Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afd7e3f739fc725a31194e0963d57f779474df4b70a95d4c9bef9b54bf51ba58
+oid sha256:0cfb1097c9f1aa4cde36057da26261025f54bcf187da72ec282c84549ffddaf5
 size 267832560

run-7/checkpoint-535/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": "4.36.2",
+  "vocab_size": 30522
+}

run-7/checkpoint-535/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afd7e3f739fc725a31194e0963d57f779474df4b70a95d4c9bef9b54bf51ba58
+size 267832560

run-7/checkpoint-535/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83264183fc80b0df4dd326d85147117b177e29d4e1e7056be73f4e4158c6b2ad
+size 535727290

run-7/checkpoint-535/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be563af85fa6b71be54e8df24fedd5b3cb6e638d9d74ad18a1f04642542f2ba2
+size 14244

run-7/checkpoint-535/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ccf061d1cd4ebd822a83470de5ec95ac551f31100e4f2f1beaf134eb343c296
+size 1064

run-7/checkpoint-535/special_tokens_map.json

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

run-7/checkpoint-535/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-7/checkpoint-535/trainer_state.json

@@ -0,0 +1,41 @@
+{
+  "best_metric": 0.45999217612288934,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-535",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 535,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.218596867262485e-06,
+      "loss": 0.5235,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.454124391078949,
+      "eval_matthews_correlation": 0.45999217612288934,
+      "eval_runtime": 0.7149,
+      "eval_samples_per_second": 1458.941,
+      "eval_steps_per_second": 92.32,
+      "step": 535
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 535,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 42865622283840.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.919855211386942e-05,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 16,
+    "seed": 36
+  }
+}

run-7/checkpoint-535/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46519a6bce092ae403faec562a8ebb7c3b17199d44f00eb39244ebd8bcca25a5
+size 4792

run-8/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": "4.36.2",
+  "vocab_size": 30522
+}

run-8/checkpoint-1069/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cfb1097c9f1aa4cde36057da26261025f54bcf187da72ec282c84549ffddaf5
+size 267832560

run-8/checkpoint-1069/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6568b67102a14ccdea77a160d6847f01dd51a324819ded071594163de8bb015
+size 535727290

run-8/checkpoint-1069/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3828aaedfc6c27d5fab62906d1f34e3818d39c6910d26a80267c7a1e80e9448a
+size 14244

run-8/checkpoint-1069/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4192fe528a5cf9ca0209185b63d78c8f5090f0d04733fbdf44002f3dee260a6f
+size 1064

run-8/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-8/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-8/checkpoint-1069/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": 0.46994423874863644,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/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,
+      "learning_rate": 9.910767749805447e-06,
+      "loss": 0.5483,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.201832996022102e-06,
+      "loss": 0.4893,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4666273593902588,
+      "eval_matthews_correlation": 0.46994423874863644,
+      "eval_runtime": 0.7045,
+      "eval_samples_per_second": 1480.442,
+      "eval_steps_per_second": 93.681,
+      "step": 1069
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1069,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 37720091767296.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.8619702503588795e-05,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 8,
+    "seed": 23
+  }
+}

run-8/checkpoint-1069/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca90f88161a3b114eb96ba6a890c567afdbf02e037dfbb031a9323ba1018eb1b
+size 4792

runs/Dec23_02-09-17_17d63b357dd6/events.out.tfevents.1703300101.17d63b357dd6.603.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dd3b670c378d33f2ac34ff495437a77c21aee2ac64a29d5879c9fade9d28e85
+size 5349

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46519a6bce092ae403faec562a8ebb7c3b17199d44f00eb39244ebd8bcca25a5
+oid sha256:ca90f88161a3b114eb96ba6a890c567afdbf02e037dfbb031a9323ba1018eb1b
 size 4792