Upload folder using huggingface_hub

checkpoint-2997/config.json

@@ -0,0 +1,33 @@
+{
+  "_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,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "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": "regression",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-2997/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c96a4c1c5e7487b6e911c08a9dd8ed81e3d85c5d8a1a13ec31318d95483e5211
+size 437955572

checkpoint-2997/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0adcb4c6e3767672d8858138522bf36b83cf8e67ddf80aa3b79745be654ba60
+size 876032250

checkpoint-2997/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15868a90ef3e62ff16238f9b84e62db191fc1cfe5f22ed15683108ead25d7cc7
+size 14244

checkpoint-2997/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcf4ba443321f156cf775f416da09fe5e969b14aea6958b16d75e0e256be6b3c
+size 1064

checkpoint-2997/trainer_state.json

@@ -0,0 +1,140 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 2000,
+  "global_step": 2997,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2002002002002002,
+      "grad_norm": 1.730615258216858,
+      "learning_rate": 4.827407663099758e-05,
+      "loss": 0.1121,
+      "step": 200
+    },
+    {
+      "epoch": 0.4004004004004004,
+      "grad_norm": 2.940678358078003,
+      "learning_rate": 4.482222989299275e-05,
+      "loss": 0.1164,
+      "step": 400
+    },
+    {
+      "epoch": 0.6006006006006006,
+      "grad_norm": 2.0178420543670654,
+      "learning_rate": 4.137038315498792e-05,
+      "loss": 0.1169,
+      "step": 600
+    },
+    {
+      "epoch": 0.8008008008008008,
+      "grad_norm": 3.802590847015381,
+      "learning_rate": 3.791853641698308e-05,
+      "loss": 0.1136,
+      "step": 800
+    },
+    {
+      "epoch": 1.001001001001001,
+      "grad_norm": 2.495525360107422,
+      "learning_rate": 3.446668967897825e-05,
+      "loss": 0.1171,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2012012012012012,
+      "grad_norm": 1.5867379903793335,
+      "learning_rate": 3.101484294097342e-05,
+      "loss": 0.0843,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4014014014014013,
+      "grad_norm": 5.485960960388184,
+      "learning_rate": 2.756299620296859e-05,
+      "loss": 0.0873,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6016016016016015,
+      "grad_norm": 3.2986955642700195,
+      "learning_rate": 2.4111149464963755e-05,
+      "loss": 0.0855,
+      "step": 1600
+    },
+    {
+      "epoch": 1.8018018018018018,
+      "grad_norm": 1.8128502368927002,
+      "learning_rate": 2.0659302726958925e-05,
+      "loss": 0.0843,
+      "step": 1800
+    },
+    {
+      "epoch": 2.002002002002002,
+      "grad_norm": 3.2942447662353516,
+      "learning_rate": 1.720745598895409e-05,
+      "loss": 0.084,
+      "step": 2000
+    },
+    {
+      "epoch": 2.002002002002002,
+      "eval_accuracy": 0.0,
+      "eval_loss": 0.21560150384902954,
+      "eval_runtime": 1.2891,
+      "eval_samples_per_second": 6199.057,
+      "eval_steps_per_second": 96.969,
+      "step": 2000
+    },
+    {
+      "epoch": 2.2022022022022023,
+      "grad_norm": 2.1141810417175293,
+      "learning_rate": 1.375560925094926e-05,
+      "loss": 0.0558,
+      "step": 2200
+    },
+    {
+      "epoch": 2.4024024024024024,
+      "grad_norm": 1.59791100025177,
+      "learning_rate": 1.0303762512944426e-05,
+      "loss": 0.0577,
+      "step": 2400
+    },
+    {
+      "epoch": 2.6026026026026026,
+      "grad_norm": 1.3982253074645996,
+      "learning_rate": 6.8519157749395936e-06,
+      "loss": 0.0579,
+      "step": 2600
+    },
+    {
+      "epoch": 2.8028028028028027,
+      "grad_norm": 2.2633321285247803,
+      "learning_rate": 3.4000690369347603e-06,
+      "loss": 0.0559,
+      "step": 2800
+    }
+  ],
+  "logging_steps": 200,
+  "max_steps": 2997,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 4000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 246379193967870.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2997/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98debd4cd74f325a683625aa96d903d59a8b229450f46a2f15d60b21af34c73c
+size 5176