Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de3b6033bbe97da966aa94d3c4669106d2fdc131aaf33cbc1c66e3747e6db6a6
+oid sha256:00d8c03fe456d3a647c70500cb66d5808e11a842ca1e00e553f4c683c0c57aaa
 size 267832560

run-6/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": "4.39.2",
+  "vocab_size": 30522
+}

run-6/checkpoint-4276/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00d8c03fe456d3a647c70500cb66d5808e11a842ca1e00e553f4c683c0c57aaa
+size 267832560

run-6/checkpoint-4276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ef2384257e3f6ab43d26aaa5d9955b355c6358c2fad12d8fec90a238b6934ce
+size 535727290

run-6/checkpoint-4276/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc301365ccf10832ab2afa68cd8d382165f0839d438ebeb5d09ff523b6183049
+size 14244

run-6/checkpoint-4276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5f7d46dda100e300ff5b88a1ddd7abeb92fe0f679238cb9bcbbefb26198de1d
+size 1064

run-6/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-6/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-6/checkpoint-4276/trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": 0.5312319613383731,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola\\run-6\\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": 20.960588455200195,
+      "learning_rate": 1.1786229789654309e-05,
+      "loss": 0.5916,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 8.482439994812012,
+      "learning_rate": 1.1207906443743891e-05,
+      "loss": 0.5669,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 5.808671951293945,
+      "learning_rate": 1.0629583097833473e-05,
+      "loss": 0.5521,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 45.093868255615234,
+      "learning_rate": 1.0051259751923056e-05,
+      "loss": 0.5405,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6268027424812317,
+      "eval_matthews_correlation": 0.41222715814310473,
+      "eval_runtime": 0.8446,
+      "eval_samples_per_second": 1234.939,
+      "eval_steps_per_second": 78.146,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 0.9396941065788269,
+      "learning_rate": 9.472936406012638e-06,
+      "loss": 0.4693,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.3982331454753876,
+      "learning_rate": 8.89461306010222e-06,
+      "loss": 0.4566,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 30.939773559570312,
+      "learning_rate": 8.316289714191805e-06,
+      "loss": 0.5094,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 21.7435302734375,
+      "learning_rate": 7.737966368281385e-06,
+      "loss": 0.485,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.7867382764816284,
+      "eval_matthews_correlation": 0.5312319613383731,
+      "eval_runtime": 0.8357,
+      "eval_samples_per_second": 1247.998,
+      "eval_steps_per_second": 78.972,
+      "step": 4276
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 65111866045632.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.2364553135564726e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 5
+  }
+}

run-6/checkpoint-4276/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bb4f305fd6833deb5125f712ed47baba841bd34445f1ecd0516278217739802
+size 4984