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 sha256:0b1d2f4fc04c35a35df3c64368ef56adb5df6d816fd9bcea8cea3f92122d365e
+size 504150808

checkpoints/checkpoint-480/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf542ff5a425dbaead13fed82be3db3d40176e598a1d816abdcce8ab80288258
+size 1008422138

checkpoints/checkpoint-480/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:871de3da2d1202e8f50678c5d827c37d41cc37ab477ba423e4cdc9c9bd14bbee
+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": 10.322837829589844,
+      "eval_normalizer": 95717.0,
+      "eval_runtime": 87.7846,
+      "eval_samples_per_second": 608.956,
+      "eval_steps_per_second": 1.196,
+      "step": 49
+    },
+    {
+      "epoch": 1.020460358056266,
+      "grad_norm": 46.59355545043945,
+      "learning_rate": 2.5e-06,
+      "loss": 10.6797,
+      "step": 50
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 9.83644962310791,
+      "eval_normalizer": 95497.0,
+      "eval_runtime": 86.1922,
+      "eval_samples_per_second": 620.207,
+      "eval_steps_per_second": 1.218,
+      "step": 98
+    },
+    {
+      "epoch": 2.040920716112532,
+      "grad_norm": 37.12765121459961,
+      "learning_rate": 5e-06,
+      "loss": 9.9107,
+      "step": 100
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 9.46417236328125,
+      "eval_normalizer": 95100.0,
+      "eval_runtime": 85.1382,
+      "eval_samples_per_second": 627.885,
+      "eval_steps_per_second": 1.233,
+      "step": 147
+    },
+    {
+      "epoch": 3.061381074168798,
+      "grad_norm": 35.19115447998047,
+      "learning_rate": 7.5e-06,
+      "loss": 9.4644,
+      "step": 150
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 9.03406810760498,
+      "eval_normalizer": 94635.0,
+      "eval_runtime": 84.7707,
+      "eval_samples_per_second": 630.607,
+      "eval_steps_per_second": 1.239,
+      "step": 196
+    },
+    {
+      "epoch": 4.081841432225064,
+      "grad_norm": 31.461456298828125,
+      "learning_rate": 1e-05,
+      "loss": 8.9262,
+      "step": 200
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 8.583660125732422,
+      "eval_normalizer": 95831.0,
+      "eval_runtime": 84.8031,
+      "eval_samples_per_second": 630.366,
+      "eval_steps_per_second": 1.238,
+      "step": 245
+    },
+    {
+      "epoch": 5.10230179028133,
+      "grad_norm": 29.246294021606445,
+      "learning_rate": 1.25e-05,
+      "loss": 8.3791,
+      "step": 250
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 8.097399711608887,
+      "eval_normalizer": 95552.0,
+      "eval_runtime": 84.683,
+      "eval_samples_per_second": 631.26,
+      "eval_steps_per_second": 1.24,
+      "step": 294
+    },
+    {
+      "epoch": 6.122762148337596,
+      "grad_norm": 26.726572036743164,
+      "learning_rate": 1.5e-05,
+      "loss": 7.8237,
+      "step": 300
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 7.682345867156982,
+      "eval_normalizer": 95485.0,
+      "eval_runtime": 84.5469,
+      "eval_samples_per_second": 632.276,
+      "eval_steps_per_second": 1.242,
+      "step": 343
+    },
+    {
+      "epoch": 7.143222506393862,
+      "grad_norm": 18.71774673461914,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 7.2912,
+      "step": 350
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 7.393515586853027,
+      "eval_normalizer": 95672.0,
+      "eval_runtime": 84.4083,
+      "eval_samples_per_second": 633.315,
+      "eval_steps_per_second": 1.244,
+      "step": 392
+    },
+    {
+      "epoch": 8.163682864450127,
+      "grad_norm": 28.14803123474121,
+      "learning_rate": 2e-05,
+      "loss": 6.8385,
+      "step": 400
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 7.203690052032471,
+      "eval_normalizer": 94988.0,
+      "eval_runtime": 84.1097,
+      "eval_samples_per_second": 635.563,
+      "eval_steps_per_second": 1.248,
+      "step": 441
+    },
+    {
+      "epoch": 9.184143222506394,
+      "grad_norm": 16.951704025268555,
+      "learning_rate": 2.2499999999999998e-05,
+      "loss": 6.5428,
+      "step": 450
+    },
+    {
+      "epoch": 9.797953964194374,
+      "eval_accuracy": 0.0,
+      "eval_loss": 7.147161483764648,
+      "eval_normalizer": 95280.0,
+      "eval_runtime": 84.3523,
+      "eval_samples_per_second": 633.735,
+      "eval_steps_per_second": 1.245,
+      "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": 1.2262268299959091e+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:c9aafeddeb70594fd32db941f95ee1d7a2daf58027ecc4c0fb9e57ba222b6f1e
+size 5432