Training in progress epoch 0

README.md

@@ -14,8 +14,8 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 9.8474
-- Validation Loss: 4.0982
+- Train Loss: 10.2613
+- Validation Loss: 4.5342
 - Epoch: 0
 
 ## Model description
@@ -42,12 +42,12 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 9.8474     | 4.0982          | 0     |
+| 10.2613    | 4.5342          | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.17.0
-- TensorFlow 2.8.0-rc0
-- Datasets 1.17.0
+- Transformers 4.24.0.dev0
+- TensorFlow 2.10.0
+- Datasets 2.6.1
 - Tokenizers 0.11.0

config.json

@@ -7,21 +7,24 @@
   "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",
-  "transformers_version": "4.17.0",
+  "transformers_version": "4.24.0.dev0",
   "use_cache": true,
   "vocab_size": 250112
 }

special_tokens_map.json

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

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c794e7c894eb31620508997e861d6aeff34adef862099431c899512482efa43c
-size 1201092992
+oid sha256:73be4e9d8d3df22db6675a2f0bbc6738efe6f1f79533417b3739ba7caf3e9d02
+size 2225556432

tokenizer_config.json

@@ -1 +1,11 @@
-{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "special_tokens_map_file": "/home/matt/.cache/huggingface/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "name_or_path": "google/mt5-small", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}
+{
+  "additional_special_tokens": null,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "name_or_path": "google/mt5-small",
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/home/matt/.cache/huggingface/hub/models--google--mt5-small/snapshots/f03a52d3eaa650878b6f52e443bc4d5b385e786e/special_tokens_map.json",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}