Commit
•
9155a49
1
Parent(s):
d1eda3e
End of training
Browse files- README.md +11 -8
- generation_config.json +1 -1
- logs/events.out.tfevents.1702890312.94ffa4c68314.42.4 +2 -2
- logs/events.out.tfevents.1702890871.94ffa4c68314.42.5 +3 -0
- logs/events.out.tfevents.1702891019.94ffa4c68314.42.6 +3 -0
- logs/events.out.tfevents.1702891302.94ffa4c68314.42.7 +3 -0
- logs/events.out.tfevents.1702891424.94ffa4c68314.42.8 +3 -0
- model.safetensors +1 -1
- trainer_state.json +21 -14
- training_args.bin +1 -1
README.md
CHANGED
@@ -12,6 +12,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
12 |
# food-recipe-generation
|
13 |
|
14 |
This model was trained from scratch on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
|
16 |
## Model description
|
17 |
|
@@ -36,16 +43,12 @@ The following hyperparameters were used during training:
|
|
36 |
- seed: 42
|
37 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
38 |
- lr_scheduler_type: linear
|
39 |
-
- num_epochs: 0.
|
40 |
- mixed_precision_training: Native AMP
|
41 |
|
42 |
-
### Training results
|
43 |
-
|
44 |
-
|
45 |
-
|
46 |
### Framework versions
|
47 |
|
48 |
-
- Transformers 4.
|
49 |
-
- Pytorch 2.
|
50 |
-
- Datasets 2.
|
51 |
- Tokenizers 0.15.0
|
|
|
12 |
# food-recipe-generation
|
13 |
|
14 |
This model was trained from scratch on an unknown dataset.
|
15 |
+
It achieves the following results on the evaluation set:
|
16 |
+
- eval_loss: 1.1495
|
17 |
+
- eval_runtime: 18.2071
|
18 |
+
- eval_samples_per_second: 109.847
|
19 |
+
- eval_steps_per_second: 1.758
|
20 |
+
- epoch: 0.0
|
21 |
+
- step: 5
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 0.1
|
47 |
- mixed_precision_training: Native AMP
|
48 |
|
|
|
|
|
|
|
|
|
49 |
### Framework versions
|
50 |
|
51 |
+
- Transformers 4.36.0
|
52 |
+
- Pytorch 2.0.0
|
53 |
+
- Datasets 2.1.0
|
54 |
- Tokenizers 0.15.0
|
generation_config.json
CHANGED
@@ -2,5 +2,5 @@
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 50256,
|
4 |
"eos_token_id": 50256,
|
5 |
-
"transformers_version": "4.
|
6 |
}
|
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 50256,
|
4 |
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.36.0"
|
6 |
}
|
logs/events.out.tfevents.1702890312.94ffa4c68314.42.4
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1bf6db4b1bd629a6a7ae0e4599e4400c583db86e41f54f160c93a3d6ba088c27
|
3 |
+
size 6488
|
logs/events.out.tfevents.1702890871.94ffa4c68314.42.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67cd43d76757476261ba2f4f4e61ff10a288ff29d524db52b754393270508a68
|
3 |
+
size 5071
|
logs/events.out.tfevents.1702891019.94ffa4c68314.42.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ecbc75e4a6673145f1c5354bfa7cbab2cf6ea0b0698bb1201737678ca4c06f46
|
3 |
+
size 5071
|
logs/events.out.tfevents.1702891302.94ffa4c68314.42.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1154511ab0129c857aa272addb8906154993b185869d60e5a905de4e7fc768ba
|
3 |
+
size 5071
|
logs/events.out.tfevents.1702891424.94ffa4c68314.42.8
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46e1ac97fb5a6ac92cd7be0bf00839a741c50d6032ec9701e1d240ac574a47dc
|
3 |
+
size 5071
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 497918592
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:666cbb5e59aaee04ea8170f35956d96e7095a86374ac8b9475767573c0d09143
|
3 |
size 497918592
|
trainer_state.json
CHANGED
@@ -1,28 +1,35 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
-
"eval_steps":
|
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 |
-
|
17 |
-
|
18 |
-
"
|
|
|
|
|
|
|
|
|
|
|
19 |
}
|
20 |
],
|
21 |
-
"logging_steps":
|
22 |
-
"max_steps":
|
|
|
23 |
"num_train_epochs": 1,
|
24 |
-
"save_steps":
|
25 |
-
"total_flos":
|
|
|
26 |
"trial_name": null,
|
27 |
"trial_params": null
|
28 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.001632386549134835,
|
5 |
+
"eval_steps": 5,
|
6 |
+
"global_step": 5,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"learning_rate": 4.9185667752443e-05,
|
14 |
+
"loss": 1.1026,
|
15 |
+
"step": 5
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.0,
|
19 |
+
"eval_loss": 1.1494640111923218,
|
20 |
+
"eval_runtime": 18.2071,
|
21 |
+
"eval_samples_per_second": 109.847,
|
22 |
+
"eval_steps_per_second": 1.758,
|
23 |
+
"step": 5
|
24 |
}
|
25 |
],
|
26 |
+
"logging_steps": 5,
|
27 |
+
"max_steps": 307,
|
28 |
+
"num_input_tokens_seen": 0,
|
29 |
"num_train_epochs": 1,
|
30 |
+
"save_steps": 5,
|
31 |
+
"total_flos": 10451681280000.0,
|
32 |
+
"train_batch_size": 32,
|
33 |
"trial_name": null,
|
34 |
"trial_params": null
|
35 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4283
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24f7cc470173209200fa7833aefd3c6f1ea8b6b4e8765bc96a7ce199e4c5e43d
|
3 |
size 4283
|