cosimoiaia
commited on
Commit
•
b142f95
1
Parent(s):
8e00dad
Upload folder using huggingface_hub
Browse files- all_results.json +7 -0
- checkpoint-1500/adapter_model/adapter_config.json +19 -0
- checkpoint-1500/adapter_model/adapter_model.bin +3 -0
- checkpoint-1500/optimizer.pt +3 -0
- checkpoint-1500/rng_state.pth +3 -0
- checkpoint-1500/scheduler.pt +3 -0
- checkpoint-1500/special_tokens_map.json +6 -0
- checkpoint-1500/tokenizer.json +0 -0
- checkpoint-1500/tokenizer_config.json +10 -0
- checkpoint-1500/trainer_state.json +22 -0
- checkpoint-1500/training_args.bin +3 -0
- checkpoint-3000/adapter_model/adapter_config.json +19 -0
- checkpoint-3000/adapter_model/adapter_model.bin +3 -0
- checkpoint-3000/optimizer.pt +3 -0
- checkpoint-3000/rng_state.pth +3 -0
- checkpoint-3000/scheduler.pt +3 -0
- checkpoint-3000/special_tokens_map.json +6 -0
- checkpoint-3000/tokenizer.json +0 -0
- checkpoint-3000/tokenizer_config.json +10 -0
- checkpoint-3000/trainer_state.json +34 -0
- checkpoint-3000/training_args.bin +3 -0
- completed +0 -0
- metrics.json +1 -0
- train_results.json +7 -0
- trainer_state.json +43 -0
all_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.47,
|
3 |
+
"train_loss": 13223.026456787109,
|
4 |
+
"train_runtime": 91003.2011,
|
5 |
+
"train_samples_per_second": 0.527,
|
6 |
+
"train_steps_per_second": 0.033
|
7 |
+
}
|
checkpoint-1500/adapter_model/adapter_config.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"base_model_name_or_path": "EleutherAI/gpt-neox-20b",
|
3 |
+
"bias": "none",
|
4 |
+
"fan_in_fan_out": false,
|
5 |
+
"inference_mode": true,
|
6 |
+
"init_lora_weights": true,
|
7 |
+
"lora_alpha": 16,
|
8 |
+
"lora_dropout": 0.0,
|
9 |
+
"modules_to_save": null,
|
10 |
+
"peft_type": "LORA",
|
11 |
+
"r": 64,
|
12 |
+
"target_modules": [
|
13 |
+
"dense_h_to_4h",
|
14 |
+
"dense",
|
15 |
+
"dense_4h_to_h",
|
16 |
+
"query_key_value"
|
17 |
+
],
|
18 |
+
"task_type": "CAUSAL_LM"
|
19 |
+
}
|
checkpoint-1500/adapter_model/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5020c200968f1a86264f93d6f26f80e09c20a82987346d1961462870a010b69d
|
3 |
+
size 1107425613
|
checkpoint-1500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bba1a4b584ca5b3e31c590a97549024dcc8ba114e25c3f1f642c75c7fc63834c
|
3 |
+
size 7157341505
|
checkpoint-1500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62645c695530bea3f09200c274e27a94375cae128377db5b017b297143c54c49
|
3 |
+
size 14575
|
checkpoint-1500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d397c26ac1ddd7670b9ddd8b909580a771b707ad5b586b657ad627e8bc4e787f
|
3 |
+
size 627
|
checkpoint-1500/special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
checkpoint-1500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1500/tokenizer_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"eos_token": "<|endoftext|>",
|
6 |
+
"model_max_length": 1000000000000000019884624838656,
|
7 |
+
"padding_side": "right",
|
8 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
9 |
+
"unk_token": "<|endoftext|>"
|
10 |
+
}
|
checkpoint-1500/trainer_state.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.23539104337079975,
|
5 |
+
"global_step": 1500,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.16,
|
12 |
+
"learning_rate": 0.0002,
|
13 |
+
"loss": 1.3674,
|
14 |
+
"step": 1000
|
15 |
+
}
|
16 |
+
],
|
17 |
+
"max_steps": 3000,
|
18 |
+
"num_train_epochs": 1,
|
19 |
+
"total_flos": 2.430441850634404e+17,
|
20 |
+
"trial_name": null,
|
21 |
+
"trial_params": null
|
22 |
+
}
|
checkpoint-1500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e4f0f86233c379952dd17ffcde85e775e1d0857fab05b4255b2f0994a5f05dc
|
3 |
+
size 5691
|
checkpoint-3000/adapter_model/adapter_config.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"base_model_name_or_path": "EleutherAI/gpt-neox-20b",
|
3 |
+
"bias": "none",
|
4 |
+
"fan_in_fan_out": false,
|
5 |
+
"inference_mode": true,
|
6 |
+
"init_lora_weights": true,
|
7 |
+
"lora_alpha": 16,
|
8 |
+
"lora_dropout": 0.0,
|
9 |
+
"modules_to_save": null,
|
10 |
+
"peft_type": "LORA",
|
11 |
+
"r": 64,
|
12 |
+
"target_modules": [
|
13 |
+
"dense_h_to_4h",
|
14 |
+
"dense",
|
15 |
+
"dense_4h_to_h",
|
16 |
+
"query_key_value"
|
17 |
+
],
|
18 |
+
"task_type": "CAUSAL_LM"
|
19 |
+
}
|
checkpoint-3000/adapter_model/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a50ab6199547153b4141d5d2269f7f0bc0476dccfa4eecb220494eb827bf814
|
3 |
+
size 1107425613
|
checkpoint-3000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:afc4e6d663ffd0dc3f0f83e15a4636f6cc13945354579396dcdd34138901c2d4
|
3 |
+
size 7157341505
|
checkpoint-3000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62645c695530bea3f09200c274e27a94375cae128377db5b017b297143c54c49
|
3 |
+
size 14575
|
checkpoint-3000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb57538b0fddb988f32d5e33311bcf25efee1aa4001ec3e33ef4a2dd884d77d3
|
3 |
+
size 627
|
checkpoint-3000/special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
checkpoint-3000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-3000/tokenizer_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"eos_token": "<|endoftext|>",
|
6 |
+
"model_max_length": 1000000000000000019884624838656,
|
7 |
+
"padding_side": "right",
|
8 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
9 |
+
"unk_token": "<|endoftext|>"
|
10 |
+
}
|
checkpoint-3000/trainer_state.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.4707820867415995,
|
5 |
+
"global_step": 3000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.16,
|
12 |
+
"learning_rate": 0.0002,
|
13 |
+
"loss": 1.3674,
|
14 |
+
"step": 1000
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.31,
|
18 |
+
"learning_rate": 0.0002,
|
19 |
+
"loss": 39667.712,
|
20 |
+
"step": 2000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.47,
|
24 |
+
"learning_rate": 0.0002,
|
25 |
+
"loss": 0.0,
|
26 |
+
"step": 3000
|
27 |
+
}
|
28 |
+
],
|
29 |
+
"max_steps": 3000,
|
30 |
+
"num_train_epochs": 1,
|
31 |
+
"total_flos": 4.834313788425339e+17,
|
32 |
+
"trial_name": null,
|
33 |
+
"trial_params": null
|
34 |
+
}
|
checkpoint-3000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e4f0f86233c379952dd17ffcde85e775e1d0857fab05b4255b2f0994a5f05dc
|
3 |
+
size 5691
|
completed
ADDED
File without changes
|
metrics.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"run_name": "/mnt/vol_b/Loquace-neox-20b", "train_runtime": 91003.2011, "train_samples_per_second": 0.527, "train_steps_per_second": 0.033, "train_loss": 13223.026456787109, "epoch": 0.47}
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.47,
|
3 |
+
"train_loss": 13223.026456787109,
|
4 |
+
"train_runtime": 91003.2011,
|
5 |
+
"train_samples_per_second": 0.527,
|
6 |
+
"train_steps_per_second": 0.033
|
7 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.4707820867415995,
|
5 |
+
"global_step": 3000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.16,
|
12 |
+
"learning_rate": 0.0002,
|
13 |
+
"loss": 1.3674,
|
14 |
+
"step": 1000
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.31,
|
18 |
+
"learning_rate": 0.0002,
|
19 |
+
"loss": 39667.712,
|
20 |
+
"step": 2000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.47,
|
24 |
+
"learning_rate": 0.0002,
|
25 |
+
"loss": 0.0,
|
26 |
+
"step": 3000
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.47,
|
30 |
+
"step": 3000,
|
31 |
+
"total_flos": 4.834313788425339e+17,
|
32 |
+
"train_loss": 13223.026456787109,
|
33 |
+
"train_runtime": 91003.2011,
|
34 |
+
"train_samples_per_second": 0.527,
|
35 |
+
"train_steps_per_second": 0.033
|
36 |
+
}
|
37 |
+
],
|
38 |
+
"max_steps": 3000,
|
39 |
+
"num_train_epochs": 1,
|
40 |
+
"total_flos": 4.834313788425339e+17,
|
41 |
+
"trial_name": null,
|
42 |
+
"trial_params": null
|
43 |
+
}
|