End of training

README.md

@@ -1,11 +1,15 @@
 ---
 base_model: sanchit-gandhi/distil-zephyr-1.5b-ssft-ultrachat
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- HuggingFaceH4/ultrachat_200k
 model-index:
 - name: sanchit-gandhi/distil-zephyr-1.5b-ssft-ultrachat
   results: []
@@ -16,7 +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 the generator 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/ultrachat_200k dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.1553
 

config.json

@@ -21,6 +21,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.1",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

wandb/debug-internal.log

@@ -1209,3 +1209,9 @@
 2024-04-26 14:29:57,655 DEBUG   HandlerThread:902882 [handler.py:handle_request():146] handle_request: stop_status
 2024-04-26 14:29:57,656 DEBUG   SenderThread:902882 [sender.py:send_request():406] send_request: stop_status
 2024-04-26 14:29:59,403 INFO    Thread-12 :902882 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat-200k/wandb/run-20240426_141119-5f1mm3ag/files/output.log
+2024-04-26 14:30:01,405 INFO    Thread-12 :902882 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat-200k/wandb/run-20240426_141119-5f1mm3ag/files/output.log
+2024-04-26 14:30:02,406 INFO    Thread-12 :902882 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat-200k/wandb/run-20240426_141119-5f1mm3ag/files/output.log
+2024-04-26 14:30:02,569 DEBUG   HandlerThread:902882 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 14:30:03,407 INFO    Thread-12 :902882 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat-200k/wandb/run-20240426_141119-5f1mm3ag/files/output.log
+2024-04-26 14:30:08,034 DEBUG   HandlerThread:902882 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 14:30:09,413 INFO    Thread-12 :902882 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat-200k/wandb/run-20240426_141119-5f1mm3ag/files/output.log

wandb/run-20240426_141119-5f1mm3ag/files/output.log

@@ -587,3 +587,17 @@ Training completed. Do not forget to share your model on huggingface.co/models =
 [INFO|tokenization_utils_base.py:2488] 2024-04-26 14:29:57,657 >> tokenizer config file saved in ./tokenizer_config.json
 [INFO|tokenization_utils_base.py:2497] 2024-04-26 14:29:57,658 >> Special tokens file saved in ./special_tokens_map.json
 [INFO|modelcard.py:450] 2024-04-26 14:29:57,809 >> Dropping the following result as it does not have all the necessary fields:
+{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}, 'dataset': {'name': 'generator', 'type': 'generator', 'config': 'default', 'split': 'train', 'args': 'default'}}
+events.out.tfevents.1714141786.ip-26-0-165-24.901068.1: 100%|██████████| 359/359 [00:00<00:00, 4.59kB/s]
+2024-04-26 14:30:01 - INFO - __main__ - Model saved to ./
+2024-04-26 14:30:01 - INFO - __main__ - Pushing to hub...
+[INFO|modelcard.py:450] 2024-04-26 14:30:01,559 >> Dropping the following result as it does not have all the necessary fields:
+{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}, 'dataset': {'name': 'HuggingFaceH4/ultrachat_200k', 'type': 'HuggingFaceH4/ultrachat_200k', 'config': 'default', 'split': 'train', 'args': 'default'}}
+[INFO|configuration_utils.py:471] 2024-04-26 14:30:01,563 >> Configuration saved in ./config.json
+[INFO|trainer.py:3305] 2024-04-26 14:30:01,565 >> Saving model checkpoint to ./
+[INFO|configuration_utils.py:471] 2024-04-26 14:30:01,566 >> Configuration saved in ./config.json
+[INFO|configuration_utils.py:697] 2024-04-26 14:30:01,568 >> Configuration saved in ./generation_config.json
+[INFO|modeling_utils.py:2590] 2024-04-26 14:30:06,973 >> Model weights saved in ./model.safetensors
+[INFO|tokenization_utils_base.py:2488] 2024-04-26 14:30:06,976 >> tokenizer config file saved in ./tokenizer_config.json
+[INFO|tokenization_utils_base.py:2497] 2024-04-26 14:30:06,977 >> Special tokens file saved in ./special_tokens_map.json
+[INFO|modelcard.py:450] 2024-04-26 14:30:07,032 >> Dropping the following result as it does not have all the necessary fields:

wandb/run-20240426_141119-5f1mm3ag/logs/debug-internal.log

@@ -1209,3 +1209,9 @@
 2024-04-26 14:29:57,655 DEBUG   HandlerThread:902882 [handler.py:handle_request():146] handle_request: stop_status
 2024-04-26 14:29:57,656 DEBUG   SenderThread:902882 [sender.py:send_request():406] send_request: stop_status
 2024-04-26 14:29:59,403 INFO    Thread-12 :902882 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat-200k/wandb/run-20240426_141119-5f1mm3ag/files/output.log
+2024-04-26 14:30:01,405 INFO    Thread-12 :902882 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat-200k/wandb/run-20240426_141119-5f1mm3ag/files/output.log
+2024-04-26 14:30:02,406 INFO    Thread-12 :902882 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat-200k/wandb/run-20240426_141119-5f1mm3ag/files/output.log
+2024-04-26 14:30:02,569 DEBUG   HandlerThread:902882 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 14:30:03,407 INFO    Thread-12 :902882 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat-200k/wandb/run-20240426_141119-5f1mm3ag/files/output.log
+2024-04-26 14:30:08,034 DEBUG   HandlerThread:902882 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 14:30:09,413 INFO    Thread-12 :902882 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat-200k/wandb/run-20240426_141119-5f1mm3ag/files/output.log