Saving weights and logs of epoch 1
Browse files- config.json +35 -13
- flax_model.msgpack +2 -2
config.json
CHANGED
|
@@ -1,24 +1,45 @@
|
|
| 1 |
{
|
| 2 |
"activation_function": "gelu_new",
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
],
|
| 6 |
-
"attn_pdrop": 0.1,
|
| 7 |
"bos_token_id": 50256,
|
| 8 |
-
"
|
| 9 |
"eos_token_id": 50256,
|
| 10 |
"gradient_checkpointing": false,
|
|
|
|
| 11 |
"initializer_range": 0.02,
|
|
|
|
| 12 |
"layer_norm_epsilon": 1e-05,
|
| 13 |
-
"
|
| 14 |
-
"
|
| 15 |
-
"
|
| 16 |
-
"
|
| 17 |
-
"
|
| 18 |
-
"n_layer": 12,
|
| 19 |
-
"n_positions": 1024,
|
| 20 |
-
"resid_pdrop": 0.1,
|
| 21 |
-
"scale_attn_weights": true,
|
| 22 |
"summary_activation": null,
|
| 23 |
"summary_first_dropout": 0.1,
|
| 24 |
"summary_proj_to_labels": true,
|
|
@@ -26,5 +47,6 @@
|
|
| 26 |
"summary_use_proj": true,
|
| 27 |
"transformers_version": "4.9.0.dev0",
|
| 28 |
"use_cache": true,
|
| 29 |
-
"vocab_size": 50257
|
|
|
|
| 30 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"activation_function": "gelu_new",
|
| 3 |
"architectures": [
|
| 4 |
+
"GPTNeoForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0,
|
| 7 |
+
"attention_layers": [
|
| 8 |
+
"global",
|
| 9 |
+
"local",
|
| 10 |
+
"global",
|
| 11 |
+
"local",
|
| 12 |
+
"global",
|
| 13 |
+
"local",
|
| 14 |
+
"global",
|
| 15 |
+
"local",
|
| 16 |
+
"global",
|
| 17 |
+
"local",
|
| 18 |
+
"global",
|
| 19 |
+
"local"
|
| 20 |
+
],
|
| 21 |
+
"attention_types": [
|
| 22 |
+
[
|
| 23 |
+
[
|
| 24 |
+
"global",
|
| 25 |
+
"local"
|
| 26 |
+
],
|
| 27 |
+
6
|
| 28 |
+
]
|
| 29 |
],
|
|
|
|
| 30 |
"bos_token_id": 50256,
|
| 31 |
+
"embed_dropout": 0,
|
| 32 |
"eos_token_id": 50256,
|
| 33 |
"gradient_checkpointing": false,
|
| 34 |
+
"hidden_size": 768,
|
| 35 |
"initializer_range": 0.02,
|
| 36 |
+
"intermediate_size": null,
|
| 37 |
"layer_norm_epsilon": 1e-05,
|
| 38 |
+
"max_position_embeddings": 2048,
|
| 39 |
+
"model_type": "gpt_neo",
|
| 40 |
+
"num_heads": 12,
|
| 41 |
+
"num_layers": 12,
|
| 42 |
+
"resid_dropout": 0,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
"summary_activation": null,
|
| 44 |
"summary_first_dropout": 0.1,
|
| 45 |
"summary_proj_to_labels": true,
|
|
|
|
| 47 |
"summary_use_proj": true,
|
| 48 |
"transformers_version": "4.9.0.dev0",
|
| 49 |
"use_cache": true,
|
| 50 |
+
"vocab_size": 50257,
|
| 51 |
+
"window_size": 256
|
| 52 |
}
|
flax_model.msgpack
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:233aac18c03b6ab547d579ffd39d91420694e4ef557079492f46e7d029b7e645
|
| 3 |
+
size 500800120
|