Training in progress, epoch 1
Browse files- adapter_config.json +38 -0
- adapter_model.safetensors +3 -0
- runs/Oct30_17-11-27_368ad1980789/events.out.tfevents.1761844367.368ad1980789.6156.0 +3 -0
- runs/Oct30_17-11-27_368ad1980789/events.out.tfevents.1761844483.368ad1980789.6156.1 +3 -0
- runs/Oct30_17-16-33_368ad1980789/events.out.tfevents.1761844600.368ad1980789.6156.2 +3 -0
- runs/Oct30_17-18-01_368ad1980789/events.out.tfevents.1761844686.368ad1980789.6156.3 +3 -0
- runs/Oct30_17-18-01_368ad1980789/events.out.tfevents.1761844784.368ad1980789.6156.4 +3 -0
- training_args.bin +1 -1
adapter_config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "deepseek-ai/DeepSeek-OCR",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 8,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"qalora_group_size": 16,
|
| 24 |
+
"r": 8,
|
| 25 |
+
"rank_pattern": {},
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"k_proj",
|
| 29 |
+
"v_proj",
|
| 30 |
+
"q_proj"
|
| 31 |
+
],
|
| 32 |
+
"target_parameters": null,
|
| 33 |
+
"task_type": "CAUSAL_LM",
|
| 34 |
+
"trainable_token_indices": null,
|
| 35 |
+
"use_dora": false,
|
| 36 |
+
"use_qalora": false,
|
| 37 |
+
"use_rslora": false
|
| 38 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e85737225bf441eb2c89f8db866f00db74e462b967bc87990f7ad123f5de8bfa
|
| 3 |
+
size 2958552
|
runs/Oct30_17-11-27_368ad1980789/events.out.tfevents.1761844367.368ad1980789.6156.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af056b189e2531dcdce9f4e637ba163bb396980e3e45a66dd2717d914d982f10
|
| 3 |
+
size 8627
|
runs/Oct30_17-11-27_368ad1980789/events.out.tfevents.1761844483.368ad1980789.6156.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75abd8a60ed094a5ea5fecffe03041ccc616c014d17d182340ad969e7d5e1dc0
|
| 3 |
+
size 8145
|
runs/Oct30_17-16-33_368ad1980789/events.out.tfevents.1761844600.368ad1980789.6156.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdabc56d70992c153c5b39d410d960b4f8d896d7f6216eaa885f0df72f0dbb25
|
| 3 |
+
size 8144
|
runs/Oct30_17-18-01_368ad1980789/events.out.tfevents.1761844686.368ad1980789.6156.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:520ef9eb1051f59bcb4f8fd7104d7f9b9ac2f7c304054d6e7c65b9195710270d
|
| 3 |
+
size 4184
|
runs/Oct30_17-18-01_368ad1980789/events.out.tfevents.1761844784.368ad1980789.6156.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b539fd900614d258eaf4aeb9adb15db390de41e94d53124b0853519571b9a1a
|
| 3 |
+
size 8114
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef879f1b8ed58799570e7334d766a84e2505fed0c5a419f72ae6951cc1b8074a
|
| 3 |
size 5304
|