Model save
Browse files- README.md +6 -12
- config.json +2 -2
- model.safetensors +2 -2
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
-
- Loss: 3.
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -44,17 +44,11 @@ The following hyperparameters were used during training:
|
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
| 47 |
-
| Training Loss | Epoch
|
| 48 |
-
|
| 49 |
-
| 3.
|
| 50 |
-
| 3.
|
| 51 |
-
| 3.
|
| 52 |
-
| 3.4908 | 0.4267 | 20000 | 3.4197 |
|
| 53 |
-
| 3.4619 | 0.5333 | 25000 | 3.3903 |
|
| 54 |
-
| 3.4429 | 0.64 | 30000 | 3.3747 |
|
| 55 |
-
| 3.4329 | 0.7467 | 35000 | 3.3571 |
|
| 56 |
-
| 3.3625 | 0.8533 | 40000 | 3.2989 |
|
| 57 |
-
| 3.3315 | 0.96 | 45000 | 3.2592 |
|
| 58 |
|
| 59 |
|
| 60 |
### Framework versions
|
|
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 3.4163
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
|
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 49 |
+
| 3.7975 | 0.32 | 5000 | 3.8163 |
|
| 50 |
+
| 3.5694 | 0.64 | 10000 | 3.5999 |
|
| 51 |
+
| 3.3983 | 0.96 | 15000 | 3.4163 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
|
| 53 |
|
| 54 |
### Framework versions
|
config.json
CHANGED
|
@@ -3,13 +3,13 @@
|
|
| 3 |
"NeoLLMForCausalLM"
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
-
"attention_dropout": 0.
|
| 7 |
"auto_map": {
|
| 8 |
"AutoConfig": "configuration_neollm.NeoLLMConfig",
|
| 9 |
"AutoModel": "modeling_neollm.NeoLLMModel",
|
| 10 |
"AutoModelForCausalLM": "modeling_neollm.NeoLLMForCausalLM"
|
| 11 |
},
|
| 12 |
-
"dropout_rate": 0.
|
| 13 |
"dtype": "bfloat16",
|
| 14 |
"eos_token_id": 151645,
|
| 15 |
"fan_ratio": 0.125,
|
|
|
|
| 3 |
"NeoLLMForCausalLM"
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
"auto_map": {
|
| 8 |
"AutoConfig": "configuration_neollm.NeoLLMConfig",
|
| 9 |
"AutoModel": "modeling_neollm.NeoLLMModel",
|
| 10 |
"AutoModelForCausalLM": "modeling_neollm.NeoLLMForCausalLM"
|
| 11 |
},
|
| 12 |
+
"dropout_rate": 0.0,
|
| 13 |
"dtype": "bfloat16",
|
| 14 |
"eos_token_id": 151645,
|
| 15 |
"fan_ratio": 0.125,
|
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 sha256:14a73049118eb00022b428d10b8c7d9713770f38ef65f86eda0129f09ad2156f
|
| 3 |
+
size 245234560
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5585
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86d71a19a4e8e2ae7a224dd51e85a427e5436faac9e034d1764e85669441181e
|
| 3 |
size 5585
|