Upload folder using huggingface_hub
Browse files- pilot-replication-v3/conlinear_84/checkpoint_014000/metrics.json +0 -0
- pilot-replication-v3/conlinear_84/checkpoint_014000/model.pt +3 -0
- pilot-replication-v3/conlinear_84/checkpoint_014000/optimizer.pt +3 -0
- pilot-replication-v3/conlinear_84/checkpoint_014000/random_states.pt +3 -0
- pilot-replication-v3/conlinear_84/checkpoint_014000/tokenizer/merges.txt +0 -0
- pilot-replication-v3/conlinear_84/checkpoint_014000/tokenizer/special_tokens_map.json +6 -0
- pilot-replication-v3/conlinear_84/checkpoint_014000/tokenizer/tokenizer.json +0 -0
- pilot-replication-v3/conlinear_84/checkpoint_014000/tokenizer/tokenizer_config.json +21 -0
- pilot-replication-v3/conlinear_84/checkpoint_014000/tokenizer/vocab.json +0 -0
- pilot-replication-v3/conlinear_84/checkpoint_014000/training_state.json +5 -0
pilot-replication-v3/conlinear_84/checkpoint_014000/metrics.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pilot-replication-v3/conlinear_84/checkpoint_014000/model.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d15b4b3d7ddda6c2084d587238c2f2ba4c420ebef6052b58bb33537bc05c998
|
| 3 |
+
size 126994575
|
pilot-replication-v3/conlinear_84/checkpoint_014000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:514aecd3c0d6b7a19a472c7c63eb47be9c91b1098ea82519056727aa94b0e6d2
|
| 3 |
+
size 254071534
|
pilot-replication-v3/conlinear_84/checkpoint_014000/random_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f8dc0be50e452d6b594e74d1e2dd584657d4faf9682b3957b1ead2d8a9967c1
|
| 3 |
+
size 13591
|
pilot-replication-v3/conlinear_84/checkpoint_014000/tokenizer/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pilot-replication-v3/conlinear_84/checkpoint_014000/tokenizer/special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"pad_token": "<|endoftext|>",
|
| 5 |
+
"unk_token": "<|endoftext|>"
|
| 6 |
+
}
|
pilot-replication-v3/conlinear_84/checkpoint_014000/tokenizer/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pilot-replication-v3/conlinear_84/checkpoint_014000/tokenizer/tokenizer_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"50256": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
}
|
| 12 |
+
},
|
| 13 |
+
"bos_token": "<|endoftext|>",
|
| 14 |
+
"clean_up_tokenization_spaces": false,
|
| 15 |
+
"eos_token": "<|endoftext|>",
|
| 16 |
+
"extra_special_tokens": {},
|
| 17 |
+
"model_max_length": 1024,
|
| 18 |
+
"pad_token": "<|endoftext|>",
|
| 19 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 20 |
+
"unk_token": "<|endoftext|>"
|
| 21 |
+
}
|
pilot-replication-v3/conlinear_84/checkpoint_014000/tokenizer/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pilot-replication-v3/conlinear_84/checkpoint_014000/training_state.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"global_batch": 14000,
|
| 3 |
+
"effective_batch": 14000,
|
| 4 |
+
"miniepoch_num": 14
|
| 5 |
+
}
|