Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33d23e56b7e959f7736dbcaf24e3daa98b04467970485dd231d5adb16bfb319b
+oid sha256:02b32d780fca60e4ce2846583884ce1da4c8863e74205b19af2572784e946a5f
 size 498612824

run-hrrn3119/checkpoint-20336/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "FacebookAI/roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

run-hrrn3119/checkpoint-20336/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02b32d780fca60e4ce2846583884ce1da4c8863e74205b19af2572784e946a5f
+size 498612824

run-hrrn3119/checkpoint-20336/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f72e8c452eed628a765311aa043eb2e6a12b67c834a9e4fb5ad7ab55d755a121
+size 997345530

run-hrrn3119/checkpoint-20336/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:589a0cc2e4e3857a9a1dabdb34fe04180c09f66a2b09d6a0dc7494dc6e5d6493
+size 14180

run-hrrn3119/checkpoint-20336/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0586f31828669d6794c8132cddb25d1ac0dec4bc06b8703a52787544b45eb54
+size 1064

run-hrrn3119/checkpoint-20336/special_tokens_map.json

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

run-hrrn3119/checkpoint-20336/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "unk_token": "<unk>"
+}

run-hrrn3119/checkpoint-20336/trainer_state.json

@@ -0,0 +1,356 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 20336,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 4.128891468048096,
+      "learning_rate": 2.9262391817466563e-05,
+      "loss": 0.3492,
+      "step": 500
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 7.290346145629883,
+      "learning_rate": 2.8524783634933124e-05,
+      "loss": 0.3139,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 4.3120012283325195,
+      "learning_rate": 2.7787175452399686e-05,
+      "loss": 0.3064,
+      "step": 1500
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 3.9245710372924805,
+      "learning_rate": 2.7049567269866248e-05,
+      "loss": 0.285,
+      "step": 2000
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 3.7431070804595947,
+      "learning_rate": 2.631195908733281e-05,
+      "loss": 0.2719,
+      "step": 2500
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 8.229458808898926,
+      "learning_rate": 2.557435090479937e-05,
+      "loss": 0.2635,
+      "step": 3000
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 7.368682384490967,
+      "learning_rate": 2.4836742722265933e-05,
+      "loss": 0.2581,
+      "step": 3500
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 15.96370792388916,
+      "learning_rate": 2.4099134539732495e-05,
+      "loss": 0.2575,
+      "step": 4000
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 4.469223976135254,
+      "learning_rate": 2.3361526357199057e-05,
+      "loss": 0.2524,
+      "step": 4500
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 38.71263122558594,
+      "learning_rate": 2.262391817466562e-05,
+      "loss": 0.2397,
+      "step": 5000
+    },
+    {
+      "epoch": 1.0,
+      "eval_Accuracy": 0.9054996127033308,
+      "eval_F1": 0.8622136172959018,
+      "eval_Precision": 0.9124644280022766,
+      "eval_Recall": 0.8172086859007034,
+      "eval_loss": 0.3134010136127472,
+      "eval_runtime": 102.8535,
+      "eval_samples_per_second": 263.589,
+      "eval_steps_per_second": 32.95,
+      "step": 5084
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 2.243791103363037,
+      "learning_rate": 2.188630999213218e-05,
+      "loss": 0.2153,
+      "step": 5500
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 23.5120792388916,
+      "learning_rate": 2.1148701809598742e-05,
+      "loss": 0.1915,
+      "step": 6000
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 5.028568744659424,
+      "learning_rate": 2.0411093627065304e-05,
+      "loss": 0.199,
+      "step": 6500
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 1.7690353393554688,
+      "learning_rate": 1.9673485444531865e-05,
+      "loss": 0.1942,
+      "step": 7000
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 8.04137134552002,
+      "learning_rate": 1.8935877261998427e-05,
+      "loss": 0.1798,
+      "step": 7500
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 4.065598487854004,
+      "learning_rate": 1.819826907946499e-05,
+      "loss": 0.1945,
+      "step": 8000
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 1.5622484683990479,
+      "learning_rate": 1.746066089693155e-05,
+      "loss": 0.2016,
+      "step": 8500
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 16.104820251464844,
+      "learning_rate": 1.6723052714398112e-05,
+      "loss": 0.1894,
+      "step": 9000
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 19.27669334411621,
+      "learning_rate": 1.5985444531864674e-05,
+      "loss": 0.1794,
+      "step": 9500
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 0.7860851883888245,
+      "learning_rate": 1.5247836349331236e-05,
+      "loss": 0.1756,
+      "step": 10000
+    },
+    {
+      "epoch": 2.0,
+      "eval_Accuracy": 0.9363726900520084,
+      "eval_F1": 0.9097095001308558,
+      "eval_Precision": 0.9348106712564543,
+      "eval_Recall": 0.8859210928738913,
+      "eval_loss": 0.2499203383922577,
+      "eval_runtime": 102.6336,
+      "eval_samples_per_second": 264.153,
+      "eval_steps_per_second": 33.02,
+      "step": 10168
+    },
+    {
+      "epoch": 2.07,
+      "grad_norm": 4.466465473175049,
+      "learning_rate": 1.4510228166797798e-05,
+      "loss": 0.1498,
+      "step": 10500
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.24395695328712463,
+      "learning_rate": 1.377261998426436e-05,
+      "loss": 0.1346,
+      "step": 11000
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 82.869384765625,
+      "learning_rate": 1.3035011801730921e-05,
+      "loss": 0.1402,
+      "step": 11500
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 11.058635711669922,
+      "learning_rate": 1.2297403619197483e-05,
+      "loss": 0.1319,
+      "step": 12000
+    },
+    {
+      "epoch": 2.46,
+      "grad_norm": 0.09861055761575699,
+      "learning_rate": 1.1559795436664045e-05,
+      "loss": 0.1335,
+      "step": 12500
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 19.91216278076172,
+      "learning_rate": 1.0822187254130605e-05,
+      "loss": 0.132,
+      "step": 13000
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 6.106110572814941,
+      "learning_rate": 1.0084579071597168e-05,
+      "loss": 0.1345,
+      "step": 13500
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 50.40985870361328,
+      "learning_rate": 9.34697088906373e-06,
+      "loss": 0.124,
+      "step": 14000
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 0.419050395488739,
+      "learning_rate": 8.609362706530292e-06,
+      "loss": 0.1268,
+      "step": 14500
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 0.2709197700023651,
+      "learning_rate": 7.871754523996854e-06,
+      "loss": 0.1328,
+      "step": 15000
+    },
+    {
+      "epoch": 3.0,
+      "eval_Accuracy": 0.9474751945704696,
+      "eval_F1": 0.9249815614792962,
+      "eval_Precision": 0.9570478578436716,
+      "eval_Recall": 0.8949943929044755,
+      "eval_loss": 0.24683944880962372,
+      "eval_runtime": 103.4766,
+      "eval_samples_per_second": 262.001,
+      "eval_steps_per_second": 32.751,
+      "step": 15252
+    },
+    {
+      "epoch": 3.05,
+      "grad_norm": 0.021914571523666382,
+      "learning_rate": 7.1341463414634146e-06,
+      "loss": 0.1103,
+      "step": 15500
+    },
+    {
+      "epoch": 3.15,
+      "grad_norm": 14.233478546142578,
+      "learning_rate": 6.396538158929977e-06,
+      "loss": 0.0912,
+      "step": 16000
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 10.4210844039917,
+      "learning_rate": 5.658929976396538e-06,
+      "loss": 0.0842,
+      "step": 16500
+    },
+    {
+      "epoch": 3.34,
+      "grad_norm": 0.34130796790122986,
+      "learning_rate": 4.9213217938631e-06,
+      "loss": 0.0776,
+      "step": 17000
+    },
+    {
+      "epoch": 3.44,
+      "grad_norm": 0.10451962798833847,
+      "learning_rate": 4.183713611329662e-06,
+      "loss": 0.089,
+      "step": 17500
+    },
+    {
+      "epoch": 3.54,
+      "grad_norm": 0.11272258311510086,
+      "learning_rate": 3.4461054287962234e-06,
+      "loss": 0.0785,
+      "step": 18000
+    },
+    {
+      "epoch": 3.64,
+      "grad_norm": 0.04916612058877945,
+      "learning_rate": 2.7084972462627856e-06,
+      "loss": 0.0881,
+      "step": 18500
+    },
+    {
+      "epoch": 3.74,
+      "grad_norm": 0.015323754400014877,
+      "learning_rate": 1.970889063729347e-06,
+      "loss": 0.0683,
+      "step": 19000
+    },
+    {
+      "epoch": 3.84,
+      "grad_norm": 0.16511893272399902,
+      "learning_rate": 1.2332808811959087e-06,
+      "loss": 0.0694,
+      "step": 19500
+    },
+    {
+      "epoch": 3.93,
+      "grad_norm": 0.26697444915771484,
+      "learning_rate": 4.956726986624704e-07,
+      "loss": 0.0785,
+      "step": 20000
+    },
+    {
+      "epoch": 4.0,
+      "eval_Accuracy": 0.9562170336763676,
+      "eval_F1": 0.9394109540094941,
+      "eval_Precision": 0.9407074217951339,
+      "eval_Recall": 0.9381180548475889,
+      "eval_loss": 0.23856626451015472,
+      "eval_runtime": 101.2196,
+      "eval_samples_per_second": 267.843,
+      "eval_steps_per_second": 33.482,
+      "step": 20336
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 20336,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 1.61533152577983e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "_wandb": {},
+    "assignments": {},
+    "learning_rate": 3e-05,
+    "metric": "eval/loss",
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16
+  }
+}

run-hrrn3119/checkpoint-20336/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a32a0c0723e093fb9e4eedfc3d49c1c5731ca9445a4a2b2369f6539477f369a0
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f591bcc7bb3d751c372b9e555545d558094f5e42774fe55fce79687d449affc
+oid sha256:a32a0c0723e093fb9e4eedfc3d49c1c5731ca9445a4a2b2369f6539477f369a0
 size 4920