Training in progress, step 5000, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,84 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24",
+    "25": "LABEL_25"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_25": 25,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:991c75e1099f234f2673cc6436dc0f67f660a1ad937c46162f71a2dde44c4404
+size 498686648

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd68bff05ecee5d2f081107fbc59c0bb48377d7cf4f69c712cde565446148009
+size 997493050

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afb3aa757b5bd4c947379dddad61d23adf2ed5d9383d4fce36e07d65ba927980
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53783de9c17f2448e4c300d68d33ed9aeebddbed03cec656386c1ef893a7684b
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,111 @@
+{
+  "best_metric": 3.28760027885437,
+  "best_model_checkpoint": "/kaggle/working/results/checkpoint-5000",
+  "epoch": 0.3586800573888092,
+  "eval_steps": 5000,
+  "global_step": 5000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.035868005738880916,
+      "grad_norm": 1.1287097930908203,
+      "learning_rate": 0.00019641319942611193,
+      "loss": 3.2489,
+      "step": 500
+    },
+    {
+      "epoch": 0.07173601147776183,
+      "grad_norm": 1.3482087850570679,
+      "learning_rate": 0.00019282639885222382,
+      "loss": 3.2389,
+      "step": 1000
+    },
+    {
+      "epoch": 0.10760401721664276,
+      "grad_norm": 1.3707690238952637,
+      "learning_rate": 0.00018923959827833574,
+      "loss": 3.2339,
+      "step": 1500
+    },
+    {
+      "epoch": 0.14347202295552366,
+      "grad_norm": 1.2300260066986084,
+      "learning_rate": 0.00018565279770444763,
+      "loss": 3.2373,
+      "step": 2000
+    },
+    {
+      "epoch": 0.1793400286944046,
+      "grad_norm": 1.2338874340057373,
+      "learning_rate": 0.00018206599713055954,
+      "loss": 3.2341,
+      "step": 2500
+    },
+    {
+      "epoch": 0.2152080344332855,
+      "grad_norm": 1.14376962184906,
+      "learning_rate": 0.00017847919655667146,
+      "loss": 3.2326,
+      "step": 3000
+    },
+    {
+      "epoch": 0.25107604017216645,
+      "grad_norm": 1.055780053138733,
+      "learning_rate": 0.00017489239598278338,
+      "loss": 3.2295,
+      "step": 3500
+    },
+    {
+      "epoch": 0.28694404591104733,
+      "grad_norm": 1.2641570568084717,
+      "learning_rate": 0.00017130559540889527,
+      "loss": 3.2309,
+      "step": 4000
+    },
+    {
+      "epoch": 0.32281205164992827,
+      "grad_norm": 1.0373996496200562,
+      "learning_rate": 0.0001677187948350072,
+      "loss": 3.2308,
+      "step": 4500
+    },
+    {
+      "epoch": 0.3586800573888092,
+      "grad_norm": 1.0670695304870605,
+      "learning_rate": 0.0001641319942611191,
+      "loss": 3.2285,
+      "step": 5000
+    },
+    {
+      "epoch": 0.3586800573888092,
+      "eval_loss": 3.28760027885437,
+      "eval_runtime": 134.1534,
+      "eval_samples_per_second": 58.142,
+      "eval_steps_per_second": 0.455,
+      "step": 5000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 27880,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 5000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.210684035072e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3b6bb10b1f34645fa9d8bc628b5a8f229a8f09b61b334eafba0471fc1ca9ef1
+size 5240