Hugging Face's logo

flax-community
/
gpt2-medium-indonesian

Text Generation
Transformers
PyTorch
JAX
TensorBoard
Indonesian
gpt2
text-generation-inference
Model card Files
xet
 Metrics Community
7
cahya commited on
Commit
c9bc4ca
·
1 Parent(s): 4eada35

Saving weights and logs of step 10000

Browse files
Files changed (7) hide show
  1. config.json +0 -2
  2. events.out.tfevents.1625843003.t1v-n-528d9406-w-0.250031.3.v2 +2 -2
  3. flax_model.msgpack +1 -1
  4. wandb/run-20210709_144100-2k1kyrq2/files/output.log +2 -0
  5. wandb/run-20210709_144100-2k1kyrq2/files/wandb-summary.json +1 -1
  6. wandb/run-20210709_144100-2k1kyrq2/logs/debug-internal.log +0 -0
  7. wandb/run-20210709_144100-2k1kyrq2/run-2k1kyrq2.wandb +0 -0
config.json CHANGED
@@ -1,5 +1,4 @@
1
  {
2
- "_name_or_path": ".",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
@@ -33,7 +32,6 @@
33
  "max_length": 50
34
  }
35
  },
36
- "torch_dtype": "float32",
37
  "transformers_version": "4.9.0.dev0",
38
  "use_cache": true,
39
  "vocab_size": 50257
 
1
  {
 
2
  "activation_function": "gelu_new",
3
  "architectures": [
4
  "GPT2LMHeadModel"
 
32
  "max_length": 50
33
  }
34
  },
 
35
  "transformers_version": "4.9.0.dev0",
36
  "use_cache": true,
37
  "vocab_size": 50257
events.out.tfevents.1625843003.t1v-n-528d9406-w-0.250031.3.v2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65f1a7d1164ca3b62fcc3dea900488379e35e8dbc651d2d586a093e695813bb7
3
- size 735138
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d95b12f427bf583b9067304b1335be00b71a33d36f953dad1f1e647a8f0526c
3
+ size 1470349
flax_model.msgpack CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c82df389e510b831d9a5c33f348a258ef105f78170ccc3efd78ab838d40a038b
3
  size 1419302302
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e12359d533ceae1fa223871492c62e14d0c586867a48c6ef7a6a2fc30357060a
3
  size 1419302302
wandb/run-20210709_144100-2k1kyrq2/files/output.log CHANGED
@@ -422,3 +422,5 @@ loading file None
422
  #37: 75%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████ | 3/4 [00:29<00:08, 8.43s/ba]
423
  #43: 75%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████ | 3/4 [00:28<00:08, 8.75s/ba]
424
  Step... (5000 | Loss: 3.704026460647583, Learning Rate: 0.00238410709425807)
 
 
 
422
  #37: 75%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████ | 3/4 [00:29<00:08, 8.43s/ba]
423
  #43: 75%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████ | 3/4 [00:28<00:08, 8.75s/ba]
424
  Step... (5000 | Loss: 3.704026460647583, Learning Rate: 0.00238410709425807)
425
+ Step... (5000 | Eval Loss: 3.6012017726898193 | Eval Perplexity: 36.64224364155734)
426
+ Step... (10000 | Loss: 3.3888800144195557, Learning Rate: 0.0023642408195883036)
wandb/run-20210709_144100-2k1kyrq2/files/wandb-summary.json CHANGED
@@ -1 +1 @@
1
- {"global_step": 5000, "_timestamp": 1625848638.071834, "train_time": 5622.2197265625, "train_learning_rate": 0.00238410709425807, "_step": 9997, "train_loss": 3.5673484802246094}
 
1
+ {"global_step": 10000, "_timestamp": 1625854463.854469, "train_time": 17070.388671875, "train_learning_rate": 0.0023642408195883036, "_step": 19994, "train_loss": 3.383782386779785, "eval_loss": 3.6012017726898193, "eval_perplexity": 36.642242431640625}
wandb/run-20210709_144100-2k1kyrq2/logs/debug-internal.log CHANGED
The diff for this file is too large to render. See raw diff
 
wandb/run-20210709_144100-2k1kyrq2/run-2k1kyrq2.wandb CHANGED
Binary files a/wandb/run-20210709_144100-2k1kyrq2/run-2k1kyrq2.wandb and b/wandb/run-20210709_144100-2k1kyrq2/run-2k1kyrq2.wandb differ