Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18a98a0236a29d3b4d9e10e45a5ab64e5fcb720807f133fb528b9ece986c0090
+oid sha256:f3af3360eb07f988be802e50844e65238f892c0c25140a8710cdc4a6b3ce8777
 size 498625128

run-2/checkpoint-2252/config.json

@@ -0,0 +1,44 @@
+{
+  "_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"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
+  "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": "4.47.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

run-2/checkpoint-2252/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3af3360eb07f988be802e50844e65238f892c0c25140a8710cdc4a6b3ce8777
+size 498625128

run-2/checkpoint-2252/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33f12e8d1717c5b899c75fa812aa00a8acb0bc0a1464b62a7afb52f2480dbf78
+size 997370106

run-2/checkpoint-2252/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c12ed69c86e794797a0b1de6c0630e157810b87167e91afae46f31f0a4ae43d
+size 14244

run-2/checkpoint-2252/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b9ef4caa9fab23c06601a91477ff795d3bad427df8a8549689178f48d3f4118
+size 1064

run-2/checkpoint-2252/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

run-2/checkpoint-2252/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

run-2/checkpoint-2252/trainer_state.json

@@ -0,0 +1,102 @@
+{
+  "best_metric": 0.6208587338139933,
+  "best_model_checkpoint": "students_scores_model/run-2/checkpoint-1126",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 2252,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8880994671403197,
+      "grad_norm": 7.292171478271484,
+      "learning_rate": 3.526354733861817e-05,
+      "loss": 1.0895,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.5011171601790574,
+      "eval_loss": 1.1365867853164673,
+      "eval_runtime": 37.7018,
+      "eval_samples_per_second": 59.679,
+      "eval_steps_per_second": 7.48,
+      "step": 563
+    },
+    {
+      "epoch": 1.7761989342806395,
+      "grad_norm": 11.239688873291016,
+      "learning_rate": 2.764723041883023e-05,
+      "loss": 0.8974,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.6208587338139933,
+      "eval_loss": 0.8815694451332092,
+      "eval_runtime": 37.5893,
+      "eval_samples_per_second": 59.857,
+      "eval_steps_per_second": 7.502,
+      "step": 1126
+    },
+    {
+      "epoch": 2.664298401420959,
+      "grad_norm": 12.65758991241455,
+      "learning_rate": 2.003091349904229e-05,
+      "loss": 0.7725,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.5950155132637635,
+      "eval_loss": 0.9455859661102295,
+      "eval_runtime": 37.7615,
+      "eval_samples_per_second": 59.585,
+      "eval_steps_per_second": 7.468,
+      "step": 1689
+    },
+    {
+      "epoch": 3.552397868561279,
+      "grad_norm": 15.075959205627441,
+      "learning_rate": 1.2414596579254345e-05,
+      "loss": 0.6214,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.610500685281775,
+      "eval_loss": 1.0504252910614014,
+      "eval_runtime": 37.6588,
+      "eval_samples_per_second": 59.747,
+      "eval_steps_per_second": 7.488,
+      "step": 2252
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2815,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 8412751900993536.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.2879864258406114e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "weight_decay": 0.060543241151812754
+  }
+}

run-2/checkpoint-2252/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07844380fb9421e367e0fe8c8cfeb6356de89708d1d3002c9565a87a48709fa1
+size 5368

runs/Dec08_13-30-03_3b937233628b/events.out.tfevents.1733669115.3b937233628b.23.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82cb54b757afa2352c764f3f54f42bff0a7b2f77c4a50d1376e6d4102004b6ed
-size 6938
+oid sha256:17fc49ebc7cb40d21e7387a353571581676725c777056c558131b94d3f73f436
+size 7466