jorgeortizfuentes
commited on
Commit
•
8aade8b
1
Parent(s):
ade5837
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": 1.3722278172331406,
|
4 |
+
"train_runtime": 228465.2602,
|
5 |
+
"train_samples": 15080876,
|
6 |
+
"train_samples_per_second": 66.009,
|
7 |
+
"train_steps_per_second": 1.031
|
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:bef03536069f8ad00eac83eff95790f718953230928976ecbc85a5d92e2d5f1f
|
3 |
size 439561560
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 1.3722278172331406,
|
4 |
+
"train_runtime": 228465.2602,
|
5 |
+
"train_samples": 15080876,
|
6 |
+
"train_samples_per_second": 66.009,
|
7 |
+
"train_steps_per_second": 1.031
|
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": 235639,
|
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": 1.6042,
|
14 |
+
"step": 23564
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.2,
|
18 |
+
"learning_rate": 2e-05,
|
19 |
+
"loss": 1.4558,
|
20 |
+
"step": 47128
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.3,
|
24 |
+
"learning_rate": 2e-05,
|
25 |
+
"loss": 1.4046,
|
26 |
+
"step": 70692
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.4,
|
30 |
+
"learning_rate": 2e-05,
|
31 |
+
"loss": 1.3729,
|
32 |
+
"step": 94256
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.5,
|
36 |
+
"learning_rate": 2e-05,
|
37 |
+
"loss": 1.3504,
|
38 |
+
"step": 117820
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.6,
|
42 |
+
"learning_rate": 2e-05,
|
43 |
+
"loss": 1.3312,
|
44 |
+
"step": 141384
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.7,
|
48 |
+
"learning_rate": 2e-05,
|
49 |
+
"loss": 1.3171,
|
50 |
+
"step": 164948
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.8,
|
54 |
+
"learning_rate": 2e-05,
|
55 |
+
"loss": 1.3048,
|
56 |
+
"step": 188512
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.9,
|
60 |
+
"learning_rate": 2e-05,
|
61 |
+
"loss": 1.2958,
|
62 |
+
"step": 212076
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 1.0,
|
66 |
+
"step": 235639,
|
67 |
+
"total_flos": 3.9693813820965274e+18,
|
68 |
+
"train_loss": 1.3722278172331406,
|
69 |
+
"train_runtime": 228465.2602,
|
70 |
+
"train_samples_per_second": 66.009,
|
71 |
+
"train_steps_per_second": 1.031
|
72 |
+
}
|
73 |
+
],
|
74 |
+
"max_steps": 235639,
|
75 |
+
"num_train_epochs": 1,
|
76 |
+
"total_flos": 3.9693813820965274e+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 sha256:529a1db40bfb1079cbd62d79d1c157831cd25e378764d83ef7dc5fca9dd279db
|
3 |
size 4027
|