added all checkpoint-224 files
Browse files- README.md +44 -6
- adapter_model.bin +2 -2
- optimizer.pt +3 -0
- pytorch_model.bin +2 -2
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- scheduler.pt +3 -0
- tokenizer.model +2 -2
- trainer_state.json +25 -0
- training_args.bin +2 -2
README.md
CHANGED
@@ -1,9 +1,47 @@
|
|
1 |
---
|
2 |
-
|
3 |
-
- autotrain
|
4 |
-
- text-generation
|
5 |
-
widget:
|
6 |
-
- text: "I love AutoTrain because "
|
7 |
---
|
|
|
8 |
|
9 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: False
|
17 |
+
- bnb_4bit_compute_dtype: float16
|
18 |
+
|
19 |
+
The following `bitsandbytes` quantization config was used during training:
|
20 |
+
- quant_method: bitsandbytes
|
21 |
+
- load_in_8bit: False
|
22 |
+
- load_in_4bit: True
|
23 |
+
- llm_int8_threshold: 6.0
|
24 |
+
- llm_int8_skip_modules: None
|
25 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
26 |
+
- llm_int8_has_fp16_weight: False
|
27 |
+
- bnb_4bit_quant_type: nf4
|
28 |
+
- bnb_4bit_use_double_quant: False
|
29 |
+
- bnb_4bit_compute_dtype: float16
|
30 |
+
|
31 |
+
The following `bitsandbytes` quantization config was used during training:
|
32 |
+
- quant_method: bitsandbytes
|
33 |
+
- load_in_8bit: False
|
34 |
+
- load_in_4bit: True
|
35 |
+
- llm_int8_threshold: 6.0
|
36 |
+
- llm_int8_skip_modules: None
|
37 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
38 |
+
- llm_int8_has_fp16_weight: False
|
39 |
+
- bnb_4bit_quant_type: nf4
|
40 |
+
- bnb_4bit_use_double_quant: False
|
41 |
+
- bnb_4bit_compute_dtype: float16
|
42 |
+
### Framework versions
|
43 |
+
|
44 |
+
- PEFT 0.6.0.dev0
|
45 |
+
- PEFT 0.6.0.dev0
|
46 |
+
|
47 |
+
- PEFT 0.6.0.dev0
|
adapter_model.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 sha256:52a88a362ba10cc7d3b298e821cc743fe665ccca08ff957fbeccc25227f0940d
|
3 |
+
size 133
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61371664eada1133ad98bc10a65280e06ff48022cf5bf2934a5e7c1d9ad735aa
|
3 |
+
size 133
|
pytorch_model.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:c716b504fedf976ce03a01d801288cc6a7bd0404492e2fff0b737a85c507d5dc
|
3 |
+
size 128
|
rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0fb04a401faf45e97e604ba74a7510e0d79bcfd4801fe755f7b0d9ba62131a60
|
3 |
+
size 130
|
rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27ba3cb7042fe6286f8632b9f39aaafec00aa72e829fe045873e20714e085624
|
3 |
+
size 130
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01497f3c511dcf1fd093d8883b2bc0f335f4988461683fa8bf67ceb800d43641
|
3 |
+
size 128
|
tokenizer.model
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 sha256:1a8f238a200be6c23fbba0f9a999ab4fe3c09ca303b29805e68cf6659bfb7d89
|
3 |
+
size 131
|
trainer_state.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.991111111111111,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 224,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.59,
|
13 |
+
"learning_rate": 4.477611940298508e-05,
|
14 |
+
"loss": 0.4999,
|
15 |
+
"step": 179
|
16 |
+
}
|
17 |
+
],
|
18 |
+
"logging_steps": 179,
|
19 |
+
"max_steps": 224,
|
20 |
+
"num_train_epochs": 2,
|
21 |
+
"save_steps": 500,
|
22 |
+
"total_flos": 1.4875603767813734e+17,
|
23 |
+
"trial_name": null,
|
24 |
+
"trial_params": null
|
25 |
+
}
|
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:d338051d006afbaa1215bd674029cc6dc0fc40ed753d82c46d1e983c044892cf
|
3 |
+
size 129
|