Upload folder using huggingface_hub

checkpoints/checkpoint-480/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-480/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7502713b520d1d6108a6bfaeff6646fde2a8fa4d456efe17de77174ce5615ed
+size 504150808

checkpoints/checkpoint-480/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b118e71e6535c812c44ace61f784ae54141938656720d526595fe2d23d0dab7
+size 1008422138

checkpoints/checkpoint-480/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccc1ad987286018db9ad51d8c8895b946e5aaec518ff253777862a23ef30ae76
+size 14244

checkpoints/checkpoint-480/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26b55d838e0227d6cf7a6fd51710e303d66d2ff0eaaeea4658dc2e1f1928254f
+size 1064

checkpoints/checkpoint-480/trainer_state.json

@@ -0,0 +1,196 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.797953964194374,
+  "eval_steps": 500,
+  "global_step": 480,
+  "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": 10.375521659851074,
+      "eval_normalizer": 95717.0,
+      "eval_runtime": 88.4075,
+      "eval_samples_per_second": 604.666,
+      "eval_steps_per_second": 1.188,
+      "step": 49
+    },
+    {
+      "epoch": 1.020460358056266,
+      "grad_norm": 102.27652740478516,
+      "learning_rate": 2.5e-06,
+      "loss": 10.7607,
+      "step": 50
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 9.948525428771973,
+      "eval_normalizer": 95497.0,
+      "eval_runtime": 89.95,
+      "eval_samples_per_second": 594.297,
+      "eval_steps_per_second": 1.167,
+      "step": 98
+    },
+    {
+      "epoch": 2.040920716112532,
+      "grad_norm": 93.75347900390625,
+      "learning_rate": 5e-06,
+      "loss": 10.0627,
+      "step": 100
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 9.633269309997559,
+      "eval_normalizer": 95100.0,
+      "eval_runtime": 88.058,
+      "eval_samples_per_second": 607.066,
+      "eval_steps_per_second": 1.192,
+      "step": 147
+    },
+    {
+      "epoch": 3.061381074168798,
+      "grad_norm": 84.73119354248047,
+      "learning_rate": 7.5e-06,
+      "loss": 9.6809,
+      "step": 150
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 9.280492782592773,
+      "eval_normalizer": 94635.0,
+      "eval_runtime": 86.4189,
+      "eval_samples_per_second": 618.58,
+      "eval_steps_per_second": 1.215,
+      "step": 196
+    },
+    {
+      "epoch": 4.081841432225064,
+      "grad_norm": 78.88302612304688,
+      "learning_rate": 1e-05,
+      "loss": 9.3254,
+      "step": 200
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 8.890591621398926,
+      "eval_normalizer": 95831.0,
+      "eval_runtime": 88.325,
+      "eval_samples_per_second": 605.231,
+      "eval_steps_per_second": 1.189,
+      "step": 245
+    },
+    {
+      "epoch": 5.10230179028133,
+      "grad_norm": 70.8497543334961,
+      "learning_rate": 1.25e-05,
+      "loss": 8.917,
+      "step": 250
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 8.414776802062988,
+      "eval_normalizer": 95552.0,
+      "eval_runtime": 86.9696,
+      "eval_samples_per_second": 614.663,
+      "eval_steps_per_second": 1.207,
+      "step": 294
+    },
+    {
+      "epoch": 6.122762148337596,
+      "grad_norm": 62.845542907714844,
+      "learning_rate": 1.5e-05,
+      "loss": 8.4106,
+      "step": 300
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 8.028265953063965,
+      "eval_normalizer": 95485.0,
+      "eval_runtime": 87.803,
+      "eval_samples_per_second": 608.829,
+      "eval_steps_per_second": 1.196,
+      "step": 343
+    },
+    {
+      "epoch": 7.143222506393862,
+      "grad_norm": 59.77174377441406,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 7.8447,
+      "step": 350
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 7.741627216339111,
+      "eval_normalizer": 95672.0,
+      "eval_runtime": 90.4313,
+      "eval_samples_per_second": 591.134,
+      "eval_steps_per_second": 1.161,
+      "step": 392
+    },
+    {
+      "epoch": 8.163682864450127,
+      "grad_norm": 45.9865608215332,
+      "learning_rate": 2e-05,
+      "loss": 7.3547,
+      "step": 400
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 7.572998046875,
+      "eval_normalizer": 94988.0,
+      "eval_runtime": 88.4942,
+      "eval_samples_per_second": 604.073,
+      "eval_steps_per_second": 1.187,
+      "step": 441
+    },
+    {
+      "epoch": 9.184143222506394,
+      "grad_norm": 35.62842559814453,
+      "learning_rate": 2.2499999999999998e-05,
+      "loss": 6.9851,
+      "step": 450
+    },
+    {
+      "epoch": 9.797953964194374,
+      "eval_accuracy": 0.0,
+      "eval_loss": 7.2480034828186035,
+      "eval_normalizer": 95280.0,
+      "eval_runtime": 88.1108,
+      "eval_samples_per_second": 606.702,
+      "eval_steps_per_second": 1.192,
+      "step": 480
+    }
+  ],
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1449062664891392e+17,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/checkpoint-480/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb193080a1694f7c49fa8ccdc5fce0395c84848a774063199a7eae7c12393373
+size 5432