Model save
Browse files- README.md +60 -0
- all_results.json +9 -0
- generation_config.json +12 -0
- runs/Sep30_16-23-59_COE-CS-sv003/events.out.tfevents.1727713941.COE-CS-sv003.1328701.0 +2 -2
- train_results.json +9 -0
- trainer_state.json +3052 -0
README.md
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: other
|
| 4 |
+
base_model: Qwen/Qwen1.5-0.5B-Chat
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: qwen_0.5_feedback_dirty
|
| 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 |
+
# qwen_0.5_feedback_dirty
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen1.5-0.5B-Chat](https://huggingface.co/Qwen/Qwen1.5-0.5B-Chat) 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": 104409178570752.0,
|
| 4 |
+
"train_loss": 1.2488443794731108,
|
| 5 |
+
"train_runtime": 1971.1476,
|
| 6 |
+
"train_samples": 98881,
|
| 7 |
+
"train_samples_per_second": 17.39,
|
| 8 |
+
"train_steps_per_second": 1.087
|
| 9 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.1,
|
| 10 |
+
"top_p": 0.8,
|
| 11 |
+
"transformers_version": "4.45.1"
|
| 12 |
+
}
|
runs/Sep30_16-23-59_COE-CS-sv003/events.out.tfevents.1727713941.COE-CS-sv003.1328701.0
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:f87585865dc18afd83ac616bcfde79af4576e0a248839d4582f8a45b963853c5
|
| 3 |
+
size 96758
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 104409178570752.0,
|
| 4 |
+
"train_loss": 1.2488443794731108,
|
| 5 |
+
"train_runtime": 1971.1476,
|
| 6 |
+
"train_samples": 98881,
|
| 7 |
+
"train_samples_per_second": 17.39,
|
| 8 |
+
"train_steps_per_second": 1.087
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3052 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2143,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0004666355576294914,
|
| 13 |
+
"grad_norm": 9.80569798486889,
|
| 14 |
+
"learning_rate": 4.6511627906976744e-08,
|
| 15 |
+
"loss": 2.0528,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0023331777881474567,
|
| 20 |
+
"grad_norm": 11.170695783429226,
|
| 21 |
+
"learning_rate": 2.3255813953488374e-07,
|
| 22 |
+
"loss": 2.1257,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.004666355576294913,
|
| 27 |
+
"grad_norm": 10.299964663909256,
|
| 28 |
+
"learning_rate": 4.651162790697675e-07,
|
| 29 |
+
"loss": 2.1053,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.006999533364442371,
|
| 34 |
+
"grad_norm": 8.193532512360106,
|
| 35 |
+
"learning_rate": 6.976744186046513e-07,
|
| 36 |
+
"loss": 2.0846,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.009332711152589827,
|
| 41 |
+
"grad_norm": 7.913282318442771,
|
| 42 |
+
"learning_rate": 9.30232558139535e-07,
|
| 43 |
+
"loss": 2.0703,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.011665888940737284,
|
| 48 |
+
"grad_norm": 5.1976478753102695,
|
| 49 |
+
"learning_rate": 1.1627906976744188e-06,
|
| 50 |
+
"loss": 2.0447,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.013999066728884742,
|
| 55 |
+
"grad_norm": 3.327102797078764,
|
| 56 |
+
"learning_rate": 1.3953488372093025e-06,
|
| 57 |
+
"loss": 2.009,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.016332244517032198,
|
| 62 |
+
"grad_norm": 2.8990750203341213,
|
| 63 |
+
"learning_rate": 1.6279069767441862e-06,
|
| 64 |
+
"loss": 1.96,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.018665422305179653,
|
| 69 |
+
"grad_norm": 2.7398670194452257,
|
| 70 |
+
"learning_rate": 1.86046511627907e-06,
|
| 71 |
+
"loss": 1.9107,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.020998600093327113,
|
| 76 |
+
"grad_norm": 2.5093466657100376,
|
| 77 |
+
"learning_rate": 2.0930232558139536e-06,
|
| 78 |
+
"loss": 1.8824,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.02333177788147457,
|
| 83 |
+
"grad_norm": 2.539393259914437,
|
| 84 |
+
"learning_rate": 2.3255813953488376e-06,
|
| 85 |
+
"loss": 1.8068,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.025664955669622024,
|
| 90 |
+
"grad_norm": 2.385030943190482,
|
| 91 |
+
"learning_rate": 2.558139534883721e-06,
|
| 92 |
+
"loss": 1.8136,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.027998133457769483,
|
| 97 |
+
"grad_norm": 1.503294665821055,
|
| 98 |
+
"learning_rate": 2.790697674418605e-06,
|
| 99 |
+
"loss": 1.6936,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.03033131124591694,
|
| 104 |
+
"grad_norm": 1.2909407802544917,
|
| 105 |
+
"learning_rate": 3.0232558139534885e-06,
|
| 106 |
+
"loss": 1.6416,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.032664489034064395,
|
| 111 |
+
"grad_norm": 1.6338317963717872,
|
| 112 |
+
"learning_rate": 3.2558139534883724e-06,
|
| 113 |
+
"loss": 1.5935,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.03499766682221185,
|
| 118 |
+
"grad_norm": 1.0741783431016825,
|
| 119 |
+
"learning_rate": 3.4883720930232564e-06,
|
| 120 |
+
"loss": 1.5743,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.03733084461035931,
|
| 125 |
+
"grad_norm": 2.0009334094497935,
|
| 126 |
+
"learning_rate": 3.72093023255814e-06,
|
| 127 |
+
"loss": 1.5656,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.03966402239850677,
|
| 132 |
+
"grad_norm": 1.0372560314506016,
|
| 133 |
+
"learning_rate": 3.953488372093024e-06,
|
| 134 |
+
"loss": 1.5313,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.041997200186654225,
|
| 139 |
+
"grad_norm": 1.0104596338751055,
|
| 140 |
+
"learning_rate": 4.186046511627907e-06,
|
| 141 |
+
"loss": 1.5563,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.04433037797480168,
|
| 146 |
+
"grad_norm": 1.0490066470026633,
|
| 147 |
+
"learning_rate": 4.418604651162791e-06,
|
| 148 |
+
"loss": 1.5156,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.04666355576294914,
|
| 153 |
+
"grad_norm": 1.0535385716867722,
|
| 154 |
+
"learning_rate": 4.651162790697675e-06,
|
| 155 |
+
"loss": 1.5011,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.04899673355109659,
|
| 160 |
+
"grad_norm": 1.0136671807295665,
|
| 161 |
+
"learning_rate": 4.883720930232559e-06,
|
| 162 |
+
"loss": 1.4834,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.05132991133924405,
|
| 167 |
+
"grad_norm": 1.026154126791642,
|
| 168 |
+
"learning_rate": 5.116279069767442e-06,
|
| 169 |
+
"loss": 1.4987,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.053663089127391504,
|
| 174 |
+
"grad_norm": 1.0396688598036314,
|
| 175 |
+
"learning_rate": 5.348837209302326e-06,
|
| 176 |
+
"loss": 1.4789,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.05599626691553897,
|
| 181 |
+
"grad_norm": 1.0528265921299778,
|
| 182 |
+
"learning_rate": 5.58139534883721e-06,
|
| 183 |
+
"loss": 1.4869,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.05832944470368642,
|
| 188 |
+
"grad_norm": 0.980376108268983,
|
| 189 |
+
"learning_rate": 5.8139534883720935e-06,
|
| 190 |
+
"loss": 1.4484,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.06066262249183388,
|
| 195 |
+
"grad_norm": 0.9975356266204255,
|
| 196 |
+
"learning_rate": 6.046511627906977e-06,
|
| 197 |
+
"loss": 1.4639,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.06299580027998133,
|
| 202 |
+
"grad_norm": 1.0111634170832666,
|
| 203 |
+
"learning_rate": 6.279069767441861e-06,
|
| 204 |
+
"loss": 1.4583,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.06532897806812879,
|
| 209 |
+
"grad_norm": 0.9697052033186522,
|
| 210 |
+
"learning_rate": 6.511627906976745e-06,
|
| 211 |
+
"loss": 1.452,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.06766215585627625,
|
| 216 |
+
"grad_norm": 1.0019712799076745,
|
| 217 |
+
"learning_rate": 6.744186046511628e-06,
|
| 218 |
+
"loss": 1.4542,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.0699953336444237,
|
| 223 |
+
"grad_norm": 0.9918157971629793,
|
| 224 |
+
"learning_rate": 6.976744186046513e-06,
|
| 225 |
+
"loss": 1.4245,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.07232851143257116,
|
| 230 |
+
"grad_norm": 1.0749224168951386,
|
| 231 |
+
"learning_rate": 7.209302325581395e-06,
|
| 232 |
+
"loss": 1.4412,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.07466168922071861,
|
| 237 |
+
"grad_norm": 1.0472967676718108,
|
| 238 |
+
"learning_rate": 7.44186046511628e-06,
|
| 239 |
+
"loss": 1.4383,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.07699486700886607,
|
| 244 |
+
"grad_norm": 1.0500296683118158,
|
| 245 |
+
"learning_rate": 7.674418604651164e-06,
|
| 246 |
+
"loss": 1.4269,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.07932804479701354,
|
| 251 |
+
"grad_norm": 1.031289784533538,
|
| 252 |
+
"learning_rate": 7.906976744186048e-06,
|
| 253 |
+
"loss": 1.4405,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.081661222585161,
|
| 258 |
+
"grad_norm": 7.038247729625548,
|
| 259 |
+
"learning_rate": 8.139534883720931e-06,
|
| 260 |
+
"loss": 1.4111,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.08399440037330845,
|
| 265 |
+
"grad_norm": 1.078414766377112,
|
| 266 |
+
"learning_rate": 8.372093023255815e-06,
|
| 267 |
+
"loss": 1.4302,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.0863275781614559,
|
| 272 |
+
"grad_norm": 1.1261343707762819,
|
| 273 |
+
"learning_rate": 8.604651162790698e-06,
|
| 274 |
+
"loss": 1.4193,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.08866075594960336,
|
| 279 |
+
"grad_norm": 1.0205795295260502,
|
| 280 |
+
"learning_rate": 8.837209302325582e-06,
|
| 281 |
+
"loss": 1.408,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.09099393373775082,
|
| 286 |
+
"grad_norm": 1.0305628773132736,
|
| 287 |
+
"learning_rate": 9.069767441860465e-06,
|
| 288 |
+
"loss": 1.396,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.09332711152589827,
|
| 293 |
+
"grad_norm": 1.0168323756412534,
|
| 294 |
+
"learning_rate": 9.30232558139535e-06,
|
| 295 |
+
"loss": 1.3989,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.09566028931404573,
|
| 300 |
+
"grad_norm": 1.0592651034511553,
|
| 301 |
+
"learning_rate": 9.534883720930234e-06,
|
| 302 |
+
"loss": 1.4059,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.09799346710219319,
|
| 307 |
+
"grad_norm": 1.0527619853339831,
|
| 308 |
+
"learning_rate": 9.767441860465117e-06,
|
| 309 |
+
"loss": 1.3953,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.10032664489034064,
|
| 314 |
+
"grad_norm": 1.0382749975421044,
|
| 315 |
+
"learning_rate": 1e-05,
|
| 316 |
+
"loss": 1.3678,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.1026598226784881,
|
| 321 |
+
"grad_norm": 1.0740445133437382,
|
| 322 |
+
"learning_rate": 9.99983405533249e-06,
|
| 323 |
+
"loss": 1.3626,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.10499300046663555,
|
| 328 |
+
"grad_norm": 1.0412363791977077,
|
| 329 |
+
"learning_rate": 9.999336232345011e-06,
|
| 330 |
+
"loss": 1.3715,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.10732617825478301,
|
| 335 |
+
"grad_norm": 1.0798331517563926,
|
| 336 |
+
"learning_rate": 9.998506564081992e-06,
|
| 337 |
+
"loss": 1.3614,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.10965935604293048,
|
| 342 |
+
"grad_norm": 1.011407284567422,
|
| 343 |
+
"learning_rate": 9.997345105615042e-06,
|
| 344 |
+
"loss": 1.3528,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.11199253383107793,
|
| 349 |
+
"grad_norm": 1.0264212045694465,
|
| 350 |
+
"learning_rate": 9.995851934039295e-06,
|
| 351 |
+
"loss": 1.3702,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.11432571161922539,
|
| 356 |
+
"grad_norm": 1.0151265854031215,
|
| 357 |
+
"learning_rate": 9.9940271484683e-06,
|
| 358 |
+
"loss": 1.3971,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.11665888940737285,
|
| 363 |
+
"grad_norm": 1.0137571222792463,
|
| 364 |
+
"learning_rate": 9.991870870027426e-06,
|
| 365 |
+
"loss": 1.3481,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.1189920671955203,
|
| 370 |
+
"grad_norm": 1.0336506251390232,
|
| 371 |
+
"learning_rate": 9.98938324184584e-06,
|
| 372 |
+
"loss": 1.3625,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.12132524498366776,
|
| 377 |
+
"grad_norm": 1.0253769415462977,
|
| 378 |
+
"learning_rate": 9.986564429046992e-06,
|
| 379 |
+
"loss": 1.3499,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.12365842277181521,
|
| 384 |
+
"grad_norm": 1.0522229786461792,
|
| 385 |
+
"learning_rate": 9.983414618737666e-06,
|
| 386 |
+
"loss": 1.3528,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.12599160055996267,
|
| 391 |
+
"grad_norm": 1.024999010728076,
|
| 392 |
+
"learning_rate": 9.979934019995548e-06,
|
| 393 |
+
"loss": 1.3547,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.12832477834811012,
|
| 398 |
+
"grad_norm": 1.1093536513592763,
|
| 399 |
+
"learning_rate": 9.976122863855362e-06,
|
| 400 |
+
"loss": 1.3401,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.13065795613625758,
|
| 405 |
+
"grad_norm": 1.1061969996450292,
|
| 406 |
+
"learning_rate": 9.971981403293523e-06,
|
| 407 |
+
"loss": 1.35,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.13299113392440504,
|
| 412 |
+
"grad_norm": 0.9968287298176753,
|
| 413 |
+
"learning_rate": 9.967509913211345e-06,
|
| 414 |
+
"loss": 1.3603,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.1353243117125525,
|
| 419 |
+
"grad_norm": 1.013612829026822,
|
| 420 |
+
"learning_rate": 9.962708690416808e-06,
|
| 421 |
+
"loss": 1.3493,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.13765748950069995,
|
| 426 |
+
"grad_norm": 1.0568780094515353,
|
| 427 |
+
"learning_rate": 9.957578053604837e-06,
|
| 428 |
+
"loss": 1.3507,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.1399906672888474,
|
| 433 |
+
"grad_norm": 1.0302035014997373,
|
| 434 |
+
"learning_rate": 9.952118343336159e-06,
|
| 435 |
+
"loss": 1.3528,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.14232384507699486,
|
| 440 |
+
"grad_norm": 1.1204985268605412,
|
| 441 |
+
"learning_rate": 9.946329922014698e-06,
|
| 442 |
+
"loss": 1.3214,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.14465702286514232,
|
| 447 |
+
"grad_norm": 1.0206602255786714,
|
| 448 |
+
"learning_rate": 9.940213173863515e-06,
|
| 449 |
+
"loss": 1.3397,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.14699020065328977,
|
| 454 |
+
"grad_norm": 1.0047788253768313,
|
| 455 |
+
"learning_rate": 9.933768504899305e-06,
|
| 456 |
+
"loss": 1.3403,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.14932337844143723,
|
| 461 |
+
"grad_norm": 1.0059602159950058,
|
| 462 |
+
"learning_rate": 9.926996342905447e-06,
|
| 463 |
+
"loss": 1.339,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.15165655622958468,
|
| 468 |
+
"grad_norm": 1.0680858345826512,
|
| 469 |
+
"learning_rate": 9.919897137403608e-06,
|
| 470 |
+
"loss": 1.3282,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.15398973401773214,
|
| 475 |
+
"grad_norm": 1.0988238449226573,
|
| 476 |
+
"learning_rate": 9.912471359623905e-06,
|
| 477 |
+
"loss": 1.3387,
|
| 478 |
+
"step": 330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.15632291180587962,
|
| 482 |
+
"grad_norm": 1.0407753070461003,
|
| 483 |
+
"learning_rate": 9.904719502473635e-06,
|
| 484 |
+
"loss": 1.3419,
|
| 485 |
+
"step": 335
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.15865608959402708,
|
| 489 |
+
"grad_norm": 1.9678367855655712,
|
| 490 |
+
"learning_rate": 9.896642080504533e-06,
|
| 491 |
+
"loss": 1.305,
|
| 492 |
+
"step": 340
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.16098926738217453,
|
| 496 |
+
"grad_norm": 1.0132213744433203,
|
| 497 |
+
"learning_rate": 9.888239629878644e-06,
|
| 498 |
+
"loss": 1.3162,
|
| 499 |
+
"step": 345
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.163322445170322,
|
| 503 |
+
"grad_norm": 1.0630881401389387,
|
| 504 |
+
"learning_rate": 9.879512708332719e-06,
|
| 505 |
+
"loss": 1.3301,
|
| 506 |
+
"step": 350
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.16565562295846945,
|
| 510 |
+
"grad_norm": 1.0924159128355844,
|
| 511 |
+
"learning_rate": 9.870461895141195e-06,
|
| 512 |
+
"loss": 1.3132,
|
| 513 |
+
"step": 355
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.1679888007466169,
|
| 517 |
+
"grad_norm": 1.023846931107391,
|
| 518 |
+
"learning_rate": 9.861087791077743e-06,
|
| 519 |
+
"loss": 1.329,
|
| 520 |
+
"step": 360
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.17032197853476436,
|
| 524 |
+
"grad_norm": 1.047359966523088,
|
| 525 |
+
"learning_rate": 9.851391018375401e-06,
|
| 526 |
+
"loss": 1.3072,
|
| 527 |
+
"step": 365
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.1726551563229118,
|
| 531 |
+
"grad_norm": 1.044195763995568,
|
| 532 |
+
"learning_rate": 9.841372220685255e-06,
|
| 533 |
+
"loss": 1.3109,
|
| 534 |
+
"step": 370
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.17498833411105927,
|
| 538 |
+
"grad_norm": 1.0128207414270844,
|
| 539 |
+
"learning_rate": 9.831032063033726e-06,
|
| 540 |
+
"loss": 1.3137,
|
| 541 |
+
"step": 375
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.17732151189920672,
|
| 545 |
+
"grad_norm": 1.0376596949653651,
|
| 546 |
+
"learning_rate": 9.820371231778422e-06,
|
| 547 |
+
"loss": 1.315,
|
| 548 |
+
"step": 380
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.17965468968735418,
|
| 552 |
+
"grad_norm": 1.0732468663894352,
|
| 553 |
+
"learning_rate": 9.809390434562587e-06,
|
| 554 |
+
"loss": 1.3303,
|
| 555 |
+
"step": 385
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.18198786747550164,
|
| 559 |
+
"grad_norm": 1.0310831100992088,
|
| 560 |
+
"learning_rate": 9.798090400268112e-06,
|
| 561 |
+
"loss": 1.3006,
|
| 562 |
+
"step": 390
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.1843210452636491,
|
| 566 |
+
"grad_norm": 1.0787827591552768,
|
| 567 |
+
"learning_rate": 9.786471878967174e-06,
|
| 568 |
+
"loss": 1.3181,
|
| 569 |
+
"step": 395
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.18665422305179655,
|
| 573 |
+
"grad_norm": 1.0756929184793924,
|
| 574 |
+
"learning_rate": 9.774535641872435e-06,
|
| 575 |
+
"loss": 1.31,
|
| 576 |
+
"step": 400
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.188987400839944,
|
| 580 |
+
"grad_norm": 1.0427098406775361,
|
| 581 |
+
"learning_rate": 9.762282481285852e-06,
|
| 582 |
+
"loss": 1.3156,
|
| 583 |
+
"step": 405
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.19132057862809146,
|
| 587 |
+
"grad_norm": 1.0326233577660273,
|
| 588 |
+
"learning_rate": 9.749713210546088e-06,
|
| 589 |
+
"loss": 1.293,
|
| 590 |
+
"step": 410
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.19365375641623891,
|
| 594 |
+
"grad_norm": 1.0741587494935991,
|
| 595 |
+
"learning_rate": 9.736828663974527e-06,
|
| 596 |
+
"loss": 1.282,
|
| 597 |
+
"step": 415
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.19598693420438637,
|
| 601 |
+
"grad_norm": 1.0816194382016036,
|
| 602 |
+
"learning_rate": 9.723629696819886e-06,
|
| 603 |
+
"loss": 1.2938,
|
| 604 |
+
"step": 420
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.19832011199253383,
|
| 608 |
+
"grad_norm": 0.9984733308364518,
|
| 609 |
+
"learning_rate": 9.710117185201454e-06,
|
| 610 |
+
"loss": 1.2857,
|
| 611 |
+
"step": 425
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.20065328978068128,
|
| 615 |
+
"grad_norm": 0.9906611455624028,
|
| 616 |
+
"learning_rate": 9.696292026050924e-06,
|
| 617 |
+
"loss": 1.2858,
|
| 618 |
+
"step": 430
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.20298646756882874,
|
| 622 |
+
"grad_norm": 1.0663086458961843,
|
| 623 |
+
"learning_rate": 9.682155137052879e-06,
|
| 624 |
+
"loss": 1.3047,
|
| 625 |
+
"step": 435
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.2053196453569762,
|
| 629 |
+
"grad_norm": 1.0107057639706856,
|
| 630 |
+
"learning_rate": 9.667707456583852e-06,
|
| 631 |
+
"loss": 1.3029,
|
| 632 |
+
"step": 440
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.20765282314512365,
|
| 636 |
+
"grad_norm": 1.0168731805211708,
|
| 637 |
+
"learning_rate": 9.652949943650056e-06,
|
| 638 |
+
"loss": 1.2726,
|
| 639 |
+
"step": 445
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.2099860009332711,
|
| 643 |
+
"grad_norm": 1.0160477312627205,
|
| 644 |
+
"learning_rate": 9.637883577823723e-06,
|
| 645 |
+
"loss": 1.2753,
|
| 646 |
+
"step": 450
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.21231917872141856,
|
| 650 |
+
"grad_norm": 1.1693881065930087,
|
| 651 |
+
"learning_rate": 9.62250935917808e-06,
|
| 652 |
+
"loss": 1.3133,
|
| 653 |
+
"step": 455
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.21465235650956602,
|
| 657 |
+
"grad_norm": 1.0557301758163573,
|
| 658 |
+
"learning_rate": 9.606828308220969e-06,
|
| 659 |
+
"loss": 1.2919,
|
| 660 |
+
"step": 460
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.21698553429771347,
|
| 664 |
+
"grad_norm": 4.373400569853208,
|
| 665 |
+
"learning_rate": 9.590841465827101e-06,
|
| 666 |
+
"loss": 1.2824,
|
| 667 |
+
"step": 465
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.21931871208586096,
|
| 671 |
+
"grad_norm": 1.0619679865152813,
|
| 672 |
+
"learning_rate": 9.574549893168979e-06,
|
| 673 |
+
"loss": 1.2929,
|
| 674 |
+
"step": 470
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.2216518898740084,
|
| 678 |
+
"grad_norm": 1.0679642526657762,
|
| 679 |
+
"learning_rate": 9.55795467164644e-06,
|
| 680 |
+
"loss": 1.2535,
|
| 681 |
+
"step": 475
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.22398506766215587,
|
| 685 |
+
"grad_norm": 1.5564747329752795,
|
| 686 |
+
"learning_rate": 9.541056902814899e-06,
|
| 687 |
+
"loss": 1.2675,
|
| 688 |
+
"step": 480
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.22631824545030332,
|
| 692 |
+
"grad_norm": 1.0444627624649723,
|
| 693 |
+
"learning_rate": 9.523857708312201e-06,
|
| 694 |
+
"loss": 1.2845,
|
| 695 |
+
"step": 485
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.22865142323845078,
|
| 699 |
+
"grad_norm": 1.0667210588899647,
|
| 700 |
+
"learning_rate": 9.506358229784195e-06,
|
| 701 |
+
"loss": 1.2848,
|
| 702 |
+
"step": 490
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.23098460102659824,
|
| 706 |
+
"grad_norm": 1.5842276148510732,
|
| 707 |
+
"learning_rate": 9.488559628808939e-06,
|
| 708 |
+
"loss": 1.2699,
|
| 709 |
+
"step": 495
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.2333177788147457,
|
| 713 |
+
"grad_norm": 0.9922450399570858,
|
| 714 |
+
"learning_rate": 9.4704630868196e-06,
|
| 715 |
+
"loss": 1.2803,
|
| 716 |
+
"step": 500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.23565095660289315,
|
| 720 |
+
"grad_norm": 1.0132074141463145,
|
| 721 |
+
"learning_rate": 9.452069805026038e-06,
|
| 722 |
+
"loss": 1.2705,
|
| 723 |
+
"step": 505
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.2379841343910406,
|
| 727 |
+
"grad_norm": 1.026988458522716,
|
| 728 |
+
"learning_rate": 9.433381004335062e-06,
|
| 729 |
+
"loss": 1.2762,
|
| 730 |
+
"step": 510
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.24031731217918806,
|
| 734 |
+
"grad_norm": 1.1203984022146773,
|
| 735 |
+
"learning_rate": 9.414397925269402e-06,
|
| 736 |
+
"loss": 1.3016,
|
| 737 |
+
"step": 515
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.24265048996733551,
|
| 741 |
+
"grad_norm": 1.0671496131373208,
|
| 742 |
+
"learning_rate": 9.395121827885356e-06,
|
| 743 |
+
"loss": 1.2911,
|
| 744 |
+
"step": 520
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.24498366775548297,
|
| 748 |
+
"grad_norm": 2.7685041556877423,
|
| 749 |
+
"learning_rate": 9.37555399168915e-06,
|
| 750 |
+
"loss": 1.2775,
|
| 751 |
+
"step": 525
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.24731684554363043,
|
| 755 |
+
"grad_norm": 2.8528623255508117,
|
| 756 |
+
"learning_rate": 9.355695715552013e-06,
|
| 757 |
+
"loss": 1.2716,
|
| 758 |
+
"step": 530
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.24965002333177788,
|
| 762 |
+
"grad_norm": 1.2859643878984603,
|
| 763 |
+
"learning_rate": 9.335548317623957e-06,
|
| 764 |
+
"loss": 1.2728,
|
| 765 |
+
"step": 535
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.25198320111992534,
|
| 769 |
+
"grad_norm": 2.4274725182984844,
|
| 770 |
+
"learning_rate": 9.315113135246285e-06,
|
| 771 |
+
"loss": 1.2754,
|
| 772 |
+
"step": 540
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.2543163789080728,
|
| 776 |
+
"grad_norm": 1.1217174489348858,
|
| 777 |
+
"learning_rate": 9.294391524862811e-06,
|
| 778 |
+
"loss": 1.2604,
|
| 779 |
+
"step": 545
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.25664955669622025,
|
| 783 |
+
"grad_norm": 1.0486163590013748,
|
| 784 |
+
"learning_rate": 9.273384861929837e-06,
|
| 785 |
+
"loss": 1.2703,
|
| 786 |
+
"step": 550
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.2589827344843677,
|
| 790 |
+
"grad_norm": 1.0528093884917247,
|
| 791 |
+
"learning_rate": 9.252094540824839e-06,
|
| 792 |
+
"loss": 1.2691,
|
| 793 |
+
"step": 555
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.26131591227251516,
|
| 797 |
+
"grad_norm": 1.9102440979365067,
|
| 798 |
+
"learning_rate": 9.23052197475392e-06,
|
| 799 |
+
"loss": 1.2659,
|
| 800 |
+
"step": 560
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.2636490900606626,
|
| 804 |
+
"grad_norm": 1.0178265895261382,
|
| 805 |
+
"learning_rate": 9.208668595658002e-06,
|
| 806 |
+
"loss": 1.2752,
|
| 807 |
+
"step": 565
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.26598226784881007,
|
| 811 |
+
"grad_norm": 2.197285212459847,
|
| 812 |
+
"learning_rate": 9.186535854117778e-06,
|
| 813 |
+
"loss": 1.2634,
|
| 814 |
+
"step": 570
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.26831544563695753,
|
| 818 |
+
"grad_norm": 1.0083314151134946,
|
| 819 |
+
"learning_rate": 9.164125219257419e-06,
|
| 820 |
+
"loss": 1.2624,
|
| 821 |
+
"step": 575
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.270648623425105,
|
| 825 |
+
"grad_norm": 1.0602777669989065,
|
| 826 |
+
"learning_rate": 9.141438178647066e-06,
|
| 827 |
+
"loss": 1.2643,
|
| 828 |
+
"step": 580
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.27298180121325244,
|
| 832 |
+
"grad_norm": 1.0717173948847758,
|
| 833 |
+
"learning_rate": 9.118476238204086e-06,
|
| 834 |
+
"loss": 1.2876,
|
| 835 |
+
"step": 585
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.2753149790013999,
|
| 839 |
+
"grad_norm": 1.1056050793242909,
|
| 840 |
+
"learning_rate": 9.095240922093106e-06,
|
| 841 |
+
"loss": 1.2728,
|
| 842 |
+
"step": 590
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.27764815678954735,
|
| 846 |
+
"grad_norm": 1.0422843147354741,
|
| 847 |
+
"learning_rate": 9.071733772624847e-06,
|
| 848 |
+
"loss": 1.2581,
|
| 849 |
+
"step": 595
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.2799813345776948,
|
| 853 |
+
"grad_norm": 1.0261265251675429,
|
| 854 |
+
"learning_rate": 9.047956350153752e-06,
|
| 855 |
+
"loss": 1.2678,
|
| 856 |
+
"step": 600
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.28231451236584226,
|
| 860 |
+
"grad_norm": 1.034637763098494,
|
| 861 |
+
"learning_rate": 9.023910232974409e-06,
|
| 862 |
+
"loss": 1.2521,
|
| 863 |
+
"step": 605
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.2846476901539897,
|
| 867 |
+
"grad_norm": 1.0323624643145786,
|
| 868 |
+
"learning_rate": 8.999597017216783e-06,
|
| 869 |
+
"loss": 1.261,
|
| 870 |
+
"step": 610
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.2869808679421372,
|
| 874 |
+
"grad_norm": 1.0481523558473382,
|
| 875 |
+
"learning_rate": 8.975018316740278e-06,
|
| 876 |
+
"loss": 1.254,
|
| 877 |
+
"step": 615
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.28931404573028463,
|
| 881 |
+
"grad_norm": 1.1605502914450527,
|
| 882 |
+
"learning_rate": 8.950175763026606e-06,
|
| 883 |
+
"loss": 1.263,
|
| 884 |
+
"step": 620
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.2916472235184321,
|
| 888 |
+
"grad_norm": 1.0934897325180564,
|
| 889 |
+
"learning_rate": 8.92507100507149e-06,
|
| 890 |
+
"loss": 1.2486,
|
| 891 |
+
"step": 625
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.29398040130657954,
|
| 895 |
+
"grad_norm": 1.0558730155031821,
|
| 896 |
+
"learning_rate": 8.899705709275218e-06,
|
| 897 |
+
"loss": 1.2428,
|
| 898 |
+
"step": 630
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.296313579094727,
|
| 902 |
+
"grad_norm": 1.0295350215627783,
|
| 903 |
+
"learning_rate": 8.87408155933202e-06,
|
| 904 |
+
"loss": 1.2707,
|
| 905 |
+
"step": 635
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.29864675688287445,
|
| 909 |
+
"grad_norm": 1.0694009076261313,
|
| 910 |
+
"learning_rate": 8.848200256118312e-06,
|
| 911 |
+
"loss": 1.2653,
|
| 912 |
+
"step": 640
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.3009799346710219,
|
| 916 |
+
"grad_norm": 1.0753277243247061,
|
| 917 |
+
"learning_rate": 8.822063517579798e-06,
|
| 918 |
+
"loss": 1.2397,
|
| 919 |
+
"step": 645
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.30331311245916937,
|
| 923 |
+
"grad_norm": 1.0535024700747178,
|
| 924 |
+
"learning_rate": 8.795673078617433e-06,
|
| 925 |
+
"loss": 1.2595,
|
| 926 |
+
"step": 650
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.3056462902473168,
|
| 930 |
+
"grad_norm": 1.0137561554460717,
|
| 931 |
+
"learning_rate": 8.769030690972262e-06,
|
| 932 |
+
"loss": 1.2262,
|
| 933 |
+
"step": 655
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.3079794680354643,
|
| 937 |
+
"grad_norm": 1.0932783124268566,
|
| 938 |
+
"learning_rate": 8.742138123109152e-06,
|
| 939 |
+
"loss": 1.2393,
|
| 940 |
+
"step": 660
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.31031264582361173,
|
| 944 |
+
"grad_norm": 1.0628280551049016,
|
| 945 |
+
"learning_rate": 8.714997160099394e-06,
|
| 946 |
+
"loss": 1.2529,
|
| 947 |
+
"step": 665
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.31264582361175924,
|
| 951 |
+
"grad_norm": 1.0650855341182235,
|
| 952 |
+
"learning_rate": 8.687609603502221e-06,
|
| 953 |
+
"loss": 1.239,
|
| 954 |
+
"step": 670
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.3149790013999067,
|
| 958 |
+
"grad_norm": 1.0418454815263511,
|
| 959 |
+
"learning_rate": 8.659977271245224e-06,
|
| 960 |
+
"loss": 1.2365,
|
| 961 |
+
"step": 675
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.31731217918805416,
|
| 965 |
+
"grad_norm": 1.0693052438489,
|
| 966 |
+
"learning_rate": 8.632101997503676e-06,
|
| 967 |
+
"loss": 1.2553,
|
| 968 |
+
"step": 680
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.3196453569762016,
|
| 972 |
+
"grad_norm": 1.3138342888196584,
|
| 973 |
+
"learning_rate": 8.603985632578793e-06,
|
| 974 |
+
"loss": 1.2461,
|
| 975 |
+
"step": 685
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.32197853476434907,
|
| 979 |
+
"grad_norm": 1.0223048276218463,
|
| 980 |
+
"learning_rate": 8.575630042774903e-06,
|
| 981 |
+
"loss": 1.225,
|
| 982 |
+
"step": 690
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.3243117125524965,
|
| 986 |
+
"grad_norm": 1.0450282062346927,
|
| 987 |
+
"learning_rate": 8.54703711027558e-06,
|
| 988 |
+
"loss": 1.2262,
|
| 989 |
+
"step": 695
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.326644890340644,
|
| 993 |
+
"grad_norm": 0.9918363416045388,
|
| 994 |
+
"learning_rate": 8.51820873301869e-06,
|
| 995 |
+
"loss": 1.2573,
|
| 996 |
+
"step": 700
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.32897806812879143,
|
| 1000 |
+
"grad_norm": 1.06271246651747,
|
| 1001 |
+
"learning_rate": 8.489146824570427e-06,
|
| 1002 |
+
"loss": 1.2548,
|
| 1003 |
+
"step": 705
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.3313112459169389,
|
| 1007 |
+
"grad_norm": 1.9277320512581375,
|
| 1008 |
+
"learning_rate": 8.459853313998285e-06,
|
| 1009 |
+
"loss": 1.2272,
|
| 1010 |
+
"step": 710
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.33364442370508635,
|
| 1014 |
+
"grad_norm": 1.0225880982273274,
|
| 1015 |
+
"learning_rate": 8.430330145743011e-06,
|
| 1016 |
+
"loss": 1.2584,
|
| 1017 |
+
"step": 715
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.3359776014932338,
|
| 1021 |
+
"grad_norm": 1.0170952993101696,
|
| 1022 |
+
"learning_rate": 8.40057927948954e-06,
|
| 1023 |
+
"loss": 1.2332,
|
| 1024 |
+
"step": 720
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.33831077928138126,
|
| 1028 |
+
"grad_norm": 1.0726533938970475,
|
| 1029 |
+
"learning_rate": 8.370602690036922e-06,
|
| 1030 |
+
"loss": 1.2551,
|
| 1031 |
+
"step": 725
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.3406439570695287,
|
| 1035 |
+
"grad_norm": 1.0448011850008472,
|
| 1036 |
+
"learning_rate": 8.340402367167217e-06,
|
| 1037 |
+
"loss": 1.2558,
|
| 1038 |
+
"step": 730
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.34297713485767617,
|
| 1042 |
+
"grad_norm": 1.0134797522135224,
|
| 1043 |
+
"learning_rate": 8.309980315513444e-06,
|
| 1044 |
+
"loss": 1.2589,
|
| 1045 |
+
"step": 735
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.3453103126458236,
|
| 1049 |
+
"grad_norm": 1.0991723144604053,
|
| 1050 |
+
"learning_rate": 8.279338554426501e-06,
|
| 1051 |
+
"loss": 1.2392,
|
| 1052 |
+
"step": 740
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.3476434904339711,
|
| 1056 |
+
"grad_norm": 1.071882495980135,
|
| 1057 |
+
"learning_rate": 8.248479117841131e-06,
|
| 1058 |
+
"loss": 1.2587,
|
| 1059 |
+
"step": 745
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.34997666822211854,
|
| 1063 |
+
"grad_norm": 1.0685500688501697,
|
| 1064 |
+
"learning_rate": 8.21740405414091e-06,
|
| 1065 |
+
"loss": 1.2353,
|
| 1066 |
+
"step": 750
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.352309846010266,
|
| 1070 |
+
"grad_norm": 1.042339901064479,
|
| 1071 |
+
"learning_rate": 8.186115426022286e-06,
|
| 1072 |
+
"loss": 1.245,
|
| 1073 |
+
"step": 755
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.35464302379841345,
|
| 1077 |
+
"grad_norm": 1.066718894369678,
|
| 1078 |
+
"learning_rate": 8.15461531035765e-06,
|
| 1079 |
+
"loss": 1.2464,
|
| 1080 |
+
"step": 760
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.3569762015865609,
|
| 1084 |
+
"grad_norm": 1.0022004592600267,
|
| 1085 |
+
"learning_rate": 8.122905798057496e-06,
|
| 1086 |
+
"loss": 1.2288,
|
| 1087 |
+
"step": 765
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.35930937937470836,
|
| 1091 |
+
"grad_norm": 1.0463029745800396,
|
| 1092 |
+
"learning_rate": 8.09098899393161e-06,
|
| 1093 |
+
"loss": 1.2366,
|
| 1094 |
+
"step": 770
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.3616425571628558,
|
| 1098 |
+
"grad_norm": 1.003258240089985,
|
| 1099 |
+
"learning_rate": 8.058867016549372e-06,
|
| 1100 |
+
"loss": 1.2427,
|
| 1101 |
+
"step": 775
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.36397573495100327,
|
| 1105 |
+
"grad_norm": 1.0222698171488636,
|
| 1106 |
+
"learning_rate": 8.026541998099128e-06,
|
| 1107 |
+
"loss": 1.2322,
|
| 1108 |
+
"step": 780
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.3663089127391507,
|
| 1112 |
+
"grad_norm": 1.0420407590803933,
|
| 1113 |
+
"learning_rate": 7.99401608424665e-06,
|
| 1114 |
+
"loss": 1.2206,
|
| 1115 |
+
"step": 785
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.3686420905272982,
|
| 1119 |
+
"grad_norm": 1.04348299507265,
|
| 1120 |
+
"learning_rate": 7.961291433992724e-06,
|
| 1121 |
+
"loss": 1.226,
|
| 1122 |
+
"step": 790
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.37097526831544564,
|
| 1126 |
+
"grad_norm": 1.022552265241213,
|
| 1127 |
+
"learning_rate": 7.92837021952983e-06,
|
| 1128 |
+
"loss": 1.2259,
|
| 1129 |
+
"step": 795
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.3733084461035931,
|
| 1133 |
+
"grad_norm": 1.097606795470717,
|
| 1134 |
+
"learning_rate": 7.895254626097965e-06,
|
| 1135 |
+
"loss": 1.2384,
|
| 1136 |
+
"step": 800
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.37564162389174055,
|
| 1140 |
+
"grad_norm": 1.0541836162910783,
|
| 1141 |
+
"learning_rate": 7.861946851839587e-06,
|
| 1142 |
+
"loss": 1.2487,
|
| 1143 |
+
"step": 805
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.377974801679888,
|
| 1147 |
+
"grad_norm": 1.0349968149631121,
|
| 1148 |
+
"learning_rate": 7.828449107653703e-06,
|
| 1149 |
+
"loss": 1.2403,
|
| 1150 |
+
"step": 810
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.38030797946803546,
|
| 1154 |
+
"grad_norm": 1.062977072731999,
|
| 1155 |
+
"learning_rate": 7.794763617049124e-06,
|
| 1156 |
+
"loss": 1.2151,
|
| 1157 |
+
"step": 815
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.3826411572561829,
|
| 1161 |
+
"grad_norm": 1.017338250886252,
|
| 1162 |
+
"learning_rate": 7.760892615996863e-06,
|
| 1163 |
+
"loss": 1.2171,
|
| 1164 |
+
"step": 820
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.3849743350443304,
|
| 1168 |
+
"grad_norm": 2.3082015473298063,
|
| 1169 |
+
"learning_rate": 7.726838352781722e-06,
|
| 1170 |
+
"loss": 1.2324,
|
| 1171 |
+
"step": 825
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.38730751283247783,
|
| 1175 |
+
"grad_norm": 1.058808550011615,
|
| 1176 |
+
"learning_rate": 7.692603087853061e-06,
|
| 1177 |
+
"loss": 1.1991,
|
| 1178 |
+
"step": 830
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.3896406906206253,
|
| 1182 |
+
"grad_norm": 1.0499629018100114,
|
| 1183 |
+
"learning_rate": 7.658189093674738e-06,
|
| 1184 |
+
"loss": 1.2086,
|
| 1185 |
+
"step": 835
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.39197386840877274,
|
| 1189 |
+
"grad_norm": 1.0569128259398222,
|
| 1190 |
+
"learning_rate": 7.623598654574282e-06,
|
| 1191 |
+
"loss": 1.2272,
|
| 1192 |
+
"step": 840
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.3943070461969202,
|
| 1196 |
+
"grad_norm": 1.0286667886499616,
|
| 1197 |
+
"learning_rate": 7.588834066591262e-06,
|
| 1198 |
+
"loss": 1.1978,
|
| 1199 |
+
"step": 845
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.39664022398506765,
|
| 1203 |
+
"grad_norm": 1.2741293758254737,
|
| 1204 |
+
"learning_rate": 7.5538976373248714e-06,
|
| 1205 |
+
"loss": 1.2325,
|
| 1206 |
+
"step": 850
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.3989734017732151,
|
| 1210 |
+
"grad_norm": 1.0435046533642063,
|
| 1211 |
+
"learning_rate": 7.518791685780769e-06,
|
| 1212 |
+
"loss": 1.2181,
|
| 1213 |
+
"step": 855
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.40130657956136256,
|
| 1217 |
+
"grad_norm": 1.0477549817973404,
|
| 1218 |
+
"learning_rate": 7.483518542217136e-06,
|
| 1219 |
+
"loss": 1.21,
|
| 1220 |
+
"step": 860
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.40363975734951,
|
| 1224 |
+
"grad_norm": 1.0098176664351024,
|
| 1225 |
+
"learning_rate": 7.448080547990004e-06,
|
| 1226 |
+
"loss": 1.2155,
|
| 1227 |
+
"step": 865
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.4059729351376575,
|
| 1231 |
+
"grad_norm": 1.0230304313094294,
|
| 1232 |
+
"learning_rate": 7.412480055397844e-06,
|
| 1233 |
+
"loss": 1.2223,
|
| 1234 |
+
"step": 870
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.40830611292580493,
|
| 1238 |
+
"grad_norm": 1.0759762672999653,
|
| 1239 |
+
"learning_rate": 7.376719427525415e-06,
|
| 1240 |
+
"loss": 1.2253,
|
| 1241 |
+
"step": 875
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.4106392907139524,
|
| 1245 |
+
"grad_norm": 1.0624534512175727,
|
| 1246 |
+
"learning_rate": 7.340801038086919e-06,
|
| 1247 |
+
"loss": 1.2162,
|
| 1248 |
+
"step": 880
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.41297246850209984,
|
| 1252 |
+
"grad_norm": 1.0857553904287731,
|
| 1253 |
+
"learning_rate": 7.304727271268435e-06,
|
| 1254 |
+
"loss": 1.221,
|
| 1255 |
+
"step": 885
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.4153056462902473,
|
| 1259 |
+
"grad_norm": 1.0668655239257339,
|
| 1260 |
+
"learning_rate": 7.2685005215696555e-06,
|
| 1261 |
+
"loss": 1.2144,
|
| 1262 |
+
"step": 890
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.41763882407839475,
|
| 1266 |
+
"grad_norm": 1.1051644997392926,
|
| 1267 |
+
"learning_rate": 7.232123193644957e-06,
|
| 1268 |
+
"loss": 1.2267,
|
| 1269 |
+
"step": 895
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.4199720018665422,
|
| 1273 |
+
"grad_norm": 1.072660002160975,
|
| 1274 |
+
"learning_rate": 7.1955977021437725e-06,
|
| 1275 |
+
"loss": 1.2052,
|
| 1276 |
+
"step": 900
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.42230517965468967,
|
| 1280 |
+
"grad_norm": 1.0547907347649101,
|
| 1281 |
+
"learning_rate": 7.158926471550322e-06,
|
| 1282 |
+
"loss": 1.217,
|
| 1283 |
+
"step": 905
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.4246383574428371,
|
| 1287 |
+
"grad_norm": 1.0373918799651074,
|
| 1288 |
+
"learning_rate": 7.122111936022668e-06,
|
| 1289 |
+
"loss": 1.1991,
|
| 1290 |
+
"step": 910
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.4269715352309846,
|
| 1294 |
+
"grad_norm": 1.0180347309655173,
|
| 1295 |
+
"learning_rate": 7.085156539231159e-06,
|
| 1296 |
+
"loss": 1.2048,
|
| 1297 |
+
"step": 915
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.42930471301913203,
|
| 1301 |
+
"grad_norm": 1.0020432136327553,
|
| 1302 |
+
"learning_rate": 7.048062734196205e-06,
|
| 1303 |
+
"loss": 1.2069,
|
| 1304 |
+
"step": 920
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.4316378908072795,
|
| 1308 |
+
"grad_norm": 1.0019624234869275,
|
| 1309 |
+
"learning_rate": 7.010832983125464e-06,
|
| 1310 |
+
"loss": 1.2123,
|
| 1311 |
+
"step": 925
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.43397106859542695,
|
| 1315 |
+
"grad_norm": 1.0444982695681746,
|
| 1316 |
+
"learning_rate": 6.9734697572504e-06,
|
| 1317 |
+
"loss": 1.2149,
|
| 1318 |
+
"step": 930
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.4363042463835744,
|
| 1322 |
+
"grad_norm": 1.055679566452759,
|
| 1323 |
+
"learning_rate": 6.935975536662254e-06,
|
| 1324 |
+
"loss": 1.2142,
|
| 1325 |
+
"step": 935
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.4386374241717219,
|
| 1329 |
+
"grad_norm": 1.0048337902872553,
|
| 1330 |
+
"learning_rate": 6.898352810147412e-06,
|
| 1331 |
+
"loss": 1.2126,
|
| 1332 |
+
"step": 940
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.44097060195986937,
|
| 1336 |
+
"grad_norm": 1.0301369602777193,
|
| 1337 |
+
"learning_rate": 6.8606040750222105e-06,
|
| 1338 |
+
"loss": 1.2124,
|
| 1339 |
+
"step": 945
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.4433037797480168,
|
| 1343 |
+
"grad_norm": 1.1560038891523179,
|
| 1344 |
+
"learning_rate": 6.822731836967169e-06,
|
| 1345 |
+
"loss": 1.1984,
|
| 1346 |
+
"step": 950
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.4456369575361643,
|
| 1350 |
+
"grad_norm": 1.5225878413594751,
|
| 1351 |
+
"learning_rate": 6.784738609860668e-06,
|
| 1352 |
+
"loss": 1.194,
|
| 1353 |
+
"step": 955
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.44797013532431174,
|
| 1357 |
+
"grad_norm": 1.0394310371271565,
|
| 1358 |
+
"learning_rate": 6.746626915612086e-06,
|
| 1359 |
+
"loss": 1.2145,
|
| 1360 |
+
"step": 960
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.4503033131124592,
|
| 1364 |
+
"grad_norm": 1.025841604703853,
|
| 1365 |
+
"learning_rate": 6.708399283994392e-06,
|
| 1366 |
+
"loss": 1.208,
|
| 1367 |
+
"step": 965
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.45263649090060665,
|
| 1371 |
+
"grad_norm": 1.0626994430061882,
|
| 1372 |
+
"learning_rate": 6.6700582524762354e-06,
|
| 1373 |
+
"loss": 1.2222,
|
| 1374 |
+
"step": 970
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.4549696686887541,
|
| 1378 |
+
"grad_norm": 1.0339134333462732,
|
| 1379 |
+
"learning_rate": 6.631606366053507e-06,
|
| 1380 |
+
"loss": 1.1966,
|
| 1381 |
+
"step": 975
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.45730284647690156,
|
| 1385 |
+
"grad_norm": 1.0081371270360229,
|
| 1386 |
+
"learning_rate": 6.593046177080409e-06,
|
| 1387 |
+
"loss": 1.1999,
|
| 1388 |
+
"step": 980
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.459636024265049,
|
| 1392 |
+
"grad_norm": 1.0694789970224579,
|
| 1393 |
+
"learning_rate": 6.554380245100035e-06,
|
| 1394 |
+
"loss": 1.204,
|
| 1395 |
+
"step": 985
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.46196920205319647,
|
| 1399 |
+
"grad_norm": 1.000889123266167,
|
| 1400 |
+
"learning_rate": 6.51561113667448e-06,
|
| 1401 |
+
"loss": 1.2194,
|
| 1402 |
+
"step": 990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.4643023798413439,
|
| 1406 |
+
"grad_norm": 1.0630980618578947,
|
| 1407 |
+
"learning_rate": 6.476741425214464e-06,
|
| 1408 |
+
"loss": 1.1853,
|
| 1409 |
+
"step": 995
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.4666355576294914,
|
| 1413 |
+
"grad_norm": 1.0311623863233943,
|
| 1414 |
+
"learning_rate": 6.437773690808526e-06,
|
| 1415 |
+
"loss": 1.1926,
|
| 1416 |
+
"step": 1000
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.46896873541763884,
|
| 1420 |
+
"grad_norm": 1.0533210989046884,
|
| 1421 |
+
"learning_rate": 6.3987105200517565e-06,
|
| 1422 |
+
"loss": 1.2123,
|
| 1423 |
+
"step": 1005
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.4713019132057863,
|
| 1427 |
+
"grad_norm": 1.0436147901486108,
|
| 1428 |
+
"learning_rate": 6.359554505874109e-06,
|
| 1429 |
+
"loss": 1.1944,
|
| 1430 |
+
"step": 1010
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.47363509099393375,
|
| 1434 |
+
"grad_norm": 5.5623971506515755,
|
| 1435 |
+
"learning_rate": 6.320308247368285e-06,
|
| 1436 |
+
"loss": 1.2146,
|
| 1437 |
+
"step": 1015
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.4759682687820812,
|
| 1441 |
+
"grad_norm": 1.0083178059337383,
|
| 1442 |
+
"learning_rate": 6.280974349617215e-06,
|
| 1443 |
+
"loss": 1.1896,
|
| 1444 |
+
"step": 1020
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.47830144657022866,
|
| 1448 |
+
"grad_norm": 0.9918638956644074,
|
| 1449 |
+
"learning_rate": 6.241555423521129e-06,
|
| 1450 |
+
"loss": 1.2006,
|
| 1451 |
+
"step": 1025
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.4806346243583761,
|
| 1455 |
+
"grad_norm": 1.0425283854831346,
|
| 1456 |
+
"learning_rate": 6.202054085624262e-06,
|
| 1457 |
+
"loss": 1.1955,
|
| 1458 |
+
"step": 1030
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.4829678021465236,
|
| 1462 |
+
"grad_norm": 1.0174742035512065,
|
| 1463 |
+
"learning_rate": 6.162472957941167e-06,
|
| 1464 |
+
"loss": 1.183,
|
| 1465 |
+
"step": 1035
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.48530097993467103,
|
| 1469 |
+
"grad_norm": 1.0687571711931383,
|
| 1470 |
+
"learning_rate": 6.122814667782674e-06,
|
| 1471 |
+
"loss": 1.1985,
|
| 1472 |
+
"step": 1040
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.4876341577228185,
|
| 1476 |
+
"grad_norm": 1.0330507478699027,
|
| 1477 |
+
"learning_rate": 6.083081847581491e-06,
|
| 1478 |
+
"loss": 1.1945,
|
| 1479 |
+
"step": 1045
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.48996733551096594,
|
| 1483 |
+
"grad_norm": 1.0594437081263992,
|
| 1484 |
+
"learning_rate": 6.0432771347174755e-06,
|
| 1485 |
+
"loss": 1.1991,
|
| 1486 |
+
"step": 1050
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.4923005132991134,
|
| 1490 |
+
"grad_norm": 1.013334160895624,
|
| 1491 |
+
"learning_rate": 6.0034031713425636e-06,
|
| 1492 |
+
"loss": 1.2163,
|
| 1493 |
+
"step": 1055
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.49463369108726085,
|
| 1497 |
+
"grad_norm": 1.034975289803585,
|
| 1498 |
+
"learning_rate": 5.963462604205392e-06,
|
| 1499 |
+
"loss": 1.2049,
|
| 1500 |
+
"step": 1060
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.4969668688754083,
|
| 1504 |
+
"grad_norm": 1.0450297189254285,
|
| 1505 |
+
"learning_rate": 5.923458084475616e-06,
|
| 1506 |
+
"loss": 1.2088,
|
| 1507 |
+
"step": 1065
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.49930004666355576,
|
| 1511 |
+
"grad_norm": 1.0056642936962568,
|
| 1512 |
+
"learning_rate": 5.883392267567925e-06,
|
| 1513 |
+
"loss": 1.2074,
|
| 1514 |
+
"step": 1070
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.5016332244517032,
|
| 1518 |
+
"grad_norm": 1.016432945817497,
|
| 1519 |
+
"learning_rate": 5.843267812965783e-06,
|
| 1520 |
+
"loss": 1.2003,
|
| 1521 |
+
"step": 1075
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.5039664022398507,
|
| 1525 |
+
"grad_norm": 1.0274596198864308,
|
| 1526 |
+
"learning_rate": 5.803087384044903e-06,
|
| 1527 |
+
"loss": 1.1848,
|
| 1528 |
+
"step": 1080
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.5062995800279981,
|
| 1532 |
+
"grad_norm": 1.0466692891981038,
|
| 1533 |
+
"learning_rate": 5.7628536478964535e-06,
|
| 1534 |
+
"loss": 1.1996,
|
| 1535 |
+
"step": 1085
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.5086327578161456,
|
| 1539 |
+
"grad_norm": 1.0492908600438546,
|
| 1540 |
+
"learning_rate": 5.722569275150019e-06,
|
| 1541 |
+
"loss": 1.1687,
|
| 1542 |
+
"step": 1090
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.510965935604293,
|
| 1546 |
+
"grad_norm": 1.0525465489835544,
|
| 1547 |
+
"learning_rate": 5.682236939796337e-06,
|
| 1548 |
+
"loss": 1.188,
|
| 1549 |
+
"step": 1095
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.5132991133924405,
|
| 1553 |
+
"grad_norm": 1.0772606646287202,
|
| 1554 |
+
"learning_rate": 5.6418593190098015e-06,
|
| 1555 |
+
"loss": 1.1919,
|
| 1556 |
+
"step": 1100
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.515632291180588,
|
| 1560 |
+
"grad_norm": 1.0262934950657279,
|
| 1561 |
+
"learning_rate": 5.601439092970751e-06,
|
| 1562 |
+
"loss": 1.1974,
|
| 1563 |
+
"step": 1105
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.5179654689687354,
|
| 1567 |
+
"grad_norm": 0.9882060325666545,
|
| 1568 |
+
"learning_rate": 5.560978944687577e-06,
|
| 1569 |
+
"loss": 1.178,
|
| 1570 |
+
"step": 1110
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.5202986467568829,
|
| 1574 |
+
"grad_norm": 1.091230449252659,
|
| 1575 |
+
"learning_rate": 5.52048155981862e-06,
|
| 1576 |
+
"loss": 1.1781,
|
| 1577 |
+
"step": 1115
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.5226318245450303,
|
| 1581 |
+
"grad_norm": 1.0720517862549939,
|
| 1582 |
+
"learning_rate": 5.4799496264939075e-06,
|
| 1583 |
+
"loss": 1.2012,
|
| 1584 |
+
"step": 1120
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.5249650023331778,
|
| 1588 |
+
"grad_norm": 1.0360319501350228,
|
| 1589 |
+
"learning_rate": 5.43938583513672e-06,
|
| 1590 |
+
"loss": 1.1781,
|
| 1591 |
+
"step": 1125
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.5272981801213252,
|
| 1595 |
+
"grad_norm": 1.0608281252879077,
|
| 1596 |
+
"learning_rate": 5.398792878285003e-06,
|
| 1597 |
+
"loss": 1.1936,
|
| 1598 |
+
"step": 1130
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.5296313579094727,
|
| 1602 |
+
"grad_norm": 1.0178618190287725,
|
| 1603 |
+
"learning_rate": 5.358173450412649e-06,
|
| 1604 |
+
"loss": 1.1705,
|
| 1605 |
+
"step": 1135
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.5319645356976201,
|
| 1609 |
+
"grad_norm": 1.0410116914098466,
|
| 1610 |
+
"learning_rate": 5.317530247750639e-06,
|
| 1611 |
+
"loss": 1.1886,
|
| 1612 |
+
"step": 1140
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.5342977134857676,
|
| 1616 |
+
"grad_norm": 1.001349734951812,
|
| 1617 |
+
"learning_rate": 5.276865968108075e-06,
|
| 1618 |
+
"loss": 1.1691,
|
| 1619 |
+
"step": 1145
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.5366308912739151,
|
| 1623 |
+
"grad_norm": 1.0165757948985048,
|
| 1624 |
+
"learning_rate": 5.2361833106931006e-06,
|
| 1625 |
+
"loss": 1.1818,
|
| 1626 |
+
"step": 1150
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.5389640690620625,
|
| 1630 |
+
"grad_norm": 1.0243614948148276,
|
| 1631 |
+
"learning_rate": 5.195484975933741e-06,
|
| 1632 |
+
"loss": 1.1804,
|
| 1633 |
+
"step": 1155
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.54129724685021,
|
| 1637 |
+
"grad_norm": 1.0155665041576496,
|
| 1638 |
+
"learning_rate": 5.1547736652986476e-06,
|
| 1639 |
+
"loss": 1.1835,
|
| 1640 |
+
"step": 1160
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.5436304246383574,
|
| 1644 |
+
"grad_norm": 3.5489961672985837,
|
| 1645 |
+
"learning_rate": 5.114052081117782e-06,
|
| 1646 |
+
"loss": 1.1865,
|
| 1647 |
+
"step": 1165
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.5459636024265049,
|
| 1651 |
+
"grad_norm": 1.072922376002081,
|
| 1652 |
+
"learning_rate": 5.073322926403046e-06,
|
| 1653 |
+
"loss": 1.1863,
|
| 1654 |
+
"step": 1170
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.5482967802146523,
|
| 1658 |
+
"grad_norm": 1.0757002599320986,
|
| 1659 |
+
"learning_rate": 5.032588904668851e-06,
|
| 1660 |
+
"loss": 1.192,
|
| 1661 |
+
"step": 1175
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.5506299580027998,
|
| 1665 |
+
"grad_norm": 1.052150214959031,
|
| 1666 |
+
"learning_rate": 4.991852719752678e-06,
|
| 1667 |
+
"loss": 1.1794,
|
| 1668 |
+
"step": 1180
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.5529631357909472,
|
| 1672 |
+
"grad_norm": 0.9792604457009882,
|
| 1673 |
+
"learning_rate": 4.951117075635589e-06,
|
| 1674 |
+
"loss": 1.1652,
|
| 1675 |
+
"step": 1185
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.5552963135790947,
|
| 1679 |
+
"grad_norm": 1.029786781573815,
|
| 1680 |
+
"learning_rate": 4.9103846762627525e-06,
|
| 1681 |
+
"loss": 1.1928,
|
| 1682 |
+
"step": 1190
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.5576294913672422,
|
| 1686 |
+
"grad_norm": 1.0817411344510528,
|
| 1687 |
+
"learning_rate": 4.869658225363957e-06,
|
| 1688 |
+
"loss": 1.1754,
|
| 1689 |
+
"step": 1195
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.5599626691553896,
|
| 1693 |
+
"grad_norm": 1.053945287751612,
|
| 1694 |
+
"learning_rate": 4.828940426274143e-06,
|
| 1695 |
+
"loss": 1.1822,
|
| 1696 |
+
"step": 1200
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.5622958469435371,
|
| 1700 |
+
"grad_norm": 1.0192353718407916,
|
| 1701 |
+
"learning_rate": 4.788233981753963e-06,
|
| 1702 |
+
"loss": 1.1951,
|
| 1703 |
+
"step": 1205
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.5646290247316845,
|
| 1707 |
+
"grad_norm": 1.0394836583943379,
|
| 1708 |
+
"learning_rate": 4.747541593810378e-06,
|
| 1709 |
+
"loss": 1.166,
|
| 1710 |
+
"step": 1210
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.566962202519832,
|
| 1714 |
+
"grad_norm": 1.0389217017606585,
|
| 1715 |
+
"learning_rate": 4.7068659635173034e-06,
|
| 1716 |
+
"loss": 1.1996,
|
| 1717 |
+
"step": 1215
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.5692953803079794,
|
| 1721 |
+
"grad_norm": 0.9924671865453442,
|
| 1722 |
+
"learning_rate": 4.666209790836317e-06,
|
| 1723 |
+
"loss": 1.1817,
|
| 1724 |
+
"step": 1220
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.5716285580961269,
|
| 1728 |
+
"grad_norm": 1.0453993868221274,
|
| 1729 |
+
"learning_rate": 4.6255757744374415e-06,
|
| 1730 |
+
"loss": 1.1521,
|
| 1731 |
+
"step": 1225
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.5739617358842743,
|
| 1735 |
+
"grad_norm": 0.9914403625368045,
|
| 1736 |
+
"learning_rate": 4.584966611520015e-06,
|
| 1737 |
+
"loss": 1.182,
|
| 1738 |
+
"step": 1230
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.5762949136724218,
|
| 1742 |
+
"grad_norm": 1.0158066663315228,
|
| 1743 |
+
"learning_rate": 4.54438499763365e-06,
|
| 1744 |
+
"loss": 1.175,
|
| 1745 |
+
"step": 1235
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.5786280914605693,
|
| 1749 |
+
"grad_norm": 0.995287982999789,
|
| 1750 |
+
"learning_rate": 4.503833626499318e-06,
|
| 1751 |
+
"loss": 1.1739,
|
| 1752 |
+
"step": 1240
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 0.5809612692487167,
|
| 1756 |
+
"grad_norm": 4.524070869987053,
|
| 1757 |
+
"learning_rate": 4.463315189830538e-06,
|
| 1758 |
+
"loss": 1.1867,
|
| 1759 |
+
"step": 1245
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.5832944470368642,
|
| 1763 |
+
"grad_norm": 1.2218885713123742,
|
| 1764 |
+
"learning_rate": 4.422832377154711e-06,
|
| 1765 |
+
"loss": 1.1849,
|
| 1766 |
+
"step": 1250
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 0.5856276248250116,
|
| 1770 |
+
"grad_norm": 5.8430320880046125,
|
| 1771 |
+
"learning_rate": 4.382387875634592e-06,
|
| 1772 |
+
"loss": 1.1845,
|
| 1773 |
+
"step": 1255
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.5879608026131591,
|
| 1777 |
+
"grad_norm": 0.9787534737025482,
|
| 1778 |
+
"learning_rate": 4.341984369889924e-06,
|
| 1779 |
+
"loss": 1.1864,
|
| 1780 |
+
"step": 1260
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 0.5902939804013065,
|
| 1784 |
+
"grad_norm": 1.0209274044087666,
|
| 1785 |
+
"learning_rate": 4.301624541819238e-06,
|
| 1786 |
+
"loss": 1.1912,
|
| 1787 |
+
"step": 1265
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.592627158189454,
|
| 1791 |
+
"grad_norm": 1.010815006280802,
|
| 1792 |
+
"learning_rate": 4.261311070421834e-06,
|
| 1793 |
+
"loss": 1.1754,
|
| 1794 |
+
"step": 1270
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 0.5949603359776015,
|
| 1798 |
+
"grad_norm": 0.999697309191565,
|
| 1799 |
+
"learning_rate": 4.221046631619956e-06,
|
| 1800 |
+
"loss": 1.1854,
|
| 1801 |
+
"step": 1275
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.5972935137657489,
|
| 1805 |
+
"grad_norm": 1.0078708746467304,
|
| 1806 |
+
"learning_rate": 4.180833898081167e-06,
|
| 1807 |
+
"loss": 1.1794,
|
| 1808 |
+
"step": 1280
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 0.5996266915538964,
|
| 1812 |
+
"grad_norm": 1.0344224025938935,
|
| 1813 |
+
"learning_rate": 4.140675539040945e-06,
|
| 1814 |
+
"loss": 1.1768,
|
| 1815 |
+
"step": 1285
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.6019598693420438,
|
| 1819 |
+
"grad_norm": 1.0205495767156563,
|
| 1820 |
+
"learning_rate": 4.100574220125507e-06,
|
| 1821 |
+
"loss": 1.1998,
|
| 1822 |
+
"step": 1290
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 0.6042930471301913,
|
| 1826 |
+
"grad_norm": 1.0190563305814853,
|
| 1827 |
+
"learning_rate": 4.060532603174865e-06,
|
| 1828 |
+
"loss": 1.1763,
|
| 1829 |
+
"step": 1295
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.6066262249183387,
|
| 1833 |
+
"grad_norm": 0.9863626578246152,
|
| 1834 |
+
"learning_rate": 4.020553346066145e-06,
|
| 1835 |
+
"loss": 1.1757,
|
| 1836 |
+
"step": 1300
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 0.6089594027064862,
|
| 1840 |
+
"grad_norm": 1.0418605510739205,
|
| 1841 |
+
"learning_rate": 3.980639102537156e-06,
|
| 1842 |
+
"loss": 1.1845,
|
| 1843 |
+
"step": 1305
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.6112925804946336,
|
| 1847 |
+
"grad_norm": 1.0007447729446544,
|
| 1848 |
+
"learning_rate": 3.94079252201025e-06,
|
| 1849 |
+
"loss": 1.1632,
|
| 1850 |
+
"step": 1310
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.6136257582827811,
|
| 1854 |
+
"grad_norm": 1.0189409387487824,
|
| 1855 |
+
"learning_rate": 3.9010162494164475e-06,
|
| 1856 |
+
"loss": 1.1815,
|
| 1857 |
+
"step": 1315
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.6159589360709286,
|
| 1861 |
+
"grad_norm": 1.0678347017077865,
|
| 1862 |
+
"learning_rate": 3.861312925019881e-06,
|
| 1863 |
+
"loss": 1.1741,
|
| 1864 |
+
"step": 1320
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 0.618292113859076,
|
| 1868 |
+
"grad_norm": 1.023653450517148,
|
| 1869 |
+
"learning_rate": 3.821685184242536e-06,
|
| 1870 |
+
"loss": 1.1772,
|
| 1871 |
+
"step": 1325
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.6206252916472235,
|
| 1875 |
+
"grad_norm": 1.0077779192122773,
|
| 1876 |
+
"learning_rate": 3.782135657489321e-06,
|
| 1877 |
+
"loss": 1.1894,
|
| 1878 |
+
"step": 1330
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 0.6229584694353709,
|
| 1882 |
+
"grad_norm": 1.012837709347067,
|
| 1883 |
+
"learning_rate": 3.742666969973463e-06,
|
| 1884 |
+
"loss": 1.1662,
|
| 1885 |
+
"step": 1335
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.6252916472235185,
|
| 1889 |
+
"grad_norm": 1.0245464657464427,
|
| 1890 |
+
"learning_rate": 3.703281741542252e-06,
|
| 1891 |
+
"loss": 1.1625,
|
| 1892 |
+
"step": 1340
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 0.6276248250116659,
|
| 1896 |
+
"grad_norm": 1.0253512043230175,
|
| 1897 |
+
"learning_rate": 3.663982586503143e-06,
|
| 1898 |
+
"loss": 1.1636,
|
| 1899 |
+
"step": 1345
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.6299580027998134,
|
| 1903 |
+
"grad_norm": 1.0666491380450174,
|
| 1904 |
+
"learning_rate": 3.6247721134502234e-06,
|
| 1905 |
+
"loss": 1.1811,
|
| 1906 |
+
"step": 1350
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 0.6322911805879609,
|
| 1910 |
+
"grad_norm": 1.0172119940529185,
|
| 1911 |
+
"learning_rate": 3.5856529250910565e-06,
|
| 1912 |
+
"loss": 1.1771,
|
| 1913 |
+
"step": 1355
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.6346243583761083,
|
| 1917 |
+
"grad_norm": 0.9785985628256346,
|
| 1918 |
+
"learning_rate": 3.5466276180739266e-06,
|
| 1919 |
+
"loss": 1.192,
|
| 1920 |
+
"step": 1360
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 0.6369575361642558,
|
| 1924 |
+
"grad_norm": 1.051013550076441,
|
| 1925 |
+
"learning_rate": 3.507698782815472e-06,
|
| 1926 |
+
"loss": 1.1865,
|
| 1927 |
+
"step": 1365
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.6392907139524032,
|
| 1931 |
+
"grad_norm": 1.8737444993472034,
|
| 1932 |
+
"learning_rate": 3.468869003328742e-06,
|
| 1933 |
+
"loss": 1.1748,
|
| 1934 |
+
"step": 1370
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 0.6416238917405507,
|
| 1938 |
+
"grad_norm": 1.0228057469556182,
|
| 1939 |
+
"learning_rate": 3.430140857051675e-06,
|
| 1940 |
+
"loss": 1.1832,
|
| 1941 |
+
"step": 1375
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.6439570695286981,
|
| 1945 |
+
"grad_norm": 1.007877431639191,
|
| 1946 |
+
"learning_rate": 3.3915169146760142e-06,
|
| 1947 |
+
"loss": 1.1733,
|
| 1948 |
+
"step": 1380
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 0.6462902473168456,
|
| 1952 |
+
"grad_norm": 1.0941054982268608,
|
| 1953 |
+
"learning_rate": 3.352999739976669e-06,
|
| 1954 |
+
"loss": 1.1687,
|
| 1955 |
+
"step": 1385
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.648623425104993,
|
| 1959 |
+
"grad_norm": 1.0342658633630413,
|
| 1960 |
+
"learning_rate": 3.3145918896415395e-06,
|
| 1961 |
+
"loss": 1.1712,
|
| 1962 |
+
"step": 1390
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 0.6509566028931405,
|
| 1966 |
+
"grad_norm": 1.025916026681626,
|
| 1967 |
+
"learning_rate": 3.276295913101808e-06,
|
| 1968 |
+
"loss": 1.1737,
|
| 1969 |
+
"step": 1395
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.653289780681288,
|
| 1973 |
+
"grad_norm": 1.0182487186812592,
|
| 1974 |
+
"learning_rate": 3.2381143523627113e-06,
|
| 1975 |
+
"loss": 1.1633,
|
| 1976 |
+
"step": 1400
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 0.6556229584694354,
|
| 1980 |
+
"grad_norm": 1.021349784405787,
|
| 1981 |
+
"learning_rate": 3.200049741834811e-06,
|
| 1982 |
+
"loss": 1.1892,
|
| 1983 |
+
"step": 1405
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.6579561362575829,
|
| 1987 |
+
"grad_norm": 1.0140718526442885,
|
| 1988 |
+
"learning_rate": 3.16210460816576e-06,
|
| 1989 |
+
"loss": 1.1657,
|
| 1990 |
+
"step": 1410
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 0.6602893140457303,
|
| 1994 |
+
"grad_norm": 1.041699791176852,
|
| 1995 |
+
"learning_rate": 3.1242814700725977e-06,
|
| 1996 |
+
"loss": 1.1744,
|
| 1997 |
+
"step": 1415
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.6626224918338778,
|
| 2001 |
+
"grad_norm": 1.0427445022423676,
|
| 2002 |
+
"learning_rate": 3.0865828381745515e-06,
|
| 2003 |
+
"loss": 1.1779,
|
| 2004 |
+
"step": 1420
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 0.6649556696220252,
|
| 2008 |
+
"grad_norm": 0.9640107625514102,
|
| 2009 |
+
"learning_rate": 3.0490112148263973e-06,
|
| 2010 |
+
"loss": 1.157,
|
| 2011 |
+
"step": 1425
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.6672888474101727,
|
| 2015 |
+
"grad_norm": 1.0334095168392121,
|
| 2016 |
+
"learning_rate": 3.011569093952352e-06,
|
| 2017 |
+
"loss": 1.1758,
|
| 2018 |
+
"step": 1430
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 0.6696220251983201,
|
| 2022 |
+
"grad_norm": 1.0183642848591992,
|
| 2023 |
+
"learning_rate": 2.974258960880535e-06,
|
| 2024 |
+
"loss": 1.1589,
|
| 2025 |
+
"step": 1435
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.6719552029864676,
|
| 2029 |
+
"grad_norm": 1.0119473556723952,
|
| 2030 |
+
"learning_rate": 2.9370832921779986e-06,
|
| 2031 |
+
"loss": 1.1639,
|
| 2032 |
+
"step": 1440
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 0.6742883807746151,
|
| 2036 |
+
"grad_norm": 1.0371459621618861,
|
| 2037 |
+
"learning_rate": 2.9000445554863355e-06,
|
| 2038 |
+
"loss": 1.165,
|
| 2039 |
+
"step": 1445
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.6766215585627625,
|
| 2043 |
+
"grad_norm": 1.04529673821227,
|
| 2044 |
+
"learning_rate": 2.8631452093578817e-06,
|
| 2045 |
+
"loss": 1.169,
|
| 2046 |
+
"step": 1450
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 0.67895473635091,
|
| 2050 |
+
"grad_norm": 1.0106613305134293,
|
| 2051 |
+
"learning_rate": 2.826387703092528e-06,
|
| 2052 |
+
"loss": 1.1584,
|
| 2053 |
+
"step": 1455
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.6812879141390574,
|
| 2057 |
+
"grad_norm": 1.0113769481277664,
|
| 2058 |
+
"learning_rate": 2.7897744765751376e-06,
|
| 2059 |
+
"loss": 1.1818,
|
| 2060 |
+
"step": 1460
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 0.6836210919272049,
|
| 2064 |
+
"grad_norm": 1.0410617373961402,
|
| 2065 |
+
"learning_rate": 2.753307960113593e-06,
|
| 2066 |
+
"loss": 1.1859,
|
| 2067 |
+
"step": 1465
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.6859542697153523,
|
| 2071 |
+
"grad_norm": 0.9922290642664283,
|
| 2072 |
+
"learning_rate": 2.7169905742774692e-06,
|
| 2073 |
+
"loss": 1.1654,
|
| 2074 |
+
"step": 1470
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 0.6882874475034998,
|
| 2078 |
+
"grad_norm": 0.9854965604430632,
|
| 2079 |
+
"learning_rate": 2.680824729737378e-06,
|
| 2080 |
+
"loss": 1.1599,
|
| 2081 |
+
"step": 1475
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.6906206252916472,
|
| 2085 |
+
"grad_norm": 0.9743286263890597,
|
| 2086 |
+
"learning_rate": 2.6448128271049335e-06,
|
| 2087 |
+
"loss": 1.1694,
|
| 2088 |
+
"step": 1480
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 0.6929538030797947,
|
| 2092 |
+
"grad_norm": 16.6481135030239,
|
| 2093 |
+
"learning_rate": 2.608957256773424e-06,
|
| 2094 |
+
"loss": 1.1748,
|
| 2095 |
+
"step": 1485
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.6952869808679422,
|
| 2099 |
+
"grad_norm": 1.0101412182159915,
|
| 2100 |
+
"learning_rate": 2.5732603987591254e-06,
|
| 2101 |
+
"loss": 1.1512,
|
| 2102 |
+
"step": 1490
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 0.6976201586560896,
|
| 2106 |
+
"grad_norm": 1.0080746469827888,
|
| 2107 |
+
"learning_rate": 2.5377246225433306e-06,
|
| 2108 |
+
"loss": 1.1706,
|
| 2109 |
+
"step": 1495
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.6999533364442371,
|
| 2113 |
+
"grad_norm": 1.0163159887181514,
|
| 2114 |
+
"learning_rate": 2.5023522869150708e-06,
|
| 2115 |
+
"loss": 1.1731,
|
| 2116 |
+
"step": 1500
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.7022865142323845,
|
| 2120 |
+
"grad_norm": 1.0291675596418361,
|
| 2121 |
+
"learning_rate": 2.4671457398145315e-06,
|
| 2122 |
+
"loss": 1.1803,
|
| 2123 |
+
"step": 1505
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.704619692020532,
|
| 2127 |
+
"grad_norm": 1.0014228929233164,
|
| 2128 |
+
"learning_rate": 2.4321073181772176e-06,
|
| 2129 |
+
"loss": 1.1614,
|
| 2130 |
+
"step": 1510
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 0.7069528698086794,
|
| 2134 |
+
"grad_norm": 0.9947617503534548,
|
| 2135 |
+
"learning_rate": 2.3972393477788157e-06,
|
| 2136 |
+
"loss": 1.1689,
|
| 2137 |
+
"step": 1515
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.7092860475968269,
|
| 2141 |
+
"grad_norm": 1.0104502129791082,
|
| 2142 |
+
"learning_rate": 2.362544143080835e-06,
|
| 2143 |
+
"loss": 1.1574,
|
| 2144 |
+
"step": 1520
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.7116192253849744,
|
| 2148 |
+
"grad_norm": 1.0120328767933888,
|
| 2149 |
+
"learning_rate": 2.328024007076952e-06,
|
| 2150 |
+
"loss": 1.1697,
|
| 2151 |
+
"step": 1525
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.7139524031731218,
|
| 2155 |
+
"grad_norm": 1.0052997117469944,
|
| 2156 |
+
"learning_rate": 2.2936812311401687e-06,
|
| 2157 |
+
"loss": 1.1815,
|
| 2158 |
+
"step": 1530
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 0.7162855809612693,
|
| 2162 |
+
"grad_norm": 1.0043182668642912,
|
| 2163 |
+
"learning_rate": 2.259518094870693e-06,
|
| 2164 |
+
"loss": 1.1759,
|
| 2165 |
+
"step": 1535
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.7186187587494167,
|
| 2169 |
+
"grad_norm": 0.9945694347808323,
|
| 2170 |
+
"learning_rate": 2.225536865944646e-06,
|
| 2171 |
+
"loss": 1.1667,
|
| 2172 |
+
"step": 1540
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 0.7209519365375642,
|
| 2176 |
+
"grad_norm": 1.0242529787658874,
|
| 2177 |
+
"learning_rate": 2.191739799963518e-06,
|
| 2178 |
+
"loss": 1.1628,
|
| 2179 |
+
"step": 1545
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.7232851143257116,
|
| 2183 |
+
"grad_norm": 1.0314454474479464,
|
| 2184 |
+
"learning_rate": 2.1581291403044634e-06,
|
| 2185 |
+
"loss": 1.1664,
|
| 2186 |
+
"step": 1550
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.7256182921138591,
|
| 2190 |
+
"grad_norm": 1.0626629907867327,
|
| 2191 |
+
"learning_rate": 2.1247071179713774e-06,
|
| 2192 |
+
"loss": 1.1559,
|
| 2193 |
+
"step": 1555
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.7279514699020065,
|
| 2197 |
+
"grad_norm": 1.0368896856506735,
|
| 2198 |
+
"learning_rate": 2.0914759514468106e-06,
|
| 2199 |
+
"loss": 1.154,
|
| 2200 |
+
"step": 1560
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 0.730284647690154,
|
| 2204 |
+
"grad_norm": 0.9698442188484383,
|
| 2205 |
+
"learning_rate": 2.0584378465447196e-06,
|
| 2206 |
+
"loss": 1.1733,
|
| 2207 |
+
"step": 1565
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.7326178254783015,
|
| 2211 |
+
"grad_norm": 1.0155332076663621,
|
| 2212 |
+
"learning_rate": 2.0255949962640335e-06,
|
| 2213 |
+
"loss": 1.1835,
|
| 2214 |
+
"step": 1570
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 0.7349510032664489,
|
| 2218 |
+
"grad_norm": 1.005548586828338,
|
| 2219 |
+
"learning_rate": 1.9929495806431024e-06,
|
| 2220 |
+
"loss": 1.1618,
|
| 2221 |
+
"step": 1575
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.7372841810545964,
|
| 2225 |
+
"grad_norm": 0.9954603864820935,
|
| 2226 |
+
"learning_rate": 1.9605037666149836e-06,
|
| 2227 |
+
"loss": 1.1581,
|
| 2228 |
+
"step": 1580
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 0.7396173588427438,
|
| 2232 |
+
"grad_norm": 0.9913998993751404,
|
| 2233 |
+
"learning_rate": 1.928259707863605e-06,
|
| 2234 |
+
"loss": 1.1623,
|
| 2235 |
+
"step": 1585
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.7419505366308913,
|
| 2239 |
+
"grad_norm": 0.9361603703191916,
|
| 2240 |
+
"learning_rate": 1.8962195446808086e-06,
|
| 2241 |
+
"loss": 1.1518,
|
| 2242 |
+
"step": 1590
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 0.7442837144190387,
|
| 2246 |
+
"grad_norm": 1.0014693385898898,
|
| 2247 |
+
"learning_rate": 1.864385403824287e-06,
|
| 2248 |
+
"loss": 1.1728,
|
| 2249 |
+
"step": 1595
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.7466168922071862,
|
| 2253 |
+
"grad_norm": 1.0210675029402585,
|
| 2254 |
+
"learning_rate": 1.8327593983764057e-06,
|
| 2255 |
+
"loss": 1.1556,
|
| 2256 |
+
"step": 1600
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 0.7489500699953336,
|
| 2260 |
+
"grad_norm": 1.0120342541176695,
|
| 2261 |
+
"learning_rate": 1.8013436276039514e-06,
|
| 2262 |
+
"loss": 1.161,
|
| 2263 |
+
"step": 1605
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.7512832477834811,
|
| 2267 |
+
"grad_norm": 0.9937379195757003,
|
| 2268 |
+
"learning_rate": 1.7701401768187743e-06,
|
| 2269 |
+
"loss": 1.1467,
|
| 2270 |
+
"step": 1610
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 0.7536164255716286,
|
| 2274 |
+
"grad_norm": 1.0709112087231152,
|
| 2275 |
+
"learning_rate": 1.7391511172393849e-06,
|
| 2276 |
+
"loss": 1.1563,
|
| 2277 |
+
"step": 1615
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.755949603359776,
|
| 2281 |
+
"grad_norm": 1.9013001176682678,
|
| 2282 |
+
"learning_rate": 1.708378505853457e-06,
|
| 2283 |
+
"loss": 1.1619,
|
| 2284 |
+
"step": 1620
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 0.7582827811479235,
|
| 2288 |
+
"grad_norm": 0.9717127760277121,
|
| 2289 |
+
"learning_rate": 1.6778243852812936e-06,
|
| 2290 |
+
"loss": 1.1714,
|
| 2291 |
+
"step": 1625
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.7606159589360709,
|
| 2295 |
+
"grad_norm": 0.993395064380433,
|
| 2296 |
+
"learning_rate": 1.6474907836402508e-06,
|
| 2297 |
+
"loss": 1.151,
|
| 2298 |
+
"step": 1630
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 0.7629491367242184,
|
| 2302 |
+
"grad_norm": 1.044875343861766,
|
| 2303 |
+
"learning_rate": 1.617379714410099e-06,
|
| 2304 |
+
"loss": 1.1765,
|
| 2305 |
+
"step": 1635
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.7652823145123658,
|
| 2309 |
+
"grad_norm": 0.9890249688622542,
|
| 2310 |
+
"learning_rate": 1.5874931762993934e-06,
|
| 2311 |
+
"loss": 1.1594,
|
| 2312 |
+
"step": 1640
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 0.7676154923005133,
|
| 2316 |
+
"grad_norm": 1.032867531902376,
|
| 2317 |
+
"learning_rate": 1.557833153112781e-06,
|
| 2318 |
+
"loss": 1.1618,
|
| 2319 |
+
"step": 1645
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.7699486700886607,
|
| 2323 |
+
"grad_norm": 1.022368485837898,
|
| 2324 |
+
"learning_rate": 1.5284016136193398e-06,
|
| 2325 |
+
"loss": 1.1515,
|
| 2326 |
+
"step": 1650
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 0.7722818478768082,
|
| 2330 |
+
"grad_norm": 0.9890950564022281,
|
| 2331 |
+
"learning_rate": 1.4992005114218805e-06,
|
| 2332 |
+
"loss": 1.1599,
|
| 2333 |
+
"step": 1655
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 0.7746150256649557,
|
| 2337 |
+
"grad_norm": 0.9854856037226626,
|
| 2338 |
+
"learning_rate": 1.470231784827284e-06,
|
| 2339 |
+
"loss": 1.1649,
|
| 2340 |
+
"step": 1660
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 0.7769482034531031,
|
| 2344 |
+
"grad_norm": 0.9729215886975489,
|
| 2345 |
+
"learning_rate": 1.4414973567178291e-06,
|
| 2346 |
+
"loss": 1.1618,
|
| 2347 |
+
"step": 1665
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 0.7792813812412506,
|
| 2351 |
+
"grad_norm": 1.0026486142505144,
|
| 2352 |
+
"learning_rate": 1.4129991344235655e-06,
|
| 2353 |
+
"loss": 1.1473,
|
| 2354 |
+
"step": 1670
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 0.781614559029398,
|
| 2358 |
+
"grad_norm": 1.0366250861374733,
|
| 2359 |
+
"learning_rate": 1.3847390095957003e-06,
|
| 2360 |
+
"loss": 1.1569,
|
| 2361 |
+
"step": 1675
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 0.7839477368175455,
|
| 2365 |
+
"grad_norm": 0.9938986816098982,
|
| 2366 |
+
"learning_rate": 1.3567188580810436e-06,
|
| 2367 |
+
"loss": 1.1536,
|
| 2368 |
+
"step": 1680
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 0.7862809146056929,
|
| 2372 |
+
"grad_norm": 1.0219505206702795,
|
| 2373 |
+
"learning_rate": 1.3289405397974842e-06,
|
| 2374 |
+
"loss": 1.1758,
|
| 2375 |
+
"step": 1685
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 0.7886140923938404,
|
| 2379 |
+
"grad_norm": 0.9890034372786042,
|
| 2380 |
+
"learning_rate": 1.3014058986105377e-06,
|
| 2381 |
+
"loss": 1.1544,
|
| 2382 |
+
"step": 1690
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 0.7909472701819878,
|
| 2386 |
+
"grad_norm": 1.0051626263000517,
|
| 2387 |
+
"learning_rate": 1.2741167622109557e-06,
|
| 2388 |
+
"loss": 1.1587,
|
| 2389 |
+
"step": 1695
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 0.7932804479701353,
|
| 2393 |
+
"grad_norm": 0.9785431846862271,
|
| 2394 |
+
"learning_rate": 1.2470749419934059e-06,
|
| 2395 |
+
"loss": 1.1695,
|
| 2396 |
+
"step": 1700
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 0.7956136257582828,
|
| 2400 |
+
"grad_norm": 1.0113931313333073,
|
| 2401 |
+
"learning_rate": 1.2202822329362345e-06,
|
| 2402 |
+
"loss": 1.1687,
|
| 2403 |
+
"step": 1705
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 0.7979468035464302,
|
| 2407 |
+
"grad_norm": 0.9842370692313657,
|
| 2408 |
+
"learning_rate": 1.1937404134823178e-06,
|
| 2409 |
+
"loss": 1.1615,
|
| 2410 |
+
"step": 1710
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 0.8002799813345777,
|
| 2414 |
+
"grad_norm": 1.0032465562671002,
|
| 2415 |
+
"learning_rate": 1.1674512454210202e-06,
|
| 2416 |
+
"loss": 1.1638,
|
| 2417 |
+
"step": 1715
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.8026131591227251,
|
| 2421 |
+
"grad_norm": 0.9750019313206011,
|
| 2422 |
+
"learning_rate": 1.1414164737712402e-06,
|
| 2423 |
+
"loss": 1.1327,
|
| 2424 |
+
"step": 1720
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 0.8049463369108726,
|
| 2428 |
+
"grad_norm": 0.9944410520677437,
|
| 2429 |
+
"learning_rate": 1.1156378266655904e-06,
|
| 2430 |
+
"loss": 1.1598,
|
| 2431 |
+
"step": 1725
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.80727951469902,
|
| 2435 |
+
"grad_norm": 0.956147368891967,
|
| 2436 |
+
"learning_rate": 1.0901170152356778e-06,
|
| 2437 |
+
"loss": 1.153,
|
| 2438 |
+
"step": 1730
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 0.8096126924871675,
|
| 2442 |
+
"grad_norm": 1.009266943435006,
|
| 2443 |
+
"learning_rate": 1.064855733498531e-06,
|
| 2444 |
+
"loss": 1.1605,
|
| 2445 |
+
"step": 1735
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 0.811945870275315,
|
| 2449 |
+
"grad_norm": 0.9858125902435397,
|
| 2450 |
+
"learning_rate": 1.0398556582441482e-06,
|
| 2451 |
+
"loss": 1.1291,
|
| 2452 |
+
"step": 1740
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 0.8142790480634624,
|
| 2456 |
+
"grad_norm": 1.0068331019756107,
|
| 2457 |
+
"learning_rate": 1.015118448924201e-06,
|
| 2458 |
+
"loss": 1.1779,
|
| 2459 |
+
"step": 1745
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 0.8166122258516099,
|
| 2463 |
+
"grad_norm": 1.0270194084422106,
|
| 2464 |
+
"learning_rate": 9.90645747541878e-07,
|
| 2465 |
+
"loss": 1.1514,
|
| 2466 |
+
"step": 1750
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 0.8189454036397573,
|
| 2470 |
+
"grad_norm": 0.9913211372941862,
|
| 2471 |
+
"learning_rate": 9.664391785428977e-07,
|
| 2472 |
+
"loss": 1.1726,
|
| 2473 |
+
"step": 1755
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 0.8212785814279048,
|
| 2477 |
+
"grad_norm": 1.0058927499098955,
|
| 2478 |
+
"learning_rate": 9.42500348707679e-07,
|
| 2479 |
+
"loss": 1.1724,
|
| 2480 |
+
"step": 1760
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 0.8236117592160522,
|
| 2484 |
+
"grad_norm": 1.0001313085991983,
|
| 2485 |
+
"learning_rate": 9.188308470446828e-07,
|
| 2486 |
+
"loss": 1.1401,
|
| 2487 |
+
"step": 1765
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 0.8259449370041997,
|
| 2491 |
+
"grad_norm": 0.9846329030889268,
|
| 2492 |
+
"learning_rate": 8.954322446849445e-07,
|
| 2493 |
+
"loss": 1.1572,
|
| 2494 |
+
"step": 1770
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 0.8282781147923471,
|
| 2498 |
+
"grad_norm": 1.0063720343872646,
|
| 2499 |
+
"learning_rate": 8.723060947777778e-07,
|
| 2500 |
+
"loss": 1.1711,
|
| 2501 |
+
"step": 1775
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 0.8306112925804946,
|
| 2505 |
+
"grad_norm": 0.9951396903238764,
|
| 2506 |
+
"learning_rate": 8.494539323876871e-07,
|
| 2507 |
+
"loss": 1.1592,
|
| 2508 |
+
"step": 1780
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 0.832944470368642,
|
| 2512 |
+
"grad_norm": 1.2632922939514373,
|
| 2513 |
+
"learning_rate": 8.268772743924669e-07,
|
| 2514 |
+
"loss": 1.1487,
|
| 2515 |
+
"step": 1785
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 0.8352776481567895,
|
| 2519 |
+
"grad_norm": 0.9820295659793887,
|
| 2520 |
+
"learning_rate": 8.045776193825205e-07,
|
| 2521 |
+
"loss": 1.1695,
|
| 2522 |
+
"step": 1790
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 0.837610825944937,
|
| 2526 |
+
"grad_norm": 1.0136705861025064,
|
| 2527 |
+
"learning_rate": 7.825564475613806e-07,
|
| 2528 |
+
"loss": 1.1749,
|
| 2529 |
+
"step": 1795
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 0.8399440037330844,
|
| 2533 |
+
"grad_norm": 1.3190123794807675,
|
| 2534 |
+
"learning_rate": 7.60815220647464e-07,
|
| 2535 |
+
"loss": 1.1522,
|
| 2536 |
+
"step": 1800
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 0.8422771815212319,
|
| 2540 |
+
"grad_norm": 1.0121978497804316,
|
| 2541 |
+
"learning_rate": 7.393553817770366e-07,
|
| 2542 |
+
"loss": 1.1548,
|
| 2543 |
+
"step": 1805
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 0.8446103593093793,
|
| 2547 |
+
"grad_norm": 1.0081857177545837,
|
| 2548 |
+
"learning_rate": 7.181783554084309e-07,
|
| 2549 |
+
"loss": 1.1662,
|
| 2550 |
+
"step": 1810
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 0.8469435370975268,
|
| 2554 |
+
"grad_norm": 0.9884812082696532,
|
| 2555 |
+
"learning_rate": 6.972855472274853e-07,
|
| 2556 |
+
"loss": 1.1586,
|
| 2557 |
+
"step": 1815
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 0.8492767148856742,
|
| 2561 |
+
"grad_norm": 1.0596164266865373,
|
| 2562 |
+
"learning_rate": 6.766783440542435e-07,
|
| 2563 |
+
"loss": 1.1598,
|
| 2564 |
+
"step": 1820
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 0.8516098926738217,
|
| 2568 |
+
"grad_norm": 0.9864623184262068,
|
| 2569 |
+
"learning_rate": 6.563581137508979e-07,
|
| 2570 |
+
"loss": 1.1618,
|
| 2571 |
+
"step": 1825
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 0.8539430704619692,
|
| 2575 |
+
"grad_norm": 0.9841399159800569,
|
| 2576 |
+
"learning_rate": 6.363262051309909e-07,
|
| 2577 |
+
"loss": 1.166,
|
| 2578 |
+
"step": 1830
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 0.8562762482501166,
|
| 2582 |
+
"grad_norm": 0.9995451256789106,
|
| 2583 |
+
"learning_rate": 6.165839478698909e-07,
|
| 2584 |
+
"loss": 1.1689,
|
| 2585 |
+
"step": 1835
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 0.8586094260382641,
|
| 2589 |
+
"grad_norm": 1.0013682575089107,
|
| 2590 |
+
"learning_rate": 5.971326524165228e-07,
|
| 2591 |
+
"loss": 1.1751,
|
| 2592 |
+
"step": 1840
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 0.8609426038264115,
|
| 2596 |
+
"grad_norm": 0.9830017970130511,
|
| 2597 |
+
"learning_rate": 5.77973609906391e-07,
|
| 2598 |
+
"loss": 1.1638,
|
| 2599 |
+
"step": 1845
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 0.863275781614559,
|
| 2603 |
+
"grad_norm": 0.9981206625537882,
|
| 2604 |
+
"learning_rate": 5.591080920758696e-07,
|
| 2605 |
+
"loss": 1.1612,
|
| 2606 |
+
"step": 1850
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 0.8656089594027064,
|
| 2610 |
+
"grad_norm": 0.9771135919710268,
|
| 2611 |
+
"learning_rate": 5.405373511777939e-07,
|
| 2612 |
+
"loss": 1.1532,
|
| 2613 |
+
"step": 1855
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 0.8679421371908539,
|
| 2617 |
+
"grad_norm": 0.9699898660770429,
|
| 2618 |
+
"learning_rate": 5.222626198983311e-07,
|
| 2619 |
+
"loss": 1.1542,
|
| 2620 |
+
"step": 1860
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 0.8702753149790013,
|
| 2624 |
+
"grad_norm": 0.9785528960722001,
|
| 2625 |
+
"learning_rate": 5.042851112751656e-07,
|
| 2626 |
+
"loss": 1.1421,
|
| 2627 |
+
"step": 1865
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 0.8726084927671488,
|
| 2631 |
+
"grad_norm": 0.9982971422441073,
|
| 2632 |
+
"learning_rate": 4.86606018616973e-07,
|
| 2633 |
+
"loss": 1.1604,
|
| 2634 |
+
"step": 1870
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 0.8749416705552963,
|
| 2638 |
+
"grad_norm": 0.9955398626550551,
|
| 2639 |
+
"learning_rate": 4.692265154242137e-07,
|
| 2640 |
+
"loss": 1.1564,
|
| 2641 |
+
"step": 1875
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 0.8772748483434438,
|
| 2645 |
+
"grad_norm": 0.9961630302537697,
|
| 2646 |
+
"learning_rate": 4.521477553112419e-07,
|
| 2647 |
+
"loss": 1.1506,
|
| 2648 |
+
"step": 1880
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 0.8796080261315913,
|
| 2652 |
+
"grad_norm": 1.9412087784453136,
|
| 2653 |
+
"learning_rate": 4.3537087192972226e-07,
|
| 2654 |
+
"loss": 1.1524,
|
| 2655 |
+
"step": 1885
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 0.8819412039197387,
|
| 2659 |
+
"grad_norm": 0.9659131243497191,
|
| 2660 |
+
"learning_rate": 4.1889697889338997e-07,
|
| 2661 |
+
"loss": 1.1426,
|
| 2662 |
+
"step": 1890
|
| 2663 |
+
},
|
| 2664 |
+
{
|
| 2665 |
+
"epoch": 0.8842743817078862,
|
| 2666 |
+
"grad_norm": 1.0054794831414513,
|
| 2667 |
+
"learning_rate": 4.0272716970412516e-07,
|
| 2668 |
+
"loss": 1.1643,
|
| 2669 |
+
"step": 1895
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 0.8866075594960336,
|
| 2673 |
+
"grad_norm": 2.2435692316015152,
|
| 2674 |
+
"learning_rate": 3.8686251767937335e-07,
|
| 2675 |
+
"loss": 1.1409,
|
| 2676 |
+
"step": 1900
|
| 2677 |
+
},
|
| 2678 |
+
{
|
| 2679 |
+
"epoch": 0.8889407372841811,
|
| 2680 |
+
"grad_norm": 0.975599574657007,
|
| 2681 |
+
"learning_rate": 3.713040758808945e-07,
|
| 2682 |
+
"loss": 1.1675,
|
| 2683 |
+
"step": 1905
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 0.8912739150723286,
|
| 2687 |
+
"grad_norm": 1.0081779298483409,
|
| 2688 |
+
"learning_rate": 3.560528770448712e-07,
|
| 2689 |
+
"loss": 1.1706,
|
| 2690 |
+
"step": 1910
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 0.893607092860476,
|
| 2694 |
+
"grad_norm": 1.0302265982184113,
|
| 2695 |
+
"learning_rate": 3.4110993351334944e-07,
|
| 2696 |
+
"loss": 1.1774,
|
| 2697 |
+
"step": 1915
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 0.8959402706486235,
|
| 2701 |
+
"grad_norm": 1.0236714374782956,
|
| 2702 |
+
"learning_rate": 3.2647623716704935e-07,
|
| 2703 |
+
"loss": 1.1758,
|
| 2704 |
+
"step": 1920
|
| 2705 |
+
},
|
| 2706 |
+
{
|
| 2707 |
+
"epoch": 0.8982734484367709,
|
| 2708 |
+
"grad_norm": 1.002618038580871,
|
| 2709 |
+
"learning_rate": 3.1215275935951917e-07,
|
| 2710 |
+
"loss": 1.163,
|
| 2711 |
+
"step": 1925
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 0.9006066262249184,
|
| 2715 |
+
"grad_norm": 0.9913857413056198,
|
| 2716 |
+
"learning_rate": 2.981404508526653e-07,
|
| 2717 |
+
"loss": 1.1557,
|
| 2718 |
+
"step": 1930
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 0.9029398040130658,
|
| 2722 |
+
"grad_norm": 0.9804197100619393,
|
| 2723 |
+
"learning_rate": 2.844402417536374e-07,
|
| 2724 |
+
"loss": 1.1328,
|
| 2725 |
+
"step": 1935
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 0.9052729818012133,
|
| 2729 |
+
"grad_norm": 0.979529365433251,
|
| 2730 |
+
"learning_rate": 2.7105304145309317e-07,
|
| 2731 |
+
"loss": 1.1588,
|
| 2732 |
+
"step": 1940
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 0.9076061595893608,
|
| 2736 |
+
"grad_norm": 1.0031066535474602,
|
| 2737 |
+
"learning_rate": 2.5797973856483417e-07,
|
| 2738 |
+
"loss": 1.1741,
|
| 2739 |
+
"step": 1945
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 0.9099393373775082,
|
| 2743 |
+
"grad_norm": 0.9598452778844618,
|
| 2744 |
+
"learning_rate": 2.452212008668198e-07,
|
| 2745 |
+
"loss": 1.1528,
|
| 2746 |
+
"step": 1950
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 0.9122725151656557,
|
| 2750 |
+
"grad_norm": 0.9818674018055525,
|
| 2751 |
+
"learning_rate": 2.3277827524356976e-07,
|
| 2752 |
+
"loss": 1.1353,
|
| 2753 |
+
"step": 1955
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 0.9146056929538031,
|
| 2757 |
+
"grad_norm": 0.9772553061089622,
|
| 2758 |
+
"learning_rate": 2.206517876299452e-07,
|
| 2759 |
+
"loss": 1.1353,
|
| 2760 |
+
"step": 1960
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 0.9169388707419506,
|
| 2764 |
+
"grad_norm": 1.7683487182064883,
|
| 2765 |
+
"learning_rate": 2.0884254295632954e-07,
|
| 2766 |
+
"loss": 1.1695,
|
| 2767 |
+
"step": 1965
|
| 2768 |
+
},
|
| 2769 |
+
{
|
| 2770 |
+
"epoch": 0.919272048530098,
|
| 2771 |
+
"grad_norm": 0.9830006540104176,
|
| 2772 |
+
"learning_rate": 1.9735132509519305e-07,
|
| 2773 |
+
"loss": 1.1516,
|
| 2774 |
+
"step": 1970
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 0.9216052263182455,
|
| 2778 |
+
"grad_norm": 0.9800427923143794,
|
| 2779 |
+
"learning_rate": 1.861788968090683e-07,
|
| 2780 |
+
"loss": 1.1425,
|
| 2781 |
+
"step": 1975
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 0.9239384041063929,
|
| 2785 |
+
"grad_norm": 1.0365510364196127,
|
| 2786 |
+
"learning_rate": 1.7532599969991348e-07,
|
| 2787 |
+
"loss": 1.1598,
|
| 2788 |
+
"step": 1980
|
| 2789 |
+
},
|
| 2790 |
+
{
|
| 2791 |
+
"epoch": 0.9262715818945404,
|
| 2792 |
+
"grad_norm": 0.9919774295532647,
|
| 2793 |
+
"learning_rate": 1.6479335415989007e-07,
|
| 2794 |
+
"loss": 1.1543,
|
| 2795 |
+
"step": 1985
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 0.9286047596826879,
|
| 2799 |
+
"grad_norm": 0.9766973093741765,
|
| 2800 |
+
"learning_rate": 1.5458165932354163e-07,
|
| 2801 |
+
"loss": 1.1647,
|
| 2802 |
+
"step": 1990
|
| 2803 |
+
},
|
| 2804 |
+
{
|
| 2805 |
+
"epoch": 0.9309379374708353,
|
| 2806 |
+
"grad_norm": 0.9868485378239865,
|
| 2807 |
+
"learning_rate": 1.4469159302139157e-07,
|
| 2808 |
+
"loss": 1.1417,
|
| 2809 |
+
"step": 1995
|
| 2810 |
+
},
|
| 2811 |
+
{
|
| 2812 |
+
"epoch": 0.9332711152589828,
|
| 2813 |
+
"grad_norm": 0.9855408237895734,
|
| 2814 |
+
"learning_rate": 1.351238117349446e-07,
|
| 2815 |
+
"loss": 1.1517,
|
| 2816 |
+
"step": 2000
|
| 2817 |
+
},
|
| 2818 |
+
{
|
| 2819 |
+
"epoch": 0.9356042930471302,
|
| 2820 |
+
"grad_norm": 1.3352309241558546,
|
| 2821 |
+
"learning_rate": 1.2587895055311494e-07,
|
| 2822 |
+
"loss": 1.1644,
|
| 2823 |
+
"step": 2005
|
| 2824 |
+
},
|
| 2825 |
+
{
|
| 2826 |
+
"epoch": 0.9379374708352777,
|
| 2827 |
+
"grad_norm": 0.9862069849547848,
|
| 2828 |
+
"learning_rate": 1.1695762313006842e-07,
|
| 2829 |
+
"loss": 1.1569,
|
| 2830 |
+
"step": 2010
|
| 2831 |
+
},
|
| 2832 |
+
{
|
| 2833 |
+
"epoch": 0.9402706486234251,
|
| 2834 |
+
"grad_norm": 1.2953103633672411,
|
| 2835 |
+
"learning_rate": 1.0836042164448945e-07,
|
| 2836 |
+
"loss": 1.1472,
|
| 2837 |
+
"step": 2015
|
| 2838 |
+
},
|
| 2839 |
+
{
|
| 2840 |
+
"epoch": 0.9426038264115726,
|
| 2841 |
+
"grad_norm": 0.9878175845860757,
|
| 2842 |
+
"learning_rate": 1.0008791676027641e-07,
|
| 2843 |
+
"loss": 1.1548,
|
| 2844 |
+
"step": 2020
|
| 2845 |
+
},
|
| 2846 |
+
{
|
| 2847 |
+
"epoch": 0.94493700419972,
|
| 2848 |
+
"grad_norm": 1.010885190462538,
|
| 2849 |
+
"learning_rate": 9.214065758865687e-08,
|
| 2850 |
+
"loss": 1.1691,
|
| 2851 |
+
"step": 2025
|
| 2852 |
+
},
|
| 2853 |
+
{
|
| 2854 |
+
"epoch": 0.9472701819878675,
|
| 2855 |
+
"grad_norm": 1.0064738316551112,
|
| 2856 |
+
"learning_rate": 8.451917165174406e-08,
|
| 2857 |
+
"loss": 1.1553,
|
| 2858 |
+
"step": 2030
|
| 2859 |
+
},
|
| 2860 |
+
{
|
| 2861 |
+
"epoch": 0.949603359776015,
|
| 2862 |
+
"grad_norm": 1.0133963030142776,
|
| 2863 |
+
"learning_rate": 7.722396484751705e-08,
|
| 2864 |
+
"loss": 1.1316,
|
| 2865 |
+
"step": 2035
|
| 2866 |
+
},
|
| 2867 |
+
{
|
| 2868 |
+
"epoch": 0.9519365375641624,
|
| 2869 |
+
"grad_norm": 0.9940590775854898,
|
| 2870 |
+
"learning_rate": 7.02555214162437e-08,
|
| 2871 |
+
"loss": 1.1627,
|
| 2872 |
+
"step": 2040
|
| 2873 |
+
},
|
| 2874 |
+
{
|
| 2875 |
+
"epoch": 0.9542697153523099,
|
| 2876 |
+
"grad_norm": 1.0167056416961604,
|
| 2877 |
+
"learning_rate": 6.361430390833479e-08,
|
| 2878 |
+
"loss": 1.168,
|
| 2879 |
+
"step": 2045
|
| 2880 |
+
},
|
| 2881 |
+
{
|
| 2882 |
+
"epoch": 0.9566028931404573,
|
| 2883 |
+
"grad_norm": 0.9836310384519065,
|
| 2884 |
+
"learning_rate": 5.7300753153643474e-08,
|
| 2885 |
+
"loss": 1.1598,
|
| 2886 |
+
"step": 2050
|
| 2887 |
+
},
|
| 2888 |
+
{
|
| 2889 |
+
"epoch": 0.9589360709286048,
|
| 2890 |
+
"grad_norm": 1.92459846263964,
|
| 2891 |
+
"learning_rate": 5.1315288232201e-08,
|
| 2892 |
+
"loss": 1.1521,
|
| 2893 |
+
"step": 2055
|
| 2894 |
+
},
|
| 2895 |
+
{
|
| 2896 |
+
"epoch": 0.9612692487167522,
|
| 2897 |
+
"grad_norm": 0.9796387717857206,
|
| 2898 |
+
"learning_rate": 4.5658306446402234e-08,
|
| 2899 |
+
"loss": 1.1525,
|
| 2900 |
+
"step": 2060
|
| 2901 |
+
},
|
| 2902 |
+
{
|
| 2903 |
+
"epoch": 0.9636024265048997,
|
| 2904 |
+
"grad_norm": 0.9845259162114289,
|
| 2905 |
+
"learning_rate": 4.033018329463289e-08,
|
| 2906 |
+
"loss": 1.1696,
|
| 2907 |
+
"step": 2065
|
| 2908 |
+
},
|
| 2909 |
+
{
|
| 2910 |
+
"epoch": 0.9659356042930471,
|
| 2911 |
+
"grad_norm": 0.9916548397519503,
|
| 2912 |
+
"learning_rate": 3.5331272446341717e-08,
|
| 2913 |
+
"loss": 1.1501,
|
| 2914 |
+
"step": 2070
|
| 2915 |
+
},
|
| 2916 |
+
{
|
| 2917 |
+
"epoch": 0.9682687820811946,
|
| 2918 |
+
"grad_norm": 1.000735051429408,
|
| 2919 |
+
"learning_rate": 3.066190571856864e-08,
|
| 2920 |
+
"loss": 1.1534,
|
| 2921 |
+
"step": 2075
|
| 2922 |
+
},
|
| 2923 |
+
{
|
| 2924 |
+
"epoch": 0.9706019598693421,
|
| 2925 |
+
"grad_norm": 5.38784324543692,
|
| 2926 |
+
"learning_rate": 2.6322393053916928e-08,
|
| 2927 |
+
"loss": 1.1408,
|
| 2928 |
+
"step": 2080
|
| 2929 |
+
},
|
| 2930 |
+
{
|
| 2931 |
+
"epoch": 0.9729351376574895,
|
| 2932 |
+
"grad_norm": 1.0081839281875051,
|
| 2933 |
+
"learning_rate": 2.231302249998124e-08,
|
| 2934 |
+
"loss": 1.164,
|
| 2935 |
+
"step": 2085
|
| 2936 |
+
},
|
| 2937 |
+
{
|
| 2938 |
+
"epoch": 0.975268315445637,
|
| 2939 |
+
"grad_norm": 0.9710613753352443,
|
| 2940 |
+
"learning_rate": 1.86340601902274e-08,
|
| 2941 |
+
"loss": 1.1543,
|
| 2942 |
+
"step": 2090
|
| 2943 |
+
},
|
| 2944 |
+
{
|
| 2945 |
+
"epoch": 0.9776014932337844,
|
| 2946 |
+
"grad_norm": 0.9946172418863637,
|
| 2947 |
+
"learning_rate": 1.5285750326325953e-08,
|
| 2948 |
+
"loss": 1.1604,
|
| 2949 |
+
"step": 2095
|
| 2950 |
+
},
|
| 2951 |
+
{
|
| 2952 |
+
"epoch": 0.9799346710219319,
|
| 2953 |
+
"grad_norm": 0.9894502702163277,
|
| 2954 |
+
"learning_rate": 1.2268315161944044e-08,
|
| 2955 |
+
"loss": 1.1547,
|
| 2956 |
+
"step": 2100
|
| 2957 |
+
},
|
| 2958 |
+
{
|
| 2959 |
+
"epoch": 0.9822678488100793,
|
| 2960 |
+
"grad_norm": 1.0249944772363728,
|
| 2961 |
+
"learning_rate": 9.581954987991083e-09,
|
| 2962 |
+
"loss": 1.1657,
|
| 2963 |
+
"step": 2105
|
| 2964 |
+
},
|
| 2965 |
+
{
|
| 2966 |
+
"epoch": 0.9846010265982268,
|
| 2967 |
+
"grad_norm": 0.9878502233618688,
|
| 2968 |
+
"learning_rate": 7.226848119326058e-09,
|
| 2969 |
+
"loss": 1.1642,
|
| 2970 |
+
"step": 2110
|
| 2971 |
+
},
|
| 2972 |
+
{
|
| 2973 |
+
"epoch": 0.9869342043863742,
|
| 2974 |
+
"grad_norm": 0.9882911634354341,
|
| 2975 |
+
"learning_rate": 5.203150882918673e-09,
|
| 2976 |
+
"loss": 1.1382,
|
| 2977 |
+
"step": 2115
|
| 2978 |
+
},
|
| 2979 |
+
{
|
| 2980 |
+
"epoch": 0.9892673821745217,
|
| 2981 |
+
"grad_norm": 1.0074220012013155,
|
| 2982 |
+
"learning_rate": 3.5109976074759745e-09,
|
| 2983 |
+
"loss": 1.1578,
|
| 2984 |
+
"step": 2120
|
| 2985 |
+
},
|
| 2986 |
+
{
|
| 2987 |
+
"epoch": 0.9916005599626692,
|
| 2988 |
+
"grad_norm": 0.981600169075199,
|
| 2989 |
+
"learning_rate": 2.1505006145222663e-09,
|
| 2990 |
+
"loss": 1.163,
|
| 2991 |
+
"step": 2125
|
| 2992 |
+
},
|
| 2993 |
+
{
|
| 2994 |
+
"epoch": 0.9939337377508166,
|
| 2995 |
+
"grad_norm": 1.0352562521548165,
|
| 2996 |
+
"learning_rate": 1.121750210946737e-09,
|
| 2997 |
+
"loss": 1.1739,
|
| 2998 |
+
"step": 2130
|
| 2999 |
+
},
|
| 3000 |
+
{
|
| 3001 |
+
"epoch": 0.9962669155389641,
|
| 3002 |
+
"grad_norm": 0.9805349365623601,
|
| 3003 |
+
"learning_rate": 4.2481468300603625e-10,
|
| 3004 |
+
"loss": 1.1601,
|
| 3005 |
+
"step": 2135
|
| 3006 |
+
},
|
| 3007 |
+
{
|
| 3008 |
+
"epoch": 0.9986000933271115,
|
| 3009 |
+
"grad_norm": 1.0014288495338382,
|
| 3010 |
+
"learning_rate": 5.974029179456332e-11,
|
| 3011 |
+
"loss": 1.1526,
|
| 3012 |
+
"step": 2140
|
| 3013 |
+
},
|
| 3014 |
+
{
|
| 3015 |
+
"epoch": 1.0,
|
| 3016 |
+
"eval_runtime": 0.8954,
|
| 3017 |
+
"eval_samples_per_second": 11.168,
|
| 3018 |
+
"eval_steps_per_second": 3.351,
|
| 3019 |
+
"step": 2143
|
| 3020 |
+
},
|
| 3021 |
+
{
|
| 3022 |
+
"epoch": 1.0,
|
| 3023 |
+
"step": 2143,
|
| 3024 |
+
"total_flos": 104409178570752.0,
|
| 3025 |
+
"train_loss": 1.2488443794731108,
|
| 3026 |
+
"train_runtime": 1971.1476,
|
| 3027 |
+
"train_samples_per_second": 17.39,
|
| 3028 |
+
"train_steps_per_second": 1.087
|
| 3029 |
+
}
|
| 3030 |
+
],
|
| 3031 |
+
"logging_steps": 5,
|
| 3032 |
+
"max_steps": 2143,
|
| 3033 |
+
"num_input_tokens_seen": 0,
|
| 3034 |
+
"num_train_epochs": 1,
|
| 3035 |
+
"save_steps": 100,
|
| 3036 |
+
"stateful_callbacks": {
|
| 3037 |
+
"TrainerControl": {
|
| 3038 |
+
"args": {
|
| 3039 |
+
"should_epoch_stop": false,
|
| 3040 |
+
"should_evaluate": false,
|
| 3041 |
+
"should_log": false,
|
| 3042 |
+
"should_save": true,
|
| 3043 |
+
"should_training_stop": true
|
| 3044 |
+
},
|
| 3045 |
+
"attributes": {}
|
| 3046 |
+
}
|
| 3047 |
+
},
|
| 3048 |
+
"total_flos": 104409178570752.0,
|
| 3049 |
+
"train_batch_size": 4,
|
| 3050 |
+
"trial_name": null,
|
| 3051 |
+
"trial_params": null
|
| 3052 |
+
}
|