Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:140c5c4aae059734bfb29b490fd2cb75dfad163904b5c2036e14995f4d10084a
+oid sha256:4ef26ae5b6f9ca280387a49c5b1acb3127e2250c3cdaa16f8cf379652b10f6f5
 size 267835644

run-4/checkpoint-148/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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-148/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6510cb323181762db4ff0209681e5eb91f54c28f1bb9558ab81128e9a77f1f2
+size 267835644

run-4/checkpoint-148/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:542a38ab811a7a64f05d5d576bba9a27a75cb61f8b62516735b1340d787c7456
+size 535733434

run-4/checkpoint-148/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beeffb808001b0be26f7a73b2a9fe516aeb1406caf37058e8b7199a3634f8a16
+size 14244

run-4/checkpoint-148/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6de64c80e3ed115a0400f2a6a7b5ab019473668ab2f60e8d0943864660deead
+size 1064

run-4/checkpoint-148/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-148/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-148/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.6044520547945206,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-SA/run-4/checkpoint-148",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 148,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5445205479452054,
+      "eval_loss": 0.9511860609054565,
+      "eval_runtime": 3.6019,
+      "eval_samples_per_second": 162.136,
+      "eval_steps_per_second": 10.272,
+      "step": 74
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6044520547945206,
+      "eval_loss": 0.8700098991394043,
+      "eval_runtime": 3.5892,
+      "eval_samples_per_second": 162.709,
+      "eval_steps_per_second": 10.309,
+      "step": 148
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 222,
+  "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": 3.862929244106666e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 64,
+    "seed": 36
+  }
+}

run-4/checkpoint-148/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b68a5a09e11a71eb1659f00decd8865869967c08792fa0c2e48c10d41869ae8d
+size 4984

run-4/checkpoint-222/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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-222/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ef26ae5b6f9ca280387a49c5b1acb3127e2250c3cdaa16f8cf379652b10f6f5
+size 267835644

run-4/checkpoint-222/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d57d99e46e336735617cd28c91bb42653737aad39bb04a1136ac2a4d1a554489
+size 535733434

run-4/checkpoint-222/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42ba44106afb09807ac2b30d216e509bf8f4bb4c5ac602791243620236780b13
+size 14244

run-4/checkpoint-222/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:063e7d3ece0aea633da4ff61b0d2f140adb47f44eaf896520e89617269b350fa
+size 1064

run-4/checkpoint-222/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-222/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-222/trainer_state.json

@@ -0,0 +1,53 @@
+{
+  "best_metric": 0.6301369863013698,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-SA/run-4/checkpoint-222",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 222,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5445205479452054,
+      "eval_loss": 0.9511860609054565,
+      "eval_runtime": 3.6019,
+      "eval_samples_per_second": 162.136,
+      "eval_steps_per_second": 10.272,
+      "step": 74
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6044520547945206,
+      "eval_loss": 0.8700098991394043,
+      "eval_runtime": 3.5892,
+      "eval_samples_per_second": 162.709,
+      "eval_steps_per_second": 10.309,
+      "step": 148
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6301369863013698,
+      "eval_loss": 0.8435251712799072,
+      "eval_runtime": 3.6087,
+      "eval_samples_per_second": 161.831,
+      "eval_steps_per_second": 10.253,
+      "step": 222
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 222,
+  "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": 3.862929244106666e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 64,
+    "seed": 36
+  }
+}

run-4/checkpoint-222/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b68a5a09e11a71eb1659f00decd8865869967c08792fa0c2e48c10d41869ae8d
+size 4984

runs/Apr01_13-09-37_c7a746a4e968/events.out.tfevents.1711979710.c7a746a4e968.35.7

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d391e589b4abdfa97bcefebf58821fc1d6b4ba5c87ce5c288b715c841097bff
-size 4974
+oid sha256:7648a39f994805730bc31c8b3f0587c49fe7ee78215a658ea73879c9cf785e82
+size 5974