Upload folder using huggingface_hub

checkpoints/checkpoint-1150/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-1150/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a63a7aaacb78738e33f88838c761ab34ec41a1acf9785c9072d4d6552c755c49
+size 504150808

checkpoints/checkpoint-1150/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70d34b2b252bf9828e1845772491ea9b11c68900045d33123d286e97f0f41e05
+size 1008422138

checkpoints/checkpoint-1150/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cffe30b4973ab3c5219ac84152ce542de04ea5ee05dd61b1948b25af2c4abf6
+size 14244

checkpoints/checkpoint-1150/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a270807dd8bca0c5558ff423b2cda25f4e01efbcb772cd80538e335a7dd36e7f
+size 1064

checkpoints/checkpoint-1150/trainer_state.json

@@ -0,0 +1,214 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.998697351280938,
+  "eval_steps": 500,
+  "global_step": 1150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08684324793747286,
+      "grad_norm": 119.13929748535156,
+      "learning_rate": 2.5e-06,
+      "loss": 10.2285,
+      "step": 50
+    },
+    {
+      "epoch": 0.17368649587494572,
+      "grad_norm": 69.53515625,
+      "learning_rate": 5e-06,
+      "loss": 7.8282,
+      "step": 100
+    },
+    {
+      "epoch": 0.26052974381241856,
+      "grad_norm": 38.81575393676758,
+      "learning_rate": 7.5e-06,
+      "loss": 6.1856,
+      "step": 150
+    },
+    {
+      "epoch": 0.34737299174989145,
+      "grad_norm": 35.44122314453125,
+      "learning_rate": 1e-05,
+      "loss": 5.5474,
+      "step": 200
+    },
+    {
+      "epoch": 0.4342162396873643,
+      "grad_norm": 45.1701545715332,
+      "learning_rate": 1.25e-05,
+      "loss": 5.0381,
+      "step": 250
+    },
+    {
+      "epoch": 0.5210594876248371,
+      "grad_norm": 32.618980407714844,
+      "learning_rate": 1.5e-05,
+      "loss": 4.6559,
+      "step": 300
+    },
+    {
+      "epoch": 0.60790273556231,
+      "grad_norm": 27.301441192626953,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 4.2472,
+      "step": 350
+    },
+    {
+      "epoch": 0.6947459834997829,
+      "grad_norm": 20.96350860595703,
+      "learning_rate": 2e-05,
+      "loss": 3.888,
+      "step": 400
+    },
+    {
+      "epoch": 0.7815892314372558,
+      "grad_norm": 21.377185821533203,
+      "learning_rate": 2.2499999999999998e-05,
+      "loss": 3.5698,
+      "step": 450
+    },
+    {
+      "epoch": 0.8684324793747286,
+      "grad_norm": 19.703227996826172,
+      "learning_rate": 2.5e-05,
+      "loss": 3.3225,
+      "step": 500
+    },
+    {
+      "epoch": 0.9552757273122015,
+      "grad_norm": 25.189373016357422,
+      "learning_rate": 2.75e-05,
+      "loss": 3.1904,
+      "step": 550
+    },
+    {
+      "epoch": 0.998697351280938,
+      "eval_accuracy": 0.0,
+      "eval_loss": 6.819223880767822,
+      "eval_normalizer": 136811.0,
+      "eval_runtime": 95.7843,
+      "eval_samples_per_second": 615.445,
+      "eval_steps_per_second": 1.211,
+      "step": 575
+    },
+    {
+      "epoch": 1.0434216239687364,
+      "grad_norm": 24.1675968170166,
+      "learning_rate": 3e-05,
+      "loss": 3.095,
+      "step": 600
+    },
+    {
+      "epoch": 1.1302648719062094,
+      "grad_norm": 18.355623245239258,
+      "learning_rate": 3.2500000000000004e-05,
+      "loss": 2.9629,
+      "step": 650
+    },
+    {
+      "epoch": 1.2171081198436822,
+      "grad_norm": 24.27044677734375,
+      "learning_rate": 3.5000000000000004e-05,
+      "loss": 2.8883,
+      "step": 700
+    },
+    {
+      "epoch": 1.303951367781155,
+      "grad_norm": 17.9877986907959,
+      "learning_rate": 3.75e-05,
+      "loss": 2.8165,
+      "step": 750
+    },
+    {
+      "epoch": 1.390794615718628,
+      "grad_norm": 27.353044509887695,
+      "learning_rate": 4e-05,
+      "loss": 2.7525,
+      "step": 800
+    },
+    {
+      "epoch": 1.4776378636561007,
+      "grad_norm": 22.09605598449707,
+      "learning_rate": 4.25e-05,
+      "loss": 2.6736,
+      "step": 850
+    },
+    {
+      "epoch": 1.5644811115935737,
+      "grad_norm": 21.224653244018555,
+      "learning_rate": 4.4999999999999996e-05,
+      "loss": 2.6135,
+      "step": 900
+    },
+    {
+      "epoch": 1.6513243595310465,
+      "grad_norm": 21.1419620513916,
+      "learning_rate": 4.75e-05,
+      "loss": 2.5637,
+      "step": 950
+    },
+    {
+      "epoch": 1.7381676074685193,
+      "grad_norm": 18.591278076171875,
+      "learning_rate": 5e-05,
+      "loss": 2.4905,
+      "step": 1000
+    },
+    {
+      "epoch": 1.825010855405992,
+      "grad_norm": 19.953432083129883,
+      "learning_rate": 5.25e-05,
+      "loss": 2.4256,
+      "step": 1050
+    },
+    {
+      "epoch": 1.911854103343465,
+      "grad_norm": 18.62944221496582,
+      "learning_rate": 5.5e-05,
+      "loss": 2.3984,
+      "step": 1100
+    },
+    {
+      "epoch": 1.998697351280938,
+      "grad_norm": 19.104263305664062,
+      "learning_rate": 5.75e-05,
+      "loss": 2.3322,
+      "step": 1150
+    },
+    {
+      "epoch": 1.998697351280938,
+      "eval_accuracy": 0.0,
+      "eval_loss": 6.3023457527160645,
+      "eval_normalizer": 136797.0,
+      "eval_runtime": 96.2451,
+      "eval_samples_per_second": 612.499,
+      "eval_steps_per_second": 1.205,
+      "step": 1150
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 5750,
+  "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": 3.698158250535322e+16,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/checkpoint-1150/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2eb3a10fbbc23b7e9459aec997464606f0d6188a9a2dfdf7ab9d2150b17bd3d
+size 5432