Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: llama3.2
|
| 4 |
+
base_model: meta-llama/Llama-3.2-3B
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
datasets:
|
| 10 |
+
- generator
|
| 11 |
+
model-index:
|
| 12 |
+
- name: llama3.1-3b-coding-gpt4o-100k2
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# llama3.1-3b-coding-gpt4o-100k2
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [meta-llama/Llama-3.2-3B](https://huggingface.co/meta-llama/Llama-3.2-3B) on the generator dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 1.6301
|
| 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: 0.002
|
| 43 |
+
- train_batch_size: 16
|
| 44 |
+
- eval_batch_size: 16
|
| 45 |
+
- seed: 42
|
| 46 |
+
- distributed_type: multi-GPU
|
| 47 |
+
- num_devices: 8
|
| 48 |
+
- gradient_accumulation_steps: 2
|
| 49 |
+
- total_train_batch_size: 256
|
| 50 |
+
- total_eval_batch_size: 128
|
| 51 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 52 |
+
- lr_scheduler_type: cosine
|
| 53 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 54 |
+
- num_epochs: 10
|
| 55 |
+
|
| 56 |
+
### Training results
|
| 57 |
+
|
| 58 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 59 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 60 |
+
| 1.0031 | 1.0 | 68 | 1.5510 |
|
| 61 |
+
| 0.9546 | 2.0 | 136 | 1.5149 |
|
| 62 |
+
| 0.936 | 3.0 | 204 | 1.5085 |
|
| 63 |
+
| 0.9186 | 4.0 | 272 | 1.5175 |
|
| 64 |
+
| 0.8948 | 5.0 | 340 | 1.5302 |
|
| 65 |
+
| 0.8742 | 6.0 | 408 | 1.5502 |
|
| 66 |
+
| 0.8556 | 7.0 | 476 | 1.5617 |
|
| 67 |
+
| 0.8428 | 8.0 | 544 | 1.5965 |
|
| 68 |
+
| 0.8168 | 9.0 | 612 | 1.6217 |
|
| 69 |
+
| 0.8191 | 9.8593 | 670 | 1.6301 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- PEFT 0.15.1
|
| 75 |
+
- Transformers 4.50.3
|
| 76 |
+
- Pytorch 2.6.0+cu124
|
| 77 |
+
- Datasets 3.5.0
|
| 78 |
+
- Tokenizers 0.21.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1612749744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68e6c34ff5b83d4da958c29a94d06b20fa3f6c199f168e1e0b501445b8a3d7a3
|
| 3 |
size 1612749744
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.85925925925926,
|
| 3 |
+
"total_flos": 2.9601022627828204e+18,
|
| 4 |
+
"train_loss": 0.9062140895359552,
|
| 5 |
+
"train_runtime": 3484.2972,
|
| 6 |
+
"train_samples": 116368,
|
| 7 |
+
"train_samples_per_second": 49.516,
|
| 8 |
+
"train_steps_per_second": 0.192
|
| 9 |
+
}
|
runs/Apr01_02-59-08_green-face-echoes-fin-01/events.out.tfevents.1743476556.green-face-echoes-fin-01.64054.0
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 sha256:32e81dadfde0db11eeefe569842f22d0c579cff25c34b4af794fd35d7ed548fb
|
| 3 |
+
size 37706
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.85925925925926,
|
| 3 |
+
"total_flos": 2.9601022627828204e+18,
|
| 4 |
+
"train_loss": 0.9062140895359552,
|
| 5 |
+
"train_runtime": 3484.2972,
|
| 6 |
+
"train_samples": 116368,
|
| 7 |
+
"train_samples_per_second": 49.516,
|
| 8 |
+
"train_steps_per_second": 0.192
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1068 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 9.85925925925926,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 670,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.014814814814814815,
|
| 14 |
+
"grad_norm": 0.4682641327381134,
|
| 15 |
+
"learning_rate": 2.9850746268656717e-05,
|
| 16 |
+
"loss": 1.4595,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.07407407407407407,
|
| 21 |
+
"grad_norm": 0.30114030838012695,
|
| 22 |
+
"learning_rate": 0.00014925373134328358,
|
| 23 |
+
"loss": 1.4529,
|
| 24 |
+
"step": 5
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.14814814814814814,
|
| 28 |
+
"grad_norm": 0.2646062970161438,
|
| 29 |
+
"learning_rate": 0.00029850746268656717,
|
| 30 |
+
"loss": 1.3781,
|
| 31 |
+
"step": 10
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.2222222222222222,
|
| 35 |
+
"grad_norm": 0.2039109170436859,
|
| 36 |
+
"learning_rate": 0.00044776119402985075,
|
| 37 |
+
"loss": 1.2598,
|
| 38 |
+
"step": 15
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.2962962962962963,
|
| 42 |
+
"grad_norm": 0.12383515387773514,
|
| 43 |
+
"learning_rate": 0.0005970149253731343,
|
| 44 |
+
"loss": 1.1834,
|
| 45 |
+
"step": 20
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.37037037037037035,
|
| 49 |
+
"grad_norm": 0.1035536378622055,
|
| 50 |
+
"learning_rate": 0.0007462686567164179,
|
| 51 |
+
"loss": 1.1305,
|
| 52 |
+
"step": 25
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.4444444444444444,
|
| 56 |
+
"grad_norm": 0.09090688824653625,
|
| 57 |
+
"learning_rate": 0.0008955223880597015,
|
| 58 |
+
"loss": 1.0904,
|
| 59 |
+
"step": 30
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.5185185185185185,
|
| 63 |
+
"grad_norm": 0.1432366669178009,
|
| 64 |
+
"learning_rate": 0.001044776119402985,
|
| 65 |
+
"loss": 1.0762,
|
| 66 |
+
"step": 35
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.5925925925925926,
|
| 70 |
+
"grad_norm": 0.07171270251274109,
|
| 71 |
+
"learning_rate": 0.0011940298507462687,
|
| 72 |
+
"loss": 1.0618,
|
| 73 |
+
"step": 40
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.6666666666666666,
|
| 77 |
+
"grad_norm": 0.07491806894540787,
|
| 78 |
+
"learning_rate": 0.0013432835820895524,
|
| 79 |
+
"loss": 1.0421,
|
| 80 |
+
"step": 45
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.7407407407407407,
|
| 84 |
+
"grad_norm": 0.06790623813867569,
|
| 85 |
+
"learning_rate": 0.0014925373134328358,
|
| 86 |
+
"loss": 1.0302,
|
| 87 |
+
"step": 50
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.8148148148148148,
|
| 91 |
+
"grad_norm": 0.08844709396362305,
|
| 92 |
+
"learning_rate": 0.0016417910447761195,
|
| 93 |
+
"loss": 1.018,
|
| 94 |
+
"step": 55
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.8888888888888888,
|
| 98 |
+
"grad_norm": 0.08857131749391556,
|
| 99 |
+
"learning_rate": 0.001791044776119403,
|
| 100 |
+
"loss": 1.0156,
|
| 101 |
+
"step": 60
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.9629629629629629,
|
| 105 |
+
"grad_norm": 0.09674689918756485,
|
| 106 |
+
"learning_rate": 0.0019402985074626867,
|
| 107 |
+
"loss": 1.0031,
|
| 108 |
+
"step": 65
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 1.0,
|
| 112 |
+
"eval_loss": 1.551000714302063,
|
| 113 |
+
"eval_runtime": 0.869,
|
| 114 |
+
"eval_samples_per_second": 4.603,
|
| 115 |
+
"eval_steps_per_second": 1.151,
|
| 116 |
+
"step": 68
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.0296296296296297,
|
| 120 |
+
"grad_norm": 0.09539825469255447,
|
| 121 |
+
"learning_rate": 0.001999877856940653,
|
| 122 |
+
"loss": 0.9937,
|
| 123 |
+
"step": 70
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.1037037037037036,
|
| 127 |
+
"grad_norm": 0.09851890057325363,
|
| 128 |
+
"learning_rate": 0.0019991315351855746,
|
| 129 |
+
"loss": 0.9895,
|
| 130 |
+
"step": 75
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.1777777777777778,
|
| 134 |
+
"grad_norm": 0.06911145895719528,
|
| 135 |
+
"learning_rate": 0.0019977072547317748,
|
| 136 |
+
"loss": 0.9817,
|
| 137 |
+
"step": 80
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.2518518518518518,
|
| 141 |
+
"grad_norm": 0.06769894808530807,
|
| 142 |
+
"learning_rate": 0.001995605982021898,
|
| 143 |
+
"loss": 0.9762,
|
| 144 |
+
"step": 85
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.325925925925926,
|
| 148 |
+
"grad_norm": 0.06828448921442032,
|
| 149 |
+
"learning_rate": 0.001992829142870326,
|
| 150 |
+
"loss": 0.9743,
|
| 151 |
+
"step": 90
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.4,
|
| 155 |
+
"grad_norm": 0.06951478868722916,
|
| 156 |
+
"learning_rate": 0.0019893786214956943,
|
| 157 |
+
"loss": 0.9743,
|
| 158 |
+
"step": 95
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.474074074074074,
|
| 162 |
+
"grad_norm": 0.06752126663923264,
|
| 163 |
+
"learning_rate": 0.001985256759242359,
|
| 164 |
+
"loss": 0.9718,
|
| 165 |
+
"step": 100
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.5481481481481483,
|
| 169 |
+
"grad_norm": 0.06669533252716064,
|
| 170 |
+
"learning_rate": 0.0019804663529916825,
|
| 171 |
+
"loss": 0.9743,
|
| 172 |
+
"step": 105
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.6222222222222222,
|
| 176 |
+
"grad_norm": 0.06977611780166626,
|
| 177 |
+
"learning_rate": 0.001975010653264216,
|
| 178 |
+
"loss": 0.9678,
|
| 179 |
+
"step": 110
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.6962962962962962,
|
| 183 |
+
"grad_norm": 0.07217196375131607,
|
| 184 |
+
"learning_rate": 0.0019688933620140635,
|
| 185 |
+
"loss": 0.9694,
|
| 186 |
+
"step": 115
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.7703703703703704,
|
| 190 |
+
"grad_norm": 0.06247986480593681,
|
| 191 |
+
"learning_rate": 0.0019621186301169314,
|
| 192 |
+
"loss": 0.9625,
|
| 193 |
+
"step": 120
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.8444444444444446,
|
| 197 |
+
"grad_norm": 0.07415565848350525,
|
| 198 |
+
"learning_rate": 0.001954691054553556,
|
| 199 |
+
"loss": 0.9697,
|
| 200 |
+
"step": 125
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.9185185185185185,
|
| 204 |
+
"grad_norm": 0.07004866003990173,
|
| 205 |
+
"learning_rate": 0.0019466156752904343,
|
| 206 |
+
"loss": 0.957,
|
| 207 |
+
"step": 130
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.9925925925925925,
|
| 211 |
+
"grad_norm": 0.06320279091596603,
|
| 212 |
+
"learning_rate": 0.0019378979718599645,
|
| 213 |
+
"loss": 0.9546,
|
| 214 |
+
"step": 135
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 2.0,
|
| 218 |
+
"eval_loss": 1.5149173736572266,
|
| 219 |
+
"eval_runtime": 0.8697,
|
| 220 |
+
"eval_samples_per_second": 4.599,
|
| 221 |
+
"eval_steps_per_second": 1.15,
|
| 222 |
+
"step": 136
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 2.0592592592592593,
|
| 226 |
+
"grad_norm": 0.07447217404842377,
|
| 227 |
+
"learning_rate": 0.0019285438596423204,
|
| 228 |
+
"loss": 0.9443,
|
| 229 |
+
"step": 140
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 2.1333333333333333,
|
| 233 |
+
"grad_norm": 0.06741169095039368,
|
| 234 |
+
"learning_rate": 0.0019185596858515798,
|
| 235 |
+
"loss": 0.9371,
|
| 236 |
+
"step": 145
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.2074074074074073,
|
| 240 |
+
"grad_norm": 0.06852757930755615,
|
| 241 |
+
"learning_rate": 0.0019079522252288387,
|
| 242 |
+
"loss": 0.9395,
|
| 243 |
+
"step": 150
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 2.2814814814814817,
|
| 247 |
+
"grad_norm": 0.06586603075265884,
|
| 248 |
+
"learning_rate": 0.0018967286754452213,
|
| 249 |
+
"loss": 0.937,
|
| 250 |
+
"step": 155
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 2.3555555555555556,
|
| 254 |
+
"grad_norm": 0.0683656558394432,
|
| 255 |
+
"learning_rate": 0.0018848966522179167,
|
| 256 |
+
"loss": 0.9336,
|
| 257 |
+
"step": 160
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 2.4296296296296296,
|
| 261 |
+
"grad_norm": 0.07259602099657059,
|
| 262 |
+
"learning_rate": 0.001872464184142548,
|
| 263 |
+
"loss": 0.935,
|
| 264 |
+
"step": 165
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 2.5037037037037035,
|
| 268 |
+
"grad_norm": 0.06436455249786377,
|
| 269 |
+
"learning_rate": 0.0018594397072453856,
|
| 270 |
+
"loss": 0.9316,
|
| 271 |
+
"step": 170
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 2.5777777777777775,
|
| 275 |
+
"grad_norm": 0.08042966574430466,
|
| 276 |
+
"learning_rate": 0.0018458320592590974,
|
| 277 |
+
"loss": 0.938,
|
| 278 |
+
"step": 175
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.651851851851852,
|
| 282 |
+
"grad_norm": 0.0699801966547966,
|
| 283 |
+
"learning_rate": 0.0018316504736259254,
|
| 284 |
+
"loss": 0.9422,
|
| 285 |
+
"step": 180
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.725925925925926,
|
| 289 |
+
"grad_norm": 0.06373833864927292,
|
| 290 |
+
"learning_rate": 0.0018169045732323492,
|
| 291 |
+
"loss": 0.9348,
|
| 292 |
+
"step": 185
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 2.8,
|
| 296 |
+
"grad_norm": 0.07165364176034927,
|
| 297 |
+
"learning_rate": 0.0018016043638794975,
|
| 298 |
+
"loss": 0.9354,
|
| 299 |
+
"step": 190
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 2.8740740740740742,
|
| 303 |
+
"grad_norm": 0.06121128425002098,
|
| 304 |
+
"learning_rate": 0.0017857602274937308,
|
| 305 |
+
"loss": 0.9386,
|
| 306 |
+
"step": 195
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 2.948148148148148,
|
| 310 |
+
"grad_norm": 0.06334740668535233,
|
| 311 |
+
"learning_rate": 0.0017693829150820068,
|
| 312 |
+
"loss": 0.936,
|
| 313 |
+
"step": 200
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 3.0,
|
| 317 |
+
"eval_loss": 1.508521318435669,
|
| 318 |
+
"eval_runtime": 0.8697,
|
| 319 |
+
"eval_samples_per_second": 4.599,
|
| 320 |
+
"eval_steps_per_second": 1.15,
|
| 321 |
+
"step": 204
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 3.0148148148148146,
|
| 325 |
+
"grad_norm": 0.07033156603574753,
|
| 326 |
+
"learning_rate": 0.0017524835394368066,
|
| 327 |
+
"loss": 0.9317,
|
| 328 |
+
"step": 205
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 3.088888888888889,
|
| 332 |
+
"grad_norm": 0.06662800908088684,
|
| 333 |
+
"learning_rate": 0.0017350735675955695,
|
| 334 |
+
"loss": 0.9145,
|
| 335 |
+
"step": 210
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 3.162962962962963,
|
| 339 |
+
"grad_norm": 0.06688813865184784,
|
| 340 |
+
"learning_rate": 0.001717164813059761,
|
| 341 |
+
"loss": 0.9094,
|
| 342 |
+
"step": 215
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 3.237037037037037,
|
| 346 |
+
"grad_norm": 0.07399953156709671,
|
| 347 |
+
"learning_rate": 0.0016987694277788418,
|
| 348 |
+
"loss": 0.9147,
|
| 349 |
+
"step": 220
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 3.311111111111111,
|
| 353 |
+
"grad_norm": 0.06779713183641434,
|
| 354 |
+
"learning_rate": 0.0016798998939045893,
|
| 355 |
+
"loss": 0.9123,
|
| 356 |
+
"step": 225
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 3.3851851851851853,
|
| 360 |
+
"grad_norm": 0.06676509976387024,
|
| 361 |
+
"learning_rate": 0.001660569015321357,
|
| 362 |
+
"loss": 0.9099,
|
| 363 |
+
"step": 230
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 3.4592592592592593,
|
| 367 |
+
"grad_norm": 0.06683938950300217,
|
| 368 |
+
"learning_rate": 0.001640789908958026,
|
| 369 |
+
"loss": 0.9112,
|
| 370 |
+
"step": 235
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 3.533333333333333,
|
| 374 |
+
"grad_norm": 0.06712319701910019,
|
| 375 |
+
"learning_rate": 0.001620575995887538,
|
| 376 |
+
"loss": 0.914,
|
| 377 |
+
"step": 240
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 3.6074074074074076,
|
| 381 |
+
"grad_norm": 0.06718605011701584,
|
| 382 |
+
"learning_rate": 0.001599940992220053,
|
| 383 |
+
"loss": 0.9156,
|
| 384 |
+
"step": 245
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 3.6814814814814816,
|
| 388 |
+
"grad_norm": 0.06765800714492798,
|
| 389 |
+
"learning_rate": 0.0015788988997959114,
|
| 390 |
+
"loss": 0.9168,
|
| 391 |
+
"step": 250
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 3.7555555555555555,
|
| 395 |
+
"grad_norm": 0.06374535709619522,
|
| 396 |
+
"learning_rate": 0.0015574639966847127,
|
| 397 |
+
"loss": 0.9114,
|
| 398 |
+
"step": 255
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 3.8296296296296295,
|
| 402 |
+
"grad_norm": 0.06388971954584122,
|
| 403 |
+
"learning_rate": 0.0015356508274969594,
|
| 404 |
+
"loss": 0.9139,
|
| 405 |
+
"step": 260
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 3.9037037037037035,
|
| 409 |
+
"grad_norm": 0.0656428337097168,
|
| 410 |
+
"learning_rate": 0.0015134741935148419,
|
| 411 |
+
"loss": 0.916,
|
| 412 |
+
"step": 265
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 3.977777777777778,
|
| 416 |
+
"grad_norm": 0.06783714145421982,
|
| 417 |
+
"learning_rate": 0.0014909491426488577,
|
| 418 |
+
"loss": 0.9186,
|
| 419 |
+
"step": 270
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 4.0,
|
| 423 |
+
"eval_loss": 1.517486810684204,
|
| 424 |
+
"eval_runtime": 0.8755,
|
| 425 |
+
"eval_samples_per_second": 4.569,
|
| 426 |
+
"eval_steps_per_second": 1.142,
|
| 427 |
+
"step": 272
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 4.044444444444444,
|
| 431 |
+
"grad_norm": 0.06940994411706924,
|
| 432 |
+
"learning_rate": 0.001468090959227082,
|
| 433 |
+
"loss": 0.9011,
|
| 434 |
+
"step": 275
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 4.118518518518519,
|
| 438 |
+
"grad_norm": 0.06819378584623337,
|
| 439 |
+
"learning_rate": 0.0014449151536240167,
|
| 440 |
+
"loss": 0.8866,
|
| 441 |
+
"step": 280
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 4.192592592592592,
|
| 445 |
+
"grad_norm": 0.0655524805188179,
|
| 446 |
+
"learning_rate": 0.0014214374517360576,
|
| 447 |
+
"loss": 0.8916,
|
| 448 |
+
"step": 285
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 4.266666666666667,
|
| 452 |
+
"grad_norm": 0.06668845564126968,
|
| 453 |
+
"learning_rate": 0.0013976737843107202,
|
| 454 |
+
"loss": 0.8871,
|
| 455 |
+
"step": 290
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 4.340740740740741,
|
| 459 |
+
"grad_norm": 0.06470604240894318,
|
| 460 |
+
"learning_rate": 0.0013736402761368597,
|
| 461 |
+
"loss": 0.8928,
|
| 462 |
+
"step": 295
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 4.4148148148148145,
|
| 466 |
+
"grad_norm": 0.06732232868671417,
|
| 467 |
+
"learning_rate": 0.0013493532351032318,
|
| 468 |
+
"loss": 0.8985,
|
| 469 |
+
"step": 300
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 4.488888888888889,
|
| 473 |
+
"grad_norm": 0.0662841871380806,
|
| 474 |
+
"learning_rate": 0.0013248291411328047,
|
| 475 |
+
"loss": 0.8869,
|
| 476 |
+
"step": 305
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 4.562962962962963,
|
| 480 |
+
"grad_norm": 0.06613945215940475,
|
| 481 |
+
"learning_rate": 0.001300084635000341,
|
| 482 |
+
"loss": 0.8963,
|
| 483 |
+
"step": 310
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 4.637037037037037,
|
| 487 |
+
"grad_norm": 0.06735741347074509,
|
| 488 |
+
"learning_rate": 0.0012751365070408334,
|
| 489 |
+
"loss": 0.9035,
|
| 490 |
+
"step": 315
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 4.711111111111111,
|
| 494 |
+
"grad_norm": 0.06463445723056793,
|
| 495 |
+
"learning_rate": 0.0012500016857564585,
|
| 496 |
+
"loss": 0.8966,
|
| 497 |
+
"step": 320
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 4.785185185185185,
|
| 501 |
+
"grad_norm": 0.06602155417203903,
|
| 502 |
+
"learning_rate": 0.0012246972263297718,
|
| 503 |
+
"loss": 0.895,
|
| 504 |
+
"step": 325
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 4.859259259259259,
|
| 508 |
+
"grad_norm": 0.06352429836988449,
|
| 509 |
+
"learning_rate": 0.0011992402990509514,
|
| 510 |
+
"loss": 0.894,
|
| 511 |
+
"step": 330
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 4.933333333333334,
|
| 515 |
+
"grad_norm": 0.06808946281671524,
|
| 516 |
+
"learning_rate": 0.0011736481776669307,
|
| 517 |
+
"loss": 0.8969,
|
| 518 |
+
"step": 335
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 5.0,
|
| 522 |
+
"grad_norm": 0.08401331305503845,
|
| 523 |
+
"learning_rate": 0.0011479382276603299,
|
| 524 |
+
"loss": 0.8948,
|
| 525 |
+
"step": 340
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 5.0,
|
| 529 |
+
"eval_loss": 1.5301542282104492,
|
| 530 |
+
"eval_runtime": 0.8691,
|
| 531 |
+
"eval_samples_per_second": 4.602,
|
| 532 |
+
"eval_steps_per_second": 1.151,
|
| 533 |
+
"step": 340
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 5.074074074074074,
|
| 537 |
+
"grad_norm": 0.06839559227228165,
|
| 538 |
+
"learning_rate": 0.0011221278944661473,
|
| 539 |
+
"loss": 0.8678,
|
| 540 |
+
"step": 345
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 5.148148148148148,
|
| 544 |
+
"grad_norm": 0.06838098913431168,
|
| 545 |
+
"learning_rate": 0.0010962346916341904,
|
| 546 |
+
"loss": 0.8666,
|
| 547 |
+
"step": 350
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 5.222222222222222,
|
| 551 |
+
"grad_norm": 0.06836072355508804,
|
| 552 |
+
"learning_rate": 0.001070276188945293,
|
| 553 |
+
"loss": 0.8731,
|
| 554 |
+
"step": 355
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 5.296296296296296,
|
| 558 |
+
"grad_norm": 0.06789132207632065,
|
| 559 |
+
"learning_rate": 0.0010442700004893765,
|
| 560 |
+
"loss": 0.8724,
|
| 561 |
+
"step": 360
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 5.37037037037037,
|
| 565 |
+
"grad_norm": 0.06825467944145203,
|
| 566 |
+
"learning_rate": 0.001018233772713443,
|
| 567 |
+
"loss": 0.8757,
|
| 568 |
+
"step": 365
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 5.444444444444445,
|
| 572 |
+
"grad_norm": 0.06852041184902191,
|
| 573 |
+
"learning_rate": 0.000992185172447616,
|
| 574 |
+
"loss": 0.8762,
|
| 575 |
+
"step": 370
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 5.518518518518518,
|
| 579 |
+
"grad_norm": 0.06898131966590881,
|
| 580 |
+
"learning_rate": 0.0009661418749173466,
|
| 581 |
+
"loss": 0.8731,
|
| 582 |
+
"step": 375
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 5.592592592592593,
|
| 586 |
+
"grad_norm": 0.06875770539045334,
|
| 587 |
+
"learning_rate": 0.0009401215517499251,
|
| 588 |
+
"loss": 0.8746,
|
| 589 |
+
"step": 380
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 5.666666666666667,
|
| 593 |
+
"grad_norm": 0.06649214774370193,
|
| 594 |
+
"learning_rate": 0.0009141418589834339,
|
| 595 |
+
"loss": 0.8748,
|
| 596 |
+
"step": 385
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 5.7407407407407405,
|
| 600 |
+
"grad_norm": 0.06804858148097992,
|
| 601 |
+
"learning_rate": 0.0008882204250862795,
|
| 602 |
+
"loss": 0.8783,
|
| 603 |
+
"step": 390
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 5.814814814814815,
|
| 607 |
+
"grad_norm": 0.06907966732978821,
|
| 608 |
+
"learning_rate": 0.0008623748389954282,
|
| 609 |
+
"loss": 0.8822,
|
| 610 |
+
"step": 395
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 5.888888888888889,
|
| 614 |
+
"grad_norm": 0.0679902508854866,
|
| 615 |
+
"learning_rate": 0.0008366226381814697,
|
| 616 |
+
"loss": 0.8777,
|
| 617 |
+
"step": 400
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 5.962962962962963,
|
| 621 |
+
"grad_norm": 0.06677145510911942,
|
| 622 |
+
"learning_rate": 0.0008109812967486025,
|
| 623 |
+
"loss": 0.8742,
|
| 624 |
+
"step": 405
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 6.0,
|
| 628 |
+
"eval_loss": 1.5502283573150635,
|
| 629 |
+
"eval_runtime": 0.8693,
|
| 630 |
+
"eval_samples_per_second": 4.602,
|
| 631 |
+
"eval_steps_per_second": 1.15,
|
| 632 |
+
"step": 408
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 6.029629629629629,
|
| 636 |
+
"grad_norm": 0.06917522847652435,
|
| 637 |
+
"learning_rate": 0.0007854682135776132,
|
| 638 |
+
"loss": 0.8605,
|
| 639 |
+
"step": 410
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 6.103703703703704,
|
| 643 |
+
"grad_norm": 0.07051009684801102,
|
| 644 |
+
"learning_rate": 0.0007601007005199021,
|
| 645 |
+
"loss": 0.8501,
|
| 646 |
+
"step": 415
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 6.177777777777778,
|
| 650 |
+
"grad_norm": 0.07272496819496155,
|
| 651 |
+
"learning_rate": 0.0007348959706505627,
|
| 652 |
+
"loss": 0.8553,
|
| 653 |
+
"step": 420
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 6.2518518518518515,
|
| 657 |
+
"grad_norm": 0.07074420154094696,
|
| 658 |
+
"learning_rate": 0.000709871126588481,
|
| 659 |
+
"loss": 0.8496,
|
| 660 |
+
"step": 425
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 6.325925925925926,
|
| 664 |
+
"grad_norm": 0.07021532952785492,
|
| 665 |
+
"learning_rate": 0.0006850431488913895,
|
| 666 |
+
"loss": 0.8547,
|
| 667 |
+
"step": 430
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 6.4,
|
| 671 |
+
"grad_norm": 0.07260267436504364,
|
| 672 |
+
"learning_rate": 0.0006604288845337453,
|
| 673 |
+
"loss": 0.8568,
|
| 674 |
+
"step": 435
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 6.474074074074074,
|
| 678 |
+
"grad_norm": 0.06939396262168884,
|
| 679 |
+
"learning_rate": 0.0006360450354752458,
|
| 680 |
+
"loss": 0.8561,
|
| 681 |
+
"step": 440
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 6.548148148148148,
|
| 685 |
+
"grad_norm": 0.06964612007141113,
|
| 686 |
+
"learning_rate": 0.0006119081473277501,
|
| 687 |
+
"loss": 0.8577,
|
| 688 |
+
"step": 445
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 6.622222222222222,
|
| 692 |
+
"grad_norm": 0.06987880170345306,
|
| 693 |
+
"learning_rate": 0.0005880345981282876,
|
| 694 |
+
"loss": 0.858,
|
| 695 |
+
"step": 450
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 6.696296296296296,
|
| 699 |
+
"grad_norm": 0.06909282505512238,
|
| 700 |
+
"learning_rate": 0.0005644405872257716,
|
| 701 |
+
"loss": 0.8559,
|
| 702 |
+
"step": 455
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 6.770370370370371,
|
| 706 |
+
"grad_norm": 0.0683453232049942,
|
| 707 |
+
"learning_rate": 0.0005411421242889642,
|
| 708 |
+
"loss": 0.8561,
|
| 709 |
+
"step": 460
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 6.844444444444444,
|
| 713 |
+
"grad_norm": 0.0680374875664711,
|
| 714 |
+
"learning_rate": 0.000518155018443151,
|
| 715 |
+
"loss": 0.859,
|
| 716 |
+
"step": 465
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 6.9185185185185185,
|
| 720 |
+
"grad_norm": 0.067069411277771,
|
| 721 |
+
"learning_rate": 0.0004954948675428853,
|
| 722 |
+
"loss": 0.8489,
|
| 723 |
+
"step": 470
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 6.992592592592593,
|
| 727 |
+
"grad_norm": 0.06691515445709229,
|
| 728 |
+
"learning_rate": 0.00047317704758809945,
|
| 729 |
+
"loss": 0.8556,
|
| 730 |
+
"step": 475
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 7.0,
|
| 734 |
+
"eval_loss": 1.5617406368255615,
|
| 735 |
+
"eval_runtime": 0.8711,
|
| 736 |
+
"eval_samples_per_second": 4.592,
|
| 737 |
+
"eval_steps_per_second": 1.148,
|
| 738 |
+
"step": 476
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 7.059259259259259,
|
| 742 |
+
"grad_norm": 0.08424794673919678,
|
| 743 |
+
"learning_rate": 0.0004512167022907494,
|
| 744 |
+
"loss": 0.8413,
|
| 745 |
+
"step": 480
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 7.133333333333334,
|
| 749 |
+
"grad_norm": 0.07284523546695709,
|
| 750 |
+
"learning_rate": 0.00042962873279907965,
|
| 751 |
+
"loss": 0.8329,
|
| 752 |
+
"step": 485
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 7.207407407407407,
|
| 756 |
+
"grad_norm": 0.06989779323339462,
|
| 757 |
+
"learning_rate": 0.0004084277875864776,
|
| 758 |
+
"loss": 0.8368,
|
| 759 |
+
"step": 490
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 7.281481481481482,
|
| 763 |
+
"grad_norm": 0.0744442567229271,
|
| 764 |
+
"learning_rate": 0.0003876282525117847,
|
| 765 |
+
"loss": 0.831,
|
| 766 |
+
"step": 495
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 7.355555555555555,
|
| 770 |
+
"grad_norm": 0.07233459502458572,
|
| 771 |
+
"learning_rate": 0.0003672442410577965,
|
| 772 |
+
"loss": 0.8344,
|
| 773 |
+
"step": 500
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 7.42962962962963,
|
| 777 |
+
"grad_norm": 0.07147523015737534,
|
| 778 |
+
"learning_rate": 0.0003472895847545905,
|
| 779 |
+
"loss": 0.837,
|
| 780 |
+
"step": 505
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 7.503703703703704,
|
| 784 |
+
"grad_norm": 0.0732484832406044,
|
| 785 |
+
"learning_rate": 0.000327777823794168,
|
| 786 |
+
"loss": 0.8427,
|
| 787 |
+
"step": 510
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 7.5777777777777775,
|
| 791 |
+
"grad_norm": 0.0711125060915947,
|
| 792 |
+
"learning_rate": 0.00030872219784278354,
|
| 793 |
+
"loss": 0.8394,
|
| 794 |
+
"step": 515
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 7.651851851851852,
|
| 798 |
+
"grad_norm": 0.07285265624523163,
|
| 799 |
+
"learning_rate": 0.0002901356370571967,
|
| 800 |
+
"loss": 0.8336,
|
| 801 |
+
"step": 520
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 7.725925925925926,
|
| 805 |
+
"grad_norm": 0.07154905050992966,
|
| 806 |
+
"learning_rate": 0.0002720307533109402,
|
| 807 |
+
"loss": 0.8403,
|
| 808 |
+
"step": 525
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 7.8,
|
| 812 |
+
"grad_norm": 0.07089488953351974,
|
| 813 |
+
"learning_rate": 0.000254419831636557,
|
| 814 |
+
"loss": 0.839,
|
| 815 |
+
"step": 530
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 7.874074074074074,
|
| 819 |
+
"grad_norm": 0.0709661915898323,
|
| 820 |
+
"learning_rate": 0.00023731482188961818,
|
| 821 |
+
"loss": 0.8353,
|
| 822 |
+
"step": 535
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 7.948148148148148,
|
| 826 |
+
"grad_norm": 0.07034063339233398,
|
| 827 |
+
"learning_rate": 0.00022072733064017102,
|
| 828 |
+
"loss": 0.8428,
|
| 829 |
+
"step": 540
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 8.0,
|
| 833 |
+
"eval_loss": 1.596451997756958,
|
| 834 |
+
"eval_runtime": 0.8703,
|
| 835 |
+
"eval_samples_per_second": 4.596,
|
| 836 |
+
"eval_steps_per_second": 1.149,
|
| 837 |
+
"step": 544
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 8.014814814814814,
|
| 841 |
+
"grad_norm": 0.07084991037845612,
|
| 842 |
+
"learning_rate": 0.00020466861329712473,
|
| 843 |
+
"loss": 0.8359,
|
| 844 |
+
"step": 545
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 8.088888888888889,
|
| 848 |
+
"grad_norm": 0.07405474036931992,
|
| 849 |
+
"learning_rate": 0.00018914956647091496,
|
| 850 |
+
"loss": 0.8195,
|
| 851 |
+
"step": 550
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 8.162962962962963,
|
| 855 |
+
"grad_norm": 0.07152204215526581,
|
| 856 |
+
"learning_rate": 0.0001741807205796314,
|
| 857 |
+
"loss": 0.8289,
|
| 858 |
+
"step": 555
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 8.237037037037037,
|
| 862 |
+
"grad_norm": 0.0712200403213501,
|
| 863 |
+
"learning_rate": 0.00015977223270362194,
|
| 864 |
+
"loss": 0.8271,
|
| 865 |
+
"step": 560
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 8.311111111111112,
|
| 869 |
+
"grad_norm": 0.07045566290616989,
|
| 870 |
+
"learning_rate": 0.0001459338796934293,
|
| 871 |
+
"loss": 0.829,
|
| 872 |
+
"step": 565
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 8.385185185185184,
|
| 876 |
+
"grad_norm": 0.0720411017537117,
|
| 877 |
+
"learning_rate": 0.000132675051535725,
|
| 878 |
+
"loss": 0.8265,
|
| 879 |
+
"step": 570
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 8.459259259259259,
|
| 883 |
+
"grad_norm": 0.07052139192819595,
|
| 884 |
+
"learning_rate": 0.00012000474498175551,
|
| 885 |
+
"loss": 0.8226,
|
| 886 |
+
"step": 575
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 8.533333333333333,
|
| 890 |
+
"grad_norm": 0.07078087329864502,
|
| 891 |
+
"learning_rate": 0.00010793155744261352,
|
| 892 |
+
"loss": 0.8241,
|
| 893 |
+
"step": 580
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 8.607407407407408,
|
| 897 |
+
"grad_norm": 0.07028964906930923,
|
| 898 |
+
"learning_rate": 9.646368115548232e-05,
|
| 899 |
+
"loss": 0.8212,
|
| 900 |
+
"step": 585
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 8.681481481481482,
|
| 904 |
+
"grad_norm": 0.0702112540602684,
|
| 905 |
+
"learning_rate": 8.56088976248095e-05,
|
| 906 |
+
"loss": 0.8232,
|
| 907 |
+
"step": 590
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 8.755555555555556,
|
| 911 |
+
"grad_norm": 0.07041744887828827,
|
| 912 |
+
"learning_rate": 7.53745723421827e-05,
|
| 913 |
+
"loss": 0.8193,
|
| 914 |
+
"step": 595
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 8.829629629629629,
|
| 918 |
+
"grad_norm": 0.06979186832904816,
|
| 919 |
+
"learning_rate": 6.576764978849003e-05,
|
| 920 |
+
"loss": 0.8186,
|
| 921 |
+
"step": 600
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 8.903703703703703,
|
| 925 |
+
"grad_norm": 0.07058751583099365,
|
| 926 |
+
"learning_rate": 5.679464872175666e-05,
|
| 927 |
+
"loss": 0.8279,
|
| 928 |
+
"step": 605
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 8.977777777777778,
|
| 932 |
+
"grad_norm": 0.07009345293045044,
|
| 933 |
+
"learning_rate": 4.846165775385458e-05,
|
| 934 |
+
"loss": 0.8168,
|
| 935 |
+
"step": 610
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 9.0,
|
| 939 |
+
"eval_loss": 1.6216613054275513,
|
| 940 |
+
"eval_runtime": 0.8697,
|
| 941 |
+
"eval_samples_per_second": 4.599,
|
| 942 |
+
"eval_steps_per_second": 1.15,
|
| 943 |
+
"step": 612
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 9.044444444444444,
|
| 947 |
+
"grad_norm": 0.0695219412446022,
|
| 948 |
+
"learning_rate": 4.077433121908747e-05,
|
| 949 |
+
"loss": 0.8172,
|
| 950 |
+
"step": 615
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 9.118518518518519,
|
| 954 |
+
"grad_norm": 0.07094599306583405,
|
| 955 |
+
"learning_rate": 3.373788533745281e-05,
|
| 956 |
+
"loss": 0.8207,
|
| 957 |
+
"step": 620
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 9.192592592592593,
|
| 961 |
+
"grad_norm": 0.07142723351716995,
|
| 962 |
+
"learning_rate": 2.7357094675186987e-05,
|
| 963 |
+
"loss": 0.8101,
|
| 964 |
+
"step": 625
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 9.266666666666667,
|
| 968 |
+
"grad_norm": 0.07132075726985931,
|
| 969 |
+
"learning_rate": 2.1636288904992585e-05,
|
| 970 |
+
"loss": 0.8137,
|
| 971 |
+
"step": 630
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 9.34074074074074,
|
| 975 |
+
"grad_norm": 0.07085540145635605,
|
| 976 |
+
"learning_rate": 1.6579349868147686e-05,
|
| 977 |
+
"loss": 0.8103,
|
| 978 |
+
"step": 635
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 9.414814814814815,
|
| 982 |
+
"grad_norm": 0.0697101578116417,
|
| 983 |
+
"learning_rate": 1.218970894049065e-05,
|
| 984 |
+
"loss": 0.8094,
|
| 985 |
+
"step": 640
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 9.488888888888889,
|
| 989 |
+
"grad_norm": 0.07001277059316635,
|
| 990 |
+
"learning_rate": 8.470344704066047e-06,
|
| 991 |
+
"loss": 0.8233,
|
| 992 |
+
"step": 645
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 9.562962962962963,
|
| 996 |
+
"grad_norm": 0.07051407545804977,
|
| 997 |
+
"learning_rate": 5.42378092601481e-06,
|
| 998 |
+
"loss": 0.8181,
|
| 999 |
+
"step": 650
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 9.637037037037038,
|
| 1003 |
+
"grad_norm": 0.07038593292236328,
|
| 1004 |
+
"learning_rate": 3.0520848460765526e-06,
|
| 1005 |
+
"loss": 0.8198,
|
| 1006 |
+
"step": 655
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 9.71111111111111,
|
| 1010 |
+
"grad_norm": 0.06979399174451828,
|
| 1011 |
+
"learning_rate": 1.3568657738678436e-06,
|
| 1012 |
+
"loss": 0.8138,
|
| 1013 |
+
"step": 660
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 9.785185185185185,
|
| 1017 |
+
"grad_norm": 0.07017084956169128,
|
| 1018 |
+
"learning_rate": 3.3927399688948866e-07,
|
| 1019 |
+
"loss": 0.8138,
|
| 1020 |
+
"step": 665
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 9.85925925925926,
|
| 1024 |
+
"grad_norm": 0.07032209634780884,
|
| 1025 |
+
"learning_rate": 0.0,
|
| 1026 |
+
"loss": 0.8191,
|
| 1027 |
+
"step": 670
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 9.85925925925926,
|
| 1031 |
+
"eval_loss": 1.630096197128296,
|
| 1032 |
+
"eval_runtime": 0.8812,
|
| 1033 |
+
"eval_samples_per_second": 4.539,
|
| 1034 |
+
"eval_steps_per_second": 1.135,
|
| 1035 |
+
"step": 670
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 9.85925925925926,
|
| 1039 |
+
"step": 670,
|
| 1040 |
+
"total_flos": 2.9601022627828204e+18,
|
| 1041 |
+
"train_loss": 0.9062140895359552,
|
| 1042 |
+
"train_runtime": 3484.2972,
|
| 1043 |
+
"train_samples_per_second": 49.516,
|
| 1044 |
+
"train_steps_per_second": 0.192
|
| 1045 |
+
}
|
| 1046 |
+
],
|
| 1047 |
+
"logging_steps": 5,
|
| 1048 |
+
"max_steps": 670,
|
| 1049 |
+
"num_input_tokens_seen": 0,
|
| 1050 |
+
"num_train_epochs": 10,
|
| 1051 |
+
"save_steps": 100,
|
| 1052 |
+
"stateful_callbacks": {
|
| 1053 |
+
"TrainerControl": {
|
| 1054 |
+
"args": {
|
| 1055 |
+
"should_epoch_stop": false,
|
| 1056 |
+
"should_evaluate": false,
|
| 1057 |
+
"should_log": false,
|
| 1058 |
+
"should_save": true,
|
| 1059 |
+
"should_training_stop": true
|
| 1060 |
+
},
|
| 1061 |
+
"attributes": {}
|
| 1062 |
+
}
|
| 1063 |
+
},
|
| 1064 |
+
"total_flos": 2.9601022627828204e+18,
|
| 1065 |
+
"train_batch_size": 16,
|
| 1066 |
+
"trial_name": null,
|
| 1067 |
+
"trial_params": null
|
| 1068 |
+
}
|