Upload folder using huggingface_hub

checkpoints/checkpoint-441/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-441/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4424fd376f8c12cb64903edb78bcbbe88ac3594024681547e376718f7fef224
+size 504150808

checkpoints/checkpoint-441/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f158a60f79497b9d4ac9c9d3c82c451835ced44cc896eb09c1e29a9cf4651f12
+size 1008422138

checkpoints/checkpoint-441/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2b7788af21980be59ded35afc520247185c73280607cac6b80c0ef29a8eee6f
+size 14244

checkpoints/checkpoint-441/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e46fbe07e6a07be6af0af4e0ab6a7672b3522b7af134fd58c6b69c23b5cf4cd
+size 1064

checkpoints/checkpoint-441/trainer_state.json

@@ -0,0 +1,179 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 441,
+  "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
+    },
+    {
+      "epoch": 2.040920716112532,
+      "grad_norm": 93.76717376708984,
+      "learning_rate": 5e-06,
+      "loss": 9.3486,
+      "step": 100
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 9.76750373840332,
+      "eval_normalizer": 95100.0,
+      "eval_runtime": 93.226,
+      "eval_samples_per_second": 573.413,
+      "eval_steps_per_second": 1.126,
+      "step": 147
+    },
+    {
+      "epoch": 3.061381074168798,
+      "grad_norm": 38.99561309814453,
+      "learning_rate": 7.5e-06,
+      "loss": 9.7762,
+      "step": 150
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 9.366472244262695,
+      "eval_normalizer": 94635.0,
+      "eval_runtime": 93.4852,
+      "eval_samples_per_second": 571.823,
+      "eval_steps_per_second": 1.123,
+      "step": 196
+    },
+    {
+      "epoch": 4.081841432225064,
+      "grad_norm": 74.63395690917969,
+      "learning_rate": 1e-05,
+      "loss": 9.173,
+      "step": 200
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 9.328910827636719,
+      "eval_normalizer": 95831.0,
+      "eval_runtime": 93.4873,
+      "eval_samples_per_second": 571.81,
+      "eval_steps_per_second": 1.123,
+      "step": 245
+    },
+    {
+      "epoch": 5.10230179028133,
+      "grad_norm": 48.3079719543457,
+      "learning_rate": 1.25e-05,
+      "loss": 8.6442,
+      "step": 250
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 8.715495109558105,
+      "eval_normalizer": 95552.0,
+      "eval_runtime": 94.2223,
+      "eval_samples_per_second": 567.35,
+      "eval_steps_per_second": 1.114,
+      "step": 294
+    },
+    {
+      "epoch": 6.122762148337596,
+      "grad_norm": 47.34691619873047,
+      "learning_rate": 1.5e-05,
+      "loss": 7.9207,
+      "step": 300
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 8.13585376739502,
+      "eval_normalizer": 95485.0,
+      "eval_runtime": 90.8479,
+      "eval_samples_per_second": 588.423,
+      "eval_steps_per_second": 1.156,
+      "step": 343
+    },
+    {
+      "epoch": 7.143222506393862,
+      "grad_norm": 29.849977493286133,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 7.7923,
+      "step": 350
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 7.713459491729736,
+      "eval_normalizer": 95672.0,
+      "eval_runtime": 92.3012,
+      "eval_samples_per_second": 579.158,
+      "eval_steps_per_second": 1.138,
+      "step": 392
+    },
+    {
+      "epoch": 8.163682864450127,
+      "grad_norm": 22.5938777923584,
+      "learning_rate": 2e-05,
+      "loss": 7.2927,
+      "step": 400
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 8.050180435180664,
+      "eval_normalizer": 94988.0,
+      "eval_runtime": 92.427,
+      "eval_samples_per_second": 578.37,
+      "eval_steps_per_second": 1.136,
+      "step": 441
+    }
+  ],
+  "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": 9.49770612734423e+16,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/checkpoint-441/training_args.bin

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