Training in progress, epoch 1

emissions.csv

@@ -9,4 +9,5 @@ timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_po
 2024-03-20T11:15:05,codecarbon,8c5cd6be-b949-4d3e-aeee-44d3635c6e6a,556.7771844863892,0.0010674387190912,1.917173959051385e-06,42.5,108.4736124826506,96.0,0.0065729901999235,0.0173266533057532,0.0148458635393778,0.0387455070450545,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
 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
 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
-2024-03-20T11:16:38,codecarbon,8c5cd6be-b949-4d3e-aeee-44d3635c6e6a,650.12664103508,0.001239097760201365,1.9059329090537992e-06,42.5,122.96952663448235,96.0,0.007675000440412098,0.01996663625107331,0.01733468854268392,0.04497632523416932,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
+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
+2024-03-20T11:17:55,codecarbon,8c5cd6be-b949-4d3e-aeee-44d3635c6e6a,726.8632326126099,0.0013595048654139598,1.8703723127216198e-06,42.5,66.55260048901644,96.0,0.008580909497539202,0.021385117941413512,0.01938079163233439,0.0493468190712871,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

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:602c8c455abf7fad327e2d64c5bedf2ddfbae8013f9edc3c3826cd3c67ff6ed0
+oid sha256:6ba4c95c0c89b7278b358aef9eec5bca4cbc1d253b7a6d6d4c02ab538822de61
 size 267832560

run-9/checkpoint-134/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "vocab_size": 30522
+}

run-9/checkpoint-134/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ba4c95c0c89b7278b358aef9eec5bca4cbc1d253b7a6d6d4c02ab538822de61
+size 267832560

run-9/checkpoint-134/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab093c9e28ebb7d16a640c3ab65aaf7c9f0523251c5a2d486731df17bb7c922b
+size 535727290

run-9/checkpoint-134/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c15f82f3b2643d5e118d3800655bf3fddf0dd415bc1916aa676dd758b6a3328
+size 14244

run-9/checkpoint-134/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96b52a1c21af0b40b8159ef32858a6f8fc72fa8710695fddea6e35184edf6849
+size 1064

run-9/checkpoint-134/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-9/checkpoint-134/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-9/checkpoint-134/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.40069938311539727,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-9/checkpoint-134",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 134,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5036426782608032,
+      "eval_matthews_correlation": 0.40069938311539727,
+      "eval_runtime": 0.3394,
+      "eval_samples_per_second": 3073.383,
+      "eval_steps_per_second": 194.481,
+      "step": 134
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 268,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.0430714365470178e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 64,
+    "seed": 25
+  }
+}

run-9/checkpoint-134/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac38b0b62b865d6295d012b6fa39dac89d29b9357c0b1b5c81ab0d7c0bafb67d
+size 4984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41134123e6324d2297988ee9a159f309008b9ed0e2c8676bc67bbdad4182508d
+oid sha256:ac38b0b62b865d6295d012b6fa39dac89d29b9357c0b1b5c81ab0d7c0bafb67d
 size 4984