Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,98 @@
+{
+  "_name_or_path": "allenai/PRIMERA",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "LEDForConditionalGeneration"
+  ],
+  "attention_dilation": [
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1
+  ],
+  "attention_dropout": 0.0,
+  "attention_mode": "sliding_chunks",
+  "attention_window": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "autoregressive": false,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "extra_pos_embeddings": 2,
+  "force_bos_token_to_be_generated": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_decoder_position_embeddings": 1024,
+  "max_encoder_position_embeddings": 4096,
+  "max_position_embeddings": 4096,
+  "model_type": "led",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_hidden_layers": 12,
+  "output_past": false,
+  "pad_token_id": 1,
+  "prefix": " ",
+  "scale_embedding": false,
+  "static_position_embeddings": false,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 50266
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2c3c8e87b4e921723149639055741f90bd9d0077b06858bfee8916fe7b15241
+size 1789281197

runs/Apr27_19-36-24_32ef514e8da2/1682624199.3576772/events.out.tfevents.1682624199.32ef514e8da2.973.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8ed22d606244b07d3f2eea44fae262e8849c87d832c05b6918ab92d43dfb69a
+size 5846

runs/Apr27_19-36-24_32ef514e8da2/events.out.tfevents.1682624199.32ef514e8da2.973.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10cf26ea68ff54c2e1b39c90bbf8fbc6a65b339277b3b45f4e20a8affc40506a
+size 5455

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d13e2fdeb952dde4d3230fc1760d86ce7172c1a4259852aaeb884ac7a2b5af76
+size 3579