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:d5f9b545b5a9baf1456b4ae3776ed515c0e656d2034cba0a79e387c5de6c2cab
+size 504150808

checkpoints/checkpoint-2088/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f68b2ca630768ce141d263a0bbdd812cdd4b885f933813cd85bc652929ea8cd
+size 1008422138

checkpoints/checkpoint-2088/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41f3448129d496a297c93c2f2f71179772d6474e347f67df83972984d95f2c55
+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": 52.15945816040039,
+      "learning_rate": 2.5e-06,
+      "loss": 10.7426,
+      "step": 50
+    },
+    {
+      "epoch": 0.19134178426213824,
+      "grad_norm": 38.14910125732422,
+      "learning_rate": 5e-06,
+      "loss": 10.0104,
+      "step": 100
+    },
+    {
+      "epoch": 0.2870126763932074,
+      "grad_norm": 39.01994705200195,
+      "learning_rate": 7.5e-06,
+      "loss": 9.6031,
+      "step": 150
+    },
+    {
+      "epoch": 0.3826835685242765,
+      "grad_norm": 33.76708984375,
+      "learning_rate": 1e-05,
+      "loss": 9.1839,
+      "step": 200
+    },
+    {
+      "epoch": 0.4783544606553456,
+      "grad_norm": 35.43233108520508,
+      "learning_rate": 1.25e-05,
+      "loss": 8.7209,
+      "step": 250
+    },
+    {
+      "epoch": 0.5740253527864148,
+      "grad_norm": 29.526994705200195,
+      "learning_rate": 1.5e-05,
+      "loss": 8.2324,
+      "step": 300
+    },
+    {
+      "epoch": 0.6696962449174838,
+      "grad_norm": 35.25413131713867,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 7.7545,
+      "step": 350
+    },
+    {
+      "epoch": 0.765367137048553,
+      "grad_norm": 40.43191909790039,
+      "learning_rate": 2e-05,
+      "loss": 7.3315,
+      "step": 400
+    },
+    {
+      "epoch": 0.8610380291796221,
+      "grad_norm": 30.023365020751953,
+      "learning_rate": 2.2499999999999998e-05,
+      "loss": 6.963,
+      "step": 450
+    },
+    {
+      "epoch": 0.9567089213106912,
+      "grad_norm": 31.878944396972656,
+      "learning_rate": 2.5e-05,
+      "loss": 6.7297,
+      "step": 500
+    },
+    {
+      "epoch": 0.9988041138483617,
+      "eval_accuracy": 0.0,
+      "eval_loss": 6.555630207061768,
+      "eval_normalizer": 94012.0,
+      "eval_runtime": 80.2813,
+      "eval_samples_per_second": 665.871,
+      "eval_steps_per_second": 1.308,
+      "step": 522
+    },
+    {
+      "epoch": 1.0535756995933987,
+      "grad_norm": 23.939258575439453,
+      "learning_rate": 2.75e-05,
+      "loss": 6.5661,
+      "step": 550
+    },
+    {
+      "epoch": 1.1492465917244679,
+      "grad_norm": 28.73314666748047,
+      "learning_rate": 3e-05,
+      "loss": 6.4297,
+      "step": 600
+    },
+    {
+      "epoch": 1.244917483855537,
+      "grad_norm": 25.804365158081055,
+      "learning_rate": 3.2500000000000004e-05,
+      "loss": 6.3161,
+      "step": 650
+    },
+    {
+      "epoch": 1.3405883759866062,
+      "grad_norm": 28.974842071533203,
+      "learning_rate": 3.5000000000000004e-05,
+      "loss": 6.231,
+      "step": 700
+    },
+    {
+      "epoch": 1.4362592681176751,
+      "grad_norm": 30.538211822509766,
+      "learning_rate": 3.75e-05,
+      "loss": 6.1787,
+      "step": 750
+    },
+    {
+      "epoch": 1.5319301602487443,
+      "grad_norm": 22.466585159301758,
+      "learning_rate": 4e-05,
+      "loss": 6.1109,
+      "step": 800
+    },
+    {
+      "epoch": 1.6276010523798135,
+      "grad_norm": 25.896324157714844,
+      "learning_rate": 4.25e-05,
+      "loss": 6.0128,
+      "step": 850
+    },
+    {
+      "epoch": 1.7232719445108826,
+      "grad_norm": 26.904653549194336,
+      "learning_rate": 4.4999999999999996e-05,
+      "loss": 5.9551,
+      "step": 900
+    },
+    {
+      "epoch": 1.8189428366419516,
+      "grad_norm": 26.616758346557617,
+      "learning_rate": 4.75e-05,
+      "loss": 5.8732,
+      "step": 950
+    },
+    {
+      "epoch": 1.9146137287730207,
+      "grad_norm": 30.21148109436035,
+      "learning_rate": 5e-05,
+      "loss": 5.7962,
+      "step": 1000
+    },
+    {
+      "epoch": 1.9988041138483617,
+      "eval_accuracy": 0.0,
+      "eval_loss": 5.6822733879089355,
+      "eval_normalizer": 93558.0,
+      "eval_runtime": 78.5931,
+      "eval_samples_per_second": 680.174,
+      "eval_steps_per_second": 1.336,
+      "step": 1044
+    },
+    {
+      "epoch": 2.0114805070557282,
+      "grad_norm": 29.994068145751953,
+      "learning_rate": 5.25e-05,
+      "loss": 5.7392,
+      "step": 1050
+    },
+    {
+      "epoch": 2.1071513991867974,
+      "grad_norm": 35.065006256103516,
+      "learning_rate": 5.5e-05,
+      "loss": 5.6481,
+      "step": 1100
+    },
+    {
+      "epoch": 2.2028222913178666,
+      "grad_norm": 37.09373092651367,
+      "learning_rate": 5.75e-05,
+      "loss": 5.5441,
+      "step": 1150
+    },
+    {
+      "epoch": 2.2984931834489357,
+      "grad_norm": 32.272159576416016,
+      "learning_rate": 6e-05,
+      "loss": 5.4931,
+      "step": 1200
+    },
+    {
+      "epoch": 2.394164075580005,
+      "grad_norm": 27.136716842651367,
+      "learning_rate": 6.25e-05,
+      "loss": 5.4324,
+      "step": 1250
+    },
+    {
+      "epoch": 2.489834967711074,
+      "grad_norm": 28.377527236938477,
+      "learning_rate": 6.500000000000001e-05,
+      "loss": 5.3281,
+      "step": 1300
+    },
+    {
+      "epoch": 2.5855058598421428,
+      "grad_norm": 25.35126495361328,
+      "learning_rate": 6.75e-05,
+      "loss": 5.2737,
+      "step": 1350
+    },
+    {
+      "epoch": 2.6811767519732124,
+      "grad_norm": 27.91370964050293,
+      "learning_rate": 7.000000000000001e-05,
+      "loss": 5.1901,
+      "step": 1400
+    },
+    {
+      "epoch": 2.776847644104281,
+      "grad_norm": 24.87859344482422,
+      "learning_rate": 7.25e-05,
+      "loss": 5.141,
+      "step": 1450
+    },
+    {
+      "epoch": 2.8725185362353503,
+      "grad_norm": 27.901790618896484,
+      "learning_rate": 7.5e-05,
+      "loss": 5.0599,
+      "step": 1500
+    },
+    {
+      "epoch": 2.9681894283664194,
+      "grad_norm": 25.183063507080078,
+      "learning_rate": 7.75e-05,
+      "loss": 5.034,
+      "step": 1550
+    },
+    {
+      "epoch": 2.9988041138483617,
+      "eval_accuracy": 0.0,
+      "eval_loss": 4.937503337860107,
+      "eval_normalizer": 94216.0,
+      "eval_runtime": 75.5016,
+      "eval_samples_per_second": 708.024,
+      "eval_steps_per_second": 1.391,
+      "step": 1566
+    },
+    {
+      "epoch": 3.065056206649127,
+      "grad_norm": 26.59418487548828,
+      "learning_rate": 8e-05,
+      "loss": 4.9628,
+      "step": 1600
+    },
+    {
+      "epoch": 3.160727098780196,
+      "grad_norm": 25.259281158447266,
+      "learning_rate": 8.25e-05,
+      "loss": 4.9004,
+      "step": 1650
+    },
+    {
+      "epoch": 3.2563979909112652,
+      "grad_norm": 25.84400749206543,
+      "learning_rate": 8.5e-05,
+      "loss": 4.8452,
+      "step": 1700
+    },
+    {
+      "epoch": 3.3520688830423344,
+      "grad_norm": 25.52320671081543,
+      "learning_rate": 8.75e-05,
+      "loss": 4.7968,
+      "step": 1750
+    },
+    {
+      "epoch": 3.4477397751734036,
+      "grad_norm": 26.29749298095703,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 4.7601,
+      "step": 1800
+    },
+    {
+      "epoch": 3.5434106673044727,
+      "grad_norm": 27.535959243774414,
+      "learning_rate": 9.25e-05,
+      "loss": 4.7155,
+      "step": 1850
+    },
+    {
+      "epoch": 3.639081559435542,
+      "grad_norm": 23.676984786987305,
+      "learning_rate": 9.5e-05,
+      "loss": 4.6651,
+      "step": 1900
+    },
+    {
+      "epoch": 3.734752451566611,
+      "grad_norm": 22.59883689880371,
+      "learning_rate": 9.750000000000001e-05,
+      "loss": 4.6527,
+      "step": 1950
+    },
+    {
+      "epoch": 3.83042334369768,
+      "grad_norm": 21.733461380004883,
+      "learning_rate": 0.0001,
+      "loss": 4.616,
+      "step": 2000
+    },
+    {
+      "epoch": 3.926094235828749,
+      "grad_norm": 25.904829025268555,
+      "learning_rate": 0.0001025,
+      "loss": 4.5769,
+      "step": 2050
+    },
+    {
+      "epoch": 3.9988041138483617,
+      "eval_accuracy": 0.0,
+      "eval_loss": 4.510604381561279,
+      "eval_normalizer": 93665.0,
+      "eval_runtime": 76.2941,
+      "eval_samples_per_second": 700.67,
+      "eval_steps_per_second": 1.376,
+      "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": 3.308487200434422e+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 sha256:24a7da9fd672d10200544391c3e51faa9174aebcae93fda1b807e8cae1690006
+size 5368