End of training
Browse files- README.md +100 -63
- adapter_model.safetensors +1 -1
README.md
CHANGED
|
@@ -7,18 +7,18 @@ tags:
|
|
| 7 |
- generated_from_trainer
|
| 8 |
base_model: taide/TAIDE-LX-7B-Chat
|
| 9 |
model-index:
|
| 10 |
-
- name: ROE_QA_TAIDE-LX-7B-
|
| 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 |
-
# ROE_QA_TAIDE-LX-7B-
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [taide/TAIDE-LX-7B-Chat](https://huggingface.co/taide/TAIDE-LX-7B-Chat) on the None dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 0.
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -53,66 +53,103 @@ The following hyperparameters were used during training:
|
|
| 53 |
|
| 54 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
|:-------------:|:------:|:----:|:---------------:|
|
| 56 |
-
| 4.
|
| 57 |
-
| 4.
|
| 58 |
-
| 3.
|
| 59 |
-
| 3.
|
| 60 |
-
| 2.
|
| 61 |
-
| 2.
|
| 62 |
-
| 2.
|
| 63 |
-
| 1.
|
| 64 |
-
| 1.
|
| 65 |
-
| 1.
|
| 66 |
-
| 1.
|
| 67 |
-
| 1.
|
| 68 |
-
| 1.
|
| 69 |
-
| 0.
|
| 70 |
-
|
|
| 71 |
-
| 1.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.
|
| 97 |
-
| 0.
|
| 98 |
-
| 0.
|
| 99 |
-
| 0.
|
| 100 |
-
| 0.
|
| 101 |
-
| 0.
|
| 102 |
-
| 0.
|
| 103 |
-
| 0.
|
| 104 |
-
| 0.
|
| 105 |
-
| 0.
|
| 106 |
-
| 0.
|
| 107 |
-
| 0.
|
| 108 |
-
| 0.
|
| 109 |
-
| 0.
|
| 110 |
-
| 0.
|
| 111 |
-
| 0.
|
| 112 |
-
| 0.
|
| 113 |
-
| 0.
|
| 114 |
-
| 0.
|
| 115 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 116 |
|
| 117 |
|
| 118 |
### Framework versions
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
base_model: taide/TAIDE-LX-7B-Chat
|
| 9 |
model-index:
|
| 10 |
+
- name: ROE_QA_TAIDE-LX-7B-Chat_Q100_80_20_V6
|
| 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 |
+
# ROE_QA_TAIDE-LX-7B-Chat_Q100_80_20_V6
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [taide/TAIDE-LX-7B-Chat](https://huggingface.co/taide/TAIDE-LX-7B-Chat) on the None dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.3442
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 53 |
|
| 54 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
|:-------------:|:------:|:----:|:---------------:|
|
| 56 |
+
| 4.8628 | 0.0321 | 100 | 3.4692 |
|
| 57 |
+
| 4.6437 | 0.0643 | 200 | 3.2308 |
|
| 58 |
+
| 3.8154 | 0.0964 | 300 | 2.8144 |
|
| 59 |
+
| 3.3006 | 0.1285 | 400 | 2.5033 |
|
| 60 |
+
| 2.953 | 0.1607 | 500 | 2.2690 |
|
| 61 |
+
| 2.2844 | 0.1928 | 600 | 1.9550 |
|
| 62 |
+
| 2.134 | 0.2249 | 700 | 1.7888 |
|
| 63 |
+
| 1.8182 | 0.2571 | 800 | 1.6310 |
|
| 64 |
+
| 1.6776 | 0.2892 | 900 | 1.5062 |
|
| 65 |
+
| 1.6317 | 0.3213 | 1000 | 1.4026 |
|
| 66 |
+
| 1.6311 | 0.3535 | 1100 | 1.2253 |
|
| 67 |
+
| 1.1003 | 0.3856 | 1200 | 1.0703 |
|
| 68 |
+
| 1.2014 | 0.4177 | 1300 | 1.0672 |
|
| 69 |
+
| 0.9489 | 0.4499 | 1400 | 0.9135 |
|
| 70 |
+
| 1.0068 | 0.4820 | 1500 | 0.8950 |
|
| 71 |
+
| 1.0342 | 0.5141 | 1600 | 0.8074 |
|
| 72 |
+
| 0.9713 | 0.5463 | 1700 | 0.7767 |
|
| 73 |
+
| 0.9598 | 0.5784 | 1800 | 0.6995 |
|
| 74 |
+
| 0.9357 | 0.6105 | 1900 | 0.6643 |
|
| 75 |
+
| 0.8298 | 0.6427 | 2000 | 0.6456 |
|
| 76 |
+
| 0.8803 | 0.6748 | 2100 | 0.6164 |
|
| 77 |
+
| 0.8899 | 0.7069 | 2200 | 0.5867 |
|
| 78 |
+
| 0.7877 | 0.7391 | 2300 | 0.5748 |
|
| 79 |
+
| 0.7792 | 0.7712 | 2400 | 0.5513 |
|
| 80 |
+
| 0.8387 | 0.8033 | 2500 | 0.5267 |
|
| 81 |
+
| 0.8625 | 0.8355 | 2600 | 0.5111 |
|
| 82 |
+
| 0.8514 | 0.8676 | 2700 | 0.4992 |
|
| 83 |
+
| 0.762 | 0.8997 | 2800 | 0.4881 |
|
| 84 |
+
| 0.779 | 0.9319 | 2900 | 0.4840 |
|
| 85 |
+
| 0.8938 | 0.9640 | 3000 | 0.4676 |
|
| 86 |
+
| 0.7007 | 0.9961 | 3100 | 0.4668 |
|
| 87 |
+
| 0.7006 | 1.0283 | 3200 | 0.4500 |
|
| 88 |
+
| 0.6622 | 1.0604 | 3300 | 0.4383 |
|
| 89 |
+
| 0.6724 | 1.0925 | 3400 | 0.4404 |
|
| 90 |
+
| 0.6551 | 1.1247 | 3500 | 0.4372 |
|
| 91 |
+
| 0.6395 | 1.1568 | 3600 | 0.4273 |
|
| 92 |
+
| 0.6317 | 1.1889 | 3700 | 0.4217 |
|
| 93 |
+
| 0.6683 | 1.2211 | 3800 | 0.4218 |
|
| 94 |
+
| 0.6987 | 1.2532 | 3900 | 0.4136 |
|
| 95 |
+
| 0.7309 | 1.2853 | 4000 | 0.4151 |
|
| 96 |
+
| 0.6192 | 1.3175 | 4100 | 0.4092 |
|
| 97 |
+
| 0.6013 | 1.3496 | 4200 | 0.4109 |
|
| 98 |
+
| 0.6138 | 1.3817 | 4300 | 0.4069 |
|
| 99 |
+
| 0.6224 | 1.4139 | 4400 | 0.4001 |
|
| 100 |
+
| 0.6414 | 1.4460 | 4500 | 0.3942 |
|
| 101 |
+
| 0.6234 | 1.4781 | 4600 | 0.3949 |
|
| 102 |
+
| 0.6365 | 1.5103 | 4700 | 0.3914 |
|
| 103 |
+
| 0.6602 | 1.5424 | 4800 | 0.3908 |
|
| 104 |
+
| 0.6646 | 1.5746 | 4900 | 0.3916 |
|
| 105 |
+
| 0.6295 | 1.6067 | 5000 | 0.3832 |
|
| 106 |
+
| 0.6379 | 1.6388 | 5100 | 0.3828 |
|
| 107 |
+
| 0.6544 | 1.6710 | 5200 | 0.3836 |
|
| 108 |
+
| 0.6224 | 1.7031 | 5300 | 0.3905 |
|
| 109 |
+
| 0.5892 | 1.7352 | 5400 | 0.3785 |
|
| 110 |
+
| 0.5985 | 1.7674 | 5500 | 0.3794 |
|
| 111 |
+
| 0.5776 | 1.7995 | 5600 | 0.3751 |
|
| 112 |
+
| 0.5799 | 1.8316 | 5700 | 0.3745 |
|
| 113 |
+
| 0.6247 | 1.8638 | 5800 | 0.3742 |
|
| 114 |
+
| 0.5724 | 1.8959 | 5900 | 0.3716 |
|
| 115 |
+
| 0.627 | 1.9280 | 6000 | 0.3750 |
|
| 116 |
+
| 0.566 | 1.9602 | 6100 | 0.3720 |
|
| 117 |
+
| 0.5754 | 1.9923 | 6200 | 0.3706 |
|
| 118 |
+
| 0.3561 | 2.0244 | 6300 | 0.3685 |
|
| 119 |
+
| 0.4468 | 2.0566 | 6400 | 0.3663 |
|
| 120 |
+
| 0.392 | 2.0887 | 6500 | 0.3669 |
|
| 121 |
+
| 0.4049 | 2.1208 | 6600 | 0.3659 |
|
| 122 |
+
| 0.3967 | 2.1530 | 6700 | 0.3649 |
|
| 123 |
+
| 0.418 | 2.1851 | 6800 | 0.3662 |
|
| 124 |
+
| 0.4973 | 2.2172 | 6900 | 0.3630 |
|
| 125 |
+
| 0.3685 | 2.2494 | 7000 | 0.3627 |
|
| 126 |
+
| 0.3967 | 2.2815 | 7100 | 0.3618 |
|
| 127 |
+
| 0.3921 | 2.3136 | 7200 | 0.3580 |
|
| 128 |
+
| 0.3905 | 2.3458 | 7300 | 0.3595 |
|
| 129 |
+
| 0.3888 | 2.3779 | 7400 | 0.3574 |
|
| 130 |
+
| 0.4403 | 2.4100 | 7500 | 0.3571 |
|
| 131 |
+
| 0.4343 | 2.4422 | 7600 | 0.3574 |
|
| 132 |
+
| 0.4088 | 2.4743 | 7700 | 0.3549 |
|
| 133 |
+
| 0.3924 | 2.5064 | 7800 | 0.3560 |
|
| 134 |
+
| 0.4383 | 2.5386 | 7900 | 0.3540 |
|
| 135 |
+
| 0.3786 | 2.5707 | 8000 | 0.3525 |
|
| 136 |
+
| 0.3779 | 2.6028 | 8100 | 0.3518 |
|
| 137 |
+
| 0.4555 | 2.6350 | 8200 | 0.3519 |
|
| 138 |
+
| 0.3813 | 2.6671 | 8300 | 0.3497 |
|
| 139 |
+
| 0.375 | 2.6992 | 8400 | 0.3505 |
|
| 140 |
+
| 0.3889 | 2.7314 | 8500 | 0.3493 |
|
| 141 |
+
| 0.3524 | 2.7635 | 8600 | 0.3469 |
|
| 142 |
+
| 0.431 | 2.7956 | 8700 | 0.3480 |
|
| 143 |
+
| 0.4185 | 2.8278 | 8800 | 0.3471 |
|
| 144 |
+
| 0.378 | 2.8599 | 8900 | 0.3487 |
|
| 145 |
+
| 0.3978 | 2.8920 | 9000 | 0.3457 |
|
| 146 |
+
| 0.421 | 2.9242 | 9100 | 0.3461 |
|
| 147 |
+
| 0.3691 | 2.9563 | 9200 | 0.3443 |
|
| 148 |
+
| 0.4019 | 2.9884 | 9300 | 0.3446 |
|
| 149 |
+
| 0.2392 | 3.0206 | 9400 | 0.3473 |
|
| 150 |
+
| 0.2213 | 3.0527 | 9500 | 0.3443 |
|
| 151 |
+
| 0.2189 | 3.0848 | 9600 | 0.3437 |
|
| 152 |
+
| 0.2363 | 3.1170 | 9700 | 0.3442 |
|
| 153 |
|
| 154 |
|
| 155 |
### Framework versions
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16794200
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7b63a166c2cdf818386642b982a14a57fa83262bc167604cf102167f7ab6fa2
|
| 3 |
size 16794200
|