Training in progress, epoch 1
Browse files- config.json +33 -0
- logs/events.out.tfevents.1735442561.94236d6c1ccc.70.0 +3 -0
- logs/events.out.tfevents.1735447998.94236d6c1ccc.116.0 +3 -0
- logs/events.out.tfevents.1735457063.94236d6c1ccc.165.0 +3 -0
- logs/events.out.tfevents.1735460485.94236d6c1ccc.208.0 +3 -0
- logs/events.out.tfevents.1735469381.94236d6c1ccc.256.0 +3 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bigscience/mt0-base",
|
3 |
+
"architectures": [
|
4 |
+
"MT5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 2048,
|
8 |
+
"d_kv": 64,
|
9 |
+
"d_model": 768,
|
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": 12,
|
21 |
+
"num_heads": 12,
|
22 |
+
"num_layers": 12,
|
23 |
+
"output_past": true,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"relative_attention_max_distance": 128,
|
26 |
+
"relative_attention_num_buckets": 32,
|
27 |
+
"tie_word_embeddings": false,
|
28 |
+
"tokenizer_class": "T5Tokenizer",
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.44.0",
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 250112
|
33 |
+
}
|
logs/events.out.tfevents.1735442561.94236d6c1ccc.70.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d746c45366cccbae1f1b443f917b3d5220d13fb90e4d1e8a78127bc45fae724
|
3 |
+
size 7098
|
logs/events.out.tfevents.1735447998.94236d6c1ccc.116.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df00cd4e3c68cb9f1fcaace4d955eeb521064c9e2bfe3662ccf8634d87c0b291
|
3 |
+
size 7304
|
logs/events.out.tfevents.1735457063.94236d6c1ccc.165.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:337eecc56cd5ee8c29cb0bab3c9a633fb1c641b87a6eefa179098c73fa29234a
|
3 |
+
size 6464
|
logs/events.out.tfevents.1735460485.94236d6c1ccc.208.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:089f003a9f4ec16f97ac269bd205069c1298a50f1e9d82f68bcda41584edc6ef
|
3 |
+
size 7093
|
logs/events.out.tfevents.1735469381.94236d6c1ccc.256.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:513736a7176322bce128295622325405b29bfd8d28691ab98b708a6b1921646a
|
3 |
+
size 5052
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:034d970c5338ed288a4c11bd00b26a27ffc5cb5a72e633817c0193aa9e1e46ba
|
3 |
+
size 2329638768
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4cc9bfe2444ca8fe13a298fadfc49fa1a667cf086045bf568c4cb6d316856d0e
|
3 |
+
size 5176
|