Training in progress, step 1000
Browse files- config.json +41 -0
- pytorch_model.bin +3 -0
- runs/Dec26_06-51-57_5b87c6b9a61a/events.out.tfevents.1703573595.5b87c6b9a61a.5647.0 +3 -0
- runs/Dec26_07-05-51_5b87c6b9a61a/events.out.tfevents.1703574362.5b87c6b9a61a.9450.0 +3 -0
- runs/Dec26_07-19-02_5b87c6b9a61a/events.out.tfevents.1703575154.5b87c6b9a61a.13013.0 +3 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "gpt2",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"end_token_id": 50256,
|
| 11 |
+
"eos_token_id": 50256,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_ctx": 1024,
|
| 16 |
+
"n_embd": 768,
|
| 17 |
+
"n_head": 12,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 12,
|
| 20 |
+
"n_positions": 1024,
|
| 21 |
+
"pad_token_id": 50256,
|
| 22 |
+
"reorder_and_upcast_attn": false,
|
| 23 |
+
"resid_pdrop": 0.1,
|
| 24 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 25 |
+
"scale_attn_weights": true,
|
| 26 |
+
"summary_activation": null,
|
| 27 |
+
"summary_first_dropout": 0.1,
|
| 28 |
+
"summary_proj_to_labels": true,
|
| 29 |
+
"summary_type": "cls_index",
|
| 30 |
+
"summary_use_proj": true,
|
| 31 |
+
"task_specific_params": {
|
| 32 |
+
"text-generation": {
|
| 33 |
+
"do_sample": true,
|
| 34 |
+
"max_length": 50
|
| 35 |
+
}
|
| 36 |
+
},
|
| 37 |
+
"torch_dtype": "float16",
|
| 38 |
+
"transformers_version": "4.35.2",
|
| 39 |
+
"use_cache": false,
|
| 40 |
+
"vocab_size": 50257
|
| 41 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:718d8ca3fdfd4858fe6eeb01a71398fd0143050fc8c973236a490485bb682987
|
| 3 |
+
size 326120926
|
runs/Dec26_06-51-57_5b87c6b9a61a/events.out.tfevents.1703573595.5b87c6b9a61a.5647.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3530c07c1bd6f34ec3c9ba1eb986456469f7d51b2fbaff0444ac26e36de93865
|
| 3 |
+
size 4600
|
runs/Dec26_07-05-51_5b87c6b9a61a/events.out.tfevents.1703574362.5b87c6b9a61a.9450.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a683925c0747e959efd46f9e78273b9b011ca1c314d50890f350e950af155203
|
| 3 |
+
size 4600
|
runs/Dec26_07-19-02_5b87c6b9a61a/events.out.tfevents.1703575154.5b87c6b9a61a.13013.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:605b8ab5fa4f96fb50a07d8f532bf6e79c2d4d8abd1108f9d92d16fa2be72810
|
| 3 |
+
size 7734
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37a5ace03b829ecef955b511bfd6e7afa19d6ecd30bb144c83d1956b53dcabd8
|
| 3 |
+
size 5944
|