Upload folder using huggingface_hub
Browse files- README.md +15 -0
- adapter_config.json +22 -0
- adapter_model.bin +3 -0
- config.json +45 -0
- my_data.json +1 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +30 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
4 |
+
## Training procedure
|
5 |
+
|
6 |
+
|
7 |
+
The following `bitsandbytes` quantization config was used during training:
|
8 |
+
- load_in_8bit: True
|
9 |
+
- llm_int8_threshold: 6.0
|
10 |
+
- llm_int8_skip_modules: None
|
11 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
12 |
+
### Framework versions
|
13 |
+
|
14 |
+
|
15 |
+
- PEFT 0.5.0.dev0
|
adapter_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "/tmp/model",
|
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": 32,
|
11 |
+
"lora_dropout": 0.05,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 16,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"c_proj",
|
18 |
+
"c_attn",
|
19 |
+
"q_attn"
|
20 |
+
],
|
21 |
+
"task_type": "CAUSAL_LM"
|
22 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b228d055c781906585629b5ea0304641fd3323d035c7faada1eb6a03a2afdd88
|
3 |
+
size 142298829
|
config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/tmp/model",
|
3 |
+
"activation_function": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"GPTBigCodeForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_softmax_in_fp32": true,
|
8 |
+
"attn_pdrop": 0.1,
|
9 |
+
"bos_token_id": 0,
|
10 |
+
"embd_pdrop": 0.1,
|
11 |
+
"eos_token_id": 0,
|
12 |
+
"inference_runner": 0,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"layer_norm_epsilon": 1e-05,
|
15 |
+
"max_batch_size": null,
|
16 |
+
"max_sequence_length": null,
|
17 |
+
"model_type": "gpt_bigcode",
|
18 |
+
"multi_query": true,
|
19 |
+
"n_embd": 6144,
|
20 |
+
"n_head": 48,
|
21 |
+
"n_inner": 24576,
|
22 |
+
"n_layer": 40,
|
23 |
+
"n_positions": 8192,
|
24 |
+
"pad_key_length": true,
|
25 |
+
"pre_allocate_kv_cache": false,
|
26 |
+
"quantization_config": {
|
27 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
28 |
+
"llm_int8_skip_modules": null,
|
29 |
+
"llm_int8_threshold": 6.0,
|
30 |
+
"load_in_8bit": true
|
31 |
+
},
|
32 |
+
"resid_pdrop": 0.1,
|
33 |
+
"scale_attention_softmax_in_fp32": true,
|
34 |
+
"scale_attn_weights": true,
|
35 |
+
"summary_activation": null,
|
36 |
+
"summary_first_dropout": 0.1,
|
37 |
+
"summary_proj_to_labels": true,
|
38 |
+
"summary_type": "cls_index",
|
39 |
+
"summary_use_proj": true,
|
40 |
+
"torch_dtype": "float32",
|
41 |
+
"transformers_version": "4.28.1",
|
42 |
+
"use_cache": true,
|
43 |
+
"validate_runner_input": true,
|
44 |
+
"vocab_size": 49152
|
45 |
+
}
|
my_data.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"finetuned_from": "/tmp/model", "tasks": "language-modeling", "dataset": "/tmp", "tags": ["language-modeling", "nlp"]}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:839ea7dd2124f1301588025fbf29900eeec3e4be34c5f6dabe0c938c82b51f8c
|
3 |
+
size 284568453
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c152074a486243089e4fc0fdee0a373a30fb0e0a6e40eb5fd0d36fdafc97a155
|
3 |
+
size 443
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ca4c1d8dcf16ca8cef509702d9f0ff30851fb7b69e07d11c3004b20e16f9f7a
|
3 |
+
size 14575
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e01603029631eb6dca3506f525e23c61280dd09e656d56b627cb98b8334c78d
|
3 |
+
size 627
|
trainer_state.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.6104975938796997,
|
3 |
+
"best_model_checkpoint": "./outputdir/checkpoint-10",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"global_step": 10,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"learning_rate": 0.0,
|
13 |
+
"loss": 1.6036,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_loss": 1.6104975938796997,
|
19 |
+
"eval_runtime": 2007.0049,
|
20 |
+
"eval_samples_per_second": 1.466,
|
21 |
+
"eval_steps_per_second": 1.466,
|
22 |
+
"step": 10
|
23 |
+
}
|
24 |
+
],
|
25 |
+
"max_steps": 10,
|
26 |
+
"num_train_epochs": 9223372036854775807,
|
27 |
+
"total_flos": 2.988576972000461e+16,
|
28 |
+
"trial_name": null,
|
29 |
+
"trial_params": null
|
30 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2c79ae3b5552ec7081ff5bdc30db051c0d206d5916db498cd68787ee48c4f10
|
3 |
+
size 3643
|