End of training
Browse files
README.md
CHANGED
@@ -2,9 +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 |
model-index:
|
9 |
- name: tinyllama-sft-wizardlm_evol_instruct_v2-full
|
10 |
results: []
|
@@ -15,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# tinyllama-sft-wizardlm_evol_instruct_v2-full
|
17 |
|
18 |
-
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
|
19 |
It achieves the following results on the evaluation set:
|
20 |
- Loss: 0.7234
|
21 |
|
|
|
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 |
+
- ucla-cmllab/WizardLM_evol_instruct_V2_100k-chat-format
|
14 |
model-index:
|
15 |
- name: tinyllama-sft-wizardlm_evol_instruct_v2-full
|
16 |
results: []
|
|
|
21 |
|
22 |
# tinyllama-sft-wizardlm_evol_instruct_v2-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 ucla-cmllab/WizardLM_evol_instruct_V2_100k-chat-format dataset.
|
25 |
It achieves the following results on the evaluation set:
|
26 |
- Loss: 0.7234
|
27 |
|
all_results.json
CHANGED
@@ -1,5 +1,10 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
|
|
|
|
|
|
|
|
|
|
3 |
"train_loss": 0.7476945167619654,
|
4 |
"train_runtime": 7284.6392,
|
5 |
"train_samples": 99999,
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"eval_loss": 0.7233731150627136,
|
4 |
+
"eval_runtime": 629.5649,
|
5 |
+
"eval_samples": 43000,
|
6 |
+
"eval_samples_per_second": 68.301,
|
7 |
+
"eval_steps_per_second": 2.135,
|
8 |
"train_loss": 0.7476945167619654,
|
9 |
"train_runtime": 7284.6392,
|
10 |
"train_samples": 99999,
|
config.json
CHANGED
@@ -23,6 +23,6 @@
|
|
23 |
"tie_word_embeddings": false,
|
24 |
"torch_dtype": "bfloat16",
|
25 |
"transformers_version": "4.39.0.dev0",
|
26 |
-
"use_cache":
|
27 |
"vocab_size": 32000
|
28 |
}
|
|
|
23 |
"tie_word_embeddings": false,
|
24 |
"torch_dtype": "bfloat16",
|
25 |
"transformers_version": "4.39.0.dev0",
|
26 |
+
"use_cache": true,
|
27 |
"vocab_size": 32000
|
28 |
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_loss": 0.7233731150627136,
|
4 |
+
"eval_runtime": 629.5649,
|
5 |
+
"eval_samples": 43000,
|
6 |
+
"eval_samples_per_second": 68.301,
|
7 |
+
"eval_steps_per_second": 2.135
|
8 |
+
}
|
runs/Apr14_16-21-00_nova.cs.ucla.edu/events.out.tfevents.1713145314.nova.cs.ucla.edu.3519625.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f93f9e296c188952bbc6e07b367d6ec427e17f3ee25e1b922b586890941be9ec
|
3 |
+
size 359
|