Training in progress, epoch 1
Browse files- emissions.csv +2 -1
- model.safetensors +1 -1
- run-9/checkpoint-268/config.json +25 -0
- run-9/checkpoint-268/model.safetensors +3 -0
- run-9/checkpoint-268/optimizer.pt +3 -0
- run-9/checkpoint-268/rng_state.pth +3 -0
- run-9/checkpoint-268/scheduler.pt +3 -0
- run-9/checkpoint-268/special_tokens_map.json +7 -0
- run-9/checkpoint-268/tokenizer.json +0 -0
- run-9/checkpoint-268/tokenizer_config.json +55 -0
- run-9/checkpoint-268/trainer_state.json +44 -0
- run-9/checkpoint-268/training_args.bin +3 -0
- run-9/checkpoint-268/vocab.txt +0 -0
- training_args.bin +1 -1
emissions.csv
CHANGED
@@ -10,4 +10,5 @@ timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_po
|
|
10 |
2024-03-20T11:15:34,codecarbon,8c5cd6be-b949-4d3e-aeee-44d3635c6e6a,585.5882697105408,0.0011148245747178,1.903768624444728e-06,42.5,76.4417344149013,96.0,0.0069131124711698,0.0179383418506606,0.0156140474828084,0.040465501804639,Norway,NOR,viken,,,Linux-5.14.0-362.8.1.el9_3.x86_64-x86_64-with-glibc2.34,3.11.3,2.3.4,24,AMD EPYC 7642 48-Core Processor,1,1 x NVIDIA A100-PCIE-40GB,10.8034,59.6573,256,machine,N,1.0
|
11 |
2024-03-20T11:16:20,codecarbon,8c5cd6be-b949-4d3e-aeee-44d3635c6e6a,631.8965435028076,0.0012026320726012,1.903210398864824e-06,42.5,109.304377937163,96.0,0.0074597954246732,0.0193441649197634,0.0168487464650472,0.0436527068094839,Norway,NOR,viken,,,Linux-5.14.0-362.8.1.el9_3.x86_64-x86_64-with-glibc2.34,3.11.3,2.3.4,24,AMD EPYC 7642 48-Core Processor,1,1 x NVIDIA A100-PCIE-40GB,10.8034,59.6573,256,machine,N,1.0
|
12 |
2024-03-20T11:16:38,codecarbon,8c5cd6be-b949-4d3e-aeee-44d3635c6e6a,650.12664103508,0.0012390977602013,1.9059329090537992e-06,42.5,122.96952663448236,96.0,0.007675000440412,0.0199666362510733,0.0173346885426839,0.0449763252341693,Norway,NOR,viken,,,Linux-5.14.0-362.8.1.el9_3.x86_64-x86_64-with-glibc2.34,3.11.3,2.3.4,24,AMD EPYC 7642 48-Core Processor,1,1 x NVIDIA A100-PCIE-40GB,10.8034,59.6573,256,machine,N,1.0
|
13 |
-
2024-03-20T11:17:55,codecarbon,8c5cd6be-b949-4d3e-aeee-44d3635c6e6a,726.8632326126099,0.
|
|
|
|
10 |
2024-03-20T11:15:34,codecarbon,8c5cd6be-b949-4d3e-aeee-44d3635c6e6a,585.5882697105408,0.0011148245747178,1.903768624444728e-06,42.5,76.4417344149013,96.0,0.0069131124711698,0.0179383418506606,0.0156140474828084,0.040465501804639,Norway,NOR,viken,,,Linux-5.14.0-362.8.1.el9_3.x86_64-x86_64-with-glibc2.34,3.11.3,2.3.4,24,AMD EPYC 7642 48-Core Processor,1,1 x NVIDIA A100-PCIE-40GB,10.8034,59.6573,256,machine,N,1.0
|
11 |
2024-03-20T11:16:20,codecarbon,8c5cd6be-b949-4d3e-aeee-44d3635c6e6a,631.8965435028076,0.0012026320726012,1.903210398864824e-06,42.5,109.304377937163,96.0,0.0074597954246732,0.0193441649197634,0.0168487464650472,0.0436527068094839,Norway,NOR,viken,,,Linux-5.14.0-362.8.1.el9_3.x86_64-x86_64-with-glibc2.34,3.11.3,2.3.4,24,AMD EPYC 7642 48-Core Processor,1,1 x NVIDIA A100-PCIE-40GB,10.8034,59.6573,256,machine,N,1.0
|
12 |
2024-03-20T11:16:38,codecarbon,8c5cd6be-b949-4d3e-aeee-44d3635c6e6a,650.12664103508,0.0012390977602013,1.9059329090537992e-06,42.5,122.96952663448236,96.0,0.007675000440412,0.0199666362510733,0.0173346885426839,0.0449763252341693,Norway,NOR,viken,,,Linux-5.14.0-362.8.1.el9_3.x86_64-x86_64-with-glibc2.34,3.11.3,2.3.4,24,AMD EPYC 7642 48-Core Processor,1,1 x NVIDIA A100-PCIE-40GB,10.8034,59.6573,256,machine,N,1.0
|
13 |
+
2024-03-20T11:17:55,codecarbon,8c5cd6be-b949-4d3e-aeee-44d3635c6e6a,726.8632326126099,0.0013595048654139,1.87037231272162e-06,42.5,66.55260048901644,96.0,0.0085809094975392,0.0213851179414135,0.0193807916323343,0.0493468190712871,Norway,NOR,viken,,,Linux-5.14.0-362.8.1.el9_3.x86_64-x86_64-with-glibc2.34,3.11.3,2.3.4,24,AMD EPYC 7642 48-Core Processor,1,1 x NVIDIA A100-PCIE-40GB,10.8034,59.6573,256,machine,N,1.0
|
14 |
+
2024-03-20T11:18:49,codecarbon,8c5cd6be-b949-4d3e-aeee-44d3635c6e6a,780.7155704498291,0.0014548135681150564,1.8634360875841488e-06,42.5,92.78079264958224,96.0,0.009216655736830498,0.022772916273872568,0.02081672810236613,0.05280630011306919,Norway,NOR,viken,,,Linux-5.14.0-362.8.1.el9_3.x86_64-x86_64-with-glibc2.34,3.11.3,2.3.4,24,AMD EPYC 7642 48-Core Processor,1,1 x NVIDIA A100-PCIE-40GB,10.8034,59.6573,256,machine,N,1.0
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267832560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47a89af68d9690511248f1b7871cfa3b08881d959960d0785c6b458145ae4566
|
3 |
size 267832560
|
run-9/checkpoint-268/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"problem_type": "single_label_classification",
|
18 |
+
"qa_dropout": 0.1,
|
19 |
+
"seq_classif_dropout": 0.2,
|
20 |
+
"sinusoidal_pos_embds": false,
|
21 |
+
"tie_weights_": true,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.38.2",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-9/checkpoint-268/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a8369f90f1e302e63349b694352eadd817ba2d4baf4faeee3686053979732d5
|
3 |
+
size 267832560
|
run-9/checkpoint-268/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1905620192e5dcf01fe015f43751c9e2035cfd3b9582ff83d5824576bfc28054
|
3 |
+
size 535727290
|
run-9/checkpoint-268/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:497e3e87dd2ea4a3ea1a17d434f0ada6c674e2f59c3b11ca1dec152b203da4de
|
3 |
+
size 14244
|
run-9/checkpoint-268/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6dd0dc2cec0a8d3c1e0bbc02dd43958401e498c81fb2ee4d0c54cdbaa4821c98
|
3 |
+
size 1064
|
run-9/checkpoint-268/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
run-9/checkpoint-268/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-9/checkpoint-268/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-9/checkpoint-268/trainer_state.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.46330744548556085,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-9/checkpoint-268",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 268,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.5036426782608032,
|
14 |
+
"eval_matthews_correlation": 0.40069938311539727,
|
15 |
+
"eval_runtime": 0.3394,
|
16 |
+
"eval_samples_per_second": 3073.383,
|
17 |
+
"eval_steps_per_second": 194.481,
|
18 |
+
"step": 134
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.5034472346305847,
|
23 |
+
"eval_matthews_correlation": 0.46330744548556085,
|
24 |
+
"eval_runtime": 0.3581,
|
25 |
+
"eval_samples_per_second": 2912.306,
|
26 |
+
"eval_steps_per_second": 184.288,
|
27 |
+
"step": 268
|
28 |
+
}
|
29 |
+
],
|
30 |
+
"logging_steps": 500,
|
31 |
+
"max_steps": 268,
|
32 |
+
"num_input_tokens_seen": 0,
|
33 |
+
"num_train_epochs": 2,
|
34 |
+
"save_steps": 500,
|
35 |
+
"total_flos": 0,
|
36 |
+
"train_batch_size": 64,
|
37 |
+
"trial_name": null,
|
38 |
+
"trial_params": {
|
39 |
+
"learning_rate": 3.0430714365470178e-05,
|
40 |
+
"num_train_epochs": 2,
|
41 |
+
"per_device_train_batch_size": 64,
|
42 |
+
"seed": 25
|
43 |
+
}
|
44 |
+
}
|
run-9/checkpoint-268/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac38b0b62b865d6295d012b6fa39dac89d29b9357c0b1b5c81ab0d7c0bafb67d
|
3 |
+
size 4984
|
run-9/checkpoint-268/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7db6bf6817bccd2005511528ed19af7abcd039666b6ad32830f38a36242c1637
|
3 |
size 4984
|