Commit
•
c782b58
1
Parent(s):
6f60379
End of training
Browse files- README.md +10 -1
- all_results.json +5 -0
- config.json +1 -1
- eval_results.json +8 -0
- runs/Oct04_23-40-49_56deac14d784/events.out.tfevents.1728216697.56deac14d784.1950.1 +3 -0
README.md
CHANGED
|
@@ -3,9 +3,18 @@ library_name: transformers
|
|
| 3 |
license: llama3.2
|
| 4 |
base_model: meta-llama/Llama-3.2-3B-Instruct
|
| 5 |
tags:
|
|
|
|
| 6 |
- trl
|
| 7 |
- sft
|
| 8 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
model-index:
|
| 10 |
- name: engineer-barc-llama3.2-3b-instruct-fft-transduction-lr1e-5_epoch3
|
| 11 |
results: []
|
|
@@ -16,7 +25,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# engineer-barc-llama3.2-3b-instruct-fft-transduction-lr1e-5_epoch3
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on the
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.0255
|
| 22 |
|
|
|
|
| 3 |
license: llama3.2
|
| 4 |
base_model: meta-llama/Llama-3.2-3B-Instruct
|
| 5 |
tags:
|
| 6 |
+
- alignment-handbook
|
| 7 |
- trl
|
| 8 |
- sft
|
| 9 |
- generated_from_trainer
|
| 10 |
+
- trl
|
| 11 |
+
- sft
|
| 12 |
+
- generated_from_trainer
|
| 13 |
+
datasets:
|
| 14 |
+
- barc0/transduction_concept_library
|
| 15 |
+
- barc0/transduction_angmented_100k-gpt4-description-gpt4omini-code_generated_problems
|
| 16 |
+
- barc0/transduction_angmented_100k_gpt4o-mini_generated_problems
|
| 17 |
+
- barc0/transduction_rearc_dataset_400k
|
| 18 |
model-index:
|
| 19 |
- name: engineer-barc-llama3.2-3b-instruct-fft-transduction-lr1e-5_epoch3
|
| 20 |
results: []
|
|
|
|
| 25 |
|
| 26 |
# engineer-barc-llama3.2-3b-instruct-fft-transduction-lr1e-5_epoch3
|
| 27 |
|
| 28 |
+
This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on the barc0/transduction_concept_library, the barc0/transduction_angmented_100k-gpt4-description-gpt4omini-code_generated_problems, the barc0/transduction_angmented_100k_gpt4o-mini_generated_problems and the barc0/transduction_rearc_dataset_400k datasets.
|
| 29 |
It achieves the following results on the evaluation set:
|
| 30 |
- Loss: 0.0255
|
| 31 |
|
all_results.json
CHANGED
|
@@ -1,5 +1,10 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"total_flos": 2332096332890112.0,
|
| 4 |
"train_loss": 0.03801635660235435,
|
| 5 |
"train_runtime": 128961.4313,
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.025541018694639206,
|
| 4 |
+
"eval_runtime": 787.6358,
|
| 5 |
+
"eval_samples": 19674,
|
| 6 |
+
"eval_samples_per_second": 24.979,
|
| 7 |
+
"eval_steps_per_second": 0.781,
|
| 8 |
"total_flos": 2332096332890112.0,
|
| 9 |
"train_loss": 0.03801635660235435,
|
| 10 |
"train_runtime": 128961.4313,
|
config.json
CHANGED
|
@@ -35,6 +35,6 @@
|
|
| 35 |
"tie_word_embeddings": true,
|
| 36 |
"torch_dtype": "bfloat16",
|
| 37 |
"transformers_version": "4.45.0.dev0",
|
| 38 |
-
"use_cache":
|
| 39 |
"vocab_size": 128256
|
| 40 |
}
|
|
|
|
| 35 |
"tie_word_embeddings": true,
|
| 36 |
"torch_dtype": "bfloat16",
|
| 37 |
"transformers_version": "4.45.0.dev0",
|
| 38 |
+
"use_cache": true,
|
| 39 |
"vocab_size": 128256
|
| 40 |
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.025541018694639206,
|
| 4 |
+
"eval_runtime": 787.6358,
|
| 5 |
+
"eval_samples": 19674,
|
| 6 |
+
"eval_samples_per_second": 24.979,
|
| 7 |
+
"eval_steps_per_second": 0.781
|
| 8 |
+
}
|
runs/Oct04_23-40-49_56deac14d784/events.out.tfevents.1728216697.56deac14d784.1950.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aaabaffc69ed79453ef0c1b1b0670963771e3ed05690d61ccbdd17e420843b6b
|
| 3 |
+
size 359
|