Training in progress, step 100, checkpoint
Browse files
last-checkpoint/README.md
CHANGED
@@ -4,18 +4,6 @@ library_name: peft
|
|
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: float16
|
18 |
-
|
19 |
The following `bitsandbytes` quantization config was used during training:
|
20 |
- quant_method: bitsandbytes
|
21 |
- load_in_8bit: False
|
@@ -29,6 +17,5 @@ The following `bitsandbytes` quantization config was used during training:
|
|
29 |
- bnb_4bit_compute_dtype: float16
|
30 |
### Framework versions
|
31 |
|
32 |
-
- PEFT 0.5.0
|
33 |
|
34 |
- PEFT 0.5.0
|
|
|
4 |
## Training procedure
|
5 |
|
6 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
The following `bitsandbytes` quantization config was used during training:
|
8 |
- quant_method: bitsandbytes
|
9 |
- load_in_8bit: False
|
|
|
17 |
- bnb_4bit_compute_dtype: float16
|
18 |
### Framework versions
|
19 |
|
|
|
20 |
|
21 |
- PEFT 0.5.0
|
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 40036040
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42c44b90ff1a08964fc953e9f694b1575dd62637b20903ba06f2273289ac56a4
|
3 |
size 40036040
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 20523679
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:425d1bc0c0c8b750363a2739a2c79a82e0cd9c38c04ebfe97f799ad7b2dc00b6
|
3 |
size 20523679
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a059a19a2996dab3b6d4818dae12c8bf997be18ff1e9dfcbb8a7af4070b27755
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5f7790259e29eb5b24d667bdfc452be2dffd1fc55eea23973e34ba06c4748b9
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,45 +1,32 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
-
"eval_steps":
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"epoch": 0.
|
13 |
-
"learning_rate": 0.
|
14 |
-
"loss":
|
15 |
-
"step":
|
16 |
},
|
17 |
{
|
18 |
-
"epoch": 0.
|
19 |
-
"eval_runtime":
|
20 |
-
"eval_samples_per_second": 1.
|
21 |
-
"eval_steps_per_second": 0.
|
22 |
-
"step":
|
23 |
-
},
|
24 |
-
{
|
25 |
-
"epoch": 0.05,
|
26 |
-
"learning_rate": 0.001,
|
27 |
-
"loss": 1.5289,
|
28 |
-
"step": 4
|
29 |
-
},
|
30 |
-
{
|
31 |
-
"epoch": 0.05,
|
32 |
-
"eval_runtime": 128.0886,
|
33 |
-
"eval_samples_per_second": 1.757,
|
34 |
-
"eval_steps_per_second": 0.226,
|
35 |
-
"step": 4
|
36 |
}
|
37 |
],
|
38 |
-
"logging_steps":
|
39 |
-
"max_steps":
|
40 |
"num_train_epochs": 3,
|
41 |
-
"save_steps":
|
42 |
-
"total_flos":
|
43 |
"trial_name": null,
|
44 |
"trial_params": null
|
45 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.31347962382445144,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 100,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.31,
|
13 |
+
"learning_rate": 0.0002,
|
14 |
+
"loss": 0.7896,
|
15 |
+
"step": 100
|
16 |
},
|
17 |
{
|
18 |
+
"epoch": 0.31,
|
19 |
+
"eval_runtime": 511.2401,
|
20 |
+
"eval_samples_per_second": 1.76,
|
21 |
+
"eval_steps_per_second": 0.221,
|
22 |
+
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
}
|
24 |
],
|
25 |
+
"logging_steps": 100,
|
26 |
+
"max_steps": 957,
|
27 |
"num_train_epochs": 3,
|
28 |
+
"save_steps": 100,
|
29 |
+
"total_flos": 1.66101082177536e+16,
|
30 |
"trial_name": null,
|
31 |
"trial_params": null
|
32 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4027
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3c40a0e487f195e0bcdca0bd80b08de3505f73bfc6a8c9eb501acf966d1c6ad
|
3 |
size 4027
|