Training in progress, step 100, checkpoint
Browse files
checkpoint-100/README.md
CHANGED
@@ -216,4 +216,23 @@ The following `bitsandbytes` quantization config was used during training:
|
|
216 |
### Framework versions
|
217 |
|
218 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
219 |
- PEFT 0.6.0
|
|
|
216 |
### Framework versions
|
217 |
|
218 |
|
219 |
+
- PEFT 0.6.0
|
220 |
+
## Training procedure
|
221 |
+
|
222 |
+
|
223 |
+
The following `bitsandbytes` quantization config was used during training:
|
224 |
+
- quant_method: bitsandbytes
|
225 |
+
- load_in_8bit: True
|
226 |
+
- load_in_4bit: False
|
227 |
+
- llm_int8_threshold: 6.0
|
228 |
+
- llm_int8_skip_modules: None
|
229 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
230 |
+
- llm_int8_has_fp16_weight: False
|
231 |
+
- bnb_4bit_quant_type: fp4
|
232 |
+
- bnb_4bit_use_double_quant: False
|
233 |
+
- bnb_4bit_compute_dtype: float32
|
234 |
+
|
235 |
+
### Framework versions
|
236 |
+
|
237 |
+
|
238 |
- PEFT 0.6.0
|
checkpoint-100/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 19690328
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2eb363a446fa149adfc7c9aca75bcc5ce379730b5b5ba1d878597a9f0e8d3e92
|
3 |
size 19690328
|
checkpoint-100/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 38087098
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1598dec3400f2272a0ed47a9648c9a3e5acd2549e74b7ed2471a822be4047c6
|
3 |
size 38087098
|
checkpoint-100/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8bbf51506fa212fc757864e047ae3c0c97354cbeaa56f140c61cf650a5f9e14c
|
3 |
size 14244
|
checkpoint-100/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4063a0cc495afa91e64cf229d411e77693c266ce2a936765a23ed9a0d4a91687
|
3 |
size 1064
|
checkpoint-100/trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "output/checkpoint-
|
4 |
-
"epoch":
|
5 |
"eval_steps": 50,
|
6 |
"global_step": 100,
|
7 |
"is_hyper_param_search": false,
|
@@ -9,47 +9,47 @@
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"epoch": 0.
|
13 |
"learning_rate": 0.0,
|
14 |
-
"loss": 0.
|
15 |
"step": 1
|
16 |
},
|
17 |
{
|
18 |
-
"epoch": 0.
|
19 |
-
"learning_rate":
|
20 |
-
"loss": 0.
|
21 |
"step": 50
|
22 |
},
|
23 |
{
|
24 |
-
"epoch": 0.
|
25 |
-
"eval_accuracy": 0.
|
26 |
-
"eval_loss": 0.
|
27 |
-
"eval_runtime":
|
28 |
-
"eval_samples_per_second": 6.
|
29 |
-
"eval_steps_per_second": 1.
|
30 |
"step": 50
|
31 |
},
|
32 |
{
|
33 |
-
"epoch":
|
34 |
-
"learning_rate": 1.
|
35 |
-
"loss": 0.
|
36 |
"step": 100
|
37 |
},
|
38 |
{
|
39 |
-
"epoch":
|
40 |
-
"eval_accuracy": 0.
|
41 |
-
"eval_loss": 0.
|
42 |
-
"eval_runtime": 28.
|
43 |
-
"eval_samples_per_second": 6.
|
44 |
-
"eval_steps_per_second": 1.
|
45 |
"step": 100
|
46 |
}
|
47 |
],
|
48 |
"logging_steps": 50,
|
49 |
-
"max_steps":
|
50 |
"num_train_epochs": 3,
|
51 |
"save_steps": 50,
|
52 |
-
"total_flos": 3.
|
53 |
"trial_name": null,
|
54 |
"trial_params": null
|
55 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.4308854341506958,
|
3 |
+
"best_model_checkpoint": "output/checkpoint-100",
|
4 |
+
"epoch": 0.2707275803722504,
|
5 |
"eval_steps": 50,
|
6 |
"global_step": 100,
|
7 |
"is_hyper_param_search": false,
|
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.0,
|
13 |
"learning_rate": 0.0,
|
14 |
+
"loss": 0.9268,
|
15 |
"step": 1
|
16 |
},
|
17 |
{
|
18 |
+
"epoch": 0.14,
|
19 |
+
"learning_rate": 6.111111111111112e-06,
|
20 |
+
"loss": 0.5897,
|
21 |
"step": 50
|
22 |
},
|
23 |
{
|
24 |
+
"epoch": 0.14,
|
25 |
+
"eval_accuracy": 0.8628571428571429,
|
26 |
+
"eval_loss": 0.4395545721054077,
|
27 |
+
"eval_runtime": 26.2003,
|
28 |
+
"eval_samples_per_second": 6.679,
|
29 |
+
"eval_steps_per_second": 1.679,
|
30 |
"step": 50
|
31 |
},
|
32 |
{
|
33 |
+
"epoch": 0.27,
|
34 |
+
"learning_rate": 1.3055555555555557e-05,
|
35 |
+
"loss": 0.4516,
|
36 |
"step": 100
|
37 |
},
|
38 |
{
|
39 |
+
"epoch": 0.27,
|
40 |
+
"eval_accuracy": 0.8457142857142858,
|
41 |
+
"eval_loss": 0.4308854341506958,
|
42 |
+
"eval_runtime": 28.5089,
|
43 |
+
"eval_samples_per_second": 6.138,
|
44 |
+
"eval_steps_per_second": 1.543,
|
45 |
"step": 100
|
46 |
}
|
47 |
],
|
48 |
"logging_steps": 50,
|
49 |
+
"max_steps": 800,
|
50 |
"num_train_epochs": 3,
|
51 |
"save_steps": 50,
|
52 |
+
"total_flos": 3.702684434141184e+16,
|
53 |
"trial_name": null,
|
54 |
"trial_params": null
|
55 |
}
|
checkpoint-100/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4600
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eab90039203ebde7fc5537527df9e43bcc8971062162dee256a3fd06a20fcd44
|
3 |
size 4600
|