ca-finetuned-flan-t5-large

README.md

@@ -0,0 +1,69 @@
+---
+license: apache-2.0
+base_model: google/flan-t5-large
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: ca-finetuned-flan-t5-large
+  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. -->
+
+# ca-finetuned-flan-t5-large
+
+This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 5.3915
+- Accuracy: 0.0667
+
+## 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: 0.0003
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 3.3712        | 1.0   | 23   | 2.8727          | 0.0028   |
+| 1.8522        | 2.0   | 46   | 3.0376          | 0.0333   |
+| 1.0511        | 3.0   | 69   | 3.3480          | 0.0528   |
+| 0.6972        | 4.0   | 92   | 3.7006          | 0.0417   |
+| 0.5066        | 5.0   | 115  | 3.8307          | 0.0556   |
+| 0.3017        | 6.0   | 138  | 4.5624          | 0.0611   |
+| 0.1929        | 7.0   | 161  | 4.6136          | 0.0694   |
+| 0.1591        | 8.0   | 184  | 4.8349          | 0.0611   |
+| 0.1061        | 9.0   | 207  | 5.0931          | 0.0611   |
+| 0.0638        | 10.0  | 230  | 5.3915          | 0.0667   |
+
+
+### Framework versions
+
+- Transformers 4.38.0.dev0
+- Pytorch 2.0.1+cu117
+- Datasets 2.16.1
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "google/flan-t5-large",
+  "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": "4.38.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32128
+}

emissions.csv

@@ -0,0 +1,2 @@
+timestamp,experiment_id,project_name,duration,emissions,energy_consumed,country_name,country_iso_code,region,on_cloud,cloud_provider,cloud_region
+2024-02-15T16:22:42,35663134-39f3-46b0-8561-a98874cd327b,codecarbon,425.9083001613617,0.04518910453572998,0.08451535760263451,Canada,CAN,,N,,

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f543f307bdea6785a50649f02aa2147539d6b41d42b601ec71b124eee62a879f
+size 3132668808

runs/Feb15_15-32-18_c0c8f2aaa2e2/events.out.tfevents.1708011141.c0c8f2aaa2e2.36424.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6d66f21933dbcdb104a25c208a12ca5dca28cd3f475ca0d0b2c7ba3c2e1d6a5
+size 4708

runs/Feb15_15-38-33_c0c8f2aaa2e2/events.out.tfevents.1708011515.c0c8f2aaa2e2.37349.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3cbdcde0b7373d61969455423829c2d02f4c6a7cbf0291511ffc3197ba7a9ad
+size 4708

runs/Feb15_15-39-10_c0c8f2aaa2e2/events.out.tfevents.1708011552.c0c8f2aaa2e2.37553.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec8ecf7bb145a88c6e99acb2c103c6eccfd2e888ed85c8064059dd1f5c2a09c5
+size 4708

runs/Feb15_15-42-28_c0c8f2aaa2e2/events.out.tfevents.1708011751.c0c8f2aaa2e2.37859.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1a5e672d8d293751aea67ee4ef2518004c188133b2720aa63dd4dab7daf5ab4
+size 4708

runs/Feb15_15-48-01_c0c8f2aaa2e2/events.out.tfevents.1708012084.c0c8f2aaa2e2.38411.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d81c9fa69f84f19b23a5e573e2ee1fe2a8e7e50330042c8bb10372d10973cae6
+size 5976

runs/Feb15_16-15-31_c0c8f2aaa2e2/events.out.tfevents.1708013734.c0c8f2aaa2e2.38769.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5017517ee1995b6285cd3de25f7bb6f07f296fa1b01d1947cf9bb508ae5dce44
+size 9817

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fe05791115b36deb55925d39b4eec88a572aba6c8294383f76e6cbf3309223b
+size 4539