End of training

README.md

@@ -1,8 +1,7 @@
 ---
+library_name: transformers
 tags:
 - generated_from_trainer
-metrics:
-- wer
 model-index:
 - name: output
   results: []
@@ -11,14 +10,18 @@ model-index:
 <!-- 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/priyanshipal/huggingface/runs/hvo6b5jz)
 # output
 
 This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.9947
-- Cer: 0.4133
-- Wer: 0.6195
+- eval_loss: 2.3722
+- eval_model_preparation_time: 0.0044
+- eval_cer: 0.3572
+- eval_wer: 0.5040
+- eval_runtime: 41.1882
+- eval_samples_per_second: 13.887
+- eval_steps_per_second: 0.874
+- step: 0
 
 ## Model description
 
@@ -45,25 +48,13 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 2000
-- training_steps: 6000
+- lr_scheduler_warmup_steps: 500
+- training_steps: 1000
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Cer    | Wer    |
-|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
-| 1.5851        | 1.6   | 1000 | 1.9947          | 0.4133 | 0.6195 |
-| 1.8352        | 3.2   | 2000 | 2.1491          | 0.4724 | 0.7895 |
-| 2.3755        | 4.8   | 3000 | 2.3793          | 0.4433 | 0.7270 |
-| 3.3134        | 6.4   | 4000 | 3.3025          | 0.5204 | 0.8033 |
-| 3.4098        | 8.0   | 5000 | 3.2885          | 0.5196 | 0.8050 |
-| 3.1155        | 9.6   | 6000 | 3.2885          | 0.5196 | 0.8050 |
-
-
 ### Framework versions
 
-- Transformers 4.43.1
+- Transformers 4.45.2
 - Pytorch 2.4.0
 - Datasets 2.20.0
-- Tokenizers 0.19.1
+- Tokenizers 0.20.1

all_results.json

@@ -1,16 +1,10 @@
 {
-    "epoch": 9.6,
-    "eval_cer": 0.4133216406903974,
-    "eval_loss": 1.9947007894515991,
-    "eval_runtime": 158.2803,
-    "eval_samples": 3136,
-    "eval_samples_per_second": 19.813,
-    "eval_steps_per_second": 1.238,
-    "eval_wer": 0.6194798466480157,
-    "total_flos": 3.700768773245485e+19,
-    "train_loss": 2.825458660195271,
-    "train_runtime": 12931.7591,
-    "train_samples": 20000,
-    "train_samples_per_second": 14.847,
-    "train_steps_per_second": 0.464
+    "eval_cer": 0.35724199025542597,
+    "eval_loss": 2.372227191925049,
+    "eval_model_preparation_time": 0.0044,
+    "eval_runtime": 41.1882,
+    "eval_samples": 572,
+    "eval_samples_per_second": 13.887,
+    "eval_steps_per_second": 0.874,
+    "eval_wer": 0.5040222319730876
 }

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/m/triton/scratch/elec/puhe/p/palp3/MUCS/indicwav2vec-hindi",
+  "_name_or_path": "/scratch/elec/puhe/p/palp3/MUCS/indicwav2vec_outputs/pd_warmup500_rerun_latest/output",
   "activation_dropout": 0.0,
   "adapter_attn_dim": null,
   "adapter_kernel_size": 3,

eval_results.json

@@ -1,10 +1,10 @@
 {
-    "epoch": 9.6,
-    "eval_cer": 0.4133216406903974,
-    "eval_loss": 1.9947007894515991,
-    "eval_runtime": 158.2803,
-    "eval_samples": 3136,
-    "eval_samples_per_second": 19.813,
-    "eval_steps_per_second": 1.238,
-    "eval_wer": 0.6194798466480157
+    "eval_cer": 0.35724199025542597,
+    "eval_loss": 2.372227191925049,
+    "eval_model_preparation_time": 0.0044,
+    "eval_runtime": 41.1882,
+    "eval_samples": 572,
+    "eval_samples_per_second": 13.887,
+    "eval_steps_per_second": 0.874,
+    "eval_wer": 0.5040222319730876
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:970b2a5b5fed4e18f8e31dabc4818871b3923a71388caa434be80e585cebee68
+oid sha256:81ae76905e24f861855c984d31eca140c59bb0b9d023d6e279dbc94e7647f56e
 size 1262426580

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88d5758118fce348aebadc5cf828d5353f39c3dd822ba51c3d9b83fec216ffa6
+oid sha256:d4f894ef290b2994d34daec3244b6a38f4886d79722ebb3a09e619200e3ab36a
 size 5496