Training in progress, epoch 1

emissions.csv

@@ -3,4 +3,5 @@ timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_po
 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-06,42.5,164.7951544056971,96.0,0.000281216286785,0.0010861108688864,0.0006348741404215,0.002002201296093,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,129.25563645362854,0.0002480293691227,1.918905634817298e-06,42.5,100.54736914935307,96.0,0.0015258966469102,0.0040307021134466,0.0034462821515401,0.009002880911897,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
-2024-03-20T11:09:11,codecarbon,8c5cd6be-b949-4d3e-aeee-44d3635c6e6a,202.64030289649963,0.00039407381368800976,1.944696134259563e-06,42.5,121.59383510113359,96.0,0.0023922337633040217,0.006508886873771047,0.005402829043070476,0.014303949680145544,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
+2024-03-20T11:09:11,codecarbon,8c5cd6be-b949-4d3e-aeee-44d3635c6e6a,202.64030289649963,0.000394073813688,1.944696134259563e-06,42.5,121.5938351011336,96.0,0.002392233763304,0.006508886873771,0.0054028290430704,0.0143039496801455,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
+2024-03-20T11:10:18,codecarbon,8c5cd6be-b949-4d3e-aeee-44d3635c6e6a,269.8455903530121,0.000516300621762389,1.913318728265911e-06,42.5,99.17360382771625,96.0,0.0031856209783090485,0.008360091132511016,0.007194782327016196,0.01874049443783626,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 sha256:654cf4ec2e6d8b5d8b344e8356dbe3d1d41431f8e36ada97e311088fe7a3c404
+oid sha256:812030577cc007c08974c27a89cd87355ccdd1000bf23176c96fed643aad86f0
 size 267832560

run-2/checkpoint-2140/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-2/checkpoint-2140/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a35148a5cb97838cafe50e324836d126e81da468fb07ffb70f35b3484dcfa39e
+size 267832560

run-2/checkpoint-2140/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:500e2b7a614d2533fb3cf37c313dada07f81b84caab4f4d6b2e24739f36b7fad
+size 535727290

run-2/checkpoint-2140/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f7aca5bbe8c11744122c922a01b3872d4fff5ea474d5f2422014e09b681400c
+size 14308

run-2/checkpoint-2140/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ff0a2352ad0f9c1ed430bd742af50efc3ff5b1e4aea7001f2a41e1cbe8096f2
+size 1064

run-2/checkpoint-2140/special_tokens_map.json

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

run-2/checkpoint-2140/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-2/checkpoint-2140/trainer_state.json

@@ -0,0 +1,90 @@
+{
+  "best_metric": 0.38853046110587136,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-1605",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 2140,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.93,
+      "grad_norm": 5.214674472808838,
+      "learning_rate": 1.8520669838507643e-06,
+      "loss": 0.6015,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5738183259963989,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.3412,
+      "eval_samples_per_second": 3056.962,
+      "eval_steps_per_second": 193.441,
+      "step": 535
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 4.423364162445068,
+      "learning_rate": 1.28741241560358e-06,
+      "loss": 0.5393,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5461441874504089,
+      "eval_matthews_correlation": 0.3010425673469933,
+      "eval_runtime": 0.3638,
+      "eval_samples_per_second": 2866.982,
+      "eval_steps_per_second": 181.42,
+      "step": 1070
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 4.518457412719727,
+      "learning_rate": 7.227578473563959e-07,
+      "loss": 0.4865,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5234982967376709,
+      "eval_matthews_correlation": 0.38853046110587136,
+      "eval_runtime": 0.3431,
+      "eval_samples_per_second": 3039.887,
+      "eval_steps_per_second": 192.361,
+      "step": 1605
+    },
+    {
+      "epoch": 3.74,
+      "grad_norm": 9.029548645019531,
+      "learning_rate": 1.581032791092116e-07,
+      "loss": 0.4682,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5316268801689148,
+      "eval_matthews_correlation": 0.38828919728832473,
+      "eval_runtime": 0.3855,
+      "eval_samples_per_second": 2705.706,
+      "eval_steps_per_second": 171.214,
+      "step": 2140
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2140,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 171868946719908.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.4167215520979487e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 33
+  }
+}

run-2/checkpoint-2140/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74dcc0151a5480783edadee6bf531c12ad12bb0ba00ddd223ea2c3a3c6f7d941
+size 4984

run-3/checkpoint-1069/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-3/checkpoint-1069/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:812030577cc007c08974c27a89cd87355ccdd1000bf23176c96fed643aad86f0
+size 267832560

run-3/checkpoint-1069/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adf3c3a1c8207b6684caff565f0a55ccd0a3297ed837819b32242a6ae0582279
+size 535727290

run-3/checkpoint-1069/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eeedf246eb4acf9f6eb593dfaa763ae577dce698c2927856cfa37f4b40d3c6d
+size 14244

run-3/checkpoint-1069/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4cecdc44eb8fde850abd267189d90f68e7d3f48ffa1044cc4df7681a03cc04d
+size 1064

run-3/checkpoint-1069/special_tokens_map.json

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

run-3/checkpoint-1069/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-3/checkpoint-1069/trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_metric": 0.409545749280308,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-1069",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1069,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "grad_norm": 8.771077156066895,
+      "learning_rate": 6.473083427439518e-06,
+      "loss": 0.5665,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 4.481599807739258,
+      "learning_rate": 4.497172735302912e-06,
+      "loss": 0.4944,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.516472339630127,
+      "eval_matthews_correlation": 0.409545749280308,
+      "eval_runtime": 0.3422,
+      "eval_samples_per_second": 3047.653,
+      "eval_steps_per_second": 192.852,
+      "step": 1069
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2138,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 37492413425856.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 8.448994119576122e-06,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 8,
+    "seed": 22
+  }
+}

run-3/checkpoint-1069/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64007b0868c2697da851f18219e28bd943844690e92026e92dcc32c8053cd01b
+size 4984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74dcc0151a5480783edadee6bf531c12ad12bb0ba00ddd223ea2c3a3c6f7d941
+oid sha256:64007b0868c2697da851f18219e28bd943844690e92026e92dcc32c8053cd01b
 size 4984