Training in progress, epoch 5, checkpoint

checkpoint-46510/config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "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,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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": "4.42.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-46510/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aca94eb741cc45f3f3ede9174fc0265171f523bdb239e4f894367a36453c2db
+size 498615900

checkpoint-46510/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c6abb2c0e199976e392a2653713a5ed01626344270f56ab229cc1326ab04b01
+size 997351674

checkpoint-46510/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdfd5dc4f28b63451fe2dfb78bf1cb37cc6afcab1fb3f83df512caaf03f97e5f
+size 14244

checkpoint-46510/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6f0c422a02f583b13d590af36609795de4d7cf948f6903ace120c8efdfd97b4
+size 1064

checkpoint-46510/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

checkpoint-46510/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

checkpoint-46510/trainer_state.json

@@ -0,0 +1,128 @@
+{
+  "best_metric": 0.528473834809328,
+  "best_model_checkpoint": "training_dir-augmented\\checkpoint-46510",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 46510,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9803293943405151,
+      "learning_rate": 8.086937622256031e-06,
+      "loss": 0.5312,
+      "step": 9302
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.40428321678321677,
+      "eval_f1": 0.3406020494510067,
+      "eval_loss": 3.0353851318359375,
+      "eval_precision": 0.6901256632128517,
+      "eval_recall": 0.40428321678321677,
+      "eval_runtime": 16.0409,
+      "eval_samples_per_second": 142.636,
+      "eval_steps_per_second": 17.829,
+      "step": 9302
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 196.54563903808594,
+      "learning_rate": 6.065203216692024e-06,
+      "loss": 0.3949,
+      "step": 18604
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.527972027972028,
+      "eval_f1": 0.526961176646401,
+      "eval_loss": 2.4327211380004883,
+      "eval_precision": 0.6358079986576912,
+      "eval_recall": 0.527972027972028,
+      "eval_runtime": 16.8165,
+      "eval_samples_per_second": 136.057,
+      "eval_steps_per_second": 17.007,
+      "step": 18604
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.016049087047576904,
+      "learning_rate": 4.0434688111280154e-06,
+      "loss": 0.3459,
+      "step": 27906
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.4943181818181818,
+      "eval_f1": 0.46533481595237636,
+      "eval_loss": 3.3212876319885254,
+      "eval_precision": 0.6366932825610363,
+      "eval_recall": 0.4943181818181818,
+      "eval_runtime": 16.4685,
+      "eval_samples_per_second": 138.932,
+      "eval_steps_per_second": 17.366,
+      "step": 27906
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.18690501153469086,
+      "learning_rate": 2.0217344055640077e-06,
+      "loss": 0.2889,
+      "step": 37208
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5380244755244755,
+      "eval_f1": 0.5246359275298862,
+      "eval_loss": 2.901275157928467,
+      "eval_precision": 0.606438596036477,
+      "eval_recall": 0.5380244755244755,
+      "eval_runtime": 16.3842,
+      "eval_samples_per_second": 139.647,
+      "eval_steps_per_second": 17.456,
+      "step": 37208
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.032341405749320984,
+      "learning_rate": 0.0,
+      "loss": 0.2405,
+      "step": 46510
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5354020979020979,
+      "eval_f1": 0.528473834809328,
+      "eval_loss": 3.196098566055298,
+      "eval_precision": 0.6116035335408587,
+      "eval_recall": 0.5354020979020979,
+      "eval_runtime": 18.2453,
+      "eval_samples_per_second": 125.402,
+      "eval_steps_per_second": 15.675,
+      "step": 46510
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 46510,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.524204110411717e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-46510/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dbf1e2674cf52d458f94b2caeee62e7225f15edfb61f198e097040d7d1a7268
+size 5240