Upload 8 files

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "t5-small",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "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": "4.35.2",
+  "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": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d673cefbe16362afa84133e7c13e18378fd4fdafb17066c0d583abb50cbbf16
+size 242041896

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dd6f93bda8e47b35dded389cd702b8b6ee6b8389d34006d15733dda91837902
+size 484163514

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49c049640c197a5cc70ce51de1fdcbefa83148ce50320706bbbb8af1cb8f10f8
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6010843f16e658bc53b6a626b8b526ca26cd659a92313617bec1c47b7cfc99b5
+size 1064

trainer_state.json

@@ -0,0 +1,151 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9993890198132146,
+  "eval_steps": 500,
+  "global_step": 11450,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.563585580867592e-05,
+      "loss": 0.3428,
+      "step": 500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.127171161735184e-05,
+      "loss": 0.237,
+      "step": 1000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 8.690756742602775e-05,
+      "loss": 0.227,
+      "step": 1500
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 8.254342323470367e-05,
+      "loss": 0.2196,
+      "step": 2000
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 7.817927904337959e-05,
+      "loss": 0.213,
+      "step": 2500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 7.381513485205552e-05,
+      "loss": 0.2091,
+      "step": 3000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 6.945099066073143e-05,
+      "loss": 0.2098,
+      "step": 3500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 6.508684646940735e-05,
+      "loss": 0.2039,
+      "step": 4000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 6.072270227808327e-05,
+      "loss": 0.2036,
+      "step": 4500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 5.63585580867592e-05,
+      "loss": 0.2022,
+      "step": 5000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 5.1994413895435114e-05,
+      "loss": 0.2029,
+      "step": 5500
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.7630269704111024e-05,
+      "loss": 0.2007,
+      "step": 6000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.326612551278694e-05,
+      "loss": 0.1984,
+      "step": 6500
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 3.8901981321462864e-05,
+      "loss": 0.1984,
+      "step": 7000
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.453783713013879e-05,
+      "loss": 0.1986,
+      "step": 7500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.01736929388147e-05,
+      "loss": 0.1948,
+      "step": 8000
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 2.580954874749062e-05,
+      "loss": 0.1941,
+      "step": 8500
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.1445404556166537e-05,
+      "loss": 0.1955,
+      "step": 9000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.7081260364842456e-05,
+      "loss": 0.1955,
+      "step": 9500
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.2717116173518373e-05,
+      "loss": 0.1949,
+      "step": 10000
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 8.352971982194293e-06,
+      "loss": 0.1951,
+      "step": 10500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 3.988827790870211e-06,
+      "loss": 0.1956,
+      "step": 11000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 11457,
+  "num_train_epochs": 1,
+  "save_steps": 10,
+  "total_flos": 1.23973090148352e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e601d63f4e46067aebd783ea178e5e6080b2c282d7f25987422c17d4a4ddda16
+size 4536