Upload 8 files

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "models/checkpoint-11450",
+  "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 sha256:95ae349830fcf8b1b15a7aa97ab4a3954d866921f3c32369aae1eaeadb5fca37
+size 242041896

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d55911340d0cd524c85ca1607095662b4e24bc31e885f87494fb47330e3dec0
+size 484163514

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e42f0539ec6d780db63a06659b9ed17aab0211c6ed1d9ac24c34a274339e498
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8497129d6493f8da5e87279122ae30607c873854fc5accd28f0a0807e632b4d6
+size 1064

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 2200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.3988863229751587,
+      "eval_runtime": 1.1028,
+      "eval_samples_per_second": 452.481,
+      "eval_steps_per_second": 14.508,
+      "step": 220
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.38775110244750977,
+      "eval_runtime": 1.1024,
+      "eval_samples_per_second": 452.63,
+      "eval_steps_per_second": 14.513,
+      "step": 440
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 7.727272727272727e-05,
+      "loss": 0.4642,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.377765029668808,
+      "eval_runtime": 1.1044,
+      "eval_samples_per_second": 451.847,
+      "eval_steps_per_second": 14.488,
+      "step": 660
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.3701080083847046,
+      "eval_runtime": 1.1029,
+      "eval_samples_per_second": 452.461,
+      "eval_steps_per_second": 14.508,
+      "step": 880
+    },
+    {
+      "epoch": 4.55,
+      "learning_rate": 5.4545454545454546e-05,
+      "loss": 0.4438,
+      "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.3616144061088562,
+      "eval_runtime": 1.1041,
+      "eval_samples_per_second": 451.939,
+      "eval_steps_per_second": 14.491,
+      "step": 1100
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.35696589946746826,
+      "eval_runtime": 1.3299,
+      "eval_samples_per_second": 375.212,
+      "eval_steps_per_second": 12.031,
+      "step": 1320
+    },
+    {
+      "epoch": 6.82,
+      "learning_rate": 3.181818181818182e-05,
+      "loss": 0.4262,
+      "step": 1500
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.3518909513950348,
+      "eval_runtime": 1.5297,
+      "eval_samples_per_second": 326.21,
+      "eval_steps_per_second": 10.46,
+      "step": 1540
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.34925374388694763,
+      "eval_runtime": 1.3276,
+      "eval_samples_per_second": 375.855,
+      "eval_steps_per_second": 12.051,
+      "step": 1760
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.34774351119995117,
+      "eval_runtime": 1.3242,
+      "eval_samples_per_second": 376.83,
+      "eval_steps_per_second": 12.083,
+      "step": 1980
+    },
+    {
+      "epoch": 9.09,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 0.4197,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2200,
+  "num_train_epochs": 10,
+  "save_steps": 10,
+  "total_flos": 2380323933388800.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fbcde2f359dc4917eca72b1089679cc09c777556b7d294151cd4c210929d209
+size 4536