Training in progress, step 1400, checkpoint
Browse files- checkpoint-1400/adapter_config.json +4 -4
- checkpoint-1400/adapter_model.bin +1 -1
- checkpoint-1400/adapter_model/adapter_model/README.md +21 -0
- checkpoint-1400/adapter_model/adapter_model/adapter_config.json +26 -0
- checkpoint-1400/adapter_model/adapter_model/adapter_model.bin +3 -0
- checkpoint-1400/optimizer.pt +1 -1
- checkpoint-1400/rng_state.pth +1 -1
- checkpoint-1400/trainer_state.json +0 -0
- checkpoint-1400/training_args.bin +2 -2
checkpoint-1400/adapter_config.json
CHANGED
|
@@ -14,12 +14,12 @@
|
|
| 14 |
"r": 64,
|
| 15 |
"revision": null,
|
| 16 |
"target_modules": [
|
| 17 |
-
"v_proj",
|
| 18 |
-
"gate_proj",
|
| 19 |
-
"k_proj",
|
| 20 |
"q_proj",
|
| 21 |
-
"o_proj",
|
| 22 |
"down_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
"up_proj"
|
| 24 |
],
|
| 25 |
"task_type": "CAUSAL_LM"
|
|
|
|
| 14 |
"r": 64,
|
| 15 |
"revision": null,
|
| 16 |
"target_modules": [
|
|
|
|
|
|
|
|
|
|
| 17 |
"q_proj",
|
|
|
|
| 18 |
"down_proj",
|
| 19 |
+
"k_proj",
|
| 20 |
+
"o_proj",
|
| 21 |
+
"v_proj",
|
| 22 |
+
"gate_proj",
|
| 23 |
"up_proj"
|
| 24 |
],
|
| 25 |
"task_type": "CAUSAL_LM"
|
checkpoint-1400/adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 335706314
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1cdeacf72565831bce356f851adef24361aaafed0f768b8967a2017ccd49abfa
|
| 3 |
size 335706314
|
checkpoint-1400/adapter_model/adapter_model/README.md
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
+
- quant_method: bitsandbytes
|
| 9 |
+
- load_in_8bit: False
|
| 10 |
+
- load_in_4bit: True
|
| 11 |
+
- llm_int8_threshold: 6.0
|
| 12 |
+
- llm_int8_skip_modules: None
|
| 13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 14 |
+
- llm_int8_has_fp16_weight: False
|
| 15 |
+
- bnb_4bit_quant_type: nf4
|
| 16 |
+
- bnb_4bit_use_double_quant: True
|
| 17 |
+
- bnb_4bit_compute_dtype: bfloat16
|
| 18 |
+
### Framework versions
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
- PEFT 0.4.0
|
checkpoint-1400/adapter_model/adapter_model/adapter_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "SkunkworksAI/Mistralic-7B-1",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 16.0,
|
| 11 |
+
"lora_dropout": 0.1,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 64,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"q_proj",
|
| 18 |
+
"down_proj",
|
| 19 |
+
"k_proj",
|
| 20 |
+
"o_proj",
|
| 21 |
+
"v_proj",
|
| 22 |
+
"gate_proj",
|
| 23 |
+
"up_proj"
|
| 24 |
+
],
|
| 25 |
+
"task_type": "CAUSAL_LM"
|
| 26 |
+
}
|
checkpoint-1400/adapter_model/adapter_model/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1cdeacf72565831bce356f851adef24361aaafed0f768b8967a2017ccd49abfa
|
| 3 |
+
size 335706314
|
checkpoint-1400/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1342453434
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aae21a655ed6e593d36c73ac73c9fd066566ec3fda07c50bd59109dbe5273bc2
|
| 3 |
size 1342453434
|
checkpoint-1400/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14180
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec38a6cacd5b4d8f01d4201c004be77bdfd8665445a97b9fdffb5bae5810d05b
|
| 3 |
size 14180
|
checkpoint-1400/trainer_state.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1400/training_args.bin
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:a0dc4baefe27a20ca1abfb0c14472e5a623dd5a74c948269b8755b83e2a3be94
|
| 3 |
+
size 6456
|