Training in progress, step 1420

README.md

@@ -1,53 +1,53 @@
----
-library_name: transformers
-license: apache-2.0
-base_model: AndrewOficial/metrology
-tags:
-- generated_from_trainer
-model-index:
-- name: metrology
-  results: []
----
-
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
-# metrology
-
-This model is a fine-tuned version of [AndrewOficial/metrology](https://huggingface.co/AndrewOficial/metrology) on an unknown dataset.
-
-## Model description
-
-More information needed
-
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
-
-More information needed
-
-## Training procedure
-
-### Training hyperparameters
-
-The following hyperparameters were used during training:
-- learning_rate: 1e-05
-- train_batch_size: 1
-- eval_batch_size: 8
-- seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 70
-- num_epochs: 3
-
-### Training results
-
-
-
-### Framework versions
-
-- Transformers 4.44.2
-- Pytorch 2.4.1+cu121
-- Tokenizers 0.19.1
+---
+library_name: transformers
+license: apache-2.0
+base_model: AndrewOficial/metrology
+tags:
+- generated_from_trainer
+model-index:
+- name: metrology
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# metrology
+
+This model is a fine-tuned version of [AndrewOficial/metrology](https://huggingface.co/AndrewOficial/metrology) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 70
+- num_epochs: 2
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.1+cpu
+- Tokenizers 0.19.1

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.1726075576.KO7.6156.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cc548544699b0a6cfa7c8a2d91ac1ca2b3b679fdc9ed2871310a1f67cd2ac54
+size 20363

generation_config.json

@@ -1,7 +1,7 @@
-{
-  "_from_model_config": true,
-  "decoder_start_token_id": 0,
-  "eos_token_id": 1,
-  "pad_token_id": 0,
-  "transformers_version": "4.44.2"
-}
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.44.2"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb9966c94b5ae7abbfbde991f938a1ded3a024be1f5a4ba3a549fcc16ddb2112
+oid sha256:17e432f6d0695838d969b8a120823006dbd7e8d632374e0312acbc62d8487322
 size 2898754440

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7e7745aa51085eba62f2323c1f4673823da132df927fe2bc82a78b407c363ff
+oid sha256:337c28c0899316630827a9cc1225fe2c020e0a1f42d3e9da0297b39f76127b3d
 size 5176