ybelkada commited on
Commit
42e3c2f
1 Parent(s): 020ed18

End of training

Browse files
Files changed (5) hide show
  1. README.md +50 -0
  2. config.json +31 -0
  3. generation_config.json +7 -0
  4. model.safetensors +3 -0
  5. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ base_model: facebook/opt-125m
4
+ tags:
5
+ - axolotl
6
+ - mamba
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: test-axolotl-axolotlmambatrainer
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # test-axolotl-axolotlmambatrainer
17
+
18
+ This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on an unknown dataset.
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 5e-05
38
+ - train_batch_size: 16
39
+ - eval_batch_size: 16
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 3.0
44
+
45
+ ### Framework versions
46
+
47
+ - Transformers 4.37.0.dev0
48
+ - Pytorch 2.0.1+cu117
49
+ - Datasets 2.16.0
50
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/opt-125m",
3
+ "_remove_final_layer_norm": false,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "architectures": [
7
+ "OPTForCausalLM"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "bos_token_id": 2,
11
+ "do_layer_norm_before": true,
12
+ "dropout": 0.1,
13
+ "enable_bias": true,
14
+ "eos_token_id": 2,
15
+ "ffn_dim": 3072,
16
+ "hidden_size": 768,
17
+ "init_std": 0.02,
18
+ "layer_norm_elementwise_affine": true,
19
+ "layerdrop": 0.0,
20
+ "max_position_embeddings": 2048,
21
+ "model_type": "opt",
22
+ "num_attention_heads": 12,
23
+ "num_hidden_layers": 12,
24
+ "pad_token_id": 1,
25
+ "prefix": "</s>",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.37.0.dev0",
28
+ "use_cache": true,
29
+ "vocab_size": 50272,
30
+ "word_embed_proj_dim": 768
31
+ }
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": "4.37.0.dev0"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3a67b42504e0c101c739fe6ef0d57eb3a9ed90267e41aba8019149a472ceae1
3
+ size 500979600
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc30ad98eb5ff2378ee247c08eb436da247e339f350f97ee4a77782dc77b3b49
3
+ size 4347