Upload folder using huggingface_hub

checkpoints/checkpoint-2088/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-2088/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3dd0b5a8267d551dec150c110de891072ba428c744f056db3681fc23b9613fa
+size 504150808

checkpoints/checkpoint-2088/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a9b86b065ba7e9798ba2ff2ee3909ad9d97c28fdd1806dc1fb3da288acac7fb
+size 1008422138

checkpoints/checkpoint-2088/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a276f177cdbfc937811ebf01d04865e6c79b3b89a5e4714443f232d96ce2bc1b
+size 14244

checkpoints/checkpoint-2088/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08c2a3f06541ff51e5720c2a22ee8d3732828c83bcce4bd21d6b8f5b4241059b
+size 1064

checkpoints/checkpoint-2088/trainer_state.json

@@ -0,0 +1,360 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.9988041138483617,
+  "eval_steps": 500,
+  "global_step": 2088,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09567089213106912,
+      "grad_norm": 80.18675231933594,
+      "learning_rate": 2.5e-06,
+      "loss": 10.5044,
+      "step": 50
+    },
+    {
+      "epoch": 0.19134178426213824,
+      "grad_norm": 39.69889450073242,
+      "learning_rate": 5e-06,
+      "loss": 10.1248,
+      "step": 100
+    },
+    {
+      "epoch": 0.2870126763932074,
+      "grad_norm": 48.89628601074219,
+      "learning_rate": 7.5e-06,
+      "loss": 9.3749,
+      "step": 150
+    },
+    {
+      "epoch": 0.3826835685242765,
+      "grad_norm": 36.422420501708984,
+      "learning_rate": 1e-05,
+      "loss": 9.3315,
+      "step": 200
+    },
+    {
+      "epoch": 0.4783544606553456,
+      "grad_norm": 39.99179458618164,
+      "learning_rate": 1.25e-05,
+      "loss": 8.4906,
+      "step": 250
+    },
+    {
+      "epoch": 0.5740253527864148,
+      "grad_norm": 31.199922561645508,
+      "learning_rate": 1.5e-05,
+      "loss": 8.4854,
+      "step": 300
+    },
+    {
+      "epoch": 0.6696962449174838,
+      "grad_norm": 34.45671844482422,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 7.6927,
+      "step": 350
+    },
+    {
+      "epoch": 0.765367137048553,
+      "grad_norm": 34.71846008300781,
+      "learning_rate": 2e-05,
+      "loss": 7.6306,
+      "step": 400
+    },
+    {
+      "epoch": 0.8610380291796221,
+      "grad_norm": 24.466449737548828,
+      "learning_rate": 2.2499999999999998e-05,
+      "loss": 7.1092,
+      "step": 450
+    },
+    {
+      "epoch": 0.9567089213106912,
+      "grad_norm": 29.206127166748047,
+      "learning_rate": 2.5e-05,
+      "loss": 7.1294,
+      "step": 500
+    },
+    {
+      "epoch": 0.9988041138483617,
+      "eval_accuracy": 0.0,
+      "eval_loss": 6.6525654792785645,
+      "eval_normalizer": 94012.0,
+      "eval_runtime": 91.0311,
+      "eval_samples_per_second": 587.239,
+      "eval_steps_per_second": 1.153,
+      "step": 522
+    },
+    {
+      "epoch": 1.0535756995933987,
+      "grad_norm": 29.739194869995117,
+      "learning_rate": 2.75e-05,
+      "loss": 6.0131,
+      "step": 550
+    },
+    {
+      "epoch": 1.1492465917244679,
+      "grad_norm": 21.925552368164062,
+      "learning_rate": 3e-05,
+      "loss": 5.6512,
+      "step": 600
+    },
+    {
+      "epoch": 1.244917483855537,
+      "grad_norm": 33.150108337402344,
+      "learning_rate": 3.2500000000000004e-05,
+      "loss": 5.943,
+      "step": 650
+    },
+    {
+      "epoch": 1.3405883759866062,
+      "grad_norm": 20.7436466217041,
+      "learning_rate": 3.5000000000000004e-05,
+      "loss": 5.8118,
+      "step": 700
+    },
+    {
+      "epoch": 1.4362592681176751,
+      "grad_norm": 31.08110809326172,
+      "learning_rate": 3.75e-05,
+      "loss": 6.1599,
+      "step": 750
+    },
+    {
+      "epoch": 1.5319301602487443,
+      "grad_norm": 23.515121459960938,
+      "learning_rate": 4e-05,
+      "loss": 5.7834,
+      "step": 800
+    },
+    {
+      "epoch": 1.6276010523798135,
+      "grad_norm": 28.59242820739746,
+      "learning_rate": 4.25e-05,
+      "loss": 6.3596,
+      "step": 850
+    },
+    {
+      "epoch": 1.7232719445108826,
+      "grad_norm": 23.43410301208496,
+      "learning_rate": 4.4999999999999996e-05,
+      "loss": 5.7949,
+      "step": 900
+    },
+    {
+      "epoch": 1.8189428366419516,
+      "grad_norm": 24.41404914855957,
+      "learning_rate": 4.75e-05,
+      "loss": 6.4384,
+      "step": 950
+    },
+    {
+      "epoch": 1.9146137287730207,
+      "grad_norm": 31.07407569885254,
+      "learning_rate": 5e-05,
+      "loss": 5.7907,
+      "step": 1000
+    },
+    {
+      "epoch": 1.9988041138483617,
+      "eval_accuracy": 0.0,
+      "eval_loss": 5.778665065765381,
+      "eval_normalizer": 93558.0,
+      "eval_runtime": 91.4836,
+      "eval_samples_per_second": 584.335,
+      "eval_steps_per_second": 1.148,
+      "step": 1044
+    },
+    {
+      "epoch": 2.0114805070557282,
+      "grad_norm": 42.43528366088867,
+      "learning_rate": 5.25e-05,
+      "loss": 6.1537,
+      "step": 1050
+    },
+    {
+      "epoch": 2.1071513991867974,
+      "grad_norm": 39.749237060546875,
+      "learning_rate": 5.5e-05,
+      "loss": 3.7061,
+      "step": 1100
+    },
+    {
+      "epoch": 2.2028222913178666,
+      "grad_norm": 34.564781188964844,
+      "learning_rate": 5.75e-05,
+      "loss": 5.7656,
+      "step": 1150
+    },
+    {
+      "epoch": 2.2984931834489357,
+      "grad_norm": 28.75893783569336,
+      "learning_rate": 6e-05,
+      "loss": 4.215,
+      "step": 1200
+    },
+    {
+      "epoch": 2.394164075580005,
+      "grad_norm": 28.530345916748047,
+      "learning_rate": 6.25e-05,
+      "loss": 5.9368,
+      "step": 1250
+    },
+    {
+      "epoch": 2.489834967711074,
+      "grad_norm": 27.216028213500977,
+      "learning_rate": 6.500000000000001e-05,
+      "loss": 4.503,
+      "step": 1300
+    },
+    {
+      "epoch": 2.5855058598421428,
+      "grad_norm": 25.836360931396484,
+      "learning_rate": 6.75e-05,
+      "loss": 5.866,
+      "step": 1350
+    },
+    {
+      "epoch": 2.6811767519732124,
+      "grad_norm": 24.025819778442383,
+      "learning_rate": 7.000000000000001e-05,
+      "loss": 4.8442,
+      "step": 1400
+    },
+    {
+      "epoch": 2.776847644104281,
+      "grad_norm": 23.39544677734375,
+      "learning_rate": 7.25e-05,
+      "loss": 5.6624,
+      "step": 1450
+    },
+    {
+      "epoch": 2.8725185362353503,
+      "grad_norm": 24.322940826416016,
+      "learning_rate": 7.5e-05,
+      "loss": 5.0865,
+      "step": 1500
+    },
+    {
+      "epoch": 2.9681894283664194,
+      "grad_norm": 37.94609069824219,
+      "learning_rate": 7.75e-05,
+      "loss": 5.4643,
+      "step": 1550
+    },
+    {
+      "epoch": 2.9988041138483617,
+      "eval_accuracy": 0.0,
+      "eval_loss": 5.018088340759277,
+      "eval_normalizer": 94216.0,
+      "eval_runtime": 96.045,
+      "eval_samples_per_second": 556.583,
+      "eval_steps_per_second": 1.093,
+      "step": 1566
+    },
+    {
+      "epoch": 3.065056206649127,
+      "grad_norm": 28.081607818603516,
+      "learning_rate": 8e-05,
+      "loss": 3.8771,
+      "step": 1600
+    },
+    {
+      "epoch": 3.160727098780196,
+      "grad_norm": 22.782175064086914,
+      "learning_rate": 8.25e-05,
+      "loss": 4.3213,
+      "step": 1650
+    },
+    {
+      "epoch": 3.2563979909112652,
+      "grad_norm": 29.36810874938965,
+      "learning_rate": 8.5e-05,
+      "loss": 4.2188,
+      "step": 1700
+    },
+    {
+      "epoch": 3.3520688830423344,
+      "grad_norm": 23.439544677734375,
+      "learning_rate": 8.75e-05,
+      "loss": 4.5686,
+      "step": 1750
+    },
+    {
+      "epoch": 3.4477397751734036,
+      "grad_norm": 22.922456741333008,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 4.6034,
+      "step": 1800
+    },
+    {
+      "epoch": 3.5434106673044727,
+      "grad_norm": 20.919992446899414,
+      "learning_rate": 9.25e-05,
+      "loss": 4.5947,
+      "step": 1850
+    },
+    {
+      "epoch": 3.639081559435542,
+      "grad_norm": 23.248443603515625,
+      "learning_rate": 9.5e-05,
+      "loss": 4.9037,
+      "step": 1900
+    },
+    {
+      "epoch": 3.734752451566611,
+      "grad_norm": 26.400527954101562,
+      "learning_rate": 9.750000000000001e-05,
+      "loss": 4.5835,
+      "step": 1950
+    },
+    {
+      "epoch": 3.83042334369768,
+      "grad_norm": 26.001136779785156,
+      "learning_rate": 0.0001,
+      "loss": 5.0425,
+      "step": 2000
+    },
+    {
+      "epoch": 3.926094235828749,
+      "grad_norm": 32.60072326660156,
+      "learning_rate": 0.0001025,
+      "loss": 4.5913,
+      "step": 2050
+    },
+    {
+      "epoch": 3.9988041138483617,
+      "eval_accuracy": 0.0,
+      "eval_loss": 4.604358196258545,
+      "eval_normalizer": 93665.0,
+      "eval_runtime": 97.2823,
+      "eval_samples_per_second": 549.504,
+      "eval_steps_per_second": 1.079,
+      "step": 2088
+    }
+  ],
+  "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": 2.5496492877852672e+17,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/checkpoint-2088/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d9f0446d794d42240d340ea77d064573ec567b5aba425b93f05513801efc856
+size 5432