Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cb3a26e85018632decd6421f23560a7ef361c476e49109703693fa333bce090
+oid sha256:c7990e33fa8b696609893e535a2f57fb904b216de13b4775c66d8ed0932dc14c
 size 498625128

run-1/checkpoint-1128/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-1/checkpoint-1128/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7990e33fa8b696609893e535a2f57fb904b216de13b4775c66d8ed0932dc14c
+size 498625128

run-1/checkpoint-1128/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dba389666a1538a58cab9c12a95eeeeeb5f4e71cb91ca95fdce47e6e6e2a545d
+size 997370106

run-1/checkpoint-1128/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81d6a1dffb064ed48c4254c80b08b7da5ab5232ebd58ed9b594f634b5b8cc850
+size 14244

run-1/checkpoint-1128/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ff2d40c223213c363127db4770730073a9d8a9eb7817acc6eb31d3bab5782f5
+size 1064

run-1/checkpoint-1128/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-1/checkpoint-1128/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-1/checkpoint-1128/trainer_state.json

@@ -0,0 +1,88 @@
+{
+  "best_metric": 0.6285243252934658,
+  "best_model_checkpoint": "students_scores_model/run-1/checkpoint-1128",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1128,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.5135559583730447,
+      "eval_loss": 1.0615456104278564,
+      "eval_runtime": 37.678,
+      "eval_samples_per_second": 59.716,
+      "eval_steps_per_second": 7.484,
+      "step": 282
+    },
+    {
+      "epoch": 1.773049645390071,
+      "grad_norm": 11.819360733032227,
+      "learning_rate": 8.537794225405964e-06,
+      "loss": 1.0289,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.5853742204012189,
+      "eval_loss": 0.9459031224250793,
+      "eval_runtime": 37.7163,
+      "eval_samples_per_second": 59.656,
+      "eval_steps_per_second": 7.477,
+      "step": 564
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.6179112498233506,
+      "eval_loss": 0.8894566893577576,
+      "eval_runtime": 37.6552,
+      "eval_samples_per_second": 59.753,
+      "eval_steps_per_second": 7.489,
+      "step": 846
+    },
+    {
+      "epoch": 3.546099290780142,
+      "grad_norm": 19.25679588317871,
+      "learning_rate": 3.8466984971609285e-06,
+      "loss": 0.8051,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.6285243252934658,
+      "eval_loss": 0.8603602647781372,
+      "eval_runtime": 37.769,
+      "eval_samples_per_second": 59.573,
+      "eval_steps_per_second": 7.466,
+      "step": 1128
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1410,
+  "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": 8400122116761600.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.3228889953650998e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "weight_decay": 0.0004860339799795757
+  }
+}

run-1/checkpoint-1128/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b6c0e80228b83305d52c2ecaa5e9378ae485930e09ca765409ad7f4e4465fdb
+size 5368

runs/Dec08_13-30-03_3b937233628b/events.out.tfevents.1733666403.3b937233628b.23.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ff516a0691054546aba5c5512cefd442aa18818efb6bc61e26b2b2d76ade055
-size 6517
+oid sha256:f6c060003c03fac1eda412c178b7f9917436d7fd9bc32116fede3618fdcf3bc8
+size 7045