Model save
Browse files- README.md +69 -0
- adapter_model.safetensors +1 -1
- all_results.json +9 -0
- runs/Sep29_07-53-20_82b7fdadb1f8/events.out.tfevents.1727596692.82b7fdadb1f8.481917.0 +2 -2
- train_results.json +9 -0
- trainer_state.json +953 -0
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: mistralai/Mistral-7B-v0.3
|
| 3 |
+
datasets:
|
| 4 |
+
- generator
|
| 5 |
+
library_name: peft
|
| 6 |
+
license: apache-2.0
|
| 7 |
+
tags:
|
| 8 |
+
- trl
|
| 9 |
+
- sft
|
| 10 |
+
- generated_from_trainer
|
| 11 |
+
model-index:
|
| 12 |
+
- name: mistral-7b-0.3-gpt4o_100k_coding-k
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# mistral-7b-0.3-gpt4o_100k_coding-k
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the generator dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 1.0798
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 0.0002
|
| 43 |
+
- train_batch_size: 2
|
| 44 |
+
- eval_batch_size: 2
|
| 45 |
+
- seed: 42
|
| 46 |
+
- distributed_type: multi-GPU
|
| 47 |
+
- num_devices: 8
|
| 48 |
+
- gradient_accumulation_steps: 2
|
| 49 |
+
- total_train_batch_size: 32
|
| 50 |
+
- total_eval_batch_size: 16
|
| 51 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 52 |
+
- lr_scheduler_type: cosine
|
| 53 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 54 |
+
- num_epochs: 1
|
| 55 |
+
|
| 56 |
+
### Training results
|
| 57 |
+
|
| 58 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 59 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 60 |
+
| 0.438 | 0.9992 | 640 | 1.0798 |
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
### Framework versions
|
| 64 |
+
|
| 65 |
+
- PEFT 0.13.1.dev0
|
| 66 |
+
- Transformers 4.45.1
|
| 67 |
+
- Pytorch 2.4.1+cu121
|
| 68 |
+
- Datasets 3.0.1
|
| 69 |
+
- Tokenizers 0.20.0
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1087481480
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7cbaf3ef2bcfe31401c182749275e3c6f06a1e76a4249b5babf570f65f50cb2
|
| 3 |
size 1087481480
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9992193598750976,
|
| 3 |
+
"total_flos": 8.955542824078541e+17,
|
| 4 |
+
"train_loss": 0.4838556606322527,
|
| 5 |
+
"train_runtime": 4573.5964,
|
| 6 |
+
"train_samples": 116368,
|
| 7 |
+
"train_samples_per_second": 4.48,
|
| 8 |
+
"train_steps_per_second": 0.14
|
| 9 |
+
}
|
runs/Sep29_07-53-20_82b7fdadb1f8/events.out.tfevents.1727596692.82b7fdadb1f8.481917.0
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 sha256:1bbb4b68e29d90892d9d3acb73212fd5a8771d6ca91c8d080c089b71777ee8dc
|
| 3 |
+
size 33737
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9992193598750976,
|
| 3 |
+
"total_flos": 8.955542824078541e+17,
|
| 4 |
+
"train_loss": 0.4838556606322527,
|
| 5 |
+
"train_runtime": 4573.5964,
|
| 6 |
+
"train_samples": 116368,
|
| 7 |
+
"train_samples_per_second": 4.48,
|
| 8 |
+
"train_steps_per_second": 0.14
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,953 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9992193598750976,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 640,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.00156128024980484,
|
| 13 |
+
"grad_norm": 4.341845512390137,
|
| 14 |
+
"learning_rate": 3.125e-06,
|
| 15 |
+
"loss": 1.3019,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0078064012490242,
|
| 20 |
+
"grad_norm": 4.292470455169678,
|
| 21 |
+
"learning_rate": 1.5625e-05,
|
| 22 |
+
"loss": 1.2557,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0156128024980484,
|
| 27 |
+
"grad_norm": 3.9200799465179443,
|
| 28 |
+
"learning_rate": 3.125e-05,
|
| 29 |
+
"loss": 1.1486,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0234192037470726,
|
| 34 |
+
"grad_norm": 3.1646339893341064,
|
| 35 |
+
"learning_rate": 4.6875e-05,
|
| 36 |
+
"loss": 0.9901,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.0312256049960968,
|
| 41 |
+
"grad_norm": 1.539257526397705,
|
| 42 |
+
"learning_rate": 6.25e-05,
|
| 43 |
+
"loss": 0.8708,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.039032006245121,
|
| 48 |
+
"grad_norm": 0.8220561742782593,
|
| 49 |
+
"learning_rate": 7.8125e-05,
|
| 50 |
+
"loss": 0.7545,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.0468384074941452,
|
| 55 |
+
"grad_norm": 0.6788249015808105,
|
| 56 |
+
"learning_rate": 9.375e-05,
|
| 57 |
+
"loss": 0.6926,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.0546448087431694,
|
| 62 |
+
"grad_norm": 0.8923994302749634,
|
| 63 |
+
"learning_rate": 0.000109375,
|
| 64 |
+
"loss": 0.6369,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.0624512099921936,
|
| 69 |
+
"grad_norm": 0.9089710712432861,
|
| 70 |
+
"learning_rate": 0.000125,
|
| 71 |
+
"loss": 0.614,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.0702576112412178,
|
| 76 |
+
"grad_norm": 0.9337915778160095,
|
| 77 |
+
"learning_rate": 0.00014062500000000002,
|
| 78 |
+
"loss": 0.5766,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.078064012490242,
|
| 83 |
+
"grad_norm": 0.7455429434776306,
|
| 84 |
+
"learning_rate": 0.00015625,
|
| 85 |
+
"loss": 0.5516,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.0858704137392662,
|
| 90 |
+
"grad_norm": 0.49435052275657654,
|
| 91 |
+
"learning_rate": 0.00017187500000000002,
|
| 92 |
+
"loss": 0.536,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.0936768149882904,
|
| 97 |
+
"grad_norm": 0.9767287969589233,
|
| 98 |
+
"learning_rate": 0.0001875,
|
| 99 |
+
"loss": 0.5417,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.1014832162373146,
|
| 104 |
+
"grad_norm": 0.8675209879875183,
|
| 105 |
+
"learning_rate": 0.00019999851261394218,
|
| 106 |
+
"loss": 0.5344,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.1092896174863388,
|
| 111 |
+
"grad_norm": 0.6101036667823792,
|
| 112 |
+
"learning_rate": 0.00019994645874763658,
|
| 113 |
+
"loss": 0.5209,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.117096018735363,
|
| 118 |
+
"grad_norm": 0.4980247914791107,
|
| 119 |
+
"learning_rate": 0.00019982007981886847,
|
| 120 |
+
"loss": 0.5043,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.1249024199843872,
|
| 125 |
+
"grad_norm": 0.34284278750419617,
|
| 126 |
+
"learning_rate": 0.00019961946980917456,
|
| 127 |
+
"loss": 0.5064,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.1327088212334114,
|
| 132 |
+
"grad_norm": 0.3613043427467346,
|
| 133 |
+
"learning_rate": 0.00019934477790194445,
|
| 134 |
+
"loss": 0.496,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.1405152224824356,
|
| 139 |
+
"grad_norm": 0.40784284472465515,
|
| 140 |
+
"learning_rate": 0.00019899620837148077,
|
| 141 |
+
"loss": 0.4996,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.1483216237314598,
|
| 146 |
+
"grad_norm": 0.3546779453754425,
|
| 147 |
+
"learning_rate": 0.0001985740204310909,
|
| 148 |
+
"loss": 0.4969,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.156128024980484,
|
| 153 |
+
"grad_norm": 0.35221970081329346,
|
| 154 |
+
"learning_rate": 0.00019807852804032305,
|
| 155 |
+
"loss": 0.5014,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.16393442622950818,
|
| 160 |
+
"grad_norm": 0.45173051953315735,
|
| 161 |
+
"learning_rate": 0.00019751009967149087,
|
| 162 |
+
"loss": 0.4895,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.1717408274785324,
|
| 167 |
+
"grad_norm": 0.3956238329410553,
|
| 168 |
+
"learning_rate": 0.00019686915803565934,
|
| 169 |
+
"loss": 0.4877,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.1795472287275566,
|
| 174 |
+
"grad_norm": 0.3475348949432373,
|
| 175 |
+
"learning_rate": 0.0001961561797682962,
|
| 176 |
+
"loss": 0.4746,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.1873536299765808,
|
| 181 |
+
"grad_norm": 0.36577436327934265,
|
| 182 |
+
"learning_rate": 0.0001953716950748227,
|
| 183 |
+
"loss": 0.4888,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.195160031225605,
|
| 188 |
+
"grad_norm": 0.3727911412715912,
|
| 189 |
+
"learning_rate": 0.0001945162873363268,
|
| 190 |
+
"loss": 0.4785,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.2029664324746292,
|
| 195 |
+
"grad_norm": 0.3759865462779999,
|
| 196 |
+
"learning_rate": 0.0001935905926757326,
|
| 197 |
+
"loss": 0.4798,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.2107728337236534,
|
| 202 |
+
"grad_norm": 0.40641459822654724,
|
| 203 |
+
"learning_rate": 0.00019259529948474833,
|
| 204 |
+
"loss": 0.4795,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.2185792349726776,
|
| 209 |
+
"grad_norm": 0.3547082543373108,
|
| 210 |
+
"learning_rate": 0.00019153114791194473,
|
| 211 |
+
"loss": 0.4809,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.2263856362217018,
|
| 216 |
+
"grad_norm": 0.3588828146457672,
|
| 217 |
+
"learning_rate": 0.00019039892931234435,
|
| 218 |
+
"loss": 0.4933,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.234192037470726,
|
| 223 |
+
"grad_norm": 0.4158973693847656,
|
| 224 |
+
"learning_rate": 0.00018919948565893142,
|
| 225 |
+
"loss": 0.4746,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.2419984387197502,
|
| 230 |
+
"grad_norm": 0.5559388399124146,
|
| 231 |
+
"learning_rate": 0.00018793370891651972,
|
| 232 |
+
"loss": 0.4791,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.2498048399687744,
|
| 237 |
+
"grad_norm": 0.3747630715370178,
|
| 238 |
+
"learning_rate": 0.00018660254037844388,
|
| 239 |
+
"loss": 0.4864,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.2576112412177986,
|
| 244 |
+
"grad_norm": 0.4632702171802521,
|
| 245 |
+
"learning_rate": 0.00018520696996656788,
|
| 246 |
+
"loss": 0.4658,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.2654176424668228,
|
| 251 |
+
"grad_norm": 0.5524964332580566,
|
| 252 |
+
"learning_rate": 0.0001837480354951308,
|
| 253 |
+
"loss": 0.4561,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.273224043715847,
|
| 258 |
+
"grad_norm": 0.4398689866065979,
|
| 259 |
+
"learning_rate": 0.00018222682189897752,
|
| 260 |
+
"loss": 0.4633,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.2810304449648712,
|
| 265 |
+
"grad_norm": 0.3512100577354431,
|
| 266 |
+
"learning_rate": 0.00018064446042674828,
|
| 267 |
+
"loss": 0.4641,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.2888368462138954,
|
| 272 |
+
"grad_norm": 0.414985716342926,
|
| 273 |
+
"learning_rate": 0.0001790021277996269,
|
| 274 |
+
"loss": 0.4664,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.2966432474629196,
|
| 279 |
+
"grad_norm": 0.3512822687625885,
|
| 280 |
+
"learning_rate": 0.0001773010453362737,
|
| 281 |
+
"loss": 0.4753,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.3044496487119438,
|
| 286 |
+
"grad_norm": 0.3715687692165375,
|
| 287 |
+
"learning_rate": 0.00017554247804459316,
|
| 288 |
+
"loss": 0.4667,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.312256049960968,
|
| 293 |
+
"grad_norm": 0.4506210684776306,
|
| 294 |
+
"learning_rate": 0.0001737277336810124,
|
| 295 |
+
"loss": 0.4694,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.3200624512099922,
|
| 300 |
+
"grad_norm": 0.36245930194854736,
|
| 301 |
+
"learning_rate": 0.0001718581617779698,
|
| 302 |
+
"loss": 0.4634,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.32786885245901637,
|
| 307 |
+
"grad_norm": 0.37324413657188416,
|
| 308 |
+
"learning_rate": 0.00016993515264033672,
|
| 309 |
+
"loss": 0.4739,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.3356752537080406,
|
| 314 |
+
"grad_norm": 0.3662189841270447,
|
| 315 |
+
"learning_rate": 0.00016796013631151897,
|
| 316 |
+
"loss": 0.4548,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.3434816549570648,
|
| 321 |
+
"grad_norm": 0.3321515917778015,
|
| 322 |
+
"learning_rate": 0.00016593458151000688,
|
| 323 |
+
"loss": 0.4533,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.351288056206089,
|
| 328 |
+
"grad_norm": 0.32358649373054504,
|
| 329 |
+
"learning_rate": 0.00016385999453716454,
|
| 330 |
+
"loss": 0.448,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.3590944574551132,
|
| 335 |
+
"grad_norm": 0.41246530413627625,
|
| 336 |
+
"learning_rate": 0.00016173791815707051,
|
| 337 |
+
"loss": 0.46,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.3669008587041374,
|
| 342 |
+
"grad_norm": 0.3504014313220978,
|
| 343 |
+
"learning_rate": 0.00015956993044924334,
|
| 344 |
+
"loss": 0.4524,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.3747072599531616,
|
| 349 |
+
"grad_norm": 0.6306522488594055,
|
| 350 |
+
"learning_rate": 0.0001573576436351046,
|
| 351 |
+
"loss": 0.4649,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.3825136612021858,
|
| 356 |
+
"grad_norm": 0.3309260308742523,
|
| 357 |
+
"learning_rate": 0.0001551027028790524,
|
| 358 |
+
"loss": 0.452,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.39032006245121,
|
| 363 |
+
"grad_norm": 0.3508729338645935,
|
| 364 |
+
"learning_rate": 0.0001528067850650368,
|
| 365 |
+
"loss": 0.4631,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.3981264637002342,
|
| 370 |
+
"grad_norm": 0.3504168391227722,
|
| 371 |
+
"learning_rate": 0.0001504715975495472,
|
| 372 |
+
"loss": 0.4553,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.4059328649492584,
|
| 377 |
+
"grad_norm": 0.3634853959083557,
|
| 378 |
+
"learning_rate": 0.00014809887689193877,
|
| 379 |
+
"loss": 0.4488,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.4137392661982826,
|
| 384 |
+
"grad_norm": 0.3699380159378052,
|
| 385 |
+
"learning_rate": 0.00014569038756304207,
|
| 386 |
+
"loss": 0.4681,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.4215456674473068,
|
| 391 |
+
"grad_norm": 0.3571968376636505,
|
| 392 |
+
"learning_rate": 0.00014324792063301662,
|
| 393 |
+
"loss": 0.4508,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.42935206869633097,
|
| 398 |
+
"grad_norm": 0.37507084012031555,
|
| 399 |
+
"learning_rate": 0.00014077329243942369,
|
| 400 |
+
"loss": 0.4542,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.4371584699453552,
|
| 405 |
+
"grad_norm": 0.3596557378768921,
|
| 406 |
+
"learning_rate": 0.000138268343236509,
|
| 407 |
+
"loss": 0.4542,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.4449648711943794,
|
| 412 |
+
"grad_norm": 0.3457932472229004,
|
| 413 |
+
"learning_rate": 0.00013573493582670003,
|
| 414 |
+
"loss": 0.4476,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.4527712724434036,
|
| 419 |
+
"grad_norm": 0.4396996796131134,
|
| 420 |
+
"learning_rate": 0.00013317495417533524,
|
| 421 |
+
"loss": 0.4538,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.4605776736924278,
|
| 426 |
+
"grad_norm": 0.3878016173839569,
|
| 427 |
+
"learning_rate": 0.00013059030200965536,
|
| 428 |
+
"loss": 0.4432,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.468384074941452,
|
| 433 |
+
"grad_norm": 0.38895392417907715,
|
| 434 |
+
"learning_rate": 0.00012798290140309923,
|
| 435 |
+
"loss": 0.4362,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.47619047619047616,
|
| 440 |
+
"grad_norm": 0.34619084000587463,
|
| 441 |
+
"learning_rate": 0.00012535469134595595,
|
| 442 |
+
"loss": 0.451,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.4839968774395004,
|
| 447 |
+
"grad_norm": 0.46733614802360535,
|
| 448 |
+
"learning_rate": 0.00012270762630343734,
|
| 449 |
+
"loss": 0.4474,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.4918032786885246,
|
| 454 |
+
"grad_norm": 0.39834851026535034,
|
| 455 |
+
"learning_rate": 0.00012004367476224206,
|
| 456 |
+
"loss": 0.4508,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.4996096799375488,
|
| 461 |
+
"grad_norm": 0.5216445922851562,
|
| 462 |
+
"learning_rate": 0.00011736481776669306,
|
| 463 |
+
"loss": 0.4334,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.507416081186573,
|
| 468 |
+
"grad_norm": 0.5899478793144226,
|
| 469 |
+
"learning_rate": 0.00011467304744553618,
|
| 470 |
+
"loss": 0.4448,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.5152224824355972,
|
| 475 |
+
"grad_norm": 0.34121420979499817,
|
| 476 |
+
"learning_rate": 0.00011197036553049625,
|
| 477 |
+
"loss": 0.4446,
|
| 478 |
+
"step": 330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.5230288836846214,
|
| 482 |
+
"grad_norm": 0.3324553072452545,
|
| 483 |
+
"learning_rate": 0.00010925878186769158,
|
| 484 |
+
"loss": 0.4464,
|
| 485 |
+
"step": 335
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.5308352849336456,
|
| 489 |
+
"grad_norm": 0.3622628152370453,
|
| 490 |
+
"learning_rate": 0.00010654031292301432,
|
| 491 |
+
"loss": 0.4389,
|
| 492 |
+
"step": 340
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.5386416861826698,
|
| 496 |
+
"grad_norm": 0.33782732486724854,
|
| 497 |
+
"learning_rate": 0.00010381698028258817,
|
| 498 |
+
"loss": 0.4446,
|
| 499 |
+
"step": 345
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.546448087431694,
|
| 503 |
+
"grad_norm": 0.36627140641212463,
|
| 504 |
+
"learning_rate": 0.00010109080914941824,
|
| 505 |
+
"loss": 0.4582,
|
| 506 |
+
"step": 350
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.5542544886807181,
|
| 510 |
+
"grad_norm": 0.37063345313072205,
|
| 511 |
+
"learning_rate": 9.836382683735132e-05,
|
| 512 |
+
"loss": 0.4536,
|
| 513 |
+
"step": 355
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.5620608899297423,
|
| 517 |
+
"grad_norm": 0.3683343827724457,
|
| 518 |
+
"learning_rate": 9.563806126346642e-05,
|
| 519 |
+
"loss": 0.4546,
|
| 520 |
+
"step": 360
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.5698672911787666,
|
| 524 |
+
"grad_norm": 0.40577879548072815,
|
| 525 |
+
"learning_rate": 9.29155394400166e-05,
|
| 526 |
+
"loss": 0.4528,
|
| 527 |
+
"step": 365
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.5776736924277908,
|
| 531 |
+
"grad_norm": 0.3519943952560425,
|
| 532 |
+
"learning_rate": 9.019828596704394e-05,
|
| 533 |
+
"loss": 0.4452,
|
| 534 |
+
"step": 370
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.585480093676815,
|
| 538 |
+
"grad_norm": 0.3319181501865387,
|
| 539 |
+
"learning_rate": 8.74883215267881e-05,
|
| 540 |
+
"loss": 0.4365,
|
| 541 |
+
"step": 375
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.5932864949258392,
|
| 545 |
+
"grad_norm": 0.37883397936820984,
|
| 546 |
+
"learning_rate": 8.478766138100834e-05,
|
| 547 |
+
"loss": 0.4378,
|
| 548 |
+
"step": 380
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.6010928961748634,
|
| 552 |
+
"grad_norm": 0.3303097188472748,
|
| 553 |
+
"learning_rate": 8.209831387233676e-05,
|
| 554 |
+
"loss": 0.4491,
|
| 555 |
+
"step": 385
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.6088992974238876,
|
| 559 |
+
"grad_norm": 0.3626279830932617,
|
| 560 |
+
"learning_rate": 7.942227893077652e-05,
|
| 561 |
+
"loss": 0.4449,
|
| 562 |
+
"step": 390
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.6167056986729118,
|
| 566 |
+
"grad_norm": 0.38927000761032104,
|
| 567 |
+
"learning_rate": 7.676154658645656e-05,
|
| 568 |
+
"loss": 0.4386,
|
| 569 |
+
"step": 395
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.624512099921936,
|
| 573 |
+
"grad_norm": 0.34341347217559814,
|
| 574 |
+
"learning_rate": 7.411809548974792e-05,
|
| 575 |
+
"loss": 0.4367,
|
| 576 |
+
"step": 400
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.6323185011709602,
|
| 580 |
+
"grad_norm": 0.48884400725364685,
|
| 581 |
+
"learning_rate": 7.149389143984295e-05,
|
| 582 |
+
"loss": 0.4481,
|
| 583 |
+
"step": 405
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.6401249024199844,
|
| 587 |
+
"grad_norm": 0.3529874384403229,
|
| 588 |
+
"learning_rate": 6.889088592289093e-05,
|
| 589 |
+
"loss": 0.4452,
|
| 590 |
+
"step": 410
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.6479313036690086,
|
| 594 |
+
"grad_norm": 0.35880032181739807,
|
| 595 |
+
"learning_rate": 6.6311014660778e-05,
|
| 596 |
+
"loss": 0.4466,
|
| 597 |
+
"step": 415
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.6557377049180327,
|
| 601 |
+
"grad_norm": 0.3469119369983673,
|
| 602 |
+
"learning_rate": 6.375619617162985e-05,
|
| 603 |
+
"loss": 0.4465,
|
| 604 |
+
"step": 420
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.663544106167057,
|
| 608 |
+
"grad_norm": 0.33010825514793396,
|
| 609 |
+
"learning_rate": 6.122833034310793e-05,
|
| 610 |
+
"loss": 0.4418,
|
| 611 |
+
"step": 425
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.6713505074160812,
|
| 615 |
+
"grad_norm": 0.32382553815841675,
|
| 616 |
+
"learning_rate": 5.872929701956054e-05,
|
| 617 |
+
"loss": 0.4344,
|
| 618 |
+
"step": 430
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.6791569086651054,
|
| 622 |
+
"grad_norm": 0.38468924164772034,
|
| 623 |
+
"learning_rate": 5.6260954604078585e-05,
|
| 624 |
+
"loss": 0.446,
|
| 625 |
+
"step": 435
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.6869633099141296,
|
| 629 |
+
"grad_norm": 0.38541513681411743,
|
| 630 |
+
"learning_rate": 5.382513867649663e-05,
|
| 631 |
+
"loss": 0.435,
|
| 632 |
+
"step": 440
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.6947697111631538,
|
| 636 |
+
"grad_norm": 0.3638440668582916,
|
| 637 |
+
"learning_rate": 5.142366062836599e-05,
|
| 638 |
+
"loss": 0.4421,
|
| 639 |
+
"step": 445
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.702576112412178,
|
| 643 |
+
"grad_norm": 0.3527115285396576,
|
| 644 |
+
"learning_rate": 4.9058306315915826e-05,
|
| 645 |
+
"loss": 0.452,
|
| 646 |
+
"step": 450
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.7103825136612022,
|
| 650 |
+
"grad_norm": 0.3580182194709778,
|
| 651 |
+
"learning_rate": 4.6730834732003104e-05,
|
| 652 |
+
"loss": 0.4457,
|
| 653 |
+
"step": 455
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.7181889149102264,
|
| 657 |
+
"grad_norm": 0.3419717848300934,
|
| 658 |
+
"learning_rate": 4.444297669803981e-05,
|
| 659 |
+
"loss": 0.4529,
|
| 660 |
+
"step": 460
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.7259953161592506,
|
| 664 |
+
"grad_norm": 0.3361879885196686,
|
| 665 |
+
"learning_rate": 4.219643357686967e-05,
|
| 666 |
+
"loss": 0.4338,
|
| 667 |
+
"step": 465
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.7338017174082748,
|
| 671 |
+
"grad_norm": 0.35652631521224976,
|
| 672 |
+
"learning_rate": 3.999287600755192e-05,
|
| 673 |
+
"loss": 0.4301,
|
| 674 |
+
"step": 470
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.741608118657299,
|
| 678 |
+
"grad_norm": 0.34089410305023193,
|
| 679 |
+
"learning_rate": 3.783394266299228e-05,
|
| 680 |
+
"loss": 0.4392,
|
| 681 |
+
"step": 475
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.7494145199063232,
|
| 685 |
+
"grad_norm": 0.3883989751338959,
|
| 686 |
+
"learning_rate": 3.5721239031346066e-05,
|
| 687 |
+
"loss": 0.4447,
|
| 688 |
+
"step": 480
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.7572209211553473,
|
| 692 |
+
"grad_norm": 0.3701310455799103,
|
| 693 |
+
"learning_rate": 3.365633622209891e-05,
|
| 694 |
+
"loss": 0.4399,
|
| 695 |
+
"step": 485
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.7650273224043715,
|
| 699 |
+
"grad_norm": 0.37045201659202576,
|
| 700 |
+
"learning_rate": 3.164076979771287e-05,
|
| 701 |
+
"loss": 0.4386,
|
| 702 |
+
"step": 490
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.7728337236533958,
|
| 706 |
+
"grad_norm": 0.3776572346687317,
|
| 707 |
+
"learning_rate": 2.9676038631707593e-05,
|
| 708 |
+
"loss": 0.4359,
|
| 709 |
+
"step": 495
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.78064012490242,
|
| 713 |
+
"grad_norm": 0.35069331526756287,
|
| 714 |
+
"learning_rate": 2.776360379402445e-05,
|
| 715 |
+
"loss": 0.439,
|
| 716 |
+
"step": 500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.7884465261514442,
|
| 720 |
+
"grad_norm": 0.33275192975997925,
|
| 721 |
+
"learning_rate": 2.5904887464504114e-05,
|
| 722 |
+
"loss": 0.4375,
|
| 723 |
+
"step": 505
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.7962529274004684,
|
| 727 |
+
"grad_norm": 0.34463104605674744,
|
| 728 |
+
"learning_rate": 2.4101271875283817e-05,
|
| 729 |
+
"loss": 0.4432,
|
| 730 |
+
"step": 510
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.8040593286494926,
|
| 734 |
+
"grad_norm": 0.3554835617542267,
|
| 735 |
+
"learning_rate": 2.2354098282902446e-05,
|
| 736 |
+
"loss": 0.4327,
|
| 737 |
+
"step": 515
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.8118657298985168,
|
| 741 |
+
"grad_norm": 0.3450513482093811,
|
| 742 |
+
"learning_rate": 2.0664665970876496e-05,
|
| 743 |
+
"loss": 0.4498,
|
| 744 |
+
"step": 520
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.819672131147541,
|
| 748 |
+
"grad_norm": 0.34782862663269043,
|
| 749 |
+
"learning_rate": 1.903423128348959e-05,
|
| 750 |
+
"loss": 0.4455,
|
| 751 |
+
"step": 525
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.8274785323965652,
|
| 755 |
+
"grad_norm": 0.3532538115978241,
|
| 756 |
+
"learning_rate": 1.7464006691513623e-05,
|
| 757 |
+
"loss": 0.4377,
|
| 758 |
+
"step": 530
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.8352849336455894,
|
| 762 |
+
"grad_norm": 0.37945592403411865,
|
| 763 |
+
"learning_rate": 1.595515989055618e-05,
|
| 764 |
+
"loss": 0.4499,
|
| 765 |
+
"step": 535
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.8430913348946136,
|
| 769 |
+
"grad_norm": 0.3615630269050598,
|
| 770 |
+
"learning_rate": 1.4508812932705363e-05,
|
| 771 |
+
"loss": 0.4427,
|
| 772 |
+
"step": 540
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.8508977361436377,
|
| 776 |
+
"grad_norm": 0.3308858275413513,
|
| 777 |
+
"learning_rate": 1.3126041392116772e-05,
|
| 778 |
+
"loss": 0.4466,
|
| 779 |
+
"step": 545
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.8587041373926619,
|
| 783 |
+
"grad_norm": 0.3379354178905487,
|
| 784 |
+
"learning_rate": 1.1807873565164506e-05,
|
| 785 |
+
"loss": 0.4508,
|
| 786 |
+
"step": 550
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.8665105386416861,
|
| 790 |
+
"grad_norm": 0.36346766352653503,
|
| 791 |
+
"learning_rate": 1.0555289705749483e-05,
|
| 792 |
+
"loss": 0.4378,
|
| 793 |
+
"step": 555
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.8743169398907104,
|
| 797 |
+
"grad_norm": 0.37977978587150574,
|
| 798 |
+
"learning_rate": 9.369221296335006e-06,
|
| 799 |
+
"loss": 0.432,
|
| 800 |
+
"step": 560
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.8821233411397346,
|
| 804 |
+
"grad_norm": 0.3398190438747406,
|
| 805 |
+
"learning_rate": 8.250550355250875e-06,
|
| 806 |
+
"loss": 0.4317,
|
| 807 |
+
"step": 565
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.8899297423887588,
|
| 811 |
+
"grad_norm": 0.3510373532772064,
|
| 812 |
+
"learning_rate": 7.200108780781556e-06,
|
| 813 |
+
"loss": 0.4526,
|
| 814 |
+
"step": 570
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.897736143637783,
|
| 818 |
+
"grad_norm": 0.341723769903183,
|
| 819 |
+
"learning_rate": 6.218677732526035e-06,
|
| 820 |
+
"loss": 0.4366,
|
| 821 |
+
"step": 575
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.9055425448868072,
|
| 825 |
+
"grad_norm": 0.36046266555786133,
|
| 826 |
+
"learning_rate": 5.306987050489442e-06,
|
| 827 |
+
"loss": 0.436,
|
| 828 |
+
"step": 580
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.9133489461358314,
|
| 832 |
+
"grad_norm": 0.3662625551223755,
|
| 833 |
+
"learning_rate": 4.465714712338398e-06,
|
| 834 |
+
"loss": 0.444,
|
| 835 |
+
"step": 585
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.9211553473848556,
|
| 839 |
+
"grad_norm": 0.3435019254684448,
|
| 840 |
+
"learning_rate": 3.6954863292237297e-06,
|
| 841 |
+
"loss": 0.4393,
|
| 842 |
+
"step": 590
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.9289617486338798,
|
| 846 |
+
"grad_norm": 0.3347768783569336,
|
| 847 |
+
"learning_rate": 2.996874680545603e-06,
|
| 848 |
+
"loss": 0.4482,
|
| 849 |
+
"step": 595
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.936768149882904,
|
| 853 |
+
"grad_norm": 0.34706735610961914,
|
| 854 |
+
"learning_rate": 2.3703992880066638e-06,
|
| 855 |
+
"loss": 0.4433,
|
| 856 |
+
"step": 600
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.9445745511319282,
|
| 860 |
+
"grad_norm": 0.33762818574905396,
|
| 861 |
+
"learning_rate": 1.8165260292704711e-06,
|
| 862 |
+
"loss": 0.4342,
|
| 863 |
+
"step": 605
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.9523809523809523,
|
| 867 |
+
"grad_norm": 0.3355940580368042,
|
| 868 |
+
"learning_rate": 1.3356667915121025e-06,
|
| 869 |
+
"loss": 0.4419,
|
| 870 |
+
"step": 610
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.9601873536299765,
|
| 874 |
+
"grad_norm": 0.34287044405937195,
|
| 875 |
+
"learning_rate": 9.281791651187366e-07,
|
| 876 |
+
"loss": 0.4345,
|
| 877 |
+
"step": 615
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.9679937548790007,
|
| 881 |
+
"grad_norm": 0.3489275872707367,
|
| 882 |
+
"learning_rate": 5.943661777680354e-07,
|
| 883 |
+
"loss": 0.4362,
|
| 884 |
+
"step": 620
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.975800156128025,
|
| 888 |
+
"grad_norm": 0.3551251292228699,
|
| 889 |
+
"learning_rate": 3.3447606908196817e-07,
|
| 890 |
+
"loss": 0.4331,
|
| 891 |
+
"step": 625
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.9836065573770492,
|
| 895 |
+
"grad_norm": 0.34148380160331726,
|
| 896 |
+
"learning_rate": 1.487021060236904e-07,
|
| 897 |
+
"loss": 0.4369,
|
| 898 |
+
"step": 630
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.9914129586260734,
|
| 902 |
+
"grad_norm": 0.35507649183273315,
|
| 903 |
+
"learning_rate": 3.7182439174832106e-08,
|
| 904 |
+
"loss": 0.4372,
|
| 905 |
+
"step": 635
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.9992193598750976,
|
| 909 |
+
"grad_norm": 0.35683757066726685,
|
| 910 |
+
"learning_rate": 0.0,
|
| 911 |
+
"loss": 0.438,
|
| 912 |
+
"step": 640
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.9992193598750976,
|
| 916 |
+
"eval_loss": 1.0797678232192993,
|
| 917 |
+
"eval_runtime": 0.9282,
|
| 918 |
+
"eval_samples_per_second": 5.387,
|
| 919 |
+
"eval_steps_per_second": 1.077,
|
| 920 |
+
"step": 640
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.9992193598750976,
|
| 924 |
+
"step": 640,
|
| 925 |
+
"total_flos": 8.955542824078541e+17,
|
| 926 |
+
"train_loss": 0.4838556606322527,
|
| 927 |
+
"train_runtime": 4573.5964,
|
| 928 |
+
"train_samples_per_second": 4.48,
|
| 929 |
+
"train_steps_per_second": 0.14
|
| 930 |
+
}
|
| 931 |
+
],
|
| 932 |
+
"logging_steps": 5,
|
| 933 |
+
"max_steps": 640,
|
| 934 |
+
"num_input_tokens_seen": 0,
|
| 935 |
+
"num_train_epochs": 1,
|
| 936 |
+
"save_steps": 100,
|
| 937 |
+
"stateful_callbacks": {
|
| 938 |
+
"TrainerControl": {
|
| 939 |
+
"args": {
|
| 940 |
+
"should_epoch_stop": false,
|
| 941 |
+
"should_evaluate": false,
|
| 942 |
+
"should_log": false,
|
| 943 |
+
"should_save": true,
|
| 944 |
+
"should_training_stop": true
|
| 945 |
+
},
|
| 946 |
+
"attributes": {}
|
| 947 |
+
}
|
| 948 |
+
},
|
| 949 |
+
"total_flos": 8.955542824078541e+17,
|
| 950 |
+
"train_batch_size": 2,
|
| 951 |
+
"trial_name": null,
|
| 952 |
+
"trial_params": null
|
| 953 |
+
}
|