Hugging Face's logo

BEE-spoke-data
/
verysmol_llama-v11-KIx2

Text Generation
Transformers
Safetensors
llama
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files
pszemraj commited on
Commit
4a8cba0
·
1 Parent(s): f44a0ea

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -43
README.md CHANGED
@@ -9,7 +9,8 @@ inference:
9
  parameters:
10
  max_new_tokens: 64
11
  do_sample: true
12
- repetition_penalty: 1.2
 
13
  no_repeat_ngram_size: 5
14
  eta_cutoff: 0.0006
15
  renormalize_logits: true
@@ -105,48 +106,11 @@ The following hyperparameters were used during training:
105
  | 2.9282 | 0.2 | 900 | 2.9923 | 0.4358 |
106
  | 2.9485 | 0.23 | 1050 | 2.9845 | 0.4357 |
107
  | 2.9365 | 0.27 | 1200 | 2.9749 | 0.4375 |
108
- | 2.8875 | 0.3 | 1350 | 2.9652 | 0.4391 |
109
- | 2.8874 | 0.33 | 1500 | 2.9619 | 0.4402 |
110
- | 2.8733 | 0.37 | 1650 | 2.9574 | 0.4408 |
111
- | 2.8541 | 0.4 | 1800 | 2.9536 | 0.4403 |
112
- | 2.8958 | 0.43 | 1950 | 2.9491 | 0.4414 |
113
- | 2.8404 | 0.47 | 2100 | 2.9434 | 0.4427 |
114
- | 2.8635 | 0.5 | 2250 | 2.9404 | 0.4425 |
115
- | 2.9031 | 0.53 | 2400 | 2.9369 | 0.4428 |
116
- | 2.8237 | 0.57 | 2550 | 2.9330 | 0.4440 |
117
- | 2.832 | 0.6 | 2700 | 2.9318 | 0.4444 |
118
- | 2.8566 | 0.63 | 2850 | 2.9305 | 0.4450 |
119
- | 2.8817 | 0.67 | 3000 | 2.9286 | 0.4443 |
120
- | 2.8733 | 0.7 | 3150 | 2.9268 | 0.4442 |
121
- | 2.8009 | 0.73 | 3300 | 2.9227 | 0.4457 |
122
- | 2.9292 | 0.77 | 3450 | 2.9229 | 0.4450 |
123
- | 2.8562 | 0.8 | 3600 | 2.9193 | 0.4456 |
124
- | 2.8441 | 0.83 | 3750 | 2.9188 | 0.4460 |
125
- | 2.904 | 0.87 | 3900 | 2.9171 | 0.4458 |
126
- | 2.857 | 0.9 | 4050 | 2.9140 | 0.4461 |
127
- | 2.8344 | 0.93 | 4200 | 2.9134 | 0.4467 |
128
- | 2.8382 | 0.97 | 4350 | 2.9122 | 0.4467 |
129
- | 2.8227 | 1.0 | 4500 | 2.9104 | 0.4468 |
130
- | 2.8121 | 1.03 | 4650 | 2.9099 | 0.4472 |
131
- | 2.8127 | 1.07 | 4800 | 2.9082 | 0.4473 |
132
- | 2.8013 | 1.1 | 4950 | 2.9084 | 0.4478 |
133
- | 2.7983 | 1.14 | 5100 | 2.9069 | 0.4474 |
134
- | 2.811 | 1.17 | 5250 | 2.9076 | 0.4480 |
135
- | 2.7807 | 1.2 | 5400 | 2.9065 | 0.4471 |
136
- | 2.8512 | 1.24 | 5550 | 2.9056 | 0.4483 |
137
- | 2.8146 | 1.27 | 5700 | 2.9049 | 0.4478 |
138
- | 2.8101 | 1.3 | 5850 | 2.9024 | 0.4482 |
139
- | 2.7968 | 1.34 | 6000 | 2.9005 | 0.4484 |
140
- | 2.8197 | 1.37 | 6150 | 2.9001 | 0.4481 |
141
- | 2.8035 | 1.4 | 6300 | 2.8997 | 0.4488 |
142
- | 2.7905 | 1.44 | 6450 | 2.8996 | 0.4488 |
143
- | 2.8239 | 1.47 | 6600 | 2.8982 | 0.4487 |
144
- | 2.8579 | 1.5 | 6750 | 2.8975 | 0.4492 |
145
- | 2.7996 | 1.54 | 6900 | 2.8960 | 0.4492 |
146
- | 2.8337 | 1.57 | 7050 | 2.8984 | 0.4490 |
147
- | 2.8087 | 1.6 | 7200 | 2.8959 | 0.4492 |
148
- | 2.8066 | 1.64 | 7350 | 2.8952 | 0.4499 |
149
- | 2.7991 | 1.67 | 7500 | 2.8950 | 0.4492 |
150
  | 2.8215 | 1.7 | 7650 | 2.8943 | 0.4496 |
151
  | 2.7714 | 1.74 | 7800 | 2.8914 | 0.4501 |
152
  | 2.8132 | 1.77 | 7950 | 2.8913 | 0.4500 |
 
9
  parameters:
10
  max_new_tokens: 64
11
  do_sample: true
12
+ temperature: 0.85
13
+ repetition_penalty: 1.35
14
  no_repeat_ngram_size: 5
15
  eta_cutoff: 0.0006
16
  renormalize_logits: true
 
106
  | 2.9282 | 0.2 | 900 | 2.9923 | 0.4358 |
107
  | 2.9485 | 0.23 | 1050 | 2.9845 | 0.4357 |
108
  | 2.9365 | 0.27 | 1200 | 2.9749 | 0.4375 |
109
+
110
+ ...
111
+
112
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
113
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
114
  | 2.8215 | 1.7 | 7650 | 2.8943 | 0.4496 |
115
  | 2.7714 | 1.74 | 7800 | 2.8914 | 0.4501 |
116
  | 2.8132 | 1.77 | 7950 | 2.8913 | 0.4500 |