End of training

README.md

@@ -13,6 +13,7 @@ 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/ladoza03/huggingface/runs/cuqrcxzo)
 # tst-translation
 
 This model is a fine-tuned version of [ladoza03/tst-translation](https://huggingface.co/ladoza03/tst-translation) on an unknown dataset.
@@ -20,9 +21,9 @@ It achieves the following results on the evaluation set:
 - eval_loss: 1.1219
 - eval_bleu: 30.1585
 - eval_gen_len: 55.5424
-- eval_runtime: 820.9592
-- eval_samples_per_second: 2.457
-- eval_steps_per_second: 0.308
+- eval_runtime: 826.2423
+- eval_samples_per_second: 2.441
+- eval_steps_per_second: 0.306
 - step: 0
 
 ## Model description
@@ -52,7 +53,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.40.0.dev0
+- Transformers 4.41.0.dev0
 - Pytorch 2.1.2
 - Datasets 2.1.0
-- Tokenizers 0.15.2
+- Tokenizers 0.19.1

all_results.json

@@ -2,15 +2,15 @@
     "eval_bleu": 30.1585,
     "eval_gen_len": 55.5424,
     "eval_loss": 1.121874213218689,
-    "eval_runtime": 820.9592,
+    "eval_runtime": 826.2423,
     "eval_samples": 2017,
-    "eval_samples_per_second": 2.457,
-    "eval_steps_per_second": 0.308,
-    "predict_bleu": 29.7226,
-    "predict_gen_len": 55.3034,
-    "predict_loss": 1.1471892595291138,
-    "predict_runtime": 830.1491,
-    "predict_samples": 2017,
-    "predict_samples_per_second": 2.43,
-    "predict_steps_per_second": 0.305
+    "eval_samples_per_second": 2.441,
+    "eval_steps_per_second": 0.306,
+    "predict_bleu": 35.5848,
+    "predict_gen_len": 59.208,
+    "predict_loss": 1.1299843788146973,
+    "predict_runtime": 385.8553,
+    "predict_samples": 1000,
+    "predict_samples_per_second": 2.592,
+    "predict_steps_per_second": 0.324
 }

config.json

@@ -27,7 +27,7 @@
   "tie_word_embeddings": false,
   "tokenizer_class": "T5Tokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.40.0.dev0",
+  "transformers_version": "4.41.0.dev0",
   "use_cache": true,
   "vocab_size": 250112
 }

eval_results.json

@@ -2,8 +2,8 @@
     "eval_bleu": 30.1585,
     "eval_gen_len": 55.5424,
     "eval_loss": 1.121874213218689,
-    "eval_runtime": 820.9592,
+    "eval_runtime": 826.2423,
     "eval_samples": 2017,
-    "eval_samples_per_second": 2.457,
-    "eval_steps_per_second": 0.308
+    "eval_samples_per_second": 2.441,
+    "eval_steps_per_second": 0.306
 }

generation_config.json

@@ -2,5 +2,5 @@
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.40.0.dev0"
+  "transformers_version": "4.41.0.dev0"
 }

predict_results.json

@@ -1,9 +1,9 @@
 {
-    "predict_bleu": 29.7226,
-    "predict_gen_len": 55.3034,
-    "predict_loss": 1.1471892595291138,
-    "predict_runtime": 830.1491,
-    "predict_samples": 2017,
-    "predict_samples_per_second": 2.43,
-    "predict_steps_per_second": 0.305
+    "predict_bleu": 35.5848,
+    "predict_gen_len": 59.208,
+    "predict_loss": 1.1299843788146973,
+    "predict_runtime": 385.8553,
+    "predict_samples": 1000,
+    "predict_samples_per_second": 2.592,
+    "predict_steps_per_second": 0.324
 }

runs/May10_15-50-18_69933a5bff83/events.out.tfevents.1715357146.69933a5bff83.147.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bb015d875f444e4df82fa6f53089035dd3915e3ae378f3c1624b1cbb87f9c77
+size 390

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0910f648726ceada34086ae80066cd253863e183cbb52ae566659a2d37716f0
-size 16330660
+oid sha256:84ec7ac09e74719df0d7ac26684f6bb9939553133a2b7916d91c08ff9d959a2f
+size 16330638

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b21ad9438d948785ae0b1c13cb76a669135fec8766dea2bc2b199ac5c6a644ba
-size 5176
+oid sha256:c62ab815e9eb54bc24ed0c1881b2a1a2de23a5c118a88cc1d3a4991fda38ca1f
+size 5304