Hugging Face's logo

0xsuid
/
GPT-Neo-125M

TensorBoard
Model card Files Metrics Community
0xsuid commited on
Commit
1f75dd3
•
1 Parent(s): 0a384a0

Upload experiments/old/2022-12-19-fdf21cd1874b02afe17fee417ba59c79dadadd87f9b5944402c89d476acb4861

Browse files
Files changed (10) hide show
  1. experiments/2022-12-19-fdf21cd1874b02afe17fee417ba59c79dadadd87f9b5944402c89d476acb4861/configs.json +24 -0
  2. experiments/2022-12-19-fdf21cd1874b02afe17fee417ba59c79dadadd87f9b5944402c89d476acb4861/final_checkpoint/config.json +54 -0
  3. experiments/2022-12-19-fdf21cd1874b02afe17fee417ba59c79dadadd87f9b5944402c89d476acb4861/final_checkpoint/pytorch_model.bin +3 -0
  4. experiments/2022-12-19-fdf21cd1874b02afe17fee417ba59c79dadadd87f9b5944402c89d476acb4861/logs/1671359478.7954867/events.out.tfevents.1671359478.7459dae3-a471-4828-975b-f8e23ae7ab31.157404.2 +3 -0
  5. experiments/2022-12-19-fdf21cd1874b02afe17fee417ba59c79dadadd87f9b5944402c89d476acb4861/logs/1671360863.3359416/events.out.tfevents.1671360863.7459dae3-a471-4828-975b-f8e23ae7ab31.2056.2 +3 -0
  6. experiments/2022-12-19-fdf21cd1874b02afe17fee417ba59c79dadadd87f9b5944402c89d476acb4861/logs/events.out.tfevents.1671359478.7459dae3-a471-4828-975b-f8e23ae7ab31.157404.1 +3 -0
  7. experiments/2022-12-19-fdf21cd1874b02afe17fee417ba59c79dadadd87f9b5944402c89d476acb4861/logs/events.out.tfevents.1671360863.7459dae3-a471-4828-975b-f8e23ae7ab31.2056.1 +3 -0
  8. experiments/2022-12-19-fdf21cd1874b02afe17fee417ba59c79dadadd87f9b5944402c89d476acb4861/logs/train_neo/events.out.tfevents.1671359468.7459dae3-a471-4828-975b-f8e23ae7ab31.157404.0 +3 -0
  9. experiments/2022-12-19-fdf21cd1874b02afe17fee417ba59c79dadadd87f9b5944402c89d476acb4861/logs/train_neo/events.out.tfevents.1671360851.7459dae3-a471-4828-975b-f8e23ae7ab31.2056.0 +3 -0
  10. experiments/2022-12-19-fdf21cd1874b02afe17fee417ba59c79dadadd87f9b5944402c89d476acb4861/output.log +0 -0
experiments/2022-12-19-fdf21cd1874b02afe17fee417ba59c79dadadd87f9b5944402c89d476acb4861/configs.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "./results",
3
+ "evaluation_strategy": "no",
4
+ "do_eval": false,
5
+ "eval_steps": 0,
6
+ "log_level": "error",
7
+ "logging_first_step": true,
8
+ "logging_steps": 5,
9
+ "logging_dir": "./logs",
10
+ "save_steps": 200,
11
+ "save_total_limit": 2,
12
+ "num_train_epochs": 5,
13
+ "per_device_train_batch_size": 6,
14
+ "optim": "adamw_torch",
15
+ "dataloader_drop_last": true,
16
+ "warmup_steps": 500,
17
+ "weight_decay": 0.05,
18
+ "learning_rate": 5e-05,
19
+ "deepspeed": "deepspeed.json",
20
+ "total_gpus": 2,
21
+ "v_cpus": 16,
22
+ "total_memory_in_gb": 48190.40625,
23
+ "dataset_limit": 0
24
+ }
experiments/2022-12-19-fdf21cd1874b02afe17fee417ba59c79dadadd87f9b5944402c89d476acb4861/final_checkpoint/config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/gpt-neo-125M",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTNeoForCausalLM"
6
+ ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global",
10
+ "local",
11
+ "global",
12
+ "local",
13
+ "global",
14
+ "local",
15
+ "global",
16
+ "local",
17
+ "global",
18
+ "local",
19
+ "global",
20
+ "local"
21
+ ],
22
+ "attention_types": [
23
+ [
24
+ [
25
+ "global",
26
+ "local"
27
+ ],
28
+ 6
29
+ ]
30
+ ],
31
+ "bos_token_id": 50256,
32
+ "embed_dropout": 0,
33
+ "eos_token_id": 50256,
34
+ "gradient_checkpointing": false,
35
+ "hidden_size": 768,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": null,
38
+ "layer_norm_epsilon": 1e-05,
39
+ "max_position_embeddings": 2048,
40
+ "model_type": "gpt_neo",
41
+ "num_heads": 12,
42
+ "num_layers": 12,
43
+ "resid_dropout": 0,
44
+ "summary_activation": null,
45
+ "summary_first_dropout": 0.1,
46
+ "summary_proj_to_labels": true,
47
+ "summary_type": "cls_index",
48
+ "summary_use_proj": true,
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.25.1",
51
+ "use_cache": true,
52
+ "vocab_size": 50259,
53
+ "window_size": 256
54
+ }
experiments/2022-12-19-fdf21cd1874b02afe17fee417ba59c79dadadd87f9b5944402c89d476acb4861/final_checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14740f45595915601d144187a21cb3f4581277b62258923673c03f6623698379
3
+ size 551160828
experiments/2022-12-19-fdf21cd1874b02afe17fee417ba59c79dadadd87f9b5944402c89d476acb4861/logs/1671359478.7954867/events.out.tfevents.1671359478.7459dae3-a471-4828-975b-f8e23ae7ab31.157404.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cddda645d2cad653f92d3e304ff1992e4195adc6f49c6e1a67b192353adc112c
3
+ size 5457
experiments/2022-12-19-fdf21cd1874b02afe17fee417ba59c79dadadd87f9b5944402c89d476acb4861/logs/1671360863.3359416/events.out.tfevents.1671360863.7459dae3-a471-4828-975b-f8e23ae7ab31.2056.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82765e7b0eec39d2ceb390ef3b1bd09d617d6befb01f506390857fa2ff8feb3e
3
+ size 5457
experiments/2022-12-19-fdf21cd1874b02afe17fee417ba59c79dadadd87f9b5944402c89d476acb4861/logs/events.out.tfevents.1671359478.7459dae3-a471-4828-975b-f8e23ae7ab31.157404.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2498a9f62160f3053d6f87cc41b38d3cfda83dfd3bd2b68d18fda58b3912410c
3
+ size 24245
experiments/2022-12-19-fdf21cd1874b02afe17fee417ba59c79dadadd87f9b5944402c89d476acb4861/logs/events.out.tfevents.1671360863.7459dae3-a471-4828-975b-f8e23ae7ab31.2056.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5f855b958bd364fda50d8150ba217702326887da9f8dc65d4dfad9c90e5d97a
3
+ size 1557670
experiments/2022-12-19-fdf21cd1874b02afe17fee417ba59c79dadadd87f9b5944402c89d476acb4861/logs/train_neo/events.out.tfevents.1671359468.7459dae3-a471-4828-975b-f8e23ae7ab31.157404.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc110c1963dd2cf1fc4e71642de9df62c6cfade1bf4cd5196e67e2537c70dab4
3
+ size 75954
experiments/2022-12-19-fdf21cd1874b02afe17fee417ba59c79dadadd87f9b5944402c89d476acb4861/logs/train_neo/events.out.tfevents.1671360851.7459dae3-a471-4828-975b-f8e23ae7ab31.2056.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2f49378d774419fefc9c869e9d683df3276f82bf843b5c041e3ed0e3b1e3691
3
+ size 5858686
experiments/2022-12-19-fdf21cd1874b02afe17fee417ba59c79dadadd87f9b5944402c89d476acb4861/output.log ADDED
The diff for this file is too large to render. See raw diff