End of training
Browse files- README.md +2 -4
- config.json +1 -1
- model.safetensors +1 -1
- runs/Sep12_17-50-14_c3b0cc9036b7/events.out.tfevents.1726163520.c3b0cc9036b7.323.0 +3 -0
- tokenizer_config.json +4 -0
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,7 +1,5 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
-
license: apache-2.0
|
| 4 |
-
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
|
| 5 |
tags:
|
| 6 |
- trl
|
| 7 |
- sft
|
|
@@ -16,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# fake_planet
|
| 18 |
|
| 19 |
-
This model
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -41,7 +39,7 @@ The following hyperparameters were used during training:
|
|
| 41 |
- seed: 42
|
| 42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
-
- num_epochs:
|
| 45 |
|
| 46 |
### Training results
|
| 47 |
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
|
|
|
|
|
|
| 3 |
tags:
|
| 4 |
- trl
|
| 5 |
- sft
|
|
|
|
| 14 |
|
| 15 |
# fake_planet
|
| 16 |
|
| 17 |
+
This model was trained from scratch on an unknown dataset.
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
|
|
| 39 |
- seed: 42
|
| 40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
- lr_scheduler_type: linear
|
| 42 |
+
- num_epochs: 10
|
| 43 |
|
| 44 |
### Training results
|
| 45 |
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "ainth89/fake_planet",
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4400216536
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f43d03e0df002022ca671f7c4a21c4ab266861d7eed85461e2efbce6762c475
|
| 3 |
size 4400216536
|
runs/Sep12_17-50-14_c3b0cc9036b7/events.out.tfevents.1726163520.c3b0cc9036b7.323.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90927dba623261ef0aff4fe230ae3c1ed3fe6154dca2c6b97e3f5295e10f5cc4
|
| 3 |
+
size 5615
|
tokenizer_config.json
CHANGED
|
@@ -33,11 +33,15 @@
|
|
| 33 |
"clean_up_tokenization_spaces": false,
|
| 34 |
"eos_token": "</s>",
|
| 35 |
"legacy": false,
|
|
|
|
| 36 |
"model_max_length": 2048,
|
| 37 |
"pad_token": "</s>",
|
| 38 |
"padding_side": "right",
|
| 39 |
"sp_model_kwargs": {},
|
|
|
|
| 40 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
|
|
| 41 |
"unk_token": "<unk>",
|
| 42 |
"use_default_system_prompt": false
|
| 43 |
}
|
|
|
|
| 33 |
"clean_up_tokenization_spaces": false,
|
| 34 |
"eos_token": "</s>",
|
| 35 |
"legacy": false,
|
| 36 |
+
"max_length": 1024,
|
| 37 |
"model_max_length": 2048,
|
| 38 |
"pad_token": "</s>",
|
| 39 |
"padding_side": "right",
|
| 40 |
"sp_model_kwargs": {},
|
| 41 |
+
"stride": 0,
|
| 42 |
"tokenizer_class": "LlamaTokenizer",
|
| 43 |
+
"truncation_side": "right",
|
| 44 |
+
"truncation_strategy": "longest_first",
|
| 45 |
"unk_token": "<unk>",
|
| 46 |
"use_default_system_prompt": false
|
| 47 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5432
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a74200f55bd652e30c6c11080a10497122b5052c2bad93b246cff402ebb969b
|
| 3 |
size 5432
|