Training in progress, epoch 1
Browse files
adapter_config.json
CHANGED
@@ -16,14 +16,14 @@
|
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": null,
|
18 |
"peft_type": "LORA",
|
19 |
-
"r":
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
24 |
"q_proj",
|
25 |
"v_proj",
|
26 |
-
"
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM",
|
29 |
"use_dora": false,
|
|
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": null,
|
18 |
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"k_proj",
|
24 |
"q_proj",
|
25 |
"v_proj",
|
26 |
+
"o_proj"
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM",
|
29 |
"use_dora": false,
|
adapter_model.safetensors
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 sha256:2aa53ba6bb5035fa3064e687f881da4156914b19ea25457dd688d25a2817b306
|
3 |
+
size 7391688
|
runs/Aug05_03-07-07_cmle-training-7460638318143501570/events.out.tfevents.1722827228.cmle-training-7460638318143501570
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:616b1aa5f82e58504f06682c2b078e6424606543528d0b9dc5ede77f689b76a8
|
3 |
+
size 51900
|
special_tokens_map.json
CHANGED
@@ -17,7 +17,13 @@
|
|
17 |
"rstrip": false,
|
18 |
"single_word": false
|
19 |
},
|
20 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
"unk_token": {
|
22 |
"content": "<unk>",
|
23 |
"lstrip": false,
|
|
|
17 |
"rstrip": false,
|
18 |
"single_word": false
|
19 |
},
|
20 |
+
"pad_token": {
|
21 |
+
"content": "<pad>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
},
|
27 |
"unk_token": {
|
28 |
"content": "<unk>",
|
29 |
"lstrip": false,
|
tokenizer.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 17518777
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a8888a50eb9fb2ad5620bce29ee509bb98a708b0a9ef16f50fbbd05343291da
|
3 |
size 17518777
|
tokenizer_config.json
CHANGED
@@ -1747,7 +1747,7 @@
|
|
1747 |
"clean_up_tokenization_spaces": false,
|
1748 |
"eos_token": "<eos>",
|
1749 |
"model_max_length": 1000000000000000019884624838656,
|
1750 |
-
"pad_token": "<
|
1751 |
"sp_model_kwargs": {},
|
1752 |
"spaces_between_special_tokens": false,
|
1753 |
"tokenizer_class": "GemmaTokenizer",
|
|
|
1747 |
"clean_up_tokenization_spaces": false,
|
1748 |
"eos_token": "<eos>",
|
1749 |
"model_max_length": 1000000000000000019884624838656,
|
1750 |
+
"pad_token": "<pad>",
|
1751 |
"sp_model_kwargs": {},
|
1752 |
"spaces_between_special_tokens": false,
|
1753 |
"tokenizer_class": "GemmaTokenizer",
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4795
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72de3545ad238858701ad82fb1e5861b6987d765b0bb0cbb6a22f8534344a3d5
|
3 |
size 4795
|