Training in progress, epoch 2
Browse files- config.json +32 -0
- logs/events.out.tfevents.1709047189.4d66d5535d1e.513.0 +3 -0
- logs/events.out.tfevents.1709047991.4d66d5535d1e.513.1 +3 -0
- logs/events.out.tfevents.1709048289.4d66d5535d1e.513.2 +3 -0
- logs/events.out.tfevents.1709048588.4d66d5535d1e.7646.0 +3 -0
- logs/events.out.tfevents.1709049210.4d66d5535d1e.7646.1 +3 -0
- logs/events.out.tfevents.1709049417.4d66d5535d1e.11156.0 +3 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "duraad/nep-spell-hft",
|
3 |
+
"architectures": [
|
4 |
+
"MT5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 1024,
|
8 |
+
"d_kv": 64,
|
9 |
+
"d_model": 512,
|
10 |
+
"decoder_start_token_id": 0,
|
11 |
+
"dense_act_fn": "gelu_new",
|
12 |
+
"dropout_rate": 0.1,
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"feed_forward_proj": "gated-gelu",
|
15 |
+
"initializer_factor": 1.0,
|
16 |
+
"is_encoder_decoder": true,
|
17 |
+
"is_gated_act": true,
|
18 |
+
"layer_norm_epsilon": 1e-06,
|
19 |
+
"model_type": "mt5",
|
20 |
+
"num_decoder_layers": 8,
|
21 |
+
"num_heads": 6,
|
22 |
+
"num_layers": 8,
|
23 |
+
"pad_token_id": 0,
|
24 |
+
"relative_attention_max_distance": 128,
|
25 |
+
"relative_attention_num_buckets": 32,
|
26 |
+
"tie_word_embeddings": false,
|
27 |
+
"tokenizer_class": "T5Tokenizer",
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.38.1",
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 250112
|
32 |
+
}
|
logs/events.out.tfevents.1709047189.4d66d5535d1e.513.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c25e7ef0bbcbdcd6baac60069a8fe8db1b536f5273010c95de971e78d09cf200
|
3 |
+
size 11332
|
logs/events.out.tfevents.1709047991.4d66d5535d1e.513.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6df94e2472c2e8d8d0f79e142787155aa58404309857a2390983bc200276472d
|
3 |
+
size 7563
|
logs/events.out.tfevents.1709048289.4d66d5535d1e.513.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:952be77e1ad84e34e7079a2d58bcb494639ed2172bd5cd4c11c080e2acd1ef83
|
3 |
+
size 6197
|
logs/events.out.tfevents.1709048588.4d66d5535d1e.7646.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:623112435bfa4ac7f14062865f085973abdfd15fb9acffe96ac86ef78b86a408
|
3 |
+
size 6197
|
logs/events.out.tfevents.1709049210.4d66d5535d1e.7646.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bdd28dec2fd130a28434feb2a0faa7b37e96b3f77ccd37cad40f7e62b9f6fab2
|
3 |
+
size 5514
|
logs/events.out.tfevents.1709049417.4d66d5535d1e.11156.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ac15670938684fb44100e706784c5e16909d476c604e7e815fddea69751879e
|
3 |
+
size 6200
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd77c8001ea2a432a66497b22af5fc1ede6db3b1b0c2615c1605054c0da8d646
|
3 |
+
size 1200729512
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba9bad4740ff4e30310e531416f5fb15fea636261b27634df8e30bc5686ea408
|
3 |
+
size 5048
|