bytesizedllm commited on
Commit
a64f53d
·
verified ·
1 Parent(s): e7f4bd4

Training in progress, epoch 1

Browse files
adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": {
4
+ "base_model_class": "MT5ForConditionalGeneration",
5
+ "parent_library": "transformers.models.mt5.modeling_mt5"
6
+ },
7
+ "base_model_name_or_path": "google/mt5-xl",
8
+ "bias": "none",
9
+ "eva_config": null,
10
+ "exclude_modules": null,
11
+ "fan_in_fan_out": false,
12
+ "inference_mode": true,
13
+ "init_lora_weights": true,
14
+ "layer_replication": null,
15
+ "layers_pattern": null,
16
+ "layers_to_transform": null,
17
+ "loftq_config": {},
18
+ "lora_alpha": 32,
19
+ "lora_bias": false,
20
+ "lora_dropout": 0.1,
21
+ "megatron_config": null,
22
+ "megatron_core": "megatron.core",
23
+ "modules_to_save": null,
24
+ "peft_type": "LORA",
25
+ "r": 8,
26
+ "rank_pattern": {},
27
+ "revision": null,
28
+ "target_modules": [
29
+ "SelfAttention.v",
30
+ "EncDecAttention.v",
31
+ "SelfAttention.q",
32
+ "EncDecAttention.q"
33
+ ],
34
+ "task_type": null,
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a54b8e6ad1d83388112460401c885811f4db296ab1445e6416b5ecafffba777e
3
+ size 18915040
runs/Feb16_19-52-41_65f836cbedbc/events.out.tfevents.1739735564.65f836cbedbc.1113.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6597e50b5b19dcb0ebdfa02a75ab229d0cbe8051c98165374751368cbab9a343
3
+ size 4184
runs/Feb16_19-54-53_65f836cbedbc/events.out.tfevents.1739735695.65f836cbedbc.3912.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db3857cac25c6445eda2dbbe2ae8b2e3a891d549597ed18a8b779fa7bbd4b594
3
+ size 5815
runs/Feb16_19-59-11_65f836cbedbc/events.out.tfevents.1739735953.65f836cbedbc.5088.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ade2524cadb6ee514729b5afb11e95b750fa572dbcb910b57e92ec963320d187
3
+ size 5815
runs/Feb16_20-03-46_65f836cbedbc/events.out.tfevents.1739736227.65f836cbedbc.6448.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c09003cde92fe29a7cd00587988749b7d4581413d45b44d6032353de16aabebf
3
+ size 5815
runs/Feb16_20-08-39_65f836cbedbc/events.out.tfevents.1739736520.65f836cbedbc.7834.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71021e85b58f21b3a6dd7b625e0d8430f0ad26dbd26e790c97f18e53d2c90ca2
3
+ size 6659
runs/Feb16_20-45-20_65f836cbedbc/events.out.tfevents.1739738721.65f836cbedbc.17262.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19fbf5fc0fea7a2b18a79b65ebc0c877fa6bef3dce863cadac34bf3c4b46ed48
3
+ size 5815
runs/Feb16_20-48-38_65f836cbedbc/events.out.tfevents.1739738919.65f836cbedbc.18311.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf275fe073c3178669a68724ec34732ef86d4a26c54b2123c2570f119f77b5c4
3
+ size 7606
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<pad>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
tokenizer_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [],
30
+ "clean_up_tokenization_spaces": false,
31
+ "eos_token": "</s>",
32
+ "extra_ids": 0,
33
+ "legacy": true,
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": "<pad>",
36
+ "sp_model_kwargs": {},
37
+ "tokenizer_class": "T5Tokenizer",
38
+ "unk_token": "<unk>"
39
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f368f50c1633d2e7cdf2cd62dfffd2b6310ae1f9b8aab46fcb4309343febd67
3
+ size 5432