Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +37 -0
- pytorch_model.bin +3 -0
- runs/Feb11_19-55-17_2cb2cefa7ce2/1676145335.978225/events.out.tfevents.1676145335.2cb2cefa7ce2.20700.1 +3 -0
- runs/Feb11_19-55-17_2cb2cefa7ce2/events.out.tfevents.1676145335.2cb2cefa7ce2.20700.0 +3 -0
- runs/Feb12_11-20-39_2cb2cefa7ce2/1676200847.8718195/events.out.tfevents.1676200847.2cb2cefa7ce2.3602.1 +3 -0
- runs/Feb12_11-20-39_2cb2cefa7ce2/events.out.tfevents.1676200847.2cb2cefa7ce2.3602.0 +3 -0
- runs/Feb12_11-38-02_2cb2cefa7ce2/1676201890.291244/events.out.tfevents.1676201890.2cb2cefa7ce2.684.1 +3 -0
- runs/Feb12_11-38-02_2cb2cefa7ce2/events.out.tfevents.1676201890.2cb2cefa7ce2.684.0 +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": 50256,
|
14 |
+
"embd_pdrop": 0.1,
|
15 |
+
"eos_token_id": 50256,
|
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": "4.26.0.dev0",
|
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:ad9a9ca61f8e357a2dd93e136417cb2bf526ec31b1c68292a9a4af5d8e6f5024
|
3 |
+
size 4600336581
|
runs/Feb11_19-55-17_2cb2cefa7ce2/1676145335.978225/events.out.tfevents.1676145335.2cb2cefa7ce2.20700.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43d6c4537c7b36ad3be0d8ab74ddf3700378e63ee7bc999f8df08f4524794848
|
3 |
+
size 5745
|
runs/Feb11_19-55-17_2cb2cefa7ce2/events.out.tfevents.1676145335.2cb2cefa7ce2.20700.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6ee29b492b13e6b46a0772c31b04364fc8cd5ff856a431e88c737db07ac5a30
|
3 |
+
size 6723
|
runs/Feb12_11-20-39_2cb2cefa7ce2/1676200847.8718195/events.out.tfevents.1676200847.2cb2cefa7ce2.3602.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4980424bae3c575aa6d31dfeb08f3bc3b708cb85389275986d44bee28e680084
|
3 |
+
size 5745
|
runs/Feb12_11-20-39_2cb2cefa7ce2/events.out.tfevents.1676200847.2cb2cefa7ce2.3602.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:818654dda7bf744983a282dd44b8554106314fe6a25ea07d9de14f4396441c5c
|
3 |
+
size 5479
|
runs/Feb12_11-38-02_2cb2cefa7ce2/1676201890.291244/events.out.tfevents.1676201890.2cb2cefa7ce2.684.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef4452847408455c6cfedd85bd46f777267dc84ef8f0c5341d9661adb537c89c
|
3 |
+
size 5745
|
runs/Feb12_11-38-02_2cb2cefa7ce2/events.out.tfevents.1676201890.2cb2cefa7ce2.684.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3599c5ad059e9c9c5ae88ae7220fb05532c03354381e3d6b09feab8739955903
|
3 |
+
size 12332
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf05cb034bf7403075300fba2e7625b78b53e9e6b6fbdd0180eedfdc13eed28f
|
3 |
+
size 3515
|