Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc3ede66c734389f0826fdf000137557aae2155b9a2d0e77df9406c70d20d3fb
+oid sha256:65d7da0d006186443d46ae59773b7e1cd81d3e1fe5f655e360149d689d877335
 size 267835644

run-1/checkpoint-1170/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-1/checkpoint-1170/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65d7da0d006186443d46ae59773b7e1cd81d3e1fe5f655e360149d689d877335
+size 267835644

run-1/checkpoint-1170/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:026c0279adde3a94b334d8ab448232b6a791d0c951de22c71908bbb05dbe6fce
+size 535733434

run-1/checkpoint-1170/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2147bf77088c2e353db3297e00caa45a715d3e4c44e8b38a6bd32371050df42f
+size 14244

run-1/checkpoint-1170/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cd1e03c582273ad26296758ff0ac819723240c6bae9c788e3933361a64af43c
+size 1064

run-1/checkpoint-1170/special_tokens_map.json

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

run-1/checkpoint-1170/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-1/checkpoint-1170/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.8082191780821918,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-SA/run-1/checkpoint-585",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1170,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.85,
+      "grad_norm": 22.795198440551758,
+      "learning_rate": 1.1916922083973807e-05,
+      "loss": 0.6472,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8082191780821918,
+      "eval_loss": 0.4663033187389374,
+      "eval_runtime": 3.5845,
+      "eval_samples_per_second": 162.924,
+      "eval_steps_per_second": 10.322,
+      "step": 585
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 13.945089340209961,
+      "learning_rate": 3.0236966481724594e-06,
+      "loss": 0.3781,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7876712328767124,
+      "eval_loss": 0.5014212727546692,
+      "eval_runtime": 3.5817,
+      "eval_samples_per_second": 163.05,
+      "eval_steps_per_second": 10.33,
+      "step": 1170
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1170,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 651429105385590.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.081014751977516e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 8,
+    "seed": 35
+  }
+}

run-1/checkpoint-1170/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d668cda970f0e7b58198421b94cd9a12080cecdba47e0c64a8024f78de6495a3
+size 4984

runs/Apr01_13-09-37_c7a746a4e968/events.out.tfevents.1711978760.c7a746a4e968.35.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7fecc420842e6d413532b04f137001a8c9313724fde2d20ba726c70855ea677
-size 5190
+oid sha256:5ebc5faf3e63a274a638f88fe1ce6fb0bd9aaa6bcbb1beea2861703059099042
+size 6078