Merge 797e19610f into dc0e64aedf

examples/Chat_finetuning_data_prep.ipynb

@@ -207,7 +207,7 @@
     "2. **Number of Messages Per Example**: Summarizes the distribution of the number of messages in each conversation, providing insight into dialogue complexity.\n",
     "3. **Total Tokens Per Example**: Calculates and summarizes the distribution of the total number of tokens in each conversation. Important for understanding fine-tuning costs.\n",
     "4. **Tokens in Assistant's Messages**: Calculates the number of tokens in the assistant's messages per conversation and summarizes this distribution. Useful for understanding the assistant's verbosity.\n",
-    "5. **Token Limit Warnings**: Checks if any examples exceed the maximum token limit (4096 tokens), as such examples will be truncated during fine-tuning, potentially resulting in data loss.\n"
+    "5. **Token Limit Warnings**: Checks if any examples exceed the maximum token limit (16,385 tokens), as such examples will be truncated during fine-tuning, potentially resulting in data loss.\n"
    ]
   },
   {
@@ -240,7 +240,7 @@
       "mean / median: 1610.2, 10.0\n",
       "p5 / p95: 6.0, 4811.200000000001\n",
       "\n",
-      "1 examples may be over the 4096 token limit, they will be truncated during fine-tuning\n"
+      "0 examples may be over the 16,385 token limit, they will be truncated during fine-tuning\n"
      ]
     }
    ],
@@ -267,8 +267,8 @@
     "print_distribution(n_messages, \"num_messages_per_example\")\n",
     "print_distribution(convo_lens, \"num_total_tokens_per_example\")\n",
     "print_distribution(assistant_message_lens, \"num_assistant_tokens_per_example\")\n",
-    "n_too_long = sum(l > 4096 for l in convo_lens)\n",
-    "print(f\"\\n{n_too_long} examples may be over the 4096 token limit, they will be truncated during fine-tuning\")"
+    "n_too_long = sum(l > 16,385 for l in convo_lens)\n",
+    "print(f\"\\n{n_too_long} examples may be over the 16,385 token limit, they will be truncated during fine-tuning\")"
    ]
   },
   {
@@ -300,7 +300,7 @@
    ],
    "source": [
     "# Pricing and default n_epochs estimate\n",
-    "MAX_TOKENS_PER_EXAMPLE = 4096\n",
+    "MAX_TOKENS_PER_EXAMPLE = 16385\n",
     "\n",
     "TARGET_EPOCHS = 3\n",
     "MIN_TARGET_EXAMPLES = 100\n",