SourCoachSauers
commited on
Commit
•
0115b42
1
Parent(s):
966e43b
color_descriptions
Browse files- README.md +6 -31
- adapter_config.json +5 -3
- adapter_model.safetensors +2 -2
- runs/Jul19_00-59-20_ip-172-18-179-228.us-west-2.compute.internal/events.out.tfevents.1721350777.ip-172-18-179-228.us-west-2.compute.internal.3457.0 +3 -0
- runs/Jul19_01-03-17_ip-172-18-179-228.us-west-2.compute.internal/events.out.tfevents.1721351010.ip-172-18-179-228.us-west-2.compute.internal.3457.1 +3 -0
- runs/Jul19_01-04-11_ip-172-18-179-228.us-west-2.compute.internal/events.out.tfevents.1721351090.ip-172-18-179-228.us-west-2.compute.internal.3457.2 +3 -0
- runs/Jul19_01-11-33_ip-172-18-179-228.us-west-2.compute.internal/events.out.tfevents.1721351504.ip-172-18-179-228.us-west-2.compute.internal.4758.0 +3 -0
- runs/Jul19_02-02-18_ip-172-18-179-228.us-west-2.compute.internal/events.out.tfevents.1721354552.ip-172-18-179-228.us-west-2.compute.internal.4758.1 +3 -0
- runs/Jul19_04-32-22_ip-172-18-179-228.us-west-2.compute.internal/events.out.tfevents.1721363551.ip-172-18-179-228.us-west-2.compute.internal.4758.2 +3 -0
- runs/Jul19_04-33-51_ip-172-18-179-228.us-west-2.compute.internal/events.out.tfevents.1721363639.ip-172-18-179-228.us-west-2.compute.internal.4758.3 +3 -0
- tokenizer.json +6 -28
- tokenizer_config.json +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -17,8 +17,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
# results
|
18 |
|
19 |
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on an unknown dataset.
|
20 |
-
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 0.5881
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -37,48 +35,25 @@ More information needed
|
|
37 |
### Training hyperparameters
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
-
- learning_rate:
|
41 |
- train_batch_size: 16
|
42 |
-
- eval_batch_size:
|
43 |
- seed: 42
|
44 |
-
- gradient_accumulation_steps:
|
45 |
-
- total_train_batch_size:
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: cosine
|
48 |
- lr_scheduler_warmup_ratio: 0.03
|
49 |
-
- num_epochs:
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
-
|:-------------:|:------:|:----:|:---------------:|
|
55 |
-
| 0.6511 | 0.0948 | 50 | 0.7913 |
|
56 |
-
| 0.5479 | 0.1896 | 100 | 0.7001 |
|
57 |
-
| 0.5125 | 0.2844 | 150 | 0.6768 |
|
58 |
-
| 0.4974 | 0.3791 | 200 | 0.6564 |
|
59 |
-
| 0.4947 | 0.4739 | 250 | 0.6490 |
|
60 |
-
| 0.4802 | 0.5687 | 300 | 0.6383 |
|
61 |
-
| 0.4762 | 0.6635 | 350 | 0.6289 |
|
62 |
-
| 0.4678 | 0.7583 | 400 | 0.6233 |
|
63 |
-
| 0.4742 | 0.8531 | 450 | 0.6157 |
|
64 |
-
| 0.4633 | 0.9479 | 500 | 0.6127 |
|
65 |
-
| 0.6096 | 1.0427 | 550 | 0.6027 |
|
66 |
-
| 0.6137 | 1.1374 | 600 | 0.5986 |
|
67 |
-
| 0.6163 | 1.2322 | 650 | 0.5963 |
|
68 |
-
| 0.6078 | 1.3270 | 700 | 0.5943 |
|
69 |
-
| 0.6019 | 1.4218 | 750 | 0.5921 |
|
70 |
-
| 0.615 | 1.5166 | 800 | 0.5906 |
|
71 |
-
| 0.6061 | 1.6114 | 850 | 0.5897 |
|
72 |
-
| 0.6106 | 1.7062 | 900 | 0.5890 |
|
73 |
-
| 0.6027 | 1.8009 | 950 | 0.5886 |
|
74 |
-
| 0.6094 | 1.8957 | 1000 | 0.5883 |
|
75 |
-
| 0.5261 | 1.9905 | 1050 | 0.5881 |
|
76 |
|
77 |
|
78 |
### Framework versions
|
79 |
|
80 |
- PEFT 0.11.1
|
81 |
- Transformers 4.42.4
|
82 |
-
- Pytorch 2.
|
83 |
- Datasets 2.20.0
|
84 |
- Tokenizers 0.19.1
|
|
|
17 |
# results
|
18 |
|
19 |
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on an unknown dataset.
|
|
|
|
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
35 |
### Training hyperparameters
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 5e-05
|
39 |
- train_batch_size: 16
|
40 |
+
- eval_batch_size: 16
|
41 |
- seed: 42
|
42 |
+
- gradient_accumulation_steps: 2
|
43 |
+
- total_train_batch_size: 32
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: cosine
|
46 |
- lr_scheduler_warmup_ratio: 0.03
|
47 |
+
- num_epochs: 4
|
48 |
|
49 |
### Training results
|
50 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
51 |
|
52 |
|
53 |
### Framework versions
|
54 |
|
55 |
- PEFT 0.11.1
|
56 |
- Transformers 4.42.4
|
57 |
+
- Pytorch 2.2.1+cu121
|
58 |
- Datasets 2.20.0
|
59 |
- Tokenizers 0.19.1
|
adapter_config.json
CHANGED
@@ -20,11 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"gate_proj",
|
24 |
-
"k_proj",
|
25 |
"o_proj",
|
|
|
|
|
26 |
"q_proj",
|
27 |
-
"
|
|
|
|
|
28 |
],
|
29 |
"task_type": "CAUSAL_LM",
|
30 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
|
|
23 |
"o_proj",
|
24 |
+
"up_proj",
|
25 |
+
"v_proj",
|
26 |
"q_proj",
|
27 |
+
"k_proj",
|
28 |
+
"gate_proj",
|
29 |
+
"down_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"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 sha256:645abf6023751672c8614dddd0d1ee30fa2675b3814886885fb9520d2face926
|
3 |
+
size 100966336
|
runs/Jul19_00-59-20_ip-172-18-179-228.us-west-2.compute.internal/events.out.tfevents.1721350777.ip-172-18-179-228.us-west-2.compute.internal.3457.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9cc54f55514bc1f151f2e4020230daea977ea40ac20ece589abae1eb2c12039d
|
3 |
+
size 5692
|
runs/Jul19_01-03-17_ip-172-18-179-228.us-west-2.compute.internal/events.out.tfevents.1721351010.ip-172-18-179-228.us-west-2.compute.internal.3457.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef7d5908131af25807a4cf5bfff2bdec65469af6b8060c697869f4e861e5e05d
|
3 |
+
size 5692
|
runs/Jul19_01-04-11_ip-172-18-179-228.us-west-2.compute.internal/events.out.tfevents.1721351090.ip-172-18-179-228.us-west-2.compute.internal.3457.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9090eaa40c6aba1a3a90f5a7c055d4d70dec79c9e19b0e00d9826fc8486e85a
|
3 |
+
size 4184
|
runs/Jul19_01-11-33_ip-172-18-179-228.us-west-2.compute.internal/events.out.tfevents.1721351504.ip-172-18-179-228.us-west-2.compute.internal.4758.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:006f9639b20c8a6cac56e074c518fa863febd289b687887488a9236d1eea0c08
|
3 |
+
size 13801
|
runs/Jul19_02-02-18_ip-172-18-179-228.us-west-2.compute.internal/events.out.tfevents.1721354552.ip-172-18-179-228.us-west-2.compute.internal.4758.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d26e819e9ed3bf2849bb33bf63a34187b22adce70676c0c27caecb09bbe33404
|
3 |
+
size 209850
|
runs/Jul19_04-32-22_ip-172-18-179-228.us-west-2.compute.internal/events.out.tfevents.1721363551.ip-172-18-179-228.us-west-2.compute.internal.4758.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5df9aa8e123395c1f7631afb3a48a5cda27c8aa4730ef75d2545d364d2d3586
|
3 |
+
size 8584
|
runs/Jul19_04-33-51_ip-172-18-179-228.us-west-2.compute.internal/events.out.tfevents.1721363639.ip-172-18-179-228.us-west-2.compute.internal.4758.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c480f55a4e64a0ddf47cab4b8e4fdb6c76ab60679366f8d846330f5de461ef5
|
3 |
+
size 895952
|
tokenizer.json
CHANGED
@@ -1,6 +1,11 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
@@ -62,12 +67,6 @@
|
|
62 |
"id": "A",
|
63 |
"type_id": 0
|
64 |
}
|
65 |
-
},
|
66 |
-
{
|
67 |
-
"SpecialToken": {
|
68 |
-
"id": "</s>",
|
69 |
-
"type_id": 0
|
70 |
-
}
|
71 |
}
|
72 |
],
|
73 |
"pair": [
|
@@ -83,12 +82,6 @@
|
|
83 |
"type_id": 0
|
84 |
}
|
85 |
},
|
86 |
-
{
|
87 |
-
"SpecialToken": {
|
88 |
-
"id": "</s>",
|
89 |
-
"type_id": 0
|
90 |
-
}
|
91 |
-
},
|
92 |
{
|
93 |
"SpecialToken": {
|
94 |
"id": "<s>",
|
@@ -100,24 +93,9 @@
|
|
100 |
"id": "B",
|
101 |
"type_id": 1
|
102 |
}
|
103 |
-
},
|
104 |
-
{
|
105 |
-
"SpecialToken": {
|
106 |
-
"id": "</s>",
|
107 |
-
"type_id": 1
|
108 |
-
}
|
109 |
}
|
110 |
],
|
111 |
"special_tokens": {
|
112 |
-
"</s>": {
|
113 |
-
"id": "</s>",
|
114 |
-
"ids": [
|
115 |
-
2
|
116 |
-
],
|
117 |
-
"tokens": [
|
118 |
-
"</s>"
|
119 |
-
]
|
120 |
-
},
|
121 |
"<s>": {
|
122 |
"id": "<s>",
|
123 |
"ids": [
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 4096,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
|
|
67 |
"id": "A",
|
68 |
"type_id": 0
|
69 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
70 |
}
|
71 |
],
|
72 |
"pair": [
|
|
|
82 |
"type_id": 0
|
83 |
}
|
84 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
85 |
{
|
86 |
"SpecialToken": {
|
87 |
"id": "<s>",
|
|
|
93 |
"id": "B",
|
94 |
"type_id": 1
|
95 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
96 |
}
|
97 |
],
|
98 |
"special_tokens": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
99 |
"<s>": {
|
100 |
"id": "<s>",
|
101 |
"ids": [
|
tokenizer_config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
-
"add_eos_token":
|
4 |
"add_prefix_space": null,
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
"add_prefix_space": null,
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5368
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dfd7cdd1c35aab3464be0d42f2aa51cc21686ab26d0335c1bb004cbb44880bdd
|
3 |
size 5368
|