Hugging Face's logo

CLMBR
/
binding-domain-transformer-4

Text Generation
Transformers
PyTorch
opt
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
abhinavp commited on
Commit
0798b61
•
1 Parent(s): f5eda4a

Training in progress, epoch 1, checkpoint

Browse files
Files changed (11) hide show
  1. checkpoint-1602720/config.json +28 -0
  2. checkpoint-1602720/generation_config.json +7 -0
  3. checkpoint-1602720/optimizer.pt +3 -0
  4. checkpoint-1602720/pytorch_model.bin +3 -0
  5. checkpoint-1602720/rng_state.pth +3 -0
  6. checkpoint-1602720/scheduler.pt +3 -0
  7. checkpoint-1602720/special_tokens_map.json +5 -0
  8. checkpoint-1602720/tokenizer.json +0 -0
  9. checkpoint-1602720/tokenizer_config.json +12 -0
  10. checkpoint-1602720/trainer_state.json +0 -0
  11. checkpoint-1602720/training_args.bin +3 -0
checkpoint-1602720/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_remove_final_layer_norm": false,
3
+ "activation_function": "relu",
4
+ "architectures": [
5
+ "OPTForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 2,
9
+ "do_layer_norm_before": true,
10
+ "dropout": 0.1,
11
+ "enable_bias": true,
12
+ "eos_token_id": 2,
13
+ "ffn_dim": 768,
14
+ "hidden_size": 768,
15
+ "init_std": 0.02,
16
+ "layer_norm_elementwise_affine": true,
17
+ "layerdrop": 0.0,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "opt",
20
+ "num_attention_heads": 8,
21
+ "num_hidden_layers": 8,
22
+ "pad_token_id": 1,
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.33.3",
25
+ "use_cache": true,
26
+ "vocab_size": 50002,
27
+ "word_embed_proj_dim": 768
28
+ }
checkpoint-1602720/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.33.3"
7
+ }
checkpoint-1602720/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebb799aeab9a759fb11168833e18cf8013c5acfd97788c370918b08b7079d741
3
+ size 537476677
checkpoint-1602720/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9ad7b17dc26ef9871615da3ceaa9ece96dc603ec255bdffb03c1465942f8218
3
+ size 268727709
checkpoint-1602720/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04142f3118878990922dac4996feac97f9116f15de83c70442f9f495b0c21e34
3
+ size 14575
checkpoint-1602720/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15780278167dd3153647088d08c19735bd004dcc7339427aca48d6f2176f4058
3
+ size 627
checkpoint-1602720/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "<eos>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
checkpoint-1602720/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1602720/tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "eos_token": "<eos>",
4
+ "max_length": null,
5
+ "model_max_length": 512,
6
+ "pad_to_multiple_of": null,
7
+ "pad_token": "<pad>",
8
+ "pad_token_type_id": 0,
9
+ "padding_side": "right",
10
+ "tokenizer_class": "PreTrainedTokenizerFast",
11
+ "unk_token": "<unk>"
12
+ }
checkpoint-1602720/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1602720/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7727d6e2dc4f39debfe64a9b0844c6d65dd691076b34578e94a04c890fae0f96
3
+ size 4283