Training in progress, epoch 1
Browse files- .ipynb_checkpoints/adapter_config-checkpoint.json +34 -0
- adapter_config.json +5 -5
- adapter_model.safetensors +1 -1
- runs/Jun13_11-46-58_snapiq0/events.out.tfevents.1718272052.snapiq0.92597.0 +3 -0
- runs/Jun13_15-10-54_snapiq0/events.out.tfevents.1718284461.snapiq0.99591.0 +3 -0
- training_args.bin +1 -1
.ipynb_checkpoints/adapter_config-checkpoint.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
|
| 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,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 128,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 256,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"o_proj",
|
| 24 |
+
"up_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"v_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"k_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
adapter_config.json
CHANGED
|
@@ -20,13 +20,13 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
-
"o_proj",
|
| 24 |
-
"up_proj",
|
| 25 |
"down_proj",
|
| 26 |
-
"gate_proj",
|
| 27 |
"v_proj",
|
| 28 |
-
"
|
| 29 |
-
"
|
|
|
|
|
|
|
|
|
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
|
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
|
|
|
|
|
|
| 23 |
"down_proj",
|
|
|
|
| 24 |
"v_proj",
|
| 25 |
+
"k_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"up_proj",
|
| 28 |
+
"o_proj",
|
| 29 |
+
"q_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"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 1879143336
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a50e90194a0dd26de77c496947788dd4091d0ab788244d2521fa1919b39a8946
|
| 3 |
size 1879143336
|
runs/Jun13_11-46-58_snapiq0/events.out.tfevents.1718272052.snapiq0.92597.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af4449f6aad98c5e48e6b0691c3942a6fe9901141fca2299f422e5d403a784fd
|
| 3 |
+
size 5329
|
runs/Jun13_15-10-54_snapiq0/events.out.tfevents.1718284461.snapiq0.99591.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:330328b8f8e61c788a54817c20ff8f76e295fd3b1d574b3aaa5f4a5060e7bdaf
|
| 3 |
+
size 7192
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5112
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:172515c3b8b704f15bffbba4c204d43bd5cb771e6bfd39964347ea23071bdb0b
|
| 3 |
size 5112
|