Training in progress, step 4, checkpoint
Browse files
last-checkpoint/README.md
CHANGED
@@ -4,30 +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
|
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: True
|
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
|
@@ -53,8 +29,6 @@ The following `bitsandbytes` quantization config was used during training:
|
|
53 |
- bnb_4bit_compute_dtype: float16
|
54 |
### Framework versions
|
55 |
|
56 |
-
- PEFT 0.5.0
|
57 |
-
- PEFT 0.5.0
|
58 |
- PEFT 0.5.0
|
59 |
|
60 |
- 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
|
|
|
29 |
- bnb_4bit_compute_dtype: float16
|
30 |
### Framework versions
|
31 |
|
|
|
|
|
32 |
- PEFT 0.5.0
|
33 |
|
34 |
- PEFT 0.5.0
|
last-checkpoint/adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 40137613
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b2afaa2d90767d6e6b3122609a0b28522b7c540e55fffa6cece521823863a13
|
3 |
size 40137613
|
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:ef41f8521e50bf504d99781460bd3460e64607713ee863c3a8562b76421fac45
|
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:fbc28aff6c1f0519ffb9cd7a501dc311b1aa599b81b95e0587dc2546c3ac6680
|
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 sha256:90f803b28408be4400865e7afc43e8d783a7dbb70d4236447fec88b54e3956a2
|
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 sha256:24d86c276b7647b8353d4643979580f8916c0427c3136aa6cb63bd500555f215
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 2,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -20,13 +20,26 @@
|
|
20 |
"eval_samples_per_second": 1.759,
|
21 |
"eval_steps_per_second": 0.227,
|
22 |
"step": 2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
}
|
24 |
],
|
25 |
"logging_steps": 2,
|
26 |
"max_steps": 240,
|
27 |
"num_train_epochs": 3,
|
28 |
"save_steps": 2,
|
29 |
-
"total_flos":
|
30 |
"trial_name": null,
|
31 |
"trial_params": null
|
32 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.05,
|
5 |
"eval_steps": 2,
|
6 |
+
"global_step": 4,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
20 |
"eval_samples_per_second": 1.759,
|
21 |
"eval_steps_per_second": 0.227,
|
22 |
"step": 2
|
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": 2,
|
39 |
"max_steps": 240,
|
40 |
"num_train_epochs": 3,
|
41 |
"save_steps": 2,
|
42 |
+
"total_flos": 664404328710144.0,
|
43 |
"trial_name": null,
|
44 |
"trial_params": null
|
45 |
}
|