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/rng_state.pth +1 -1
- checkpoint-200/scheduler.pt +1 -1
- checkpoint-200/trainer_state.json +45 -45
- 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 sha256:1c915b534dd5c63af4a4da8b51c402aa67519f4f509b5abe822440b79d0dada7
|
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:e98623969976c0a14b109a3c67209e22c6ee22bd13f81248dbbc28c82287acfc
|
3 |
size 42724
|
checkpoint-200/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 sha256:24ca455dde448b70aa653e0498d3346b98980a6d89972d5d56f2b2ec8d9c7be4
|
3 |
size 14244
|
checkpoint-200/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:d191efbbc9b0763e805de64fb2ed1cd1a38712d135eda6d145caf5703e52c386
|
3 |
size 1064
|
checkpoint-200/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": 200,
|
7 |
"is_hyper_param_search": false,
|
@@ -9,77 +9,77 @@
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"epoch": 0.
|
13 |
-
"learning_rate":
|
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":
|
29 |
-
"eval_steps_per_second": 1.
|
30 |
"step": 50
|
31 |
},
|
32 |
{
|
33 |
-
"epoch":
|
34 |
-
"learning_rate":
|
35 |
-
"loss": 0.
|
36 |
"step": 100
|
37 |
},
|
38 |
{
|
39 |
-
"epoch":
|
40 |
-
"eval_accuracy": 0.
|
41 |
-
"eval_loss": 0.
|
42 |
-
"eval_runtime":
|
43 |
-
"eval_samples_per_second":
|
44 |
-
"eval_steps_per_second": 1.
|
45 |
"step": 100
|
46 |
},
|
47 |
{
|
48 |
-
"epoch":
|
49 |
-
"learning_rate":
|
50 |
-
"loss": 0.
|
51 |
"step": 150
|
52 |
},
|
53 |
{
|
54 |
-
"epoch":
|
55 |
-
"eval_accuracy": 0.
|
56 |
-
"eval_loss": 0.
|
57 |
-
"eval_runtime":
|
58 |
-
"eval_samples_per_second":
|
59 |
-
"eval_steps_per_second": 1.
|
60 |
"step": 150
|
61 |
},
|
62 |
{
|
63 |
-
"epoch":
|
64 |
-
"learning_rate":
|
65 |
-
"loss": 0.
|
66 |
"step": 200
|
67 |
},
|
68 |
{
|
69 |
-
"epoch":
|
70 |
-
"eval_accuracy": 0.
|
71 |
-
"eval_loss": 0.
|
72 |
-
"eval_runtime":
|
73 |
-
"eval_samples_per_second":
|
74 |
-
"eval_steps_per_second": 1.
|
75 |
"step": 200
|
76 |
}
|
77 |
],
|
78 |
"logging_steps": 50,
|
79 |
-
"max_steps":
|
80 |
-
"num_train_epochs":
|
81 |
"save_steps": 50,
|
82 |
-
"total_flos":
|
83 |
"trial_name": null,
|
84 |
"trial_params": null
|
85 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.5725014805793762,
|
3 |
+
"best_model_checkpoint": "output/checkpoint-100",
|
4 |
+
"epoch": 3.7735849056603774,
|
5 |
"eval_steps": 50,
|
6 |
"global_step": 200,
|
7 |
"is_hyper_param_search": false,
|
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.02,
|
13 |
+
"learning_rate": 1.234567901234568e-06,
|
14 |
+
"loss": 0.4437,
|
15 |
"step": 1
|
16 |
},
|
17 |
{
|
18 |
+
"epoch": 0.94,
|
19 |
+
"learning_rate": 5.679012345679012e-05,
|
20 |
+
"loss": 0.455,
|
21 |
"step": 50
|
22 |
},
|
23 |
{
|
24 |
+
"epoch": 0.94,
|
25 |
+
"eval_accuracy": 0.68,
|
26 |
+
"eval_loss": 0.6171127557754517,
|
27 |
+
"eval_runtime": 29.0494,
|
28 |
+
"eval_samples_per_second": 6.024,
|
29 |
+
"eval_steps_per_second": 1.515,
|
30 |
"step": 50
|
31 |
},
|
32 |
{
|
33 |
+
"epoch": 1.89,
|
34 |
+
"learning_rate": 9.59349593495935e-05,
|
35 |
+
"loss": 0.4555,
|
36 |
"step": 100
|
37 |
},
|
38 |
{
|
39 |
+
"epoch": 1.89,
|
40 |
+
"eval_accuracy": 0.7257142857142858,
|
41 |
+
"eval_loss": 0.5725014805793762,
|
42 |
+
"eval_runtime": 28.7986,
|
43 |
+
"eval_samples_per_second": 6.077,
|
44 |
+
"eval_steps_per_second": 1.528,
|
45 |
"step": 100
|
46 |
},
|
47 |
{
|
48 |
+
"epoch": 2.83,
|
49 |
+
"learning_rate": 8.265582655826559e-05,
|
50 |
+
"loss": 0.455,
|
51 |
"step": 150
|
52 |
},
|
53 |
{
|
54 |
+
"epoch": 2.83,
|
55 |
+
"eval_accuracy": 0.7371428571428571,
|
56 |
+
"eval_loss": 0.5729417204856873,
|
57 |
+
"eval_runtime": 28.9054,
|
58 |
+
"eval_samples_per_second": 6.054,
|
59 |
+
"eval_steps_per_second": 1.522,
|
60 |
"step": 150
|
61 |
},
|
62 |
{
|
63 |
+
"epoch": 3.77,
|
64 |
+
"learning_rate": 6.910569105691057e-05,
|
65 |
+
"loss": 0.4718,
|
66 |
"step": 200
|
67 |
},
|
68 |
{
|
69 |
+
"epoch": 3.77,
|
70 |
+
"eval_accuracy": 0.6685714285714286,
|
71 |
+
"eval_loss": 0.6322054862976074,
|
72 |
+
"eval_runtime": 28.8878,
|
73 |
+
"eval_samples_per_second": 6.058,
|
74 |
+
"eval_steps_per_second": 1.523,
|
75 |
"step": 200
|
76 |
}
|
77 |
],
|
78 |
"logging_steps": 50,
|
79 |
+
"max_steps": 450,
|
80 |
+
"num_train_epochs": 9,
|
81 |
"save_steps": 50,
|
82 |
+
"total_flos": 7.652955795308544e+16,
|
83 |
"trial_name": null,
|
84 |
"trial_params": null
|
85 |
}
|
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:d91c1e3ec7fc28d5ed2a9d783b7ded0a7affbbd029319e299d9244ac0f3fbc29
|
3 |
size 4472
|