all files
Browse files- checkpoints +1 -0
- config.json +38 -0
- flax_model.msgpack +3 -0
- results_tensorboard/events.out.tfevents.1626335331.t1v-n-8cb15980-w-0.767371.3.v2 +3 -0
- results_tensorboard/events.out.tfevents.1626335616.t1v-n-8cb15980-w-0.768996.3.v2 +3 -0
- results_tensorboard/events.out.tfevents.1626338427.t1v-n-8cb15980-w-0.773256.3.v2 +3 -0
- results_tensorboard/events.out.tfevents.1626339960.t1v-n-8cb15980-w-0.776261.3.v2 +3 -0
checkpoints
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
Subproject commit 5373fdef12062d944319e0265e993f2cadce1392
|
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2ForMultipleChoice"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 50256,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 50256,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gpt2",
|
| 14 |
+
"n_ctx": 1024,
|
| 15 |
+
"n_embd": 1024,
|
| 16 |
+
"n_head": 16,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 24,
|
| 19 |
+
"n_positions": 1024,
|
| 20 |
+
"n_special": 0,
|
| 21 |
+
"predict_special_tokens": true,
|
| 22 |
+
"resid_pdrop": 0.1,
|
| 23 |
+
"scale_attn_weights": true,
|
| 24 |
+
"summary_activation": null,
|
| 25 |
+
"summary_first_dropout": 0.1,
|
| 26 |
+
"summary_proj_to_labels": true,
|
| 27 |
+
"summary_type": "cls_index",
|
| 28 |
+
"summary_use_proj": true,
|
| 29 |
+
"task_specific_params": {
|
| 30 |
+
"text-generation": {
|
| 31 |
+
"do_sample": true,
|
| 32 |
+
"max_length": 50
|
| 33 |
+
}
|
| 34 |
+
},
|
| 35 |
+
"transformers_version": "4.8.2",
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 50257
|
| 38 |
+
}
|
flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd2e92a7233e29a509eb154637ad78cef153ebf1065ed18cb43fa82960412b88
|
| 3 |
+
size 1419367919
|
results_tensorboard/events.out.tfevents.1626335331.t1v-n-8cb15980-w-0.767371.3.v2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7149f818695d44715930271eb8a1aa5738989e5ebb127eec505e28327cdbb7f
|
| 3 |
+
size 40
|
results_tensorboard/events.out.tfevents.1626335616.t1v-n-8cb15980-w-0.768996.3.v2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ce986add7a84b19092c947f288c7d0720b222f8c26ca838294923296d993f1a
|
| 3 |
+
size 125030
|
results_tensorboard/events.out.tfevents.1626338427.t1v-n-8cb15980-w-0.773256.3.v2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7dc6006f94c9517b1cfdc603014338e9f88ad83b66a48e18ca11c93a82f18ca1
|
| 3 |
+
size 75034
|
results_tensorboard/events.out.tfevents.1626339960.t1v-n-8cb15980-w-0.776261.3.v2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41c1b7e0e68e724a07aaf0411e98e5b668a9bb1ffc574be9154e20f54abd03e0
|
| 3 |
+
size 75034
|