Training in progress, epoch 1
Browse files- .gitattributes +1 -0
- config.json +3 -2
- model-00001-of-00004.safetensors +1 -1
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
- model-00004-of-00004.safetensors +1 -1
- runs/Sep29_23-50-33_COE-CS-sv003/events.out.tfevents.1727654307.COE-CS-sv003.1266748.0 +3 -0
- runs/Sep30_00-59-37_COE-CS-sv003/events.out.tfevents.1727658063.COE-CS-sv003.1275764.0 +3 -0
- tokenizer.json +0 -0
- training_args.bin +2 -2
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
CHANGED
@@ -17,12 +17,13 @@
|
|
17 |
"num_hidden_layers": 32,
|
18 |
"num_key_value_heads": 32,
|
19 |
"rms_norm_eps": 1e-06,
|
|
|
20 |
"rope_theta": 1000000.0,
|
21 |
"sliding_window": null,
|
22 |
"tie_word_embeddings": false,
|
23 |
"torch_dtype": "bfloat16",
|
24 |
-
"transformers_version": "4.
|
25 |
-
"use_cache":
|
26 |
"use_sliding_window": false,
|
27 |
"vocab_size": 151936
|
28 |
}
|
|
|
17 |
"num_hidden_layers": 32,
|
18 |
"num_key_value_heads": 32,
|
19 |
"rms_norm_eps": 1e-06,
|
20 |
+
"rope_scaling": null,
|
21 |
"rope_theta": 1000000.0,
|
22 |
"sliding_window": null,
|
23 |
"tie_word_embeddings": false,
|
24 |
"torch_dtype": "bfloat16",
|
25 |
+
"transformers_version": "4.45.1",
|
26 |
+
"use_cache": false,
|
27 |
"use_sliding_window": false,
|
28 |
"vocab_size": 151936
|
29 |
}
|
model-00001-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4988482416
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f5117656d1e10ec5b0096d88163a4ec898fe4e66d721125504ace61fca9d52e
|
3 |
size 4988482416
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4981244328
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74ccebefed1c6c4c24059bdc9e54938248447f9dfeab921883b37c7cdf63760a
|
3 |
size 4981244328
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4228306968
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73a54bdb8da8a6192e9940acc9174ee51159b6eb6bd4cf93bc5e4d6bba2a562f
|
3 |
size 4228306968
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1244659840
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ecdefd99342301d3291a9c51947000d2f6c077e1cb5ea0a3ef6733c5347b83c6
|
3 |
size 1244659840
|
runs/Sep29_23-50-33_COE-CS-sv003/events.out.tfevents.1727654307.COE-CS-sv003.1266748.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d23b2c7c7ff610605643b41e2648f2e47b9ad0e2fe3806f3d71e42b466b2bf9
|
3 |
+
size 13447
|
runs/Sep30_00-59-37_COE-CS-sv003/events.out.tfevents.1727658063.COE-CS-sv003.1275764.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4173c61236c5a0006868d6dc382488d4d2c2f03e8ecac629407c2dc7183c9e94
|
3 |
+
size 76126
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
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:d24640b4ae07999e935fa66e86600da1ab202d92bf0ec0b8140f513646dc9f79
|
3 |
+
size 7096
|