AlekseyKorshuk
commited on
Commit
·
5ba433a
1
Parent(s):
22862bd
huggingartists
Browse files- README.md +4 -4
- config.json +1 -1
- 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
- trainer_state.json +19 -5
- training_args.bin +1 -1
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/eminem")
|
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 Eminem'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/c7367126e7e6ebc13fcea9d4efca0204.1000x1000x1.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/eminem")
|
46 |
```
|
47 |
|
48 |
+
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/28zb6fn4/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 Eminem's lyrics.
|
53 |
|
54 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/13xmoy93) for full transparency and reproducibility.
|
55 |
|
56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/13xmoy93/artifacts) is logged and versioned.
|
57 |
|
58 |
## How to use
|
59 |
|
config.json
CHANGED
@@ -37,7 +37,7 @@
|
|
37 |
}
|
38 |
},
|
39 |
"torch_dtype": "float32",
|
40 |
-
"transformers_version": "4.20.
|
41 |
"use_cache": true,
|
42 |
"vocab_size": 50257
|
43 |
}
|
|
|
37 |
}
|
38 |
},
|
39 |
"torch_dtype": "float32",
|
40 |
+
"transformers_version": "4.20.1",
|
41 |
"use_cache": true,
|
42 |
"vocab_size": 50257
|
43 |
}
|
evaluation.txt
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"eval_loss": 0.
|
|
|
1 |
+
{"eval_loss": 0.16020862758159637, "eval_runtime": 14.7498, "eval_samples_per_second": 43.458, "eval_steps_per_second": 5.492, "epoch": 3.0}
|
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 sha256:891130706e9a8a83c13b1ad464cb04f299e99e0e9a3849145875756f76278279
|
3 |
size 497764120
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 995604017
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af171e9d839ef3cc49ac661172fdf27a1820c6d3c9beb691041a6bafcee3d9a9
|
3 |
size 995604017
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 510396521
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9db2a7d718d9f692ab940a3ec3093599b47a520ee7bf78bd3faa21a7957f0182
|
3 |
size 510396521
|
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:a6b955aeda6a53da09b57ad2e2981a71eb930c7a8e24ca6228a27ee60b212374
|
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 sha256:4902e21b86dca9aa366cf1646ac70fcc36589bc82a3fb506255e9ffe33a791ab
|
3 |
size 623
|
trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "output/eminem/checkpoint-
|
4 |
"epoch": 2.0,
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -1108,11 +1108,25 @@
|
|
1108 |
"eval_samples_per_second": 42.816,
|
1109 |
"eval_steps_per_second": 5.36,
|
1110 |
"step": 908
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1111 |
}
|
1112 |
],
|
1113 |
-
"max_steps":
|
1114 |
"num_train_epochs": 3,
|
1115 |
-
"total_flos":
|
1116 |
"trial_name": null,
|
1117 |
"trial_params": null
|
1118 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.16020862758159637,
|
3 |
+
"best_model_checkpoint": "output/eminem/checkpoint-910",
|
4 |
"epoch": 2.0,
|
5 |
+
"global_step": 910,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
1108 |
"eval_samples_per_second": 42.816,
|
1109 |
"eval_steps_per_second": 5.36,
|
1110 |
"step": 908
|
1111 |
+
},
|
1112 |
+
{
|
1113 |
+
"epoch": 2.0,
|
1114 |
+
"learning_rate": 2.761634319266075e-07,
|
1115 |
+
"loss": 0.4447,
|
1116 |
+
"step": 910
|
1117 |
+
},
|
1118 |
+
{
|
1119 |
+
"epoch": 2.0,
|
1120 |
+
"eval_loss": 0.16020862758159637,
|
1121 |
+
"eval_runtime": 13.0694,
|
1122 |
+
"eval_samples_per_second": 49.046,
|
1123 |
+
"eval_steps_per_second": 6.198,
|
1124 |
+
"step": 910
|
1125 |
}
|
1126 |
],
|
1127 |
+
"max_steps": 1365,
|
1128 |
"num_train_epochs": 3,
|
1129 |
+
"total_flos": 950057828352000.0,
|
1130 |
"trial_name": null,
|
1131 |
"trial_params": null
|
1132 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3311
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4452aec611dc6857dcdfba0af4b02a078c5f386a1fbf0f4c0f867307d384e2e
|
3 |
size 3311
|