Hugging Face's logo

Triangles
/
gpt-neo-125m-finetuned-philosopher_rave_100

Text Generation
Transformers
TensorBoard
Safetensors
gpt_neo
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
ColleenMacklin commited on
Commit
92b4430
•
1 Parent(s): 3cc307f

gpt-neo-125m-finetuned-philosopher_rave_100

Browse files
Files changed (4) hide show
  1. README.md +156 -0
  2. generation_config.json +6 -0
  3. runs/Apr04_15-55-42_590c786a3313/events.out.tfevents.1712246171.590c786a3313.4137.4 +2 -2
  4. runs/Apr04_15-55-42_590c786a3313/events.out.tfevents.1712248561.590c786a3313.4137.5 +3 -0
README.md ADDED
@@ -0,0 +1,156 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: EleutherAI/gpt-neo-125m
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: gpt-neo-125m-finetuned-philosopher_rave_100
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # gpt-neo-125m-finetuned-philosopher_rave_100
15
+
16
+ This model is a fine-tuned version of [EleutherAI/gpt-neo-125m](https://huggingface.co/EleutherAI/gpt-neo-125m) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 2.3681
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 3e-07
38
+ - train_batch_size: 8
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 100.0
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:-----:|:---------------:|
49
+ | No log | 1.0 | 155 | 2.6967 |
50
+ | No log | 2.0 | 310 | 2.6846 |
51
+ | No log | 3.0 | 465 | 2.6733 |
52
+ | 2.6891 | 4.0 | 620 | 2.6626 |
53
+ | 2.6891 | 5.0 | 775 | 2.6524 |
54
+ | 2.6891 | 6.0 | 930 | 2.6427 |
55
+ | 2.6569 | 7.0 | 1085 | 2.6336 |
56
+ | 2.6569 | 8.0 | 1240 | 2.6248 |
57
+ | 2.6569 | 9.0 | 1395 | 2.6164 |
58
+ | 2.6215 | 10.0 | 1550 | 2.6083 |
59
+ | 2.6215 | 11.0 | 1705 | 2.6005 |
60
+ | 2.6215 | 12.0 | 1860 | 2.5931 |
61
+ | 2.6022 | 13.0 | 2015 | 2.5858 |
62
+ | 2.6022 | 14.0 | 2170 | 2.5789 |
63
+ | 2.6022 | 15.0 | 2325 | 2.5721 |
64
+ | 2.6022 | 16.0 | 2480 | 2.5657 |
65
+ | 2.5777 | 17.0 | 2635 | 2.5594 |
66
+ | 2.5777 | 18.0 | 2790 | 2.5532 |
67
+ | 2.5777 | 19.0 | 2945 | 2.5473 |
68
+ | 2.5548 | 20.0 | 3100 | 2.5416 |
69
+ | 2.5548 | 21.0 | 3255 | 2.5360 |
70
+ | 2.5548 | 22.0 | 3410 | 2.5306 |
71
+ | 2.5359 | 23.0 | 3565 | 2.5253 |
72
+ | 2.5359 | 24.0 | 3720 | 2.5202 |
73
+ | 2.5359 | 25.0 | 3875 | 2.5152 |
74
+ | 2.5248 | 26.0 | 4030 | 2.5103 |
75
+ | 2.5248 | 27.0 | 4185 | 2.5056 |
76
+ | 2.5248 | 28.0 | 4340 | 2.5011 |
77
+ | 2.5248 | 29.0 | 4495 | 2.4966 |
78
+ | 2.5053 | 30.0 | 4650 | 2.4922 |
79
+ | 2.5053 | 31.0 | 4805 | 2.4880 |
80
+ | 2.5053 | 32.0 | 4960 | 2.4839 |
81
+ | 2.4871 | 33.0 | 5115 | 2.4798 |
82
+ | 2.4871 | 34.0 | 5270 | 2.4759 |
83
+ | 2.4871 | 35.0 | 5425 | 2.4721 |
84
+ | 2.4808 | 36.0 | 5580 | 2.4683 |
85
+ | 2.4808 | 37.0 | 5735 | 2.4647 |
86
+ | 2.4808 | 38.0 | 5890 | 2.4612 |
87
+ | 2.4659 | 39.0 | 6045 | 2.4577 |
88
+ | 2.4659 | 40.0 | 6200 | 2.4544 |
89
+ | 2.4659 | 41.0 | 6355 | 2.4511 |
90
+ | 2.4517 | 42.0 | 6510 | 2.4479 |
91
+ | 2.4517 | 43.0 | 6665 | 2.4447 |
92
+ | 2.4517 | 44.0 | 6820 | 2.4417 |
93
+ | 2.4517 | 45.0 | 6975 | 2.4387 |
94
+ | 2.4466 | 46.0 | 7130 | 2.4359 |
95
+ | 2.4466 | 47.0 | 7285 | 2.4330 |
96
+ | 2.4466 | 48.0 | 7440 | 2.4303 |
97
+ | 2.4348 | 49.0 | 7595 | 2.4276 |
98
+ | 2.4348 | 50.0 | 7750 | 2.4250 |
99
+ | 2.4348 | 51.0 | 7905 | 2.4225 |
100
+ | 2.4238 | 52.0 | 8060 | 2.4201 |
101
+ | 2.4238 | 53.0 | 8215 | 2.4177 |
102
+ | 2.4238 | 54.0 | 8370 | 2.4154 |
103
+ | 2.4172 | 55.0 | 8525 | 2.4131 |
104
+ | 2.4172 | 56.0 | 8680 | 2.4109 |
105
+ | 2.4172 | 57.0 | 8835 | 2.4088 |
106
+ | 2.4172 | 58.0 | 8990 | 2.4067 |
107
+ | 2.4097 | 59.0 | 9145 | 2.4047 |
108
+ | 2.4097 | 60.0 | 9300 | 2.4027 |
109
+ | 2.4097 | 61.0 | 9455 | 2.4008 |
110
+ | 2.4054 | 62.0 | 9610 | 2.3990 |
111
+ | 2.4054 | 63.0 | 9765 | 2.3972 |
112
+ | 2.4054 | 64.0 | 9920 | 2.3955 |
113
+ | 2.3936 | 65.0 | 10075 | 2.3938 |
114
+ | 2.3936 | 66.0 | 10230 | 2.3922 |
115
+ | 2.3936 | 67.0 | 10385 | 2.3906 |
116
+ | 2.394 | 68.0 | 10540 | 2.3891 |
117
+ | 2.394 | 69.0 | 10695 | 2.3877 |
118
+ | 2.394 | 70.0 | 10850 | 2.3863 |
119
+ | 2.387 | 71.0 | 11005 | 2.3850 |
120
+ | 2.387 | 72.0 | 11160 | 2.3837 |
121
+ | 2.387 | 73.0 | 11315 | 2.3824 |
122
+ | 2.387 | 74.0 | 11470 | 2.3813 |
123
+ | 2.3812 | 75.0 | 11625 | 2.3801 |
124
+ | 2.3812 | 76.0 | 11780 | 2.3791 |
125
+ | 2.3812 | 77.0 | 11935 | 2.3780 |
126
+ | 2.3812 | 78.0 | 12090 | 2.3771 |
127
+ | 2.3812 | 79.0 | 12245 | 2.3762 |
128
+ | 2.3812 | 80.0 | 12400 | 2.3753 |
129
+ | 2.3802 | 81.0 | 12555 | 2.3745 |
130
+ | 2.3802 | 82.0 | 12710 | 2.3737 |
131
+ | 2.3802 | 83.0 | 12865 | 2.3730 |
132
+ | 2.3687 | 84.0 | 13020 | 2.3723 |
133
+ | 2.3687 | 85.0 | 13175 | 2.3717 |
134
+ | 2.3687 | 86.0 | 13330 | 2.3711 |
135
+ | 2.3687 | 87.0 | 13485 | 2.3706 |
136
+ | 2.3722 | 88.0 | 13640 | 2.3702 |
137
+ | 2.3722 | 89.0 | 13795 | 2.3698 |
138
+ | 2.3722 | 90.0 | 13950 | 2.3694 |
139
+ | 2.3693 | 91.0 | 14105 | 2.3691 |
140
+ | 2.3693 | 92.0 | 14260 | 2.3688 |
141
+ | 2.3693 | 93.0 | 14415 | 2.3686 |
142
+ | 2.3654 | 94.0 | 14570 | 2.3684 |
143
+ | 2.3654 | 95.0 | 14725 | 2.3683 |
144
+ | 2.3654 | 96.0 | 14880 | 2.3682 |
145
+ | 2.372 | 97.0 | 15035 | 2.3682 |
146
+ | 2.372 | 98.0 | 15190 | 2.3681 |
147
+ | 2.372 | 99.0 | 15345 | 2.3681 |
148
+ | 2.3664 | 100.0 | 15500 | 2.3681 |
149
+
150
+
151
+ ### Framework versions
152
+
153
+ - Transformers 4.39.3
154
+ - Pytorch 2.2.1+cu121
155
+ - Datasets 2.18.0
156
+ - Tokenizers 0.15.2
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.39.3"
6
+ }
runs/Apr04_15-55-42_590c786a3313/events.out.tfevents.1712246171.590c786a3313.4137.4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:836f09582430028642d4e2c1cba3655196115056f3a68706f3f3737944db6029
3
- size 38510
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c12036b4b84c0acdb89a458aea50886aeb9ab0d8aa7ca52f1ce87f7a7fd43e9
3
+ size 39135
runs/Apr04_15-55-42_590c786a3313/events.out.tfevents.1712248561.590c786a3313.4137.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a97efd511432913f962f15c7d1f2fefc89962918ec2108f183d18ed354a9336f
3
+ size 359