Training in progress, epoch 6
Browse files- adapter_config.json +5 -5
- adapter_model.safetensors +3 -0
- runs/Oct24_09-55-52_7c629af4d1a6/events.out.tfevents.1729763757.7c629af4d1a6.1863.0 +3 -0
- runs/Oct24_10-17-51_7c629af4d1a6/events.out.tfevents.1729765073.7c629af4d1a6.1863.1 +3 -0
- tokenizer.json +6 -1
- tokenizer_config.json +6 -2
- training_args.bin +3 -0
adapter_config.json
CHANGED
@@ -4,7 +4,7 @@
|
|
4 |
"base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-instruct",
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
-
"inference_mode":
|
8 |
"init_lora_weights": true,
|
9 |
"layer_replication": null,
|
10 |
"layers_pattern": null,
|
@@ -23,13 +23,13 @@
|
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
26 |
-
"k_proj",
|
27 |
-
"q_proj",
|
28 |
-
"o_proj",
|
29 |
"v_proj",
|
|
|
30 |
"gate_proj",
|
31 |
"up_proj",
|
32 |
-
"
|
|
|
|
|
33 |
],
|
34 |
"task_type": "CAUSAL_LM",
|
35 |
"use_dora": false,
|
|
|
4 |
"base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-instruct",
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
"init_lora_weights": true,
|
9 |
"layer_replication": null,
|
10 |
"layers_pattern": null,
|
|
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
|
|
|
|
|
|
26 |
"v_proj",
|
27 |
+
"down_proj",
|
28 |
"gate_proj",
|
29 |
"up_proj",
|
30 |
+
"k_proj",
|
31 |
+
"o_proj",
|
32 |
+
"q_proj"
|
33 |
],
|
34 |
"task_type": "CAUSAL_LM",
|
35 |
"use_dora": false,
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9552a3e7671cff51c1610b1bfcde87412fd4db4f4b4f05e4f3cac44df5a3e6e3
|
3 |
+
size 2269178776
|
runs/Oct24_09-55-52_7c629af4d1a6/events.out.tfevents.1729763757.7c629af4d1a6.1863.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f13fdc3a0fa3d4bacbdfaadbaf52bae8ac86887feaca2e25275df331e7dee8a8
|
3 |
+
size 8221
|
runs/Oct24_10-17-51_7c629af4d1a6/events.out.tfevents.1729765073.7c629af4d1a6.1863.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d81e542a122f81baf384fa3111624dbd09d25301e9c055cc2c9739197ee94fa
|
3 |
+
size 7076
|
tokenizer.json
CHANGED
@@ -1,6 +1,11 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 3096,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
tokenizer_config.json
CHANGED
@@ -2050,14 +2050,18 @@
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
2053 |
-
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id
|
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 |
-
"
|
|
|
|
|
|
|
2063 |
}
|
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
2053 |
+
"chat_template": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are a financial expert in climate finance, particularly focusing on the Green Climate Fund (GCF) and water security initiatives. Answer questions accurately using the data from the Water Security guidelines.<|eot_id|>{% 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": 3096,
|
2057 |
"model_input_names": [
|
2058 |
"input_ids",
|
2059 |
"attention_mask"
|
2060 |
],
|
2061 |
"model_max_length": 1000000000000000019884624838656,
|
2062 |
"pad_token": "<|eot_id|>",
|
2063 |
+
"stride": 0,
|
2064 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
2065 |
+
"truncation_side": "right",
|
2066 |
+
"truncation_strategy": "longest_first"
|
2067 |
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54afb48a3e264c7d979db2df3f3e87d24358a01cc2ea7a2bd99b3e9d804df134
|
3 |
+
size 5496
|