Upload folder using huggingface_hub

checkpoint-500/config.json

@@ -0,0 +1,51 @@
+{
+  "_num_labels": 5,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.2,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.2,
+  "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"
+  },
+  "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,
+    "LABEL_6": 6
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50000
+}

checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3553fd122e9a40364bc57594951e9ff04765adc45603d302abd16fea2be87e4
+size 497810452

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb1e53bb8a14e44b96235452dfd689e48a53a7e3e113edf46560f2629b99a96c
+size 995741946

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:148a3fdc5876bfae18a12e00df6cb9bf8d6bbbd51548836314c31a3f0ef647bd
+size 14244

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14deba1360ad19266c5f51983463659a359d8ccbee331aadd2d46d79da1ccc46
+size 1064

checkpoint-500/trainer_state.json

@@ -0,0 +1,41 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.042253521126761,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 7.042253521126761,
+      "grad_norm": 2.755331039428711,
+      "learning_rate": 8.286384976525822e-06,
+      "loss": 0.7902,
+      "step": 500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 852,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 12,
+  "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": 520720154188800.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:193a38b3c23b8f3ed8afe7a4ea228c5bf00d6ed7efb5551b242be7d1e5cf7208
+size 5304

checkpoint-852/config.json

@@ -0,0 +1,51 @@
+{
+  "_num_labels": 5,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.2,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.2,
+  "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"
+  },
+  "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,
+    "LABEL_6": 6
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50000
+}

checkpoint-852/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ab01acbfc0300ea663baabc5534a51d060b55d6630e5c772911764f4e85271e
+size 497810452

checkpoint-852/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a9bbe58ef89b511acf4931b7e126f4dfc672f4ef0a0eb0718d51db27bbb4a60
+size 995741946

checkpoint-852/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58ebd43b6555c01058f9d6fee44334ef7c91276dc9a1aca888f3b24ea6134f7c
+size 14244

checkpoint-852/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eb253367271ec99de76f71924a2077b3df1892e0f71e45b5973f1292aa20f32
+size 1064

checkpoint-852/trainer_state.json

@@ -0,0 +1,41 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 12.0,
+  "eval_steps": 500,
+  "global_step": 852,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 7.042253521126761,
+      "grad_norm": 2.755331039428711,
+      "learning_rate": 8.286384976525822e-06,
+      "loss": 0.7902,
+      "step": 500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 852,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 12,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 887250308198400.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-852/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:193a38b3c23b8f3ed8afe7a4ea228c5bf00d6ed7efb5551b242be7d1e5cf7208
+size 5304

config.json

@@ -3,11 +3,11 @@
   "architectures": [
     "BertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
+  "attention_probs_dropout_prob": 0.2,
   "classifier_dropout": null,
   "directionality": "bidi",
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
+  "hidden_dropout_prob": 0.2,
   "hidden_size": 768,
   "id2label": {
     "0": "LABEL_0",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f95b3299c17d4a80c457448fd9274be737c85dffbe3ced09767f802c8b18d88
+oid sha256:8ab01acbfc0300ea663baabc5534a51d060b55d6630e5c772911764f4e85271e
 size 497810452

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2221069c77e27afc03bcc54ad09805a94646dc957f70ef43d2067628af3916fc
+oid sha256:193a38b3c23b8f3ed8afe7a4ea228c5bf00d6ed7efb5551b242be7d1e5cf7208
 size 5304