jssky commited on
Commit
d33d118
·
verified ·
1 Parent(s): 7b60462

End of training

Browse files
README.md CHANGED
@@ -114,7 +114,7 @@ xformers_attention: null
114
 
115
  This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v0.6](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v0.6) on the None dataset.
116
  It achieves the following results on the evaluation set:
117
- - Loss: 5.1028
118
 
119
  ## Model description
120
 
@@ -153,10 +153,10 @@ The following hyperparameters were used during training:
153
  | Training Loss | Epoch | Step | Validation Loss |
154
  |:-------------:|:------:|:----:|:---------------:|
155
  | 7.6743 | 0.0028 | 1 | 7.1293 |
156
- | 7.7429 | 0.0141 | 5 | 7.0976 |
157
- | 7.0434 | 0.0283 | 10 | 6.3337 |
158
- | 5.7719 | 0.0424 | 15 | 5.4988 |
159
- | 5.695 | 0.0565 | 20 | 5.1028 |
160
 
161
 
162
  ### Framework versions
 
114
 
115
  This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v0.6](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v0.6) on the None dataset.
116
  It achieves the following results on the evaluation set:
117
+ - Loss: 5.1046
118
 
119
  ## Model description
120
 
 
153
  | Training Loss | Epoch | Step | Validation Loss |
154
  |:-------------:|:------:|:----:|:---------------:|
155
  | 7.6743 | 0.0028 | 1 | 7.1293 |
156
+ | 7.7426 | 0.0141 | 5 | 7.0973 |
157
+ | 7.0417 | 0.0283 | 10 | 6.3321 |
158
+ | 5.7705 | 0.0424 | 15 | 5.4978 |
159
+ | 5.6954 | 0.0565 | 20 | 5.1046 |
160
 
161
 
162
  ### Framework versions
adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "up_proj",
24
- "o_proj",
25
- "gate_proj",
26
  "v_proj",
27
- "k_proj",
28
  "down_proj",
29
- "q_proj"
 
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
 
23
  "v_proj",
24
+ "up_proj",
25
  "down_proj",
26
+ "gate_proj",
27
+ "o_proj",
28
+ "q_proj",
29
+ "k_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66a28a9f8f443f7dce46fe12d04b3a6652a55ffeeeba0e4609553b913fa87b77
3
  size 101036698
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75d6d99a911e1898887876a012bb5f063d98f1d0f108c408c15a9a760ccc085a
3
  size 101036698
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c0ecc2e9a75d14c753ea2123cc052ce634a5ace8a27427e3887b3bd040ff88f
3
  size 100966336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6937250c3c124f08bcfec45cd4a325f3405cb3f1f96296f7ad31bd5500713d84
3
  size 100966336
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:676c5b957839737d77485c6332fc96de69385066f3eef0d74b47f677462f11dc
3
  size 6712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b55d7424e01d2da7c827809f0e75e814ca3307809331f5d1880db7934ea6a65
3
  size 6712