 2896 |
+
"epoch": 0.8505367464905037,
|
| 2897 |
+
"grad_norm": 2.4227114258373095,
|
| 2898 |
+
"learning_rate": 6.656739785325278e-07,
|
| 2899 |
+
"loss": 0.3507,
|
| 2900 |
+
"step": 2060
|
| 2901 |
+
},
|
| 2902 |
+
{
|
| 2903 |
+
"epoch": 0.8526011560693642,
|
| 2904 |
+
"grad_norm": 2.390954329942295,
|
| 2905 |
+
"learning_rate": 6.478172984380687e-07,
|
| 2906 |
+
"loss": 0.3532,
|
| 2907 |
+
"step": 2065
|
| 2908 |
+
},
|
| 2909 |
+
{
|
| 2910 |
+
"epoch": 0.8546655656482246,
|
| 2911 |
+
"grad_norm": 2.556923085001048,
|
| 2912 |
+
"learning_rate": 6.301867860174443e-07,
|
| 2913 |
+
"loss": 0.3434,
|
| 2914 |
+
"step": 2070
|
| 2915 |
+
},
|
| 2916 |
+
{
|
| 2917 |
+
"epoch": 0.856729975227085,
|
| 2918 |
+
"grad_norm": 2.3169295549044335,
|
| 2919 |
+
"learning_rate": 6.127833574665642e-07,
|
| 2920 |
+
"loss": 0.3459,
|
| 2921 |
+
"step": 2075
|
| 2922 |
+
},
|
| 2923 |
+
{
|
| 2924 |
+
"epoch": 0.8587943848059455,
|
| 2925 |
+
"grad_norm": 2.3497867089138644,
|
| 2926 |
+
"learning_rate": 5.956079171805818e-07,
|
| 2927 |
+
"loss": 0.3415,
|
| 2928 |
+
"step": 2080
|
| 2929 |
+
},
|
| 2930 |
+
{
|
| 2931 |
+
"epoch": 0.860858794384806,
|
| 2932 |
+
"grad_norm": 2.1735667040509137,
|
| 2933 |
+
"learning_rate": 5.78661357706905e-07,
|
| 2934 |
+
"loss": 0.3379,
|
| 2935 |
+
"step": 2085
|
| 2936 |
+
},
|
| 2937 |
+
{
|
| 2938 |
+
"epoch": 0.8629232039636664,
|
| 2939 |
+
"grad_norm": 2.5779842919745355,
|
| 2940 |
+
"learning_rate": 5.619445596988026e-07,
|
| 2941 |
+
"loss": 0.3425,
|
| 2942 |
+
"step": 2090
|
| 2943 |
+
},
|
| 2944 |
+
{
|
| 2945 |
+
"epoch": 0.8649876135425268,
|
| 2946 |
+
"grad_norm": 2.401992025146321,
|
| 2947 |
+
"learning_rate": 5.45458391869651e-07,
|
| 2948 |
+
"loss": 0.3489,
|
| 2949 |
+
"step": 2095
|
| 2950 |
+
},
|
| 2951 |
+
{
|
| 2952 |
+
"epoch": 0.8670520231213873,
|
| 2953 |
+
"grad_norm": 2.3105243423015587,
|
| 2954 |
+
"learning_rate": 5.29203710947781e-07,
|
| 2955 |
+
"loss": 0.335,
|
| 2956 |
+
"step": 2100
|
| 2957 |
+
},
|
| 2958 |
+
{
|
| 2959 |
+
"epoch": 0.8691164327002477,
|
| 2960 |
+
"grad_norm": 2.5027833045418943,
|
| 2961 |
+
"learning_rate": 5.131813616319641e-07,
|
| 2962 |
+
"loss": 0.35,
|
| 2963 |
+
"step": 2105
|
| 2964 |
+
},
|
| 2965 |
+
{
|
| 2966 |
+
"epoch": 0.8711808422791082,
|
| 2967 |
+
"grad_norm": 2.492666189587263,
|
| 2968 |
+
"learning_rate": 4.973921765475093e-07,
|
| 2969 |
+
"loss": 0.3419,
|
| 2970 |
+
"step": 2110
|
| 2971 |
+
},
|
| 2972 |
+
{
|
| 2973 |
+
"epoch": 0.8732452518579686,
|
| 2974 |
+
"grad_norm": 2.476326337718451,
|
| 2975 |
+
"learning_rate": 4.818369762030001e-07,
|
| 2976 |
+
"loss": 0.3437,
|
| 2977 |
+
"step": 2115
|
| 2978 |
+
},
|
| 2979 |
+
{
|
| 2980 |
+
"epoch": 0.8753096614368291,
|
| 2981 |
+
"grad_norm": 2.4895934072647923,
|
| 2982 |
+
"learning_rate": 4.6651656894765307e-07,
|
| 2983 |
+
"loss": 0.345,
|
| 2984 |
+
"step": 2120
|
| 2985 |
+
},
|
| 2986 |
+
{
|
| 2987 |
+
"epoch": 0.8773740710156895,
|
| 2988 |
+
"grad_norm": 2.432351776306209,
|
| 2989 |
+
"learning_rate": 4.5143175092931257e-07,
|
| 2990 |
+
"loss": 0.3457,
|
| 2991 |
+
"step": 2125
|
| 2992 |
+
},
|
| 2993 |
+
{
|
| 2994 |
+
"epoch": 0.87943848059455,
|
| 2995 |
+
"grad_norm": 2.5446256871769894,
|
| 2996 |
+
"learning_rate": 4.3658330605307496e-07,
|
| 2997 |
+
"loss": 0.3501,
|
| 2998 |
+
"step": 2130
|
| 2999 |
+
},
|
| 3000 |
+
{
|
| 3001 |
+
"epoch": 0.8815028901734104,
|
| 3002 |
+
"grad_norm": 2.400237240106358,
|
| 3003 |
+
"learning_rate": 4.2197200594055135e-07,
|
| 3004 |
+
"loss": 0.3417,
|
| 3005 |
+
"step": 2135
|
| 3006 |
+
},
|
| 3007 |
+
{
|
| 3008 |
+
"epoch": 0.8835672997522709,
|
| 3009 |
+
"grad_norm": 2.420863056343347,
|
| 3010 |
+
"learning_rate": 4.0759860988977715e-07,
|
| 3011 |
+
"loss": 0.3336,
|
| 3012 |
+
"step": 2140
|
| 3013 |
+
},
|
| 3014 |
+
{
|
| 3015 |
+
"epoch": 0.8856317093311313,
|
| 3016 |
+
"grad_norm": 2.5855831775345317,
|
| 3017 |
+
"learning_rate": 3.934638648357414e-07,
|
| 3018 |
+
"loss": 0.3473,
|
| 3019 |
+
"step": 2145
|
| 3020 |
+
},
|
| 3021 |
+
{
|
| 3022 |
+
"epoch": 0.8876961189099918,
|
| 3023 |
+
"grad_norm": 2.4571094742538633,
|
| 3024 |
+
"learning_rate": 3.795685053115805e-07,
|
| 3025 |
+
"loss": 0.3425,
|
| 3026 |
+
"step": 2150
|
| 3027 |
+
},
|
| 3028 |
+
{
|
| 3029 |
+
"epoch": 0.8897605284888522,
|
| 3030 |
+
"grad_norm": 2.318969751255526,
|
| 3031 |
+
"learning_rate": 3.659132534104054e-07,
|
| 3032 |
+
"loss": 0.339,
|
| 3033 |
+
"step": 2155
|
| 3034 |
+
},
|
| 3035 |
+
{
|
| 3036 |
+
"epoch": 0.8918249380677127,
|
| 3037 |
+
"grad_norm": 2.464561015161846,
|
| 3038 |
+
"learning_rate": 3.5249881874777235e-07,
|
| 3039 |
+
"loss": 0.3415,
|
| 3040 |
+
"step": 2160
|
| 3041 |
+
},
|
| 3042 |
+
{
|
| 3043 |
+
"epoch": 0.8938893476465731,
|
| 3044 |
+
"grad_norm": 2.5739185699856653,
|
| 3045 |
+
"learning_rate": 3.3932589842481434e-07,
|
| 3046 |
+
"loss": 0.3549,
|
| 3047 |
+
"step": 2165
|
| 3048 |
+
},
|
| 3049 |
+
{
|
| 3050 |
+
"epoch": 0.8959537572254336,
|
| 3051 |
+
"grad_norm": 2.3924860465104554,
|
| 3052 |
+
"learning_rate": 3.2639517699200765e-07,
|
| 3053 |
+
"loss": 0.3501,
|
| 3054 |
+
"step": 2170
|
| 3055 |
+
},
|
| 3056 |
+
{
|
| 3057 |
+
"epoch": 0.898018166804294,
|
| 3058 |
+
"grad_norm": 2.4561049545962983,
|
| 3059 |
+
"learning_rate": 3.1370732641360424e-07,
|
| 3060 |
+
"loss": 0.3382,
|
| 3061 |
+
"step": 2175
|
| 3062 |
+
},
|
| 3063 |
+
{
|
| 3064 |
+
"epoch": 0.9000825763831544,
|
| 3065 |
+
"grad_norm": 2.4531360622529985,
|
| 3066 |
+
"learning_rate": 3.0126300603270763e-07,
|
| 3067 |
+
"loss": 0.3386,
|
| 3068 |
+
"step": 2180
|
| 3069 |
+
},
|
| 3070 |
+
{
|
| 3071 |
+
"epoch": 0.9021469859620148,
|
| 3072 |
+
"grad_norm": 2.3726671856862698,
|
| 3073 |
+
"learning_rate": 2.89062862537009e-07,
|
| 3074 |
+
"loss": 0.3382,
|
| 3075 |
+
"step": 2185
|
| 3076 |
+
},
|
| 3077 |
+
{
|
| 3078 |
+
"epoch": 0.9042113955408753,
|
| 3079 |
+
"grad_norm": 2.4508531032953704,
|
| 3080 |
+
"learning_rate": 2.7710752992518906e-07,
|
| 3081 |
+
"loss": 0.3475,
|
| 3082 |
+
"step": 2190
|
| 3083 |
+
},
|
| 3084 |
+
{
|
| 3085 |
+
"epoch": 0.9062758051197357,
|
| 3086 |
+
"grad_norm": 2.344783384097571,
|
| 3087 |
+
"learning_rate": 2.653976294739596e-07,
|
| 3088 |
+
"loss": 0.3435,
|
| 3089 |
+
"step": 2195
|
| 3090 |
+
},
|
| 3091 |
+
{
|
| 3092 |
+
"epoch": 0.9083402146985962,
|
| 3093 |
+
"grad_norm": 2.3832943118751495,
|
| 3094 |
+
"learning_rate": 2.539337697057853e-07,
|
| 3095 |
+
"loss": 0.3386,
|
| 3096 |
+
"step": 2200
|
| 3097 |
+
},
|
| 3098 |
+
{
|
| 3099 |
+
"epoch": 0.9104046242774566,
|
| 3100 |
+
"grad_norm": 2.2656029102160917,
|
| 3101 |
+
"learning_rate": 2.4271654635726003e-07,
|
| 3102 |
+
"loss": 0.326,
|
| 3103 |
+
"step": 2205
|
| 3104 |
+
},
|
| 3105 |
+
{
|
| 3106 |
+
"epoch": 0.9124690338563171,
|
| 3107 |
+
"grad_norm": 2.531439971555802,
|
| 3108 |
+
"learning_rate": 2.3174654234814854e-07,
|
| 3109 |
+
"loss": 0.3336,
|
| 3110 |
+
"step": 2210
|
| 3111 |
+
},
|
| 3112 |
+
{
|
| 3113 |
+
"epoch": 0.9145334434351775,
|
| 3114 |
+
"grad_norm": 2.526736652879497,
|
| 3115 |
+
"learning_rate": 2.2102432775109151e-07,
|
| 3116 |
+
"loss": 0.3431,
|
| 3117 |
+
"step": 2215
|
| 3118 |
+
},
|
| 3119 |
+
{
|
| 3120 |
+
"epoch": 0.916597853014038,
|
| 3121 |
+
"grad_norm": 2.499234877151574,
|
| 3122 |
+
"learning_rate": 2.1055045976198286e-07,
|
| 3123 |
+
"loss": 0.3274,
|
| 3124 |
+
"step": 2220
|
| 3125 |
+
},
|
| 3126 |
+
{
|
| 3127 |
+
"epoch": 0.9186622625928984,
|
| 3128 |
+
"grad_norm": 2.347953826058282,
|
| 3129 |
+
"learning_rate": 2.0032548267101547e-07,
|
| 3130 |
+
"loss": 0.3415,
|
| 3131 |
+
"step": 2225
|
| 3132 |
+
},
|
| 3133 |
+
{
|
| 3134 |
+
"epoch": 0.9207266721717589,
|
| 3135 |
+
"grad_norm": 2.2781319110873923,
|
| 3136 |
+
"learning_rate": 1.9034992783439398e-07,
|
| 3137 |
+
"loss": 0.3313,
|
| 3138 |
+
"step": 2230
|
| 3139 |
+
},
|
| 3140 |
+
{
|
| 3141 |
+
"epoch": 0.9227910817506193,
|
| 3142 |
+
"grad_norm": 2.4985215803253777,
|
| 3143 |
+
"learning_rate": 1.8062431364672394e-07,
|
| 3144 |
+
"loss": 0.347,
|
| 3145 |
+
"step": 2235
|
| 3146 |
+
},
|
| 3147 |
+
{
|
| 3148 |
+
"epoch": 0.9248554913294798,
|
| 3149 |
+
"grad_norm": 2.3523550820055807,
|
| 3150 |
+
"learning_rate": 1.7114914551407125e-07,
|
| 3151 |
+
"loss": 0.3405,
|
| 3152 |
+
"step": 2240
|
| 3153 |
+
},
|
| 3154 |
+
{
|
| 3155 |
+
"epoch": 0.9269199009083402,
|
| 3156 |
+
"grad_norm": 2.35149253079431,
|
| 3157 |
+
"learning_rate": 1.619249158276981e-07,
|
| 3158 |
+
"loss": 0.3396,
|
| 3159 |
+
"step": 2245
|
| 3160 |
+
},
|
| 3161 |
+
{
|
| 3162 |
+
"epoch": 0.9289843104872006,
|
| 3163 |
+
"grad_norm": 2.5391046088636724,
|
| 3164 |
+
"learning_rate": 1.529521039384757e-07,
|
| 3165 |
+
"loss": 0.3382,
|
| 3166 |
+
"step": 2250
|
| 3167 |
+
},
|
| 3168 |
+
{
|
| 3169 |
+
"epoch": 0.9310487200660611,
|
| 3170 |
+
"grad_norm": 2.436611958199382,
|
| 3171 |
+
"learning_rate": 1.4423117613197535e-07,
|
| 3172 |
+
"loss": 0.3507,
|
| 3173 |
+
"step": 2255
|
| 3174 |
+
},
|
| 3175 |
+
{
|
| 3176 |
+
"epoch": 0.9331131296449215,
|
| 3177 |
+
"grad_norm": 2.368900058293189,
|
| 3178 |
+
"learning_rate": 1.357625856042344e-07,
|
| 3179 |
+
"loss": 0.3436,
|
| 3180 |
+
"step": 2260
|
| 3181 |
+
},
|
| 3182 |
+
{
|
| 3183 |
+
"epoch": 0.935177539223782,
|
| 3184 |
+
"grad_norm": 2.483713260867796,
|
| 3185 |
+
"learning_rate": 1.275467724382068e-07,
|
| 3186 |
+
"loss": 0.3493,
|
| 3187 |
+
"step": 2265
|
| 3188 |
+
},
|
| 3189 |
+
{
|
| 3190 |
+
"epoch": 0.9372419488026424,
|
| 3191 |
+
"grad_norm": 2.3378032035177556,
|
| 3192 |
+
"learning_rate": 1.1958416358089308e-07,
|
| 3193 |
+
"loss": 0.3366,
|
| 3194 |
+
"step": 2270
|
| 3195 |
+
},
|
| 3196 |
+
{
|
| 3197 |
+
"epoch": 0.9393063583815029,
|
| 3198 |
+
"grad_norm": 2.427445932737846,
|
| 3199 |
+
"learning_rate": 1.1187517282115478e-07,
|
| 3200 |
+
"loss": 0.3357,
|
| 3201 |
+
"step": 2275
|
| 3202 |
+
},
|
| 3203 |
+
{
|
| 3204 |
+
"epoch": 0.9413707679603633,
|
| 3205 |
+
"grad_norm": 2.45979849427157,
|
| 3206 |
+
"learning_rate": 1.0442020076820992e-07,
|
| 3207 |
+
"loss": 0.3432,
|
| 3208 |
+
"step": 2280
|
| 3209 |
+
},
|
| 3210 |
+
{
|
| 3211 |
+
"epoch": 0.9434351775392238,
|
| 3212 |
+
"grad_norm": 2.4102972284673485,
|
| 3213 |
+
"learning_rate": 9.72196348308152e-08,
|
| 3214 |
+
"loss": 0.3421,
|
| 3215 |
+
"step": 2285
|
| 3216 |
+
},
|
| 3217 |
+
{
|
| 3218 |
+
"epoch": 0.9454995871180842,
|
| 3219 |
+
"grad_norm": 2.4147926771751127,
|
| 3220 |
+
"learning_rate": 9.027384919713167e-08,
|
| 3221 |
+
"loss": 0.3449,
|
| 3222 |
+
"step": 2290
|
| 3223 |
+
},
|
| 3224 |
+
{
|
| 3225 |
+
"epoch": 0.9475639966969447,
|
| 3226 |
+
"grad_norm": 2.492908131419299,
|
| 3227 |
+
"learning_rate": 8.358320481528404e-08,
|
| 3228 |
+
"loss": 0.3349,
|
| 3229 |
+
"step": 2295
|
| 3230 |
+
},
|
| 3231 |
+
{
|
| 3232 |
+
"epoch": 0.9496284062758051,
|
| 3233 |
+
"grad_norm": 2.445696827488344,
|
| 3234 |
+
"learning_rate": 7.714804937459964e-08,
|
| 3235 |
+
"loss": 0.3327,
|
| 3236 |
+
"step": 2300
|
| 3237 |
+
},
|
| 3238 |
+
{
|
| 3239 |
+
"epoch": 0.9516928158546656,
|
| 3240 |
+
"grad_norm": 2.4859237981346434,
|
| 3241 |
+
"learning_rate": 7.096871728754173e-08,
|
| 3242 |
+
"loss": 0.3369,
|
| 3243 |
+
"step": 2305
|
| 3244 |
+
},
|
| 3245 |
+
{
|
| 3246 |
+
"epoch": 0.953757225433526,
|
| 3247 |
+
"grad_norm": 2.4755163895408483,
|
| 3248 |
+
"learning_rate": 6.504552967233014e-08,
|
| 3249 |
+
"loss": 0.3341,
|
| 3250 |
+
"step": 2310
|
| 3251 |
+
},
|
| 3252 |
+
{
|
| 3253 |
+
"epoch": 0.9558216350123865,
|
| 3254 |
+
"grad_norm": 2.4903780675355947,
|
| 3255 |
+
"learning_rate": 5.9378794336255595e-08,
|
| 3256 |
+
"loss": 0.3259,
|
| 3257 |
+
"step": 2315
|
| 3258 |
+
},
|
| 3259 |
+
{
|
| 3260 |
+
"epoch": 0.9578860445912469,
|
| 3261 |
+
"grad_norm": 2.3608897794698986,
|
| 3262 |
+
"learning_rate": 5.396880575968266e-08,
|
| 3263 |
+
"loss": 0.34,
|
| 3264 |
+
"step": 2320
|
| 3265 |
+
},
|
| 3266 |
+
{
|
| 3267 |
+
"epoch": 0.9599504541701074,
|
| 3268 |
+
"grad_norm": 2.349066629113589,
|
| 3269 |
+
"learning_rate": 4.881584508074688e-08,
|
| 3270 |
+
"loss": 0.3285,
|
| 3271 |
+
"step": 2325
|
| 3272 |
+
},
|
| 3273 |
+
{
|
| 3274 |
+
"epoch": 0.9620148637489678,
|
| 3275 |
+
"grad_norm": 2.475193042134275,
|
| 3276 |
+
"learning_rate": 4.39201800807465e-08,
|
| 3277 |
+
"loss": 0.339,
|
| 3278 |
+
"step": 2330
|
| 3279 |
+
},
|
| 3280 |
+
{
|
| 3281 |
+
"epoch": 0.9640792733278283,
|
| 3282 |
+
"grad_norm": 2.3656425365762384,
|
| 3283 |
+
"learning_rate": 3.92820651702247e-08,
|
| 3284 |
+
"loss": 0.3358,
|
| 3285 |
+
"step": 2335
|
| 3286 |
+
},
|
| 3287 |
+
{
|
| 3288 |
+
"epoch": 0.9661436829066887,
|
| 3289 |
+
"grad_norm": 2.441572724635035,
|
| 3290 |
+
"learning_rate": 3.4901741375747975e-08,
|
| 3291 |
+
"loss": 0.3471,
|
| 3292 |
+
"step": 2340
|
| 3293 |
+
},
|
| 3294 |
+
{
|
| 3295 |
+
"epoch": 0.9682080924855492,
|
| 3296 |
+
"grad_norm": 2.3678044079850413,
|
| 3297 |
+
"learning_rate": 3.077943632738556e-08,
|
| 3298 |
+
"loss": 0.3499,
|
| 3299 |
+
"step": 2345
|
| 3300 |
+
},
|
| 3301 |
+
{
|
| 3302 |
+
"epoch": 0.9702725020644096,
|
| 3303 |
+
"grad_norm": 2.630292946781589,
|
| 3304 |
+
"learning_rate": 2.6915364246875574e-08,
|
| 3305 |
+
"loss": 0.341,
|
| 3306 |
+
"step": 2350
|
| 3307 |
+
},
|
| 3308 |
+
{
|
| 3309 |
+
"epoch": 0.9723369116432701,
|
| 3310 |
+
"grad_norm": 2.388897601971072,
|
| 3311 |
+
"learning_rate": 2.3309725936493387e-08,
|
| 3312 |
+
"loss": 0.3437,
|
| 3313 |
+
"step": 2355
|
| 3314 |
+
},
|
| 3315 |
+
{
|
| 3316 |
+
"epoch": 0.9744013212221305,
|
| 3317 |
+
"grad_norm": 2.4665523794028785,
|
| 3318 |
+
"learning_rate": 1.9962708768620498e-08,
|
| 3319 |
+
"loss": 0.3453,
|
| 3320 |
+
"step": 2360
|
| 3321 |
+
},
|
| 3322 |
+
{
|
| 3323 |
+
"epoch": 0.976465730800991,
|
| 3324 |
+
"grad_norm": 2.448813469296534,
|
| 3325 |
+
"learning_rate": 1.687448667600067e-08,
|
| 3326 |
+
"loss": 0.3408,
|
| 3327 |
+
"step": 2365
|
| 3328 |
+
},
|
| 3329 |
+
{
|
| 3330 |
+
"epoch": 0.9785301403798513,
|
| 3331 |
+
"grad_norm": 2.3718128749961576,
|
| 3332 |
+
"learning_rate": 1.4045220142708816e-08,
|
| 3333 |
+
"loss": 0.35,
|
| 3334 |
+
"step": 2370
|
| 3335 |
+
},
|
| 3336 |
+
{
|
| 3337 |
+
"epoch": 0.9805945499587118,
|
| 3338 |
+
"grad_norm": 2.4841177332012325,
|
| 3339 |
+
"learning_rate": 1.1475056195804358e-08,
|
| 3340 |
+
"loss": 0.3518,
|
| 3341 |
+
"step": 2375
|
| 3342 |
+
},
|
| 3343 |
+
{
|
| 3344 |
+
"epoch": 0.9826589595375722,
|
| 3345 |
+
"grad_norm": 2.493744247830282,
|
| 3346 |
+
"learning_rate": 9.164128397695648e-09,
|
| 3347 |
+
"loss": 0.332,
|
| 3348 |
+
"step": 2380
|
| 3349 |
+
},
|
| 3350 |
+
{
|
| 3351 |
+
"epoch": 0.9847233691164327,
|
| 3352 |
+
"grad_norm": 2.2819847476640107,
|
| 3353 |
+
"learning_rate": 7.112556839196649e-09,
|
| 3354 |
+
"loss": 0.3301,
|
| 3355 |
+
"step": 2385
|
| 3356 |
+
},
|
| 3357 |
+
{
|
| 3358 |
+
"epoch": 0.9867877786952931,
|
| 3359 |
+
"grad_norm": 2.4247247484873173,
|
| 3360 |
+
"learning_rate": 5.3204481332880255e-09,
|
| 3361 |
+
"loss": 0.3433,
|
| 3362 |
+
"step": 2390
|
| 3363 |
+
},
|
| 3364 |
+
{
|
| 3365 |
+
"epoch": 0.9888521882741536,
|
| 3366 |
+
"grad_norm": 2.4373319136694285,
|
| 3367 |
+
"learning_rate": 3.787895409574915e-09,
|
| 3368 |
+
"loss": 0.3388,
|
| 3369 |
+
"step": 2395
|
| 3370 |
+
},
|
| 3371 |
+
{
|
| 3372 |
+
"epoch": 0.990916597853014,
|
| 3373 |
+
"grad_norm": 2.3711173222964037,
|
| 3374 |
+
"learning_rate": 2.514978309447469e-09,
|
| 3375 |
+
"loss": 0.3433,
|
| 3376 |
+
"step": 2400
|
| 3377 |
+
},
|
| 3378 |
+
{
|
| 3379 |
+
"epoch": 0.9929810074318745,
|
| 3380 |
+
"grad_norm": 2.3426000581900652,
|
| 3381 |
+
"learning_rate": 1.501762981945265e-09,
|
| 3382 |
+
"loss": 0.3368,
|
| 3383 |
+
"step": 2405
|
| 3384 |
+
},
|
| 3385 |
+
{
|
| 3386 |
+
"epoch": 0.9950454170107349,
|
| 3387 |
+
"grad_norm": 2.35822764782016,
|
| 3388 |
+
"learning_rate": 7.483020803145114e-10,
|
| 3389 |
+
"loss": 0.3396,
|
| 3390 |
+
"step": 2410
|
| 3391 |
+
},
|
| 3392 |
+
{
|
| 3393 |
+
"epoch": 0.9971098265895953,
|
| 3394 |
+
"grad_norm": 2.4725534953927233,
|
| 3395 |
+
"learning_rate": 2.5463475927745007e-10,
|
| 3396 |
+
"loss": 0.3401,
|
| 3397 |
+
"step": 2415
|
| 3398 |
+
},
|
| 3399 |
+
{
|
| 3400 |
+
"epoch": 0.9991742361684558,
|
| 3401 |
+
"grad_norm": 2.407515233988016,
|
| 3402 |
+
"learning_rate": 2.078667299343362e-11,
|
| 3403 |
+
"loss": 0.3298,
|
| 3404 |
+
"step": 2420
|
| 3405 |
+
},
|
| 3406 |
+
{
|
| 3407 |
+
"epoch": 1.0,
|
| 3408 |
+
"eval_runtime": 3.3946,
|
| 3409 |
+
"eval_samples_per_second": 2.946,
|
| 3410 |
+
"eval_steps_per_second": 0.884,
|
| 3411 |
+
"step": 2422
|
| 3412 |
+
},
|
| 3413 |
+
{
|
| 3414 |
+
"epoch": 1.0,
|
| 3415 |
+
"step": 2422,
|
| 3416 |
+
"total_flos": 253558763028480.0,
|
| 3417 |
+
"train_loss": 0.530042272082643,
|
| 3418 |
+
"train_runtime": 21564.4437,
|
| 3419 |
+
"train_samples_per_second": 1.797,
|
| 3420 |
+
"train_steps_per_second": 0.112
|
| 3421 |
+
}
|
| 3422 |
+
],
|
| 3423 |
+
"logging_steps": 5,
|
| 3424 |
+
"max_steps": 2422,
|
| 3425 |
+
"num_input_tokens_seen": 0,
|
| 3426 |
+
"num_train_epochs": 1,
|
| 3427 |
+
"save_steps": 100,
|
| 3428 |
+
"stateful_callbacks": {
|
| 3429 |
+
"TrainerControl": {
|
| 3430 |
+
"args": {
|
| 3431 |
+
"should_epoch_stop": false,
|
| 3432 |
+
"should_evaluate": false,
|
| 3433 |
+
"should_log": false,
|
| 3434 |
+
"should_save": true,
|
| 3435 |
+
"should_training_stop": true
|
| 3436 |
+
},
|
| 3437 |
+
"attributes": {}
|
| 3438 |
+
}
|
| 3439 |
+
},
|
| 3440 |
+
"total_flos": 253558763028480.0,
|
| 3441 |
+
"train_batch_size": 4,
|
| 3442 |
+
"trial_name": null,
|
| 3443 |
+
"trial_params": null
|
| 3444 |
+
}
|