End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: google-t5/t5-small
+base_model: google/flan-t5-base
 tags:
 - generated_from_trainer
 metrics:
@@ -15,14 +15,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 # video_prompt_generation
 
-This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on an unknown dataset.
+This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1494
-- Rouge1: 0.0
-- Rouge2: 0.0
-- Rougel: 0.0
-- Rougelsum: 0.0
-- Gen Len: 0.0
+- Loss: nan
+- Rouge1: 0.1089
+- Rouge2: 0.023
+- Rougel: 0.0946
+- Rougelsum: 0.0943
+- Gen Len: 10.5833
 
 ## Model description
 
@@ -47,23 +47,18 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| No log        | 1.0   | 12   | 9.1895          | 0.035  | 0.0027 | 0.032  | 0.0319    | 5.75    |
-| No log        | 2.0   | 24   | 5.4070          | 0.0319 | 0.0    | 0.0291 | 0.0292    | 5.75    |
-| No log        | 3.0   | 36   | 2.9765          | 0.0255 | 0.0    | 0.0228 | 0.0227    | 4.3333  |
-| No log        | 4.0   | 48   | 1.6960          | 0.0117 | 0.0    | 0.0117 | 0.0117    | 1.5     |
-| No log        | 5.0   | 60   | 1.3199          | 0.0029 | 0.0    | 0.0029 | 0.0029    | 0.6667  |
-| No log        | 6.0   | 72   | 1.2154          | 0.0    | 0.0    | 0.0    | 0.0       | 0.0     |
-| No log        | 7.0   | 84   | 1.1874          | 0.0    | 0.0    | 0.0    | 0.0       | 0.0     |
-| No log        | 8.0   | 96   | 1.1794          | 0.0    | 0.0    | 0.0    | 0.0       | 0.0     |
-| No log        | 9.0   | 108  | 1.1652          | 0.0    | 0.0    | 0.0    | 0.0       | 0.0     |
-| No log        | 10.0  | 120  | 1.1494          | 0.0    | 0.0    | 0.0    | 0.0       | 0.0     |
+| No log        | 1.0   | 12   | nan             | 0.1089 | 0.023  | 0.0946 | 0.0943    | 10.5833 |
+| No log        | 2.0   | 24   | nan             | 0.1089 | 0.023  | 0.0946 | 0.0943    | 10.5833 |
+| No log        | 3.0   | 36   | nan             | 0.1089 | 0.023  | 0.0946 | 0.0943    | 10.5833 |
+| No log        | 4.0   | 48   | nan             | 0.1089 | 0.023  | 0.0946 | 0.0943    | 10.5833 |
+| No log        | 5.0   | 60   | nan             | 0.1089 | 0.023  | 0.0946 | 0.0943    | 10.5833 |
 
 
 ### Framework versions

config.json

@@ -1,26 +1,26 @@
 {
-  "_name_or_path": "google-t5/t5-small",
+  "_name_or_path": "google/flan-t5-base",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
   "d_ff": 2048,
   "d_kv": 64,
-  "d_model": 512,
+  "d_model": 768,
   "decoder_start_token_id": 0,
-  "dense_act_fn": "relu",
+  "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
   "eos_token_id": 1,
-  "feed_forward_proj": "relu",
+  "feed_forward_proj": "gated-gelu",
   "initializer_factor": 1.0,
   "is_encoder_decoder": true,
-  "is_gated_act": false,
+  "is_gated_act": true,
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "n_positions": 512,
-  "num_decoder_layers": 6,
-  "num_heads": 8,
-  "num_layers": 6,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,
@@ -54,6 +54,7 @@
       "prefix": "translate English to Romanian: "
     }
   },
+  "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.40.2",
   "use_cache": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c615d805629f7f56737ff8726fe3efe947570aede676bad01008bb226e1913a6
-size 242041896
+oid sha256:197b346658905cda50c1a71fe0eb77a4d79306adaeb5d7a3c0e9208c91022d45
+size 990345064

runs/May12_11-19-03_0a0e4e6f5794/events.out.tfevents.1715512747.0a0e4e6f5794.195.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3fe2080e637a3800ca18e3f90d7357d72acd687b5ad83484d6eb7548b1f19fb
+size 8649

tokenizer_config.json

@@ -932,6 +932,7 @@
   "extra_ids": 100,
   "model_max_length": 512,
   "pad_token": "<pad>",
+  "sp_model_kwargs": {},
   "tokenizer_class": "T5Tokenizer",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b76a47b54fe442d6ee9788c7040b0e85edcbf6c32e8a8dd6be93d324735c2b7
+oid sha256:d259bfb7671380dcc534d3fa99e8f7bad9b2ce5c7babad3cea396278b1c3f6f3
 size 5176