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 sha256:3bed7f2cfb25e382ac4be9cce65744601ec378c3f71dddba796c6a8d9fd78978
+size 504150808

checkpoints/checkpoint-2088/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46577c0e432e3fe5cc025cb624e4485694b480f490078c10a7e44b1cdcc549bb
+size 1008422138

checkpoints/checkpoint-2088/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5033d675fd9f60560f379155b7c29fc5cda5de86b95aeba02ea66a14f36a2e9
+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": 52.747867584228516,
+      "learning_rate": 2.5e-06,
+      "loss": 10.8165,
+      "step": 50
+    },
+    {
+      "epoch": 0.19134178426213824,
+      "grad_norm": 66.05134582519531,
+      "learning_rate": 5e-06,
+      "loss": 10.054,
+      "step": 100
+    },
+    {
+      "epoch": 0.2870126763932074,
+      "grad_norm": 53.76071548461914,
+      "learning_rate": 7.5e-06,
+      "loss": 9.0799,
+      "step": 150
+    },
+    {
+      "epoch": 0.3826835685242765,
+      "grad_norm": 37.95576477050781,
+      "learning_rate": 1e-05,
+      "loss": 9.0591,
+      "step": 200
+    },
+    {
+      "epoch": 0.4783544606553456,
+      "grad_norm": 44.30142593383789,
+      "learning_rate": 1.25e-05,
+      "loss": 9.0954,
+      "step": 250
+    },
+    {
+      "epoch": 0.5740253527864148,
+      "grad_norm": 44.76091766357422,
+      "learning_rate": 1.5e-05,
+      "loss": 8.2617,
+      "step": 300
+    },
+    {
+      "epoch": 0.6696962449174838,
+      "grad_norm": 36.74516677856445,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 7.6069,
+      "step": 350
+    },
+    {
+      "epoch": 0.765367137048553,
+      "grad_norm": 42.63846206665039,
+      "learning_rate": 2e-05,
+      "loss": 7.278,
+      "step": 400
+    },
+    {
+      "epoch": 0.8610380291796221,
+      "grad_norm": 26.08951759338379,
+      "learning_rate": 2.2499999999999998e-05,
+      "loss": 7.0434,
+      "step": 450
+    },
+    {
+      "epoch": 0.9567089213106912,
+      "grad_norm": 23.093669891357422,
+      "learning_rate": 2.5e-05,
+      "loss": 7.5574,
+      "step": 500
+    },
+    {
+      "epoch": 0.9988041138483617,
+      "eval_accuracy": 0.0,
+      "eval_loss": 7.002418041229248,
+      "eval_normalizer": 94012.0,
+      "eval_runtime": 93.6448,
+      "eval_samples_per_second": 570.849,
+      "eval_steps_per_second": 1.121,
+      "step": 522
+    },
+    {
+      "epoch": 1.0535756995933987,
+      "grad_norm": 21.285545349121094,
+      "learning_rate": 2.75e-05,
+      "loss": 6.9275,
+      "step": 550
+    },
+    {
+      "epoch": 1.1492465917244679,
+      "grad_norm": 33.146881103515625,
+      "learning_rate": 3e-05,
+      "loss": 6.8179,
+      "step": 600
+    },
+    {
+      "epoch": 1.244917483855537,
+      "grad_norm": 28.52762222290039,
+      "learning_rate": 3.2500000000000004e-05,
+      "loss": 5.2322,
+      "step": 650
+    },
+    {
+      "epoch": 1.3405883759866062,
+      "grad_norm": 33.8976936340332,
+      "learning_rate": 3.5000000000000004e-05,
+      "loss": 5.0881,
+      "step": 700
+    },
+    {
+      "epoch": 1.4362592681176751,
+      "grad_norm": 31.849340438842773,
+      "learning_rate": 3.75e-05,
+      "loss": 6.3516,
+      "step": 750
+    },
+    {
+      "epoch": 1.5319301602487443,
+      "grad_norm": 26.819744110107422,
+      "learning_rate": 4e-05,
+      "loss": 5.6243,
+      "step": 800
+    },
+    {
+      "epoch": 1.6276010523798135,
+      "grad_norm": 27.690715789794922,
+      "learning_rate": 4.25e-05,
+      "loss": 5.4867,
+      "step": 850
+    },
+    {
+      "epoch": 1.7232719445108826,
+      "grad_norm": 39.06813430786133,
+      "learning_rate": 4.4999999999999996e-05,
+      "loss": 5.3091,
+      "step": 900
+    },
+    {
+      "epoch": 1.8189428366419516,
+      "grad_norm": 25.289762496948242,
+      "learning_rate": 4.75e-05,
+      "loss": 5.9413,
+      "step": 950
+    },
+    {
+      "epoch": 1.9146137287730207,
+      "grad_norm": 31.576900482177734,
+      "learning_rate": 5e-05,
+      "loss": 6.3911,
+      "step": 1000
+    },
+    {
+      "epoch": 1.9988041138483617,
+      "eval_accuracy": 0.0,
+      "eval_loss": 6.082557201385498,
+      "eval_normalizer": 93558.0,
+      "eval_runtime": 86.1348,
+      "eval_samples_per_second": 620.62,
+      "eval_steps_per_second": 1.219,
+      "step": 1044
+    },
+    {
+      "epoch": 2.0114805070557282,
+      "grad_norm": 36.15195846557617,
+      "learning_rate": 5.25e-05,
+      "loss": 6.4163,
+      "step": 1050
+    },
+    {
+      "epoch": 2.1071513991867974,
+      "grad_norm": 28.969654083251953,
+      "learning_rate": 5.5e-05,
+      "loss": 5.9146,
+      "step": 1100
+    },
+    {
+      "epoch": 2.2028222913178666,
+      "grad_norm": 31.072589874267578,
+      "learning_rate": 5.75e-05,
+      "loss": 4.9223,
+      "step": 1150
+    },
+    {
+      "epoch": 2.2984931834489357,
+      "grad_norm": 33.17365646362305,
+      "learning_rate": 6e-05,
+      "loss": 3.9321,
+      "step": 1200
+    },
+    {
+      "epoch": 2.394164075580005,
+      "grad_norm": 20.012985229492188,
+      "learning_rate": 6.25e-05,
+      "loss": 5.1453,
+      "step": 1250
+    },
+    {
+      "epoch": 2.489834967711074,
+      "grad_norm": 33.7502326965332,
+      "learning_rate": 6.500000000000001e-05,
+      "loss": 4.8,
+      "step": 1300
+    },
+    {
+      "epoch": 2.5855058598421428,
+      "grad_norm": 32.18284225463867,
+      "learning_rate": 6.75e-05,
+      "loss": 4.5708,
+      "step": 1350
+    },
+    {
+      "epoch": 2.6811767519732124,
+      "grad_norm": 26.967090606689453,
+      "learning_rate": 7.000000000000001e-05,
+      "loss": 4.479,
+      "step": 1400
+    },
+    {
+      "epoch": 2.776847644104281,
+      "grad_norm": 21.180952072143555,
+      "learning_rate": 7.25e-05,
+      "loss": 4.847,
+      "step": 1450
+    },
+    {
+      "epoch": 2.8725185362353503,
+      "grad_norm": 34.09960174560547,
+      "learning_rate": 7.5e-05,
+      "loss": 5.2215,
+      "step": 1500
+    },
+    {
+      "epoch": 2.9681894283664194,
+      "grad_norm": 30.934101104736328,
+      "learning_rate": 7.75e-05,
+      "loss": 6.1036,
+      "step": 1550
+    },
+    {
+      "epoch": 2.9988041138483617,
+      "eval_accuracy": 0.0,
+      "eval_loss": 5.322023868560791,
+      "eval_normalizer": 94216.0,
+      "eval_runtime": 101.6167,
+      "eval_samples_per_second": 526.065,
+      "eval_steps_per_second": 1.033,
+      "step": 1566
+    },
+    {
+      "epoch": 3.065056206649127,
+      "grad_norm": 25.038644790649414,
+      "learning_rate": 8e-05,
+      "loss": 5.2087,
+      "step": 1600
+    },
+    {
+      "epoch": 3.160727098780196,
+      "grad_norm": 32.0327033996582,
+      "learning_rate": 8.25e-05,
+      "loss": 5.0918,
+      "step": 1650
+    },
+    {
+      "epoch": 3.2563979909112652,
+      "grad_norm": 33.0177001953125,
+      "learning_rate": 8.5e-05,
+      "loss": 3.4156,
+      "step": 1700
+    },
+    {
+      "epoch": 3.3520688830423344,
+      "grad_norm": 24.040756225585938,
+      "learning_rate": 8.75e-05,
+      "loss": 3.7571,
+      "step": 1750
+    },
+    {
+      "epoch": 3.4477397751734036,
+      "grad_norm": 27.80860710144043,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 4.6411,
+      "step": 1800
+    },
+    {
+      "epoch": 3.5434106673044727,
+      "grad_norm": 25.351137161254883,
+      "learning_rate": 9.25e-05,
+      "loss": 4.0891,
+      "step": 1850
+    },
+    {
+      "epoch": 3.639081559435542,
+      "grad_norm": 25.684823989868164,
+      "learning_rate": 9.5e-05,
+      "loss": 4.0587,
+      "step": 1900
+    },
+    {
+      "epoch": 3.734752451566611,
+      "grad_norm": 24.86536407470703,
+      "learning_rate": 9.750000000000001e-05,
+      "loss": 4.0672,
+      "step": 1950
+    },
+    {
+      "epoch": 3.83042334369768,
+      "grad_norm": 23.63920021057129,
+      "learning_rate": 0.0001,
+      "loss": 4.7268,
+      "step": 2000
+    },
+    {
+      "epoch": 3.926094235828749,
+      "grad_norm": 25.422239303588867,
+      "learning_rate": 0.0001025,
+      "loss": 5.369,
+      "step": 2050
+    },
+    {
+      "epoch": 3.9988041138483617,
+      "eval_accuracy": 0.0,
+      "eval_loss": 4.845930099487305,
+      "eval_normalizer": 93665.0,
+      "eval_runtime": 98.1242,
+      "eval_samples_per_second": 544.789,
+      "eval_steps_per_second": 1.07,
+      "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": 2.3147715914406298e+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 sha256:1dba3751aa7691a086bca0b3920013c2e5e1509ccf2a749a7547f9bd962cdd0d
+size 5432