Training in progress, step 13
Browse files- adapter_config.json +45 -0
- adapter_model.safetensors +3 -0
- runs/Nov18_10-37-44_cd8df4468e73/events.out.tfevents.1763462269.cd8df4468e73.19.0 +3 -0
- special_tokens_map.json +27 -0
- tokenizer.json +0 -0
- tokenizer_config.json +0 -0
- training_args.bin +3 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": {
|
| 4 |
+
"base_model_class": "DeepseekOCRForCausalLM",
|
| 5 |
+
"parent_library": "transformers_modules.deepseek_ocr.modeling_deepseekocr",
|
| 6 |
+
"unsloth_fixed": true
|
| 7 |
+
},
|
| 8 |
+
"base_model_name_or_path": "./deepseek_ocr",
|
| 9 |
+
"bias": "none",
|
| 10 |
+
"corda_config": null,
|
| 11 |
+
"eva_config": null,
|
| 12 |
+
"exclude_modules": null,
|
| 13 |
+
"fan_in_fan_out": false,
|
| 14 |
+
"inference_mode": true,
|
| 15 |
+
"init_lora_weights": true,
|
| 16 |
+
"layer_replication": null,
|
| 17 |
+
"layers_pattern": null,
|
| 18 |
+
"layers_to_transform": null,
|
| 19 |
+
"loftq_config": {},
|
| 20 |
+
"lora_alpha": 16,
|
| 21 |
+
"lora_bias": false,
|
| 22 |
+
"lora_dropout": 0,
|
| 23 |
+
"megatron_config": null,
|
| 24 |
+
"megatron_core": "megatron.core",
|
| 25 |
+
"modules_to_save": null,
|
| 26 |
+
"peft_type": "LORA",
|
| 27 |
+
"qalora_group_size": 16,
|
| 28 |
+
"r": 16,
|
| 29 |
+
"rank_pattern": {},
|
| 30 |
+
"revision": null,
|
| 31 |
+
"target_modules": [
|
| 32 |
+
"down_proj",
|
| 33 |
+
"gate_proj",
|
| 34 |
+
"v_proj",
|
| 35 |
+
"q_proj",
|
| 36 |
+
"o_proj",
|
| 37 |
+
"k_proj",
|
| 38 |
+
"up_proj"
|
| 39 |
+
],
|
| 40 |
+
"task_type": "CAUSAL_LM",
|
| 41 |
+
"trainable_token_indices": null,
|
| 42 |
+
"use_dora": false,
|
| 43 |
+
"use_qalora": false,
|
| 44 |
+
"use_rslora": false
|
| 45 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ce748aac39bda514b703a298368c855e34224879b089333e273c029c20332bf
|
| 3 |
+
size 310662536
|
runs/Nov18_10-37-44_cd8df4468e73/events.out.tfevents.1763462269.cd8df4468e73.19.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebf13e4cb36549e22229ecbe8a8756e8ed2d3abf3d1dde73691ed1dd846d1096
|
| 3 |
+
size 10534
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|User|>",
|
| 4 |
+
"<|Assistant|>"
|
| 5 |
+
],
|
| 6 |
+
"bos_token": {
|
| 7 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
},
|
| 20 |
+
"pad_token": {
|
| 21 |
+
"content": "<｜▁pad▁｜>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false
|
| 26 |
+
}
|
| 27 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ee1cb4d909bfef0d7b79f9521d9ae3497031035e5a186d1adc177ed3509e23e
|
| 3 |
+
size 5304
|