init

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "/content/hebrew_summarizer/models/checkpoint-44000",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "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": "mt5",
+  "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": "4.30.2",
+  "use_cache": true,
+  "vocab_size": 250112
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.30.2"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e83037f8ed3c85e1cd2fa8248fb3ab096639488ba06d753ac0b798873ac1a51
+size 2401527173

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceab379fe7bbefa139bd5381d4a387a4b67cdc312873dc6174580237f137aebb
+size 1200772485

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2d3edf11a13b0b4882cd9d9076fde23fe05d6eaaedbcb58e3cddcdb1aebb8dd
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82a87986c5d72439753d5b0829cfc71f7767e5caa2f725fdbfc38243e793de27
+size 627

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db89e268649033b2f206501b13ff4b4edb14f23e84934fb956db725fcacdead8
+size 16330467

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": null,
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,149 @@
+{
+  "best_metric": 2.0858356952667236,
+  "best_model_checkpoint": "./models/checkpoint-70000",
+  "epoch": 0.9752155923041558,
+  "global_step": 70000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.7678058113561536e-05,
+      "loss": 2.5513,
+      "step": 10000
+    },
+    {
+      "epoch": 0.14,
+      "eval_gen_len": 19.0,
+      "eval_loss": 2.201458692550659,
+      "eval_rouge1": 12.1725,
+      "eval_rouge2": 2.4216,
+      "eval_rougeL": 12.077,
+      "eval_rougeLsum": 12.1411,
+      "eval_runtime": 1560.686,
+      "eval_samples_per_second": 8.565,
+      "eval_steps_per_second": 2.141,
+      "step": 10000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.535611622712307e-05,
+      "loss": 2.4881,
+      "step": 20000
+    },
+    {
+      "epoch": 0.28,
+      "eval_gen_len": 19.0,
+      "eval_loss": 2.1785953044891357,
+      "eval_rouge1": 12.7586,
+      "eval_rouge2": 2.6851,
+      "eval_rougeL": 12.6518,
+      "eval_rougeLsum": 12.733,
+      "eval_runtime": 1548.5251,
+      "eval_samples_per_second": 8.633,
+      "eval_steps_per_second": 2.158,
+      "step": 20000
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.3034174340684604e-05,
+      "loss": 2.459,
+      "step": 30000
+    },
+    {
+      "epoch": 0.42,
+      "eval_gen_len": 19.0,
+      "eval_loss": 2.1513352394104004,
+      "eval_rouge1": 12.7004,
+      "eval_rouge2": 2.6318,
+      "eval_rougeL": 12.5832,
+      "eval_rougeLsum": 12.668,
+      "eval_runtime": 1564.1475,
+      "eval_samples_per_second": 8.547,
+      "eval_steps_per_second": 2.137,
+      "step": 30000
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.071223245424614e-05,
+      "loss": 2.4361,
+      "step": 40000
+    },
+    {
+      "epoch": 0.56,
+      "eval_gen_len": 19.0,
+      "eval_loss": 2.127916097640991,
+      "eval_rouge1": 13.1946,
+      "eval_rouge2": 2.8216,
+      "eval_rougeL": 13.0738,
+      "eval_rougeLsum": 13.1592,
+      "eval_runtime": 1584.478,
+      "eval_samples_per_second": 8.437,
+      "eval_steps_per_second": 2.109,
+      "step": 40000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.8390290567807665e-05,
+      "loss": 2.4613,
+      "step": 50000
+    },
+    {
+      "epoch": 0.7,
+      "eval_gen_len": 19.0,
+      "eval_loss": 2.098001003265381,
+      "eval_rouge1": 12.8818,
+      "eval_rouge2": 2.8541,
+      "eval_rougeL": 12.7484,
+      "eval_rougeLsum": 12.8289,
+      "eval_runtime": 1565.1942,
+      "eval_samples_per_second": 8.541,
+      "eval_steps_per_second": 2.135,
+      "step": 50000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.60683486813692e-05,
+      "loss": 2.462,
+      "step": 60000
+    },
+    {
+      "epoch": 0.84,
+      "eval_gen_len": 19.0,
+      "eval_loss": 2.0897421836853027,
+      "eval_rouge1": 13.1141,
+      "eval_rouge2": 2.8014,
+      "eval_rougeL": 12.9971,
+      "eval_rougeLsum": 13.0729,
+      "eval_runtime": 1561.4037,
+      "eval_samples_per_second": 8.562,
+      "eval_steps_per_second": 2.14,
+      "step": 60000
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.374640679493074e-05,
+      "loss": 2.4478,
+      "step": 70000
+    },
+    {
+      "epoch": 0.98,
+      "eval_gen_len": 19.0,
+      "eval_loss": 2.0858356952667236,
+      "eval_rouge1": 13.4344,
+      "eval_rouge2": 2.8499,
+      "eval_rougeL": 13.3259,
+      "eval_rougeLsum": 13.3837,
+      "eval_runtime": 1559.9208,
+      "eval_samples_per_second": 8.57,
+      "eval_steps_per_second": 2.142,
+      "step": 70000
+    }
+  ],
+  "max_steps": 215337,
+  "num_train_epochs": 3,
+  "total_flos": 1.4804990931554304e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6cdf79feb16462aaa6f18f133df1146ff7f580dd53b238414315da0603c0b1c
+size 4091