Training in progress, epoch 1, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,47 @@
+{
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float16",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "no_framing",
+    "1": "has_framing"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "has_framing": 1,
+    "no_framing": 0
+  },
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0.0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.13.1",
+  "type_vocab_size": 0,
+  "use_cache": false,
+  "vocab_size": 128100
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8382937490df6137c1fd1d38ba0f2b1b42eb923ae848f769240e5dc21ea8533
+size 368871908

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8ca6d770dc2d0d444d05996b7c6eeaa860981ba26d43183f8a9919dcef2e8b3
+size 737866955

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7e633624ad002c88db2ec0b3f763a06ed8e3232a80fc4851f0a47730b62f4de
+size 14645

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:749320dbe724bd79cb64e03764e4ce7cd007dd9fa3dcc3514dae8ac78750eb22
+size 1465

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": [
+    "[PAD]",
+    "[CLS]",
+    "[SEP]"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_id": 3,
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,75 @@
+{
+  "best_global_step": 2393,
+  "best_metric": 0.0,
+  "best_model_checkpoint": "./results_deberta_framing/checkpoint-2393",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2393,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.20894274968658588,
+      "grad_norm": 7.546875,
+      "learning_rate": 1.8609834238751915e-05,
+      "loss": 0.7753585815429688,
+      "step": 500
+    },
+    {
+      "epoch": 0.41788549937317176,
+      "grad_norm": 2.30859375,
+      "learning_rate": 1.721688257417468e-05,
+      "loss": 0.6949208984375,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6268282490597576,
+      "grad_norm": 0.0870361328125,
+      "learning_rate": 1.5823930909597438e-05,
+      "loss": 0.69367626953125,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8357709987463435,
+      "grad_norm": NaN,
+      "learning_rate": 1.4430979245020198e-05,
+      "loss": 0.6934404907226562,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4597220771079302,
+      "eval_f1": 0.0,
+      "eval_loss": NaN,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_roc_auc": 0.0,
+      "eval_runtime": 329.3943,
+      "eval_samples_per_second": 29.056,
+      "eval_steps_per_second": 1.818,
+      "step": 2393
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7179,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 6497245252899744.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:268a3feca8af97dcf2a4a454060601cea918cf013dc64b3dcf7b37eb81ba5579
+size 5201