Commit
•
dcac8dd
1
Parent(s):
860f62d
Model save
Browse files- README.md +164 -0
- adapter_model.safetensors +1 -1
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +1859 -0
README.md
ADDED
|
@@ -0,0 +1,164 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-2_60-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-2_60-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 an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.0840
|
| 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 |
+
| 1.5658 | 0.6957 | 2 | 1.5854 |
|
| 57 |
+
| 1.5728 | 1.7391 | 5 | 1.5836 |
|
| 58 |
+
| 1.583 | 2.7826 | 8 | 1.5803 |
|
| 59 |
+
| 1.562 | 3.8261 | 11 | 1.5753 |
|
| 60 |
+
| 1.5687 | 4.8696 | 14 | 1.5688 |
|
| 61 |
+
| 1.5495 | 5.9130 | 17 | 1.5600 |
|
| 62 |
+
| 1.5493 | 6.9565 | 20 | 1.5482 |
|
| 63 |
+
| 1.5379 | 8.0 | 23 | 1.5340 |
|
| 64 |
+
| 1.5155 | 8.6957 | 25 | 1.5222 |
|
| 65 |
+
| 1.5131 | 9.7391 | 28 | 1.5057 |
|
| 66 |
+
| 1.4971 | 10.7826 | 31 | 1.4859 |
|
| 67 |
+
| 1.4675 | 11.8261 | 34 | 1.4652 |
|
| 68 |
+
| 1.4518 | 12.8696 | 37 | 1.4474 |
|
| 69 |
+
| 1.4267 | 13.9130 | 40 | 1.4301 |
|
| 70 |
+
| 1.4004 | 14.9565 | 43 | 1.4132 |
|
| 71 |
+
| 1.3993 | 16.0 | 46 | 1.3976 |
|
| 72 |
+
| 1.3748 | 16.6957 | 48 | 1.3881 |
|
| 73 |
+
| 1.3664 | 17.7391 | 51 | 1.3743 |
|
| 74 |
+
| 1.3465 | 18.7826 | 54 | 1.3614 |
|
| 75 |
+
| 1.3407 | 19.8261 | 57 | 1.3488 |
|
| 76 |
+
| 1.32 | 20.8696 | 60 | 1.3369 |
|
| 77 |
+
| 1.305 | 21.9130 | 63 | 1.3247 |
|
| 78 |
+
| 1.281 | 22.9565 | 66 | 1.3119 |
|
| 79 |
+
| 1.2869 | 24.0 | 69 | 1.2986 |
|
| 80 |
+
| 1.2523 | 24.6957 | 71 | 1.2903 |
|
| 81 |
+
| 1.2642 | 25.7391 | 74 | 1.2783 |
|
| 82 |
+
| 1.2323 | 26.7826 | 77 | 1.2657 |
|
| 83 |
+
| 1.2121 | 27.8261 | 80 | 1.2535 |
|
| 84 |
+
| 1.1896 | 28.8696 | 83 | 1.2410 |
|
| 85 |
+
| 1.1678 | 29.9130 | 86 | 1.2283 |
|
| 86 |
+
| 1.1768 | 30.9565 | 89 | 1.2154 |
|
| 87 |
+
| 1.1824 | 32.0 | 92 | 1.2030 |
|
| 88 |
+
| 1.1589 | 32.6957 | 94 | 1.1948 |
|
| 89 |
+
| 1.126 | 33.7391 | 97 | 1.1820 |
|
| 90 |
+
| 1.1059 | 34.7826 | 100 | 1.1694 |
|
| 91 |
+
| 1.1334 | 35.8261 | 103 | 1.1582 |
|
| 92 |
+
| 1.1081 | 36.8696 | 106 | 1.1483 |
|
| 93 |
+
| 1.0794 | 37.9130 | 109 | 1.1392 |
|
| 94 |
+
| 1.0614 | 38.9565 | 112 | 1.1315 |
|
| 95 |
+
| 1.0877 | 40.0 | 115 | 1.1259 |
|
| 96 |
+
| 1.0198 | 40.6957 | 117 | 1.1229 |
|
| 97 |
+
| 1.0538 | 41.7391 | 120 | 1.1193 |
|
| 98 |
+
| 1.0351 | 42.7826 | 123 | 1.1165 |
|
| 99 |
+
| 1.0121 | 43.8261 | 126 | 1.1144 |
|
| 100 |
+
| 1.0475 | 44.8696 | 129 | 1.1125 |
|
| 101 |
+
| 1.035 | 45.9130 | 132 | 1.1105 |
|
| 102 |
+
| 1.0582 | 46.9565 | 135 | 1.1090 |
|
| 103 |
+
| 1.029 | 48.0 | 138 | 1.1072 |
|
| 104 |
+
| 1.0353 | 48.6957 | 140 | 1.1064 |
|
| 105 |
+
| 1.0203 | 49.7391 | 143 | 1.1048 |
|
| 106 |
+
| 1.0313 | 50.7826 | 146 | 1.1035 |
|
| 107 |
+
| 1.0473 | 51.8261 | 149 | 1.1026 |
|
| 108 |
+
| 1.0189 | 52.8696 | 152 | 1.1011 |
|
| 109 |
+
| 1.0088 | 53.9130 | 155 | 1.1001 |
|
| 110 |
+
| 1.0336 | 54.9565 | 158 | 1.0989 |
|
| 111 |
+
| 1.0014 | 56.0 | 161 | 1.0981 |
|
| 112 |
+
| 1.0036 | 56.6957 | 163 | 1.0972 |
|
| 113 |
+
| 1.0266 | 57.7391 | 166 | 1.0962 |
|
| 114 |
+
| 0.9893 | 58.7826 | 169 | 1.0956 |
|
| 115 |
+
| 1.0122 | 59.8261 | 172 | 1.0948 |
|
| 116 |
+
| 1.0456 | 60.8696 | 175 | 1.0939 |
|
| 117 |
+
| 0.9873 | 61.9130 | 178 | 1.0933 |
|
| 118 |
+
| 1.0189 | 62.9565 | 181 | 1.0926 |
|
| 119 |
+
| 1.0325 | 64.0 | 184 | 1.0918 |
|
| 120 |
+
| 1.0081 | 64.6957 | 186 | 1.0912 |
|
| 121 |
+
| 0.995 | 65.7391 | 189 | 1.0908 |
|
| 122 |
+
| 1.0104 | 66.7826 | 192 | 1.0903 |
|
| 123 |
+
| 0.9979 | 67.8261 | 195 | 1.0896 |
|
| 124 |
+
| 0.9927 | 68.8696 | 198 | 1.0893 |
|
| 125 |
+
| 0.9898 | 69.9130 | 201 | 1.0887 |
|
| 126 |
+
| 1.0087 | 70.9565 | 204 | 1.0882 |
|
| 127 |
+
| 0.9903 | 72.0 | 207 | 1.0878 |
|
| 128 |
+
| 1.0198 | 72.6957 | 209 | 1.0877 |
|
| 129 |
+
| 1.0078 | 73.7391 | 212 | 1.0874 |
|
| 130 |
+
| 1.0056 | 74.7826 | 215 | 1.0870 |
|
| 131 |
+
| 1.0114 | 75.8261 | 218 | 1.0867 |
|
| 132 |
+
| 0.9982 | 76.8696 | 221 | 1.0864 |
|
| 133 |
+
| 1.0105 | 77.9130 | 224 | 1.0860 |
|
| 134 |
+
| 1.0033 | 78.9565 | 227 | 1.0859 |
|
| 135 |
+
| 1.0024 | 80.0 | 230 | 1.0858 |
|
| 136 |
+
| 1.0091 | 80.6957 | 232 | 1.0855 |
|
| 137 |
+
| 0.9971 | 81.7391 | 235 | 1.0853 |
|
| 138 |
+
| 0.969 | 82.7826 | 238 | 1.0851 |
|
| 139 |
+
| 1.0242 | 83.8261 | 241 | 1.0847 |
|
| 140 |
+
| 0.9949 | 84.8696 | 244 | 1.0850 |
|
| 141 |
+
| 0.9715 | 85.9130 | 247 | 1.0847 |
|
| 142 |
+
| 1.0164 | 86.9565 | 250 | 1.0846 |
|
| 143 |
+
| 0.9729 | 88.0 | 253 | 1.0845 |
|
| 144 |
+
| 1.0065 | 88.6957 | 255 | 1.0845 |
|
| 145 |
+
| 0.994 | 89.7391 | 258 | 1.0845 |
|
| 146 |
+
| 0.9852 | 90.7826 | 261 | 1.0843 |
|
| 147 |
+
| 0.9755 | 91.8261 | 264 | 1.0842 |
|
| 148 |
+
| 1.0191 | 92.8696 | 267 | 1.0839 |
|
| 149 |
+
| 0.9864 | 93.9130 | 270 | 1.0841 |
|
| 150 |
+
| 0.9773 | 94.9565 | 273 | 1.0841 |
|
| 151 |
+
| 0.9869 | 96.0 | 276 | 1.0842 |
|
| 152 |
+
| 0.986 | 96.6957 | 278 | 1.0841 |
|
| 153 |
+
| 0.9925 | 97.7391 | 281 | 1.0840 |
|
| 154 |
+
| 0.9882 | 98.7826 | 284 | 1.0840 |
|
| 155 |
+
| 0.9917 | 99.8261 | 287 | 1.0840 |
|
| 156 |
+
|
| 157 |
+
|
| 158 |
+
### Framework versions
|
| 159 |
+
|
| 160 |
+
- PEFT 0.12.0
|
| 161 |
+
- Transformers 4.44.0
|
| 162 |
+
- Pytorch 2.1.2+cu121
|
| 163 |
+
- Datasets 2.20.0
|
| 164 |
+
- 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 sha256:14c09c4de54b933757cd5753f1dfc2bad44df8f8e1b9e2dba7bcd68985549d4a
|
| 3 |
size 167832240
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 99.82608695652173,
|
| 3 |
+
"total_flos": 4.445754122074849e+17,
|
| 4 |
+
"train_loss": 1.1405799933011525,
|
| 5 |
+
"train_runtime": 16000.7915,
|
| 6 |
+
"train_samples": 46,
|
| 7 |
+
"train_samples_per_second": 0.431,
|
| 8 |
+
"train_steps_per_second": 0.019
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 99.82608695652173,
|
| 3 |
+
"total_flos": 4.445754122074849e+17,
|
| 4 |
+
"train_loss": 1.1405799933011525,
|
| 5 |
+
"train_runtime": 16000.7915,
|
| 6 |
+
"train_samples": 46,
|
| 7 |
+
"train_samples_per_second": 0.431,
|
| 8 |
+
"train_steps_per_second": 0.019
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1859 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0839496850967407,
|
| 3 |
+
"best_model_checkpoint": "data/Llama-31-8B_task-2_60-samples_config-4_full/checkpoint-267",
|
| 4 |
+
"epoch": 99.82608695652173,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 287,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.34782608695652173,
|
| 13 |
+
"grad_norm": 0.5254858136177063,
|
| 14 |
+
"learning_rate": 3.3333333333333335e-07,
|
| 15 |
+
"loss": 1.6001,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.6956521739130435,
|
| 20 |
+
"grad_norm": 0.48315590620040894,
|
| 21 |
+
"learning_rate": 6.666666666666667e-07,
|
| 22 |
+
"loss": 1.5658,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.6956521739130435,
|
| 27 |
+
"eval_loss": 1.5853713750839233,
|
| 28 |
+
"eval_runtime": 12.9778,
|
| 29 |
+
"eval_samples_per_second": 0.925,
|
| 30 |
+
"eval_steps_per_second": 0.925,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.391304347826087,
|
| 35 |
+
"grad_norm": 0.4942804276943207,
|
| 36 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 37 |
+
"loss": 1.5728,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.7391304347826086,
|
| 42 |
+
"eval_loss": 1.583631992340088,
|
| 43 |
+
"eval_runtime": 12.9766,
|
| 44 |
+
"eval_samples_per_second": 0.925,
|
| 45 |
+
"eval_steps_per_second": 0.925,
|
| 46 |
+
"step": 5
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 2.0869565217391304,
|
| 50 |
+
"grad_norm": 0.5288798809051514,
|
| 51 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 52 |
+
"loss": 1.5934,
|
| 53 |
+
"step": 6
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 2.782608695652174,
|
| 57 |
+
"grad_norm": 0.5049395561218262,
|
| 58 |
+
"learning_rate": 2.666666666666667e-06,
|
| 59 |
+
"loss": 1.583,
|
| 60 |
+
"step": 8
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 2.782608695652174,
|
| 64 |
+
"eval_loss": 1.580271601676941,
|
| 65 |
+
"eval_runtime": 12.9795,
|
| 66 |
+
"eval_samples_per_second": 0.925,
|
| 67 |
+
"eval_steps_per_second": 0.925,
|
| 68 |
+
"step": 8
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 3.4782608695652173,
|
| 72 |
+
"grad_norm": 0.468879371881485,
|
| 73 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 74 |
+
"loss": 1.562,
|
| 75 |
+
"step": 10
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 3.8260869565217392,
|
| 79 |
+
"eval_loss": 1.5752835273742676,
|
| 80 |
+
"eval_runtime": 12.9747,
|
| 81 |
+
"eval_samples_per_second": 0.925,
|
| 82 |
+
"eval_steps_per_second": 0.925,
|
| 83 |
+
"step": 11
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 4.173913043478261,
|
| 87 |
+
"grad_norm": 0.45035144686698914,
|
| 88 |
+
"learning_rate": 4.000000000000001e-06,
|
| 89 |
+
"loss": 1.5779,
|
| 90 |
+
"step": 12
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 4.869565217391305,
|
| 94 |
+
"grad_norm": 0.44937947392463684,
|
| 95 |
+
"learning_rate": 4.666666666666667e-06,
|
| 96 |
+
"loss": 1.5687,
|
| 97 |
+
"step": 14
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 4.869565217391305,
|
| 101 |
+
"eval_loss": 1.5688363313674927,
|
| 102 |
+
"eval_runtime": 12.9875,
|
| 103 |
+
"eval_samples_per_second": 0.924,
|
| 104 |
+
"eval_steps_per_second": 0.924,
|
| 105 |
+
"step": 14
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 5.565217391304348,
|
| 109 |
+
"grad_norm": 0.439909964799881,
|
| 110 |
+
"learning_rate": 5.333333333333334e-06,
|
| 111 |
+
"loss": 1.5495,
|
| 112 |
+
"step": 16
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 5.913043478260869,
|
| 116 |
+
"eval_loss": 1.5600029230117798,
|
| 117 |
+
"eval_runtime": 12.9772,
|
| 118 |
+
"eval_samples_per_second": 0.925,
|
| 119 |
+
"eval_steps_per_second": 0.925,
|
| 120 |
+
"step": 17
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 6.260869565217392,
|
| 124 |
+
"grad_norm": 0.4658964276313782,
|
| 125 |
+
"learning_rate": 6e-06,
|
| 126 |
+
"loss": 1.5541,
|
| 127 |
+
"step": 18
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 6.956521739130435,
|
| 131 |
+
"grad_norm": 0.5037180185317993,
|
| 132 |
+
"learning_rate": 6.666666666666667e-06,
|
| 133 |
+
"loss": 1.5493,
|
| 134 |
+
"step": 20
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 6.956521739130435,
|
| 138 |
+
"eval_loss": 1.548214316368103,
|
| 139 |
+
"eval_runtime": 12.9784,
|
| 140 |
+
"eval_samples_per_second": 0.925,
|
| 141 |
+
"eval_steps_per_second": 0.925,
|
| 142 |
+
"step": 20
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 7.6521739130434785,
|
| 146 |
+
"grad_norm": 0.47590604424476624,
|
| 147 |
+
"learning_rate": 7.333333333333333e-06,
|
| 148 |
+
"loss": 1.5379,
|
| 149 |
+
"step": 22
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 8.0,
|
| 153 |
+
"eval_loss": 1.5340198278427124,
|
| 154 |
+
"eval_runtime": 12.9772,
|
| 155 |
+
"eval_samples_per_second": 0.925,
|
| 156 |
+
"eval_steps_per_second": 0.925,
|
| 157 |
+
"step": 23
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 8.347826086956522,
|
| 161 |
+
"grad_norm": 0.4758809506893158,
|
| 162 |
+
"learning_rate": 8.000000000000001e-06,
|
| 163 |
+
"loss": 1.5155,
|
| 164 |
+
"step": 24
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 8.695652173913043,
|
| 168 |
+
"eval_loss": 1.5222147703170776,
|
| 169 |
+
"eval_runtime": 12.9749,
|
| 170 |
+
"eval_samples_per_second": 0.925,
|
| 171 |
+
"eval_steps_per_second": 0.925,
|
| 172 |
+
"step": 25
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 9.043478260869565,
|
| 176 |
+
"grad_norm": 0.44333091378211975,
|
| 177 |
+
"learning_rate": 8.666666666666668e-06,
|
| 178 |
+
"loss": 1.5287,
|
| 179 |
+
"step": 26
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 9.73913043478261,
|
| 183 |
+
"grad_norm": 0.4040922224521637,
|
| 184 |
+
"learning_rate": 9.333333333333334e-06,
|
| 185 |
+
"loss": 1.5131,
|
| 186 |
+
"step": 28
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 9.73913043478261,
|
| 190 |
+
"eval_loss": 1.5057040452957153,
|
| 191 |
+
"eval_runtime": 12.977,
|
| 192 |
+
"eval_samples_per_second": 0.925,
|
| 193 |
+
"eval_steps_per_second": 0.925,
|
| 194 |
+
"step": 28
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 10.434782608695652,
|
| 198 |
+
"grad_norm": 0.39793452620506287,
|
| 199 |
+
"learning_rate": 1e-05,
|
| 200 |
+
"loss": 1.4971,
|
| 201 |
+
"step": 30
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 10.782608695652174,
|
| 205 |
+
"eval_loss": 1.4859318733215332,
|
| 206 |
+
"eval_runtime": 12.9807,
|
| 207 |
+
"eval_samples_per_second": 0.924,
|
| 208 |
+
"eval_steps_per_second": 0.924,
|
| 209 |
+
"step": 31
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 11.130434782608695,
|
| 213 |
+
"grad_norm": 0.4213944971561432,
|
| 214 |
+
"learning_rate": 9.99864620589731e-06,
|
| 215 |
+
"loss": 1.4727,
|
| 216 |
+
"step": 32
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 11.826086956521738,
|
| 220 |
+
"grad_norm": 0.4004620909690857,
|
| 221 |
+
"learning_rate": 9.994585556692624e-06,
|
| 222 |
+
"loss": 1.4675,
|
| 223 |
+
"step": 34
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 11.826086956521738,
|
| 227 |
+
"eval_loss": 1.4652339220046997,
|
| 228 |
+
"eval_runtime": 12.9758,
|
| 229 |
+
"eval_samples_per_second": 0.925,
|
| 230 |
+
"eval_steps_per_second": 0.925,
|
| 231 |
+
"step": 34
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 12.521739130434783,
|
| 235 |
+
"grad_norm": 0.35341501235961914,
|
| 236 |
+
"learning_rate": 9.987820251299121e-06,
|
| 237 |
+
"loss": 1.4518,
|
| 238 |
+
"step": 36
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 12.869565217391305,
|
| 242 |
+
"eval_loss": 1.4474080801010132,
|
| 243 |
+
"eval_runtime": 12.9771,
|
| 244 |
+
"eval_samples_per_second": 0.925,
|
| 245 |
+
"eval_steps_per_second": 0.925,
|
| 246 |
+
"step": 37
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 13.217391304347826,
|
| 250 |
+
"grad_norm": 0.31634095311164856,
|
| 251 |
+
"learning_rate": 9.978353953249023e-06,
|
| 252 |
+
"loss": 1.4225,
|
| 253 |
+
"step": 38
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 13.91304347826087,
|
| 257 |
+
"grad_norm": 0.32467326521873474,
|
| 258 |
+
"learning_rate": 9.966191788709716e-06,
|
| 259 |
+
"loss": 1.4267,
|
| 260 |
+
"step": 40
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 13.91304347826087,
|
| 264 |
+
"eval_loss": 1.4301291704177856,
|
| 265 |
+
"eval_runtime": 12.9757,
|
| 266 |
+
"eval_samples_per_second": 0.925,
|
| 267 |
+
"eval_steps_per_second": 0.925,
|
| 268 |
+
"step": 40
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 14.608695652173914,
|
| 272 |
+
"grad_norm": 0.3214071989059448,
|
| 273 |
+
"learning_rate": 9.951340343707852e-06,
|
| 274 |
+
"loss": 1.4004,
|
| 275 |
+
"step": 42
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 14.956521739130435,
|
| 279 |
+
"eval_loss": 1.413205623626709,
|
| 280 |
+
"eval_runtime": 12.9784,
|
| 281 |
+
"eval_samples_per_second": 0.925,
|
| 282 |
+
"eval_steps_per_second": 0.925,
|
| 283 |
+
"step": 43
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 15.304347826086957,
|
| 287 |
+
"grad_norm": 0.26766690611839294,
|
| 288 |
+
"learning_rate": 9.933807660562898e-06,
|
| 289 |
+
"loss": 1.3894,
|
| 290 |
+
"step": 44
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 16.0,
|
| 294 |
+
"grad_norm": 0.24698252975940704,
|
| 295 |
+
"learning_rate": 9.913603233532067e-06,
|
| 296 |
+
"loss": 1.3993,
|
| 297 |
+
"step": 46
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 16.0,
|
| 301 |
+
"eval_loss": 1.3975735902786255,
|
| 302 |
+
"eval_runtime": 12.9795,
|
| 303 |
+
"eval_samples_per_second": 0.925,
|
| 304 |
+
"eval_steps_per_second": 0.925,
|
| 305 |
+
"step": 46
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 16.695652173913043,
|
| 309 |
+
"grad_norm": 0.2775205671787262,
|
| 310 |
+
"learning_rate": 9.890738003669029e-06,
|
| 311 |
+
"loss": 1.3748,
|
| 312 |
+
"step": 48
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 16.695652173913043,
|
| 316 |
+
"eval_loss": 1.3880764245986938,
|
| 317 |
+
"eval_runtime": 12.9755,
|
| 318 |
+
"eval_samples_per_second": 0.925,
|
| 319 |
+
"eval_steps_per_second": 0.925,
|
| 320 |
+
"step": 48
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 17.391304347826086,
|
| 324 |
+
"grad_norm": 0.2671767473220825,
|
| 325 |
+
"learning_rate": 9.86522435289912e-06,
|
| 326 |
+
"loss": 1.3664,
|
| 327 |
+
"step": 50
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 17.73913043478261,
|
| 331 |
+
"eval_loss": 1.3743128776550293,
|
| 332 |
+
"eval_runtime": 12.98,
|
| 333 |
+
"eval_samples_per_second": 0.925,
|
| 334 |
+
"eval_steps_per_second": 0.925,
|
| 335 |
+
"step": 51
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 18.08695652173913,
|
| 339 |
+
"grad_norm": 0.23573799431324005,
|
| 340 |
+
"learning_rate": 9.83707609731432e-06,
|
| 341 |
+
"loss": 1.3404,
|
| 342 |
+
"step": 52
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 18.782608695652176,
|
| 346 |
+
"grad_norm": 0.23537954688072205,
|
| 347 |
+
"learning_rate": 9.806308479691595e-06,
|
| 348 |
+
"loss": 1.3465,
|
| 349 |
+
"step": 54
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 18.782608695652176,
|
| 353 |
+
"eval_loss": 1.361410140991211,
|
| 354 |
+
"eval_runtime": 12.9811,
|
| 355 |
+
"eval_samples_per_second": 0.924,
|
| 356 |
+
"eval_steps_per_second": 0.924,
|
| 357 |
+
"step": 54
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 19.47826086956522,
|
| 361 |
+
"grad_norm": 0.24991613626480103,
|
| 362 |
+
"learning_rate": 9.77293816123866e-06,
|
| 363 |
+
"loss": 1.3407,
|
| 364 |
+
"step": 56
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 19.82608695652174,
|
| 368 |
+
"eval_loss": 1.3488320112228394,
|
| 369 |
+
"eval_runtime": 12.9784,
|
| 370 |
+
"eval_samples_per_second": 0.925,
|
| 371 |
+
"eval_steps_per_second": 0.925,
|
| 372 |
+
"step": 57
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 20.17391304347826,
|
| 376 |
+
"grad_norm": 0.22332234680652618,
|
| 377 |
+
"learning_rate": 9.736983212571646e-06,
|
| 378 |
+
"loss": 1.3237,
|
| 379 |
+
"step": 58
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 20.869565217391305,
|
| 383 |
+
"grad_norm": 0.225299671292305,
|
| 384 |
+
"learning_rate": 9.698463103929542e-06,
|
| 385 |
+
"loss": 1.32,
|
| 386 |
+
"step": 60
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 20.869565217391305,
|
| 390 |
+
"eval_loss": 1.3369255065917969,
|
| 391 |
+
"eval_runtime": 12.9791,
|
| 392 |
+
"eval_samples_per_second": 0.925,
|
| 393 |
+
"eval_steps_per_second": 0.925,
|
| 394 |
+
"step": 60
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 21.565217391304348,
|
| 398 |
+
"grad_norm": 0.24724063277244568,
|
| 399 |
+
"learning_rate": 9.657398694630713e-06,
|
| 400 |
+
"loss": 1.305,
|
| 401 |
+
"step": 62
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 21.91304347826087,
|
| 405 |
+
"eval_loss": 1.3247287273406982,
|
| 406 |
+
"eval_runtime": 12.9775,
|
| 407 |
+
"eval_samples_per_second": 0.925,
|
| 408 |
+
"eval_steps_per_second": 0.925,
|
| 409 |
+
"step": 63
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 22.26086956521739,
|
| 413 |
+
"grad_norm": 0.24492307007312775,
|
| 414 |
+
"learning_rate": 9.613812221777212e-06,
|
| 415 |
+
"loss": 1.2923,
|
| 416 |
+
"step": 64
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 22.956521739130434,
|
| 420 |
+
"grad_norm": 0.2448989301919937,
|
| 421 |
+
"learning_rate": 9.567727288213005e-06,
|
| 422 |
+
"loss": 1.281,
|
| 423 |
+
"step": 66
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 22.956521739130434,
|
| 427 |
+
"eval_loss": 1.3119220733642578,
|
| 428 |
+
"eval_runtime": 12.9822,
|
| 429 |
+
"eval_samples_per_second": 0.924,
|
| 430 |
+
"eval_steps_per_second": 0.924,
|
| 431 |
+
"step": 66
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 23.652173913043477,
|
| 435 |
+
"grad_norm": 0.22922120988368988,
|
| 436 |
+
"learning_rate": 9.519168849742603e-06,
|
| 437 |
+
"loss": 1.2869,
|
| 438 |
+
"step": 68
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 24.0,
|
| 442 |
+
"eval_loss": 1.298582911491394,
|
| 443 |
+
"eval_runtime": 12.9756,
|
| 444 |
+
"eval_samples_per_second": 0.925,
|
| 445 |
+
"eval_steps_per_second": 0.925,
|
| 446 |
+
"step": 69
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 24.347826086956523,
|
| 450 |
+
"grad_norm": 0.20991288125514984,
|
| 451 |
+
"learning_rate": 9.468163201617063e-06,
|
| 452 |
+
"loss": 1.2523,
|
| 453 |
+
"step": 70
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 24.695652173913043,
|
| 457 |
+
"eval_loss": 1.2903255224227905,
|
| 458 |
+
"eval_runtime": 12.978,
|
| 459 |
+
"eval_samples_per_second": 0.925,
|
| 460 |
+
"eval_steps_per_second": 0.925,
|
| 461 |
+
"step": 71
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 25.043478260869566,
|
| 465 |
+
"grad_norm": 0.22222064435482025,
|
| 466 |
+
"learning_rate": 9.414737964294636e-06,
|
| 467 |
+
"loss": 1.2628,
|
| 468 |
+
"step": 72
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 25.73913043478261,
|
| 472 |
+
"grad_norm": 0.21490232646465302,
|
| 473 |
+
"learning_rate": 9.358922068483813e-06,
|
| 474 |
+
"loss": 1.2642,
|
| 475 |
+
"step": 74
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 25.73913043478261,
|
| 479 |
+
"eval_loss": 1.278277039527893,
|
| 480 |
+
"eval_runtime": 12.9804,
|
| 481 |
+
"eval_samples_per_second": 0.924,
|
| 482 |
+
"eval_steps_per_second": 0.924,
|
| 483 |
+
"step": 74
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 26.434782608695652,
|
| 487 |
+
"grad_norm": 0.22001975774765015,
|
| 488 |
+
"learning_rate": 9.30074573947683e-06,
|
| 489 |
+
"loss": 1.2323,
|
| 490 |
+
"step": 76
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 26.782608695652176,
|
| 494 |
+
"eval_loss": 1.265702247619629,
|
| 495 |
+
"eval_runtime": 12.9772,
|
| 496 |
+
"eval_samples_per_second": 0.925,
|
| 497 |
+
"eval_steps_per_second": 0.925,
|
| 498 |
+
"step": 77
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 27.130434782608695,
|
| 502 |
+
"grad_norm": 0.20034939050674438,
|
| 503 |
+
"learning_rate": 9.24024048078213e-06,
|
| 504 |
+
"loss": 1.2395,
|
| 505 |
+
"step": 78
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 27.82608695652174,
|
| 509 |
+
"grad_norm": 0.19895507395267487,
|
| 510 |
+
"learning_rate": 9.177439057064684e-06,
|
| 511 |
+
"loss": 1.2121,
|
| 512 |
+
"step": 80
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 27.82608695652174,
|
| 516 |
+
"eval_loss": 1.253515362739563,
|
| 517 |
+
"eval_runtime": 12.9793,
|
| 518 |
+
"eval_samples_per_second": 0.925,
|
| 519 |
+
"eval_steps_per_second": 0.925,
|
| 520 |
+
"step": 80
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 28.52173913043478,
|
| 524 |
+
"grad_norm": 0.19117023050785065,
|
| 525 |
+
"learning_rate": 9.112375476403313e-06,
|
| 526 |
+
"loss": 1.1896,
|
| 527 |
+
"step": 82
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 28.869565217391305,
|
| 531 |
+
"eval_loss": 1.2409998178482056,
|
| 532 |
+
"eval_runtime": 12.9782,
|
| 533 |
+
"eval_samples_per_second": 0.925,
|
| 534 |
+
"eval_steps_per_second": 0.925,
|
| 535 |
+
"step": 83
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 29.217391304347824,
|
| 539 |
+
"grad_norm": 0.2141137570142746,
|
| 540 |
+
"learning_rate": 9.045084971874738e-06,
|
| 541 |
+
"loss": 1.2215,
|
| 542 |
+
"step": 84
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 29.91304347826087,
|
| 546 |
+
"grad_norm": 0.23155109584331512,
|
| 547 |
+
"learning_rate": 8.97560398247424e-06,
|
| 548 |
+
"loss": 1.1678,
|
| 549 |
+
"step": 86
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 29.91304347826087,
|
| 553 |
+
"eval_loss": 1.2283284664154053,
|
| 554 |
+
"eval_runtime": 12.9808,
|
| 555 |
+
"eval_samples_per_second": 0.924,
|
| 556 |
+
"eval_steps_per_second": 0.924,
|
| 557 |
+
"step": 86
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 30.608695652173914,
|
| 561 |
+
"grad_norm": 0.2200462818145752,
|
| 562 |
+
"learning_rate": 8.903970133383297e-06,
|
| 563 |
+
"loss": 1.1768,
|
| 564 |
+
"step": 88
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 30.956521739130434,
|
| 568 |
+
"eval_loss": 1.2153583765029907,
|
| 569 |
+
"eval_runtime": 12.9811,
|
| 570 |
+
"eval_samples_per_second": 0.924,
|
| 571 |
+
"eval_steps_per_second": 0.924,
|
| 572 |
+
"step": 89
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 31.304347826086957,
|
| 576 |
+
"grad_norm": 0.29315873980522156,
|
| 577 |
+
"learning_rate": 8.83022221559489e-06,
|
| 578 |
+
"loss": 1.1623,
|
| 579 |
+
"step": 90
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 32.0,
|
| 583 |
+
"grad_norm": 0.22663454711437225,
|
| 584 |
+
"learning_rate": 8.754400164907496e-06,
|
| 585 |
+
"loss": 1.1824,
|
| 586 |
+
"step": 92
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 32.0,
|
| 590 |
+
"eval_loss": 1.20297372341156,
|
| 591 |
+
"eval_runtime": 12.9813,
|
| 592 |
+
"eval_samples_per_second": 0.924,
|
| 593 |
+
"eval_steps_per_second": 0.924,
|
| 594 |
+
"step": 92
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 32.69565217391305,
|
| 598 |
+
"grad_norm": 0.2229231745004654,
|
| 599 |
+
"learning_rate": 8.676545040299145e-06,
|
| 600 |
+
"loss": 1.1589,
|
| 601 |
+
"step": 94
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 32.69565217391305,
|
| 605 |
+
"eval_loss": 1.1947580575942993,
|
| 606 |
+
"eval_runtime": 12.9744,
|
| 607 |
+
"eval_samples_per_second": 0.925,
|
| 608 |
+
"eval_steps_per_second": 0.925,
|
| 609 |
+
"step": 94
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 33.391304347826086,
|
| 613 |
+
"grad_norm": 0.2454340010881424,
|
| 614 |
+
"learning_rate": 8.596699001693257e-06,
|
| 615 |
+
"loss": 1.126,
|
| 616 |
+
"step": 96
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 33.73913043478261,
|
| 620 |
+
"eval_loss": 1.1819590330123901,
|
| 621 |
+
"eval_runtime": 12.9877,
|
| 622 |
+
"eval_samples_per_second": 0.924,
|
| 623 |
+
"eval_steps_per_second": 0.924,
|
| 624 |
+
"step": 97
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 34.08695652173913,
|
| 628 |
+
"grad_norm": 0.23333889245986938,
|
| 629 |
+
"learning_rate": 8.51490528712831e-06,
|
| 630 |
+
"loss": 1.1243,
|
| 631 |
+
"step": 98
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 34.78260869565217,
|
| 635 |
+
"grad_norm": 0.23953379690647125,
|
| 636 |
+
"learning_rate": 8.43120818934367e-06,
|
| 637 |
+
"loss": 1.1059,
|
| 638 |
+
"step": 100
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 34.78260869565217,
|
| 642 |
+
"eval_loss": 1.169416069984436,
|
| 643 |
+
"eval_runtime": 12.9903,
|
| 644 |
+
"eval_samples_per_second": 0.924,
|
| 645 |
+
"eval_steps_per_second": 0.924,
|
| 646 |
+
"step": 100
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 35.47826086956522,
|
| 650 |
+
"grad_norm": 0.23915378749370575,
|
| 651 |
+
"learning_rate": 8.345653031794292e-06,
|
| 652 |
+
"loss": 1.1334,
|
| 653 |
+
"step": 102
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 35.82608695652174,
|
| 657 |
+
"eval_loss": 1.1582151651382446,
|
| 658 |
+
"eval_runtime": 12.9858,
|
| 659 |
+
"eval_samples_per_second": 0.924,
|
| 660 |
+
"eval_steps_per_second": 0.924,
|
| 661 |
+
"step": 103
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 36.17391304347826,
|
| 665 |
+
"grad_norm": 0.23581968247890472,
|
| 666 |
+
"learning_rate": 8.258286144107277e-06,
|
| 667 |
+
"loss": 1.0911,
|
| 668 |
+
"step": 104
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 36.869565217391305,
|
| 672 |
+
"grad_norm": 0.207149475812912,
|
| 673 |
+
"learning_rate": 8.16915483699355e-06,
|
| 674 |
+
"loss": 1.1081,
|
| 675 |
+
"step": 106
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 36.869565217391305,
|
| 679 |
+
"eval_loss": 1.1483094692230225,
|
| 680 |
+
"eval_runtime": 12.9841,
|
| 681 |
+
"eval_samples_per_second": 0.924,
|
| 682 |
+
"eval_steps_per_second": 0.924,
|
| 683 |
+
"step": 106
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 37.56521739130435,
|
| 687 |
+
"grad_norm": 0.20900563895702362,
|
| 688 |
+
"learning_rate": 8.078307376628292e-06,
|
| 689 |
+
"loss": 1.0794,
|
| 690 |
+
"step": 108
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 37.91304347826087,
|
| 694 |
+
"eval_loss": 1.139157772064209,
|
| 695 |
+
"eval_runtime": 12.9828,
|
| 696 |
+
"eval_samples_per_second": 0.924,
|
| 697 |
+
"eval_steps_per_second": 0.924,
|
| 698 |
+
"step": 109
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 38.26086956521739,
|
| 702 |
+
"grad_norm": 0.19496272504329681,
|
| 703 |
+
"learning_rate": 7.985792958513932e-06,
|
| 704 |
+
"loss": 1.0814,
|
| 705 |
+
"step": 110
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 38.95652173913044,
|
| 709 |
+
"grad_norm": 0.20283730328083038,
|
| 710 |
+
"learning_rate": 7.891661680839932e-06,
|
| 711 |
+
"loss": 1.0614,
|
| 712 |
+
"step": 112
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 38.95652173913044,
|
| 716 |
+
"eval_loss": 1.1314579248428345,
|
| 717 |
+
"eval_runtime": 13.0034,
|
| 718 |
+
"eval_samples_per_second": 0.923,
|
| 719 |
+
"eval_steps_per_second": 0.923,
|
| 720 |
+
"step": 112
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 39.65217391304348,
|
| 724 |
+
"grad_norm": 0.18000271916389465,
|
| 725 |
+
"learning_rate": 7.795964517353734e-06,
|
| 726 |
+
"loss": 1.0877,
|
| 727 |
+
"step": 114
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 40.0,
|
| 731 |
+
"eval_loss": 1.1258946657180786,
|
| 732 |
+
"eval_runtime": 12.9887,
|
| 733 |
+
"eval_samples_per_second": 0.924,
|
| 734 |
+
"eval_steps_per_second": 0.924,
|
| 735 |
+
"step": 115
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 40.34782608695652,
|
| 739 |
+
"grad_norm": 0.1749521791934967,
|
| 740 |
+
"learning_rate": 7.698753289757565e-06,
|
| 741 |
+
"loss": 1.0198,
|
| 742 |
+
"step": 116
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 40.69565217391305,
|
| 746 |
+
"eval_loss": 1.122938632965088,
|
| 747 |
+
"eval_runtime": 12.988,
|
| 748 |
+
"eval_samples_per_second": 0.924,
|
| 749 |
+
"eval_steps_per_second": 0.924,
|
| 750 |
+
"step": 117
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 41.04347826086956,
|
| 754 |
+
"grad_norm": 0.16494785249233246,
|
| 755 |
+
"learning_rate": 7.600080639646077e-06,
|
| 756 |
+
"loss": 1.0862,
|
| 757 |
+
"step": 118
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 41.73913043478261,
|
| 761 |
+
"grad_norm": 0.1447688788175583,
|
| 762 |
+
"learning_rate": 7.500000000000001e-06,
|
| 763 |
+
"loss": 1.0538,
|
| 764 |
+
"step": 120
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 41.73913043478261,
|
| 768 |
+
"eval_loss": 1.1193265914916992,
|
| 769 |
+
"eval_runtime": 12.9856,
|
| 770 |
+
"eval_samples_per_second": 0.924,
|
| 771 |
+
"eval_steps_per_second": 0.924,
|
| 772 |
+
"step": 120
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 42.43478260869565,
|
| 776 |
+
"grad_norm": 0.1363561749458313,
|
| 777 |
+
"learning_rate": 7.398565566251232e-06,
|
| 778 |
+
"loss": 1.0351,
|
| 779 |
+
"step": 122
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 42.78260869565217,
|
| 783 |
+
"eval_loss": 1.116489291191101,
|
| 784 |
+
"eval_runtime": 12.9859,
|
| 785 |
+
"eval_samples_per_second": 0.924,
|
| 786 |
+
"eval_steps_per_second": 0.924,
|
| 787 |
+
"step": 123
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 43.130434782608695,
|
| 791 |
+
"grad_norm": 0.149055615067482,
|
| 792 |
+
"learning_rate": 7.295832266935059e-06,
|
| 793 |
+
"loss": 1.0684,
|
| 794 |
+
"step": 124
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 43.82608695652174,
|
| 798 |
+
"grad_norm": 0.12285248190164566,
|
| 799 |
+
"learning_rate": 7.191855733945388e-06,
|
| 800 |
+
"loss": 1.0121,
|
| 801 |
+
"step": 126
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 43.82608695652174,
|
| 805 |
+
"eval_loss": 1.1143923997879028,
|
| 806 |
+
"eval_runtime": 12.9844,
|
| 807 |
+
"eval_samples_per_second": 0.924,
|
| 808 |
+
"eval_steps_per_second": 0.924,
|
| 809 |
+
"step": 126
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 44.52173913043478,
|
| 813 |
+
"grad_norm": 0.13907888531684875,
|
| 814 |
+
"learning_rate": 7.08669227240909e-06,
|
| 815 |
+
"loss": 1.0475,
|
| 816 |
+
"step": 128
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 44.869565217391305,
|
| 820 |
+
"eval_loss": 1.1124660968780518,
|
| 821 |
+
"eval_runtime": 12.9826,
|
| 822 |
+
"eval_samples_per_second": 0.924,
|
| 823 |
+
"eval_steps_per_second": 0.924,
|
| 824 |
+
"step": 129
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 45.21739130434783,
|
| 828 |
+
"grad_norm": 0.12828341126441956,
|
| 829 |
+
"learning_rate": 6.980398830195785e-06,
|
| 830 |
+
"loss": 1.0647,
|
| 831 |
+
"step": 130
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 45.91304347826087,
|
| 835 |
+
"grad_norm": 0.11993666738271713,
|
| 836 |
+
"learning_rate": 6.873032967079562e-06,
|
| 837 |
+
"loss": 1.035,
|
| 838 |
+
"step": 132
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 45.91304347826087,
|
| 842 |
+
"eval_loss": 1.1105235815048218,
|
| 843 |
+
"eval_runtime": 12.9835,
|
| 844 |
+
"eval_samples_per_second": 0.924,
|
| 845 |
+
"eval_steps_per_second": 0.924,
|
| 846 |
+
"step": 132
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 46.608695652173914,
|
| 850 |
+
"grad_norm": 0.11968977749347687,
|
| 851 |
+
"learning_rate": 6.7646528235693445e-06,
|
| 852 |
+
"loss": 1.0582,
|
| 853 |
+
"step": 134
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 46.95652173913044,
|
| 857 |
+
"eval_loss": 1.1090105772018433,
|
| 858 |
+
"eval_runtime": 12.981,
|
| 859 |
+
"eval_samples_per_second": 0.924,
|
| 860 |
+
"eval_steps_per_second": 0.924,
|
| 861 |
+
"step": 135
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 47.30434782608695,
|
| 865 |
+
"grad_norm": 0.12057274580001831,
|
| 866 |
+
"learning_rate": 6.655317089424791e-06,
|
| 867 |
+
"loss": 1.0257,
|
| 868 |
+
"step": 136
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 48.0,
|
| 872 |
+
"grad_norm": 0.13167637586593628,
|
| 873 |
+
"learning_rate": 6.545084971874738e-06,
|
| 874 |
+
"loss": 1.029,
|
| 875 |
+
"step": 138
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 48.0,
|
| 879 |
+
"eval_loss": 1.10718834400177,
|
| 880 |
+
"eval_runtime": 12.9849,
|
| 881 |
+
"eval_samples_per_second": 0.924,
|
| 882 |
+
"eval_steps_per_second": 0.924,
|
| 883 |
+
"step": 138
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 48.69565217391305,
|
| 887 |
+
"grad_norm": 0.11730153858661652,
|
| 888 |
+
"learning_rate": 6.434016163555452e-06,
|
| 889 |
+
"loss": 1.0353,
|
| 890 |
+
"step": 140
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 48.69565217391305,
|
| 894 |
+
"eval_loss": 1.1063708066940308,
|
| 895 |
+
"eval_runtime": 12.9872,
|
| 896 |
+
"eval_samples_per_second": 0.924,
|
| 897 |
+
"eval_steps_per_second": 0.924,
|
| 898 |
+
"step": 140
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 49.391304347826086,
|
| 902 |
+
"grad_norm": 0.1166403666138649,
|
| 903 |
+
"learning_rate": 6.322170810186013e-06,
|
| 904 |
+
"loss": 1.0203,
|
| 905 |
+
"step": 142
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 49.73913043478261,
|
| 909 |
+
"eval_loss": 1.1048336029052734,
|
| 910 |
+
"eval_runtime": 12.9919,
|
| 911 |
+
"eval_samples_per_second": 0.924,
|
| 912 |
+
"eval_steps_per_second": 0.924,
|
| 913 |
+
"step": 143
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 50.08695652173913,
|
| 917 |
+
"grad_norm": 0.13392803072929382,
|
| 918 |
+
"learning_rate": 6.209609477998339e-06,
|
| 919 |
+
"loss": 1.0411,
|
| 920 |
+
"step": 144
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 50.78260869565217,
|
| 924 |
+
"grad_norm": 0.11808019131422043,
|
| 925 |
+
"learning_rate": 6.0963931209395165e-06,
|
| 926 |
+
"loss": 1.0313,
|
| 927 |
+
"step": 146
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 50.78260869565217,
|
| 931 |
+
"eval_loss": 1.1034945249557495,
|
| 932 |
+
"eval_runtime": 12.9911,
|
| 933 |
+
"eval_samples_per_second": 0.924,
|
| 934 |
+
"eval_steps_per_second": 0.924,
|
| 935 |
+
"step": 146
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 51.47826086956522,
|
| 939 |
+
"grad_norm": 0.12019839882850647,
|
| 940 |
+
"learning_rate": 5.982583047664151e-06,
|
| 941 |
+
"loss": 1.0473,
|
| 942 |
+
"step": 148
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 51.82608695652174,
|
| 946 |
+
"eval_loss": 1.1025954484939575,
|
| 947 |
+
"eval_runtime": 12.987,
|
| 948 |
+
"eval_samples_per_second": 0.924,
|
| 949 |
+
"eval_steps_per_second": 0.924,
|
| 950 |
+
"step": 149
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 52.17391304347826,
|
| 954 |
+
"grad_norm": 0.13823947310447693,
|
| 955 |
+
"learning_rate": 5.8682408883346535e-06,
|
| 956 |
+
"loss": 1.0099,
|
| 957 |
+
"step": 150
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 52.869565217391305,
|
| 961 |
+
"grad_norm": 0.13493500649929047,
|
| 962 |
+
"learning_rate": 5.753428561247416e-06,
|
| 963 |
+
"loss": 1.0189,
|
| 964 |
+
"step": 152
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 52.869565217391305,
|
| 968 |
+
"eval_loss": 1.1011220216751099,
|
| 969 |
+
"eval_runtime": 12.9858,
|
| 970 |
+
"eval_samples_per_second": 0.924,
|
| 971 |
+
"eval_steps_per_second": 0.924,
|
| 972 |
+
"step": 152
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 53.56521739130435,
|
| 976 |
+
"grad_norm": 0.11930125206708908,
|
| 977 |
+
"learning_rate": 5.638208239302975e-06,
|
| 978 |
+
"loss": 1.0088,
|
| 979 |
+
"step": 154
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 53.91304347826087,
|
| 983 |
+
"eval_loss": 1.100091576576233,
|
| 984 |
+
"eval_runtime": 12.9925,
|
| 985 |
+
"eval_samples_per_second": 0.924,
|
| 986 |
+
"eval_steps_per_second": 0.924,
|
| 987 |
+
"step": 155
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 54.26086956521739,
|
| 991 |
+
"grad_norm": 0.1283315271139145,
|
| 992 |
+
"learning_rate": 5.522642316338268e-06,
|
| 993 |
+
"loss": 1.0471,
|
| 994 |
+
"step": 156
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 54.95652173913044,
|
| 998 |
+
"grad_norm": 0.12327709794044495,
|
| 999 |
+
"learning_rate": 5.406793373339292e-06,
|
| 1000 |
+
"loss": 1.0336,
|
| 1001 |
+
"step": 158
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 54.95652173913044,
|
| 1005 |
+
"eval_loss": 1.0989197492599487,
|
| 1006 |
+
"eval_runtime": 12.9836,
|
| 1007 |
+
"eval_samples_per_second": 0.924,
|
| 1008 |
+
"eval_steps_per_second": 0.924,
|
| 1009 |
+
"step": 158
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 55.65217391304348,
|
| 1013 |
+
"grad_norm": 0.1234331727027893,
|
| 1014 |
+
"learning_rate": 5.290724144552379e-06,
|
| 1015 |
+
"loss": 1.0014,
|
| 1016 |
+
"step": 160
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 56.0,
|
| 1020 |
+
"eval_loss": 1.098119854927063,
|
| 1021 |
+
"eval_runtime": 12.9883,
|
| 1022 |
+
"eval_samples_per_second": 0.924,
|
| 1023 |
+
"eval_steps_per_second": 0.924,
|
| 1024 |
+
"step": 161
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 56.34782608695652,
|
| 1028 |
+
"grad_norm": 0.1393013894557953,
|
| 1029 |
+
"learning_rate": 5.174497483512506e-06,
|
| 1030 |
+
"loss": 1.0036,
|
| 1031 |
+
"step": 162
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 56.69565217391305,
|
| 1035 |
+
"eval_loss": 1.0972312688827515,
|
| 1036 |
+
"eval_runtime": 12.9843,
|
| 1037 |
+
"eval_samples_per_second": 0.924,
|
| 1038 |
+
"eval_steps_per_second": 0.924,
|
| 1039 |
+
"step": 163
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 57.04347826086956,
|
| 1043 |
+
"grad_norm": 0.12967315316200256,
|
| 1044 |
+
"learning_rate": 5.0581763290069865e-06,
|
| 1045 |
+
"loss": 1.0466,
|
| 1046 |
+
"step": 164
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 57.73913043478261,
|
| 1050 |
+
"grad_norm": 0.1203417107462883,
|
| 1051 |
+
"learning_rate": 4.941823670993016e-06,
|
| 1052 |
+
"loss": 1.0266,
|
| 1053 |
+
"step": 166
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 57.73913043478261,
|
| 1057 |
+
"eval_loss": 1.0962202548980713,
|
| 1058 |
+
"eval_runtime": 12.984,
|
| 1059 |
+
"eval_samples_per_second": 0.924,
|
| 1060 |
+
"eval_steps_per_second": 0.924,
|
| 1061 |
+
"step": 166
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 58.43478260869565,
|
| 1065 |
+
"grad_norm": 0.12664881348609924,
|
| 1066 |
+
"learning_rate": 4.825502516487497e-06,
|
| 1067 |
+
"loss": 0.9893,
|
| 1068 |
+
"step": 168
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 58.78260869565217,
|
| 1072 |
+
"eval_loss": 1.0956058502197266,
|
| 1073 |
+
"eval_runtime": 12.983,
|
| 1074 |
+
"eval_samples_per_second": 0.924,
|
| 1075 |
+
"eval_steps_per_second": 0.924,
|
| 1076 |
+
"step": 169
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 59.130434782608695,
|
| 1080 |
+
"grad_norm": 0.1268896907567978,
|
| 1081 |
+
"learning_rate": 4.7092758554476215e-06,
|
| 1082 |
+
"loss": 1.0363,
|
| 1083 |
+
"step": 170
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 59.82608695652174,
|
| 1087 |
+
"grad_norm": 0.12260066717863083,
|
| 1088 |
+
"learning_rate": 4.59320662666071e-06,
|
| 1089 |
+
"loss": 1.0122,
|
| 1090 |
+
"step": 172
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 59.82608695652174,
|
| 1094 |
+
"eval_loss": 1.0947729349136353,
|
| 1095 |
+
"eval_runtime": 12.9887,
|
| 1096 |
+
"eval_samples_per_second": 0.924,
|
| 1097 |
+
"eval_steps_per_second": 0.924,
|
| 1098 |
+
"step": 172
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 60.52173913043478,
|
| 1102 |
+
"grad_norm": 0.12348895519971848,
|
| 1103 |
+
"learning_rate": 4.477357683661734e-06,
|
| 1104 |
+
"loss": 1.0456,
|
| 1105 |
+
"step": 174
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 60.869565217391305,
|
| 1109 |
+
"eval_loss": 1.0938516855239868,
|
| 1110 |
+
"eval_runtime": 12.9852,
|
| 1111 |
+
"eval_samples_per_second": 0.924,
|
| 1112 |
+
"eval_steps_per_second": 0.924,
|
| 1113 |
+
"step": 175
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 61.21739130434783,
|
| 1117 |
+
"grad_norm": 0.1181364431977272,
|
| 1118 |
+
"learning_rate": 4.361791760697027e-06,
|
| 1119 |
+
"loss": 1.0021,
|
| 1120 |
+
"step": 176
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 61.91304347826087,
|
| 1124 |
+
"grad_norm": 0.12426912784576416,
|
| 1125 |
+
"learning_rate": 4.246571438752585e-06,
|
| 1126 |
+
"loss": 0.9873,
|
| 1127 |
+
"step": 178
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 61.91304347826087,
|
| 1131 |
+
"eval_loss": 1.0932997465133667,
|
| 1132 |
+
"eval_runtime": 12.9851,
|
| 1133 |
+
"eval_samples_per_second": 0.924,
|
| 1134 |
+
"eval_steps_per_second": 0.924,
|
| 1135 |
+
"step": 178
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 62.608695652173914,
|
| 1139 |
+
"grad_norm": 0.12317227572202682,
|
| 1140 |
+
"learning_rate": 4.131759111665349e-06,
|
| 1141 |
+
"loss": 1.0189,
|
| 1142 |
+
"step": 180
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 62.95652173913044,
|
| 1146 |
+
"eval_loss": 1.0926170349121094,
|
| 1147 |
+
"eval_runtime": 12.9854,
|
| 1148 |
+
"eval_samples_per_second": 0.924,
|
| 1149 |
+
"eval_steps_per_second": 0.924,
|
| 1150 |
+
"step": 181
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 63.30434782608695,
|
| 1154 |
+
"grad_norm": 0.14774170517921448,
|
| 1155 |
+
"learning_rate": 4.017416952335849e-06,
|
| 1156 |
+
"loss": 0.9927,
|
| 1157 |
+
"step": 182
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 64.0,
|
| 1161 |
+
"grad_norm": 0.12388727813959122,
|
| 1162 |
+
"learning_rate": 3.903606879060483e-06,
|
| 1163 |
+
"loss": 1.0325,
|
| 1164 |
+
"step": 184
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 64.0,
|
| 1168 |
+
"eval_loss": 1.0917848348617554,
|
| 1169 |
+
"eval_runtime": 12.981,
|
| 1170 |
+
"eval_samples_per_second": 0.924,
|
| 1171 |
+
"eval_steps_per_second": 0.924,
|
| 1172 |
+
"step": 184
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 64.69565217391305,
|
| 1176 |
+
"grad_norm": 0.12087590992450714,
|
| 1177 |
+
"learning_rate": 3.790390522001662e-06,
|
| 1178 |
+
"loss": 1.0081,
|
| 1179 |
+
"step": 186
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 64.69565217391305,
|
| 1183 |
+
"eval_loss": 1.0912106037139893,
|
| 1184 |
+
"eval_runtime": 12.9845,
|
| 1185 |
+
"eval_samples_per_second": 0.924,
|
| 1186 |
+
"eval_steps_per_second": 0.924,
|
| 1187 |
+
"step": 186
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 65.3913043478261,
|
| 1191 |
+
"grad_norm": 0.12642121315002441,
|
| 1192 |
+
"learning_rate": 3.6778291898139907e-06,
|
| 1193 |
+
"loss": 0.995,
|
| 1194 |
+
"step": 188
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 65.73913043478261,
|
| 1198 |
+
"eval_loss": 1.0907906293869019,
|
| 1199 |
+
"eval_runtime": 12.9837,
|
| 1200 |
+
"eval_samples_per_second": 0.924,
|
| 1201 |
+
"eval_steps_per_second": 0.924,
|
| 1202 |
+
"step": 189
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 66.08695652173913,
|
| 1206 |
+
"grad_norm": 0.13900116086006165,
|
| 1207 |
+
"learning_rate": 3.5659838364445505e-06,
|
| 1208 |
+
"loss": 1.0352,
|
| 1209 |
+
"step": 190
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 66.78260869565217,
|
| 1213 |
+
"grad_norm": 0.13428539037704468,
|
| 1214 |
+
"learning_rate": 3.4549150281252635e-06,
|
| 1215 |
+
"loss": 1.0104,
|
| 1216 |
+
"step": 192
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 66.78260869565217,
|
| 1220 |
+
"eval_loss": 1.0903018712997437,
|
| 1221 |
+
"eval_runtime": 12.9828,
|
| 1222 |
+
"eval_samples_per_second": 0.924,
|
| 1223 |
+
"eval_steps_per_second": 0.924,
|
| 1224 |
+
"step": 192
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 67.47826086956522,
|
| 1228 |
+
"grad_norm": 0.12461841106414795,
|
| 1229 |
+
"learning_rate": 3.3446829105752103e-06,
|
| 1230 |
+
"loss": 0.9979,
|
| 1231 |
+
"step": 194
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 67.82608695652173,
|
| 1235 |
+
"eval_loss": 1.089614748954773,
|
| 1236 |
+
"eval_runtime": 12.9828,
|
| 1237 |
+
"eval_samples_per_second": 0.924,
|
| 1238 |
+
"eval_steps_per_second": 0.924,
|
| 1239 |
+
"step": 195
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 68.17391304347827,
|
| 1243 |
+
"grad_norm": 0.13673454523086548,
|
| 1244 |
+
"learning_rate": 3.2353471764306567e-06,
|
| 1245 |
+
"loss": 1.015,
|
| 1246 |
+
"step": 196
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 68.8695652173913,
|
| 1250 |
+
"grad_norm": 0.12500186264514923,
|
| 1251 |
+
"learning_rate": 3.12696703292044e-06,
|
| 1252 |
+
"loss": 0.9927,
|
| 1253 |
+
"step": 198
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 68.8695652173913,
|
| 1257 |
+
"eval_loss": 1.0892704725265503,
|
| 1258 |
+
"eval_runtime": 12.986,
|
| 1259 |
+
"eval_samples_per_second": 0.924,
|
| 1260 |
+
"eval_steps_per_second": 0.924,
|
| 1261 |
+
"step": 198
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 69.56521739130434,
|
| 1265 |
+
"grad_norm": 0.12714624404907227,
|
| 1266 |
+
"learning_rate": 3.019601169804216e-06,
|
| 1267 |
+
"loss": 0.9898,
|
| 1268 |
+
"step": 200
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 69.91304347826087,
|
| 1272 |
+
"eval_loss": 1.0887213945388794,
|
| 1273 |
+
"eval_runtime": 12.9821,
|
| 1274 |
+
"eval_samples_per_second": 0.924,
|
| 1275 |
+
"eval_steps_per_second": 0.924,
|
| 1276 |
+
"step": 201
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 70.26086956521739,
|
| 1280 |
+
"grad_norm": 0.1471695601940155,
|
| 1281 |
+
"learning_rate": 2.9133077275909112e-06,
|
| 1282 |
+
"loss": 1.0112,
|
| 1283 |
+
"step": 202
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 70.95652173913044,
|
| 1287 |
+
"grad_norm": 0.12886075675487518,
|
| 1288 |
+
"learning_rate": 2.8081442660546126e-06,
|
| 1289 |
+
"loss": 1.0087,
|
| 1290 |
+
"step": 204
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 70.95652173913044,
|
| 1294 |
+
"eval_loss": 1.0882389545440674,
|
| 1295 |
+
"eval_runtime": 12.9829,
|
| 1296 |
+
"eval_samples_per_second": 0.924,
|
| 1297 |
+
"eval_steps_per_second": 0.924,
|
| 1298 |
+
"step": 204
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 71.65217391304348,
|
| 1302 |
+
"grad_norm": 0.13256506621837616,
|
| 1303 |
+
"learning_rate": 2.7041677330649408e-06,
|
| 1304 |
+
"loss": 0.9903,
|
| 1305 |
+
"step": 206
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 72.0,
|
| 1309 |
+
"eval_loss": 1.0877516269683838,
|
| 1310 |
+
"eval_runtime": 12.9825,
|
| 1311 |
+
"eval_samples_per_second": 0.924,
|
| 1312 |
+
"eval_steps_per_second": 0.924,
|
| 1313 |
+
"step": 207
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 72.34782608695652,
|
| 1317 |
+
"grad_norm": 0.131199449300766,
|
| 1318 |
+
"learning_rate": 2.601434433748771e-06,
|
| 1319 |
+
"loss": 1.0198,
|
| 1320 |
+
"step": 208
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 72.69565217391305,
|
| 1324 |
+
"eval_loss": 1.0877233743667603,
|
| 1325 |
+
"eval_runtime": 12.9886,
|
| 1326 |
+
"eval_samples_per_second": 0.924,
|
| 1327 |
+
"eval_steps_per_second": 0.924,
|
| 1328 |
+
"step": 209
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 73.04347826086956,
|
| 1332 |
+
"grad_norm": 0.12681709229946136,
|
| 1333 |
+
"learning_rate": 2.5000000000000015e-06,
|
| 1334 |
+
"loss": 0.9942,
|
| 1335 |
+
"step": 210
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 73.73913043478261,
|
| 1339 |
+
"grad_norm": 0.12825633585453033,
|
| 1340 |
+
"learning_rate": 2.3999193603539234e-06,
|
| 1341 |
+
"loss": 1.0078,
|
| 1342 |
+
"step": 212
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 73.73913043478261,
|
| 1346 |
+
"eval_loss": 1.0873947143554688,
|
| 1347 |
+
"eval_runtime": 12.985,
|
| 1348 |
+
"eval_samples_per_second": 0.924,
|
| 1349 |
+
"eval_steps_per_second": 0.924,
|
| 1350 |
+
"step": 212
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 74.43478260869566,
|
| 1354 |
+
"grad_norm": 0.12875820696353912,
|
| 1355 |
+
"learning_rate": 2.3012467102424373e-06,
|
| 1356 |
+
"loss": 1.0056,
|
| 1357 |
+
"step": 214
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 74.78260869565217,
|
| 1361 |
+
"eval_loss": 1.086978793144226,
|
| 1362 |
+
"eval_runtime": 12.9911,
|
| 1363 |
+
"eval_samples_per_second": 0.924,
|
| 1364 |
+
"eval_steps_per_second": 0.924,
|
| 1365 |
+
"step": 215
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 75.1304347826087,
|
| 1369 |
+
"grad_norm": 0.16595281660556793,
|
| 1370 |
+
"learning_rate": 2.204035482646267e-06,
|
| 1371 |
+
"loss": 0.9857,
|
| 1372 |
+
"step": 216
|
| 1373 |
+
},
|
| 1374 |
+
{
|
| 1375 |
+
"epoch": 75.82608695652173,
|
| 1376 |
+
"grad_norm": 0.1281590312719345,
|
| 1377 |
+
"learning_rate": 2.1083383191600676e-06,
|
| 1378 |
+
"loss": 1.0114,
|
| 1379 |
+
"step": 218
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 75.82608695652173,
|
| 1383 |
+
"eval_loss": 1.0867377519607544,
|
| 1384 |
+
"eval_runtime": 12.9863,
|
| 1385 |
+
"eval_samples_per_second": 0.924,
|
| 1386 |
+
"eval_steps_per_second": 0.924,
|
| 1387 |
+
"step": 218
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 76.52173913043478,
|
| 1391 |
+
"grad_norm": 0.1323501169681549,
|
| 1392 |
+
"learning_rate": 2.0142070414860704e-06,
|
| 1393 |
+
"loss": 0.9982,
|
| 1394 |
+
"step": 220
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 76.8695652173913,
|
| 1398 |
+
"eval_loss": 1.0864088535308838,
|
| 1399 |
+
"eval_runtime": 12.9841,
|
| 1400 |
+
"eval_samples_per_second": 0.924,
|
| 1401 |
+
"eval_steps_per_second": 0.924,
|
| 1402 |
+
"step": 221
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 77.21739130434783,
|
| 1406 |
+
"grad_norm": 0.1450796127319336,
|
| 1407 |
+
"learning_rate": 1.9216926233717087e-06,
|
| 1408 |
+
"loss": 0.974,
|
| 1409 |
+
"step": 222
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 77.91304347826087,
|
| 1413 |
+
"grad_norm": 0.13413220643997192,
|
| 1414 |
+
"learning_rate": 1.8308451630064484e-06,
|
| 1415 |
+
"loss": 1.0105,
|
| 1416 |
+
"step": 224
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 77.91304347826087,
|
| 1420 |
+
"eval_loss": 1.086008906364441,
|
| 1421 |
+
"eval_runtime": 13.0104,
|
| 1422 |
+
"eval_samples_per_second": 0.922,
|
| 1423 |
+
"eval_steps_per_second": 0.922,
|
| 1424 |
+
"step": 224
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 78.6086956521739,
|
| 1428 |
+
"grad_norm": 0.1377415508031845,
|
| 1429 |
+
"learning_rate": 1.7417138558927244e-06,
|
| 1430 |
+
"loss": 1.0033,
|
| 1431 |
+
"step": 226
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 78.95652173913044,
|
| 1435 |
+
"eval_loss": 1.085876226425171,
|
| 1436 |
+
"eval_runtime": 12.9858,
|
| 1437 |
+
"eval_samples_per_second": 0.924,
|
| 1438 |
+
"eval_steps_per_second": 0.924,
|
| 1439 |
+
"step": 227
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 79.30434782608695,
|
| 1443 |
+
"grad_norm": 0.13374638557434082,
|
| 1444 |
+
"learning_rate": 1.6543469682057105e-06,
|
| 1445 |
+
"loss": 0.9876,
|
| 1446 |
+
"step": 228
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 80.0,
|
| 1450 |
+
"grad_norm": 0.12589867413043976,
|
| 1451 |
+
"learning_rate": 1.5687918106563326e-06,
|
| 1452 |
+
"loss": 1.0024,
|
| 1453 |
+
"step": 230
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 80.0,
|
| 1457 |
+
"eval_loss": 1.0857700109481812,
|
| 1458 |
+
"eval_runtime": 12.9853,
|
| 1459 |
+
"eval_samples_per_second": 0.924,
|
| 1460 |
+
"eval_steps_per_second": 0.924,
|
| 1461 |
+
"step": 230
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 80.69565217391305,
|
| 1465 |
+
"grad_norm": 0.1440684199333191,
|
| 1466 |
+
"learning_rate": 1.4850947128716914e-06,
|
| 1467 |
+
"loss": 1.0091,
|
| 1468 |
+
"step": 232
|
| 1469 |
+
},
|
| 1470 |
+
{
|
| 1471 |
+
"epoch": 80.69565217391305,
|
| 1472 |
+
"eval_loss": 1.0854946374893188,
|
| 1473 |
+
"eval_runtime": 12.994,
|
| 1474 |
+
"eval_samples_per_second": 0.924,
|
| 1475 |
+
"eval_steps_per_second": 0.924,
|
| 1476 |
+
"step": 232
|
| 1477 |
+
},
|
| 1478 |
+
{
|
| 1479 |
+
"epoch": 81.3913043478261,
|
| 1480 |
+
"grad_norm": 0.13353127241134644,
|
| 1481 |
+
"learning_rate": 1.4033009983067454e-06,
|
| 1482 |
+
"loss": 0.9971,
|
| 1483 |
+
"step": 234
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"epoch": 81.73913043478261,
|
| 1487 |
+
"eval_loss": 1.0853348970413208,
|
| 1488 |
+
"eval_runtime": 12.9853,
|
| 1489 |
+
"eval_samples_per_second": 0.924,
|
| 1490 |
+
"eval_steps_per_second": 0.924,
|
| 1491 |
+
"step": 235
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 82.08695652173913,
|
| 1495 |
+
"grad_norm": 0.14419566094875336,
|
| 1496 |
+
"learning_rate": 1.3234549597008572e-06,
|
| 1497 |
+
"loss": 0.9801,
|
| 1498 |
+
"step": 236
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 82.78260869565217,
|
| 1502 |
+
"grad_norm": 0.13215622305870056,
|
| 1503 |
+
"learning_rate": 1.2455998350925042e-06,
|
| 1504 |
+
"loss": 0.969,
|
| 1505 |
+
"step": 238
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 82.78260869565217,
|
| 1509 |
+
"eval_loss": 1.0850697755813599,
|
| 1510 |
+
"eval_runtime": 12.9889,
|
| 1511 |
+
"eval_samples_per_second": 0.924,
|
| 1512 |
+
"eval_steps_per_second": 0.924,
|
| 1513 |
+
"step": 238
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 83.47826086956522,
|
| 1517 |
+
"grad_norm": 0.1365135759115219,
|
| 1518 |
+
"learning_rate": 1.1697777844051105e-06,
|
| 1519 |
+
"loss": 1.0242,
|
| 1520 |
+
"step": 240
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 83.82608695652173,
|
| 1524 |
+
"eval_loss": 1.0847272872924805,
|
| 1525 |
+
"eval_runtime": 12.9926,
|
| 1526 |
+
"eval_samples_per_second": 0.924,
|
| 1527 |
+
"eval_steps_per_second": 0.924,
|
| 1528 |
+
"step": 241
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 84.17391304347827,
|
| 1532 |
+
"grad_norm": 0.14472560584545135,
|
| 1533 |
+
"learning_rate": 1.096029866616704e-06,
|
| 1534 |
+
"loss": 1.0026,
|
| 1535 |
+
"step": 242
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 84.8695652173913,
|
| 1539 |
+
"grad_norm": 0.13619466125965118,
|
| 1540 |
+
"learning_rate": 1.0243960175257605e-06,
|
| 1541 |
+
"loss": 0.9949,
|
| 1542 |
+
"step": 244
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 84.8695652173913,
|
| 1546 |
+
"eval_loss": 1.0849597454071045,
|
| 1547 |
+
"eval_runtime": 12.9855,
|
| 1548 |
+
"eval_samples_per_second": 0.924,
|
| 1549 |
+
"eval_steps_per_second": 0.924,
|
| 1550 |
+
"step": 244
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 85.56521739130434,
|
| 1554 |
+
"grad_norm": 0.13221730291843414,
|
| 1555 |
+
"learning_rate": 9.549150281252633e-07,
|
| 1556 |
+
"loss": 0.9715,
|
| 1557 |
+
"step": 246
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 85.91304347826087,
|
| 1561 |
+
"eval_loss": 1.0846881866455078,
|
| 1562 |
+
"eval_runtime": 12.9911,
|
| 1563 |
+
"eval_samples_per_second": 0.924,
|
| 1564 |
+
"eval_steps_per_second": 0.924,
|
| 1565 |
+
"step": 247
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 86.26086956521739,
|
| 1569 |
+
"grad_norm": 0.14602892100811005,
|
| 1570 |
+
"learning_rate": 8.876245235966884e-07,
|
| 1571 |
+
"loss": 0.9918,
|
| 1572 |
+
"step": 248
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 86.95652173913044,
|
| 1576 |
+
"grad_norm": 0.1370145082473755,
|
| 1577 |
+
"learning_rate": 8.225609429353187e-07,
|
| 1578 |
+
"loss": 1.0164,
|
| 1579 |
+
"step": 250
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 86.95652173913044,
|
| 1583 |
+
"eval_loss": 1.084583044052124,
|
| 1584 |
+
"eval_runtime": 12.9873,
|
| 1585 |
+
"eval_samples_per_second": 0.924,
|
| 1586 |
+
"eval_steps_per_second": 0.924,
|
| 1587 |
+
"step": 250
|
| 1588 |
+
},
|
| 1589 |
+
{
|
| 1590 |
+
"epoch": 87.65217391304348,
|
| 1591 |
+
"grad_norm": 0.1295238435268402,
|
| 1592 |
+
"learning_rate": 7.597595192178702e-07,
|
| 1593 |
+
"loss": 0.9729,
|
| 1594 |
+
"step": 252
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"epoch": 88.0,
|
| 1598 |
+
"eval_loss": 1.084546685218811,
|
| 1599 |
+
"eval_runtime": 12.9858,
|
| 1600 |
+
"eval_samples_per_second": 0.924,
|
| 1601 |
+
"eval_steps_per_second": 0.924,
|
| 1602 |
+
"step": 253
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 88.34782608695652,
|
| 1606 |
+
"grad_norm": 0.12774939835071564,
|
| 1607 |
+
"learning_rate": 6.992542605231739e-07,
|
| 1608 |
+
"loss": 1.0065,
|
| 1609 |
+
"step": 254
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 88.69565217391305,
|
| 1613 |
+
"eval_loss": 1.0845379829406738,
|
| 1614 |
+
"eval_runtime": 12.9859,
|
| 1615 |
+
"eval_samples_per_second": 0.924,
|
| 1616 |
+
"eval_steps_per_second": 0.924,
|
| 1617 |
+
"step": 255
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 89.04347826086956,
|
| 1621 |
+
"grad_norm": 0.12875907123088837,
|
| 1622 |
+
"learning_rate": 6.410779315161885e-07,
|
| 1623 |
+
"loss": 1.0004,
|
| 1624 |
+
"step": 256
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 89.73913043478261,
|
| 1628 |
+
"grad_norm": 0.13160941004753113,
|
| 1629 |
+
"learning_rate": 5.852620357053651e-07,
|
| 1630 |
+
"loss": 0.994,
|
| 1631 |
+
"step": 258
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 89.73913043478261,
|
| 1635 |
+
"eval_loss": 1.0845232009887695,
|
| 1636 |
+
"eval_runtime": 12.9865,
|
| 1637 |
+
"eval_samples_per_second": 0.924,
|
| 1638 |
+
"eval_steps_per_second": 0.924,
|
| 1639 |
+
"step": 258
|
| 1640 |
+
},
|
| 1641 |
+
{
|
| 1642 |
+
"epoch": 90.43478260869566,
|
| 1643 |
+
"grad_norm": 0.1342068612575531,
|
| 1644 |
+
"learning_rate": 5.318367983829393e-07,
|
| 1645 |
+
"loss": 0.9852,
|
| 1646 |
+
"step": 260
|
| 1647 |
+
},
|
| 1648 |
+
{
|
| 1649 |
+
"epoch": 90.78260869565217,
|
| 1650 |
+
"eval_loss": 1.084337830543518,
|
| 1651 |
+
"eval_runtime": 12.9887,
|
| 1652 |
+
"eval_samples_per_second": 0.924,
|
| 1653 |
+
"eval_steps_per_second": 0.924,
|
| 1654 |
+
"step": 261
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 91.1304347826087,
|
| 1658 |
+
"grad_norm": 0.14868062734603882,
|
| 1659 |
+
"learning_rate": 4.808311502573976e-07,
|
| 1660 |
+
"loss": 1.0154,
|
| 1661 |
+
"step": 262
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 91.82608695652173,
|
| 1665 |
+
"grad_norm": 0.14731329679489136,
|
| 1666 |
+
"learning_rate": 4.322727117869951e-07,
|
| 1667 |
+
"loss": 0.9755,
|
| 1668 |
+
"step": 264
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 91.82608695652173,
|
| 1672 |
+
"eval_loss": 1.0842256546020508,
|
| 1673 |
+
"eval_runtime": 12.9863,
|
| 1674 |
+
"eval_samples_per_second": 0.924,
|
| 1675 |
+
"eval_steps_per_second": 0.924,
|
| 1676 |
+
"step": 264
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 92.52173913043478,
|
| 1680 |
+
"grad_norm": 0.14365264773368835,
|
| 1681 |
+
"learning_rate": 3.8618777822278854e-07,
|
| 1682 |
+
"loss": 1.0191,
|
| 1683 |
+
"step": 266
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 92.8695652173913,
|
| 1687 |
+
"eval_loss": 1.0839496850967407,
|
| 1688 |
+
"eval_runtime": 12.9888,
|
| 1689 |
+
"eval_samples_per_second": 0.924,
|
| 1690 |
+
"eval_steps_per_second": 0.924,
|
| 1691 |
+
"step": 267
|
| 1692 |
+
},
|
| 1693 |
+
{
|
| 1694 |
+
"epoch": 93.21739130434783,
|
| 1695 |
+
"grad_norm": 0.15139809250831604,
|
| 1696 |
+
"learning_rate": 3.426013053692878e-07,
|
| 1697 |
+
"loss": 0.9765,
|
| 1698 |
+
"step": 268
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 93.91304347826087,
|
| 1702 |
+
"grad_norm": 0.14520440995693207,
|
| 1703 |
+
"learning_rate": 3.015368960704584e-07,
|
| 1704 |
+
"loss": 0.9864,
|
| 1705 |
+
"step": 270
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 93.91304347826087,
|
| 1709 |
+
"eval_loss": 1.0840731859207153,
|
| 1710 |
+
"eval_runtime": 12.9887,
|
| 1711 |
+
"eval_samples_per_second": 0.924,
|
| 1712 |
+
"eval_steps_per_second": 0.924,
|
| 1713 |
+
"step": 270
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 94.6086956521739,
|
| 1717 |
+
"grad_norm": 0.13488347828388214,
|
| 1718 |
+
"learning_rate": 2.63016787428354e-07,
|
| 1719 |
+
"loss": 0.9773,
|
| 1720 |
+
"step": 272
|
| 1721 |
+
},
|
| 1722 |
+
{
|
| 1723 |
+
"epoch": 94.95652173913044,
|
| 1724 |
+
"eval_loss": 1.084143042564392,
|
| 1725 |
+
"eval_runtime": 12.9839,
|
| 1726 |
+
"eval_samples_per_second": 0.924,
|
| 1727 |
+
"eval_steps_per_second": 0.924,
|
| 1728 |
+
"step": 273
|
| 1729 |
+
},
|
| 1730 |
+
{
|
| 1731 |
+
"epoch": 95.30434782608695,
|
| 1732 |
+
"grad_norm": 0.14086610078811646,
|
| 1733 |
+
"learning_rate": 2.2706183876134047e-07,
|
| 1734 |
+
"loss": 1.0173,
|
| 1735 |
+
"step": 274
|
| 1736 |
+
},
|
| 1737 |
+
{
|
| 1738 |
+
"epoch": 96.0,
|
| 1739 |
+
"grad_norm": 0.13791334629058838,
|
| 1740 |
+
"learning_rate": 1.9369152030840553e-07,
|
| 1741 |
+
"loss": 0.9869,
|
| 1742 |
+
"step": 276
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 96.0,
|
| 1746 |
+
"eval_loss": 1.0842411518096924,
|
| 1747 |
+
"eval_runtime": 12.9864,
|
| 1748 |
+
"eval_samples_per_second": 0.924,
|
| 1749 |
+
"eval_steps_per_second": 0.924,
|
| 1750 |
+
"step": 276
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 96.69565217391305,
|
| 1754 |
+
"grad_norm": 0.14270715415477753,
|
| 1755 |
+
"learning_rate": 1.6292390268568103e-07,
|
| 1756 |
+
"loss": 0.986,
|
| 1757 |
+
"step": 278
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 96.69565217391305,
|
| 1761 |
+
"eval_loss": 1.0841034650802612,
|
| 1762 |
+
"eval_runtime": 12.985,
|
| 1763 |
+
"eval_samples_per_second": 0.924,
|
| 1764 |
+
"eval_steps_per_second": 0.924,
|
| 1765 |
+
"step": 278
|
| 1766 |
+
},
|
| 1767 |
+
{
|
| 1768 |
+
"epoch": 97.3913043478261,
|
| 1769 |
+
"grad_norm": 0.13356775045394897,
|
| 1770 |
+
"learning_rate": 1.3477564710088097e-07,
|
| 1771 |
+
"loss": 0.9925,
|
| 1772 |
+
"step": 280
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 97.73913043478261,
|
| 1776 |
+
"eval_loss": 1.084011197090149,
|
| 1777 |
+
"eval_runtime": 12.9842,
|
| 1778 |
+
"eval_samples_per_second": 0.924,
|
| 1779 |
+
"eval_steps_per_second": 0.924,
|
| 1780 |
+
"step": 281
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 98.08695652173913,
|
| 1784 |
+
"grad_norm": 0.15943579375743866,
|
| 1785 |
+
"learning_rate": 1.0926199633097156e-07,
|
| 1786 |
+
"loss": 0.9947,
|
| 1787 |
+
"step": 282
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 98.78260869565217,
|
| 1791 |
+
"grad_norm": 0.1478174775838852,
|
| 1792 |
+
"learning_rate": 8.639676646793382e-08,
|
| 1793 |
+
"loss": 0.9882,
|
| 1794 |
+
"step": 284
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 98.78260869565217,
|
| 1798 |
+
"eval_loss": 1.0840474367141724,
|
| 1799 |
+
"eval_runtime": 12.9842,
|
| 1800 |
+
"eval_samples_per_second": 0.924,
|
| 1801 |
+
"eval_steps_per_second": 0.924,
|
| 1802 |
+
"step": 284
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 99.47826086956522,
|
| 1806 |
+
"grad_norm": 0.14343644678592682,
|
| 1807 |
+
"learning_rate": 6.61923394371039e-08,
|
| 1808 |
+
"loss": 0.9917,
|
| 1809 |
+
"step": 286
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 99.82608695652173,
|
| 1813 |
+
"eval_loss": 1.0840203762054443,
|
| 1814 |
+
"eval_runtime": 12.9837,
|
| 1815 |
+
"eval_samples_per_second": 0.924,
|
| 1816 |
+
"eval_steps_per_second": 0.924,
|
| 1817 |
+
"step": 287
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 99.82608695652173,
|
| 1821 |
+
"step": 287,
|
| 1822 |
+
"total_flos": 4.445754122074849e+17,
|
| 1823 |
+
"train_loss": 1.1405799933011525,
|
| 1824 |
+
"train_runtime": 16000.7915,
|
| 1825 |
+
"train_samples_per_second": 0.431,
|
| 1826 |
+
"train_steps_per_second": 0.019
|
| 1827 |
+
}
|
| 1828 |
+
],
|
| 1829 |
+
"logging_steps": 2,
|
| 1830 |
+
"max_steps": 300,
|
| 1831 |
+
"num_input_tokens_seen": 0,
|
| 1832 |
+
"num_train_epochs": 150,
|
| 1833 |
+
"save_steps": 25,
|
| 1834 |
+
"stateful_callbacks": {
|
| 1835 |
+
"EarlyStoppingCallback": {
|
| 1836 |
+
"args": {
|
| 1837 |
+
"early_stopping_patience": 7,
|
| 1838 |
+
"early_stopping_threshold": 0.0
|
| 1839 |
+
},
|
| 1840 |
+
"attributes": {
|
| 1841 |
+
"early_stopping_patience_counter": 0
|
| 1842 |
+
}
|
| 1843 |
+
},
|
| 1844 |
+
"TrainerControl": {
|
| 1845 |
+
"args": {
|
| 1846 |
+
"should_epoch_stop": false,
|
| 1847 |
+
"should_evaluate": false,
|
| 1848 |
+
"should_log": false,
|
| 1849 |
+
"should_save": true,
|
| 1850 |
+
"should_training_stop": true
|
| 1851 |
+
},
|
| 1852 |
+
"attributes": {}
|
| 1853 |
+
}
|
| 1854 |
+
},
|
| 1855 |
+
"total_flos": 4.445754122074849e+17,
|
| 1856 |
+
"train_batch_size": 1,
|
| 1857 |
+
"trial_name": null,
|
| 1858 |
+
"trial_params": null
|
| 1859 |
+
}
|