Training in progress, step 200, checkpoint
Browse files- checkpoint-200/README.md +0 -19
- checkpoint-200/adapter_model.bin +1 -1
- checkpoint-200/optimizer.pt +1 -1
- checkpoint-200/trainer_state.json +26 -26
- checkpoint-200/training_args.bin +1 -1
checkpoint-200/README.md
CHANGED
@@ -216,23 +216,4 @@ The following `bitsandbytes` quantization config was used during training:
|
|
216 |
### Framework versions
|
217 |
|
218 |
|
219 |
-
- PEFT 0.6.0.dev0
|
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.dev0
|
|
|
216 |
### Framework versions
|
217 |
|
218 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
219 |
- PEFT 0.6.0.dev0
|
checkpoint-200/adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9873829
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df156c15f1a54b7f026004fa1f67e111a709e0d6acd21d6cbbd98f69fcc78a18
|
3 |
size 9873829
|
checkpoint-200/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 42724
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:065f253474063fef6dd5b47f6acfebbdc3f9af82c35df048a6049d9f0cb110e4
|
3 |
size 42724
|
checkpoint-200/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "output/checkpoint-50",
|
4 |
"epoch": 0.16033670708487824,
|
5 |
"eval_steps": 50,
|
@@ -11,67 +11,67 @@
|
|
11 |
{
|
12 |
"epoch": 0.0,
|
13 |
"learning_rate": 4.444444444444445e-07,
|
14 |
-
"loss": 0.
|
15 |
"step": 1
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.04,
|
19 |
"learning_rate": 2e-05,
|
20 |
-
"loss": 0.
|
21 |
"step": 50
|
22 |
},
|
23 |
{
|
24 |
"epoch": 0.04,
|
25 |
-
"eval_accuracy": 0.
|
26 |
-
"eval_loss": 0.
|
27 |
-
"eval_runtime": 61.
|
28 |
-
"eval_samples_per_second": 5.
|
29 |
-
"eval_steps_per_second": 1.
|
30 |
"step": 50
|
31 |
},
|
32 |
{
|
33 |
"epoch": 0.08,
|
34 |
"learning_rate": 4.222222222222222e-05,
|
35 |
-
"loss": 0.
|
36 |
"step": 100
|
37 |
},
|
38 |
{
|
39 |
"epoch": 0.08,
|
40 |
-
"eval_accuracy": 0.
|
41 |
-
"eval_loss": 0.
|
42 |
-
"eval_runtime":
|
43 |
-
"eval_samples_per_second": 5.
|
44 |
-
"eval_steps_per_second": 1.
|
45 |
"step": 100
|
46 |
},
|
47 |
{
|
48 |
"epoch": 0.12,
|
49 |
"learning_rate": 6.444444444444446e-05,
|
50 |
-
"loss": 0.
|
51 |
"step": 150
|
52 |
},
|
53 |
{
|
54 |
"epoch": 0.12,
|
55 |
-
"eval_accuracy": 0.
|
56 |
-
"eval_loss": 0.
|
57 |
-
"eval_runtime":
|
58 |
-
"eval_samples_per_second": 5.
|
59 |
-
"eval_steps_per_second": 1.
|
60 |
"step": 150
|
61 |
},
|
62 |
{
|
63 |
"epoch": 0.16,
|
64 |
"learning_rate": 8.666666666666667e-05,
|
65 |
-
"loss": 0.
|
66 |
"step": 200
|
67 |
},
|
68 |
{
|
69 |
"epoch": 0.16,
|
70 |
-
"eval_accuracy": 0.
|
71 |
-
"eval_loss": 0.
|
72 |
-
"eval_runtime":
|
73 |
-
"eval_samples_per_second": 5.
|
74 |
-
"eval_steps_per_second": 1.
|
75 |
"step": 200
|
76 |
}
|
77 |
],
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.6430063247680664,
|
3 |
"best_model_checkpoint": "output/checkpoint-50",
|
4 |
"epoch": 0.16033670708487824,
|
5 |
"eval_steps": 50,
|
|
|
11 |
{
|
12 |
"epoch": 0.0,
|
13 |
"learning_rate": 4.444444444444445e-07,
|
14 |
+
"loss": 0.5542,
|
15 |
"step": 1
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.04,
|
19 |
"learning_rate": 2e-05,
|
20 |
+
"loss": 0.554,
|
21 |
"step": 50
|
22 |
},
|
23 |
{
|
24 |
"epoch": 0.04,
|
25 |
+
"eval_accuracy": 0.6626865671641791,
|
26 |
+
"eval_loss": 0.6430063247680664,
|
27 |
+
"eval_runtime": 61.7692,
|
28 |
+
"eval_samples_per_second": 5.423,
|
29 |
+
"eval_steps_per_second": 1.36,
|
30 |
"step": 50
|
31 |
},
|
32 |
{
|
33 |
"epoch": 0.08,
|
34 |
"learning_rate": 4.222222222222222e-05,
|
35 |
+
"loss": 0.5957,
|
36 |
"step": 100
|
37 |
},
|
38 |
{
|
39 |
"epoch": 0.08,
|
40 |
+
"eval_accuracy": 0.6686567164179105,
|
41 |
+
"eval_loss": 0.6705919504165649,
|
42 |
+
"eval_runtime": 60.4388,
|
43 |
+
"eval_samples_per_second": 5.543,
|
44 |
+
"eval_steps_per_second": 1.39,
|
45 |
"step": 100
|
46 |
},
|
47 |
{
|
48 |
"epoch": 0.12,
|
49 |
"learning_rate": 6.444444444444446e-05,
|
50 |
+
"loss": 0.5668,
|
51 |
"step": 150
|
52 |
},
|
53 |
{
|
54 |
"epoch": 0.12,
|
55 |
+
"eval_accuracy": 0.6805970149253732,
|
56 |
+
"eval_loss": 0.7224913835525513,
|
57 |
+
"eval_runtime": 56.4882,
|
58 |
+
"eval_samples_per_second": 5.93,
|
59 |
+
"eval_steps_per_second": 1.487,
|
60 |
"step": 150
|
61 |
},
|
62 |
{
|
63 |
"epoch": 0.16,
|
64 |
"learning_rate": 8.666666666666667e-05,
|
65 |
+
"loss": 0.5626,
|
66 |
"step": 200
|
67 |
},
|
68 |
{
|
69 |
"epoch": 0.16,
|
70 |
+
"eval_accuracy": 0.6746268656716418,
|
71 |
+
"eval_loss": 0.7115103006362915,
|
72 |
+
"eval_runtime": 56.506,
|
73 |
+
"eval_samples_per_second": 5.929,
|
74 |
+
"eval_steps_per_second": 1.487,
|
75 |
"step": 200
|
76 |
}
|
77 |
],
|
checkpoint-200/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4472
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87bd30bd4b21b4a0c66f1fd545858ef6e2d33b5984a8d292e79011acc3affd6b
|
3 |
size 4472
|