Training in progress, epoch 1

emissions.csv

@@ -1,3 +1,4 @@
 timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
 2024-03-20T11:01:49,codecarbon,b81813c9-ab45-4ccc-83d8-f2a4316cf89f,58.719741344451904,0.0001371672341424,2.3359645496020573e-06,42.5,163.5453820128516,96.0,0.000693154864841,0.0027206010653682,0.001565091044108,0.0049788469743173,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
-2024-03-20T11:05:19,codecarbon,6c2c2758-17f0-4446-8584-48873e3efe79,58.880845069885254,0.0001376040301180982,2.336991426579849e-06,42.5,164.69223718998342,96.0,0.000695071282154984,0.0027303655176247332,0.0015692648379007977,0.004994701637680515,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
+2024-03-20T11:05:19,codecarbon,6c2c2758-17f0-4446-8584-48873e3efe79,58.88084506988525,0.000137604030118,2.336991426579849e-06,42.5,164.69223718998342,96.0,0.0006950712821549,0.0027303655176247,0.0015692648379007,0.0049947016376805,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
+2024-03-20T11:06:12,codecarbon,8c5cd6be-b949-4d3e-aeee-44d3635c6e6a,23.822866678237915,5.516064570736377e-05,2.3154495406614006e-06,42.5,164.7951544056971,96.0,0.0002812162867850728,0.0010861108688864363,0.0006348741404215495,0.002002201296093059,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 sha256:44085a9e06281f621e40dbb3f78797b2409634448ac9deac09a4392aedf646ad
+oid sha256:47a89af68d9690511248f1b7871cfa3b08881d959960d0785c6b458145ae4566
 size 267832560

run-0/checkpoint-535/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-0/checkpoint-535/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47a89af68d9690511248f1b7871cfa3b08881d959960d0785c6b458145ae4566
+size 267832560

run-0/checkpoint-535/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bb20422aba0f2c699175f897f856d13235ca281d52b3af3dd019cbaf8950497
+size 535727290

run-0/checkpoint-535/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:629119240156f5bdd665de8b1edbd1247dc5d4322a8f37d92132ef93df16ea3a
+size 14244

run-0/checkpoint-535/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39b5c50cc84c95dc7201d769aa1513c6c689feb8184c80ed38fd03e5e89c9a65
+size 1064

run-0/checkpoint-535/special_tokens_map.json

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

run-0/checkpoint-535/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-0/checkpoint-535/trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": 0.40760885904937505,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-535",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 535,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.93,
+      "grad_norm": 3.8641507625579834,
+      "learning_rate": 3.8123782979849475e-05,
+      "loss": 0.553,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.48692557215690613,
+      "eval_matthews_correlation": 0.40760885904937505,
+      "eval_runtime": 0.3431,
+      "eval_samples_per_second": 3040.316,
+      "eval_steps_per_second": 192.388,
+      "step": 535
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1070,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 42973252045248.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.156569787445428e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 16,
+    "seed": 15
+  }
+}

run-0/checkpoint-535/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7db6bf6817bccd2005511528ed19af7abcd039666b6ad32830f38a36242c1637
+size 4984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e966bd13fe99ec138cfa4cf5ef74fa9a5d3dad47932168ad43b74d576a91e594
+oid sha256:7db6bf6817bccd2005511528ed19af7abcd039666b6ad32830f38a36242c1637
 size 4984