Upload 8 files

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": "4.27.4",
+  "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": "4.27.4"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e0a85de5f90b0140c76169b0a44ae8684db447e594346e8f8e48d769a7633f1
+size 242071641

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cc11f15efb3481532d2eb68567c5af957ef4d398fc068694830deed3269eb4c
+size 14575

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5ddd690ee0ad537eae8b7a7925d681dd4d4e8525251eccb6717bbe2da89261c
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:673069abc9f27049d729924b4bbb245d2d0143dd368e6562a56ee5e9416412b9
+size 627

trainer_state.json

@@ -0,0 +1,274 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9868723033140548,
+  "global_step": 21500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.9545579730101903e-05,
+      "loss": 1.1232,
+      "step": 500
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9086569356467456e-05,
+      "loss": 0.0953,
+      "step": 1000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.8627558982833013e-05,
+      "loss": 0.0845,
+      "step": 1500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.816854860919857e-05,
+      "loss": 0.0796,
+      "step": 2000
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.7709538235564126e-05,
+      "loss": 0.0796,
+      "step": 2500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.725052786192968e-05,
+      "loss": 0.078,
+      "step": 3000
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.6791517488295236e-05,
+      "loss": 0.0766,
+      "step": 3500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.6332507114660793e-05,
+      "loss": 0.0742,
+      "step": 4000
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.587349674102635e-05,
+      "loss": 0.0741,
+      "step": 4500
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.5414486367391906e-05,
+      "loss": 0.0743,
+      "step": 5000
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.495547599375746e-05,
+      "loss": 0.0738,
+      "step": 5500
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.4496465620123017e-05,
+      "loss": 0.0725,
+      "step": 6000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.4037455246488572e-05,
+      "loss": 0.0728,
+      "step": 6500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.3578444872854129e-05,
+      "loss": 0.0706,
+      "step": 7000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.3119434499219684e-05,
+      "loss": 0.0697,
+      "step": 7500
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.266042412558524e-05,
+      "loss": 0.0713,
+      "step": 8000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.2201413751950796e-05,
+      "loss": 0.0701,
+      "step": 8500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.1742403378316352e-05,
+      "loss": 0.07,
+      "step": 9000
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.1283393004681905e-05,
+      "loss": 0.0692,
+      "step": 9500
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.0824382631047464e-05,
+      "loss": 0.069,
+      "step": 10000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.0365372257413017e-05,
+      "loss": 0.0694,
+      "step": 10500
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.906361883778575e-06,
+      "loss": 0.0691,
+      "step": 11000
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.44735151014413e-06,
+      "loss": 0.0685,
+      "step": 11500
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.988341136509687e-06,
+      "loss": 0.0682,
+      "step": 12000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.529330762875242e-06,
+      "loss": 0.0682,
+      "step": 12500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.070320389240799e-06,
+      "loss": 0.0682,
+      "step": 13000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 7.6113100156063535e-06,
+      "loss": 0.067,
+      "step": 13500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 7.152299641971909e-06,
+      "loss": 0.0669,
+      "step": 14000
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 6.693289268337465e-06,
+      "loss": 0.066,
+      "step": 14500
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 6.234278894703021e-06,
+      "loss": 0.0664,
+      "step": 15000
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 5.776186541815846e-06,
+      "loss": 0.0667,
+      "step": 15500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 5.317176168181402e-06,
+      "loss": 0.0667,
+      "step": 16000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 4.858165794546958e-06,
+      "loss": 0.0671,
+      "step": 16500
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 4.3991554209125135e-06,
+      "loss": 0.0668,
+      "step": 17000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.940145047278069e-06,
+      "loss": 0.0661,
+      "step": 17500
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.4811346736436247e-06,
+      "loss": 0.0674,
+      "step": 18000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.0221243000091805e-06,
+      "loss": 0.0662,
+      "step": 18500
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.5631139263747363e-06,
+      "loss": 0.067,
+      "step": 19000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.104103552740292e-06,
+      "loss": 0.0657,
+      "step": 19500
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.645093179105848e-06,
+      "loss": 0.0658,
+      "step": 20000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.1860828054714039e-06,
+      "loss": 0.0663,
+      "step": 20500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.270724318369595e-07,
+      "loss": 0.0661,
+      "step": 21000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.6898007894978427e-07,
+      "loss": 0.0666,
+      "step": 21500
+    }
+  ],
+  "max_steps": 21786,
+  "num_train_epochs": 1,
+  "total_flos": 4.6557579706368e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d233f9b90f3820095541074b2705fbe32e08ff220d764fd9c262afcd8809171
+size 3707