Upload 9 files
Browse files- .gitattributes +1 -0
- nanoBERT/Untitled.ipynb +6 -0
- nanoBERT/config.json +26 -0
- nanoBERT/optimizer.ptrom +3 -0
- nanoBERT/pytorch_model.bin +3 -0
- nanoBERT/rng_state.pth +3 -0
- nanoBERT/scaler.ptrom +0 -0
- nanoBERT/scheduler.ptrom +0 -0
- nanoBERT/trainer_state.json +58 -0
- nanoBERT/training_args.bin +3 -0
.gitattributes
CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
+
nanoBERT/optimizer.ptrom filter=lfs diff=lfs merge=lfs -text
|
nanoBERT/Untitled.ipynb
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cells": [],
|
3 |
+
"metadata": {},
|
4 |
+
"nbformat": 4,
|
5 |
+
"nbformat_minor": 5
|
6 |
+
}
|
nanoBERT/config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"RobertaForMaskedLM"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"bos_token_id": 0,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 156,
|
16 |
+
"model_type": "roberta",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 1,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.24.0",
|
23 |
+
"type_vocab_size": 1,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 26
|
26 |
+
}
|
nanoBERT/optimizer.ptrom
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb969b1ab3ff914645cddeb934b97f0cf688befd1ffe5f3b64bcc408dc7fc65c
|
3 |
+
size 686428357
|
nanoBERT/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc2599ebbaaa6646f7643f2fb1df0baa317fc6e971b3d09a9947a39bdbae1d9f
|
3 |
+
size 343225593
|
nanoBERT/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:480c67de8b9bfeb4dbd3007480909db7f5578bbed902b6f324de023e2a3a64a6
|
3 |
+
size 16619
|
nanoBERT/scaler.ptrom
ADDED
Binary file (557 Bytes). View file
|
|
nanoBERT/scheduler.ptrom
ADDED
Binary file (627 Bytes). View file
|
|
nanoBERT/trainer_state.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"global_step": 90537,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"learning_rate": 8.568437488910182e-05,
|
13 |
+
"loss": 0.6812,
|
14 |
+
"step": 30179
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_loss": 0.4761524796485901,
|
19 |
+
"eval_runtime": 466.6948,
|
20 |
+
"eval_samples_per_second": 2327.907,
|
21 |
+
"eval_steps_per_second": 8.085,
|
22 |
+
"step": 30179
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 2.0,
|
26 |
+
"learning_rate": 6.427552432662622e-05,
|
27 |
+
"loss": 0.4541,
|
28 |
+
"step": 60358
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 2.0,
|
32 |
+
"eval_loss": 0.40283310413360596,
|
33 |
+
"eval_runtime": 444.5085,
|
34 |
+
"eval_samples_per_second": 2444.097,
|
35 |
+
"eval_steps_per_second": 8.488,
|
36 |
+
"step": 60358
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 3.0,
|
40 |
+
"learning_rate": 4.286667376415061e-05,
|
41 |
+
"loss": 0.4044,
|
42 |
+
"step": 90537
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 3.0,
|
46 |
+
"eval_loss": 0.3708195686340332,
|
47 |
+
"eval_runtime": 459.9775,
|
48 |
+
"eval_samples_per_second": 2361.902,
|
49 |
+
"eval_steps_per_second": 8.203,
|
50 |
+
"step": 90537
|
51 |
+
}
|
52 |
+
],
|
53 |
+
"max_steps": 150895,
|
54 |
+
"num_train_epochs": 5,
|
55 |
+
"total_flos": 2.0634769474023252e+18,
|
56 |
+
"trial_name": null,
|
57 |
+
"trial_params": null
|
58 |
+
}
|
nanoBERT/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e69821d24dedad6b1cd05be1cd3782f50d047d831f39f22e2f1f9fdd15ccab17
|
3 |
+
size 3387
|