push test model

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/notebooks/gatortron/release/mp_rank_00",
+  "architectures": [
+    "MegatronBertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "finetuning_task": "xnli",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "megatron-bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_type": "BertWordPieceCase",
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50176
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99dc61efb97c4e3b1c61b578c282dd806d8b5b8ea5cf1a17fbfddd5f838954e3
+size 2842385821

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ffb2f221c06f38c5f373625c62e75925dc347eb1e09368b5b28123898bafe3b
+size 1421213165

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d0bf7da4af913df41ab7c80a256e14734accd3050598b8e3c41f337f03e1de8
+size 14503

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38881130d7eca12d28c76e2663b05ff4bd08e4ac46f64cb692299b8ca56ec883
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:723111581889c6dee007f0c22cd936e3e03f6d46ead8dc9f3df6a8228968c663
+size 623

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "name_or_path": "/notebooks/gatortron/release/mp_rank_00",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,82 @@
+{
+  "best_metric": 0.061439353972673416,
+  "best_model_checkpoint": "/tmp/debug_covidfact_gatortron/checkpoint-1248",
+  "epoch": 6.0,
+  "global_step": 1248,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9041591320072333,
+      "eval_loss": 0.2822079658508301,
+      "eval_runtime": 10.5311,
+      "eval_samples_per_second": 52.511,
+      "eval_steps_per_second": 6.647,
+      "step": 208
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9710669077757685,
+      "eval_loss": 0.10182330012321472,
+      "eval_runtime": 10.4772,
+      "eval_samples_per_second": 52.781,
+      "eval_steps_per_second": 6.681,
+      "step": 416
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 3.798076923076923e-05,
+      "loss": 0.193,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9674502712477396,
+      "eval_loss": 0.12143626064062119,
+      "eval_runtime": 10.3087,
+      "eval_samples_per_second": 53.644,
+      "eval_steps_per_second": 6.79,
+      "step": 624
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9801084990958409,
+      "eval_loss": 0.07419443130493164,
+      "eval_runtime": 10.2802,
+      "eval_samples_per_second": 53.793,
+      "eval_steps_per_second": 6.809,
+      "step": 832
+    },
+    {
+      "epoch": 4.81,
+      "learning_rate": 2.5961538461538464e-05,
+      "loss": 0.025,
+      "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.976491862567812,
+      "eval_loss": 0.07501477003097534,
+      "eval_runtime": 10.2703,
+      "eval_samples_per_second": 53.845,
+      "eval_steps_per_second": 6.816,
+      "step": 1040
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.976491862567812,
+      "eval_loss": 0.061439353972673416,
+      "eval_runtime": 10.3008,
+      "eval_samples_per_second": 53.685,
+      "eval_steps_per_second": 6.796,
+      "step": 1248
+    }
+  ],
+  "max_steps": 2080,
+  "num_train_epochs": 10,
+  "total_flos": 1.3910473494715392e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0c43171afd2f0a5e56cc53b9e1be66fa8d603f0eeeed78b67fe95453270487d
+size 3311