End of training
Browse files- README.md +28 -108
- adapter_config.json +6 -6
- adapter_model.safetensors +2 -2
- runs/Sep25_10-20-01_sammie/events.out.tfevents.1727281819.sammie.5660.0 +3 -0
- tokenizer_config.json +1 -1
- training_args.bin +1 -1
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 |
|
@@ -40,7 +40,7 @@ More information needed
|
|
40 |
### Training hyperparameters
|
41 |
|
42 |
The following hyperparameters were used during training:
|
43 |
-
- learning_rate: 0.
|
44 |
- train_batch_size: 8
|
45 |
- eval_batch_size: 8
|
46 |
- seed: 42
|
@@ -55,112 +55,32 @@ The following hyperparameters were used during training:
|
|
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 |
-
| 1.4569 | 0.2542 | 270 | 1.4604 |
|
85 |
-
| 1.4287 | 0.2637 | 280 | 1.4549 |
|
86 |
-
| 1.412 | 0.2731 | 290 | 1.4505 |
|
87 |
-
| 1.4113 | 0.2825 | 300 | 1.4474 |
|
88 |
-
| 1.4106 | 0.2919 | 310 | 1.4435 |
|
89 |
-
| 1.4074 | 0.3013 | 320 | 1.4398 |
|
90 |
-
| 1.4139 | 0.3107 | 330 | 1.4362 |
|
91 |
-
| 1.3989 | 0.3202 | 340 | 1.4325 |
|
92 |
-
| 1.3803 | 0.3296 | 350 | 1.4292 |
|
93 |
-
| 1.3489 | 0.3390 | 360 | 1.4272 |
|
94 |
-
| 1.4065 | 0.3484 | 370 | 1.4236 |
|
95 |
-
| 1.4201 | 0.3578 | 380 | 1.4208 |
|
96 |
-
| 1.3936 | 0.3672 | 390 | 1.4174 |
|
97 |
-
| 1.3934 | 0.3766 | 400 | 1.4142 |
|
98 |
-
| 1.4117 | 0.3861 | 410 | 1.4121 |
|
99 |
-
| 1.3812 | 0.3955 | 420 | 1.4091 |
|
100 |
-
| 1.3882 | 0.4049 | 430 | 1.4065 |
|
101 |
-
| 1.3849 | 0.4143 | 440 | 1.4039 |
|
102 |
-
| 1.3537 | 0.4237 | 450 | 1.4011 |
|
103 |
-
| 1.3892 | 0.4331 | 460 | 1.3993 |
|
104 |
-
| 1.3915 | 0.4426 | 470 | 1.3971 |
|
105 |
-
| 1.3766 | 0.4520 | 480 | 1.3967 |
|
106 |
-
| 1.3422 | 0.4614 | 490 | 1.3968 |
|
107 |
-
| 1.3525 | 0.4708 | 500 | 1.3917 |
|
108 |
-
| 1.3662 | 0.4802 | 510 | 1.3878 |
|
109 |
-
| 1.3254 | 0.4896 | 520 | 1.3871 |
|
110 |
-
| 1.3047 | 0.4991 | 530 | 1.3840 |
|
111 |
-
| 1.3064 | 0.5085 | 540 | 1.3820 |
|
112 |
-
| 1.3662 | 0.5179 | 550 | 1.3805 |
|
113 |
-
| 1.3177 | 0.5273 | 560 | 1.3793 |
|
114 |
-
| 1.315 | 0.5367 | 570 | 1.3762 |
|
115 |
-
| 1.3275 | 0.5461 | 580 | 1.3742 |
|
116 |
-
| 1.3631 | 0.5556 | 590 | 1.3727 |
|
117 |
-
| 1.3324 | 0.5650 | 600 | 1.3697 |
|
118 |
-
| 1.317 | 0.5744 | 610 | 1.3679 |
|
119 |
-
| 1.3479 | 0.5838 | 620 | 1.3669 |
|
120 |
-
| 1.3526 | 0.5932 | 630 | 1.3650 |
|
121 |
-
| 1.2873 | 0.6026 | 640 | 1.3640 |
|
122 |
-
| 1.3318 | 0.6121 | 650 | 1.3615 |
|
123 |
-
| 1.302 | 0.6215 | 660 | 1.3599 |
|
124 |
-
| 1.2907 | 0.6309 | 670 | 1.3582 |
|
125 |
-
| 1.3387 | 0.6403 | 680 | 1.3565 |
|
126 |
-
| 1.3278 | 0.6497 | 690 | 1.3552 |
|
127 |
-
| 1.3073 | 0.6591 | 700 | 1.3538 |
|
128 |
-
| 1.2986 | 0.6685 | 710 | 1.3532 |
|
129 |
-
| 1.3461 | 0.6780 | 720 | 1.3509 |
|
130 |
-
| 1.3229 | 0.6874 | 730 | 1.3500 |
|
131 |
-
| 1.3055 | 0.6968 | 740 | 1.3490 |
|
132 |
-
| 1.3307 | 0.7062 | 750 | 1.3476 |
|
133 |
-
| 1.3308 | 0.7156 | 760 | 1.3468 |
|
134 |
-
| 1.3083 | 0.7250 | 770 | 1.3459 |
|
135 |
-
| 1.312 | 0.7345 | 780 | 1.3447 |
|
136 |
-
| 1.3068 | 0.7439 | 790 | 1.3424 |
|
137 |
-
| 1.3202 | 0.7533 | 800 | 1.3415 |
|
138 |
-
| 1.2872 | 0.7627 | 810 | 1.3403 |
|
139 |
-
| 1.311 | 0.7721 | 820 | 1.3393 |
|
140 |
-
| 1.3213 | 0.7815 | 830 | 1.3385 |
|
141 |
-
| 1.3302 | 0.7910 | 840 | 1.3372 |
|
142 |
-
| 1.3243 | 0.8004 | 850 | 1.3362 |
|
143 |
-
| 1.3077 | 0.8098 | 860 | 1.3352 |
|
144 |
-
| 1.3229 | 0.8192 | 870 | 1.3344 |
|
145 |
-
| 1.3243 | 0.8286 | 880 | 1.3333 |
|
146 |
-
| 1.2909 | 0.8380 | 890 | 1.3327 |
|
147 |
-
| 1.3205 | 0.8475 | 900 | 1.3319 |
|
148 |
-
| 1.2863 | 0.8569 | 910 | 1.3314 |
|
149 |
-
| 1.2583 | 0.8663 | 920 | 1.3305 |
|
150 |
-
| 1.29 | 0.8757 | 930 | 1.3298 |
|
151 |
-
| 1.2706 | 0.8851 | 940 | 1.3294 |
|
152 |
-
| 1.272 | 0.8945 | 950 | 1.3291 |
|
153 |
-
| 1.2899 | 0.9040 | 960 | 1.3285 |
|
154 |
-
| 1.3184 | 0.9134 | 970 | 1.3280 |
|
155 |
-
| 1.3323 | 0.9228 | 980 | 1.3276 |
|
156 |
-
| 1.3314 | 0.9322 | 990 | 1.3272 |
|
157 |
-
| 1.2965 | 0.9416 | 1000 | 1.3269 |
|
158 |
-
| 1.2874 | 0.9510 | 1010 | 1.3266 |
|
159 |
-
| 1.2569 | 0.9605 | 1020 | 1.3263 |
|
160 |
-
| 1.2622 | 0.9699 | 1030 | 1.3261 |
|
161 |
-
| 1.3258 | 0.9793 | 1040 | 1.3259 |
|
162 |
-
| 1.3072 | 0.9887 | 1050 | 1.3257 |
|
163 |
-
| 1.2555 | 0.9981 | 1060 | 1.3256 |
|
164 |
|
165 |
|
166 |
### 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: 1.6823
|
25 |
|
26 |
## Model description
|
27 |
|
|
|
40 |
### Training hyperparameters
|
41 |
|
42 |
The following hyperparameters were used during training:
|
43 |
+
- learning_rate: 0.0001
|
44 |
- train_batch_size: 8
|
45 |
- eval_batch_size: 8
|
46 |
- seed: 42
|
|
|
55 |
|
56 |
| Training Loss | Epoch | Step | Validation Loss |
|
57 |
|:-------------:|:------:|:----:|:---------------:|
|
58 |
+
| 4.5606 | 0.0377 | 10 | 4.0606 |
|
59 |
+
| 3.7693 | 0.0753 | 20 | 3.5539 |
|
60 |
+
| 3.3915 | 0.1130 | 30 | 3.2022 |
|
61 |
+
| 3.0938 | 0.1507 | 40 | 2.9560 |
|
62 |
+
| 2.8692 | 0.1883 | 50 | 2.7576 |
|
63 |
+
| 2.6774 | 0.2260 | 60 | 2.5706 |
|
64 |
+
| 2.5012 | 0.2637 | 70 | 2.3805 |
|
65 |
+
| 2.3332 | 0.3013 | 80 | 2.2277 |
|
66 |
+
| 2.159 | 0.3390 | 90 | 2.1030 |
|
67 |
+
| 2.0806 | 0.3766 | 100 | 2.0125 |
|
68 |
+
| 1.9781 | 0.4143 | 110 | 1.9497 |
|
69 |
+
| 1.9683 | 0.4520 | 120 | 1.9005 |
|
70 |
+
| 1.917 | 0.4896 | 130 | 1.8584 |
|
71 |
+
| 1.8551 | 0.5273 | 140 | 1.8224 |
|
72 |
+
| 1.8121 | 0.5650 | 150 | 1.7910 |
|
73 |
+
| 1.7998 | 0.6026 | 160 | 1.7673 |
|
74 |
+
| 1.7484 | 0.6403 | 170 | 1.7486 |
|
75 |
+
| 1.7221 | 0.6780 | 180 | 1.7331 |
|
76 |
+
| 1.7171 | 0.7156 | 190 | 1.7207 |
|
77 |
+
| 1.7103 | 0.7533 | 200 | 1.7108 |
|
78 |
+
| 1.7086 | 0.7910 | 210 | 1.7025 |
|
79 |
+
| 1.7083 | 0.8286 | 220 | 1.6955 |
|
80 |
+
| 1.7065 | 0.8663 | 230 | 1.6907 |
|
81 |
+
| 1.6829 | 0.9040 | 240 | 1.6864 |
|
82 |
+
| 1.6892 | 0.9416 | 250 | 1.6838 |
|
83 |
+
| 1.6985 | 0.9793 | 260 | 1.6823 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
84 |
|
85 |
|
86 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -20,17 +20,17 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
|
|
|
|
23 |
"self_attn.o_proj.weight",
|
24 |
"up_proj",
|
25 |
-
"self_attn.qkv_proj.weight",
|
26 |
"gate_proj",
|
27 |
-
"v_proj",
|
28 |
"mlp.down_proj",
|
29 |
-
"
|
|
|
30 |
"q_proj",
|
31 |
-
"
|
32 |
-
"down_proj",
|
33 |
-
"o_proj"
|
34 |
],
|
35 |
"task_type": "CAUSAL_LM",
|
36 |
"use_dora": false,
|
|
|
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 |
+
"self_attn.qkv_proj.weight",
|
31 |
+
"v_proj",
|
32 |
"q_proj",
|
33 |
+
"k_proj"
|
|
|
|
|
34 |
],
|
35 |
"task_type": "CAUSAL_LM",
|
36 |
"use_dora": false,
|
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 sha256:60d95b10b6e140a9626a7058d5038528f2ff80148dc4569b881db56052046509
|
3 |
+
size 40
|
runs/Sep25_10-20-01_sammie/events.out.tfevents.1727281819.sammie.5660.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3e63819d085438648634605eb393dfba776abe42f88c364ec419d89de2b4d87
|
3 |
+
size 18738
|
tokenizer_config.json
CHANGED
@@ -35,7 +35,7 @@
|
|
35 |
"legacy": false,
|
36 |
"model_max_length": 2048,
|
37 |
"pad_token": "</s>",
|
38 |
-
"padding_side": "
|
39 |
"sp_model_kwargs": {},
|
40 |
"tokenizer_class": "LlamaTokenizer",
|
41 |
"unk_token": "<unk>",
|
|
|
35 |
"legacy": false,
|
36 |
"model_max_length": 2048,
|
37 |
"pad_token": "</s>",
|
38 |
+
"padding_side": "right",
|
39 |
"sp_model_kwargs": {},
|
40 |
"tokenizer_class": "LlamaTokenizer",
|
41 |
"unk_token": "<unk>",
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92ef00ea7a676ed017f06f373e7b051d049f571471eb21b599f6dcb299f671b4
|
3 |
size 5560
|