Upload folder using huggingface_hub

checkpoints/checkpoint-522/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-522/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dfda997f0743ddd9f63ae97d31a82eddd1dc57b4572dba9eaefa8de7e5649a7
+size 504150808

checkpoints/checkpoint-522/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecf7386edfdfbd7fa306f6a9e8904300b02070bc10014c6859da9b688fbdc492
+size 1008422138

checkpoints/checkpoint-522/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ef92370526152e59eaf4d7f98222ff6912a144969e1b6df2d81e2fa935c5890
+size 14244

checkpoints/checkpoint-522/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1994053220917f7e6d6befdf004f4d788fdd3b4921010d1cd29b1ed245442fbc
+size 1064

checkpoints/checkpoint-522/trainer_state.json

@@ -0,0 +1,113 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9988041138483617,
+  "eval_steps": 500,
+  "global_step": 522,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09567089213106912,
+      "grad_norm": 79.64751434326172,
+      "learning_rate": 2.5e-06,
+      "loss": 10.5359,
+      "step": 50
+    },
+    {
+      "epoch": 0.19134178426213824,
+      "grad_norm": 57.142730712890625,
+      "learning_rate": 5e-06,
+      "loss": 9.4534,
+      "step": 100
+    },
+    {
+      "epoch": 0.2870126763932074,
+      "grad_norm": 56.33840560913086,
+      "learning_rate": 7.5e-06,
+      "loss": 8.7762,
+      "step": 150
+    },
+    {
+      "epoch": 0.3826835685242765,
+      "grad_norm": 48.39895248413086,
+      "learning_rate": 1e-05,
+      "loss": 8.0812,
+      "step": 200
+    },
+    {
+      "epoch": 0.4783544606553456,
+      "grad_norm": 51.66913604736328,
+      "learning_rate": 1.25e-05,
+      "loss": 7.4712,
+      "step": 250
+    },
+    {
+      "epoch": 0.5740253527864148,
+      "grad_norm": 39.3389778137207,
+      "learning_rate": 1.5e-05,
+      "loss": 6.9249,
+      "step": 300
+    },
+    {
+      "epoch": 0.6696962449174838,
+      "grad_norm": 42.176029205322266,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 6.3373,
+      "step": 350
+    },
+    {
+      "epoch": 0.765367137048553,
+      "grad_norm": 27.88520622253418,
+      "learning_rate": 2e-05,
+      "loss": 5.8156,
+      "step": 400
+    },
+    {
+      "epoch": 0.8610380291796221,
+      "grad_norm": 27.722829818725586,
+      "learning_rate": 2.2499999999999998e-05,
+      "loss": 5.362,
+      "step": 450
+    },
+    {
+      "epoch": 0.9567089213106912,
+      "grad_norm": 28.680429458618164,
+      "learning_rate": 2.5e-05,
+      "loss": 5.0434,
+      "step": 500
+    },
+    {
+      "epoch": 0.9988041138483617,
+      "eval_accuracy": 0.0,
+      "eval_loss": 8.436083793640137,
+      "eval_normalizer": 94012.0,
+      "eval_runtime": 81.5272,
+      "eval_samples_per_second": 655.695,
+      "eval_steps_per_second": 1.288,
+      "step": 522
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 5220,
+  "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": 1.3743656853651456e+16,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/checkpoint-522/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe7e211af70ccdcbef5785bd97518ac7bfd13ca661e2594863d6da57a849ebea
+size 5432