End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: google/mt5-large
+base_model: google/mt5-base
 tags:
 - generated_from_trainer
 model-index:
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # CS505_COQE_mt5-large_train_Instruction0_SOAPL_v1
 
-This model is a fine-tuned version of [google/mt5-large](https://huggingface.co/google/mt5-large) on an unknown dataset.
+This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on an unknown dataset.
 
 ## Model description
 
@@ -33,12 +33,13 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0003
-- train_batch_size: 8
-- eval_batch_size: 16
+- train_batch_size: 16
+- eval_batch_size: 64
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 25
+- mixed_precision_training: Native AMP
 
 ### Training results
 

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "google/mt5-large",
+  "_name_or_path": "google/mt5-base",
   "architectures": [
     "MT5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 2816,
+  "d_ff": 2048,
   "d_kv": 64,
-  "d_model": 1024,
+  "d_model": 768,
   "decoder_start_token_id": 0,
   "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
@@ -17,9 +17,9 @@
   "is_gated_act": true,
   "layer_norm_epsilon": 1e-06,
   "model_type": "mt5",
-  "num_decoder_layers": 24,
-  "num_heads": 16,
-  "num_layers": 24,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:987ab4405551ed5c48205b6001cfc57ccde109748de1db2138c9da7abff8141f
-size 4918393736
+oid sha256:5c5f036c184ab68dfb1b7282a377edc1552b79d442cd03ed44839cbfac772c66
+size 2329638768

runs/Jul08_03-05-46_939c593de51a/events.out.tfevents.1720407947.939c593de51a.14164.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a7f3a7053d4a986fafd27f2a42dadaea35b0a8385c902556c163a69be15403d
+size 5265

runs/Jul08_03-12-50_939c593de51a/events.out.tfevents.1720408371.939c593de51a.16618.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ae34a2ad7f2048b82f9eb1542112f8e13031c39f188b60977411ca44e804c10
+size 5826

runs/Jul08_03-16-57_939c593de51a/events.out.tfevents.1720408618.939c593de51a.16618.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21b79b05521ff5376bce53fe7b9e68b2a46f2b18a79020591fca157a54746870
+size 5618

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7f199d4fa304de5c0e876b3261397f31a50449ac88e1fb9250703215318c429
+oid sha256:4834dc8904d4b10be7d02cdd980943a62c29cf5c26fcc519df05314ac321dce9
 size 5176