Training in progress, epoch 0, checkpoint
Browse files- checkpoint-2671200/config.json +24 -0
- checkpoint-2671200/optimizer.pt +3 -0
- checkpoint-2671200/pytorch_model.bin +3 -0
- checkpoint-2671200/rng_state.pth +3 -0
- checkpoint-2671200/scheduler.pt +3 -0
- checkpoint-2671200/special_tokens_map.json +5 -0
- checkpoint-2671200/tokenizer.json +0 -0
- checkpoint-2671200/tokenizer_config.json +12 -0
- checkpoint-2671200/trainer_state.json +0 -0
- checkpoint-2671200/training_args.bin +3 -0
checkpoint-2671200/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-2671200/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bb29760fd6333b4915b5f3e3c844bdeda27d0db452ce391c37c724dedfe775f
|
3 |
+
size 544373707
|
checkpoint-2671200/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae88aa72fd7385de27a174b6edccf24bea5f95e18bebdf0b2c2f3f8105866bb9
|
3 |
+
size 272184705
|
checkpoint-2671200/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:066605e248b3d9569328c1f3adfc8bf4dd9eed2b4e3ec41edab6361b1b28d9c4
|
3 |
+
size 14511
|
checkpoint-2671200/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2672947c065420b4f20d76eb1b96e5a205a9c4b226faadedabf8fe7b446efb47
|
3 |
+
size 627
|
checkpoint-2671200/special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "<eos>",
|
3 |
+
"pad_token": "<pad>",
|
4 |
+
"unk_token": "<unk>"
|
5 |
+
}
|
checkpoint-2671200/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-2671200/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-2671200/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-2671200/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9cf28e2e1309d8e1ddf54adb1f745a40e5c73d47b8868178947dad280da042d9
|
3 |
+
size 4219
|