Upload storri summeriser v1

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "t5-small",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 6,
+  "num_heads": 8,
+  "num_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0",
+  "use_cache": true,
+  "vocab_size": 32128
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.26.0"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b45088b0e992855a36b5143235c1f9bb05b7515e2eec49977f1d13fd8501967a
+size 484130565

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07087c578fa01bd46c8afb4daa3faadc92a2bf119686533c67688abe87ce6e2d
+size 242071641

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4951f392d22059d281796414f6dca76f8e46780ddf6451d1213232275115fd8d
+size 14575

runs/Feb08_23-27-36_37305da455f1/1675898862.1438448/events.out.tfevents.1675898862.37305da455f1.590.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dcfa7f5694fe7b47ab900e9d1e4b970c140ba52ee605febc170bb0522e64e0f
+size 5903

runs/Feb08_23-27-36_37305da455f1/events.out.tfevents.1675898862.37305da455f1.590.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef08701025c5c735b2cd05e08d25f228ed9ddf2adaa205a8c3f95b836b79cb1e
+size 8606

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66653a75d9883d91b38c17e61aacaeeb6cdf04c662c4e9ce1418e37a40bc480d
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c29c54132aa43de9c23164c913f590553c2947da78190b2f57a0cbecefbfd2b
+size 627

trainer_state.json

@@ -0,0 +1,109 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.91644908616188,
+  "global_step": 4500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.7828546562228025e-05,
+      "loss": 2.0396,
+      "step": 500
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.5652741514360316e-05,
+      "loss": 1.9399,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 19.0,
+      "eval_loss": 1.7441270351409912,
+      "eval_rouge1": 0.246,
+      "eval_rouge2": 0.1167,
+      "eval_rougeL": 0.2027,
+      "eval_rougeLsum": 0.2025,
+      "eval_runtime": 183.8875,
+      "eval_samples_per_second": 12.497,
+      "eval_steps_per_second": 1.566,
+      "step": 1149
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.348128807658834e-05,
+      "loss": 1.9212,
+      "step": 1500
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 1.1305483028720628e-05,
+      "loss": 1.8858,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 18.9987,
+      "eval_loss": 1.7244781255722046,
+      "eval_rouge1": 0.246,
+      "eval_rouge2": 0.116,
+      "eval_rougeL": 0.203,
+      "eval_rougeLsum": 0.2028,
+      "eval_runtime": 185.1368,
+      "eval_samples_per_second": 12.412,
+      "eval_steps_per_second": 1.556,
+      "step": 2298
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 9.129677980852917e-06,
+      "loss": 1.8875,
+      "step": 2500
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 6.953872932985205e-06,
+      "loss": 1.8767,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 18.9956,
+      "eval_loss": 1.7172995805740356,
+      "eval_rouge1": 0.2459,
+      "eval_rouge2": 0.116,
+      "eval_rougeL": 0.2024,
+      "eval_rougeLsum": 0.2022,
+      "eval_runtime": 180.4003,
+      "eval_samples_per_second": 12.738,
+      "eval_steps_per_second": 1.596,
+      "step": 3447
+    },
+    {
+      "epoch": 3.05,
+      "learning_rate": 4.778067885117494e-06,
+      "loss": 1.8909,
+      "step": 3500
+    },
+    {
+      "epoch": 3.48,
+      "learning_rate": 2.6022628372497826e-06,
+      "loss": 1.8648,
+      "step": 4000
+    },
+    {
+      "epoch": 3.92,
+      "learning_rate": 4.264577893820714e-07,
+      "loss": 1.8835,
+      "step": 4500
+    }
+  ],
+  "max_steps": 4596,
+  "num_train_epochs": 4,
+  "total_flos": 9722809102368768.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca5d12770a9856d5b5cf760696a2cb9b1ffd88364c09c3360e3800c40a0ce2a8
+size 3643