Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbf6f5bf5dd623eec815f7c63a7124ed6b88ebb334825d7b5c3a31ac2b8412b0
+oid sha256:fc61f32feaa64d61e7c15e0bcfe16cf3db40ea5bb5b7e2ee1888cbea7246b7e5
 size 498625128

run-3/checkpoint-1689/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23cdc65134c4067fdbacc7b8a8d9ae754d8a8a51da1de03e4f6d00b56054f751
+oid sha256:9dd029f5704e9b25cfa87f606538e427a2201a505c3cf4c5f5375f7bbeae1e03
 size 997370106

run-3/checkpoint-1689/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68f1d83a24dea24b3ee8fe08ca2d8c2be0524aab6848d54221b60f93a60135a4
+oid sha256:071c5e9be8c89f7e7601ef6e67c044701f3e899071b5431a452dcbeb2c3af0a4
 size 14244

run-4/checkpoint-563/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-4/checkpoint-563/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc61f32feaa64d61e7c15e0bcfe16cf3db40ea5bb5b7e2ee1888cbea7246b7e5
+size 498625128

run-4/checkpoint-563/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50c36f4422c9c2e637df2b6be2fbcefde2849645373189cbffcfdb3058bba94c
+size 997370106

run-4/checkpoint-563/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49348fa43bd53147898b45d0b95d766e80d34cb0478edbfadb78cb95f3ed5edb
+size 14244

run-4/checkpoint-563/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f99020927996d37b0cf8d2bcee476ef4a66b6fd93a6119be58efba10b9fbf4a
+size 1064

run-4/checkpoint-563/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-4/checkpoint-563/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-4/checkpoint-563/trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": 0.5337342004113407,
+  "best_model_checkpoint": "students_scores_model/run-4/checkpoint-563",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 563,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8880994671403197,
+      "grad_norm": 12.275317192077637,
+      "learning_rate": 1.4598246141554418e-05,
+      "loss": 1.0768,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.5337342004113407,
+      "eval_loss": 1.0920056104660034,
+      "eval_runtime": 37.5701,
+      "eval_samples_per_second": 59.888,
+      "eval_steps_per_second": 7.506,
+      "step": 563
+    }
+  ],
+  "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": 2104964038656000.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.7751215070615847e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "weight_decay": 0.0002884204184667258
+  }
+}

run-4/checkpoint-563/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a62e1f6a90ed4f39459c087d00d082ce1ebfa6be7f9d0f437b408dd861a50103
+size 5368

runs/Dec08_21-54-18_6ff5f1d99a72/events.out.tfevents.1733700639.6ff5f1d99a72.23.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73f11de237d874e6c3adb9f25bbc85d2e7613d213346fe6b6a903a5bfe7aaefd
+size 5883

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41cd9f34492133ce5e58fc156e903c1cff1ce7d1d888c589c0adfe36c39998cb
+oid sha256:a62e1f6a90ed4f39459c087d00d082ce1ebfa6be7f9d0f437b408dd861a50103
 size 5368