Upload folder using huggingface_hub
Browse files- pilot-replication-exact/control_42/checkpoint_006000/metrics.json +0 -0
- pilot-replication-exact/control_42/checkpoint_006000/model.pt +3 -0
- pilot-replication-exact/control_42/checkpoint_006000/optimizer.pt +3 -0
- pilot-replication-exact/control_42/checkpoint_006000/random_states.pt +3 -0
- pilot-replication-exact/control_42/checkpoint_006000/tokenizer/merges.txt +0 -0
- pilot-replication-exact/control_42/checkpoint_006000/tokenizer/special_tokens_map.json +6 -0
- pilot-replication-exact/control_42/checkpoint_006000/tokenizer/tokenizer.json +0 -0
- pilot-replication-exact/control_42/checkpoint_006000/tokenizer/tokenizer_config.json +21 -0
- pilot-replication-exact/control_42/checkpoint_006000/tokenizer/vocab.json +0 -0
- pilot-replication-exact/control_42/checkpoint_006000/training_state.json +5 -0
pilot-replication-exact/control_42/checkpoint_006000/metrics.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pilot-replication-exact/control_42/checkpoint_006000/model.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df92a6cf45a87a59ff378a02221e0ad307f62ff4977638d0bf4efa062f07e70f
|
| 3 |
+
size 70500767
|
pilot-replication-exact/control_42/checkpoint_006000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25086de3e83e8120e0f0182b6955fe13e8f071622689226339718cd5c98f0365
|
| 3 |
+
size 141053195
|
pilot-replication-exact/control_42/checkpoint_006000/random_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fcf63926d4a5c894d7214f2fd7c3e7216521c4af7024cbc19d6034b2355ad30
|
| 3 |
+
size 13655
|
pilot-replication-exact/control_42/checkpoint_006000/tokenizer/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pilot-replication-exact/control_42/checkpoint_006000/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-exact/control_42/checkpoint_006000/tokenizer/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pilot-replication-exact/control_42/checkpoint_006000/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-exact/control_42/checkpoint_006000/tokenizer/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pilot-replication-exact/control_42/checkpoint_006000/training_state.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"global_batch": 6000,
|
| 3 |
+
"effective_batch": 6000,
|
| 4 |
+
"miniepoch_num": 6
|
| 5 |
+
}
|