Upload 7 files

.gitattributes

@@ -16,3 +16,4 @@ notebooks/results/checkpoint-500/rng_state.pth filter=lfs diff=lfs merge=lfs -te
 notebooks/results/checkpoint-500/scheduler.pt filter=lfs diff=lfs merge=lfs -text
 notebooks/results/checkpoint-500/training_args.bin filter=lfs diff=lfs merge=lfs -text
 notebooks/results/checkpoint-500/optimizer.pt filter=lfs diff=lfs merge=lfs -text
+optimizer.pt filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,26 @@
+{
+  "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": "4.51.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3a56cbfa62fb1546a0efc5c4204eaca9c45d3d1eacf4ac30c1d54c59df17d97
+size 437958648

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d55a2992e8ded638eaa281302a9c17000bab30d50c5f8af0a8e2c9872ec09115
+size 876033163

trainer_state.json

@@ -0,0 +1,174 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.2795905310300704,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06397952655150352,
+      "grad_norm": 5.188015460968018,
+      "learning_rate": 4.8944337811900195e-05,
+      "loss": 0.5162,
+      "step": 100
+    },
+    {
+      "epoch": 0.12795905310300704,
+      "grad_norm": 8.62886905670166,
+      "learning_rate": 4.7878012369375135e-05,
+      "loss": 0.4123,
+      "step": 200
+    },
+    {
+      "epoch": 0.19193857965451055,
+      "grad_norm": 6.661285877227783,
+      "learning_rate": 4.681168692685008e-05,
+      "loss": 0.4106,
+      "step": 300
+    },
+    {
+      "epoch": 0.2559181062060141,
+      "grad_norm": 7.992310523986816,
+      "learning_rate": 4.5745361484325014e-05,
+      "loss": 0.3619,
+      "step": 400
+    },
+    {
+      "epoch": 0.3198976327575176,
+      "grad_norm": 8.48903751373291,
+      "learning_rate": 4.467903604179996e-05,
+      "loss": 0.3724,
+      "step": 500
+    },
+    {
+      "epoch": 0.3838771593090211,
+      "grad_norm": 7.3620219230651855,
+      "learning_rate": 4.3612710599274906e-05,
+      "loss": 0.3582,
+      "step": 600
+    },
+    {
+      "epoch": 0.44785668586052463,
+      "grad_norm": 7.127757549285889,
+      "learning_rate": 4.254638515674984e-05,
+      "loss": 0.351,
+      "step": 700
+    },
+    {
+      "epoch": 0.5118362124120281,
+      "grad_norm": 8.284778594970703,
+      "learning_rate": 4.1480059714224785e-05,
+      "loss": 0.3517,
+      "step": 800
+    },
+    {
+      "epoch": 0.5758157389635317,
+      "grad_norm": 6.389641284942627,
+      "learning_rate": 4.0413734271699725e-05,
+      "loss": 0.3197,
+      "step": 900
+    },
+    {
+      "epoch": 0.6397952655150352,
+      "grad_norm": 8.652924537658691,
+      "learning_rate": 3.9347408829174664e-05,
+      "loss": 0.3457,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7037747920665387,
+      "grad_norm": 9.87730598449707,
+      "learning_rate": 3.828108338664961e-05,
+      "loss": 0.3152,
+      "step": 1100
+    },
+    {
+      "epoch": 0.7677543186180422,
+      "grad_norm": 9.235931396484375,
+      "learning_rate": 3.721475794412455e-05,
+      "loss": 0.3312,
+      "step": 1200
+    },
+    {
+      "epoch": 0.8317338451695457,
+      "grad_norm": 8.75272274017334,
+      "learning_rate": 3.614843250159949e-05,
+      "loss": 0.3098,
+      "step": 1300
+    },
+    {
+      "epoch": 0.8957133717210493,
+      "grad_norm": 3.6930184364318848,
+      "learning_rate": 3.508210705907443e-05,
+      "loss": 0.3057,
+      "step": 1400
+    },
+    {
+      "epoch": 0.9596928982725528,
+      "grad_norm": 15.71256160736084,
+      "learning_rate": 3.4015781616549375e-05,
+      "loss": 0.2994,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0236724248240563,
+      "grad_norm": 10.11008071899414,
+      "learning_rate": 3.2949456174024315e-05,
+      "loss": 0.2945,
+      "step": 1600
+    },
+    {
+      "epoch": 1.0876519513755598,
+      "grad_norm": 1.052371859550476,
+      "learning_rate": 3.1883130731499254e-05,
+      "loss": 0.2072,
+      "step": 1700
+    },
+    {
+      "epoch": 1.1516314779270633,
+      "grad_norm": 0.17214666306972504,
+      "learning_rate": 3.08168052889742e-05,
+      "loss": 0.1915,
+      "step": 1800
+    },
+    {
+      "epoch": 1.2156110044785668,
+      "grad_norm": 3.5573925971984863,
+      "learning_rate": 2.9750479846449137e-05,
+      "loss": 0.2268,
+      "step": 1900
+    },
+    {
+      "epoch": 1.2795905310300704,
+      "grad_norm": 12.984672546386719,
+      "learning_rate": 2.868415440392408e-05,
+      "loss": 0.1639,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 4689,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2104362220769280.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}