End of training

README.md

@@ -1,11 +1,15 @@
 ---
 base_model: PolyAgent/mistral-7b-v0.3-ua-tokenizer-v2-focus-base
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- PolyAgent/wiki_uk_en_parallel
 model-index:
 - name: mistral-v0.3-tokV2-gentle-train
   results: []
@@ -16,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mistral-v0.3-tokV2-gentle-train
 
-This model is a fine-tuned version of [PolyAgent/mistral-7b-v0.3-ua-tokenizer-v2-focus-base](https://huggingface.co/PolyAgent/mistral-7b-v0.3-ua-tokenizer-v2-focus-base) on the generator dataset.
+This model is a fine-tuned version of [PolyAgent/mistral-7b-v0.3-ua-tokenizer-v2-focus-base](https://huggingface.co/PolyAgent/mistral-7b-v0.3-ua-tokenizer-v2-focus-base) on the PolyAgent/wiki_uk_en_parallel dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.0765
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 3.0,
+    "eval_loss": 1.0764902830123901,
+    "eval_runtime": 4.3265,
+    "eval_samples": 1780,
+    "eval_samples_per_second": 91.529,
+    "eval_steps_per_second": 3.005,
     "total_flos": 1.06516665335808e+16,
     "train_loss": 1.2970494811368156,
     "train_runtime": 158321.4888,

config.json

@@ -22,6 +22,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32768
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.0764902830123901,
+    "eval_runtime": 4.3265,
+    "eval_samples": 1780,
+    "eval_samples_per_second": 91.529,
+    "eval_steps_per_second": 3.005
+}

runs/Sep18_16-01-16_ip-10-1-73-211/events.out.tfevents.1726835561.ip-10-1-73-211.186164.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15d5510f319d35d82aa2a326057efa40c48633f6638b97c1d057158b63d68705
+size 364