End of training

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

.gitignore

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

all_results.json

@@ -0,0 +1,22 @@
+{
+    "eval_gen_len": 41.562881562881564,
+    "eval_loss": 1.869093418121338,
+    "eval_rouge1": 35.1506,
+    "eval_rouge2": 16.0888,
+    "eval_rougeL": 29.7007,
+    "eval_rougeLsum": 32.4251,
+    "eval_runtime": 261.235,
+    "eval_samples": 819,
+    "eval_samples_per_second": 3.135,
+    "eval_steps_per_second": 0.199,
+    "predict_gen_len": 41.73230769230769,
+    "predict_loss": 1.8758330345153809,
+    "predict_rouge1": 35.1974,
+    "predict_rouge2": 16.4972,
+    "predict_rougeL": 30.2616,
+    "predict_rougeLsum": 32.5539,
+    "predict_runtime": 419.3492,
+    "predict_samples": 1300,
+    "predict_samples_per_second": 3.1,
+    "predict_steps_per_second": 0.196
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "navjordj/t5-large-snl",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 2816,
+  "d_kv": 64,
+  "d_model": 1024,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 24,
+  "num_heads": 16,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.0.dev0",
+  "use_cache": true,
+  "vocab_size": 250112
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "eval_gen_len": 41.562881562881564,
+    "eval_loss": 1.869093418121338,
+    "eval_rouge1": 35.1506,
+    "eval_rouge2": 16.0888,
+    "eval_rougeL": 29.7007,
+    "eval_rougeLsum": 32.4251,
+    "eval_runtime": 261.235,
+    "eval_samples": 819,
+    "eval_samples_per_second": 3.135,
+    "eval_steps_per_second": 0.199
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.27.0.dev0"
+}

predict_results.json

@@ -0,0 +1,12 @@
+{
+    "predict_gen_len": 41.73230769230769,
+    "predict_loss": 1.8758330345153809,
+    "predict_rouge1": 35.1974,
+    "predict_rouge2": 16.4972,
+    "predict_rougeL": 30.2616,
+    "predict_rougeLsum": 32.5539,
+    "predict_runtime": 419.3492,
+    "predict_samples": 1300,
+    "predict_samples_per_second": 3.1,
+    "predict_steps_per_second": 0.196
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb2816d0977b81ab3c8aae761e0dbe67a61c6bbc444a077898a7a468480bc95a
+size 4918519193

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6502d07619068a98aa2d3bb531332a694ffe108ca6c6fe62a467ccfe98d666b9
+size 16315219

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": null,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04a3a2939b492c81f85c8dfdbb652682d9b41d40602d3f450f8c30fa5d059f27
+size 3707