End of training
Browse files- README.md +27 -28
- adapter_config.json +8 -8
- adapter_model.safetensors +2 -2
- runs/Sep26_00-00-07_sammie/events.out.tfevents.1727330530.sammie.423563.0 +3 -0
- runs/Sep26_00-05-40_sammie/events.out.tfevents.1727330787.sammie.423563.1 +3 -0
- runs/Sep26_00-16-01_sammie/events.out.tfevents.1727331385.sammie.430449.0 +3 -0
- training_args.bin +2 -2
README.md
CHANGED
@@ -21,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
21 |
|
22 |
This model is a fine-tuned version of [unsloth/tinyllama-chat-bnb-4bit](https://huggingface.co/unsloth/tinyllama-chat-bnb-4bit) on the generator dataset.
|
23 |
It achieves the following results on the evaluation set:
|
24 |
-
- Loss: 1.
|
25 |
|
26 |
## Model description
|
27 |
|
@@ -49,38 +49,37 @@ The following hyperparameters were used during training:
|
|
49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
- lr_scheduler_type: linear
|
51 |
- num_epochs: 1
|
52 |
-
- mixed_precision_training: Native AMP
|
53 |
|
54 |
### Training results
|
55 |
|
56 |
| Training Loss | Epoch | Step | Validation Loss |
|
57 |
|:-------------:|:------:|:----:|:---------------:|
|
58 |
-
|
|
59 |
-
|
|
60 |
-
|
|
61 |
-
|
|
62 |
-
|
|
63 |
-
|
|
64 |
-
|
|
65 |
-
|
|
66 |
-
|
|
67 |
-
|
|
68 |
-
| 1.
|
69 |
-
| 1.
|
70 |
-
| 1.
|
71 |
-
| 1.
|
72 |
-
| 1.
|
73 |
-
| 1.
|
74 |
-
| 1.
|
75 |
-
| 1.
|
76 |
-
| 1.
|
77 |
-
| 1.
|
78 |
-
| 1.
|
79 |
-
| 1.
|
80 |
-
| 1.
|
81 |
-
| 1.
|
82 |
-
| 1.
|
83 |
-
| 1.
|
84 |
|
85 |
|
86 |
### Framework versions
|
|
|
21 |
|
22 |
This model is a fine-tuned version of [unsloth/tinyllama-chat-bnb-4bit](https://huggingface.co/unsloth/tinyllama-chat-bnb-4bit) on the generator dataset.
|
23 |
It achieves the following results on the evaluation set:
|
24 |
+
- Loss: 1.3521
|
25 |
|
26 |
## Model description
|
27 |
|
|
|
49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
- lr_scheduler_type: linear
|
51 |
- num_epochs: 1
|
|
|
52 |
|
53 |
### Training results
|
54 |
|
55 |
| Training Loss | Epoch | Step | Validation Loss |
|
56 |
|:-------------:|:------:|:----:|:---------------:|
|
57 |
+
| 3.8522 | 0.0377 | 10 | 3.0444 |
|
58 |
+
| 2.7085 | 0.0753 | 20 | 2.4069 |
|
59 |
+
| 2.191 | 0.1130 | 30 | 2.0027 |
|
60 |
+
| 1.8996 | 0.1507 | 40 | 1.8018 |
|
61 |
+
| 1.7538 | 0.1883 | 50 | 1.6850 |
|
62 |
+
| 1.6563 | 0.2260 | 60 | 1.6161 |
|
63 |
+
| 1.6275 | 0.2637 | 70 | 1.5722 |
|
64 |
+
| 1.5313 | 0.3013 | 80 | 1.5377 |
|
65 |
+
| 1.5277 | 0.3390 | 90 | 1.5104 |
|
66 |
+
| 1.5039 | 0.3766 | 100 | 1.4889 |
|
67 |
+
| 1.4768 | 0.4143 | 110 | 1.4694 |
|
68 |
+
| 1.4552 | 0.4520 | 120 | 1.4523 |
|
69 |
+
| 1.4481 | 0.4896 | 130 | 1.4385 |
|
70 |
+
| 1.4223 | 0.5273 | 140 | 1.4233 |
|
71 |
+
| 1.4145 | 0.5650 | 150 | 1.4118 |
|
72 |
+
| 1.4207 | 0.6026 | 160 | 1.4012 |
|
73 |
+
| 1.4004 | 0.6403 | 170 | 1.3925 |
|
74 |
+
| 1.4316 | 0.6780 | 180 | 1.3849 |
|
75 |
+
| 1.3841 | 0.7156 | 190 | 1.3784 |
|
76 |
+
| 1.3747 | 0.7533 | 200 | 1.3722 |
|
77 |
+
| 1.388 | 0.7910 | 210 | 1.3665 |
|
78 |
+
| 1.3508 | 0.8286 | 220 | 1.3623 |
|
79 |
+
| 1.386 | 0.8663 | 230 | 1.3586 |
|
80 |
+
| 1.3605 | 0.9040 | 240 | 1.3555 |
|
81 |
+
| 1.369 | 0.9416 | 250 | 1.3534 |
|
82 |
+
| 1.3645 | 0.9793 | 260 | 1.3521 |
|
83 |
|
84 |
|
85 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -20,19 +20,19 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
|
|
|
|
23 |
"down_proj",
|
|
|
|
|
24 |
"o_proj",
|
25 |
-
"mlp.gate_up_proj",
|
26 |
"self_attn.o_proj.weight",
|
27 |
-
"up_proj",
|
28 |
-
"gate_proj",
|
29 |
"mlp.down_proj",
|
30 |
-
"
|
31 |
-
"
|
32 |
-
"q_proj",
|
33 |
-
"k_proj"
|
34 |
],
|
35 |
"task_type": "CAUSAL_LM",
|
36 |
"use_dora": false,
|
37 |
-
"use_rslora":
|
38 |
}
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"gate_proj",
|
24 |
+
"k_proj",
|
25 |
+
"mlp.gate_up_proj",
|
26 |
"down_proj",
|
27 |
+
"v_proj",
|
28 |
+
"q_proj",
|
29 |
"o_proj",
|
|
|
30 |
"self_attn.o_proj.weight",
|
|
|
|
|
31 |
"mlp.down_proj",
|
32 |
+
"up_proj",
|
33 |
+
"self_attn.qkv_proj.weight"
|
|
|
|
|
34 |
],
|
35 |
"task_type": "CAUSAL_LM",
|
36 |
"use_dora": false,
|
37 |
+
"use_rslora": true
|
38 |
}
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56803c4d98022be7dfa3f8c0e1e22fc44c4994d771418a572448c62920ab292b
|
3 |
+
size 403743472
|
runs/Sep26_00-00-07_sammie/events.out.tfevents.1727330530.sammie.423563.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7d328eeb1fd2ee1c738e7e41da038082fa2a499f4c138a80588772bb7046075
|
3 |
+
size 6059
|
runs/Sep26_00-05-40_sammie/events.out.tfevents.1727330787.sammie.423563.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06d71f55f938bbcfff0019190477660e8cec8bb67d5504d0ca5e4f580392b22b
|
3 |
+
size 6059
|
runs/Sep26_00-16-01_sammie/events.out.tfevents.1727331385.sammie.430449.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb5ecb0e4177bd91562b8ea41ee32efba8d3a59ff9ee3d7150afc14a415e9f2f
|
3 |
+
size 18837
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e88c7f613ec531155670d9379c212ae8331d83fa95b2fb8801a6da610e8bc9d9
|
3 |
+
size 5624
|