Delete checkpoint-5000

checkpoint-5000/config.json

@@ -1,36 +0,0 @@
-{
-  "add_cross_attention": false,
-  "architectures": [
-    "BertForMaskedLM"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": null,
-  "classifier_dropout": null,
-  "directionality": "bidi",
-  "dtype": "float32",
-  "eos_token_id": null,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "is_decoder": false,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 0,
-  "pooler_fc_size": 768,
-  "pooler_num_attention_heads": 12,
-  "pooler_num_fc_layers": 3,
-  "pooler_size_per_head": 128,
-  "pooler_type": "first_token_transform",
-  "position_embedding_type": "absolute",
-  "tie_word_embeddings": false,
-  "transformers_version": "5.0.0",
-  "type_vocab_size": 2,
-  "use_cache": false,
-  "vocab_size": 100000
-}

checkpoint-5000/model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5bfee8b74ebe64a0b6d306d1b36f76b80183e9ed9b764a67adad3c015e072984
-size 959395416

checkpoint-5000/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5a38920cf7cf531672178b2f37763c4599eea3439960ec69e13e352679dfcd19
-size 1918914187

checkpoint-5000/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:afc573ccc492df8ce5717e3abe233952a69bd8cdb6d7a5a0cd81901495f6287f
-size 14645

checkpoint-5000/scaler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5fc6ba6e31f37fe7006edbf8b34f86270af7601875d81c0eb81157bf71d6ce5e
-size 1383

checkpoint-5000/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:46606f43c411b5fe51991e0ff831292c9c3a052ff50cdc18514a34bbb855d6a9
-size 1465

checkpoint-5000/tokenizer_config.json

@@ -1,16 +0,0 @@
-{
-  "backend": "tokenizers",
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": true,
-  "is_local": false,
-  "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
-  "never_split": null,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
-}

checkpoint-5000/trainer_state.json

@@ -1,263 +0,0 @@
-{
-  "best_global_step": 5000,
-  "best_metric": 1.8540898561477661,
-  "best_model_checkpoint": "/kaggle/working/MASRIBERTV4_ckpts/checkpoint-5000",
-  "epoch": 0.4271496305155696,
-  "eval_steps": 500,
-  "global_step": 5000,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.02135748152577848,
-      "grad_norm": 112.14698028564453,
-      "learning_rate": 1.245e-06,
-      "loss": 58.53020703125,
-      "step": 250
-    },
-    {
-      "epoch": 0.04271496305155696,
-      "grad_norm": 94.12735748291016,
-      "learning_rate": 2.4950000000000003e-06,
-      "loss": 49.33264453125,
-      "step": 500
-    },
-    {
-      "epoch": 0.04271496305155696,
-      "eval_loss": 5.498984336853027,
-      "eval_runtime": 1927.5234,
-      "eval_samples_per_second": 40.952,
-      "eval_steps_per_second": 2.56,
-      "step": 500
-    },
-    {
-      "epoch": 0.06407244457733544,
-      "grad_norm": 90.2774658203125,
-      "learning_rate": 3.7449999999999997e-06,
-      "loss": 44.8349609375,
-      "step": 750
-    },
-    {
-      "epoch": 0.08542992610311392,
-      "grad_norm": 95.37772369384766,
-      "learning_rate": 4.9950000000000005e-06,
-      "loss": 42.08175390625,
-      "step": 1000
-    },
-    {
-      "epoch": 0.08542992610311392,
-      "eval_loss": 4.845311641693115,
-      "eval_runtime": 1929.6401,
-      "eval_samples_per_second": 40.907,
-      "eval_steps_per_second": 2.557,
-      "step": 1000
-    },
-    {
-      "epoch": 0.1067874076288924,
-      "grad_norm": 86.53277587890625,
-      "learning_rate": 6.245e-06,
-      "loss": 40.29465234375,
-      "step": 1250
-    },
-    {
-      "epoch": 0.12814488915467087,
-      "grad_norm": 93.83633422851562,
-      "learning_rate": 7.495e-06,
-      "loss": 38.960453125,
-      "step": 1500
-    },
-    {
-      "epoch": 0.12814488915467087,
-      "eval_loss": 4.519171714782715,
-      "eval_runtime": 1928.7805,
-      "eval_samples_per_second": 40.925,
-      "eval_steps_per_second": 2.558,
-      "step": 1500
-    },
-    {
-      "epoch": 0.14950237068044936,
-      "grad_norm": 81.17627716064453,
-      "learning_rate": 8.745e-06,
-      "loss": 37.7989140625,
-      "step": 1750
-    },
-    {
-      "epoch": 0.17085985220622785,
-      "grad_norm": 84.88935089111328,
-      "learning_rate": 9.995e-06,
-      "loss": 36.94516015625,
-      "step": 2000
-    },
-    {
-      "epoch": 0.17085985220622785,
-      "eval_loss": 4.303403854370117,
-      "eval_runtime": 1928.1902,
-      "eval_samples_per_second": 40.938,
-      "eval_steps_per_second": 2.559,
-      "step": 2000
-    },
-    {
-      "epoch": 0.19221733373200633,
-      "grad_norm": 79.1358413696289,
-      "learning_rate": 1.1245e-05,
-      "loss": 36.1753828125,
-      "step": 2250
-    },
-    {
-      "epoch": 0.2135748152577848,
-      "grad_norm": 85.23380279541016,
-      "learning_rate": 1.2495000000000001e-05,
-      "loss": 35.4720703125,
-      "step": 2500
-    },
-    {
-      "epoch": 0.2135748152577848,
-      "eval_loss": 4.146875381469727,
-      "eval_runtime": 1927.7742,
-      "eval_samples_per_second": 40.947,
-      "eval_steps_per_second": 2.559,
-      "step": 2500
-    },
-    {
-      "epoch": 0.23493229678356328,
-      "grad_norm": 40.744110107421875,
-      "learning_rate": 1.3725000000000002e-05,
-      "loss": 17.465578125,
-      "step": 2750
-    },
-    {
-      "epoch": 0.25628977830934174,
-      "grad_norm": 41.063385009765625,
-      "learning_rate": 1.4975e-05,
-      "loss": 17.180029296875,
-      "step": 3000
-    },
-    {
-      "epoch": 0.25628977830934174,
-      "eval_loss": 2.0153398513793945,
-      "eval_runtime": 791.0335,
-      "eval_samples_per_second": 99.788,
-      "eval_steps_per_second": 12.474,
-      "step": 3000
-    },
-    {
-      "epoch": 0.27764725983512023,
-      "grad_norm": 43.8082275390625,
-      "learning_rate": 1.6225e-05,
-      "loss": 16.96137890625,
-      "step": 3250
-    },
-    {
-      "epoch": 0.2990047413608987,
-      "grad_norm": 41.902591705322266,
-      "learning_rate": 1.7475e-05,
-      "loss": 16.6866015625,
-      "step": 3500
-    },
-    {
-      "epoch": 0.2990047413608987,
-      "eval_loss": 1.964239239692688,
-      "eval_runtime": 796.0599,
-      "eval_samples_per_second": 99.158,
-      "eval_steps_per_second": 12.395,
-      "step": 3500
-    },
-    {
-      "epoch": 0.3203622228866772,
-      "grad_norm": 38.828636169433594,
-      "learning_rate": 1.8725e-05,
-      "loss": 16.456845703125,
-      "step": 3750
-    },
-    {
-      "epoch": 0.3417197044124557,
-      "grad_norm": 43.49476623535156,
-      "learning_rate": 1.9975e-05,
-      "loss": 16.399064453125,
-      "step": 4000
-    },
-    {
-      "epoch": 0.3417197044124557,
-      "eval_loss": 1.919270396232605,
-      "eval_runtime": 795.0187,
-      "eval_samples_per_second": 99.288,
-      "eval_steps_per_second": 12.411,
-      "step": 4000
-    },
-    {
-      "epoch": 0.3630771859382342,
-      "grad_norm": 41.28815460205078,
-      "learning_rate": 2.1225e-05,
-      "loss": 16.1804853515625,
-      "step": 4250
-    },
-    {
-      "epoch": 0.38443466746401267,
-      "grad_norm": 39.76205062866211,
-      "learning_rate": 2.2475e-05,
-      "loss": 16.03432421875,
-      "step": 4500
-    },
-    {
-      "epoch": 0.38443466746401267,
-      "eval_loss": 1.8889796733856201,
-      "eval_runtime": 793.8887,
-      "eval_samples_per_second": 99.43,
-      "eval_steps_per_second": 12.429,
-      "step": 4500
-    },
-    {
-      "epoch": 0.4057921489897911,
-      "grad_norm": 46.443695068359375,
-      "learning_rate": 2.372e-05,
-      "loss": 15.8476015625,
-      "step": 4750
-    },
-    {
-      "epoch": 0.4271496305155696,
-      "grad_norm": 37.068084716796875,
-      "learning_rate": 2.4970000000000003e-05,
-      "loss": 15.7752314453125,
-      "step": 5000
-    },
-    {
-      "epoch": 0.4271496305155696,
-      "eval_loss": 1.8540898561477661,
-      "eval_runtime": 762.2328,
-      "eval_samples_per_second": 103.559,
-      "eval_steps_per_second": 12.945,
-      "step": 5000
-    }
-  ],
-  "logging_steps": 250,
-  "max_steps": 23412,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
-  "save_steps": 500,
-  "stateful_callbacks": {
-    "EarlyStoppingCallback": {
-      "args": {
-        "early_stopping_patience": 3,
-        "early_stopping_threshold": 0.0
-      },
-      "attributes": {
-        "early_stopping_patience_counter": 0
-      }
-    },
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": false
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 1.5988961574912e+17,
-  "train_batch_size": 16,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-5000/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:39853abe7c212a05cd37a6042b4d1c2f33b18beabbb723de8075009a188aad0f
-size 5201