Commit
•
83abd62
1
Parent(s):
21e3177
End of training
Browse files- README.md +6 -2
- all_results.json +5 -0
- config.json +1 -1
- eval_results.json +8 -0
- runs/May30_11-56-23_poseidon/events.out.tfevents.1717073543.poseidon.2010350.1 +3 -0
README.md
CHANGED
@@ -2,11 +2,15 @@
|
|
2 |
license: apache-2.0
|
3 |
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
|
4 |
tags:
|
|
|
|
|
|
|
|
|
5 |
- trl
|
6 |
- sft
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
-
-
|
10 |
model-index:
|
11 |
- name: tinyllama-1.1b-mt-sft-full
|
12 |
results: []
|
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
# tinyllama-1.1b-mt-sft-full
|
19 |
|
20 |
-
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the
|
21 |
It achieves the following results on the evaluation set:
|
22 |
- Loss: 1.6971
|
23 |
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
|
4 |
tags:
|
5 |
+
- alignment-handbook
|
6 |
+
- trl
|
7 |
+
- sft
|
8 |
+
- generated_from_trainer
|
9 |
- trl
|
10 |
- sft
|
11 |
- generated_from_trainer
|
12 |
datasets:
|
13 |
+
- haoranxu/ALMA-Human-Parallel
|
14 |
model-index:
|
15 |
- name: tinyllama-1.1b-mt-sft-full
|
16 |
results: []
|
|
|
21 |
|
22 |
# tinyllama-1.1b-mt-sft-full
|
23 |
|
24 |
+
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the haoranxu/ALMA-Human-Parallel dataset.
|
25 |
It achieves the following results on the evaluation set:
|
26 |
- Loss: 1.6971
|
27 |
|
all_results.json
CHANGED
@@ -1,5 +1,10 @@
|
|
1 |
{
|
2 |
"epoch": 1.9918809201623815,
|
|
|
|
|
|
|
|
|
|
|
3 |
"total_flos": 1.4968483831454106e+17,
|
4 |
"train_loss": 1.6339908747569374,
|
5 |
"train_runtime": 3216.6871,
|
|
|
1 |
{
|
2 |
"epoch": 1.9918809201623815,
|
3 |
+
"eval_loss": 1.697079062461853,
|
4 |
+
"eval_runtime": 28.4431,
|
5 |
+
"eval_samples": 8016,
|
6 |
+
"eval_samples_per_second": 15.294,
|
7 |
+
"eval_steps_per_second": 1.934,
|
8 |
"total_flos": 1.4968483831454106e+17,
|
9 |
"train_loss": 1.6339908747569374,
|
10 |
"train_runtime": 3216.6871,
|
config.json
CHANGED
@@ -24,6 +24,6 @@
|
|
24 |
"tie_word_embeddings": false,
|
25 |
"torch_dtype": "bfloat16",
|
26 |
"transformers_version": "4.41.1",
|
27 |
-
"use_cache":
|
28 |
"vocab_size": 32000
|
29 |
}
|
|
|
24 |
"tie_word_embeddings": false,
|
25 |
"torch_dtype": "bfloat16",
|
26 |
"transformers_version": "4.41.1",
|
27 |
+
"use_cache": true,
|
28 |
"vocab_size": 32000
|
29 |
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.9918809201623815,
|
3 |
+
"eval_loss": 1.697079062461853,
|
4 |
+
"eval_runtime": 28.4431,
|
5 |
+
"eval_samples": 8016,
|
6 |
+
"eval_samples_per_second": 15.294,
|
7 |
+
"eval_steps_per_second": 1.934
|
8 |
+
}
|
runs/May30_11-56-23_poseidon/events.out.tfevents.1717073543.poseidon.2010350.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e56ffeed19ad8870b4de28dc49dcb2b340cf79af3b91d73cc1d8396345cb7c2
|
3 |
+
size 359
|