Shresthadev403
commited on
Commit
•
6e30bb5
1
Parent(s):
8b49b42
End of training
Browse files
README.md
CHANGED
@@ -13,12 +13,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
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.
|
17 |
-
- eval_runtime:
|
18 |
-
- eval_samples_per_second:
|
19 |
-
- eval_steps_per_second: 1.
|
20 |
- epoch: 0.02
|
21 |
-
- step:
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
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: 1.1328
|
17 |
+
- eval_runtime: 18.2169
|
18 |
+
- eval_samples_per_second: 109.788
|
19 |
+
- eval_steps_per_second: 1.757
|
20 |
- epoch: 0.02
|
21 |
+
- step: 55
|
22 |
|
23 |
## Model description
|
24 |
|
logs/events.out.tfevents.1702893748.c87f45a5aed4.42.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b745c560d58f901442361f39e390fc2160c183eb0f8c06e4143c1ecb00ca03d
|
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 sha256:7704850a36e6d5a6cfee818b88972a342e7735882cd0b07fd42504b010b0da80
|
3 |
size 497918592
|
tmp-checkpoint-50/config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/kaggle/working/food-recipe-generation",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 1024,
|
15 |
+
"n_embd": 768,
|
16 |
+
"n_head": 12,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 12,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"reorder_and_upcast_attn": false,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
23 |
+
"scale_attn_weights": true,
|
24 |
+
"summary_activation": null,
|
25 |
+
"summary_first_dropout": 0.1,
|
26 |
+
"summary_proj_to_labels": true,
|
27 |
+
"summary_type": "cls_index",
|
28 |
+
"summary_use_proj": true,
|
29 |
+
"task_specific_params": {
|
30 |
+
"text-generation": {
|
31 |
+
"do_sample": true,
|
32 |
+
"max_length": 50
|
33 |
+
}
|
34 |
+
},
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.36.0",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 50304
|
39 |
+
}
|
tmp-checkpoint-50/generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.36.0"
|
6 |
+
}
|
tmp-checkpoint-50/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2db25361201f94ee4603c3730182d977d0a4d9f1bc5f98ae095777c4e48f5691
|
3 |
+
size 497918592
|
trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 1.124158501625061,
|
3 |
"best_model_checkpoint": "food-recipe-generation/checkpoint-45",
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 5,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -147,6 +147,20 @@
|
|
147 |
"eval_samples_per_second": 112.306,
|
148 |
"eval_steps_per_second": 1.797,
|
149 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
150 |
}
|
151 |
],
|
152 |
"logging_steps": 5,
|
@@ -154,7 +168,7 @@
|
|
154 |
"num_input_tokens_seen": 0,
|
155 |
"num_train_epochs": 1,
|
156 |
"save_steps": 5,
|
157 |
-
"total_flos":
|
158 |
"train_batch_size": 32,
|
159 |
"trial_name": null,
|
160 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 1.124158501625061,
|
3 |
"best_model_checkpoint": "food-recipe-generation/checkpoint-45",
|
4 |
+
"epoch": 0.017956252040483185,
|
5 |
"eval_steps": 5,
|
6 |
+
"global_step": 55,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
147 |
"eval_samples_per_second": 112.306,
|
148 |
"eval_steps_per_second": 1.797,
|
149 |
"step": 50
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.02,
|
153 |
+
"learning_rate": 4.9185667752443e-05,
|
154 |
+
"loss": 1.1619,
|
155 |
+
"step": 55
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 0.02,
|
159 |
+
"eval_loss": 1.1328459978103638,
|
160 |
+
"eval_runtime": 18.2169,
|
161 |
+
"eval_samples_per_second": 109.788,
|
162 |
+
"eval_steps_per_second": 1.757,
|
163 |
+
"step": 55
|
164 |
}
|
165 |
],
|
166 |
"logging_steps": 5,
|
|
|
168 |
"num_input_tokens_seen": 0,
|
169 |
"num_train_epochs": 1,
|
170 |
"save_steps": 5,
|
171 |
+
"total_flos": 114968494080000.0,
|
172 |
"train_batch_size": 32,
|
173 |
"trial_name": null,
|
174 |
"trial_params": null
|