Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb613738e3ffdeb001374669941f1252a00de402f496459f82b20ed8886589ca
+oid sha256:1bd42efb6c1df87eb67fba8dd169e304d7a068a2256c29f404080fe4287462d4
 size 437958648

run-3/checkpoint-1684/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-3/checkpoint-1684/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bd42efb6c1df87eb67fba8dd169e304d7a068a2256c29f404080fe4287462d4
+size 437958648

run-3/checkpoint-1684/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2724c9dd6613bb713ec84179bf6faa0be276a2a3d5d92bd29d54a25e1b1e7c39
+size 876038394

run-3/checkpoint-1684/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5660e635558b6960a8447d134cce334e7f40eaf3a25c750629b8fc50d5b25497
+size 14244

run-3/checkpoint-1684/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd8c04df753493626e075070cad4d8e5755befc63407ee6f7f157cf158bd86a1
+size 1064

run-3/checkpoint-1684/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-1684/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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-1684/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": 0.8899082568807339,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-sst2/run-3/checkpoint-1684",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1684,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.637521743774414,
+      "learning_rate": 3.0568943955117345e-06,
+      "loss": 0.5094,
+      "step": 500
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 104.65070343017578,
+      "learning_rate": 2.721119527814927e-06,
+      "loss": 0.4332,
+      "step": 1000
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.10155901312828064,
+      "learning_rate": 2.3853446601181197e-06,
+      "loss": 0.4318,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8899082568807339,
+      "eval_loss": 0.4135288596153259,
+      "eval_runtime": 2.3891,
+      "eval_samples_per_second": 364.998,
+      "eval_steps_per_second": 23.022,
+      "step": 1684
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5052,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 74152095398880.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.3926692632085418e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 4,
+    "seed": 6
+  }
+}

run-3/checkpoint-1684/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cce3c6e72492bb7c1a4c484b82ee3bdab0e12eac30e90df01d84b713c962136
+size 4920

runs/Mar03_17-42-01_90708aaa767a/events.out.tfevents.1709492526.90708aaa767a.21824.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2478cec815b646343ccb87a8de41be42f1d5e465ce798ec753f35768f7f8766
+size 5790

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3c310707a9a9b300e8afc3494c59ee9399bd8e941233ac893f5f90c0f97df1e
+oid sha256:0cce3c6e72492bb7c1a4c484b82ee3bdab0e12eac30e90df01d84b713c962136
 size 4920