End of training
Browse files- README.md +48 -53
- adapter_config.json +9 -2
- adapter_model.safetensors +1 -1
- runs/Sep23_13-14-37_sammie/events.out.tfevents.1727118893.sammie.79670.0 +3 -0
- 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-bnb-4bit](https://huggingface.co/unsloth/tinyllama-bnb-4bit) on the generator dataset.
|
23 |
It achieves the following results on the evaluation set:
|
24 |
-
- Loss: 1.
|
25 |
|
26 |
## Model description
|
27 |
|
@@ -48,64 +48,59 @@ The following hyperparameters were used during training:
|
|
48 |
- total_train_batch_size: 32
|
49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
- lr_scheduler_type: linear
|
51 |
-
- num_epochs:
|
52 |
- mixed_precision_training: Native AMP
|
53 |
|
54 |
### Training results
|
55 |
|
56 |
| Training Loss | Epoch | Step | Validation Loss |
|
57 |
|:-------------:|:------:|:----:|:---------------:|
|
58 |
-
| 1.
|
59 |
-
| 1.
|
60 |
-
| 1.
|
61 |
-
| 1.
|
62 |
-
| 1.
|
63 |
-
| 1.
|
64 |
-
| 1.
|
65 |
-
| 1.
|
66 |
-
| 1.
|
67 |
-
| 1.
|
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.
|
85 |
-
| 1.
|
86 |
-
| 1.
|
87 |
-
| 1.
|
88 |
-
| 1.
|
89 |
-
| 1.
|
90 |
-
| 1.
|
91 |
-
| 1.
|
92 |
-
|
|
93 |
-
|
|
94 |
-
|
|
95 |
-
|
|
96 |
-
|
|
97 |
-
| 0.
|
98 |
-
| 0.
|
99 |
-
|
|
100 |
-
|
|
101 |
-
| 0.
|
102 |
-
| 0.
|
103 |
-
| 0.
|
104 |
-
| 0.93 | 2.7168 | 470 | 1.2395 |
|
105 |
-
| 0.9111 | 2.7746 | 480 | 1.2418 |
|
106 |
-
| 0.9125 | 2.8324 | 490 | 1.2396 |
|
107 |
-
| 0.9268 | 2.8902 | 500 | 1.2389 |
|
108 |
-
| 0.9148 | 2.9480 | 510 | 1.2394 |
|
109 |
|
110 |
|
111 |
### Framework versions
|
|
|
21 |
|
22 |
This model is a fine-tuned version of [unsloth/tinyllama-bnb-4bit](https://huggingface.co/unsloth/tinyllama-bnb-4bit) on the generator dataset.
|
23 |
It achieves the following results on the evaluation set:
|
24 |
+
- Loss: 1.0067
|
25 |
|
26 |
## Model description
|
27 |
|
|
|
48 |
- total_train_batch_size: 32
|
49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
- lr_scheduler_type: linear
|
51 |
+
- num_epochs: 2
|
52 |
- mixed_precision_training: Native AMP
|
53 |
|
54 |
### Training results
|
55 |
|
56 |
| Training Loss | Epoch | Step | Validation Loss |
|
57 |
|:-------------:|:------:|:----:|:---------------:|
|
58 |
+
| 1.4976 | 0.0431 | 10 | 1.3395 |
|
59 |
+
| 1.2954 | 0.0862 | 20 | 1.2420 |
|
60 |
+
| 1.2219 | 0.1293 | 30 | 1.1957 |
|
61 |
+
| 1.1914 | 0.1724 | 40 | 1.1660 |
|
62 |
+
| 1.1515 | 0.2155 | 50 | 1.1449 |
|
63 |
+
| 1.1491 | 0.2586 | 60 | 1.1301 |
|
64 |
+
| 1.129 | 0.3017 | 70 | 1.1172 |
|
65 |
+
| 1.1175 | 0.3448 | 80 | 1.1070 |
|
66 |
+
| 1.1129 | 0.3879 | 90 | 1.0982 |
|
67 |
+
| 1.088 | 0.4310 | 100 | 1.0902 |
|
68 |
+
| 1.0823 | 0.4741 | 110 | 1.0847 |
|
69 |
+
| 1.0912 | 0.5172 | 120 | 1.0789 |
|
70 |
+
| 1.0847 | 0.5603 | 130 | 1.0734 |
|
71 |
+
| 1.0773 | 0.6034 | 140 | 1.0689 |
|
72 |
+
| 1.0671 | 0.6466 | 150 | 1.0632 |
|
73 |
+
| 1.0711 | 0.6897 | 160 | 1.0602 |
|
74 |
+
| 1.0607 | 0.7328 | 170 | 1.0558 |
|
75 |
+
| 1.0579 | 0.7759 | 180 | 1.0515 |
|
76 |
+
| 1.0565 | 0.8190 | 190 | 1.0481 |
|
77 |
+
| 1.0605 | 0.8621 | 200 | 1.0459 |
|
78 |
+
| 1.0626 | 0.9052 | 210 | 1.0413 |
|
79 |
+
| 1.0363 | 0.9483 | 220 | 1.0392 |
|
80 |
+
| 1.0422 | 0.9914 | 230 | 1.0363 |
|
81 |
+
| 1.0365 | 1.0345 | 240 | 1.0359 |
|
82 |
+
| 1.0083 | 1.0776 | 250 | 1.0327 |
|
83 |
+
| 1.0138 | 1.1207 | 260 | 1.0297 |
|
84 |
+
| 1.015 | 1.1638 | 270 | 1.0275 |
|
85 |
+
| 1.0116 | 1.2069 | 280 | 1.0258 |
|
86 |
+
| 1.0168 | 1.25 | 290 | 1.0245 |
|
87 |
+
| 1.0147 | 1.2931 | 300 | 1.0225 |
|
88 |
+
| 1.022 | 1.3362 | 310 | 1.0203 |
|
89 |
+
| 1.0118 | 1.3793 | 320 | 1.0199 |
|
90 |
+
| 1.0069 | 1.4224 | 330 | 1.0181 |
|
91 |
+
| 1.0042 | 1.4655 | 340 | 1.0163 |
|
92 |
+
| 0.9963 | 1.5086 | 350 | 1.0145 |
|
93 |
+
| 1.0127 | 1.5517 | 360 | 1.0137 |
|
94 |
+
| 1.0076 | 1.5948 | 370 | 1.0125 |
|
95 |
+
| 1.0127 | 1.6379 | 380 | 1.0113 |
|
96 |
+
| 1.0048 | 1.6810 | 390 | 1.0102 |
|
97 |
+
| 0.9904 | 1.7241 | 400 | 1.0093 |
|
98 |
+
| 0.9971 | 1.7672 | 410 | 1.0091 |
|
99 |
+
| 1.0073 | 1.8103 | 420 | 1.0082 |
|
100 |
+
| 1.0138 | 1.8534 | 430 | 1.0077 |
|
101 |
+
| 0.9952 | 1.8966 | 440 | 1.0074 |
|
102 |
+
| 0.9977 | 1.9397 | 450 | 1.0070 |
|
103 |
+
| 0.9966 | 1.9828 | 460 | 1.0067 |
|
|
|
|
|
|
|
|
|
|
|
104 |
|
105 |
|
106 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -11,7 +11,7 @@
|
|
11 |
"layers_to_transform": null,
|
12 |
"loftq_config": {},
|
13 |
"lora_alpha": 32,
|
14 |
-
"lora_dropout": 0.
|
15 |
"megatron_config": null,
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": null,
|
@@ -20,10 +20,17 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
|
|
23 |
"mlp.gate_up_proj",
|
|
|
|
|
|
|
|
|
|
|
24 |
"self_attn.qkv_proj.weight",
|
25 |
"self_attn.o_proj.weight",
|
26 |
-
"
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM",
|
29 |
"use_dora": false,
|
|
|
11 |
"layers_to_transform": null,
|
12 |
"loftq_config": {},
|
13 |
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.2,
|
15 |
"megatron_config": null,
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": null,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"gate_proj",
|
24 |
+
"down_proj",
|
25 |
"mlp.gate_up_proj",
|
26 |
+
"v_proj",
|
27 |
+
"q_proj",
|
28 |
+
"up_proj",
|
29 |
+
"mlp.down_proj",
|
30 |
+
"o_proj",
|
31 |
"self_attn.qkv_proj.weight",
|
32 |
"self_attn.o_proj.weight",
|
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 403743472
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65aac8e52d2b349519b5438dcb882cfad4794a93ffd157f9b49d878172d92e61
|
3 |
size 403743472
|
runs/Sep23_13-14-37_sammie/events.out.tfevents.1727118893.sammie.79670.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16a8e47d84587b1d54eb6d070362ce65ae6d5e60efb01d0524b858e9e6f74578
|
3 |
+
size 28373
|
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:b191efad8e0c67e59627b59005b61e1c57ea0e8f2b81b8642ae1ab1df6697c9a
|
3 |
size 5560
|