Upload 8 files

config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "google/flan-t5-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "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",
+  "n_positions": 512,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "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: "
+    }
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 32128
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.37.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5098457d90f87ef10ebeec3fde6cd89f5a9c9f362b77cb1134e5acaaa71ff7b2
+size 990345064

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b24a7a4cdd0cdec0a74f10864aecf2539450a6c0386b5337bb0dd4cc831ed02
+size 1980860410

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a11ef4320e95074f08e8bda003554ebbcb57b7633319a235f9d1e8b878bc7503
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d3440efa4944ce6c2eabfac8f9c0b04613f5513e70b2e20bef1733e3ccc9139
+size 1064

trainer_state.json

@@ -0,0 +1,194 @@
+{
+  "best_metric": 1.3700677156448364,
+  "best_model_checkpoint": "/content/drive/MyDrive/Graduation_Models/Summary_Model/output/checkpoint-7368",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 9210,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.728555917480999e-05,
+      "loss": 1.4736,
+      "step": 500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.457111834961998e-05,
+      "loss": 1.44,
+      "step": 1000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.185667752442997e-05,
+      "loss": 1.4497,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 17.29181929181929,
+      "eval_loss": 1.3855763673782349,
+      "eval_rouge1": 46.4182,
+      "eval_rouge2": 22.6793,
+      "eval_rougeL": 38.696,
+      "eval_rougeLsum": 42.6475,
+      "eval_runtime": 121.3592,
+      "eval_samples_per_second": 6.749,
+      "eval_steps_per_second": 0.849,
+      "step": 1842
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 3.914223669923996e-05,
+      "loss": 1.4192,
+      "step": 2000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 3.642779587404995e-05,
+      "loss": 1.3345,
+      "step": 2500
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 3.3713355048859935e-05,
+      "loss": 1.3562,
+      "step": 3000
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 3.099891422366993e-05,
+      "loss": 1.3474,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 17.273504273504273,
+      "eval_loss": 1.3723567724227905,
+      "eval_rouge1": 47.1674,
+      "eval_rouge2": 23.3092,
+      "eval_rougeL": 39.4164,
+      "eval_rougeLsum": 43.3552,
+      "eval_runtime": 119.0693,
+      "eval_samples_per_second": 6.878,
+      "eval_steps_per_second": 0.865,
+      "step": 3684
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 2.8284473398479917e-05,
+      "loss": 1.2971,
+      "step": 4000
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 2.5570032573289905e-05,
+      "loss": 1.2711,
+      "step": 4500
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 2.2855591748099893e-05,
+      "loss": 1.2859,
+      "step": 5000
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 2.0141150922909884e-05,
+      "loss": 1.2818,
+      "step": 5500
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 17.247863247863247,
+      "eval_loss": 1.3706920146942139,
+      "eval_rouge1": 47.4185,
+      "eval_rouge2": 23.5442,
+      "eval_rougeL": 39.7883,
+      "eval_rougeLsum": 43.4867,
+      "eval_runtime": 118.5587,
+      "eval_samples_per_second": 6.908,
+      "eval_steps_per_second": 0.869,
+      "step": 5526
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 1.742671009771987e-05,
+      "loss": 1.2272,
+      "step": 6000
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 1.471226927252986e-05,
+      "loss": 1.2389,
+      "step": 6500
+    },
+    {
+      "epoch": 3.8,
+      "learning_rate": 1.1997828447339848e-05,
+      "loss": 1.2285,
+      "step": 7000
+    },
+    {
+      "epoch": 4.0,
+      "eval_gen_len": 17.35286935286935,
+      "eval_loss": 1.3700677156448364,
+      "eval_rouge1": 47.4833,
+      "eval_rouge2": 23.614,
+      "eval_rougeL": 39.8945,
+      "eval_rougeLsum": 43.6297,
+      "eval_runtime": 118.838,
+      "eval_samples_per_second": 6.892,
+      "eval_steps_per_second": 0.867,
+      "step": 7368
+    },
+    {
+      "epoch": 4.07,
+      "learning_rate": 9.283387622149838e-06,
+      "loss": 1.1985,
+      "step": 7500
+    },
+    {
+      "epoch": 4.34,
+      "learning_rate": 6.568946796959827e-06,
+      "loss": 1.1972,
+      "step": 8000
+    },
+    {
+      "epoch": 4.61,
+      "learning_rate": 3.854505971769816e-06,
+      "loss": 1.2093,
+      "step": 8500
+    },
+    {
+      "epoch": 4.89,
+      "learning_rate": 1.1400651465798045e-06,
+      "loss": 1.196,
+      "step": 9000
+    },
+    {
+      "epoch": 5.0,
+      "eval_gen_len": 17.313797313797313,
+      "eval_loss": 1.3741676807403564,
+      "eval_rouge1": 47.4109,
+      "eval_rouge2": 23.6186,
+      "eval_rougeL": 39.6383,
+      "eval_rougeLsum": 43.5567,
+      "eval_runtime": 122.3234,
+      "eval_samples_per_second": 6.695,
+      "eval_steps_per_second": 0.842,
+      "step": 9210
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9210,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 5.048305105187635e+16,
+  "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 sha256:6a639ab2b24605f3acffac838cf390754b379d999fa1d31893617559394994dd
+size 4920