Model save
Browse files- README.md +7 -7
- all_results.json +7 -6
- config.json +2 -1
- generation_config.json +1 -1
- model-00001-of-00003.safetensors +1 -1
- model-00002-of-00003.safetensors +1 -1
- model-00003-of-00003.safetensors +1 -1
- tokenizer.json +1 -0
- tokenizer_config.json +2 -0
- train_results.json +7 -6
- trainer_state.json +0 -0
- training_args.bin +2 -2
README.md
CHANGED
@@ -35,14 +35,14 @@ More information needed
|
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
- learning_rate: 5e-07
|
38 |
-
- train_batch_size:
|
39 |
-
- eval_batch_size:
|
40 |
-
- seed:
|
41 |
- distributed_type: multi-GPU
|
42 |
- num_devices: 8
|
43 |
-
- gradient_accumulation_steps:
|
44 |
- total_train_batch_size: 128
|
45 |
-
- total_eval_batch_size:
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: cosine
|
48 |
- lr_scheduler_warmup_ratio: 0.1
|
@@ -54,7 +54,7 @@ The following hyperparameters were used during training:
|
|
54 |
|
55 |
### Framework versions
|
56 |
|
57 |
-
- Transformers 4.
|
58 |
- Pytorch 2.1.2+cu121
|
59 |
- Datasets 2.14.6
|
60 |
-
- Tokenizers 0.
|
|
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
- learning_rate: 5e-07
|
38 |
+
- train_batch_size: 1
|
39 |
+
- eval_batch_size: 1
|
40 |
+
- seed: 42
|
41 |
- distributed_type: multi-GPU
|
42 |
- num_devices: 8
|
43 |
+
- gradient_accumulation_steps: 16
|
44 |
- total_train_batch_size: 128
|
45 |
+
- total_eval_batch_size: 8
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: cosine
|
48 |
- lr_scheduler_warmup_ratio: 0.1
|
|
|
54 |
|
55 |
### Framework versions
|
56 |
|
57 |
+
- Transformers 4.41.1
|
58 |
- Pytorch 2.1.2+cu121
|
59 |
- Datasets 2.14.6
|
60 |
+
- Tokenizers 0.19.1
|
all_results.json
CHANGED
@@ -1,8 +1,9 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
"
|
7 |
-
"
|
|
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 0.9998009950248756,
|
3 |
+
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.014570614962192004,
|
5 |
+
"train_runtime": 64930.7281,
|
6 |
+
"train_samples": 160800,
|
7 |
+
"train_samples_per_second": 2.476,
|
8 |
+
"train_steps_per_second": 0.019
|
9 |
}
|
config.json
CHANGED
@@ -3,6 +3,7 @@
|
|
3 |
"architectures": [
|
4 |
"MistralForCausalLM"
|
5 |
],
|
|
|
6 |
"bos_token_id": 1,
|
7 |
"eos_token_id": 2,
|
8 |
"hidden_act": "silu",
|
@@ -19,7 +20,7 @@
|
|
19 |
"sliding_window": 4096,
|
20 |
"tie_word_embeddings": false,
|
21 |
"torch_dtype": "bfloat16",
|
22 |
-
"transformers_version": "4.
|
23 |
"use_cache": false,
|
24 |
"vocab_size": 32000
|
25 |
}
|
|
|
3 |
"architectures": [
|
4 |
"MistralForCausalLM"
|
5 |
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
"bos_token_id": 1,
|
8 |
"eos_token_id": 2,
|
9 |
"hidden_act": "silu",
|
|
|
20 |
"sliding_window": 4096,
|
21 |
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.41.1",
|
24 |
"use_cache": false,
|
25 |
"vocab_size": 32000
|
26 |
}
|
generation_config.json
CHANGED
@@ -2,5 +2,5 @@
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
-
"transformers_version": "4.
|
6 |
}
|
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.41.1"
|
6 |
}
|
model-00001-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4943162336
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0db91e71386822f409e6ab63788ace1a576450c0f487294f79d59f5c14a22e2
|
3 |
size 4943162336
|
model-00002-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999819336
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e52446e0acc443b4873312d3c40a4dc8431e8b2dcc3b1596c653510e86e7d557
|
3 |
size 4999819336
|
model-00003-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4540516344
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84d2ee9f2f29354cf39c25a5f1bd68aac05d810bf8d0da0a0e6a5f28da90f46b
|
3 |
size 4540516344
|
tokenizer.json
CHANGED
@@ -134,6 +134,7 @@
|
|
134 |
"end_of_word_suffix": null,
|
135 |
"fuse_unk": true,
|
136 |
"byte_fallback": true,
|
|
|
137 |
"vocab": {
|
138 |
"<unk>": 0,
|
139 |
"<s>": 1,
|
|
|
134 |
"end_of_word_suffix": null,
|
135 |
"fuse_unk": true,
|
136 |
"byte_fallback": true,
|
137 |
+
"ignore_merges": false,
|
138 |
"vocab": {
|
139 |
"<unk>": 0,
|
140 |
"<s>": 1,
|
tokenizer_config.json
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
{
|
|
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
"content": "<unk>",
|
|
|
1 |
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
train_results.json
CHANGED
@@ -1,8 +1,9 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
"
|
7 |
-
"
|
|
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 0.9998009950248756,
|
3 |
+
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.014570614962192004,
|
5 |
+
"train_runtime": 64930.7281,
|
6 |
+
"train_samples": 160800,
|
7 |
+
"train_samples_per_second": 2.476,
|
8 |
+
"train_steps_per_second": 0.019
|
9 |
}
|
trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83255af7dbd2cea8368e0e7405c859e40ac92e8bf2f57a4290284d554cd32666
|
3 |
+
size 6520
|