Training in progress, epoch 0, checkpoint
Browse files- checkpoint-2365920/config.json +24 -0
- checkpoint-2365920/optimizer.pt +3 -0
- checkpoint-2365920/pytorch_model.bin +3 -0
- checkpoint-2365920/rng_state.pth +3 -0
- checkpoint-2365920/scheduler.pt +3 -0
- checkpoint-2365920/special_tokens_map.json +5 -0
- checkpoint-2365920/tokenizer.json +0 -0
- checkpoint-2365920/tokenizer_config.json +12 -0
- checkpoint-2365920/trainer_state.json +0 -0
- checkpoint-2365920/training_args.bin +3 -0
checkpoint-2365920/config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"RNNForLanguageModeling"
|
4 |
+
],
|
5 |
+
"bidirectional": false,
|
6 |
+
"dropout_p": 0.1,
|
7 |
+
"emb_init_range": 0.1,
|
8 |
+
"embedding_dim": 1024,
|
9 |
+
"embedding_kwargs": {},
|
10 |
+
"hidden_dim": 1024,
|
11 |
+
"lin_init_range": 0.03125,
|
12 |
+
"lm_in_features": 1024,
|
13 |
+
"model_type": "rnn",
|
14 |
+
"num_layers": 2,
|
15 |
+
"output_last_state": false,
|
16 |
+
"output_recurrent_outputs": false,
|
17 |
+
"recur_init_range": 0.03125,
|
18 |
+
"rnn_kwargs": {},
|
19 |
+
"rnn_type": "LSTM",
|
20 |
+
"tie_weights": true,
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.33.3",
|
23 |
+
"vocab_size": 50002
|
24 |
+
}
|
checkpoint-2365920/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17a2a48c261199e8c8ac332558118b2c7cdf529db90be59b424e6c1c780102c1
|
3 |
+
size 544373707
|
checkpoint-2365920/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a7f6bea76e7e2a0b0737063a21ece3a6ab92e30f09c93b69a28e824eae9f3ba
|
3 |
+
size 272184705
|
checkpoint-2365920/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:788556a5142d24c504f6ca591432ee5897add27b3ab1f916b570af97a3c4d2e8
|
3 |
+
size 14511
|
checkpoint-2365920/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ace703931940494e0ae43b7ba210ee5ccb6d485950fbefdd2ba346cfd0632b9c
|
3 |
+
size 627
|
checkpoint-2365920/special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "<eos>",
|
3 |
+
"pad_token": "<pad>",
|
4 |
+
"unk_token": "<unk>"
|
5 |
+
}
|
checkpoint-2365920/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-2365920/tokenizer_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"eos_token": "<eos>",
|
4 |
+
"max_length": null,
|
5 |
+
"model_max_length": 512,
|
6 |
+
"pad_to_multiple_of": null,
|
7 |
+
"pad_token": "<pad>",
|
8 |
+
"pad_token_type_id": 0,
|
9 |
+
"padding_side": "right",
|
10 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
11 |
+
"unk_token": "<unk>"
|
12 |
+
}
|
checkpoint-2365920/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-2365920/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48285c03454cda5fcc3ceba82dc3a7698f624ee840cde30337521e9a5a30bcd6
|
3 |
+
size 4219
|