Training in progress, epoch 3

checkpoint-73632/config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "mnli",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "entailment",
+    "1": "neutral",
+    "2": "contradiction"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "contradiction": 2,
+    "entailment": 0,
+    "neutral": 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-73632/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13b2c76cc1d0b14d9683a911698098fff891dd6747753018af9fe3f53bd30792
+size 866617565

checkpoint-73632/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7d6ac31a0a1096fd9ada124182aec47db1e215fd3b736925b808bbb7ecf9a5e
+size 433334445

checkpoint-73632/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79b52768bd19b77a9108ef3321f47f192cfaa0eb5a17c35a2d8e11bef86c26c6
+size 14503

checkpoint-73632/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ea4616a97724a0d5e0c699813c0051393c4215c930dfd1076ec80eac04682b4
+size 623

checkpoint-73632/special_tokens_map.json

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

checkpoint-73632/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-73632/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 73632,
+  "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": 0.5323,
+      "step": 24544
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.83015792154865,
+      "eval_loss": 0.44308236241340637,
+      "eval_runtime": 99.9144,
+      "eval_samples_per_second": 98.234,
+      "eval_steps_per_second": 12.281,
+      "step": 24544
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.3447,
+      "step": 49088
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8352521650534895,
+      "eval_loss": 0.47252869606018066,
+      "eval_runtime": 99.9537,
+      "eval_samples_per_second": 98.195,
+      "eval_steps_per_second": 12.276,
+      "step": 49088
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.2267,
+      "step": 73632
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8367804381049414,
+      "eval_loss": 0.5887367129325867,
+      "eval_runtime": 100.2091,
+      "eval_samples_per_second": 97.945,
+      "eval_steps_per_second": 12.244,
+      "step": 73632
+    }
+  ],
+  "max_steps": 73632,
+  "num_train_epochs": 3,
+  "total_flos": 3.099754961058632e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-73632/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:987dcb06464bd5cbb652af2a7c46c08796060a94cd02142160b0f18314774a7d
+size 2799

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60bff9928df8de5af1600061d3e57816ae7f5c19076a85a27df042d2e92da854
+oid sha256:c7d6ac31a0a1096fd9ada124182aec47db1e215fd3b736925b808bbb7ecf9a5e
 size 433334445

runs/Sep16_20-47-31_patrick-general-gpu/events.out.tfevents.1631825269.patrick-general-gpu.214155.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d63dc129ba69e65efaae674942c8bc47ea68e3e1aa9cd0bcbab5228325003383
-size 4260
+oid sha256:d78a1b6891b2dfddfd8f1b1adcf740ad850ee7f2443cefcd6ed9a742a4560ece
+size 4749