Upload folder using huggingface_hub
Browse files- .ipynb_checkpoints/config-checkpoint.json +26 -0
- README.md +6 -6
- all_results.json +6 -6
- config.json +2 -2
- pytorch_model.bin +1 -1
- train_results.json +6 -6
- trainer_state.json +0 -0
- training_args.bin +1 -1
.ipynb_checkpoints/config-checkpoint.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./output3",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 256,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 512,
|
12 |
+
"max_position_embeddings": 8192,
|
13 |
+
"model_type": "llama",
|
14 |
+
"num_attention_heads": 4,
|
15 |
+
"num_hidden_layers": 2,
|
16 |
+
"num_key_value_heads": 4,
|
17 |
+
"pretraining_tp": 2,
|
18 |
+
"rms_norm_eps": 1e-05,
|
19 |
+
"rope_scaling": null,
|
20 |
+
"rope_theta": 10000.0,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.34.0.dev0",
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 32000
|
26 |
+
}
|
README.md
CHANGED
@@ -1,18 +1,18 @@
|
|
1 |
---
|
2 |
-
base_model: ./
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
model-index:
|
6 |
-
- name:
|
7 |
results: []
|
8 |
---
|
9 |
|
10 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
should probably proofread and complete it, then remove this comment. -->
|
12 |
|
13 |
-
#
|
14 |
|
15 |
-
This model is a fine-tuned version of [./
|
16 |
|
17 |
## Model description
|
18 |
|
@@ -35,8 +35,8 @@ The following hyperparameters were used during training:
|
|
35 |
- train_batch_size: 1
|
36 |
- eval_batch_size: 1
|
37 |
- seed: 42
|
38 |
-
- gradient_accumulation_steps:
|
39 |
-
- total_train_batch_size:
|
40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
- lr_scheduler_type: constant
|
42 |
- num_epochs: 5.0
|
|
|
1 |
---
|
2 |
+
base_model: ./output4
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
model-index:
|
6 |
+
- name: output4
|
7 |
results: []
|
8 |
---
|
9 |
|
10 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
should probably proofread and complete it, then remove this comment. -->
|
12 |
|
13 |
+
# output4
|
14 |
|
15 |
+
This model is a fine-tuned version of [./output4](https://huggingface.co/./output4) on an unknown dataset.
|
16 |
|
17 |
## Model description
|
18 |
|
|
|
35 |
- train_batch_size: 1
|
36 |
- eval_batch_size: 1
|
37 |
- seed: 42
|
38 |
+
- gradient_accumulation_steps: 128
|
39 |
+
- total_train_batch_size: 128
|
40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
- lr_scheduler_type: constant
|
42 |
- num_epochs: 5.0
|
all_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch": 4.
|
3 |
-
"train_loss":
|
4 |
-
"train_runtime":
|
5 |
-
"train_samples":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 4.72,
|
3 |
+
"train_loss": 4.668148568960336,
|
4 |
+
"train_runtime": 1730.4041,
|
5 |
+
"train_samples": 1763,
|
6 |
+
"train_samples_per_second": 5.094,
|
7 |
+
"train_steps_per_second": 0.038
|
8 |
}
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "./
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
@@ -14,7 +14,7 @@
|
|
14 |
"num_attention_heads": 4,
|
15 |
"num_hidden_layers": 2,
|
16 |
"num_key_value_heads": 4,
|
17 |
-
"pretraining_tp":
|
18 |
"rms_norm_eps": 1e-05,
|
19 |
"rope_scaling": null,
|
20 |
"rope_theta": 10000.0,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "./output4",
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
|
|
14 |
"num_attention_heads": 4,
|
15 |
"num_hidden_layers": 2,
|
16 |
"num_key_value_heads": 4,
|
17 |
+
"pretraining_tp": 2,
|
18 |
"rms_norm_eps": 1e-05,
|
19 |
"rope_scaling": null,
|
20 |
"rope_theta": 10000.0,
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 70790896
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2849613c32e353c618b1f18ae87d4b47413ee690ecec07623224d97180e03129
|
3 |
size 70790896
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch": 4.
|
3 |
-
"train_loss":
|
4 |
-
"train_runtime":
|
5 |
-
"train_samples":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 4.72,
|
3 |
+
"train_loss": 4.668148568960336,
|
4 |
+
"train_runtime": 1730.4041,
|
5 |
+
"train_samples": 1763,
|
6 |
+
"train_samples_per_second": 5.094,
|
7 |
+
"train_steps_per_second": 0.038
|
8 |
}
|
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 4027
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62ab075136e8e12e6d8a904f1b44613cd64ca0e659e605796d6ac5e0a391b8c5
|
3 |
size 4027
|