pavitemple
commited on
Commit
•
fc1cde3
1
Parent(s):
62ae9f7
Training in progress, epoch 0
Browse files- all_results.json +6 -6
- model.safetensors +1 -1
- test_results.json +6 -6
- trainer_state.json +44 -41
- training_args.bin +1 -1
all_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch": 1.
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_loss":
|
5 |
-
"eval_runtime":
|
6 |
-
"eval_samples_per_second": 0.
|
7 |
-
"eval_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_accuracy": 0.18518518518518517,
|
4 |
+
"eval_loss": 1.7997931241989136,
|
5 |
+
"eval_runtime": 89.4733,
|
6 |
+
"eval_samples_per_second": 0.302,
|
7 |
+
"eval_steps_per_second": 0.156
|
8 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 344952756
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f1c00acebf1bcb92fb35f52d6e25ab671cd86c0a0b760bde5bf85c68193be7c
|
3 |
size 344952756
|
test_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch": 1.
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_loss":
|
5 |
-
"eval_runtime":
|
6 |
-
"eval_samples_per_second": 0.
|
7 |
-
"eval_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_accuracy": 0.18518518518518517,
|
4 |
+
"eval_loss": 1.7997931241989136,
|
5 |
+
"eval_runtime": 89.4733,
|
6 |
+
"eval_samples_per_second": 0.302,
|
7 |
+
"eval_steps_per_second": 0.156
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,64 +1,67 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "finetuned-Accident-MultipleLabels-Video-subset/checkpoint-
|
4 |
-
"epoch": 1.
|
5 |
"eval_steps": 500,
|
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 |
-
"
|
14 |
-
"
|
15 |
-
"
|
16 |
-
"eval_samples_per_second": 0.293,
|
17 |
-
"eval_steps_per_second": 0.293,
|
18 |
-
"step": 4
|
19 |
},
|
20 |
{
|
21 |
-
"epoch": 1.
|
22 |
-
"
|
23 |
-
"
|
24 |
-
"
|
25 |
-
"eval_samples_per_second": 0.282,
|
26 |
-
"eval_steps_per_second": 0.282,
|
27 |
-
"step": 5
|
28 |
},
|
29 |
{
|
30 |
-
"epoch": 1.
|
31 |
-
"
|
32 |
-
"
|
33 |
-
"
|
34 |
-
"
|
35 |
-
"
|
36 |
-
"
|
37 |
},
|
38 |
{
|
39 |
-
"epoch": 1.
|
40 |
-
"
|
41 |
-
"
|
42 |
-
"
|
43 |
-
"
|
44 |
-
"
|
45 |
-
"
|
46 |
},
|
47 |
{
|
48 |
-
"epoch": 1.
|
49 |
-
"eval_accuracy": 0.
|
50 |
-
"eval_loss":
|
51 |
-
"eval_runtime":
|
52 |
-
"eval_samples_per_second": 0.
|
53 |
-
"eval_steps_per_second": 0.
|
54 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
55 |
}
|
56 |
],
|
57 |
"logging_steps": 10,
|
58 |
-
"max_steps":
|
59 |
"num_train_epochs": 9223372036854775807,
|
60 |
"save_steps": 500,
|
61 |
-
"total_flos":
|
62 |
"trial_name": null,
|
63 |
"trial_params": null
|
64 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.09375,
|
3 |
+
"best_model_checkpoint": "finetuned-Accident-MultipleLabels-Video-subset/checkpoint-20",
|
4 |
+
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 20,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.5,
|
13 |
+
"learning_rate": 2.777777777777778e-05,
|
14 |
+
"loss": 1.9178,
|
15 |
+
"step": 10
|
|
|
|
|
|
|
16 |
},
|
17 |
{
|
18 |
+
"epoch": 1.0,
|
19 |
+
"learning_rate": 0.0,
|
20 |
+
"loss": 1.615,
|
21 |
+
"step": 20
|
|
|
|
|
|
|
22 |
},
|
23 |
{
|
24 |
+
"epoch": 1.0,
|
25 |
+
"eval_accuracy": 0.09375,
|
26 |
+
"eval_loss": 1.989668607711792,
|
27 |
+
"eval_runtime": 210.9754,
|
28 |
+
"eval_samples_per_second": 0.303,
|
29 |
+
"eval_steps_per_second": 0.152,
|
30 |
+
"step": 20
|
31 |
},
|
32 |
{
|
33 |
+
"epoch": 1.0,
|
34 |
+
"step": 20,
|
35 |
+
"total_flos": 4.984480609468416e+16,
|
36 |
+
"train_loss": 1.7663935661315917,
|
37 |
+
"train_runtime": 400.98,
|
38 |
+
"train_samples_per_second": 0.1,
|
39 |
+
"train_steps_per_second": 0.05
|
40 |
},
|
41 |
{
|
42 |
+
"epoch": 1.0,
|
43 |
+
"eval_accuracy": 0.18518518518518517,
|
44 |
+
"eval_loss": 1.7997932434082031,
|
45 |
+
"eval_runtime": 90.3944,
|
46 |
+
"eval_samples_per_second": 0.299,
|
47 |
+
"eval_steps_per_second": 0.155,
|
48 |
+
"step": 20
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 1.0,
|
52 |
+
"eval_accuracy": 0.18518518518518517,
|
53 |
+
"eval_loss": 1.7997931241989136,
|
54 |
+
"eval_runtime": 89.4733,
|
55 |
+
"eval_samples_per_second": 0.302,
|
56 |
+
"eval_steps_per_second": 0.156,
|
57 |
+
"step": 20
|
58 |
}
|
59 |
],
|
60 |
"logging_steps": 10,
|
61 |
+
"max_steps": 20,
|
62 |
"num_train_epochs": 9223372036854775807,
|
63 |
"save_steps": 500,
|
64 |
+
"total_flos": 4.984480609468416e+16,
|
65 |
"trial_name": null,
|
66 |
"trial_params": null
|
67 |
}
|
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 sha256:0a9a998eaa3a4325657997b402b9906cd6173d9cecd57450a12d2c2ace5b088f
|
3 |
size 4600
|