Training in progress, epoch 5

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cadf2bfb508a044c278d840db2fe664b22c5ec0a3792eab293fffd6023fff535
+oid sha256:9b054c19eb8c00ce89ecdd0cc4435699c58f4984933f440a71d3c8c7f161c0fe
 size 267832560

run-0/checkpoint-10690/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": "4.39.1",
+  "vocab_size": 30522
+}

run-0/checkpoint-10690/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b054c19eb8c00ce89ecdd0cc4435699c58f4984933f440a71d3c8c7f161c0fe
+size 267832560

run-0/checkpoint-10690/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97bdf1ab048d9ddd41476d27b6902578b3947ffb2e0423526c2df52ea3b0c318
+size 535727290

run-0/checkpoint-10690/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ef35ee57aa56e6b54c4bd9a47c360a9accf8e0fb7f5e528ae7fcd358d8c0f4f
+size 14308

run-0/checkpoint-10690/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9177cb2e147beae028429d87fe2a2315e2f81b34f90a13580e6443b07571d322
+size 1064

run-0/checkpoint-10690/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-10690/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-10690/trainer_state.json

@@ -0,0 +1,218 @@
+{
+  "best_metric": 0.5604304714520574,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-8552",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 10690,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "grad_norm": 7.291004657745361,
+      "learning_rate": 1.351268050159641e-05,
+      "loss": 0.5812,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 14.129287719726562,
+      "learning_rate": 1.284964416687627e-05,
+      "loss": 0.5391,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 4.682578086853027,
+      "learning_rate": 1.2186607832156134e-05,
+      "loss": 0.5557,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.5674272775650024,
+      "learning_rate": 1.1523571497435995e-05,
+      "loss": 0.5335,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5571191906929016,
+      "eval_matthews_correlation": 0.429931898675694,
+      "eval_runtime": 0.7111,
+      "eval_samples_per_second": 1466.739,
+      "eval_steps_per_second": 92.814,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 0.9350309371948242,
+      "learning_rate": 1.0860535162715857e-05,
+      "loss": 0.4251,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.13398246467113495,
+      "learning_rate": 1.0197498827995719e-05,
+      "loss": 0.494,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 35.02979278564453,
+      "learning_rate": 9.534462493275582e-06,
+      "loss": 0.4725,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 7.028965950012207,
+      "learning_rate": 8.871426158555444e-06,
+      "loss": 0.4842,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.9164985418319702,
+      "eval_matthews_correlation": 0.48570761109759075,
+      "eval_runtime": 0.7887,
+      "eval_samples_per_second": 1322.437,
+      "eval_steps_per_second": 83.683,
+      "step": 4276
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.19327987730503082,
+      "learning_rate": 8.208389823835306e-06,
+      "loss": 0.3791,
+      "step": 4500
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 0.06137663871049881,
+      "learning_rate": 7.545353489115168e-06,
+      "loss": 0.2895,
+      "step": 5000
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 0.08592221885919571,
+      "learning_rate": 6.88231715439503e-06,
+      "loss": 0.302,
+      "step": 5500
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 0.3166104257106781,
+      "learning_rate": 6.219280819674893e-06,
+      "loss": 0.3472,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.0048580169677734,
+      "eval_matthews_correlation": 0.5238644265545664,
+      "eval_runtime": 0.7244,
+      "eval_samples_per_second": 1439.815,
+      "eval_steps_per_second": 91.11,
+      "step": 6414
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 8.355254173278809,
+      "learning_rate": 5.556244484954755e-06,
+      "loss": 0.27,
+      "step": 6500
+    },
+    {
+      "epoch": 3.27,
+      "grad_norm": 1.5876544713974,
+      "learning_rate": 4.893208150234616e-06,
+      "loss": 0.2043,
+      "step": 7000
+    },
+    {
+      "epoch": 3.51,
+      "grad_norm": 46.30840301513672,
+      "learning_rate": 4.230171815514479e-06,
+      "loss": 0.1763,
+      "step": 7500
+    },
+    {
+      "epoch": 3.74,
+      "grad_norm": 56.22662353515625,
+      "learning_rate": 3.5671354807943416e-06,
+      "loss": 0.2383,
+      "step": 8000
+    },
+    {
+      "epoch": 3.98,
+      "grad_norm": 0.06078937277197838,
+      "learning_rate": 2.9040991460742034e-06,
+      "loss": 0.2567,
+      "step": 8500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.9978423118591309,
+      "eval_matthews_correlation": 0.5604304714520574,
+      "eval_runtime": 0.7266,
+      "eval_samples_per_second": 1435.55,
+      "eval_steps_per_second": 90.84,
+      "step": 8552
+    },
+    {
+      "epoch": 4.21,
+      "grad_norm": 0.01873200386762619,
+      "learning_rate": 2.2410628113540656e-06,
+      "loss": 0.1201,
+      "step": 9000
+    },
+    {
+      "epoch": 4.44,
+      "grad_norm": 2.4571433067321777,
+      "learning_rate": 1.578026476633928e-06,
+      "loss": 0.1308,
+      "step": 9500
+    },
+    {
+      "epoch": 4.68,
+      "grad_norm": 0.03429502621293068,
+      "learning_rate": 9.149901419137902e-07,
+      "loss": 0.1343,
+      "step": 10000
+    },
+    {
+      "epoch": 4.91,
+      "grad_norm": 0.35002580285072327,
+      "learning_rate": 2.5195380719365235e-07,
+      "loss": 0.1409,
+      "step": 10500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.160696029663086,
+      "eval_matthews_correlation": 0.5442538936990396,
+      "eval_runtime": 0.7197,
+      "eval_samples_per_second": 1449.204,
+      "eval_steps_per_second": 91.704,
+      "step": 10690
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 171133907892600.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.4175716836316547e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 20
+  }
+}

run-0/checkpoint-10690/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48274b221fff5652aa547d6614365662d9285f39f249964afe685924bacacf2d
+size 4984

runs/Mar23_02-09-44_4cc37c544afe/events.out.tfevents.1711160146.4cc37c544afe.560.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bc25099800b126c004c754bc5808e7eb230accd08b285abc63b14f775713560
-size 9510
+oid sha256:31e3cbd3f6f2c34ac51317e51014d4973d25a581c7e23b01eaa282664dc34ac4
+size 11043