Upload folder using huggingface_hub

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "google/mt5-small",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 1024,
+  "d_kv": 64,
+  "d_model": 512,
+  "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": 8,
+  "num_heads": 6,
+  "num_layers": 8,
+  "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": "4.45.2",
+  "use_cache": true,
+  "vocab_size": 250112
+}

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": "4.45.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e88def7b5276565cf215bfe97b0ffa73cf285b77f47c864c12081fa5254cfea
+size 1200729512

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f07014722b4cdcdde7459547dd45ae7255d344c9b1eb82414fd604e70cf83b4e
+size 2401569018

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:958d01f28cfda0f9e841e629b29bd3e8be4521883d72cff7823d9fadb8cefe44
+size 13990

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d56a5f4b5200eed634adae037a4482980a2b1fb16554bf7f508b2f6b848bb8c9
+size 1064

trainer_state.json

@@ -0,0 +1,78 @@
+{
+  "best_metric": 38.048973083496094,
+  "best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/results_experiment_4/checkpoint-210",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 210,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1462.05419921875,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 50.9406,
+      "step": 70
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 45.00191116333008,
+      "eval_runtime": 68.5228,
+      "eval_samples_per_second": 1.022,
+      "eval_steps_per_second": 0.131,
+      "step": 70
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3524.53125,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 44.4536,
+      "step": 140
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 39.292198181152344,
+      "eval_runtime": 68.6397,
+      "eval_samples_per_second": 1.02,
+      "eval_steps_per_second": 0.131,
+      "step": 140
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3753.434814453125,
+      "learning_rate": 0.0,
+      "loss": 41.8109,
+      "step": 210
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 38.048973083496094,
+      "eval_runtime": 91.0281,
+      "eval_samples_per_second": 0.769,
+      "eval_steps_per_second": 0.099,
+      "step": 210
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 210,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 220885183365120.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:456871e2c61d72601fdb30efe772e3aa01b125a463ca549f019911c790cda8bf
+size 5304