End of training

README.md

@@ -42,9 +42,9 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| No log        | 1.0   | 3    | 0.7431          | 0.5221   | 0.6314 |
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 125  | 4.2178          | 0.0595    | 0.0654 | 0.0623 | 0.4945   |
 
 
 ### Framework versions

config.json

@@ -1,7 +1,7 @@
 {
   "_name_or_path": "google/mt5-small",
   "architectures": [
-    "MT5ForSequenceClassification"
+    "MT5ForTokenClassification"
   ],
   "classifier_dropout": 0.0,
   "d_ff": 1024,
@@ -12,16 +12,33 @@
   "dropout_rate": 0.1,
   "eos_token_id": 1,
   "feed_forward_proj": "gated-gelu",
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6"
+  },
   "initializer_factor": 1.0,
   "is_encoder_decoder": true,
   "is_gated_act": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6
+  },
   "layer_norm_epsilon": 1e-06,
   "model_type": "mt5",
   "num_decoder_layers": 8,
   "num_heads": 6,
   "num_layers": 8,
   "pad_token_id": 0,
-  "problem_type": "single_label_classification",
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
   "tie_word_embeddings": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3acc0e99635cd90d5ced6d3f8cf83eaa9193e567ee00836248d8e0138e685ce
-size 689557432
+oid sha256:9ee4b3beb0258e4bd1c480f201b10586583cf516328cf7ac097e3bc5243cb39c
+size 587786644

runs/Jul17_15-42-05_26b177582b09/events.out.tfevents.1721230927.26b177582b09.255.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7062cdd7b2802e3e89375a4db9f0118e1a898b67eeec0e777d46695eacac1784
+size 6042

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2af95dfdd1aa74173b02a08194ca892df9cff3f25e027449acf814d0a881ea3
+oid sha256:18860ea2a004dfc9ee8c0db72739b4129a360e6d39f8405d4b54c4625b1bc878
 size 5112