Training in progress, epoch 1
Browse files
adapter_config.json
CHANGED
@@ -23,13 +23,13 @@
|
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
26 |
-
"o_proj",
|
27 |
"gate_proj",
|
28 |
-
"down_proj",
|
29 |
-
"v_proj",
|
30 |
"up_proj",
|
|
|
31 |
"q_proj",
|
32 |
-
"
|
|
|
|
|
33 |
],
|
34 |
"task_type": "CAUSAL_LM",
|
35 |
"use_dora": false,
|
|
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
|
|
26 |
"gate_proj",
|
|
|
|
|
27 |
"up_proj",
|
28 |
+
"down_proj",
|
29 |
"q_proj",
|
30 |
+
"o_proj",
|
31 |
+
"k_proj",
|
32 |
+
"v_proj"
|
33 |
],
|
34 |
"task_type": "CAUSAL_LM",
|
35 |
"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 2772497632
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf5deb378c9129bce6f7de7f25860c2cb5111c7d9e389a574de9a32d75b1109a
|
3 |
size 2772497632
|
runs/Jul25_08-15-17_merlin.doc.ic.ac.uk/events.out.tfevents.1721891729.merlin.doc.ic.ac.uk
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1582c97957b2cc09264ffc115b79b615f0e953fcfa56f80d9e16cd02a3b6fa91
|
3 |
+
size 22415
|
tokenizer_config.json
CHANGED
@@ -2053,15 +2053,11 @@
|
|
2053 |
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
2054 |
"clean_up_tokenization_spaces": true,
|
2055 |
"eos_token": "<|eot_id|>",
|
2056 |
-
"max_length": 2048,
|
2057 |
"model_input_names": [
|
2058 |
"input_ids",
|
2059 |
"attention_mask"
|
2060 |
],
|
2061 |
"model_max_length": 1000000000000000019884624838656,
|
2062 |
"pad_token": "<|eot_id|>",
|
2063 |
-
"
|
2064 |
-
"tokenizer_class": "PreTrainedTokenizerFast",
|
2065 |
-
"truncation_side": "right",
|
2066 |
-
"truncation_strategy": "longest_first"
|
2067 |
}
|
|
|
2053 |
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
2054 |
"clean_up_tokenization_spaces": true,
|
2055 |
"eos_token": "<|eot_id|>",
|
|
|
2056 |
"model_input_names": [
|
2057 |
"input_ids",
|
2058 |
"attention_mask"
|
2059 |
],
|
2060 |
"model_max_length": 1000000000000000019884624838656,
|
2061 |
"pad_token": "<|eot_id|>",
|
2062 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
|
|
|
|
|
|
2063 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f250493a7505a9f8d7921a54e8e00cc2259ea51a4a6595131855703ceb91dc71
|
3 |
size 5048
|