new model version
Browse files- checkpoint +0 -3
- config.json +14 -2
- counter +0 -1
- encoder.json +0 -0
- merges.txt +1 -1
- pytorch_model.bin +2 -2
- tokenizer.json +0 -0
- tokenizer_config.json +10 -0
- trainer_state.json +22 -0
- vocab.bpe +0 -0
- vocab.json +0 -0
checkpoint
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
model_checkpoint_path: "model-1809"
|
2 |
-
all_model_checkpoint_paths: "model-1000"
|
3 |
-
all_model_checkpoint_paths: "model-1809"
|
|
|
|
|
|
|
|
config.json
CHANGED
@@ -1,5 +1,9 @@
|
|
1 |
{
|
|
|
2 |
"activation_function": "gelu_new",
|
|
|
|
|
|
|
3 |
"attn_pdrop": 0.1,
|
4 |
"bos_token_id": 50256,
|
5 |
"embd_pdrop": 0.1,
|
@@ -13,7 +17,8 @@
|
|
13 |
"n_inner": null,
|
14 |
"n_layer": 24,
|
15 |
"n_positions": 1024,
|
16 |
-
"
|
|
|
17 |
"reorder_and_upcast_attn": false,
|
18 |
"resid_pdrop": 0.1,
|
19 |
"scale_attn_by_inverse_layer_idx": false,
|
@@ -23,7 +28,14 @@
|
|
23 |
"summary_proj_to_labels": true,
|
24 |
"summary_type": "cls_index",
|
25 |
"summary_use_proj": true,
|
26 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
27 |
"use_cache": true,
|
28 |
"vocab_size": 50257
|
29 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "gpt2-medium",
|
3 |
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
"attn_pdrop": 0.1,
|
8 |
"bos_token_id": 50256,
|
9 |
"embd_pdrop": 0.1,
|
|
|
17 |
"n_inner": null,
|
18 |
"n_layer": 24,
|
19 |
"n_positions": 1024,
|
20 |
+
"n_special": 0,
|
21 |
+
"predict_special_tokens": true,
|
22 |
"reorder_and_upcast_attn": false,
|
23 |
"resid_pdrop": 0.1,
|
24 |
"scale_attn_by_inverse_layer_idx": false,
|
|
|
28 |
"summary_proj_to_labels": true,
|
29 |
"summary_type": "cls_index",
|
30 |
"summary_use_proj": true,
|
31 |
+
"task_specific_params": {
|
32 |
+
"text-generation": {
|
33 |
+
"do_sample": true,
|
34 |
+
"max_length": 50
|
35 |
+
}
|
36 |
+
},
|
37 |
+
"torch_dtype": "float32",
|
38 |
+
"transformers_version": "4.23.0.dev0",
|
39 |
"use_cache": true,
|
40 |
"vocab_size": 50257
|
41 |
}
|
counter
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
1809
|
|
|
|
encoder.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
merges.txt
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
-
#version: 0.2
|
2 |
Ġ t
|
3 |
Ġ a
|
4 |
h e
|
|
|
1 |
+
#version: 0.2 - Trained by `huggingface/tokenizers`
|
2 |
Ġ t
|
3 |
Ġ a
|
4 |
h e
|
pytorch_model.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 sha256:8b771e607deb7759c82cdf3518edc6159296409048d879a8577c28311631bcd9
|
3 |
+
size 1444566873
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"eos_token": "<|endoftext|>",
|
5 |
+
"model_max_length": 1024,
|
6 |
+
"name_or_path": "gpt2-medium",
|
7 |
+
"special_tokens_map_file": null,
|
8 |
+
"tokenizer_class": "GPT2Tokenizer",
|
9 |
+
"unk_token": "<|endoftext|>"
|
10 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.05319714863283328,
|
5 |
+
"global_step": 500,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.05,
|
12 |
+
"learning_rate": 4.9473348228534955e-05,
|
13 |
+
"loss": 2.8884,
|
14 |
+
"step": 500
|
15 |
+
}
|
16 |
+
],
|
17 |
+
"max_steps": 46995,
|
18 |
+
"num_train_epochs": 5,
|
19 |
+
"total_flos": 928700694528000.0,
|
20 |
+
"trial_name": null,
|
21 |
+
"trial_params": null
|
22 |
+
}
|
vocab.bpe
DELETED
The diff for this file is too large to render.
See raw diff
|
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|