Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f9fde5fb4feac55e207638aa6954617c7f06648aa0585ff376c05579923bc87
+oid sha256:af1e566937108e24d62038dd47e8b508443926eaad838b5667f24d0105e5b1f9
 size 267835644

run-3/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-3/checkpoint-2338/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af1e566937108e24d62038dd47e8b508443926eaad838b5667f24d0105e5b1f9
+size 267835644

run-3/checkpoint-2338/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ed8ed010bef3b36956f8876e2f819784024f767d87fe39be0223a26fa803038
+size 535733434

run-3/checkpoint-2338/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7daccd3aaa72c0cc79af583be623defd437dca2f05b40eb35036183d881432f
+size 14244

run-3/checkpoint-2338/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0cccd68039d78942d518db8c4038d6f742e6de3ce30c56593e9d302fccf2006
+size 1064

run-3/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-3/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-3/checkpoint-2338/trainer_state.json

@@ -0,0 +1,72 @@
+{
+  "best_metric": 0.8082191780821918,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-SA/run-3/checkpoint-2338",
+  "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": 67.371826171875,
+      "learning_rate": 2.9568390590325436e-05,
+      "loss": 0.7154,
+      "step": 500
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 29.5689697265625,
+      "learning_rate": 2.1524758764883263e-05,
+      "loss": 0.5977,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7756849315068494,
+      "eval_loss": 0.5732079148292542,
+      "eval_runtime": 3.3767,
+      "eval_samples_per_second": 172.951,
+      "eval_steps_per_second": 10.958,
+      "step": 1169
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 6.523064613342285,
+      "learning_rate": 1.3481126939441087e-05,
+      "loss": 0.4226,
+      "step": 1500
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 27.283645629882812,
+      "learning_rate": 5.437495113998911e-06,
+      "loss": 0.3952,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8082191780821918,
+      "eval_loss": 0.6110640168190002,
+      "eval_runtime": 3.3736,
+      "eval_samples_per_second": 173.11,
+      "eval_steps_per_second": 10.968,
+      "step": 2338
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2338,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 633133530754164.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.761202241576761e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 4,
+    "seed": 34
+  }
+}

run-3/checkpoint-2338/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05d9d1105cc4b9bcdf98ecaa311fc178c26eab7b3d8c2383569f6d255249d6fb
+size 4984

runs/Apr02_02-49-58_ef019a3ab26d/events.out.tfevents.1712027448.ef019a3ab26d.26.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c1ff520626ee9658555547e3d5681f2855c21bd0979e0fb16c57f36b6b1130c
-size 5401
+oid sha256:6ed34516ea72e2b7754f815a9e8d4e0679548e5062d31d65bd227da3005cce0b
+size 6500