End of training
Browse files- README.md +9 -2
- all_results.json +5 -0
- config.json +27 -0
- eval_results.json +8 -0
README.md
CHANGED
@@ -2,11 +2,18 @@
|
|
2 |
license: apache-2.0
|
3 |
library_name: peft
|
4 |
tags:
|
|
|
|
|
|
|
|
|
5 |
- trl
|
6 |
- sft
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
-
-
|
|
|
|
|
|
|
10 |
base_model: unsloth/mistral-7b-v0.2
|
11 |
model-index:
|
12 |
- name: mistral-7b-v0.2-sft-mix-23rd-mar-v0
|
@@ -18,7 +25,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
# mistral-7b-v0.2-sft-mix-23rd-mar-v0
|
20 |
|
21 |
-
This model is a fine-tuned version of [unsloth/mistral-7b-v0.2](https://huggingface.co/unsloth/mistral-7b-v0.2) on the
|
22 |
It achieves the following results on the evaluation set:
|
23 |
- Loss: 0.9631
|
24 |
|
|
|
2 |
license: apache-2.0
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
+
- alignment-handbook
|
6 |
+
- trl
|
7 |
+
- sft
|
8 |
+
- generated_from_trainer
|
9 |
- trl
|
10 |
- sft
|
11 |
- generated_from_trainer
|
12 |
datasets:
|
13 |
+
- nthakur/deita-10k-v0-instruct
|
14 |
+
- nthakur/Bactrian-X-23-lang-instruct
|
15 |
+
- nthakur/GSM8KInstruct-Parallel-instruct
|
16 |
+
- nthakur/ultrachat-200k-instruct
|
17 |
base_model: unsloth/mistral-7b-v0.2
|
18 |
model-index:
|
19 |
- name: mistral-7b-v0.2-sft-mix-23rd-mar-v0
|
|
|
25 |
|
26 |
# mistral-7b-v0.2-sft-mix-23rd-mar-v0
|
27 |
|
28 |
+
This model is a fine-tuned version of [unsloth/mistral-7b-v0.2](https://huggingface.co/unsloth/mistral-7b-v0.2) on the nthakur/deita-10k-v0-instruct, the nthakur/Bactrian-X-23-lang-instruct, the nthakur/GSM8KInstruct-Parallel-instruct and the nthakur/ultrachat-200k-instruct datasets.
|
29 |
It achieves the following results on the evaluation set:
|
30 |
- Loss: 0.9631
|
31 |
|
all_results.json
CHANGED
@@ -1,5 +1,10 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
|
|
|
|
|
|
|
|
|
|
3 |
"train_loss": 0.9572911218241059,
|
4 |
"train_runtime": 140901.3648,
|
5 |
"train_samples": 915466,
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"eval_loss": 0.9631486535072327,
|
4 |
+
"eval_runtime": 5388.1939,
|
5 |
+
"eval_samples": 104366,
|
6 |
+
"eval_samples_per_second": 5.752,
|
7 |
+
"eval_steps_per_second": 0.12,
|
8 |
"train_loss": 0.9572911218241059,
|
9 |
"train_runtime": 140901.3648,
|
10 |
"train_samples": 915466,
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "unsloth/mistral-7b-v0.2",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"model_type": "mistral",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 32,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"rms_norm_eps": 1e-05,
|
20 |
+
"rope_theta": 1000000.0,
|
21 |
+
"sliding_window": 32768,
|
22 |
+
"tie_word_embeddings": false,
|
23 |
+
"torch_dtype": "bfloat16",
|
24 |
+
"transformers_version": "4.39.0.dev0",
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 32000
|
27 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_loss": 0.9631486535072327,
|
4 |
+
"eval_runtime": 5388.1939,
|
5 |
+
"eval_samples": 104366,
|
6 |
+
"eval_samples_per_second": 5.752,
|
7 |
+
"eval_steps_per_second": 0.12
|
8 |
+
}
|