Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +32 -0
- logs/1673114248.2759893/events.out.tfevents.1673114248.2cb2cefa7ce2.7767.1 +3 -0
- logs/events.out.tfevents.1673114248.2cb2cefa7ce2.7767.0 +3 -0
- pytorch_model.bin +3 -0
- runs/1673116074.1444244/events.out.tfevents.1673116074.2cb2cefa7ce2.29966.1 +3 -0
- runs/events.out.tfevents.1673116074.2cb2cefa7ce2.29966.0 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/flan-t5-large",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 2816,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 1024,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dense_act_fn": "gelu_new",
|
11 |
+
"dropout_rate": 0.1,
|
12 |
+
"eos_token_id": 1,
|
13 |
+
"feed_forward_proj": "gated-gelu",
|
14 |
+
"initializer_factor": 1.0,
|
15 |
+
"is_encoder_decoder": true,
|
16 |
+
"is_gated_act": true,
|
17 |
+
"layer_norm_epsilon": 1e-06,
|
18 |
+
"model_type": "t5",
|
19 |
+
"n_positions": 512,
|
20 |
+
"num_decoder_layers": 24,
|
21 |
+
"num_heads": 16,
|
22 |
+
"num_layers": 24,
|
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 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.26.0.dev0",
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 32128
|
32 |
+
}
|
logs/1673114248.2759893/events.out.tfevents.1673114248.2cb2cefa7ce2.7767.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b289b5026cfdd48b3a879246e4a031f09177653727a990c6d39b8292f7884502
|
3 |
+
size 5999
|
logs/events.out.tfevents.1673114248.2cb2cefa7ce2.7767.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9398a79f183553592bc4b0b305ac006d663d3cccff270b3a6ff4d200884d920
|
3 |
+
size 4606
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca55a22bd790f598637e428e4a403a4f22994b7d7cabd9b98851de0915c6905f
|
3 |
+
size 3132793669
|
runs/1673116074.1444244/events.out.tfevents.1673116074.2cb2cefa7ce2.29966.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ae0c8f4d2c74f7eca761f1acfcb159dc055662278177d8e8bf33160a1b749a3
|
3 |
+
size 5999
|
runs/events.out.tfevents.1673116074.2cb2cefa7ce2.29966.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ff346319e4896256aa85210e1fc40ed24a649a2ac60a1a404ec1ad0552af500
|
3 |
+
size 19763
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3370fd34cd2df4db4677f82a63f89948e4d97f6cf8a5d38ddda2da4f5292e5c8
|
3 |
+
size 3707
|