Training in progress, epoch 2

emissions.csv

@@ -1,4 +1,5 @@
 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,6c2c2758-17f0-4446-8584-48873e3efe79,58.88084506988525,0.000137604030118,2.336991426579849e-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
+2024-03-20T11:06:12,codecarbon,8c5cd6be-b949-4d3e-aeee-44d3635c6e6a,23.822866678237915,5.516064570736377e-05,2.3154495406614006e-06,42.5,164.7951544056971,96.0,0.000281216286785,0.0010861108688864,0.0006348741404215,0.002002201296093,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
+2024-03-20T11:07:57,codecarbon,8c5cd6be-b949-4d3e-aeee-44d3635c6e6a,129.25563645362854,0.00024802936912276396,1.918905634817298e-06,42.5,100.54736914935307,96.0,0.0015258966469102436,0.004030702113446694,0.0034462821515401205,0.009002880911897057,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:a18197220f1d245217268bda9cd698d9538ec28fc25861e503fbdbdf35b87be6
+oid sha256:9cd59584db4ad473ae8ec60465fb95a7a030f1a7cd50a34b855bed85d2165d88
 size 267832560

run-1/checkpoint-4276/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-1/checkpoint-4276/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cd59584db4ad473ae8ec60465fb95a7a030f1a7cd50a34b855bed85d2165d88
+size 267832560

run-1/checkpoint-4276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:729b388c3deb9f1119c582132338b3338886f806b73d1dc3e792f1338b6ef847
+size 535727290

run-1/checkpoint-4276/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff62cca5ca90644ff6466e95943774131166d93730d0a86ced509ab184e233f7
+size 14244

run-1/checkpoint-4276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1127fd09099a64d06732363b3ab4df8e750d5a7655b948cd5e8faf2a79fd8764
+size 1064

run-1/checkpoint-4276/special_tokens_map.json

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

run-1/checkpoint-4276/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-1/checkpoint-4276/trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": 0.4605477899795795,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-4276",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 4276,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "grad_norm": 21.092390060424805,
+      "learning_rate": 1.2650690583673927e-05,
+      "loss": 0.5742,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 14.845769882202148,
+      "learning_rate": 1.0975546173759478e-05,
+      "loss": 0.5397,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 13.874490737915039,
+      "learning_rate": 9.300401763845028e-06,
+      "loss": 0.5327,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 22.50566864013672,
+      "learning_rate": 7.625257353930576e-06,
+      "loss": 0.5138,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6036589741706848,
+      "eval_matthews_correlation": 0.40976281740188225,
+      "eval_runtime": 0.3434,
+      "eval_samples_per_second": 3036.988,
+      "eval_steps_per_second": 192.178,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 0.8492972254753113,
+      "learning_rate": 5.950112944016127e-06,
+      "loss": 0.4239,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 1.9886528253555298,
+      "learning_rate": 4.274968534101676e-06,
+      "loss": 0.4516,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 143.33644104003906,
+      "learning_rate": 2.5998241241872264e-06,
+      "loss": 0.4565,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 96.76008605957031,
+      "learning_rate": 9.246797142727765e-07,
+      "loss": 0.4628,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.8416754603385925,
+      "eval_matthews_correlation": 0.4605477899795795,
+      "eval_runtime": 0.3431,
+      "eval_samples_per_second": 3040.082,
+      "eval_steps_per_second": 192.373,
+      "step": 4276
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4276,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 65041234014708.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.4325834993588377e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 4,
+    "seed": 4
+  }
+}

run-1/checkpoint-4276/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a3e14306d3219fca061bb971b2957968ed8c21f8f1a0abd2b0cce499c151b2a
+size 4984