End of training
Browse files
README.md
CHANGED
|
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [microsoft/Phi-4-multimodal-instruct](https://huggingface.co/microsoft/Phi-4-multimodal-instruct) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss:
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -50,32 +50,32 @@ The following hyperparameters were used during training:
|
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
|:-------------:|:------:|:----:|:---------------:|
|
| 53 |
-
|
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
| 56 |
-
|
|
| 57 |
-
| 0.
|
| 58 |
-
|
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
|
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
|
| 80 |
|
| 81 |
### Framework versions
|
|
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [microsoft/Phi-4-multimodal-instruct](https://huggingface.co/microsoft/Phi-4-multimodal-instruct) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 47.2708
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
|:-------------:|:------:|:----:|:---------------:|
|
| 53 |
+
| 14.0644 | 0.1117 | 10 | 46.4600 |
|
| 54 |
+
| 0.806 | 0.2235 | 20 | 47.0485 |
|
| 55 |
+
| 0.8452 | 0.3352 | 30 | 48.5161 |
|
| 56 |
+
| 1.1108 | 0.4469 | 40 | 48.2024 |
|
| 57 |
+
| 0.5848 | 0.5587 | 50 | 48.0342 |
|
| 58 |
+
| 1.5352 | 0.6704 | 60 | 47.5009 |
|
| 59 |
+
| 0.8749 | 0.7821 | 70 | 46.9722 |
|
| 60 |
+
| 0.6388 | 0.8939 | 80 | 47.6718 |
|
| 61 |
+
| 0.1562 | 1.0 | 90 | 47.8837 |
|
| 62 |
+
| 0.5959 | 1.1117 | 100 | 47.5622 |
|
| 63 |
+
| 1.1912 | 1.2235 | 110 | 47.6055 |
|
| 64 |
+
| 0.4967 | 1.3352 | 120 | 47.7299 |
|
| 65 |
+
| 0.204 | 1.4469 | 130 | 48.1439 |
|
| 66 |
+
| 0.5732 | 1.5587 | 140 | 48.4459 |
|
| 67 |
+
| 0.2537 | 1.6704 | 150 | 47.5499 |
|
| 68 |
+
| 0.1044 | 1.7821 | 160 | 47.4731 |
|
| 69 |
+
| 0.177 | 1.8939 | 170 | 47.1623 |
|
| 70 |
+
| 0.131 | 2.0 | 180 | 47.0603 |
|
| 71 |
+
| 0.144 | 2.1117 | 190 | 47.2259 |
|
| 72 |
+
| 0.0884 | 2.2235 | 200 | 46.9473 |
|
| 73 |
+
| 0.5288 | 2.3352 | 210 | 47.2556 |
|
| 74 |
+
| 0.483 | 2.4469 | 220 | 47.6419 |
|
| 75 |
+
| 0.0972 | 2.5587 | 230 | 47.6346 |
|
| 76 |
+
| 0.0148 | 2.6704 | 240 | 47.5911 |
|
| 77 |
+
| 0.0224 | 2.7821 | 250 | 47.2943 |
|
| 78 |
+
| 0.2197 | 2.8939 | 260 | 47.2708 |
|
| 79 |
|
| 80 |
|
| 81 |
### Framework versions
|
eval_after.json
CHANGED
|
@@ -45,7 +45,7 @@
|
|
| 45 |
"label": "3"
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"prediction": "
|
| 49 |
"label": "3"
|
| 50 |
},
|
| 51 |
{
|
|
@@ -65,7 +65,7 @@
|
|
| 65 |
"label": "4"
|
| 66 |
},
|
| 67 |
{
|
| 68 |
-
"prediction": "
|
| 69 |
"label": "3"
|
| 70 |
},
|
| 71 |
{
|
|
@@ -97,7 +97,7 @@
|
|
| 97 |
"label": "3"
|
| 98 |
},
|
| 99 |
{
|
| 100 |
-
"prediction": "
|
| 101 |
"label": "3"
|
| 102 |
},
|
| 103 |
{
|
|
@@ -233,7 +233,7 @@
|
|
| 233 |
"label": "4"
|
| 234 |
},
|
| 235 |
{
|
| 236 |
-
"prediction": "
|
| 237 |
"label": "4"
|
| 238 |
},
|
| 239 |
{
|
|
@@ -361,8 +361,8 @@
|
|
| 361 |
"label": "3"
|
| 362 |
}
|
| 363 |
],
|
| 364 |
-
"accuracy": 0.
|
| 365 |
-
"absolute_accuracy": 0.
|
| 366 |
"binary_accuracy": 0.6111111111111112,
|
| 367 |
"num_samples": 90
|
| 368 |
}
|
|
|
|
| 45 |
"label": "3"
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"prediction": "3",
|
| 49 |
"label": "3"
|
| 50 |
},
|
| 51 |
{
|
|
|
|
| 65 |
"label": "4"
|
| 66 |
},
|
| 67 |
{
|
| 68 |
+
"prediction": "2",
|
| 69 |
"label": "3"
|
| 70 |
},
|
| 71 |
{
|
|
|
|
| 97 |
"label": "3"
|
| 98 |
},
|
| 99 |
{
|
| 100 |
+
"prediction": "3",
|
| 101 |
"label": "3"
|
| 102 |
},
|
| 103 |
{
|
|
|
|
| 233 |
"label": "4"
|
| 234 |
},
|
| 235 |
{
|
| 236 |
+
"prediction": "3",
|
| 237 |
"label": "4"
|
| 238 |
},
|
| 239 |
{
|
|
|
|
| 361 |
"label": "3"
|
| 362 |
}
|
| 363 |
],
|
| 364 |
+
"accuracy": 0.4444444444444444,
|
| 365 |
+
"absolute_accuracy": 0.4444444444444444,
|
| 366 |
"binary_accuracy": 0.6111111111111112,
|
| 367 |
"num_samples": 90
|
| 368 |
}
|
model-00001-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4997504848
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:efa0e6c3fd543970d98b0053681cd4033fd2b197c59999231ffff0b1fa164915
|
| 3 |
size 4997504848
|
model-00002-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4952333128
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bad474a4714d0e72b6a6bfddb56fef9f08fb992aab63e07b223399ef6c132db6
|
| 3 |
size 4952333128
|
model-00003-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1199389232
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c081a2e2bba9d284c1c1b51841c05547d68c7052369b7ba1fdf66f59c7e9461
|
| 3 |
size 1199389232
|
runs/May20_06-06-23_70e5a6d483fc/events.out.tfevents.1747721183.70e5a6d483fc.91308.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d0d03ec4958545c8a277590791da0937b4011cb4cfcc6efdb759328c1e004f2
|
| 3 |
+
size 72392
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5432
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ceead4cef9741a5d71101274953016a907dcada4623346b041081efca36b7f49
|
| 3 |
size 5432
|