Training in progress, step 25
Browse files- .gitignore +1 -0
- config.json +37 -0
- pytorch_model.bin +3 -0
- runs/May31_15-15-51_c676df968151/1685546218.2806802/events.out.tfevents.1685546218.c676df968151.6605.1 +3 -0
- runs/May31_15-15-51_c676df968151/events.out.tfevents.1685546218.c676df968151.6605.0 +3 -0
- runs/May31_15-37-32_c676df968151/1685547468.2634635/events.out.tfevents.1685547468.c676df968151.6605.3 +3 -0
- runs/May31_15-37-32_c676df968151/events.out.tfevents.1685547468.c676df968151.6605.2 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bigcode/santacoder",
|
| 3 |
+
"activation_function": "gelu_fast",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadCustomModel"
|
| 6 |
+
],
|
| 7 |
+
"attention_head_type": "multiquery",
|
| 8 |
+
"attn_pdrop": 0.1,
|
| 9 |
+
"auto_map": {
|
| 10 |
+
"AutoConfig": "configuration_gpt2_mq.GPT2CustomConfig",
|
| 11 |
+
"AutoModelForCausalLM": "modeling_gpt2_mq.GPT2LMHeadCustomModel"
|
| 12 |
+
},
|
| 13 |
+
"bos_token_id": 49152,
|
| 14 |
+
"embd_pdrop": 0.1,
|
| 15 |
+
"eos_token_id": 49152,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"layer_norm_epsilon": 1e-05,
|
| 18 |
+
"model_type": "gpt2",
|
| 19 |
+
"n_embd": 2048,
|
| 20 |
+
"n_head": 16,
|
| 21 |
+
"n_inner": 8192,
|
| 22 |
+
"n_layer": 24,
|
| 23 |
+
"n_positions": 2048,
|
| 24 |
+
"reorder_and_upcast_attn": false,
|
| 25 |
+
"resid_pdrop": 0.1,
|
| 26 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 27 |
+
"scale_attn_weights": true,
|
| 28 |
+
"summary_activation": null,
|
| 29 |
+
"summary_first_dropout": 0.1,
|
| 30 |
+
"summary_proj_to_labels": true,
|
| 31 |
+
"summary_type": "cls_index",
|
| 32 |
+
"summary_use_proj": true,
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.28.0",
|
| 35 |
+
"use_cache": false,
|
| 36 |
+
"vocab_size": 49280
|
| 37 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b563a1d04e5772868f088000bb0af714bec314c2550073a421992877bae9b419
|
| 3 |
+
size 4600336581
|
runs/May31_15-15-51_c676df968151/1685546218.2806802/events.out.tfevents.1685546218.c676df968151.6605.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68396bff766f960f9dbbd9e8c06a8df3c2e728b7a66273bb85693be80c3516f1
|
| 3 |
+
size 5898
|
runs/May31_15-15-51_c676df968151/events.out.tfevents.1685546218.c676df968151.6605.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b960e08b626e100796d1cd175f8c5ad450b82075b06d613ab6b3c0c15c96ff83
|
| 3 |
+
size 5289
|
runs/May31_15-37-32_c676df968151/1685547468.2634635/events.out.tfevents.1685547468.c676df968151.6605.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20118d64158197a9a5fc7a4ab16ee22ed5a05e14e3974cd4e87d01d2ff905a7f
|
| 3 |
+
size 5898
|
runs/May31_15-37-32_c676df968151/events.out.tfevents.1685547468.c676df968151.6605.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7715af37fcf799b547e23678e461eec3202cda1e4341f7c506271baad131210a
|
| 3 |
+
size 8476
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c3606663845b94ca14dda44116e63e07bfa3a1b4ced56a761c6741b0a53febd
|
| 3 |
+
size 3579
|