base 500k samples 4 epochs total (checkpoint trained)

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "Jayveersinh-Raj/guj-grammar-base",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "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": "mt5",
+  "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,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.2",
+  "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": "4.33.2"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:114407f6d2c32aa02f7d46ee665f0948ce1f11842409f8ddbb95ad5d38e1c95d
+size 4659447661

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d1be8566ca513b07a80ccc844c0dc9a3d3299f1893125592a2b5d35ee434e65
+size 2329702581

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e1ebc939c431e0d0a873844d29c6d4306286ace18a383582b3d0aded278cd7f
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c1e2f83fc1737955ca5dbbf89ec1dec84e89ca11ede4c6b0789e0988e8afa22
+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 sha256:6502d07619068a98aa2d3bb531332a694ffe108ca6c6fe62a467ccfe98d666b9
+size 16315219

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "additional_special_tokens": null,
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "legacy": true,
+  "max_length": 128,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "stride": 0,
+  "tokenizer_class": "T5Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,104 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9715578539107952,
+  "eval_steps": 500,
+  "global_step": 6100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.8383968972204266e-05,
+      "loss": 0.144,
+      "step": 500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.6767937944408533e-05,
+      "loss": 0.137,
+      "step": 1000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.51519069166128e-05,
+      "loss": 0.1307,
+      "step": 1500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.3535875888817068e-05,
+      "loss": 0.1263,
+      "step": 2000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.1919844861021333e-05,
+      "loss": 0.1241,
+      "step": 2500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.0303813833225597e-05,
+      "loss": 0.12,
+      "step": 3000
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 18.2165,
+      "eval_loss": 0.06346726417541504,
+      "eval_rouge1": 0.1191,
+      "eval_rouge2": 0.0373,
+      "eval_rougeL": 0.1197,
+      "eval_rougeLsum": 0.1193,
+      "eval_runtime": 34.2167,
+      "eval_samples_per_second": 58.451,
+      "eval_steps_per_second": 0.935,
+      "step": 3094
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 8.687782805429864e-06,
+      "loss": 0.1159,
+      "step": 3500
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 7.071751777634132e-06,
+      "loss": 0.1147,
+      "step": 4000
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 5.4557207498383965e-06,
+      "loss": 0.1122,
+      "step": 4500
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 3.839689722042664e-06,
+      "loss": 0.111,
+      "step": 5000
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 2.2236586942469294e-06,
+      "loss": 0.1104,
+      "step": 5500
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 6.076276664511959e-07,
+      "loss": 0.1089,
+      "step": 6000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6188,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "total_flos": 1.1413435354310246e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a7665e49347f091fdd3ec5c4781be8ca50d62bc8ab272e8cc0e27b3ca1b1631
+size 4155