Training in progress, epoch 1
Browse files- config.json +7 -5
- model.safetensors +2 -2
- runs/Nov30_15-20-46_033002d4189d/events.out.tfevents.1701357724.033002d4189d.7143.0 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +6 -1
- tokenizer_config.json +1 -0
- training_args.bin +2 -2
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "gpt2",
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
@@ -12,11 +12,13 @@
|
|
| 12 |
"layer_norm_epsilon": 1e-05,
|
| 13 |
"model_type": "gpt2",
|
| 14 |
"n_ctx": 1024,
|
| 15 |
-
"n_embd":
|
| 16 |
-
"n_head":
|
| 17 |
"n_inner": null,
|
| 18 |
-
"n_layer":
|
| 19 |
"n_positions": 1024,
|
|
|
|
|
|
|
| 20 |
"reorder_and_upcast_attn": false,
|
| 21 |
"resid_pdrop": 0.1,
|
| 22 |
"scale_attn_by_inverse_layer_idx": false,
|
|
@@ -33,7 +35,7 @@
|
|
| 33 |
}
|
| 34 |
},
|
| 35 |
"torch_dtype": "float32",
|
| 36 |
-
"transformers_version": "4.
|
| 37 |
"use_cache": true,
|
| 38 |
"vocab_size": 50257
|
| 39 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "gpt2-medium",
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
|
|
| 12 |
"layer_norm_epsilon": 1e-05,
|
| 13 |
"model_type": "gpt2",
|
| 14 |
"n_ctx": 1024,
|
| 15 |
+
"n_embd": 1024,
|
| 16 |
+
"n_head": 16,
|
| 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,
|
|
|
|
| 35 |
}
|
| 36 |
},
|
| 37 |
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.35.2",
|
| 39 |
"use_cache": true,
|
| 40 |
"vocab_size": 50257
|
| 41 |
}
|
model.safetensors
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 sha256:18c4812ba40f32bc11af3303d686d62f682122607d3a68144a902fe91126f848
|
| 3 |
+
size 1419322880
|
runs/Nov30_15-20-46_033002d4189d/events.out.tfevents.1701357724.033002d4189d.7143.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8661cb13e7c90baddc1acfe110edfb74b8d286ad660ef8544fcf0d76d5098680
|
| 3 |
+
size 5171
|
special_tokens_map.json
CHANGED
|
@@ -1,5 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"bos_token": "<|endoftext|>",
|
| 3 |
"eos_token": "<|endoftext|>",
|
|
|
|
| 4 |
"unk_token": "<|endoftext|>"
|
| 5 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"bos_token": "<|endoftext|>",
|
| 3 |
"eos_token": "<|endoftext|>",
|
| 4 |
+
"pad_token": "<|endoftext|>",
|
| 5 |
"unk_token": "<|endoftext|>"
|
| 6 |
}
|
tokenizer.json
CHANGED
|
@@ -1,6 +1,11 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 128,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
"padding": null,
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
tokenizer_config.json
CHANGED
|
@@ -14,6 +14,7 @@
|
|
| 14 |
"clean_up_tokenization_spaces": true,
|
| 15 |
"eos_token": "<|endoftext|>",
|
| 16 |
"model_max_length": 1024,
|
|
|
|
| 17 |
"tokenizer_class": "GPT2Tokenizer",
|
| 18 |
"unk_token": "<|endoftext|>"
|
| 19 |
}
|
|
|
|
| 14 |
"clean_up_tokenization_spaces": true,
|
| 15 |
"eos_token": "<|endoftext|>",
|
| 16 |
"model_max_length": 1024,
|
| 17 |
+
"pad_token": "<|endoftext|>",
|
| 18 |
"tokenizer_class": "GPT2Tokenizer",
|
| 19 |
"unk_token": "<|endoftext|>"
|
| 20 |
}
|
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 sha256:54a6f21a057f6da84e4672ddd60089e2d71635545f4a305edb2f019253fd5bfb
|
| 3 |
+
size 4600
|