Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d02116ed37255f0486fb8da4fe11b69450d84906bcfd3d770ef7e33287a0ac60
+oid sha256:b2e0c4c6b9f3c2af24b4908bd8450398968eeba7917eb0d0db201acdf4a5c200
 size 267832560

run-4/checkpoint-108/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": "4.38.1",
+  "vocab_size": 30522
+}

run-4/checkpoint-108/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d13078abc537fcb0efe5f814c3f802baad16914c710e55ca6adad60f40d4ac5f
+size 267832560

run-4/checkpoint-108/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec2ac5703b35203ad3c7d322c6c21a786a2743760946afaf5014c998d95c9380
+size 535727290

run-4/checkpoint-108/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:651c5772e989f99d6fcde1be4185fa44d61b799d97f17fee9f979e06ec642c3f
+size 14244

run-4/checkpoint-108/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1b0f60d1c9bbb8f0a6e9a8a4fc6767da30ff53562ce0b07fa7067820483b146
+size 1064

run-4/checkpoint-108/special_tokens_map.json

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

run-4/checkpoint-108/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-4/checkpoint-108/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-54",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 108,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6252395510673523,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.67,
+      "eval_samples_per_second": 1556.763,
+      "eval_steps_per_second": 98.51,
+      "step": 54
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6198076009750366,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.3228,
+      "eval_samples_per_second": 788.473,
+      "eval_steps_per_second": 49.894,
+      "step": 108
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 108,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.8768281401294573e-06,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 16,
+    "seed": 11
+  }
+}

run-4/checkpoint-108/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd09c7836f6b4cadd9b4466273e45bc99da8b7f3a222b324baebb0f4ebc517ed
+size 4984

run-5/checkpoint-14/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": "4.38.1",
+  "vocab_size": 30522
+}

run-5/checkpoint-14/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2e0c4c6b9f3c2af24b4908bd8450398968eeba7917eb0d0db201acdf4a5c200
+size 267832560

run-5/checkpoint-14/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36d4c0a79b711d81d96122079c870ef980b5ce5c738c1eb28add7f20ea7746e2
+size 535727290

run-5/checkpoint-14/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4ed288cd1d7f33983e156ebb2b0d229399c8436f09fc8fec974bc8a222d9801
+size 14308

run-5/checkpoint-14/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b93cc3542ff3ab87353231f4f0858fa50b30e0a32cf1b08f3896dd608c0c2e29
+size 1064

run-5/checkpoint-14/special_tokens_map.json

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

run-5/checkpoint-14/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-5/checkpoint-14/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-14",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 14,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.611514151096344,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.6874,
+      "eval_samples_per_second": 1517.237,
+      "eval_steps_per_second": 96.009,
+      "step": 14
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 42,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.5731331990343205e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 64,
+    "seed": 17
+  }
+}

run-5/checkpoint-14/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd8500f89c2644285773c3b4e3865488fe68508949b967a2ebcb93d0944a319f
+size 4984

runs/Feb27_12-32-24_dc4ea0da08d6/events.out.tfevents.1709039896.dc4ea0da08d6.176.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:293f5337296134a75c0d7149ece74326aa1d3a0245fef8a539bb761a57d4150f
+size 5878

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd09c7836f6b4cadd9b4466273e45bc99da8b7f3a222b324baebb0f4ebc517ed
+oid sha256:fd8500f89c2644285773c3b4e3865488fe68508949b967a2ebcb93d0944a319f
 size 4984