Training in progress, epoch 3

checkpoint-12630/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "sst2",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "positive": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

checkpoint-12630/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e3d676725b6275b37dd8924c66a5a829aa511fb95b79a586cae6b0bfd7c052b
+size 866610973

checkpoint-12630/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dbfeca23d6951df35b7d3db36125283bb99ee81c7f38c6f301185257e6a0624
+size 433331373

checkpoint-12630/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dad09ce466ca959f3b6cdc435393932858639962d53c1a0e568e1d07744cad5
+size 14503

checkpoint-12630/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55d12134d4d1d0b70b5996eb59099da9fc12a4d3548d43e6aba424b4512591b1
+size 623

checkpoint-12630/special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

checkpoint-12630/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-cased", "tokenizer_class": "BertTokenizer"}

checkpoint-12630/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 12630,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.233,
+      "step": 4210
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9174311926605505,
+      "eval_loss": 0.28414297103881836,
+      "eval_runtime": 8.9563,
+      "eval_samples_per_second": 97.362,
+      "eval_steps_per_second": 12.17,
+      "step": 4210
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.1261,
+      "step": 8420
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9277522935779816,
+      "eval_loss": 0.3310103714466095,
+      "eval_runtime": 8.9528,
+      "eval_samples_per_second": 97.399,
+      "eval_steps_per_second": 12.175,
+      "step": 8420
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.0768,
+      "step": 12630
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9231651376146789,
+      "eval_loss": 0.36485353112220764,
+      "eval_runtime": 8.9701,
+      "eval_samples_per_second": 97.212,
+      "eval_steps_per_second": 12.152,
+      "step": 12630
+    }
+  ],
+  "max_steps": 12630,
+  "num_train_epochs": 3,
+  "total_flos": 5.316079940232192e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-12630/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59450522d271313b7348a5aafc455ce45e338daf4aa902c944e4316883ac784f
+size 2799

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcb77e8618916e305f17322bc7309831e018f7498a06493d2f22c3af43b08203
+oid sha256:4dbfeca23d6951df35b7d3db36125283bb99ee81c7f38c6f301185257e6a0624
 size 433331373

runs/Sep19_05-56-28_patrick-general-gpu/events.out.tfevents.1632031020.patrick-general-gpu.459415.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cc18f95e952f2c9fe1f0181ebd315989c6ac450d92008d174f532d2e64548ca
-size 4190
+oid sha256:a701d8a2d7493a3c991a2cc95f5a5792ce7192794bf18bfb3eefbe52ec24aee8
+size 4670