AlekseyKorshuk
commited on
Commit
•
2b69ef9
1
Parent(s):
8f6ddaf
huggingartists
Browse files- README.md +4 -4
- config.json +2 -2
- evaluation.txt +1 -1
- flax_model.msgpack +1 -1
- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- tokenizer_config.json +1 -1
- trainer_state.json +45 -7
- training_args.bin +2 -2
README.md
CHANGED
@@ -14,7 +14,7 @@ widget:
|
|
14 |
<div class="inline-flex flex-col" style="line-height: 1.5;">
|
15 |
<div class="flex">
|
16 |
<div
|
17 |
-
style="display:DISPLAY_1; margin-left: auto; margin-right: auto; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://images.genius.com/
|
18 |
</div>
|
19 |
</div>
|
20 |
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 HuggingArtists Model 🤖</div>
|
@@ -45,15 +45,15 @@ from datasets import load_dataset
|
|
45 |
dataset = load_dataset("huggingartists/adele")
|
46 |
```
|
47 |
|
48 |
-
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/
|
49 |
|
50 |
## Training procedure
|
51 |
|
52 |
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Adele's lyrics.
|
53 |
|
54 |
-
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/
|
55 |
|
56 |
-
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/
|
57 |
|
58 |
## How to use
|
59 |
|
|
|
14 |
<div class="inline-flex flex-col" style="line-height: 1.5;">
|
15 |
<div class="flex">
|
16 |
<div
|
17 |
+
style="display:DISPLAY_1; margin-left: auto; margin-right: auto; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://images.genius.com/4c3ac1f1d845d251671a892309b5f9b5.1000x1000x1.jpg')">
|
18 |
</div>
|
19 |
</div>
|
20 |
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 HuggingArtists Model 🤖</div>
|
|
|
45 |
dataset = load_dataset("huggingartists/adele")
|
46 |
```
|
47 |
|
48 |
+
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1yyqw6ss/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
|
49 |
|
50 |
## Training procedure
|
51 |
|
52 |
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Adele's lyrics.
|
53 |
|
54 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/3qruwjpr) for full transparency and reproducibility.
|
55 |
|
56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/3qruwjpr/artifacts) is logged and versioned.
|
57 |
|
58 |
## How to use
|
59 |
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
@@ -35,7 +35,7 @@
|
|
35 |
}
|
36 |
},
|
37 |
"torch_dtype": "float32",
|
38 |
-
"transformers_version": "4.
|
39 |
"use_cache": true,
|
40 |
"vocab_size": 50257
|
41 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "huggingartists/adele",
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
|
|
35 |
}
|
36 |
},
|
37 |
"torch_dtype": "float32",
|
38 |
+
"transformers_version": "4.11.3",
|
39 |
"use_cache": true,
|
40 |
"vocab_size": 50257
|
41 |
}
|
evaluation.txt
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"eval_loss": 2.
|
|
|
1 |
+
{"eval_loss": 2.032806873321533, "eval_runtime": 2.3942, "eval_samples_per_second": 20.466, "eval_steps_per_second": 2.924, "epoch": 2.0}
|
flax_model.msgpack
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 497764120
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8de7ebcdec411942e4157c782aa76156bd207ec77191bc1ca3bb6161758bb3e4
|
3 |
size 497764120
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 995603825
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78d56a3a340520a635f064ded0b5bac3fa5678b257464c30a0e8fb4ecbff8e5a
|
3 |
size 995603825
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 510403817
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:26c56704a2b0e84454d868d0bbcb279c70cd51ffa5d00a7a4dfd62c4aea3ebf5
|
3 |
size 510403817
|
rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14567
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fea0b037dd0e89825020d4c6457b424ddb03667359afab1a7c60ed7f1b159ee1
|
3 |
size 14567
|
scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c3abe920791946cddbbf83900fa027adb5f194b76f8bdd77ace29288109de2e
|
3 |
size 623
|
tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "
|
|
|
1 |
+
{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "huggingartists/adele", "tokenizer_class": "GPT2Tokenizer"}
|
trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"best_metric": 2.
|
3 |
-
"best_model_checkpoint": "output/adele/checkpoint-
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -50,11 +50,49 @@
|
|
50 |
"eval_samples_per_second": 21.275,
|
51 |
"eval_steps_per_second": 3.113,
|
52 |
"step": 30
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
53 |
}
|
54 |
],
|
55 |
-
"max_steps":
|
56 |
-
"num_train_epochs":
|
57 |
-
"total_flos":
|
58 |
"trial_name": null,
|
59 |
"trial_params": null
|
60 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.032806873321533,
|
3 |
+
"best_model_checkpoint": "output/adele/checkpoint-58",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"global_step": 58,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
50 |
"eval_samples_per_second": 21.275,
|
51 |
"eval_steps_per_second": 3.113,
|
52 |
"step": 30
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 1.21,
|
56 |
+
"learning_rate": 1.3988015692592823e-05,
|
57 |
+
"loss": 2.4729,
|
58 |
+
"step": 35
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 1.38,
|
62 |
+
"learning_rate": 4.320852254368187e-05,
|
63 |
+
"loss": 2.506,
|
64 |
+
"step": 40
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 1.55,
|
68 |
+
"learning_rate": 7.969824496351964e-05,
|
69 |
+
"loss": 2.3156,
|
70 |
+
"step": 45
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 1.72,
|
74 |
+
"learning_rate": 0.00011301069913603334,
|
75 |
+
"loss": 2.1393,
|
76 |
+
"step": 50
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 1.9,
|
80 |
+
"learning_rate": 0.00013360900754314024,
|
81 |
+
"loss": 2.0381,
|
82 |
+
"step": 55
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 2.0,
|
86 |
+
"eval_loss": 2.032806873321533,
|
87 |
+
"eval_runtime": 2.3782,
|
88 |
+
"eval_samples_per_second": 20.604,
|
89 |
+
"eval_steps_per_second": 2.943,
|
90 |
+
"step": 58
|
91 |
}
|
92 |
],
|
93 |
+
"max_steps": 58,
|
94 |
+
"num_train_epochs": 2,
|
95 |
+
"total_flos": 60358459392000.0,
|
96 |
"trial_name": null,
|
97 |
"trial_params": null
|
98 |
}
|
training_args.bin
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 sha256:6e8f9fa0debe7e4aa1488f4f4da63381da713c0ef11d47d4e5dfda38264a7ae7
|
3 |
+
size 2863
|