Training in progress, step 150
Browse files- .gitignore +1 -0
- config.json +4 -4
- pytorch_model.bin +2 -2
- runs/Jul24_08-29-25_60ef8fe7a8e1/events.out.tfevents.1690188612.60ef8fe7a8e1.175.0 +3 -0
- runs/Jul24_08-51-02_60ef8fe7a8e1/events.out.tfevents.1690188674.60ef8fe7a8e1.175.1 +3 -0
- runs/Jul24_08-51-41_60ef8fe7a8e1/events.out.tfevents.1690188708.60ef8fe7a8e1.175.2 +3 -0
- training_args.bin +2 -2
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "/
|
| 3 |
"activation_function": "gelu_fast",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadCustomModel"
|
|
@@ -7,8 +7,8 @@
|
|
| 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,
|
|
@@ -32,6 +32,6 @@
|
|
| 32 |
"summary_use_proj": true,
|
| 33 |
"torch_dtype": "float32",
|
| 34 |
"transformers_version": "4.30.2",
|
| 35 |
-
"use_cache":
|
| 36 |
"vocab_size": 49280
|
| 37 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "bigcode/santacoder",
|
| 3 |
"activation_function": "gelu_fast",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadCustomModel"
|
|
|
|
| 7 |
"attention_head_type": "multiquery",
|
| 8 |
"attn_pdrop": 0.1,
|
| 9 |
"auto_map": {
|
| 10 |
+
"AutoConfig": "bigcode/santacoder--configuration_gpt2_mq.GPT2CustomConfig",
|
| 11 |
+
"AutoModelForCausalLM": "bigcode/santacoder--modeling_gpt2_mq.GPT2LMHeadCustomModel"
|
| 12 |
},
|
| 13 |
"bos_token_id": 49152,
|
| 14 |
"embd_pdrop": 0.1,
|
|
|
|
| 32 |
"summary_use_proj": true,
|
| 33 |
"torch_dtype": "float32",
|
| 34 |
"transformers_version": "4.30.2",
|
| 35 |
+
"use_cache": false,
|
| 36 |
"vocab_size": 49280
|
| 37 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb2043eedc9c0a6de7a406d8e83bc2fc59be54ffaa7b8698a6e5a8233091e616
|
| 3 |
+
size 4600336581
|
runs/Jul24_08-29-25_60ef8fe7a8e1/events.out.tfevents.1690188612.60ef8fe7a8e1.175.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c986742e3a7845c0f49932f02eb2e2f94e29ff7c6c904ab85d1407e180544b50
|
| 3 |
+
size 4419
|
runs/Jul24_08-51-02_60ef8fe7a8e1/events.out.tfevents.1690188674.60ef8fe7a8e1.175.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86c572abfbfd6b0f397365e79db131a8eb85c0ff9422c35df9cfc2fe8bbc24ea
|
| 3 |
+
size 4419
|
runs/Jul24_08-51-41_60ef8fe7a8e1/events.out.tfevents.1690188708.60ef8fe7a8e1.175.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bfb44f5cac1aa307091f4f828de7077666f1d2ed46439809d29b6163c95c1b58
|
| 3 |
+
size 5687
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96ecb0a88fcb86bf4ad8b7d3952294a7e772ab1f71b28699e47e223f6a02ca1c
|
| 3 |
+
size 3899
|