Upload folder using huggingface_hub

checkpoints/checkpoint-98/config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "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,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 52000
+}

checkpoints/checkpoint-98/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f8be771c8b00611b3d610f68e3eb9b4c776d737c6db7e844f5d678e4efeb618
+size 504150808

checkpoints/checkpoint-98/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b94679ce7467ca51213802b4310548311c8afe5ea7be53ecc04503ab136da22d
+size 1008422138

checkpoints/checkpoint-98/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c8eefe62090dd925fb87f948ce13b52bda47a73e784e719375b7d981e1a2e84
+size 14244

checkpoints/checkpoint-98/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4f46e3e4d04e99a348dd515e30bd7753a087b31d5bba435c17766fab11ba4c7
+size 1064

checkpoints/checkpoint-98/trainer_state.json

@@ -0,0 +1,60 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 98,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 10.588387489318848,
+      "eval_normalizer": 95717.0,
+      "eval_runtime": 91.4198,
+      "eval_samples_per_second": 584.742,
+      "eval_steps_per_second": 1.149,
+      "step": 49
+    },
+    {
+      "epoch": 1.020460358056266,
+      "grad_norm": 77.02039337158203,
+      "learning_rate": 2.5e-06,
+      "loss": 10.4871,
+      "step": 50
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 10.317421913146973,
+      "eval_normalizer": 95497.0,
+      "eval_runtime": 92.7813,
+      "eval_samples_per_second": 576.162,
+      "eval_steps_per_second": 1.132,
+      "step": 98
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 480,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 1.2610819084867584e+16,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/checkpoint-98/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6db2b7d30557896b8db73563f526aa290bbad6339930dcde51cfab52b2f61e39
+size 5432