jorgeortizfuentes
commited on
Commit
•
5799586
1
Parent(s):
5986c3d
End of training
Browse files- all_results.json +8 -0
- model.safetensors +1 -1
- train_results.json +8 -0
- trainer_state.json +79 -0
- training_args.bin +1 -1
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 1.3995336800465679,
|
4 |
+
"train_runtime": 507280.6591,
|
5 |
+
"train_samples": 33093989,
|
6 |
+
"train_samples_per_second": 65.238,
|
7 |
+
"train_steps_per_second": 1.019
|
8 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 439561560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3b0ad6dcae2db3e9cce7862f7182b0d851fd26649094f6517b0f4d791f75cac
|
3 |
size 439561560
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 1.3995336800465679,
|
4 |
+
"train_runtime": 507280.6591,
|
5 |
+
"train_samples": 33093989,
|
6 |
+
"train_samples_per_second": 65.238,
|
7 |
+
"train_steps_per_second": 1.019
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"global_step": 517094,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.1,
|
12 |
+
"learning_rate": 2e-05,
|
13 |
+
"loss": 1.5646,
|
14 |
+
"step": 51710
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.2,
|
18 |
+
"learning_rate": 2e-05,
|
19 |
+
"loss": 1.4615,
|
20 |
+
"step": 103420
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.3,
|
24 |
+
"learning_rate": 2e-05,
|
25 |
+
"loss": 1.4251,
|
26 |
+
"step": 155130
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.4,
|
30 |
+
"learning_rate": 2e-05,
|
31 |
+
"loss": 1.4013,
|
32 |
+
"step": 206840
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.5,
|
36 |
+
"learning_rate": 2e-05,
|
37 |
+
"loss": 1.3836,
|
38 |
+
"step": 258550
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.6,
|
42 |
+
"learning_rate": 2e-05,
|
43 |
+
"loss": 1.3704,
|
44 |
+
"step": 310260
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.7,
|
48 |
+
"learning_rate": 2e-05,
|
49 |
+
"loss": 1.3598,
|
50 |
+
"step": 361970
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.8,
|
54 |
+
"learning_rate": 2e-05,
|
55 |
+
"loss": 1.3506,
|
56 |
+
"step": 413680
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.9,
|
60 |
+
"learning_rate": 2e-05,
|
61 |
+
"loss": 1.3429,
|
62 |
+
"step": 465390
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 1.0,
|
66 |
+
"step": 517094,
|
67 |
+
"total_flos": 8.710545978622679e+18,
|
68 |
+
"train_loss": 1.3995336800465679,
|
69 |
+
"train_runtime": 507280.6591,
|
70 |
+
"train_samples_per_second": 65.238,
|
71 |
+
"train_steps_per_second": 1.019
|
72 |
+
}
|
73 |
+
],
|
74 |
+
"max_steps": 517094,
|
75 |
+
"num_train_epochs": 1,
|
76 |
+
"total_flos": 8.710545978622679e+18,
|
77 |
+
"trial_name": null,
|
78 |
+
"trial_params": null
|
79 |
+
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4027
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49d681f38698ac6d569934e98f56251207288b895239d0f52efcbf50293519af
|
3 |
size 4027
|