Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +46 -0
- pytorch_model.bin +3 -0
- runs/Mar01_01-48-18_codespaces-c26992/1677635304.0596771/events.out.tfevents.1677635304.codespaces-c26992.28753.1 +3 -0
- runs/Mar01_01-48-18_codespaces-c26992/events.out.tfevents.1677635304.codespaces-c26992.28753.0 +3 -0
- runs/Mar01_01-50-43_codespaces-c26992/1677635446.3804421/events.out.tfevents.1677635446.codespaces-c26992.30161.1 +3 -0
- runs/Mar01_01-50-43_codespaces-c26992/events.out.tfevents.1677635446.codespaces-c26992.30161.0 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./models",
|
| 3 |
+
"_num_labels": 1,
|
| 4 |
+
"activation_function": "gelu_new",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"GPT2LMHeadModel"
|
| 7 |
+
],
|
| 8 |
+
"attn_pdrop": 0.1,
|
| 9 |
+
"bos_token_id": 50256,
|
| 10 |
+
"embd_pdrop": 0.1,
|
| 11 |
+
"eos_token_id": 50256,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "LABEL_0"
|
| 14 |
+
},
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"label2id": {
|
| 17 |
+
"LABEL_0": 0
|
| 18 |
+
},
|
| 19 |
+
"layer_norm_epsilon": 1e-05,
|
| 20 |
+
"model_type": "gpt2",
|
| 21 |
+
"n_ctx": 1024,
|
| 22 |
+
"n_embd": 768,
|
| 23 |
+
"n_head": 12,
|
| 24 |
+
"n_inner": null,
|
| 25 |
+
"n_layer": 6,
|
| 26 |
+
"n_positions": 1024,
|
| 27 |
+
"reorder_and_upcast_attn": false,
|
| 28 |
+
"resid_pdrop": 0.1,
|
| 29 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 30 |
+
"scale_attn_weights": true,
|
| 31 |
+
"summary_activation": null,
|
| 32 |
+
"summary_first_dropout": 0.1,
|
| 33 |
+
"summary_proj_to_labels": true,
|
| 34 |
+
"summary_type": "cls_index",
|
| 35 |
+
"summary_use_proj": true,
|
| 36 |
+
"task_specific_params": {
|
| 37 |
+
"text-generation": {
|
| 38 |
+
"do_sample": true,
|
| 39 |
+
"max_length": 50
|
| 40 |
+
}
|
| 41 |
+
},
|
| 42 |
+
"torch_dtype": "float32",
|
| 43 |
+
"transformers_version": "4.26.1",
|
| 44 |
+
"use_cache": true,
|
| 45 |
+
"vocab_size": 50257
|
| 46 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9b85231130ee159dd58c0bb5df9c6bb32059eb64484fb8ea8ad4d4afd18e1f6
|
| 3 |
+
size 333968953
|
runs/Mar01_01-48-18_codespaces-c26992/1677635304.0596771/events.out.tfevents.1677635304.codespaces-c26992.28753.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2b9d163bfb4d1d3d83c6d5c79f72687211501f271a0ba23caa86d3bda246411
|
| 3 |
+
size 5693
|
runs/Mar01_01-48-18_codespaces-c26992/events.out.tfevents.1677635304.codespaces-c26992.28753.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:689b2b75ef0bcfa086714e00458342ba69c05c5e5749aed562652dbe8d3e306d
|
| 3 |
+
size 4136
|
runs/Mar01_01-50-43_codespaces-c26992/1677635446.3804421/events.out.tfevents.1677635446.codespaces-c26992.30161.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31d6dc925b2e82810f31a0144eab00056516c48c0f3f62ceaa98a1ee1f6cf607
|
| 3 |
+
size 5693
|
runs/Mar01_01-50-43_codespaces-c26992/events.out.tfevents.1677635446.codespaces-c26992.30161.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a080309dc29294eb8e088e157a1355b630ef85adbd397f2da142856f39190a5
|
| 3 |
+
size 4363
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb4aecc2aa8dea8267d7791f7bd7df1e4d941a9ab8c362835ec8a66f882158c5
|
| 3 |
+
size 3515
|