antonpolishko
commited on
Commit
•
f64a21e
1
Parent(s):
4f38f5f
End of training
Browse files
README.md
CHANGED
@@ -1,11 +1,15 @@
|
|
1 |
---
|
2 |
base_model: PolyAgent/mistral-7b-v0.3-ua-tokenizer-v2-focus-base
|
3 |
tags:
|
|
|
|
|
|
|
|
|
4 |
- trl
|
5 |
- sft
|
6 |
- generated_from_trainer
|
7 |
datasets:
|
8 |
-
-
|
9 |
model-index:
|
10 |
- name: mistral-v0.3-tokV2-gentle-train
|
11 |
results: []
|
@@ -16,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
# mistral-v0.3-tokV2-gentle-train
|
18 |
|
19 |
-
This model is a fine-tuned version of [PolyAgent/mistral-7b-v0.3-ua-tokenizer-v2-focus-base](https://huggingface.co/PolyAgent/mistral-7b-v0.3-ua-tokenizer-v2-focus-base) on the
|
20 |
It achieves the following results on the evaluation set:
|
21 |
- Loss: 1.0765
|
22 |
|
|
|
1 |
---
|
2 |
base_model: PolyAgent/mistral-7b-v0.3-ua-tokenizer-v2-focus-base
|
3 |
tags:
|
4 |
+
- alignment-handbook
|
5 |
+
- trl
|
6 |
+
- sft
|
7 |
+
- generated_from_trainer
|
8 |
- trl
|
9 |
- sft
|
10 |
- generated_from_trainer
|
11 |
datasets:
|
12 |
+
- PolyAgent/wiki_uk_en_parallel
|
13 |
model-index:
|
14 |
- name: mistral-v0.3-tokV2-gentle-train
|
15 |
results: []
|
|
|
20 |
|
21 |
# mistral-v0.3-tokV2-gentle-train
|
22 |
|
23 |
+
This model is a fine-tuned version of [PolyAgent/mistral-7b-v0.3-ua-tokenizer-v2-focus-base](https://huggingface.co/PolyAgent/mistral-7b-v0.3-ua-tokenizer-v2-focus-base) on the PolyAgent/wiki_uk_en_parallel dataset.
|
24 |
It achieves the following results on the evaluation set:
|
25 |
- Loss: 1.0765
|
26 |
|
all_results.json
CHANGED
@@ -1,5 +1,10 @@
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
|
|
|
|
|
|
|
|
|
|
3 |
"total_flos": 1.06516665335808e+16,
|
4 |
"train_loss": 1.2970494811368156,
|
5 |
"train_runtime": 158321.4888,
|
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
+
"eval_loss": 1.0764902830123901,
|
4 |
+
"eval_runtime": 4.3265,
|
5 |
+
"eval_samples": 1780,
|
6 |
+
"eval_samples_per_second": 91.529,
|
7 |
+
"eval_steps_per_second": 3.005,
|
8 |
"total_flos": 1.06516665335808e+16,
|
9 |
"train_loss": 1.2970494811368156,
|
10 |
"train_runtime": 158321.4888,
|
config.json
CHANGED
@@ -22,6 +22,6 @@
|
|
22 |
"tie_word_embeddings": false,
|
23 |
"torch_dtype": "bfloat16",
|
24 |
"transformers_version": "4.44.0",
|
25 |
-
"use_cache":
|
26 |
"vocab_size": 32768
|
27 |
}
|
|
|
22 |
"tie_word_embeddings": false,
|
23 |
"torch_dtype": "bfloat16",
|
24 |
"transformers_version": "4.44.0",
|
25 |
+
"use_cache": true,
|
26 |
"vocab_size": 32768
|
27 |
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_loss": 1.0764902830123901,
|
4 |
+
"eval_runtime": 4.3265,
|
5 |
+
"eval_samples": 1780,
|
6 |
+
"eval_samples_per_second": 91.529,
|
7 |
+
"eval_steps_per_second": 3.005
|
8 |
+
}
|
runs/Sep18_16-01-16_ip-10-1-73-211/events.out.tfevents.1726835561.ip-10-1-73-211.186164.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15d5510f319d35d82aa2a326057efa40c48633f6638b97c1d057158b63d68705
|
3 |
+
size 364
|