Training in progress, step 1134

config.json

@@ -1,33 +1,33 @@
-{
-  "_name_or_path": "AndrewOficial/metrology",
-  "architectures": [
-    "T5ForConditionalGeneration"
-  ],
-  "classifier_dropout": 0.0,
-  "d_ff": 2816,
-  "d_kv": 64,
-  "d_model": 1024,
-  "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": "t5",
-  "n_positions": 512,
-  "num_decoder_layers": 24,
-  "num_heads": 16,
-  "num_layers": 24,
-  "output_past": true,
-  "pad_token_id": 0,
-  "relative_attention_max_distance": 128,
-  "relative_attention_num_buckets": 32,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.44.2",
-  "use_cache": true,
-  "vocab_size": 3574
-}
+{
+  "_name_or_path": "AndrewOficial/metrology",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2816,
+  "d_kv": 64,
+  "d_model": 1024,
+  "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": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 24,
+  "num_heads": 16,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 3574
+}

events.out.tfevents.1725983167.KO7.7708.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9cbaa48ed48596f966bc77aaead5c5d7be2b4dc91e874854ea083681d4d7a7a
+size 17198

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:153a04cccf7f50dcaebfd148eb124671086339f4e1402e695b67459be87e39e6
+oid sha256:7dfa1c919c0dd67a70e8e05617de67293482148f1d00345a740eed7918e239b0
 size 2898754440

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f861cc4c1bef8c9edfd5d8d682a73ff9e09f1931f9d0966ae1d7100dcb0dabb
+oid sha256:c3afed4a1c7608f1d5c0eb77100ada2ff432f5c3e7fa594d5f89abdef464ae13
 size 5176