Upload experiments/2022-12-21-a12ddf66d95706b1f5f35892f7f60ad628d199c701a09dddd2ad64e8a86a0bae
Browse files- experiments/2022-12-21-a12ddf66d95706b1f5f35892f7f60ad628d199c701a09dddd2ad64e8a86a0bae/configs.json +25 -0
- experiments/2022-12-21-a12ddf66d95706b1f5f35892f7f60ad628d199c701a09dddd2ad64e8a86a0bae/deepspeed.json +48 -0
- experiments/2022-12-21-a12ddf66d95706b1f5f35892f7f60ad628d199c701a09dddd2ad64e8a86a0bae/final_checkpoint/config.json +54 -0
- experiments/2022-12-21-a12ddf66d95706b1f5f35892f7f60ad628d199c701a09dddd2ad64e8a86a0bae/final_checkpoint/pytorch_model.bin +3 -0
- experiments/2022-12-21-a12ddf66d95706b1f5f35892f7f60ad628d199c701a09dddd2ad64e8a86a0bae/logs/1671556838.4800577/events.out.tfevents.1671556838.2a17441b-6300-46db-8932-ac62cda77916.2267.2 +3 -0
- experiments/2022-12-21-a12ddf66d95706b1f5f35892f7f60ad628d199c701a09dddd2ad64e8a86a0bae/logs/events.out.tfevents.1671556838.2a17441b-6300-46db-8932-ac62cda77916.2267.1 +3 -0
- experiments/2022-12-21-a12ddf66d95706b1f5f35892f7f60ad628d199c701a09dddd2ad64e8a86a0bae/logs/train_neo/events.out.tfevents.1671556765.2a17441b-6300-46db-8932-ac62cda77916.2267.0 +3 -0
- experiments/2022-12-21-a12ddf66d95706b1f5f35892f7f60ad628d199c701a09dddd2ad64e8a86a0bae/output.log +0 -0
experiments/2022-12-21-a12ddf66d95706b1f5f35892f7f60ad628d199c701a09dddd2ad64e8a86a0bae/configs.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"local_rank": 3,
|
20 |
+
"deepspeed": "deepspeed.json",
|
21 |
+
"total_gpus": 4,
|
22 |
+
"v_cpus": 12,
|
23 |
+
"total_memory_in_gb": 48191.34375,
|
24 |
+
"dataset_limit": 0
|
25 |
+
}
|
experiments/2022-12-21-a12ddf66d95706b1f5f35892f7f60ad628d199c701a09dddd2ad64e8a86a0bae/deepspeed.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"optimizer": {
|
3 |
+
"type": "AdamW",
|
4 |
+
"params": {
|
5 |
+
"lr": "auto",
|
6 |
+
"betas": "auto",
|
7 |
+
"eps": "auto",
|
8 |
+
"weight_decay": "auto"
|
9 |
+
}
|
10 |
+
},
|
11 |
+
|
12 |
+
"scheduler": {
|
13 |
+
"type": "WarmupLR",
|
14 |
+
"params": {
|
15 |
+
"warmup_min_lr": "auto",
|
16 |
+
"warmup_max_lr": "auto",
|
17 |
+
"warmup_num_steps": "auto"
|
18 |
+
}
|
19 |
+
},
|
20 |
+
|
21 |
+
"zero_optimization": {
|
22 |
+
"stage": 2,
|
23 |
+
"offload_optimizer": {
|
24 |
+
"device": "cpu",
|
25 |
+
"pin_memory": true
|
26 |
+
},
|
27 |
+
"allgather_partitions": true,
|
28 |
+
"allgather_bucket_size": 5e8,
|
29 |
+
"overlap_comm": true,
|
30 |
+
"reduce_scatter": true,
|
31 |
+
"reduce_bucket_size": 5e8,
|
32 |
+
"contiguous_gradients": true
|
33 |
+
},
|
34 |
+
|
35 |
+
"tensorboard": {
|
36 |
+
"enabled": true,
|
37 |
+
"output_path": "logs/",
|
38 |
+
"job_name": "train_neo"
|
39 |
+
},
|
40 |
+
|
41 |
+
"zero_allow_untested_optimizer": true,
|
42 |
+
"gradient_accumulation_steps": "auto",
|
43 |
+
"gradient_clipping": "auto",
|
44 |
+
"steps_per_print": 2000,
|
45 |
+
"train_batch_size": "auto",
|
46 |
+
"train_micro_batch_size_per_gpu": "auto",
|
47 |
+
"wall_clock_breakdown": false
|
48 |
+
}
|
experiments/2022-12-21-a12ddf66d95706b1f5f35892f7f60ad628d199c701a09dddd2ad64e8a86a0bae/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": 50257,
|
53 |
+
"window_size": 256
|
54 |
+
}
|
experiments/2022-12-21-a12ddf66d95706b1f5f35892f7f60ad628d199c701a09dddd2ad64e8a86a0bae/final_checkpoint/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1dae543ecfea8918caadf861f881236794f36006b1ff845b0cc89202ef7f842
|
3 |
+
size 551154684
|
experiments/2022-12-21-a12ddf66d95706b1f5f35892f7f60ad628d199c701a09dddd2ad64e8a86a0bae/logs/1671556838.4800577/events.out.tfevents.1671556838.2a17441b-6300-46db-8932-ac62cda77916.2267.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93a65b0b8e4d89bc617e485fdea0539d3561c182f50e87046a5befd661cc2401
|
3 |
+
size 5457
|
experiments/2022-12-21-a12ddf66d95706b1f5f35892f7f60ad628d199c701a09dddd2ad64e8a86a0bae/logs/events.out.tfevents.1671556838.2a17441b-6300-46db-8932-ac62cda77916.2267.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c2e20f24bfe076a8b2a2045af9f5fe2140b6619eb6e61e99aec749cf3be5ab5
|
3 |
+
size 776121
|
experiments/2022-12-21-a12ddf66d95706b1f5f35892f7f60ad628d199c701a09dddd2ad64e8a86a0bae/logs/train_neo/events.out.tfevents.1671556765.2a17441b-6300-46db-8932-ac62cda77916.2267.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec0dc137250bf95b5f973bd58c5ae55062c10e7eb18e25e40696942a2e7775c1
|
3 |
+
size 2929062
|
experiments/2022-12-21-a12ddf66d95706b1f5f35892f7f60ad628d199c701a09dddd2ad64e8a86a0bae/output.log
ADDED
The diff for this file is too large to render.
See raw diff
|
|