Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2568e0007836b615d904bf862c49c8b5f05f33a16aa2be19f5f695b93634883
+oid sha256:507bd3c7beab0c0ea26bc5642b0f7c99c4fc15dd058a6d771e2b572986dac1cb
 size 267835644

run-5/checkpoint-2338/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-5/checkpoint-2338/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47786503e71f4b0dc378851ac0c8a430401667adc04c41d7cfd51ea866f5f891
+size 267835644

run-5/checkpoint-2338/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85d6bff66d5e36636494dfb1e95ed1dc2835a4424a56b8b9be0ceff98f1aba47
+size 535733434

run-5/checkpoint-2338/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff3f0bef5ddaaad0103d11c421bbb5e6e8af62c07c0588fdd1039772b9c2fb3c
+size 14308

run-5/checkpoint-2338/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7dfbb434cc38f628c62d4d661433e70ca1c13d43224ed67117e06da33174eb3
+size 1064

run-5/checkpoint-2338/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-2338/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-2338/trainer_state.json

@@ -0,0 +1,72 @@
+{
+  "best_metric": 0.7893835616438356,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-SA/run-5/checkpoint-1169",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 2338,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.43,
+      "grad_norm": 5.201071262359619,
+      "learning_rate": 1.1428870609437754e-05,
+      "loss": 0.706,
+      "step": 500
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.526836633682251,
+      "learning_rate": 9.52849305549067e-06,
+      "loss": 0.5265,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7893835616438356,
+      "eval_loss": 0.5095133185386658,
+      "eval_runtime": 3.5658,
+      "eval_samples_per_second": 163.78,
+      "eval_steps_per_second": 10.376,
+      "step": 1169
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 53.4073600769043,
+      "learning_rate": 7.6281155015435886e-06,
+      "loss": 0.4275,
+      "step": 1500
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 18.367666244506836,
+      "learning_rate": 5.727737947596506e-06,
+      "loss": 0.4062,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7791095890410958,
+      "eval_loss": 0.5382534861564636,
+      "eval_runtime": 3.5769,
+      "eval_samples_per_second": 163.268,
+      "eval_steps_per_second": 10.344,
+      "step": 2338
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3507,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 651755105188110.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.3329248163384835e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 4,
+    "seed": 29
+  }
+}

run-5/checkpoint-2338/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2169875d997fb2cd49501109cfd101c2eb5aaba058ae6185bc1a61c9a68c978a
+size 4984

run-5/checkpoint-3507/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-5/checkpoint-3507/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:507bd3c7beab0c0ea26bc5642b0f7c99c4fc15dd058a6d771e2b572986dac1cb
+size 267835644

run-5/checkpoint-3507/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b42312284d58359ebd0cf7ee6202fbaa141b25022fecb251c0b43116e2764e4
+size 535733434

run-5/checkpoint-3507/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15a6d84d31f5389d0c42fd58a04f1359bb14a0b4558077a206e47bda9b33b4c3
+size 14308

run-5/checkpoint-3507/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2948a4a5e5686bb0780170433cd937dc47201e1aab6546982faa1e885e236e8b
+size 1064

run-5/checkpoint-3507/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-3507/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-3507/trainer_state.json

@@ -0,0 +1,102 @@
+{
+  "best_metric": 0.7893835616438356,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-SA/run-5/checkpoint-1169",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3507,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.43,
+      "grad_norm": 5.201071262359619,
+      "learning_rate": 1.1428870609437754e-05,
+      "loss": 0.706,
+      "step": 500
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.526836633682251,
+      "learning_rate": 9.52849305549067e-06,
+      "loss": 0.5265,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7893835616438356,
+      "eval_loss": 0.5095133185386658,
+      "eval_runtime": 3.5658,
+      "eval_samples_per_second": 163.78,
+      "eval_steps_per_second": 10.376,
+      "step": 1169
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 53.4073600769043,
+      "learning_rate": 7.6281155015435886e-06,
+      "loss": 0.4275,
+      "step": 1500
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 18.367666244506836,
+      "learning_rate": 5.727737947596506e-06,
+      "loss": 0.4062,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7791095890410958,
+      "eval_loss": 0.5382534861564636,
+      "eval_runtime": 3.5769,
+      "eval_samples_per_second": 163.268,
+      "eval_steps_per_second": 10.344,
+      "step": 2338
+    },
+    {
+      "epoch": 2.14,
+      "grad_norm": 4.965297698974609,
+      "learning_rate": 3.827360393649423e-06,
+      "loss": 0.4058,
+      "step": 2500
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 19.966022491455078,
+      "learning_rate": 1.9269828397023416e-06,
+      "loss": 0.2917,
+      "step": 3000
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 25.14493179321289,
+      "learning_rate": 2.6605285755259148e-08,
+      "loss": 0.3059,
+      "step": 3500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7808219178082192,
+      "eval_loss": 0.6381190419197083,
+      "eval_runtime": 3.5897,
+      "eval_samples_per_second": 162.69,
+      "eval_steps_per_second": 10.307,
+      "step": 3507
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3507,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 1140510309116220.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.3329248163384835e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 4,
+    "seed": 29
+  }
+}

run-5/checkpoint-3507/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2169875d997fb2cd49501109cfd101c2eb5aaba058ae6185bc1a61c9a68c978a
+size 4984

runs/Apr01_13-09-37_c7a746a4e968/events.out.tfevents.1711980093.c7a746a4e968.35.8

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75bc919501ceb1366d23aff40f01837af1ef6e753ffbcc89e60c52b70a8e3636
-size 5613
+oid sha256:2bc2b314a7b16b0d1ee82c4e7fa2bb342f93491bbb2270f6444918dddaec6e99
+size 7457