End of training

README.md

@@ -1,9 +1,15 @@
 ---
 base_model: sanchit-gandhi/distil-zephyr-1.5b-ssft-ultrachat
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: sanchit-gandhi/distil-zephyr-1.5b-ssft-ultrachat
   results: []
@@ -14,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # sanchit-gandhi/distil-zephyr-1.5b-ssft-ultrachat
 
-This model is a fine-tuned version of [sanchit-gandhi/distil-zephyr-1.5b-ssft-ultrachat](https://huggingface.co/sanchit-gandhi/distil-zephyr-1.5b-ssft-ultrachat) on an unknown dataset.
+This model is a fine-tuned version of [sanchit-gandhi/distil-zephyr-1.5b-ssft-ultrachat](https://huggingface.co/sanchit-gandhi/distil-zephyr-1.5b-ssft-ultrachat) on the HuggingFaceH4/ultrafeedback_binarized dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.6412
 - Rewards/chosen: -0.1044

config.json

@@ -21,6 +21,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.40.1",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

wandb/debug-internal.log

@@ -952,3 +952,15 @@
 2024-04-26 16:12:13,359 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
 2024-04-26 16:12:16,352 DEBUG   SenderThread:713738 [sender.py:send():379] send: stats
 2024-04-26 16:12:18,516 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:12:21,271 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:12:22,121 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:12:22,121 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:12:22,121 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
+2024-04-26 16:12:23,708 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:12:25,275 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:12:28,710 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:12:33,787 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:12:35,286 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:12:37,121 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:12:37,121 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:12:37,121 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status

wandb/run-20240426_155715-vljs8xzo/files/output.log

@@ -450,3 +450,16 @@ events.out.tfevents.1714147034.ip-26-0-160-225.711598.0:   0%|          | 0.00/2
 
 
 
+Upload 4 LFS files: 100%|██████████| 4/4 [01:26<00:00, 21.75s/it]0:24<00:00, 57.8MB/s]:00<?, ?B/s]
+[INFO|modelcard.py:450] 2024-04-26 16:12:22,694 >> Dropping the following result as it does not have all the necessary fields:
+{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}, 'dataset': {'name': 'HuggingFaceH4/ultrafeedback_binarized', 'type': 'HuggingFaceH4/ultrafeedback_binarized'}}
+[INFO|configuration_utils.py:471] 2024-04-26 16:12:22,700 >> Configuration saved in ./config.json
+[INFO|trainer.py:3305] 2024-04-26 16:12:22,704 >> Saving model checkpoint to ./
+[INFO|configuration_utils.py:471] 2024-04-26 16:12:22,706 >> Configuration saved in ./config.json
+[INFO|configuration_utils.py:697] 2024-04-26 16:12:22,708 >> Configuration saved in ./generation_config.json
+2024-04-26 16:12:22 - INFO - __main__ - Model saved to ./
+2024-04-26 16:12:22 - INFO - __main__ - Pushing to hub...
+[INFO|modeling_utils.py:2598] 2024-04-26 16:12:33,635 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 2 checkpoint shards. You can find where each parameters has been saved in the index located at ./model.safetensors.index.json.
+[INFO|tokenization_utils_base.py:2488] 2024-04-26 16:12:33,638 >> tokenizer config file saved in ./tokenizer_config.json
+[INFO|tokenization_utils_base.py:2497] 2024-04-26 16:12:33,640 >> Special tokens file saved in ./special_tokens_map.json
+[INFO|modelcard.py:450] 2024-04-26 16:12:33,786 >> Dropping the following result as it does not have all the necessary fields:

wandb/run-20240426_155715-vljs8xzo/logs/debug-internal.log

@@ -952,3 +952,15 @@
 2024-04-26 16:12:13,359 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
 2024-04-26 16:12:16,352 DEBUG   SenderThread:713738 [sender.py:send():379] send: stats
 2024-04-26 16:12:18,516 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:12:21,271 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:12:22,121 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:12:22,121 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:12:22,121 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
+2024-04-26 16:12:23,708 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:12:25,275 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:12:28,710 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:12:33,787 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:12:35,286 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:12:37,121 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:12:37,121 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:12:37,121 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status