Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e9ad20a0bd5710a330976ae6a2da344cd0d1163c0b082aca7c3e79a15d39390
+oid sha256:fd1cf37042376bf75928630d852047aee2172386ecc63d16679086aba3fb4206
 size 267832560

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

run-0/checkpoint-4276/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd1cf37042376bf75928630d852047aee2172386ecc63d16679086aba3fb4206
+size 267832560

run-0/checkpoint-4276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d6c49f5557e67a441bbacfd63608783c3e3fd570c81e3c404e23d85c073036e
+size 535727290

run-0/checkpoint-4276/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db4d744d63771944a923989dff8d29085f87e171ec694f475cdec1803c695dab
+size 14308

run-0/checkpoint-4276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1df798a809fa8077c1dd94359a622e89782f4372c32b960981036c165c94dc2f
+size 1064

run-0/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-0/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-0/checkpoint-4276/trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": 0.48570761109759075,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/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": 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
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 65184309154272.0,
+  "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-4276/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:b204273c16396bf76ca73a25ddecfc6f334a1607ce190b7901ad335547104968
-size 5762
+oid sha256:08b36c7516c1308eac99bf37821f602a672bda460b1d568a2b7e723325460c4a
+size 6941