Commit
•
94e0efc
1
Parent(s):
7b18984
End of training
Browse files- README.md +7 -9
- config.json +1 -1
- logs/events.out.tfevents.1702955299.f861084c800d.26.0 +3 -0
- model.safetensors +1 -1
- trainer_state.json +17 -3
README.md
CHANGED
@@ -1,6 +1,4 @@
|
|
1 |
---
|
2 |
-
license: mit
|
3 |
-
base_model: gpt2
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
@@ -13,14 +11,14 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# food-recipe-generation
|
15 |
|
16 |
-
This model
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- eval_loss:
|
19 |
-
- eval_runtime:
|
20 |
-
- eval_samples_per_second: 111.
|
21 |
-
- eval_steps_per_second: 1.
|
22 |
-
- epoch:
|
23 |
-
- step:
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
1 |
---
|
|
|
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
model-index:
|
|
|
11 |
|
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: 0.9693
|
17 |
+
- eval_runtime: 1995.4615
|
18 |
+
- eval_samples_per_second: 111.811
|
19 |
+
- eval_steps_per_second: 1.747
|
20 |
+
- epoch: 1.59
|
21 |
+
- step: 100000
|
22 |
|
23 |
## Model description
|
24 |
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/kaggle/working/food-recipe-generation",
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
logs/events.out.tfevents.1702955299.f861084c800d.26.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:903645a666d79f54bb6d9837684ceffc1d0a9ecd70e75689469dbfbcc2a108aa
|
3 |
+
size 5099
|
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:af09b0cb96c80ba2c2efbb742971e5d8d3f924752b6de7ace4783c83116d6d77
|
3 |
size 497918592
|
trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 50000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -21,6 +21,20 @@
|
|
21 |
"eval_samples_per_second": 111.193,
|
22 |
"eval_steps_per_second": 1.738,
|
23 |
"step": 50000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
}
|
25 |
],
|
26 |
"logging_steps": 50000,
|
@@ -28,7 +42,7 @@
|
|
28 |
"num_input_tokens_seen": 0,
|
29 |
"num_train_epochs": 500,
|
30 |
"save_steps": 50000,
|
31 |
-
"total_flos":
|
32 |
"train_batch_size": 32,
|
33 |
"trial_name": null,
|
34 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.5936001019904067,
|
5 |
"eval_steps": 50000,
|
6 |
+
"global_step": 100000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
21 |
"eval_samples_per_second": 111.193,
|
22 |
"eval_steps_per_second": 1.738,
|
23 |
"step": 50000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 1.59,
|
27 |
+
"learning_rate": 4.992035346050262e-05,
|
28 |
+
"loss": 1.0123,
|
29 |
+
"step": 100000
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 1.59,
|
33 |
+
"eval_loss": 0.9693423509597778,
|
34 |
+
"eval_runtime": 1995.4615,
|
35 |
+
"eval_samples_per_second": 111.811,
|
36 |
+
"eval_steps_per_second": 1.747,
|
37 |
+
"step": 100000
|
38 |
}
|
39 |
],
|
40 |
"logging_steps": 50000,
|
|
|
42 |
"num_input_tokens_seen": 0,
|
43 |
"num_train_epochs": 500,
|
44 |
"save_steps": 50000,
|
45 |
+
"total_flos": 2.0903329898496e+17,
|
46 |
"train_batch_size": 32,
|
47 |
"trial_name": null,
|
48 |
"trial_params": null
|