mdeputy/output

README.md

@@ -1,65 +1,66 @@
----
-tags:
-- generated_from_trainer
-metrics:
-- f1
-- precision
-- recall
-- accuracy
-model-index:
-- name: output
-  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. -->
-
-# output
-
-This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.3839
-- F1: 0.0
-- Precision: 0.0
-- Recall: 0.0
-- Accuracy: 0.0
-
-## 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: 8
-- eval_batch_size: 8
-- seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 100
-- num_epochs: 1
-
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | F1  | Precision | Recall | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:---:|:---------:|:------:|:--------:|
-| No log        | 1.0   | 12   | 1.3839          | 0.0 | 0.0       | 0.0    | 0.0      |
-
-
-### Framework versions
-
-- Transformers 4.41.2
-- Pytorch 2.3.1+cu121
-- Datasets 2.20.0
-- Tokenizers 0.19.1
+---
+tags:
+- generated_from_trainer
+metrics:
+- f1
+- precision
+- recall
+- accuracy
+model-index:
+- name: output
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/mdeputy-Gleghorn%20Lab/huggingface/runs/c2hwu750)
+# output
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3546
+- F1: 0.0
+- Precision: 0.0
+- Recall: 0.0
+- Accuracy: 0.0
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1  | Precision | Recall | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---:|:---------:|:------:|:--------:|
+| No log        | 1.0   | 12   | 1.3546          | 0.0 | 0.0       | 0.0    | 0.0      |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

config.json

@@ -1,31 +1,31 @@
-{
-  "architectures": [
-    "AttAlexNetForClassification"
-  ],
-  "attention_type": "sdpa",
-  "classifier_dim": 4096,
-  "classifier_dropout": 0.1,
-  "dual_obj": false,
-  "hidden_act": "silu",
-  "hidden_size": 64,
-  "img_size": 1024,
-  "in_channels": 3,
-  "intermediate_size": 1024,
-  "is_causal": false,
-  "max_position_embeddings": 4096,
-  "model_type": "att_alexnet",
-  "moe": false,
-  "n_filts": 4,
-  "num_attention_heads": 8,
-  "num_classes": 3,
-  "num_experts": 8,
-  "num_hidden_layers": 6,
-  "num_layers": 2,
-  "output_router_logits": true,
-  "patch_size": 16,
-  "problem_type": "single_label_classification",
-  "router_aux_loss_coef": 0.01,
-  "topk": 2,
-  "torch_dtype": "float32",
-  "transformers_version": "4.41.2"
-}
+{
+  "architectures": [
+    "AttAlexNetForClassification"
+  ],
+  "attention_type": "sdpa",
+  "classifier_dim": 4096,
+  "classifier_dropout": 0.1,
+  "dual_obj": false,
+  "hidden_act": "silu",
+  "hidden_size": 64,
+  "img_size": 1024,
+  "in_channels": 3,
+  "intermediate_size": 1024,
+  "is_causal": false,
+  "max_position_embeddings": 4096,
+  "model_type": "att_alexnet",
+  "moe": false,
+  "n_filts": 4,
+  "num_attention_heads": 8,
+  "num_classes": 3,
+  "num_experts": 8,
+  "num_hidden_layers": 6,
+  "num_layers": 2,
+  "output_router_logits": true,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "router_aux_loss_coef": 0.01,
+  "topk": 2,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9899c7d40fc35e849b89b4ec543dc48d6092715079b93c3fd81a25a4edef789
+oid sha256:48fb8b6ccb294ad28094830a21ffc4ac5a3c2248faab9ca6ce3dcc074c981b25
 size 127944324

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5a66d978e8cb98dc136203309cce0bf89e5e123b35245583c7c06dfe7c251d0
-size 5112
+oid sha256:56a72c7d512f06b3f59e0d1b6c1079ce04ea733fe2671846e3da70581b341df4
+size 5048