Commit
•
02a742a
1
Parent(s):
b1b44f7
Model save
Browse files- README.md +129 -0
- adapter_model.safetensors +1 -1
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +1824 -0
README.md
ADDED
|
@@ -0,0 +1,129 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: llama3.1
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: Llama-31-8B_task-1_120-samples_config-4_full
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# Llama-31-8B_task-1_120-samples_config-4_full
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.9120
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 1e-05
|
| 41 |
+
- train_batch_size: 1
|
| 42 |
+
- eval_batch_size: 1
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- gradient_accumulation_steps: 16
|
| 46 |
+
- total_train_batch_size: 16
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
+
- num_epochs: 150
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:-------:|:----:|:---------------:|
|
| 56 |
+
| 2.4687 | 0.9091 | 5 | 2.4589 |
|
| 57 |
+
| 2.5083 | 2.0 | 11 | 2.4440 |
|
| 58 |
+
| 2.4676 | 2.9091 | 16 | 2.4218 |
|
| 59 |
+
| 2.4562 | 4.0 | 22 | 2.3870 |
|
| 60 |
+
| 2.377 | 4.9091 | 27 | 2.3475 |
|
| 61 |
+
| 2.3303 | 6.0 | 33 | 2.2793 |
|
| 62 |
+
| 2.2553 | 6.9091 | 38 | 2.2254 |
|
| 63 |
+
| 2.174 | 8.0 | 44 | 2.1392 |
|
| 64 |
+
| 2.131 | 8.9091 | 49 | 2.0661 |
|
| 65 |
+
| 2.0142 | 10.0 | 55 | 1.9626 |
|
| 66 |
+
| 1.8873 | 10.9091 | 60 | 1.8746 |
|
| 67 |
+
| 1.7633 | 12.0 | 66 | 1.7650 |
|
| 68 |
+
| 1.726 | 12.9091 | 71 | 1.6563 |
|
| 69 |
+
| 1.5711 | 14.0 | 77 | 1.5123 |
|
| 70 |
+
| 1.4344 | 14.9091 | 82 | 1.3950 |
|
| 71 |
+
| 1.3201 | 16.0 | 88 | 1.2661 |
|
| 72 |
+
| 1.1787 | 16.9091 | 93 | 1.1831 |
|
| 73 |
+
| 1.1444 | 18.0 | 99 | 1.1188 |
|
| 74 |
+
| 1.0591 | 18.9091 | 104 | 1.0836 |
|
| 75 |
+
| 1.0151 | 20.0 | 110 | 1.0540 |
|
| 76 |
+
| 1.0277 | 20.9091 | 115 | 1.0388 |
|
| 77 |
+
| 1.0025 | 22.0 | 121 | 1.0250 |
|
| 78 |
+
| 1.0161 | 22.9091 | 126 | 1.0154 |
|
| 79 |
+
| 0.9946 | 24.0 | 132 | 1.0047 |
|
| 80 |
+
| 0.9773 | 24.9091 | 137 | 0.9970 |
|
| 81 |
+
| 0.9708 | 26.0 | 143 | 0.9890 |
|
| 82 |
+
| 0.9374 | 26.9091 | 148 | 0.9822 |
|
| 83 |
+
| 0.9403 | 28.0 | 154 | 0.9751 |
|
| 84 |
+
| 0.94 | 28.9091 | 159 | 0.9703 |
|
| 85 |
+
| 0.902 | 30.0 | 165 | 0.9633 |
|
| 86 |
+
| 0.9215 | 30.9091 | 170 | 0.9604 |
|
| 87 |
+
| 0.8854 | 32.0 | 176 | 0.9548 |
|
| 88 |
+
| 0.96 | 32.9091 | 181 | 0.9503 |
|
| 89 |
+
| 0.9162 | 34.0 | 187 | 0.9453 |
|
| 90 |
+
| 0.8686 | 34.9091 | 192 | 0.9429 |
|
| 91 |
+
| 0.906 | 36.0 | 198 | 0.9385 |
|
| 92 |
+
| 0.8762 | 36.9091 | 203 | 0.9354 |
|
| 93 |
+
| 0.8929 | 38.0 | 209 | 0.9332 |
|
| 94 |
+
| 0.8687 | 38.9091 | 214 | 0.9301 |
|
| 95 |
+
| 0.8933 | 40.0 | 220 | 0.9279 |
|
| 96 |
+
| 0.858 | 40.9091 | 225 | 0.9241 |
|
| 97 |
+
| 0.8481 | 42.0 | 231 | 0.9223 |
|
| 98 |
+
| 0.8228 | 42.9091 | 236 | 0.9217 |
|
| 99 |
+
| 0.8593 | 44.0 | 242 | 0.9186 |
|
| 100 |
+
| 0.8238 | 44.9091 | 247 | 0.9156 |
|
| 101 |
+
| 0.8081 | 46.0 | 253 | 0.9161 |
|
| 102 |
+
| 0.8327 | 46.9091 | 258 | 0.9129 |
|
| 103 |
+
| 0.8029 | 48.0 | 264 | 0.9110 |
|
| 104 |
+
| 0.7909 | 48.9091 | 269 | 0.9094 |
|
| 105 |
+
| 0.7826 | 50.0 | 275 | 0.9079 |
|
| 106 |
+
| 0.773 | 50.9091 | 280 | 0.9122 |
|
| 107 |
+
| 0.7377 | 52.0 | 286 | 0.9078 |
|
| 108 |
+
| 0.7491 | 52.9091 | 291 | 0.9050 |
|
| 109 |
+
| 0.7414 | 54.0 | 297 | 0.9093 |
|
| 110 |
+
| 0.7275 | 54.9091 | 302 | 0.9053 |
|
| 111 |
+
| 0.7198 | 56.0 | 308 | 0.9046 |
|
| 112 |
+
| 0.7203 | 56.9091 | 313 | 0.9093 |
|
| 113 |
+
| 0.6903 | 58.0 | 319 | 0.9042 |
|
| 114 |
+
| 0.6987 | 58.9091 | 324 | 0.9107 |
|
| 115 |
+
| 0.7141 | 60.0 | 330 | 0.9079 |
|
| 116 |
+
| 0.7023 | 60.9091 | 335 | 0.9120 |
|
| 117 |
+
| 0.6945 | 62.0 | 341 | 0.9087 |
|
| 118 |
+
| 0.6897 | 62.9091 | 346 | 0.9130 |
|
| 119 |
+
| 0.6597 | 64.0 | 352 | 0.9134 |
|
| 120 |
+
| 0.6954 | 64.9091 | 357 | 0.9120 |
|
| 121 |
+
|
| 122 |
+
|
| 123 |
+
### Framework versions
|
| 124 |
+
|
| 125 |
+
- PEFT 0.12.0
|
| 126 |
+
- Transformers 4.44.0
|
| 127 |
+
- Pytorch 2.1.2+cu121
|
| 128 |
+
- Datasets 2.20.0
|
| 129 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 167832240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18024a4767336de1643bc9edfa5aad95937302833f3d2ca2ce9e421fc6d34208
|
| 3 |
size 167832240
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 64.9090909090909,
|
| 3 |
+
"total_flos": 8.780093794235187e+16,
|
| 4 |
+
"train_loss": 1.1563805774146436,
|
| 5 |
+
"train_runtime": 6696.4639,
|
| 6 |
+
"train_samples": 88,
|
| 7 |
+
"train_samples_per_second": 1.971,
|
| 8 |
+
"train_steps_per_second": 0.112
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 64.9090909090909,
|
| 3 |
+
"total_flos": 8.780093794235187e+16,
|
| 4 |
+
"train_loss": 1.1563805774146436,
|
| 5 |
+
"train_runtime": 6696.4639,
|
| 6 |
+
"train_samples": 88,
|
| 7 |
+
"train_samples_per_second": 1.971,
|
| 8 |
+
"train_steps_per_second": 0.112
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1824 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9042022824287415,
|
| 3 |
+
"best_model_checkpoint": "data/Llama-31-8B_task-1_120-samples_config-4_full/checkpoint-319",
|
| 4 |
+
"epoch": 64.9090909090909,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 357,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.18181818181818182,
|
| 13 |
+
"grad_norm": 1.9413753747940063,
|
| 14 |
+
"learning_rate": 1.3333333333333336e-07,
|
| 15 |
+
"loss": 2.4963,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.36363636363636365,
|
| 20 |
+
"grad_norm": 1.9993785619735718,
|
| 21 |
+
"learning_rate": 2.666666666666667e-07,
|
| 22 |
+
"loss": 2.515,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.7272727272727273,
|
| 27 |
+
"grad_norm": 1.8845915794372559,
|
| 28 |
+
"learning_rate": 5.333333333333335e-07,
|
| 29 |
+
"loss": 2.4687,
|
| 30 |
+
"step": 4
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.9090909090909091,
|
| 34 |
+
"eval_loss": 2.458869218826294,
|
| 35 |
+
"eval_runtime": 9.6295,
|
| 36 |
+
"eval_samples_per_second": 2.492,
|
| 37 |
+
"eval_steps_per_second": 2.492,
|
| 38 |
+
"step": 5
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.0909090909090908,
|
| 42 |
+
"grad_norm": 2.0253942012786865,
|
| 43 |
+
"learning_rate": 8.000000000000001e-07,
|
| 44 |
+
"loss": 2.4759,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.4545454545454546,
|
| 49 |
+
"grad_norm": 1.8723983764648438,
|
| 50 |
+
"learning_rate": 1.066666666666667e-06,
|
| 51 |
+
"loss": 2.4786,
|
| 52 |
+
"step": 8
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.8181818181818183,
|
| 56 |
+
"grad_norm": 1.924127459526062,
|
| 57 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 58 |
+
"loss": 2.5083,
|
| 59 |
+
"step": 10
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 2.0,
|
| 63 |
+
"eval_loss": 2.443969488143921,
|
| 64 |
+
"eval_runtime": 9.6222,
|
| 65 |
+
"eval_samples_per_second": 2.494,
|
| 66 |
+
"eval_steps_per_second": 2.494,
|
| 67 |
+
"step": 11
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 2.1818181818181817,
|
| 71 |
+
"grad_norm": 1.7455520629882812,
|
| 72 |
+
"learning_rate": 1.6000000000000001e-06,
|
| 73 |
+
"loss": 2.4117,
|
| 74 |
+
"step": 12
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.5454545454545454,
|
| 78 |
+
"grad_norm": 1.710787296295166,
|
| 79 |
+
"learning_rate": 1.8666666666666669e-06,
|
| 80 |
+
"loss": 2.4583,
|
| 81 |
+
"step": 14
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.909090909090909,
|
| 85 |
+
"grad_norm": 1.6907106637954712,
|
| 86 |
+
"learning_rate": 2.133333333333334e-06,
|
| 87 |
+
"loss": 2.4676,
|
| 88 |
+
"step": 16
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 2.909090909090909,
|
| 92 |
+
"eval_loss": 2.421785593032837,
|
| 93 |
+
"eval_runtime": 9.6333,
|
| 94 |
+
"eval_samples_per_second": 2.491,
|
| 95 |
+
"eval_steps_per_second": 2.491,
|
| 96 |
+
"step": 16
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 3.2727272727272725,
|
| 100 |
+
"grad_norm": 1.5824416875839233,
|
| 101 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 102 |
+
"loss": 2.4237,
|
| 103 |
+
"step": 18
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 3.6363636363636362,
|
| 107 |
+
"grad_norm": 1.59761643409729,
|
| 108 |
+
"learning_rate": 2.666666666666667e-06,
|
| 109 |
+
"loss": 2.4148,
|
| 110 |
+
"step": 20
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 4.0,
|
| 114 |
+
"grad_norm": 1.6097276210784912,
|
| 115 |
+
"learning_rate": 2.9333333333333338e-06,
|
| 116 |
+
"loss": 2.4562,
|
| 117 |
+
"step": 22
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 4.0,
|
| 121 |
+
"eval_loss": 2.3870151042938232,
|
| 122 |
+
"eval_runtime": 9.6315,
|
| 123 |
+
"eval_samples_per_second": 2.492,
|
| 124 |
+
"eval_steps_per_second": 2.492,
|
| 125 |
+
"step": 22
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 4.363636363636363,
|
| 129 |
+
"grad_norm": 1.636257529258728,
|
| 130 |
+
"learning_rate": 3.2000000000000003e-06,
|
| 131 |
+
"loss": 2.4287,
|
| 132 |
+
"step": 24
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 4.7272727272727275,
|
| 136 |
+
"grad_norm": 1.5569593906402588,
|
| 137 |
+
"learning_rate": 3.4666666666666672e-06,
|
| 138 |
+
"loss": 2.377,
|
| 139 |
+
"step": 26
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 4.909090909090909,
|
| 143 |
+
"eval_loss": 2.3474807739257812,
|
| 144 |
+
"eval_runtime": 9.6237,
|
| 145 |
+
"eval_samples_per_second": 2.494,
|
| 146 |
+
"eval_steps_per_second": 2.494,
|
| 147 |
+
"step": 27
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 5.090909090909091,
|
| 151 |
+
"grad_norm": 1.808140516281128,
|
| 152 |
+
"learning_rate": 3.7333333333333337e-06,
|
| 153 |
+
"loss": 2.3605,
|
| 154 |
+
"step": 28
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 5.454545454545454,
|
| 158 |
+
"grad_norm": 1.7729766368865967,
|
| 159 |
+
"learning_rate": 4.000000000000001e-06,
|
| 160 |
+
"loss": 2.3404,
|
| 161 |
+
"step": 30
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 5.818181818181818,
|
| 165 |
+
"grad_norm": 1.9055501222610474,
|
| 166 |
+
"learning_rate": 4.266666666666668e-06,
|
| 167 |
+
"loss": 2.3303,
|
| 168 |
+
"step": 32
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 6.0,
|
| 172 |
+
"eval_loss": 2.2793145179748535,
|
| 173 |
+
"eval_runtime": 9.6178,
|
| 174 |
+
"eval_samples_per_second": 2.495,
|
| 175 |
+
"eval_steps_per_second": 2.495,
|
| 176 |
+
"step": 33
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 6.181818181818182,
|
| 180 |
+
"grad_norm": 1.628233790397644,
|
| 181 |
+
"learning_rate": 4.533333333333334e-06,
|
| 182 |
+
"loss": 2.2739,
|
| 183 |
+
"step": 34
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 6.545454545454545,
|
| 187 |
+
"grad_norm": 1.4241219758987427,
|
| 188 |
+
"learning_rate": 4.800000000000001e-06,
|
| 189 |
+
"loss": 2.3294,
|
| 190 |
+
"step": 36
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 6.909090909090909,
|
| 194 |
+
"grad_norm": 1.5400785207748413,
|
| 195 |
+
"learning_rate": 5.0666666666666676e-06,
|
| 196 |
+
"loss": 2.2553,
|
| 197 |
+
"step": 38
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 6.909090909090909,
|
| 201 |
+
"eval_loss": 2.2254207134246826,
|
| 202 |
+
"eval_runtime": 9.6211,
|
| 203 |
+
"eval_samples_per_second": 2.495,
|
| 204 |
+
"eval_steps_per_second": 2.495,
|
| 205 |
+
"step": 38
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 7.2727272727272725,
|
| 209 |
+
"grad_norm": 1.4445594549179077,
|
| 210 |
+
"learning_rate": 5.333333333333334e-06,
|
| 211 |
+
"loss": 2.2498,
|
| 212 |
+
"step": 40
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 7.636363636363637,
|
| 216 |
+
"grad_norm": 1.7270216941833496,
|
| 217 |
+
"learning_rate": 5.600000000000001e-06,
|
| 218 |
+
"loss": 2.1853,
|
| 219 |
+
"step": 42
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 8.0,
|
| 223 |
+
"grad_norm": 2.017972707748413,
|
| 224 |
+
"learning_rate": 5.8666666666666675e-06,
|
| 225 |
+
"loss": 2.174,
|
| 226 |
+
"step": 44
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 8.0,
|
| 230 |
+
"eval_loss": 2.139225721359253,
|
| 231 |
+
"eval_runtime": 9.6197,
|
| 232 |
+
"eval_samples_per_second": 2.495,
|
| 233 |
+
"eval_steps_per_second": 2.495,
|
| 234 |
+
"step": 44
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 8.363636363636363,
|
| 238 |
+
"grad_norm": 1.3301095962524414,
|
| 239 |
+
"learning_rate": 6.133333333333334e-06,
|
| 240 |
+
"loss": 2.1429,
|
| 241 |
+
"step": 46
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 8.727272727272727,
|
| 245 |
+
"grad_norm": 1.083661675453186,
|
| 246 |
+
"learning_rate": 6.4000000000000006e-06,
|
| 247 |
+
"loss": 2.131,
|
| 248 |
+
"step": 48
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 8.909090909090908,
|
| 252 |
+
"eval_loss": 2.0661048889160156,
|
| 253 |
+
"eval_runtime": 9.6328,
|
| 254 |
+
"eval_samples_per_second": 2.491,
|
| 255 |
+
"eval_steps_per_second": 2.491,
|
| 256 |
+
"step": 49
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 9.090909090909092,
|
| 260 |
+
"grad_norm": 1.0499473810195923,
|
| 261 |
+
"learning_rate": 6.666666666666667e-06,
|
| 262 |
+
"loss": 2.0813,
|
| 263 |
+
"step": 50
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 9.454545454545455,
|
| 267 |
+
"grad_norm": 1.014916181564331,
|
| 268 |
+
"learning_rate": 6.9333333333333344e-06,
|
| 269 |
+
"loss": 2.0497,
|
| 270 |
+
"step": 52
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 9.818181818181818,
|
| 274 |
+
"grad_norm": 1.0278065204620361,
|
| 275 |
+
"learning_rate": 7.2000000000000005e-06,
|
| 276 |
+
"loss": 2.0142,
|
| 277 |
+
"step": 54
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 10.0,
|
| 281 |
+
"eval_loss": 1.9625515937805176,
|
| 282 |
+
"eval_runtime": 9.6185,
|
| 283 |
+
"eval_samples_per_second": 2.495,
|
| 284 |
+
"eval_steps_per_second": 2.495,
|
| 285 |
+
"step": 55
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 10.181818181818182,
|
| 289 |
+
"grad_norm": 0.9720411896705627,
|
| 290 |
+
"learning_rate": 7.4666666666666675e-06,
|
| 291 |
+
"loss": 1.9759,
|
| 292 |
+
"step": 56
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 10.545454545454545,
|
| 296 |
+
"grad_norm": 0.9346638321876526,
|
| 297 |
+
"learning_rate": 7.733333333333334e-06,
|
| 298 |
+
"loss": 1.941,
|
| 299 |
+
"step": 58
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 10.909090909090908,
|
| 303 |
+
"grad_norm": 0.8559221029281616,
|
| 304 |
+
"learning_rate": 8.000000000000001e-06,
|
| 305 |
+
"loss": 1.8873,
|
| 306 |
+
"step": 60
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 10.909090909090908,
|
| 310 |
+
"eval_loss": 1.8745914697647095,
|
| 311 |
+
"eval_runtime": 9.6239,
|
| 312 |
+
"eval_samples_per_second": 2.494,
|
| 313 |
+
"eval_steps_per_second": 2.494,
|
| 314 |
+
"step": 60
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 11.272727272727273,
|
| 318 |
+
"grad_norm": 0.8817884922027588,
|
| 319 |
+
"learning_rate": 8.266666666666667e-06,
|
| 320 |
+
"loss": 1.9132,
|
| 321 |
+
"step": 62
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 11.636363636363637,
|
| 325 |
+
"grad_norm": 0.8232048749923706,
|
| 326 |
+
"learning_rate": 8.533333333333335e-06,
|
| 327 |
+
"loss": 1.8387,
|
| 328 |
+
"step": 64
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 12.0,
|
| 332 |
+
"grad_norm": 0.8017051815986633,
|
| 333 |
+
"learning_rate": 8.8e-06,
|
| 334 |
+
"loss": 1.7633,
|
| 335 |
+
"step": 66
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 12.0,
|
| 339 |
+
"eval_loss": 1.7650254964828491,
|
| 340 |
+
"eval_runtime": 9.6208,
|
| 341 |
+
"eval_samples_per_second": 2.495,
|
| 342 |
+
"eval_steps_per_second": 2.495,
|
| 343 |
+
"step": 66
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 12.363636363636363,
|
| 347 |
+
"grad_norm": 0.9119341373443604,
|
| 348 |
+
"learning_rate": 9.066666666666667e-06,
|
| 349 |
+
"loss": 1.72,
|
| 350 |
+
"step": 68
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 12.727272727272727,
|
| 354 |
+
"grad_norm": 0.8771039843559265,
|
| 355 |
+
"learning_rate": 9.333333333333334e-06,
|
| 356 |
+
"loss": 1.726,
|
| 357 |
+
"step": 70
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 12.909090909090908,
|
| 361 |
+
"eval_loss": 1.6562695503234863,
|
| 362 |
+
"eval_runtime": 9.6212,
|
| 363 |
+
"eval_samples_per_second": 2.494,
|
| 364 |
+
"eval_steps_per_second": 2.494,
|
| 365 |
+
"step": 71
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 13.090909090909092,
|
| 369 |
+
"grad_norm": 0.9313778877258301,
|
| 370 |
+
"learning_rate": 9.600000000000001e-06,
|
| 371 |
+
"loss": 1.6816,
|
| 372 |
+
"step": 72
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 13.454545454545455,
|
| 376 |
+
"grad_norm": 1.1438463926315308,
|
| 377 |
+
"learning_rate": 9.866666666666668e-06,
|
| 378 |
+
"loss": 1.6168,
|
| 379 |
+
"step": 74
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 13.818181818181818,
|
| 383 |
+
"grad_norm": 1.0701647996902466,
|
| 384 |
+
"learning_rate": 9.999945845889795e-06,
|
| 385 |
+
"loss": 1.5711,
|
| 386 |
+
"step": 76
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 14.0,
|
| 390 |
+
"eval_loss": 1.5122851133346558,
|
| 391 |
+
"eval_runtime": 9.627,
|
| 392 |
+
"eval_samples_per_second": 2.493,
|
| 393 |
+
"eval_steps_per_second": 2.493,
|
| 394 |
+
"step": 77
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 14.181818181818182,
|
| 398 |
+
"grad_norm": 0.9771044254302979,
|
| 399 |
+
"learning_rate": 9.999512620046523e-06,
|
| 400 |
+
"loss": 1.5488,
|
| 401 |
+
"step": 78
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 14.545454545454545,
|
| 405 |
+
"grad_norm": 0.91764235496521,
|
| 406 |
+
"learning_rate": 9.99864620589731e-06,
|
| 407 |
+
"loss": 1.4504,
|
| 408 |
+
"step": 80
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 14.909090909090908,
|
| 412 |
+
"grad_norm": 0.9226170182228088,
|
| 413 |
+
"learning_rate": 9.99734667851357e-06,
|
| 414 |
+
"loss": 1.4344,
|
| 415 |
+
"step": 82
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 14.909090909090908,
|
| 419 |
+
"eval_loss": 1.3950275182724,
|
| 420 |
+
"eval_runtime": 9.6306,
|
| 421 |
+
"eval_samples_per_second": 2.492,
|
| 422 |
+
"eval_steps_per_second": 2.492,
|
| 423 |
+
"step": 82
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 15.272727272727273,
|
| 427 |
+
"grad_norm": 0.8576654195785522,
|
| 428 |
+
"learning_rate": 9.995614150494293e-06,
|
| 429 |
+
"loss": 1.3568,
|
| 430 |
+
"step": 84
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 15.636363636363637,
|
| 434 |
+
"grad_norm": 0.9888388514518738,
|
| 435 |
+
"learning_rate": 9.993448771956285e-06,
|
| 436 |
+
"loss": 1.3195,
|
| 437 |
+
"step": 86
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 16.0,
|
| 441 |
+
"grad_norm": 0.9264158010482788,
|
| 442 |
+
"learning_rate": 9.99085073052117e-06,
|
| 443 |
+
"loss": 1.3201,
|
| 444 |
+
"step": 88
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 16.0,
|
| 448 |
+
"eval_loss": 1.2661280632019043,
|
| 449 |
+
"eval_runtime": 9.6187,
|
| 450 |
+
"eval_samples_per_second": 2.495,
|
| 451 |
+
"eval_steps_per_second": 2.495,
|
| 452 |
+
"step": 88
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 16.363636363636363,
|
| 456 |
+
"grad_norm": 0.8193872570991516,
|
| 457 |
+
"learning_rate": 9.987820251299121e-06,
|
| 458 |
+
"loss": 1.2496,
|
| 459 |
+
"step": 90
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 16.727272727272727,
|
| 463 |
+
"grad_norm": 0.7646848559379578,
|
| 464 |
+
"learning_rate": 9.984357596869369e-06,
|
| 465 |
+
"loss": 1.1787,
|
| 466 |
+
"step": 92
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 16.90909090909091,
|
| 470 |
+
"eval_loss": 1.18313729763031,
|
| 471 |
+
"eval_runtime": 9.6587,
|
| 472 |
+
"eval_samples_per_second": 2.485,
|
| 473 |
+
"eval_steps_per_second": 2.485,
|
| 474 |
+
"step": 93
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 17.09090909090909,
|
| 478 |
+
"grad_norm": 0.7123040556907654,
|
| 479 |
+
"learning_rate": 9.980463067257437e-06,
|
| 480 |
+
"loss": 1.2232,
|
| 481 |
+
"step": 94
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 17.454545454545453,
|
| 485 |
+
"grad_norm": 0.6257199645042419,
|
| 486 |
+
"learning_rate": 9.976136999909156e-06,
|
| 487 |
+
"loss": 1.1068,
|
| 488 |
+
"step": 96
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 17.818181818181817,
|
| 492 |
+
"grad_norm": 0.7334635257720947,
|
| 493 |
+
"learning_rate": 9.971379769661422e-06,
|
| 494 |
+
"loss": 1.1444,
|
| 495 |
+
"step": 98
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 18.0,
|
| 499 |
+
"eval_loss": 1.1187793016433716,
|
| 500 |
+
"eval_runtime": 9.6189,
|
| 501 |
+
"eval_samples_per_second": 2.495,
|
| 502 |
+
"eval_steps_per_second": 2.495,
|
| 503 |
+
"step": 99
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 18.181818181818183,
|
| 507 |
+
"grad_norm": 0.589821457862854,
|
| 508 |
+
"learning_rate": 9.966191788709716e-06,
|
| 509 |
+
"loss": 1.1334,
|
| 510 |
+
"step": 100
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 18.545454545454547,
|
| 514 |
+
"grad_norm": 0.5560262799263,
|
| 515 |
+
"learning_rate": 9.960573506572391e-06,
|
| 516 |
+
"loss": 1.0929,
|
| 517 |
+
"step": 102
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 18.90909090909091,
|
| 521 |
+
"grad_norm": 0.5528337359428406,
|
| 522 |
+
"learning_rate": 9.95452541005172e-06,
|
| 523 |
+
"loss": 1.0591,
|
| 524 |
+
"step": 104
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 18.90909090909091,
|
| 528 |
+
"eval_loss": 1.0836217403411865,
|
| 529 |
+
"eval_runtime": 9.632,
|
| 530 |
+
"eval_samples_per_second": 2.492,
|
| 531 |
+
"eval_steps_per_second": 2.492,
|
| 532 |
+
"step": 104
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 19.272727272727273,
|
| 536 |
+
"grad_norm": 0.5791244506835938,
|
| 537 |
+
"learning_rate": 9.948048023191728e-06,
|
| 538 |
+
"loss": 1.0522,
|
| 539 |
+
"step": 106
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 19.636363636363637,
|
| 543 |
+
"grad_norm": 0.5012540817260742,
|
| 544 |
+
"learning_rate": 9.941141907232766e-06,
|
| 545 |
+
"loss": 1.0986,
|
| 546 |
+
"step": 108
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 20.0,
|
| 550 |
+
"grad_norm": 0.4489583969116211,
|
| 551 |
+
"learning_rate": 9.933807660562898e-06,
|
| 552 |
+
"loss": 1.0151,
|
| 553 |
+
"step": 110
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 20.0,
|
| 557 |
+
"eval_loss": 1.0539679527282715,
|
| 558 |
+
"eval_runtime": 9.6338,
|
| 559 |
+
"eval_samples_per_second": 2.491,
|
| 560 |
+
"eval_steps_per_second": 2.491,
|
| 561 |
+
"step": 110
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 20.363636363636363,
|
| 565 |
+
"grad_norm": 0.384694367647171,
|
| 566 |
+
"learning_rate": 9.926045918666045e-06,
|
| 567 |
+
"loss": 1.0363,
|
| 568 |
+
"step": 112
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 20.727272727272727,
|
| 572 |
+
"grad_norm": 0.3782545030117035,
|
| 573 |
+
"learning_rate": 9.91785735406693e-06,
|
| 574 |
+
"loss": 1.0277,
|
| 575 |
+
"step": 114
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 20.90909090909091,
|
| 579 |
+
"eval_loss": 1.0388442277908325,
|
| 580 |
+
"eval_runtime": 9.6309,
|
| 581 |
+
"eval_samples_per_second": 2.492,
|
| 582 |
+
"eval_steps_per_second": 2.492,
|
| 583 |
+
"step": 115
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 21.09090909090909,
|
| 587 |
+
"grad_norm": 0.3923183083534241,
|
| 588 |
+
"learning_rate": 9.909242676272797e-06,
|
| 589 |
+
"loss": 1.0385,
|
| 590 |
+
"step": 116
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 21.454545454545453,
|
| 594 |
+
"grad_norm": 0.3774013817310333,
|
| 595 |
+
"learning_rate": 9.90020263171194e-06,
|
| 596 |
+
"loss": 1.0073,
|
| 597 |
+
"step": 118
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 21.818181818181817,
|
| 601 |
+
"grad_norm": 0.3472942113876343,
|
| 602 |
+
"learning_rate": 9.890738003669029e-06,
|
| 603 |
+
"loss": 1.0025,
|
| 604 |
+
"step": 120
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 22.0,
|
| 608 |
+
"eval_loss": 1.0249600410461426,
|
| 609 |
+
"eval_runtime": 9.6161,
|
| 610 |
+
"eval_samples_per_second": 2.496,
|
| 611 |
+
"eval_steps_per_second": 2.496,
|
| 612 |
+
"step": 121
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 22.181818181818183,
|
| 616 |
+
"grad_norm": 0.3280906081199646,
|
| 617 |
+
"learning_rate": 9.880849612217238e-06,
|
| 618 |
+
"loss": 0.9887,
|
| 619 |
+
"step": 122
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 22.545454545454547,
|
| 623 |
+
"grad_norm": 0.3648756742477417,
|
| 624 |
+
"learning_rate": 9.870538314147194e-06,
|
| 625 |
+
"loss": 1.0023,
|
| 626 |
+
"step": 124
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 22.90909090909091,
|
| 630 |
+
"grad_norm": 0.390601247549057,
|
| 631 |
+
"learning_rate": 9.859805002892733e-06,
|
| 632 |
+
"loss": 1.0161,
|
| 633 |
+
"step": 126
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 22.90909090909091,
|
| 637 |
+
"eval_loss": 1.0154192447662354,
|
| 638 |
+
"eval_runtime": 9.6244,
|
| 639 |
+
"eval_samples_per_second": 2.494,
|
| 640 |
+
"eval_steps_per_second": 2.494,
|
| 641 |
+
"step": 126
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 23.272727272727273,
|
| 645 |
+
"grad_norm": 0.3790784180164337,
|
| 646 |
+
"learning_rate": 9.84865060845349e-06,
|
| 647 |
+
"loss": 0.9941,
|
| 648 |
+
"step": 128
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 23.636363636363637,
|
| 652 |
+
"grad_norm": 0.36824390292167664,
|
| 653 |
+
"learning_rate": 9.83707609731432e-06,
|
| 654 |
+
"loss": 0.9697,
|
| 655 |
+
"step": 130
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 24.0,
|
| 659 |
+
"grad_norm": 0.39850422739982605,
|
| 660 |
+
"learning_rate": 9.825082472361558e-06,
|
| 661 |
+
"loss": 0.9946,
|
| 662 |
+
"step": 132
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 24.0,
|
| 666 |
+
"eval_loss": 1.0047398805618286,
|
| 667 |
+
"eval_runtime": 9.6214,
|
| 668 |
+
"eval_samples_per_second": 2.494,
|
| 669 |
+
"eval_steps_per_second": 2.494,
|
| 670 |
+
"step": 132
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 24.363636363636363,
|
| 674 |
+
"grad_norm": 0.34537094831466675,
|
| 675 |
+
"learning_rate": 9.812670772796113e-06,
|
| 676 |
+
"loss": 0.9699,
|
| 677 |
+
"step": 134
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 24.727272727272727,
|
| 681 |
+
"grad_norm": 0.38018471002578735,
|
| 682 |
+
"learning_rate": 9.799842074043438e-06,
|
| 683 |
+
"loss": 0.9773,
|
| 684 |
+
"step": 136
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 24.90909090909091,
|
| 688 |
+
"eval_loss": 0.9969633221626282,
|
| 689 |
+
"eval_runtime": 9.6246,
|
| 690 |
+
"eval_samples_per_second": 2.494,
|
| 691 |
+
"eval_steps_per_second": 2.494,
|
| 692 |
+
"step": 137
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 25.09090909090909,
|
| 696 |
+
"grad_norm": 0.40856873989105225,
|
| 697 |
+
"learning_rate": 9.786597487660336e-06,
|
| 698 |
+
"loss": 0.9836,
|
| 699 |
+
"step": 138
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 25.454545454545453,
|
| 703 |
+
"grad_norm": 0.37090280652046204,
|
| 704 |
+
"learning_rate": 9.77293816123866e-06,
|
| 705 |
+
"loss": 0.9658,
|
| 706 |
+
"step": 140
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 25.818181818181817,
|
| 710 |
+
"grad_norm": 0.4068634808063507,
|
| 711 |
+
"learning_rate": 9.75886527830587e-06,
|
| 712 |
+
"loss": 0.9708,
|
| 713 |
+
"step": 142
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 26.0,
|
| 717 |
+
"eval_loss": 0.9890053272247314,
|
| 718 |
+
"eval_runtime": 9.6268,
|
| 719 |
+
"eval_samples_per_second": 2.493,
|
| 720 |
+
"eval_steps_per_second": 2.493,
|
| 721 |
+
"step": 143
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 26.181818181818183,
|
| 725 |
+
"grad_norm": 0.38360726833343506,
|
| 726 |
+
"learning_rate": 9.744380058222483e-06,
|
| 727 |
+
"loss": 0.9676,
|
| 728 |
+
"step": 144
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 26.545454545454547,
|
| 732 |
+
"grad_norm": 0.38106632232666016,
|
| 733 |
+
"learning_rate": 9.729483756076436e-06,
|
| 734 |
+
"loss": 0.972,
|
| 735 |
+
"step": 146
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 26.90909090909091,
|
| 739 |
+
"grad_norm": 0.36939358711242676,
|
| 740 |
+
"learning_rate": 9.714177662574316e-06,
|
| 741 |
+
"loss": 0.9374,
|
| 742 |
+
"step": 148
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 26.90909090909091,
|
| 746 |
+
"eval_loss": 0.9821727275848389,
|
| 747 |
+
"eval_runtime": 9.622,
|
| 748 |
+
"eval_samples_per_second": 2.494,
|
| 749 |
+
"eval_steps_per_second": 2.494,
|
| 750 |
+
"step": 148
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 27.272727272727273,
|
| 754 |
+
"grad_norm": 0.37566348910331726,
|
| 755 |
+
"learning_rate": 9.698463103929542e-06,
|
| 756 |
+
"loss": 0.9219,
|
| 757 |
+
"step": 150
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 27.636363636363637,
|
| 761 |
+
"grad_norm": 0.3677101731300354,
|
| 762 |
+
"learning_rate": 9.682341441747446e-06,
|
| 763 |
+
"loss": 0.9798,
|
| 764 |
+
"step": 152
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 28.0,
|
| 768 |
+
"grad_norm": 0.3695693016052246,
|
| 769 |
+
"learning_rate": 9.665814072907293e-06,
|
| 770 |
+
"loss": 0.9403,
|
| 771 |
+
"step": 154
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 28.0,
|
| 775 |
+
"eval_loss": 0.9750909209251404,
|
| 776 |
+
"eval_runtime": 9.6244,
|
| 777 |
+
"eval_samples_per_second": 2.494,
|
| 778 |
+
"eval_steps_per_second": 2.494,
|
| 779 |
+
"step": 154
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 28.363636363636363,
|
| 783 |
+
"grad_norm": 0.42501190304756165,
|
| 784 |
+
"learning_rate": 9.648882429441258e-06,
|
| 785 |
+
"loss": 0.9428,
|
| 786 |
+
"step": 156
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 28.727272727272727,
|
| 790 |
+
"grad_norm": 0.3643590807914734,
|
| 791 |
+
"learning_rate": 9.63154797841033e-06,
|
| 792 |
+
"loss": 0.94,
|
| 793 |
+
"step": 158
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 28.90909090909091,
|
| 797 |
+
"eval_loss": 0.9702978134155273,
|
| 798 |
+
"eval_runtime": 9.6253,
|
| 799 |
+
"eval_samples_per_second": 2.493,
|
| 800 |
+
"eval_steps_per_second": 2.493,
|
| 801 |
+
"step": 159
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 29.09090909090909,
|
| 805 |
+
"grad_norm": 0.3957996666431427,
|
| 806 |
+
"learning_rate": 9.613812221777212e-06,
|
| 807 |
+
"loss": 0.9274,
|
| 808 |
+
"step": 160
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 29.454545454545453,
|
| 812 |
+
"grad_norm": 0.4291062355041504,
|
| 813 |
+
"learning_rate": 9.595676696276173e-06,
|
| 814 |
+
"loss": 0.9886,
|
| 815 |
+
"step": 162
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 29.818181818181817,
|
| 819 |
+
"grad_norm": 0.5365828275680542,
|
| 820 |
+
"learning_rate": 9.577142973279896e-06,
|
| 821 |
+
"loss": 0.902,
|
| 822 |
+
"step": 164
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 30.0,
|
| 826 |
+
"eval_loss": 0.9632946848869324,
|
| 827 |
+
"eval_runtime": 9.6187,
|
| 828 |
+
"eval_samples_per_second": 2.495,
|
| 829 |
+
"eval_steps_per_second": 2.495,
|
| 830 |
+
"step": 165
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 30.181818181818183,
|
| 834 |
+
"grad_norm": 0.38883283734321594,
|
| 835 |
+
"learning_rate": 9.55821265866333e-06,
|
| 836 |
+
"loss": 0.8967,
|
| 837 |
+
"step": 166
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 30.545454545454547,
|
| 841 |
+
"grad_norm": 0.41333243250846863,
|
| 842 |
+
"learning_rate": 9.538887392664544e-06,
|
| 843 |
+
"loss": 0.9142,
|
| 844 |
+
"step": 168
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 30.90909090909091,
|
| 848 |
+
"grad_norm": 0.4123990833759308,
|
| 849 |
+
"learning_rate": 9.519168849742603e-06,
|
| 850 |
+
"loss": 0.9215,
|
| 851 |
+
"step": 170
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 30.90909090909091,
|
| 855 |
+
"eval_loss": 0.9604056477546692,
|
| 856 |
+
"eval_runtime": 9.627,
|
| 857 |
+
"eval_samples_per_second": 2.493,
|
| 858 |
+
"eval_steps_per_second": 2.493,
|
| 859 |
+
"step": 170
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 31.272727272727273,
|
| 863 |
+
"grad_norm": 0.407969206571579,
|
| 864 |
+
"learning_rate": 9.499058738432492e-06,
|
| 865 |
+
"loss": 0.9574,
|
| 866 |
+
"step": 172
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 31.636363636363637,
|
| 870 |
+
"grad_norm": 0.4867004156112671,
|
| 871 |
+
"learning_rate": 9.478558801197065e-06,
|
| 872 |
+
"loss": 0.9208,
|
| 873 |
+
"step": 174
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 32.0,
|
| 877 |
+
"grad_norm": 0.4684889316558838,
|
| 878 |
+
"learning_rate": 9.457670814276083e-06,
|
| 879 |
+
"loss": 0.8854,
|
| 880 |
+
"step": 176
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 32.0,
|
| 884 |
+
"eval_loss": 0.9548270106315613,
|
| 885 |
+
"eval_runtime": 9.6173,
|
| 886 |
+
"eval_samples_per_second": 2.495,
|
| 887 |
+
"eval_steps_per_second": 2.495,
|
| 888 |
+
"step": 176
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 32.36363636363637,
|
| 892 |
+
"grad_norm": 0.527631938457489,
|
| 893 |
+
"learning_rate": 9.436396587532297e-06,
|
| 894 |
+
"loss": 0.8831,
|
| 895 |
+
"step": 178
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 32.72727272727273,
|
| 899 |
+
"grad_norm": 0.44928282499313354,
|
| 900 |
+
"learning_rate": 9.414737964294636e-06,
|
| 901 |
+
"loss": 0.96,
|
| 902 |
+
"step": 180
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 32.90909090909091,
|
| 906 |
+
"eval_loss": 0.9503173232078552,
|
| 907 |
+
"eval_runtime": 9.624,
|
| 908 |
+
"eval_samples_per_second": 2.494,
|
| 909 |
+
"eval_steps_per_second": 2.494,
|
| 910 |
+
"step": 181
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 33.09090909090909,
|
| 914 |
+
"grad_norm": 0.5621985197067261,
|
| 915 |
+
"learning_rate": 9.392696821198488e-06,
|
| 916 |
+
"loss": 0.8666,
|
| 917 |
+
"step": 182
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 33.45454545454545,
|
| 921 |
+
"grad_norm": 0.523452877998352,
|
| 922 |
+
"learning_rate": 9.370275068023097e-06,
|
| 923 |
+
"loss": 0.922,
|
| 924 |
+
"step": 184
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 33.81818181818182,
|
| 928 |
+
"grad_norm": 0.5437294840812683,
|
| 929 |
+
"learning_rate": 9.347474647526095e-06,
|
| 930 |
+
"loss": 0.9162,
|
| 931 |
+
"step": 186
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 34.0,
|
| 935 |
+
"eval_loss": 0.9452812075614929,
|
| 936 |
+
"eval_runtime": 9.6313,
|
| 937 |
+
"eval_samples_per_second": 2.492,
|
| 938 |
+
"eval_steps_per_second": 2.492,
|
| 939 |
+
"step": 187
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 34.18181818181818,
|
| 943 |
+
"grad_norm": 0.46963879466056824,
|
| 944 |
+
"learning_rate": 9.324297535275156e-06,
|
| 945 |
+
"loss": 0.8254,
|
| 946 |
+
"step": 188
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 34.54545454545455,
|
| 950 |
+
"grad_norm": 0.48245498538017273,
|
| 951 |
+
"learning_rate": 9.30074573947683e-06,
|
| 952 |
+
"loss": 0.9174,
|
| 953 |
+
"step": 190
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 34.90909090909091,
|
| 957 |
+
"grad_norm": 0.5139335989952087,
|
| 958 |
+
"learning_rate": 9.276821300802535e-06,
|
| 959 |
+
"loss": 0.8686,
|
| 960 |
+
"step": 192
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 34.90909090909091,
|
| 964 |
+
"eval_loss": 0.9428532719612122,
|
| 965 |
+
"eval_runtime": 9.6309,
|
| 966 |
+
"eval_samples_per_second": 2.492,
|
| 967 |
+
"eval_steps_per_second": 2.492,
|
| 968 |
+
"step": 192
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 35.27272727272727,
|
| 972 |
+
"grad_norm": 0.45418813824653625,
|
| 973 |
+
"learning_rate": 9.25252629221175e-06,
|
| 974 |
+
"loss": 0.9011,
|
| 975 |
+
"step": 194
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 35.63636363636363,
|
| 979 |
+
"grad_norm": 0.5155036449432373,
|
| 980 |
+
"learning_rate": 9.227862818772392e-06,
|
| 981 |
+
"loss": 0.8754,
|
| 982 |
+
"step": 196
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 36.0,
|
| 986 |
+
"grad_norm": 0.4917118549346924,
|
| 987 |
+
"learning_rate": 9.202833017478421e-06,
|
| 988 |
+
"loss": 0.906,
|
| 989 |
+
"step": 198
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 36.0,
|
| 993 |
+
"eval_loss": 0.9385306239128113,
|
| 994 |
+
"eval_runtime": 9.6304,
|
| 995 |
+
"eval_samples_per_second": 2.492,
|
| 996 |
+
"eval_steps_per_second": 2.492,
|
| 997 |
+
"step": 198
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 36.36363636363637,
|
| 1001 |
+
"grad_norm": 0.5289394855499268,
|
| 1002 |
+
"learning_rate": 9.177439057064684e-06,
|
| 1003 |
+
"loss": 0.8751,
|
| 1004 |
+
"step": 200
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 36.72727272727273,
|
| 1008 |
+
"grad_norm": 0.5498368144035339,
|
| 1009 |
+
"learning_rate": 9.151683137818989e-06,
|
| 1010 |
+
"loss": 0.8762,
|
| 1011 |
+
"step": 202
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 36.90909090909091,
|
| 1015 |
+
"eval_loss": 0.9353806972503662,
|
| 1016 |
+
"eval_runtime": 9.6269,
|
| 1017 |
+
"eval_samples_per_second": 2.493,
|
| 1018 |
+
"eval_steps_per_second": 2.493,
|
| 1019 |
+
"step": 203
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 37.09090909090909,
|
| 1023 |
+
"grad_norm": 0.516069233417511,
|
| 1024 |
+
"learning_rate": 9.125567491391476e-06,
|
| 1025 |
+
"loss": 0.869,
|
| 1026 |
+
"step": 204
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 37.45454545454545,
|
| 1030 |
+
"grad_norm": 0.5102888345718384,
|
| 1031 |
+
"learning_rate": 9.099094380601244e-06,
|
| 1032 |
+
"loss": 0.8518,
|
| 1033 |
+
"step": 206
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 37.81818181818182,
|
| 1037 |
+
"grad_norm": 0.5379929542541504,
|
| 1038 |
+
"learning_rate": 9.072266099240286e-06,
|
| 1039 |
+
"loss": 0.8929,
|
| 1040 |
+
"step": 208
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 38.0,
|
| 1044 |
+
"eval_loss": 0.9331977963447571,
|
| 1045 |
+
"eval_runtime": 9.6277,
|
| 1046 |
+
"eval_samples_per_second": 2.493,
|
| 1047 |
+
"eval_steps_per_second": 2.493,
|
| 1048 |
+
"step": 209
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 38.18181818181818,
|
| 1052 |
+
"grad_norm": 0.6433578729629517,
|
| 1053 |
+
"learning_rate": 9.045084971874738e-06,
|
| 1054 |
+
"loss": 0.8756,
|
| 1055 |
+
"step": 210
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 38.54545454545455,
|
| 1059 |
+
"grad_norm": 0.6186140179634094,
|
| 1060 |
+
"learning_rate": 9.017553353643479e-06,
|
| 1061 |
+
"loss": 0.8582,
|
| 1062 |
+
"step": 212
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 38.90909090909091,
|
| 1066 |
+
"grad_norm": 0.608066976070404,
|
| 1067 |
+
"learning_rate": 8.989673630054044e-06,
|
| 1068 |
+
"loss": 0.8687,
|
| 1069 |
+
"step": 214
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 38.90909090909091,
|
| 1073 |
+
"eval_loss": 0.9301042556762695,
|
| 1074 |
+
"eval_runtime": 9.6307,
|
| 1075 |
+
"eval_samples_per_second": 2.492,
|
| 1076 |
+
"eval_steps_per_second": 2.492,
|
| 1077 |
+
"step": 214
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 39.27272727272727,
|
| 1081 |
+
"grad_norm": 0.6045626401901245,
|
| 1082 |
+
"learning_rate": 8.961448216775955e-06,
|
| 1083 |
+
"loss": 0.8119,
|
| 1084 |
+
"step": 216
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 39.63636363636363,
|
| 1088 |
+
"grad_norm": 0.6160129308700562,
|
| 1089 |
+
"learning_rate": 8.932879559431392e-06,
|
| 1090 |
+
"loss": 0.8301,
|
| 1091 |
+
"step": 218
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 40.0,
|
| 1095 |
+
"grad_norm": 0.6550566554069519,
|
| 1096 |
+
"learning_rate": 8.903970133383297e-06,
|
| 1097 |
+
"loss": 0.8933,
|
| 1098 |
+
"step": 220
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 40.0,
|
| 1102 |
+
"eval_loss": 0.9279410243034363,
|
| 1103 |
+
"eval_runtime": 9.6288,
|
| 1104 |
+
"eval_samples_per_second": 2.493,
|
| 1105 |
+
"eval_steps_per_second": 2.493,
|
| 1106 |
+
"step": 220
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 40.36363636363637,
|
| 1110 |
+
"grad_norm": 0.6415209770202637,
|
| 1111 |
+
"learning_rate": 8.874722443520898e-06,
|
| 1112 |
+
"loss": 0.8325,
|
| 1113 |
+
"step": 222
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 40.72727272727273,
|
| 1117 |
+
"grad_norm": 0.6836015582084656,
|
| 1118 |
+
"learning_rate": 8.845139024042664e-06,
|
| 1119 |
+
"loss": 0.858,
|
| 1120 |
+
"step": 224
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 40.90909090909091,
|
| 1124 |
+
"eval_loss": 0.9241297841072083,
|
| 1125 |
+
"eval_runtime": 9.6293,
|
| 1126 |
+
"eval_samples_per_second": 2.492,
|
| 1127 |
+
"eval_steps_per_second": 2.492,
|
| 1128 |
+
"step": 225
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 41.09090909090909,
|
| 1132 |
+
"grad_norm": 0.6644122004508972,
|
| 1133 |
+
"learning_rate": 8.815222438236726e-06,
|
| 1134 |
+
"loss": 0.8649,
|
| 1135 |
+
"step": 226
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 41.45454545454545,
|
| 1139 |
+
"grad_norm": 0.6619220972061157,
|
| 1140 |
+
"learning_rate": 8.784975278258783e-06,
|
| 1141 |
+
"loss": 0.8085,
|
| 1142 |
+
"step": 228
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 41.81818181818182,
|
| 1146 |
+
"grad_norm": 0.6005414724349976,
|
| 1147 |
+
"learning_rate": 8.754400164907496e-06,
|
| 1148 |
+
"loss": 0.8481,
|
| 1149 |
+
"step": 230
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 42.0,
|
| 1153 |
+
"eval_loss": 0.9222747683525085,
|
| 1154 |
+
"eval_runtime": 9.6426,
|
| 1155 |
+
"eval_samples_per_second": 2.489,
|
| 1156 |
+
"eval_steps_per_second": 2.489,
|
| 1157 |
+
"step": 231
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 42.18181818181818,
|
| 1161 |
+
"grad_norm": 0.722902238368988,
|
| 1162 |
+
"learning_rate": 8.723499747397415e-06,
|
| 1163 |
+
"loss": 0.8578,
|
| 1164 |
+
"step": 232
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 42.54545454545455,
|
| 1168 |
+
"grad_norm": 0.7436155080795288,
|
| 1169 |
+
"learning_rate": 8.692276703129421e-06,
|
| 1170 |
+
"loss": 0.7996,
|
| 1171 |
+
"step": 234
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 42.90909090909091,
|
| 1175 |
+
"grad_norm": 0.6658902168273926,
|
| 1176 |
+
"learning_rate": 8.660733737458751e-06,
|
| 1177 |
+
"loss": 0.8228,
|
| 1178 |
+
"step": 236
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 42.90909090909091,
|
| 1182 |
+
"eval_loss": 0.9217340350151062,
|
| 1183 |
+
"eval_runtime": 9.6277,
|
| 1184 |
+
"eval_samples_per_second": 2.493,
|
| 1185 |
+
"eval_steps_per_second": 2.493,
|
| 1186 |
+
"step": 236
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 43.27272727272727,
|
| 1190 |
+
"grad_norm": 0.6352283358573914,
|
| 1191 |
+
"learning_rate": 8.628873583460593e-06,
|
| 1192 |
+
"loss": 0.8113,
|
| 1193 |
+
"step": 238
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 43.63636363636363,
|
| 1197 |
+
"grad_norm": 1.0223489999771118,
|
| 1198 |
+
"learning_rate": 8.596699001693257e-06,
|
| 1199 |
+
"loss": 0.8149,
|
| 1200 |
+
"step": 240
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 44.0,
|
| 1204 |
+
"grad_norm": 0.7334797978401184,
|
| 1205 |
+
"learning_rate": 8.564212779959003e-06,
|
| 1206 |
+
"loss": 0.8593,
|
| 1207 |
+
"step": 242
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 44.0,
|
| 1211 |
+
"eval_loss": 0.9185922741889954,
|
| 1212 |
+
"eval_runtime": 9.6303,
|
| 1213 |
+
"eval_samples_per_second": 2.492,
|
| 1214 |
+
"eval_steps_per_second": 2.492,
|
| 1215 |
+
"step": 242
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 44.36363636363637,
|
| 1219 |
+
"grad_norm": 0.7544272541999817,
|
| 1220 |
+
"learning_rate": 8.531417733062476e-06,
|
| 1221 |
+
"loss": 0.7958,
|
| 1222 |
+
"step": 244
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 44.72727272727273,
|
| 1226 |
+
"grad_norm": 0.8189204335212708,
|
| 1227 |
+
"learning_rate": 8.498316702566828e-06,
|
| 1228 |
+
"loss": 0.8238,
|
| 1229 |
+
"step": 246
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 44.90909090909091,
|
| 1233 |
+
"eval_loss": 0.9156233668327332,
|
| 1234 |
+
"eval_runtime": 9.6451,
|
| 1235 |
+
"eval_samples_per_second": 2.488,
|
| 1236 |
+
"eval_steps_per_second": 2.488,
|
| 1237 |
+
"step": 247
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 45.09090909090909,
|
| 1241 |
+
"grad_norm": 0.6729193329811096,
|
| 1242 |
+
"learning_rate": 8.464912556547486e-06,
|
| 1243 |
+
"loss": 0.835,
|
| 1244 |
+
"step": 248
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 45.45454545454545,
|
| 1248 |
+
"grad_norm": 0.6723213195800781,
|
| 1249 |
+
"learning_rate": 8.43120818934367e-06,
|
| 1250 |
+
"loss": 0.7991,
|
| 1251 |
+
"step": 250
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 45.81818181818182,
|
| 1255 |
+
"grad_norm": 0.8917332887649536,
|
| 1256 |
+
"learning_rate": 8.397206521307584e-06,
|
| 1257 |
+
"loss": 0.8081,
|
| 1258 |
+
"step": 252
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 46.0,
|
| 1262 |
+
"eval_loss": 0.9161267876625061,
|
| 1263 |
+
"eval_runtime": 9.6325,
|
| 1264 |
+
"eval_samples_per_second": 2.492,
|
| 1265 |
+
"eval_steps_per_second": 2.492,
|
| 1266 |
+
"step": 253
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 46.18181818181818,
|
| 1270 |
+
"grad_norm": 0.7718498110771179,
|
| 1271 |
+
"learning_rate": 8.362910498551402e-06,
|
| 1272 |
+
"loss": 0.8071,
|
| 1273 |
+
"step": 254
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 46.54545454545455,
|
| 1277 |
+
"grad_norm": 0.7421916127204895,
|
| 1278 |
+
"learning_rate": 8.328323092691985e-06,
|
| 1279 |
+
"loss": 0.7838,
|
| 1280 |
+
"step": 256
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 46.90909090909091,
|
| 1284 |
+
"grad_norm": 0.775203287601471,
|
| 1285 |
+
"learning_rate": 8.293447300593402e-06,
|
| 1286 |
+
"loss": 0.8327,
|
| 1287 |
+
"step": 258
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 46.90909090909091,
|
| 1291 |
+
"eval_loss": 0.912854015827179,
|
| 1292 |
+
"eval_runtime": 9.6464,
|
| 1293 |
+
"eval_samples_per_second": 2.488,
|
| 1294 |
+
"eval_steps_per_second": 2.488,
|
| 1295 |
+
"step": 258
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 47.27272727272727,
|
| 1299 |
+
"grad_norm": 0.6994480490684509,
|
| 1300 |
+
"learning_rate": 8.258286144107277e-06,
|
| 1301 |
+
"loss": 0.7949,
|
| 1302 |
+
"step": 260
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 47.63636363636363,
|
| 1306 |
+
"grad_norm": 0.8607519865036011,
|
| 1307 |
+
"learning_rate": 8.222842669810936e-06,
|
| 1308 |
+
"loss": 0.7794,
|
| 1309 |
+
"step": 262
|
| 1310 |
+
},
|
| 1311 |
+
{
|
| 1312 |
+
"epoch": 48.0,
|
| 1313 |
+
"grad_norm": 0.8172978758811951,
|
| 1314 |
+
"learning_rate": 8.18711994874345e-06,
|
| 1315 |
+
"loss": 0.8029,
|
| 1316 |
+
"step": 264
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 48.0,
|
| 1320 |
+
"eval_loss": 0.9110000133514404,
|
| 1321 |
+
"eval_runtime": 9.6168,
|
| 1322 |
+
"eval_samples_per_second": 2.496,
|
| 1323 |
+
"eval_steps_per_second": 2.496,
|
| 1324 |
+
"step": 264
|
| 1325 |
+
},
|
| 1326 |
+
{
|
| 1327 |
+
"epoch": 48.36363636363637,
|
| 1328 |
+
"grad_norm": 0.8061463236808777,
|
| 1329 |
+
"learning_rate": 8.151121076139534e-06,
|
| 1330 |
+
"loss": 0.8099,
|
| 1331 |
+
"step": 266
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 48.72727272727273,
|
| 1335 |
+
"grad_norm": 0.9735673069953918,
|
| 1336 |
+
"learning_rate": 8.11484917116136e-06,
|
| 1337 |
+
"loss": 0.7909,
|
| 1338 |
+
"step": 268
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 48.90909090909091,
|
| 1342 |
+
"eval_loss": 0.9093864560127258,
|
| 1343 |
+
"eval_runtime": 9.6205,
|
| 1344 |
+
"eval_samples_per_second": 2.495,
|
| 1345 |
+
"eval_steps_per_second": 2.495,
|
| 1346 |
+
"step": 269
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 49.09090909090909,
|
| 1350 |
+
"grad_norm": 0.8723132014274597,
|
| 1351 |
+
"learning_rate": 8.078307376628292e-06,
|
| 1352 |
+
"loss": 0.7628,
|
| 1353 |
+
"step": 270
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 49.45454545454545,
|
| 1357 |
+
"grad_norm": 0.7607284188270569,
|
| 1358 |
+
"learning_rate": 8.041498858744572e-06,
|
| 1359 |
+
"loss": 0.7665,
|
| 1360 |
+
"step": 272
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 49.81818181818182,
|
| 1364 |
+
"grad_norm": 0.8277180194854736,
|
| 1365 |
+
"learning_rate": 8.004426806824985e-06,
|
| 1366 |
+
"loss": 0.7826,
|
| 1367 |
+
"step": 274
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 50.0,
|
| 1371 |
+
"eval_loss": 0.9079095721244812,
|
| 1372 |
+
"eval_runtime": 9.6142,
|
| 1373 |
+
"eval_samples_per_second": 2.496,
|
| 1374 |
+
"eval_steps_per_second": 2.496,
|
| 1375 |
+
"step": 275
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 50.18181818181818,
|
| 1379 |
+
"grad_norm": 0.8411371111869812,
|
| 1380 |
+
"learning_rate": 7.967094433018508e-06,
|
| 1381 |
+
"loss": 0.7943,
|
| 1382 |
+
"step": 276
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 50.54545454545455,
|
| 1386 |
+
"grad_norm": 0.834507167339325,
|
| 1387 |
+
"learning_rate": 7.929504972030003e-06,
|
| 1388 |
+
"loss": 0.7586,
|
| 1389 |
+
"step": 278
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 50.90909090909091,
|
| 1393 |
+
"grad_norm": 1.0113625526428223,
|
| 1394 |
+
"learning_rate": 7.891661680839932e-06,
|
| 1395 |
+
"loss": 0.773,
|
| 1396 |
+
"step": 280
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 50.90909090909091,
|
| 1400 |
+
"eval_loss": 0.9122073650360107,
|
| 1401 |
+
"eval_runtime": 9.6327,
|
| 1402 |
+
"eval_samples_per_second": 2.492,
|
| 1403 |
+
"eval_steps_per_second": 2.492,
|
| 1404 |
+
"step": 280
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 51.27272727272727,
|
| 1408 |
+
"grad_norm": 0.8380469083786011,
|
| 1409 |
+
"learning_rate": 7.85356783842216e-06,
|
| 1410 |
+
"loss": 0.7737,
|
| 1411 |
+
"step": 282
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 51.63636363636363,
|
| 1415 |
+
"grad_norm": 0.8534033894538879,
|
| 1416 |
+
"learning_rate": 7.815226745459831e-06,
|
| 1417 |
+
"loss": 0.7941,
|
| 1418 |
+
"step": 284
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 52.0,
|
| 1422 |
+
"grad_norm": 0.8890909552574158,
|
| 1423 |
+
"learning_rate": 7.776641724059398e-06,
|
| 1424 |
+
"loss": 0.7377,
|
| 1425 |
+
"step": 286
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 52.0,
|
| 1429 |
+
"eval_loss": 0.9077624678611755,
|
| 1430 |
+
"eval_runtime": 9.6175,
|
| 1431 |
+
"eval_samples_per_second": 2.495,
|
| 1432 |
+
"eval_steps_per_second": 2.495,
|
| 1433 |
+
"step": 286
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 52.36363636363637,
|
| 1437 |
+
"grad_norm": 0.9524686336517334,
|
| 1438 |
+
"learning_rate": 7.737816117462752e-06,
|
| 1439 |
+
"loss": 0.7699,
|
| 1440 |
+
"step": 288
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 52.72727272727273,
|
| 1444 |
+
"grad_norm": 0.8625631928443909,
|
| 1445 |
+
"learning_rate": 7.698753289757565e-06,
|
| 1446 |
+
"loss": 0.7491,
|
| 1447 |
+
"step": 290
|
| 1448 |
+
},
|
| 1449 |
+
{
|
| 1450 |
+
"epoch": 52.90909090909091,
|
| 1451 |
+
"eval_loss": 0.9050046801567078,
|
| 1452 |
+
"eval_runtime": 9.6225,
|
| 1453 |
+
"eval_samples_per_second": 2.494,
|
| 1454 |
+
"eval_steps_per_second": 2.494,
|
| 1455 |
+
"step": 291
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 53.09090909090909,
|
| 1459 |
+
"grad_norm": 1.0375274419784546,
|
| 1460 |
+
"learning_rate": 7.65945662558579e-06,
|
| 1461 |
+
"loss": 0.7661,
|
| 1462 |
+
"step": 292
|
| 1463 |
+
},
|
| 1464 |
+
{
|
| 1465 |
+
"epoch": 53.45454545454545,
|
| 1466 |
+
"grad_norm": 0.8255937695503235,
|
| 1467 |
+
"learning_rate": 7.619929529850397e-06,
|
| 1468 |
+
"loss": 0.7606,
|
| 1469 |
+
"step": 294
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 53.81818181818182,
|
| 1473 |
+
"grad_norm": 1.0094412565231323,
|
| 1474 |
+
"learning_rate": 7.580175427420358e-06,
|
| 1475 |
+
"loss": 0.7414,
|
| 1476 |
+
"step": 296
|
| 1477 |
+
},
|
| 1478 |
+
{
|
| 1479 |
+
"epoch": 54.0,
|
| 1480 |
+
"eval_loss": 0.9093080163002014,
|
| 1481 |
+
"eval_runtime": 9.6164,
|
| 1482 |
+
"eval_samples_per_second": 2.496,
|
| 1483 |
+
"eval_steps_per_second": 2.496,
|
| 1484 |
+
"step": 297
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 54.18181818181818,
|
| 1488 |
+
"grad_norm": 0.8360889554023743,
|
| 1489 |
+
"learning_rate": 7.54019776283389e-06,
|
| 1490 |
+
"loss": 0.7467,
|
| 1491 |
+
"step": 298
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 54.54545454545455,
|
| 1495 |
+
"grad_norm": 0.9806857109069824,
|
| 1496 |
+
"learning_rate": 7.500000000000001e-06,
|
| 1497 |
+
"loss": 0.7445,
|
| 1498 |
+
"step": 300
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 54.90909090909091,
|
| 1502 |
+
"grad_norm": 1.0003647804260254,
|
| 1503 |
+
"learning_rate": 7.459585621898353e-06,
|
| 1504 |
+
"loss": 0.7275,
|
| 1505 |
+
"step": 302
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 54.90909090909091,
|
| 1509 |
+
"eval_loss": 0.9052907824516296,
|
| 1510 |
+
"eval_runtime": 9.6259,
|
| 1511 |
+
"eval_samples_per_second": 2.493,
|
| 1512 |
+
"eval_steps_per_second": 2.493,
|
| 1513 |
+
"step": 302
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 55.27272727272727,
|
| 1517 |
+
"grad_norm": 1.080519437789917,
|
| 1518 |
+
"learning_rate": 7.418958130277483e-06,
|
| 1519 |
+
"loss": 0.7526,
|
| 1520 |
+
"step": 304
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 55.63636363636363,
|
| 1524 |
+
"grad_norm": 1.2365224361419678,
|
| 1525 |
+
"learning_rate": 7.378121045351378e-06,
|
| 1526 |
+
"loss": 0.7289,
|
| 1527 |
+
"step": 306
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 56.0,
|
| 1531 |
+
"grad_norm": 0.9447788000106812,
|
| 1532 |
+
"learning_rate": 7.337077905494472e-06,
|
| 1533 |
+
"loss": 0.7198,
|
| 1534 |
+
"step": 308
|
| 1535 |
+
},
|
| 1536 |
+
{
|
| 1537 |
+
"epoch": 56.0,
|
| 1538 |
+
"eval_loss": 0.9046055674552917,
|
| 1539 |
+
"eval_runtime": 9.6309,
|
| 1540 |
+
"eval_samples_per_second": 2.492,
|
| 1541 |
+
"eval_steps_per_second": 2.492,
|
| 1542 |
+
"step": 308
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 56.36363636363637,
|
| 1546 |
+
"grad_norm": 0.9524107575416565,
|
| 1547 |
+
"learning_rate": 7.295832266935059e-06,
|
| 1548 |
+
"loss": 0.766,
|
| 1549 |
+
"step": 310
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 56.72727272727273,
|
| 1553 |
+
"grad_norm": 0.9705169796943665,
|
| 1554 |
+
"learning_rate": 7.254387703447154e-06,
|
| 1555 |
+
"loss": 0.7203,
|
| 1556 |
+
"step": 312
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 56.90909090909091,
|
| 1560 |
+
"eval_loss": 0.9092791676521301,
|
| 1561 |
+
"eval_runtime": 9.6325,
|
| 1562 |
+
"eval_samples_per_second": 2.492,
|
| 1563 |
+
"eval_steps_per_second": 2.492,
|
| 1564 |
+
"step": 313
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 57.09090909090909,
|
| 1568 |
+
"grad_norm": 1.0789105892181396,
|
| 1569 |
+
"learning_rate": 7.212747806040845e-06,
|
| 1570 |
+
"loss": 0.6951,
|
| 1571 |
+
"step": 314
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 57.45454545454545,
|
| 1575 |
+
"grad_norm": 1.1204413175582886,
|
| 1576 |
+
"learning_rate": 7.170916182651141e-06,
|
| 1577 |
+
"loss": 0.7249,
|
| 1578 |
+
"step": 316
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 57.81818181818182,
|
| 1582 |
+
"grad_norm": 1.0801540613174438,
|
| 1583 |
+
"learning_rate": 7.128896457825364e-06,
|
| 1584 |
+
"loss": 0.6903,
|
| 1585 |
+
"step": 318
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 58.0,
|
| 1589 |
+
"eval_loss": 0.9042022824287415,
|
| 1590 |
+
"eval_runtime": 9.621,
|
| 1591 |
+
"eval_samples_per_second": 2.495,
|
| 1592 |
+
"eval_steps_per_second": 2.495,
|
| 1593 |
+
"step": 319
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 58.18181818181818,
|
| 1597 |
+
"grad_norm": 1.052799105644226,
|
| 1598 |
+
"learning_rate": 7.08669227240909e-06,
|
| 1599 |
+
"loss": 0.7306,
|
| 1600 |
+
"step": 320
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 58.54545454545455,
|
| 1604 |
+
"grad_norm": 1.020494818687439,
|
| 1605 |
+
"learning_rate": 7.04430728323069e-06,
|
| 1606 |
+
"loss": 0.7288,
|
| 1607 |
+
"step": 322
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 58.90909090909091,
|
| 1611 |
+
"grad_norm": 1.0670812129974365,
|
| 1612 |
+
"learning_rate": 7.0017451627844765e-06,
|
| 1613 |
+
"loss": 0.6987,
|
| 1614 |
+
"step": 324
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 58.90909090909091,
|
| 1618 |
+
"eval_loss": 0.9106718897819519,
|
| 1619 |
+
"eval_runtime": 9.6324,
|
| 1620 |
+
"eval_samples_per_second": 2.492,
|
| 1621 |
+
"eval_steps_per_second": 2.492,
|
| 1622 |
+
"step": 324
|
| 1623 |
+
},
|
| 1624 |
+
{
|
| 1625 |
+
"epoch": 59.27272727272727,
|
| 1626 |
+
"grad_norm": 1.0681415796279907,
|
| 1627 |
+
"learning_rate": 6.959009598912493e-06,
|
| 1628 |
+
"loss": 0.6906,
|
| 1629 |
+
"step": 326
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 59.63636363636363,
|
| 1633 |
+
"grad_norm": 1.1053000688552856,
|
| 1634 |
+
"learning_rate": 6.916104294484988e-06,
|
| 1635 |
+
"loss": 0.7063,
|
| 1636 |
+
"step": 328
|
| 1637 |
+
},
|
| 1638 |
+
{
|
| 1639 |
+
"epoch": 60.0,
|
| 1640 |
+
"grad_norm": 1.0191996097564697,
|
| 1641 |
+
"learning_rate": 6.873032967079562e-06,
|
| 1642 |
+
"loss": 0.7141,
|
| 1643 |
+
"step": 330
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 60.0,
|
| 1647 |
+
"eval_loss": 0.9078884124755859,
|
| 1648 |
+
"eval_runtime": 9.6326,
|
| 1649 |
+
"eval_samples_per_second": 2.492,
|
| 1650 |
+
"eval_steps_per_second": 2.492,
|
| 1651 |
+
"step": 330
|
| 1652 |
+
},
|
| 1653 |
+
{
|
| 1654 |
+
"epoch": 60.36363636363637,
|
| 1655 |
+
"grad_norm": 1.0764459371566772,
|
| 1656 |
+
"learning_rate": 6.829799348659061e-06,
|
| 1657 |
+
"loss": 0.7079,
|
| 1658 |
+
"step": 332
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 60.72727272727273,
|
| 1662 |
+
"grad_norm": 1.146618366241455,
|
| 1663 |
+
"learning_rate": 6.7864071852482205e-06,
|
| 1664 |
+
"loss": 0.7023,
|
| 1665 |
+
"step": 334
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 60.90909090909091,
|
| 1669 |
+
"eval_loss": 0.9119828343391418,
|
| 1670 |
+
"eval_runtime": 9.6211,
|
| 1671 |
+
"eval_samples_per_second": 2.495,
|
| 1672 |
+
"eval_steps_per_second": 2.495,
|
| 1673 |
+
"step": 335
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 61.09090909090909,
|
| 1677 |
+
"grad_norm": 1.274398684501648,
|
| 1678 |
+
"learning_rate": 6.7428602366090764e-06,
|
| 1679 |
+
"loss": 0.6856,
|
| 1680 |
+
"step": 336
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 61.45454545454545,
|
| 1684 |
+
"grad_norm": 1.1239506006240845,
|
| 1685 |
+
"learning_rate": 6.699162275915208e-06,
|
| 1686 |
+
"loss": 0.6603,
|
| 1687 |
+
"step": 338
|
| 1688 |
+
},
|
| 1689 |
+
{
|
| 1690 |
+
"epoch": 61.81818181818182,
|
| 1691 |
+
"grad_norm": 1.3075493574142456,
|
| 1692 |
+
"learning_rate": 6.655317089424791e-06,
|
| 1693 |
+
"loss": 0.6945,
|
| 1694 |
+
"step": 340
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 62.0,
|
| 1698 |
+
"eval_loss": 0.9086711406707764,
|
| 1699 |
+
"eval_runtime": 9.6164,
|
| 1700 |
+
"eval_samples_per_second": 2.496,
|
| 1701 |
+
"eval_steps_per_second": 2.496,
|
| 1702 |
+
"step": 341
|
| 1703 |
+
},
|
| 1704 |
+
{
|
| 1705 |
+
"epoch": 62.18181818181818,
|
| 1706 |
+
"grad_norm": 1.1385191679000854,
|
| 1707 |
+
"learning_rate": 6.611328476152557e-06,
|
| 1708 |
+
"loss": 0.7058,
|
| 1709 |
+
"step": 342
|
| 1710 |
+
},
|
| 1711 |
+
{
|
| 1712 |
+
"epoch": 62.54545454545455,
|
| 1713 |
+
"grad_norm": 1.2736291885375977,
|
| 1714 |
+
"learning_rate": 6.567200247540599e-06,
|
| 1715 |
+
"loss": 0.6662,
|
| 1716 |
+
"step": 344
|
| 1717 |
+
},
|
| 1718 |
+
{
|
| 1719 |
+
"epoch": 62.90909090909091,
|
| 1720 |
+
"grad_norm": 1.1537060737609863,
|
| 1721 |
+
"learning_rate": 6.522936227128139e-06,
|
| 1722 |
+
"loss": 0.6897,
|
| 1723 |
+
"step": 346
|
| 1724 |
+
},
|
| 1725 |
+
{
|
| 1726 |
+
"epoch": 62.90909090909091,
|
| 1727 |
+
"eval_loss": 0.9129719734191895,
|
| 1728 |
+
"eval_runtime": 9.6291,
|
| 1729 |
+
"eval_samples_per_second": 2.492,
|
| 1730 |
+
"eval_steps_per_second": 2.492,
|
| 1731 |
+
"step": 346
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 63.27272727272727,
|
| 1735 |
+
"grad_norm": 1.4773812294006348,
|
| 1736 |
+
"learning_rate": 6.4785402502202345e-06,
|
| 1737 |
+
"loss": 0.6822,
|
| 1738 |
+
"step": 348
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 63.63636363636363,
|
| 1742 |
+
"grad_norm": 1.3053030967712402,
|
| 1743 |
+
"learning_rate": 6.434016163555452e-06,
|
| 1744 |
+
"loss": 0.6596,
|
| 1745 |
+
"step": 350
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 64.0,
|
| 1749 |
+
"grad_norm": 1.1616432666778564,
|
| 1750 |
+
"learning_rate": 6.389367824972575e-06,
|
| 1751 |
+
"loss": 0.6597,
|
| 1752 |
+
"step": 352
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 64.0,
|
| 1756 |
+
"eval_loss": 0.9133894443511963,
|
| 1757 |
+
"eval_runtime": 9.6317,
|
| 1758 |
+
"eval_samples_per_second": 2.492,
|
| 1759 |
+
"eval_steps_per_second": 2.492,
|
| 1760 |
+
"step": 352
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 64.36363636363636,
|
| 1764 |
+
"grad_norm": 1.0900788307189941,
|
| 1765 |
+
"learning_rate": 6.344599103076329e-06,
|
| 1766 |
+
"loss": 0.6563,
|
| 1767 |
+
"step": 354
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 64.72727272727273,
|
| 1771 |
+
"grad_norm": 1.2286537885665894,
|
| 1772 |
+
"learning_rate": 6.299713876902188e-06,
|
| 1773 |
+
"loss": 0.6954,
|
| 1774 |
+
"step": 356
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 64.9090909090909,
|
| 1778 |
+
"eval_loss": 0.9120491147041321,
|
| 1779 |
+
"eval_runtime": 9.6347,
|
| 1780 |
+
"eval_samples_per_second": 2.491,
|
| 1781 |
+
"eval_steps_per_second": 2.491,
|
| 1782 |
+
"step": 357
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 64.9090909090909,
|
| 1786 |
+
"step": 357,
|
| 1787 |
+
"total_flos": 8.780093794235187e+16,
|
| 1788 |
+
"train_loss": 1.1563805774146436,
|
| 1789 |
+
"train_runtime": 6696.4639,
|
| 1790 |
+
"train_samples_per_second": 1.971,
|
| 1791 |
+
"train_steps_per_second": 0.112
|
| 1792 |
+
}
|
| 1793 |
+
],
|
| 1794 |
+
"logging_steps": 2,
|
| 1795 |
+
"max_steps": 750,
|
| 1796 |
+
"num_input_tokens_seen": 0,
|
| 1797 |
+
"num_train_epochs": 150,
|
| 1798 |
+
"save_steps": 25,
|
| 1799 |
+
"stateful_callbacks": {
|
| 1800 |
+
"EarlyStoppingCallback": {
|
| 1801 |
+
"args": {
|
| 1802 |
+
"early_stopping_patience": 7,
|
| 1803 |
+
"early_stopping_threshold": 0.0
|
| 1804 |
+
},
|
| 1805 |
+
"attributes": {
|
| 1806 |
+
"early_stopping_patience_counter": 0
|
| 1807 |
+
}
|
| 1808 |
+
},
|
| 1809 |
+
"TrainerControl": {
|
| 1810 |
+
"args": {
|
| 1811 |
+
"should_epoch_stop": false,
|
| 1812 |
+
"should_evaluate": false,
|
| 1813 |
+
"should_log": false,
|
| 1814 |
+
"should_save": true,
|
| 1815 |
+
"should_training_stop": true
|
| 1816 |
+
},
|
| 1817 |
+
"attributes": {}
|
| 1818 |
+
}
|
| 1819 |
+
},
|
| 1820 |
+
"total_flos": 8.780093794235187e+16,
|
| 1821 |
+
"train_batch_size": 1,
|
| 1822 |
+
"trial_name": null,
|
| 1823 |
+
"trial_params": null
|
| 1824 |
+
}
|