Delete checkpoint-1100

checkpoint-1100/model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:95d2da0b49dadfb0c2e16d8675e186f56db1db6b89e096c8c72dc2fb3933d1aa
-size 1112204984

checkpoint-1100/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:30c661c2016fbe6ab525e0d8b2c4af79d97bed930976bd1547877e1add79f06b
-size 2219803258

checkpoint-1100/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:73ad35afe7245582c3a30c2d911f786a320ba177c1efc7548bb163ec485239fa
-size 14244

checkpoint-1100/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e224eb97d58d959997cdc13c3d0c1c5045788254f92e7f75adbd5a9690a9db11
-size 1064

checkpoint-1100/sentencepiece.bpe.model

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
-size 5069051

checkpoint-1100/special_tokens_map.json

@@ -1,51 +0,0 @@
-{
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}

checkpoint-1100/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
-size 17082999

checkpoint-1100/tokenizer_config.json

@@ -1,62 +0,0 @@
-{
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<pad>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "3": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "250001": {
-      "content": "<mask>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "bos_token": "<s>",
-  "clean_up_tokenization_spaces": false,
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "extra_special_tokens": {},
-  "mask_token": "<mask>",
-  "max_length": 128,
-  "model_max_length": 512,
-  "pad_to_multiple_of": null,
-  "pad_token": "<pad>",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
-  "sep_token": "</s>",
-  "stride": 0,
-  "tokenizer_class": "XLMRobertaTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
-  "unk_token": "<unk>"
-}

checkpoint-1100/trainer_state.json

@@ -1,229 +0,0 @@
-{
-  "best_metric": 0.622703721149317,
-  "best_model_checkpoint": "./trained_on_contrastive_encoder_10_epoch_question_freeze_0/checkpoint-1100",
-  "epoch": 0.9981851179673321,
-  "eval_steps": 100,
-  "global_step": 1100,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.09074410163339383,
-      "grad_norm": 4.864197254180908,
-      "learning_rate": 9.903e-06,
-      "loss": 0.706,
-      "step": 100
-    },
-    {
-      "epoch": 0.09074410163339383,
-      "eval_accuracy": 0.8221413477342099,
-      "eval_f1_pos": 0.0,
-      "eval_loss": 0.6011108756065369,
-      "eval_runtime": 31.8999,
-      "eval_samples_per_second": 267.023,
-      "eval_steps_per_second": 16.709,
-      "step": 100
-    },
-    {
-      "epoch": 0.18148820326678766,
-      "grad_norm": 3.3921830654144287,
-      "learning_rate": 9.804000000000001e-06,
-      "loss": 0.6796,
-      "step": 200
-    },
-    {
-      "epoch": 0.18148820326678766,
-      "eval_accuracy": 0.8084057290443766,
-      "eval_f1_pos": 0.37757437070938216,
-      "eval_loss": 0.5799795389175415,
-      "eval_runtime": 32.9637,
-      "eval_samples_per_second": 258.405,
-      "eval_steps_per_second": 16.169,
-      "step": 200
-    },
-    {
-      "epoch": 0.27223230490018147,
-      "grad_norm": 10.387075424194336,
-      "learning_rate": 9.704e-06,
-      "loss": 0.606,
-      "step": 300
-    },
-    {
-      "epoch": 0.27223230490018147,
-      "eval_accuracy": 0.6152852782343273,
-      "eval_f1_pos": 0.442592277598231,
-      "eval_loss": 0.6913803219795227,
-      "eval_runtime": 31.9515,
-      "eval_samples_per_second": 266.591,
-      "eval_steps_per_second": 16.682,
-      "step": 300
-    },
-    {
-      "epoch": 0.3629764065335753,
-      "grad_norm": 17.31307601928711,
-      "learning_rate": 9.604000000000002e-06,
-      "loss": 0.5344,
-      "step": 400
-    },
-    {
-      "epoch": 0.3629764065335753,
-      "eval_accuracy": 0.642286921812632,
-      "eval_f1_pos": 0.4836468395187256,
-      "eval_loss": 0.6743361353874207,
-      "eval_runtime": 34.1976,
-      "eval_samples_per_second": 249.082,
-      "eval_steps_per_second": 15.586,
-      "step": 400
-    },
-    {
-      "epoch": 0.4537205081669691,
-      "grad_norm": 14.772553443908691,
-      "learning_rate": 9.504e-06,
-      "loss": 0.5077,
-      "step": 500
-    },
-    {
-      "epoch": 0.4537205081669691,
-      "eval_accuracy": 0.7073256633012445,
-      "eval_f1_pos": 0.527751468081076,
-      "eval_loss": 0.5418139696121216,
-      "eval_runtime": 31.806,
-      "eval_samples_per_second": 267.811,
-      "eval_steps_per_second": 16.758,
-      "step": 500
-    },
-    {
-      "epoch": 0.5444646098003629,
-      "grad_norm": 17.365032196044922,
-      "learning_rate": 9.405e-06,
-      "loss": 0.4533,
-      "step": 600
-    },
-    {
-      "epoch": 0.5444646098003629,
-      "eval_accuracy": 0.7528762620333411,
-      "eval_f1_pos": 0.572415193987406,
-      "eval_loss": 0.5408028364181519,
-      "eval_runtime": 33.2247,
-      "eval_samples_per_second": 256.375,
-      "eval_steps_per_second": 16.042,
-      "step": 600
-    },
-    {
-      "epoch": 0.6352087114337568,
-      "grad_norm": 37.66470718383789,
-      "learning_rate": 9.305000000000002e-06,
-      "loss": 0.452,
-      "step": 700
-    },
-    {
-      "epoch": 0.6352087114337568,
-      "eval_accuracy": 0.7457149565625734,
-      "eval_f1_pos": 0.571089108910891,
-      "eval_loss": 0.45808446407318115,
-      "eval_runtime": 33.2944,
-      "eval_samples_per_second": 255.839,
-      "eval_steps_per_second": 16.009,
-      "step": 700
-    },
-    {
-      "epoch": 0.7259528130671506,
-      "grad_norm": 28.712770462036133,
-      "learning_rate": 9.205e-06,
-      "loss": 0.4402,
-      "step": 800
-    },
-    {
-      "epoch": 0.7259528130671506,
-      "eval_accuracy": 0.7641465132660249,
-      "eval_f1_pos": 0.5853457172342621,
-      "eval_loss": 0.4426897168159485,
-      "eval_runtime": 32.2392,
-      "eval_samples_per_second": 264.213,
-      "eval_steps_per_second": 16.533,
-      "step": 800
-    },
-    {
-      "epoch": 0.8166969147005445,
-      "grad_norm": 16.69965171813965,
-      "learning_rate": 9.105e-06,
-      "loss": 0.4197,
-      "step": 900
-    },
-    {
-      "epoch": 0.8166969147005445,
-      "eval_accuracy": 0.7602723644047898,
-      "eval_f1_pos": 0.5824130879345604,
-      "eval_loss": 0.4644756317138672,
-      "eval_runtime": 31.9357,
-      "eval_samples_per_second": 266.724,
-      "eval_steps_per_second": 16.69,
-      "step": 900
-    },
-    {
-      "epoch": 0.9074410163339383,
-      "grad_norm": 29.23394203186035,
-      "learning_rate": 9.005000000000001e-06,
-      "loss": 0.4153,
-      "step": 1000
-    },
-    {
-      "epoch": 0.9074410163339383,
-      "eval_accuracy": 0.7779995304061986,
-      "eval_f1_pos": 0.5992795083704174,
-      "eval_loss": 0.4298250675201416,
-      "eval_runtime": 31.9166,
-      "eval_samples_per_second": 266.883,
-      "eval_steps_per_second": 16.7,
-      "step": 1000
-    },
-    {
-      "epoch": 0.9981851179673321,
-      "grad_norm": 8.876638412475586,
-      "learning_rate": 8.905e-06,
-      "loss": 0.4162,
-      "step": 1100
-    },
-    {
-      "epoch": 0.9981851179673321,
-      "eval_accuracy": 0.8119276825545902,
-      "eval_f1_pos": 0.622703721149317,
-      "eval_loss": 0.352287232875824,
-      "eval_runtime": 31.9198,
-      "eval_samples_per_second": 266.856,
-      "eval_steps_per_second": 16.698,
-      "step": 1100
-    }
-  ],
-  "logging_steps": 100,
-  "max_steps": 10000,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 10,
-  "save_steps": 100,
-  "stateful_callbacks": {
-    "EarlyStoppingCallback": {
-      "args": {
-        "early_stopping_patience": 2,
-        "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": 0.0,
-  "train_batch_size": 16,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-1100/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:15e0b4e07163290fc63734da0b9913f0b396eb3be141ebfbcf569bf53170e2ee
-size 5368