Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: gemma
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: google/gemma-7b
|
| 9 |
+
datasets:
|
| 10 |
+
- generator
|
| 11 |
+
model-index:
|
| 12 |
+
- name: gemma-7b-sft-qlora-no-robots
|
| 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 |
+
# gemma-7b-sft-qlora-no-robots
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the generator dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 4.2389
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 0.0002
|
| 43 |
+
- train_batch_size: 4
|
| 44 |
+
- eval_batch_size: 4
|
| 45 |
+
- seed: 42
|
| 46 |
+
- distributed_type: multi-GPU
|
| 47 |
+
- num_devices: 4
|
| 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: 50
|
| 55 |
+
|
| 56 |
+
### Training results
|
| 57 |
+
|
| 58 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 59 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 60 |
+
| 17.168 | 1.0 | 3 | 15.0876 |
|
| 61 |
+
| 14.9207 | 2.0 | 6 | 8.7644 |
|
| 62 |
+
| 14.9207 | 3.0 | 9 | 4.8425 |
|
| 63 |
+
| 7.3214 | 4.0 | 12 | 3.0239 |
|
| 64 |
+
| 2.9627 | 5.0 | 15 | 2.2565 |
|
| 65 |
+
| 2.9627 | 6.0 | 18 | 1.8792 |
|
| 66 |
+
| 1.7971 | 7.0 | 21 | 1.7648 |
|
| 67 |
+
| 1.7971 | 8.0 | 24 | 1.7012 |
|
| 68 |
+
| 1.4939 | 9.0 | 27 | 1.5479 |
|
| 69 |
+
| 1.2756 | 10.0 | 30 | 1.5051 |
|
| 70 |
+
| 1.2756 | 11.0 | 33 | 1.3975 |
|
| 71 |
+
| 1.0884 | 12.0 | 36 | 1.4440 |
|
| 72 |
+
| 1.0884 | 13.0 | 39 | 1.4135 |
|
| 73 |
+
| 0.9429 | 14.0 | 42 | 1.4587 |
|
| 74 |
+
| 0.7653 | 15.0 | 45 | 1.4874 |
|
| 75 |
+
| 0.7653 | 16.0 | 48 | 1.5958 |
|
| 76 |
+
| 0.6424 | 17.0 | 51 | 1.5928 |
|
| 77 |
+
| 0.6424 | 18.0 | 54 | 1.6838 |
|
| 78 |
+
| 0.5346 | 19.0 | 57 | 1.8264 |
|
| 79 |
+
| 0.4249 | 20.0 | 60 | 1.9655 |
|
| 80 |
+
| 0.4249 | 21.0 | 63 | 2.1370 |
|
| 81 |
+
| 0.3347 | 22.0 | 66 | 2.6981 |
|
| 82 |
+
| 0.3347 | 23.0 | 69 | 2.7131 |
|
| 83 |
+
| 0.2655 | 24.0 | 72 | 2.7668 |
|
| 84 |
+
| 0.2026 | 25.0 | 75 | 2.8615 |
|
| 85 |
+
| 0.2026 | 26.0 | 78 | 3.1596 |
|
| 86 |
+
| 0.1588 | 27.0 | 81 | 3.3286 |
|
| 87 |
+
| 0.1588 | 28.0 | 84 | 3.5463 |
|
| 88 |
+
| 0.1319 | 29.0 | 87 | 3.3686 |
|
| 89 |
+
| 0.1111 | 30.0 | 90 | 3.6859 |
|
| 90 |
+
| 0.1111 | 31.0 | 93 | 3.7810 |
|
| 91 |
+
| 0.0939 | 32.0 | 96 | 3.7559 |
|
| 92 |
+
| 0.0939 | 33.0 | 99 | 3.9164 |
|
| 93 |
+
| 0.082 | 34.0 | 102 | 3.9693 |
|
| 94 |
+
| 0.0709 | 35.0 | 105 | 4.0430 |
|
| 95 |
+
| 0.0709 | 36.0 | 108 | 4.1017 |
|
| 96 |
+
| 0.0638 | 37.0 | 111 | 4.1449 |
|
| 97 |
+
| 0.0638 | 38.0 | 114 | 4.1639 |
|
| 98 |
+
| 0.0597 | 39.0 | 117 | 4.1880 |
|
| 99 |
+
| 0.0556 | 40.0 | 120 | 4.2123 |
|
| 100 |
+
| 0.0556 | 41.0 | 123 | 4.2196 |
|
| 101 |
+
| 0.0535 | 42.0 | 126 | 4.2262 |
|
| 102 |
+
| 0.0535 | 43.0 | 129 | 4.2301 |
|
| 103 |
+
| 0.0521 | 44.0 | 132 | 4.2314 |
|
| 104 |
+
| 0.0521 | 45.0 | 135 | 4.2365 |
|
| 105 |
+
| 0.0521 | 46.0 | 138 | 4.2350 |
|
| 106 |
+
| 0.0525 | 47.0 | 141 | 4.2364 |
|
| 107 |
+
| 0.0525 | 48.0 | 144 | 4.2320 |
|
| 108 |
+
| 0.0509 | 49.0 | 147 | 4.2361 |
|
| 109 |
+
| 0.0505 | 50.0 | 150 | 4.2389 |
|
| 110 |
+
|
| 111 |
+
|
| 112 |
+
### Framework versions
|
| 113 |
+
|
| 114 |
+
- PEFT 0.7.1
|
| 115 |
+
- Transformers 4.39.0.dev0
|
| 116 |
+
- Pytorch 2.2.2+cu121
|
| 117 |
+
- Datasets 2.14.6
|
| 118 |
+
- Tokenizers 0.15.2
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 100060536
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91039626473e4cb5c0fa03d2c01cc67cc749e62f55112ce48049e7a9d69817ec
|
| 3 |
size 100060536
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"train_loss": 1.2187181319793066,
|
| 4 |
+
"train_runtime": 1336.0597,
|
| 5 |
+
"train_samples": 926,
|
| 6 |
+
"train_samples_per_second": 3.256,
|
| 7 |
+
"train_steps_per_second": 0.112
|
| 8 |
+
}
|
runs/Apr09_02-14-22_deep-diver-main-silent-eagle-1-0-0/events.out.tfevents.1712643385.deep-diver-main-silent-eagle-1-0-0.585.0
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:e44c0e8a00fbb8bd0844082d7cf225f1cf63320795c06f79e37a3394b08d1586
|
| 3 |
+
size 25417
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"train_loss": 1.2187181319793066,
|
| 4 |
+
"train_runtime": 1336.0597,
|
| 5 |
+
"train_samples": 926,
|
| 6 |
+
"train_samples_per_second": 3.256,
|
| 7 |
+
"train_steps_per_second": 0.112
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,647 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 50.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 150,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.33,
|
| 13 |
+
"grad_norm": 74.0,
|
| 14 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 15 |
+
"loss": 17.168,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_loss": 15.087593078613281,
|
| 21 |
+
"eval_runtime": 1.3097,
|
| 22 |
+
"eval_samples_per_second": 1.527,
|
| 23 |
+
"eval_steps_per_second": 0.764,
|
| 24 |
+
"step": 3
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.67,
|
| 28 |
+
"grad_norm": 67.5,
|
| 29 |
+
"learning_rate": 6.666666666666667e-05,
|
| 30 |
+
"loss": 14.9207,
|
| 31 |
+
"step": 5
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 2.0,
|
| 35 |
+
"eval_loss": 8.764444351196289,
|
| 36 |
+
"eval_runtime": 1.3178,
|
| 37 |
+
"eval_samples_per_second": 1.518,
|
| 38 |
+
"eval_steps_per_second": 0.759,
|
| 39 |
+
"step": 6
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 3.0,
|
| 43 |
+
"eval_loss": 4.842519760131836,
|
| 44 |
+
"eval_runtime": 1.321,
|
| 45 |
+
"eval_samples_per_second": 1.514,
|
| 46 |
+
"eval_steps_per_second": 0.757,
|
| 47 |
+
"step": 9
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 3.33,
|
| 51 |
+
"grad_norm": 15.875,
|
| 52 |
+
"learning_rate": 0.00013333333333333334,
|
| 53 |
+
"loss": 7.3214,
|
| 54 |
+
"step": 10
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 4.0,
|
| 58 |
+
"eval_loss": 3.023890495300293,
|
| 59 |
+
"eval_runtime": 1.3205,
|
| 60 |
+
"eval_samples_per_second": 1.515,
|
| 61 |
+
"eval_steps_per_second": 0.757,
|
| 62 |
+
"step": 12
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 5.0,
|
| 66 |
+
"grad_norm": 5.53125,
|
| 67 |
+
"learning_rate": 0.0002,
|
| 68 |
+
"loss": 2.9627,
|
| 69 |
+
"step": 15
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 5.0,
|
| 73 |
+
"eval_loss": 2.256518602371216,
|
| 74 |
+
"eval_runtime": 1.3203,
|
| 75 |
+
"eval_samples_per_second": 1.515,
|
| 76 |
+
"eval_steps_per_second": 0.757,
|
| 77 |
+
"step": 15
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 6.0,
|
| 81 |
+
"eval_loss": 1.8792051076889038,
|
| 82 |
+
"eval_runtime": 1.3249,
|
| 83 |
+
"eval_samples_per_second": 1.51,
|
| 84 |
+
"eval_steps_per_second": 0.755,
|
| 85 |
+
"step": 18
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 6.67,
|
| 89 |
+
"grad_norm": 1.640625,
|
| 90 |
+
"learning_rate": 0.00019932383577419432,
|
| 91 |
+
"loss": 1.7971,
|
| 92 |
+
"step": 20
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 7.0,
|
| 96 |
+
"eval_loss": 1.7647607326507568,
|
| 97 |
+
"eval_runtime": 1.324,
|
| 98 |
+
"eval_samples_per_second": 1.511,
|
| 99 |
+
"eval_steps_per_second": 0.755,
|
| 100 |
+
"step": 21
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 8.0,
|
| 104 |
+
"eval_loss": 1.7012015581130981,
|
| 105 |
+
"eval_runtime": 1.3248,
|
| 106 |
+
"eval_samples_per_second": 1.51,
|
| 107 |
+
"eval_steps_per_second": 0.755,
|
| 108 |
+
"step": 24
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 8.33,
|
| 112 |
+
"grad_norm": 2.234375,
|
| 113 |
+
"learning_rate": 0.00019730448705798239,
|
| 114 |
+
"loss": 1.4939,
|
| 115 |
+
"step": 25
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 9.0,
|
| 119 |
+
"eval_loss": 1.547886610031128,
|
| 120 |
+
"eval_runtime": 1.3259,
|
| 121 |
+
"eval_samples_per_second": 1.508,
|
| 122 |
+
"eval_steps_per_second": 0.754,
|
| 123 |
+
"step": 27
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 10.0,
|
| 127 |
+
"grad_norm": 1.78125,
|
| 128 |
+
"learning_rate": 0.00019396926207859084,
|
| 129 |
+
"loss": 1.2756,
|
| 130 |
+
"step": 30
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 10.0,
|
| 134 |
+
"eval_loss": 1.5050724744796753,
|
| 135 |
+
"eval_runtime": 1.3222,
|
| 136 |
+
"eval_samples_per_second": 1.513,
|
| 137 |
+
"eval_steps_per_second": 0.756,
|
| 138 |
+
"step": 30
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 11.0,
|
| 142 |
+
"eval_loss": 1.3975391387939453,
|
| 143 |
+
"eval_runtime": 1.3256,
|
| 144 |
+
"eval_samples_per_second": 1.509,
|
| 145 |
+
"eval_steps_per_second": 0.754,
|
| 146 |
+
"step": 33
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 11.67,
|
| 150 |
+
"grad_norm": 1.1796875,
|
| 151 |
+
"learning_rate": 0.00018936326403234125,
|
| 152 |
+
"loss": 1.0884,
|
| 153 |
+
"step": 35
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 12.0,
|
| 157 |
+
"eval_loss": 1.444014549255371,
|
| 158 |
+
"eval_runtime": 1.325,
|
| 159 |
+
"eval_samples_per_second": 1.509,
|
| 160 |
+
"eval_steps_per_second": 0.755,
|
| 161 |
+
"step": 36
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 13.0,
|
| 165 |
+
"eval_loss": 1.413475513458252,
|
| 166 |
+
"eval_runtime": 1.3258,
|
| 167 |
+
"eval_samples_per_second": 1.509,
|
| 168 |
+
"eval_steps_per_second": 0.754,
|
| 169 |
+
"step": 39
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 13.33,
|
| 173 |
+
"grad_norm": 1.3046875,
|
| 174 |
+
"learning_rate": 0.00018354878114129367,
|
| 175 |
+
"loss": 0.9429,
|
| 176 |
+
"step": 40
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 14.0,
|
| 180 |
+
"eval_loss": 1.4587093591690063,
|
| 181 |
+
"eval_runtime": 1.3247,
|
| 182 |
+
"eval_samples_per_second": 1.51,
|
| 183 |
+
"eval_steps_per_second": 0.755,
|
| 184 |
+
"step": 42
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 15.0,
|
| 188 |
+
"grad_norm": 2.21875,
|
| 189 |
+
"learning_rate": 0.0001766044443118978,
|
| 190 |
+
"loss": 0.7653,
|
| 191 |
+
"step": 45
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 15.0,
|
| 195 |
+
"eval_loss": 1.487448811531067,
|
| 196 |
+
"eval_runtime": 1.3231,
|
| 197 |
+
"eval_samples_per_second": 1.512,
|
| 198 |
+
"eval_steps_per_second": 0.756,
|
| 199 |
+
"step": 45
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 16.0,
|
| 203 |
+
"eval_loss": 1.5958000421524048,
|
| 204 |
+
"eval_runtime": 1.3242,
|
| 205 |
+
"eval_samples_per_second": 1.51,
|
| 206 |
+
"eval_steps_per_second": 0.755,
|
| 207 |
+
"step": 48
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 16.67,
|
| 211 |
+
"grad_norm": 0.9921875,
|
| 212 |
+
"learning_rate": 0.0001686241637868734,
|
| 213 |
+
"loss": 0.6424,
|
| 214 |
+
"step": 50
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 17.0,
|
| 218 |
+
"eval_loss": 1.592842698097229,
|
| 219 |
+
"eval_runtime": 1.3242,
|
| 220 |
+
"eval_samples_per_second": 1.51,
|
| 221 |
+
"eval_steps_per_second": 0.755,
|
| 222 |
+
"step": 51
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 18.0,
|
| 226 |
+
"eval_loss": 1.683807373046875,
|
| 227 |
+
"eval_runtime": 1.3252,
|
| 228 |
+
"eval_samples_per_second": 1.509,
|
| 229 |
+
"eval_steps_per_second": 0.755,
|
| 230 |
+
"step": 54
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 18.33,
|
| 234 |
+
"grad_norm": 4.78125,
|
| 235 |
+
"learning_rate": 0.00015971585917027862,
|
| 236 |
+
"loss": 0.5346,
|
| 237 |
+
"step": 55
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 19.0,
|
| 241 |
+
"eval_loss": 1.8263951539993286,
|
| 242 |
+
"eval_runtime": 1.3248,
|
| 243 |
+
"eval_samples_per_second": 1.51,
|
| 244 |
+
"eval_steps_per_second": 0.755,
|
| 245 |
+
"step": 57
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 20.0,
|
| 249 |
+
"grad_norm": 0.99609375,
|
| 250 |
+
"learning_rate": 0.00015000000000000001,
|
| 251 |
+
"loss": 0.4249,
|
| 252 |
+
"step": 60
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 20.0,
|
| 256 |
+
"eval_loss": 1.9654637575149536,
|
| 257 |
+
"eval_runtime": 1.3233,
|
| 258 |
+
"eval_samples_per_second": 1.511,
|
| 259 |
+
"eval_steps_per_second": 0.756,
|
| 260 |
+
"step": 60
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 21.0,
|
| 264 |
+
"eval_loss": 2.137000560760498,
|
| 265 |
+
"eval_runtime": 1.3247,
|
| 266 |
+
"eval_samples_per_second": 1.51,
|
| 267 |
+
"eval_steps_per_second": 0.755,
|
| 268 |
+
"step": 63
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 21.67,
|
| 272 |
+
"grad_norm": 1.484375,
|
| 273 |
+
"learning_rate": 0.0001396079766039157,
|
| 274 |
+
"loss": 0.3347,
|
| 275 |
+
"step": 65
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 22.0,
|
| 279 |
+
"eval_loss": 2.698075294494629,
|
| 280 |
+
"eval_runtime": 1.3255,
|
| 281 |
+
"eval_samples_per_second": 1.509,
|
| 282 |
+
"eval_steps_per_second": 0.754,
|
| 283 |
+
"step": 66
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 23.0,
|
| 287 |
+
"eval_loss": 2.713052272796631,
|
| 288 |
+
"eval_runtime": 1.3259,
|
| 289 |
+
"eval_samples_per_second": 1.508,
|
| 290 |
+
"eval_steps_per_second": 0.754,
|
| 291 |
+
"step": 69
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 23.33,
|
| 295 |
+
"grad_norm": 1.71875,
|
| 296 |
+
"learning_rate": 0.00012868032327110904,
|
| 297 |
+
"loss": 0.2655,
|
| 298 |
+
"step": 70
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 24.0,
|
| 302 |
+
"eval_loss": 2.7668490409851074,
|
| 303 |
+
"eval_runtime": 1.3252,
|
| 304 |
+
"eval_samples_per_second": 1.509,
|
| 305 |
+
"eval_steps_per_second": 0.755,
|
| 306 |
+
"step": 72
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 25.0,
|
| 310 |
+
"grad_norm": 0.734375,
|
| 311 |
+
"learning_rate": 0.00011736481776669306,
|
| 312 |
+
"loss": 0.2026,
|
| 313 |
+
"step": 75
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 25.0,
|
| 317 |
+
"eval_loss": 2.8614566326141357,
|
| 318 |
+
"eval_runtime": 1.3226,
|
| 319 |
+
"eval_samples_per_second": 1.512,
|
| 320 |
+
"eval_steps_per_second": 0.756,
|
| 321 |
+
"step": 75
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 26.0,
|
| 325 |
+
"eval_loss": 3.1595633029937744,
|
| 326 |
+
"eval_runtime": 1.3267,
|
| 327 |
+
"eval_samples_per_second": 1.507,
|
| 328 |
+
"eval_steps_per_second": 0.754,
|
| 329 |
+
"step": 78
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 26.67,
|
| 333 |
+
"grad_norm": 0.73828125,
|
| 334 |
+
"learning_rate": 0.00010581448289104758,
|
| 335 |
+
"loss": 0.1588,
|
| 336 |
+
"step": 80
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 27.0,
|
| 340 |
+
"eval_loss": 3.3285796642303467,
|
| 341 |
+
"eval_runtime": 1.3243,
|
| 342 |
+
"eval_samples_per_second": 1.51,
|
| 343 |
+
"eval_steps_per_second": 0.755,
|
| 344 |
+
"step": 81
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 28.0,
|
| 348 |
+
"eval_loss": 3.546278953552246,
|
| 349 |
+
"eval_runtime": 1.3248,
|
| 350 |
+
"eval_samples_per_second": 1.51,
|
| 351 |
+
"eval_steps_per_second": 0.755,
|
| 352 |
+
"step": 84
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 28.33,
|
| 356 |
+
"grad_norm": 1.015625,
|
| 357 |
+
"learning_rate": 9.418551710895243e-05,
|
| 358 |
+
"loss": 0.1319,
|
| 359 |
+
"step": 85
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 29.0,
|
| 363 |
+
"eval_loss": 3.3686463832855225,
|
| 364 |
+
"eval_runtime": 1.3245,
|
| 365 |
+
"eval_samples_per_second": 1.51,
|
| 366 |
+
"eval_steps_per_second": 0.755,
|
| 367 |
+
"step": 87
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 30.0,
|
| 371 |
+
"grad_norm": 0.56640625,
|
| 372 |
+
"learning_rate": 8.263518223330697e-05,
|
| 373 |
+
"loss": 0.1111,
|
| 374 |
+
"step": 90
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 30.0,
|
| 378 |
+
"eval_loss": 3.685863733291626,
|
| 379 |
+
"eval_runtime": 1.3215,
|
| 380 |
+
"eval_samples_per_second": 1.513,
|
| 381 |
+
"eval_steps_per_second": 0.757,
|
| 382 |
+
"step": 90
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 31.0,
|
| 386 |
+
"eval_loss": 3.780993700027466,
|
| 387 |
+
"eval_runtime": 1.3257,
|
| 388 |
+
"eval_samples_per_second": 1.509,
|
| 389 |
+
"eval_steps_per_second": 0.754,
|
| 390 |
+
"step": 93
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 31.67,
|
| 394 |
+
"grad_norm": 0.4375,
|
| 395 |
+
"learning_rate": 7.131967672889101e-05,
|
| 396 |
+
"loss": 0.0939,
|
| 397 |
+
"step": 95
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 32.0,
|
| 401 |
+
"eval_loss": 3.7559256553649902,
|
| 402 |
+
"eval_runtime": 1.3244,
|
| 403 |
+
"eval_samples_per_second": 1.51,
|
| 404 |
+
"eval_steps_per_second": 0.755,
|
| 405 |
+
"step": 96
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 33.0,
|
| 409 |
+
"eval_loss": 3.916355848312378,
|
| 410 |
+
"eval_runtime": 1.3252,
|
| 411 |
+
"eval_samples_per_second": 1.509,
|
| 412 |
+
"eval_steps_per_second": 0.755,
|
| 413 |
+
"step": 99
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 33.33,
|
| 417 |
+
"grad_norm": 0.390625,
|
| 418 |
+
"learning_rate": 6.039202339608432e-05,
|
| 419 |
+
"loss": 0.082,
|
| 420 |
+
"step": 100
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 34.0,
|
| 424 |
+
"eval_loss": 3.9693491458892822,
|
| 425 |
+
"eval_runtime": 1.3217,
|
| 426 |
+
"eval_samples_per_second": 1.513,
|
| 427 |
+
"eval_steps_per_second": 0.757,
|
| 428 |
+
"step": 102
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 35.0,
|
| 432 |
+
"grad_norm": 0.283203125,
|
| 433 |
+
"learning_rate": 5.000000000000002e-05,
|
| 434 |
+
"loss": 0.0709,
|
| 435 |
+
"step": 105
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 35.0,
|
| 439 |
+
"eval_loss": 4.04301118850708,
|
| 440 |
+
"eval_runtime": 1.3186,
|
| 441 |
+
"eval_samples_per_second": 1.517,
|
| 442 |
+
"eval_steps_per_second": 0.758,
|
| 443 |
+
"step": 105
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 36.0,
|
| 447 |
+
"eval_loss": 4.101677417755127,
|
| 448 |
+
"eval_runtime": 1.3238,
|
| 449 |
+
"eval_samples_per_second": 1.511,
|
| 450 |
+
"eval_steps_per_second": 0.755,
|
| 451 |
+
"step": 108
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 36.67,
|
| 455 |
+
"grad_norm": 0.27734375,
|
| 456 |
+
"learning_rate": 4.028414082972141e-05,
|
| 457 |
+
"loss": 0.0638,
|
| 458 |
+
"step": 110
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 37.0,
|
| 462 |
+
"eval_loss": 4.144949913024902,
|
| 463 |
+
"eval_runtime": 1.3248,
|
| 464 |
+
"eval_samples_per_second": 1.51,
|
| 465 |
+
"eval_steps_per_second": 0.755,
|
| 466 |
+
"step": 111
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 38.0,
|
| 470 |
+
"eval_loss": 4.1638994216918945,
|
| 471 |
+
"eval_runtime": 1.3218,
|
| 472 |
+
"eval_samples_per_second": 1.513,
|
| 473 |
+
"eval_steps_per_second": 0.757,
|
| 474 |
+
"step": 114
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 38.33,
|
| 478 |
+
"grad_norm": 0.3125,
|
| 479 |
+
"learning_rate": 3.137583621312665e-05,
|
| 480 |
+
"loss": 0.0597,
|
| 481 |
+
"step": 115
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 39.0,
|
| 485 |
+
"eval_loss": 4.187974452972412,
|
| 486 |
+
"eval_runtime": 1.3246,
|
| 487 |
+
"eval_samples_per_second": 1.51,
|
| 488 |
+
"eval_steps_per_second": 0.755,
|
| 489 |
+
"step": 117
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 40.0,
|
| 493 |
+
"grad_norm": 0.318359375,
|
| 494 |
+
"learning_rate": 2.339555568810221e-05,
|
| 495 |
+
"loss": 0.0556,
|
| 496 |
+
"step": 120
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 40.0,
|
| 500 |
+
"eval_loss": 4.212304592132568,
|
| 501 |
+
"eval_runtime": 1.3229,
|
| 502 |
+
"eval_samples_per_second": 1.512,
|
| 503 |
+
"eval_steps_per_second": 0.756,
|
| 504 |
+
"step": 120
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 41.0,
|
| 508 |
+
"eval_loss": 4.219560623168945,
|
| 509 |
+
"eval_runtime": 1.3269,
|
| 510 |
+
"eval_samples_per_second": 1.507,
|
| 511 |
+
"eval_steps_per_second": 0.754,
|
| 512 |
+
"step": 123
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 41.67,
|
| 516 |
+
"grad_norm": 0.201171875,
|
| 517 |
+
"learning_rate": 1.6451218858706374e-05,
|
| 518 |
+
"loss": 0.0535,
|
| 519 |
+
"step": 125
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 42.0,
|
| 523 |
+
"eval_loss": 4.226192951202393,
|
| 524 |
+
"eval_runtime": 1.3243,
|
| 525 |
+
"eval_samples_per_second": 1.51,
|
| 526 |
+
"eval_steps_per_second": 0.755,
|
| 527 |
+
"step": 126
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 43.0,
|
| 531 |
+
"eval_loss": 4.230067729949951,
|
| 532 |
+
"eval_runtime": 1.3252,
|
| 533 |
+
"eval_samples_per_second": 1.509,
|
| 534 |
+
"eval_steps_per_second": 0.755,
|
| 535 |
+
"step": 129
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 43.33,
|
| 539 |
+
"grad_norm": 0.2490234375,
|
| 540 |
+
"learning_rate": 1.0636735967658784e-05,
|
| 541 |
+
"loss": 0.0521,
|
| 542 |
+
"step": 130
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 44.0,
|
| 546 |
+
"eval_loss": 4.231449604034424,
|
| 547 |
+
"eval_runtime": 1.3262,
|
| 548 |
+
"eval_samples_per_second": 1.508,
|
| 549 |
+
"eval_steps_per_second": 0.754,
|
| 550 |
+
"step": 132
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 45.0,
|
| 554 |
+
"grad_norm": 0.10986328125,
|
| 555 |
+
"learning_rate": 6.030737921409169e-06,
|
| 556 |
+
"loss": 0.0521,
|
| 557 |
+
"step": 135
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 45.0,
|
| 561 |
+
"eval_loss": 4.2365241050720215,
|
| 562 |
+
"eval_runtime": 1.3238,
|
| 563 |
+
"eval_samples_per_second": 1.511,
|
| 564 |
+
"eval_steps_per_second": 0.755,
|
| 565 |
+
"step": 135
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 46.0,
|
| 569 |
+
"eval_loss": 4.234958171844482,
|
| 570 |
+
"eval_runtime": 1.3255,
|
| 571 |
+
"eval_samples_per_second": 1.509,
|
| 572 |
+
"eval_steps_per_second": 0.754,
|
| 573 |
+
"step": 138
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 46.67,
|
| 577 |
+
"grad_norm": 0.12451171875,
|
| 578 |
+
"learning_rate": 2.6955129420176196e-06,
|
| 579 |
+
"loss": 0.0525,
|
| 580 |
+
"step": 140
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 47.0,
|
| 584 |
+
"eval_loss": 4.236445426940918,
|
| 585 |
+
"eval_runtime": 1.3261,
|
| 586 |
+
"eval_samples_per_second": 1.508,
|
| 587 |
+
"eval_steps_per_second": 0.754,
|
| 588 |
+
"step": 141
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 48.0,
|
| 592 |
+
"eval_loss": 4.231955051422119,
|
| 593 |
+
"eval_runtime": 1.3237,
|
| 594 |
+
"eval_samples_per_second": 1.511,
|
| 595 |
+
"eval_steps_per_second": 0.755,
|
| 596 |
+
"step": 144
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 48.33,
|
| 600 |
+
"grad_norm": 0.1357421875,
|
| 601 |
+
"learning_rate": 6.761642258056978e-07,
|
| 602 |
+
"loss": 0.0509,
|
| 603 |
+
"step": 145
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 49.0,
|
| 607 |
+
"eval_loss": 4.236112594604492,
|
| 608 |
+
"eval_runtime": 1.3264,
|
| 609 |
+
"eval_samples_per_second": 1.508,
|
| 610 |
+
"eval_steps_per_second": 0.754,
|
| 611 |
+
"step": 147
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 50.0,
|
| 615 |
+
"grad_norm": 0.09326171875,
|
| 616 |
+
"learning_rate": 0.0,
|
| 617 |
+
"loss": 0.0505,
|
| 618 |
+
"step": 150
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 50.0,
|
| 622 |
+
"eval_loss": 4.238922595977783,
|
| 623 |
+
"eval_runtime": 1.3223,
|
| 624 |
+
"eval_samples_per_second": 1.513,
|
| 625 |
+
"eval_steps_per_second": 0.756,
|
| 626 |
+
"step": 150
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 50.0,
|
| 630 |
+
"step": 150,
|
| 631 |
+
"total_flos": 4.601366279314473e+17,
|
| 632 |
+
"train_loss": 1.2187181319793066,
|
| 633 |
+
"train_runtime": 1336.0597,
|
| 634 |
+
"train_samples_per_second": 3.256,
|
| 635 |
+
"train_steps_per_second": 0.112
|
| 636 |
+
}
|
| 637 |
+
],
|
| 638 |
+
"logging_steps": 5,
|
| 639 |
+
"max_steps": 150,
|
| 640 |
+
"num_input_tokens_seen": 0,
|
| 641 |
+
"num_train_epochs": 50,
|
| 642 |
+
"save_steps": 100,
|
| 643 |
+
"total_flos": 4.601366279314473e+17,
|
| 644 |
+
"train_batch_size": 4,
|
| 645 |
+
"trial_name": null,
|
| 646 |
+
"trial_params": null
|
| 647 |
+
}
|