flatten the repo to one model

README.md

@@ -53,11 +53,18 @@ The demo uses 40%.
 
 These numbers come from 5,000 places in emails from people the model never saw in training. "Right" means the suggestion exactly matched what the person typed next. Right suggestions are about 6 characters long on average.
 
-## Which file to use
+## Files
 
-Use `gru-512/model_quint8.onnx`. Everything on this page is about that model.
+| File | What it is |
+|---|---|
+| `model_quint8.onnx` | The model to use. 0.98 MB. |
+| `model.onnx` | The same model before shrinking. 3.8 MB. |
+| `best.pt` | The PyTorch checkpoint. |
+| `vocab.json` | The character ids. |
+| `report.json` | The full training and test results. |
+| `train.py` | The training script. |
 
-I also tried a bigger version with 3.46M parameters and 3.5 MB. It wasn't better. When both models suggest equally often, 9% of the time, the small one is right about 85% of the time and the big one 82%. The big one got the same training settings and may need different ones to do well. Its test results are in [`gru-1024/report.json`](gru-1024/report.json).
+I also tried a bigger version with 3.46M parameters and 3.5 MB. It wasn't better. When both models suggest equally often, 9% of the time, the small one is right about 85% of the time and the big one 82%. The big one got the same training settings and may need different ones to do well.
 
 ## Use it
 
@@ -66,7 +73,7 @@ The model takes one character and its memory of the text so far. It returns its
 ```js
 import * as ort from "onnxruntime-web";
 
-const session = await ort.InferenceSession.create("gru-512/model_quint8.onnx", {
+const session = await ort.InferenceSession.create("model_quint8.onnx", {
   executionProviders: ["wasm"],
 });
 let state = new ort.Tensor("float32", new Float32Array(512), [1, 512]);

gru-1024/report.json

@@ -1,548 +0,0 @@
-{
-  "args": {
-    "hidden": 1024,
-    "epochs": 30,
-    "batch": 256,
-    "seq": 256,
-    "burn_in": 32,
-    "lr": 0.0015,
-    "typo_rate": 0.08,
-    "limit_frac": 1.0,
-    "eval_positions": 5000,
-    "context": 128,
-    "horizon": 48,
-    "repo": "cfahlgren1/email-autocomplete-gru",
-    "run_name": "gru-1024",
-    "no_push": false
-  },
-  "device": "cuda",
-  "parameters": 3455202,
-  "data": {
-    "train": {
-      "emails": 119859,
-      "chars": 40136658
-    },
-    "val": {
-      "emails": 8252,
-      "chars": 2775980
-    },
-    "test": {
-      "emails": 6922,
-      "chars": 2710169
-    }
-  },
-  "history": [
-    {
-      "epoch": 1,
-      "train_loss": 1.8596,
-      "val_loss": 1.5191,
-      "seconds": 55.7,
-      "chars_per_sec": 720188
-    },
-    {
-      "epoch": 2,
-      "train_loss": 1.4333,
-      "val_loss": 1.4266,
-      "seconds": 55.5,
-      "chars_per_sec": 723185
-    },
-    {
-      "epoch": 3,
-      "train_loss": 1.3665,
-      "val_loss": 1.3819,
-      "seconds": 55.4,
-      "chars_per_sec": 723324
-    },
-    {
-      "epoch": 4,
-      "train_loss": 1.3315,
-      "val_loss": 1.362,
-      "seconds": 55.5,
-      "chars_per_sec": 723075
-    },
-    {
-      "epoch": 5,
-      "train_loss": 1.3059,
-      "val_loss": 1.3342,
-      "seconds": 55.5,
-      "chars_per_sec": 722890
-    },
-    {
-      "epoch": 6,
-      "train_loss": 1.2868,
-      "val_loss": 1.3185,
-      "seconds": 55.5,
-      "chars_per_sec": 722953
-    },
-    {
-      "epoch": 7,
-      "train_loss": 1.2707,
-      "val_loss": 1.3043,
-      "seconds": 55.5,
-      "chars_per_sec": 723013
-    },
-    {
-      "epoch": 8,
-      "train_loss": 1.2574,
-      "val_loss": 1.2968,
-      "seconds": 55.4,
-      "chars_per_sec": 723400
-    },
-    {
-      "epoch": 9,
-      "train_loss": 1.2459,
-      "val_loss": 1.2835,
-      "seconds": 55.5,
-      "chars_per_sec": 723045
-    },
-    {
-      "epoch": 10,
-      "train_loss": 1.2354,
-      "val_loss": 1.2769,
-      "seconds": 55.5,
-      "chars_per_sec": 722475
-    },
-    {
-      "epoch": 11,
-      "train_loss": 1.2265,
-      "val_loss": 1.2713,
-      "seconds": 55.5,
-      "chars_per_sec": 722542
-    },
-    {
-      "epoch": 12,
-      "train_loss": 1.2184,
-      "val_loss": 1.2632,
-      "seconds": 55.4,
-      "chars_per_sec": 723603
-    },
-    {
-      "epoch": 13,
-      "train_loss": 1.2111,
-      "val_loss": 1.2572,
-      "seconds": 55.7,
-      "chars_per_sec": 720567
-    },
-    {
-      "epoch": 14,
-      "train_loss": 1.2039,
-      "val_loss": 1.2495,
-      "seconds": 55.5,
-      "chars_per_sec": 723089
-    },
-    {
-      "epoch": 15,
-      "train_loss": 1.1984,
-      "val_loss": 1.2443,
-      "seconds": 55.4,
-      "chars_per_sec": 723365
-    },
-    {
-      "epoch": 16,
-      "train_loss": 1.1929,
-      "val_loss": 1.2407,
-      "seconds": 55.4,
-      "chars_per_sec": 723319
-    },
-    {
-      "epoch": 17,
-      "train_loss": 1.1875,
-      "val_loss": 1.2363,
-      "seconds": 55.4,
-      "chars_per_sec": 723459
-    },
-    {
-      "epoch": 18,
-      "train_loss": 1.1832,
-      "val_loss": 1.2317,
-      "seconds": 55.4,
-      "chars_per_sec": 723834
-    },
-    {
-      "epoch": 19,
-      "train_loss": 1.1786,
-      "val_loss": 1.2282,
-      "seconds": 55.4,
-      "chars_per_sec": 723621
-    },
-    {
-      "epoch": 20,
-      "train_loss": 1.1746,
-      "val_loss": 1.225,
-      "seconds": 55.4,
-      "chars_per_sec": 723320
-    },
-    {
-      "epoch": 21,
-      "train_loss": 1.1708,
-      "val_loss": 1.2223,
-      "seconds": 55.5,
-      "chars_per_sec": 722922
-    },
-    {
-      "epoch": 22,
-      "train_loss": 1.1676,
-      "val_loss": 1.2203,
-      "seconds": 55.5,
-      "chars_per_sec": 723142
-    },
-    {
-      "epoch": 23,
-      "train_loss": 1.1647,
-      "val_loss": 1.217,
-      "seconds": 55.5,
-      "chars_per_sec": 723245
-    },
-    {
-      "epoch": 24,
-      "train_loss": 1.1615,
-      "val_loss": 1.2153,
-      "seconds": 55.4,
-      "chars_per_sec": 723442
-    },
-    {
-      "epoch": 25,
-      "train_loss": 1.1597,
-      "val_loss": 1.2136,
-      "seconds": 55.5,
-      "chars_per_sec": 723051
-    },
-    {
-      "epoch": 26,
-      "train_loss": 1.1576,
-      "val_loss": 1.2121,
-      "seconds": 55.4,
-      "chars_per_sec": 723355
-    },
-    {
-      "epoch": 27,
-      "train_loss": 1.1561,
-      "val_loss": 1.211,
-      "seconds": 55.4,
-      "chars_per_sec": 723432
-    },
-    {
-      "epoch": 28,
-      "train_loss": 1.1549,
-      "val_loss": 1.2102,
-      "seconds": 55.5,
-      "chars_per_sec": 723253
-    },
-    {
-      "epoch": 29,
-      "train_loss": 1.1539,
-      "val_loss": 1.2099,
-      "seconds": 55.4,
-      "chars_per_sec": 723672
-    },
-    {
-      "epoch": 30,
-      "train_loss": 1.1537,
-      "val_loss": 1.2093,
-      "seconds": 55.4,
-      "chars_per_sec": 723458
-    }
-  ],
-  "best_val_loss": 1.2093,
-  "test_positions": 5000,
-  "held_out_sender_suggestions": {
-    "0.05": {
-      "coverage": 0.5678,
-      "precision": 0.2194,
-      "avg_chars_when_correct": 6.43,
-      "chars_saved_per_position": 0.801
-    },
-    "0.1": {
-      "coverage": 0.4106,
-      "precision": 0.3307,
-      "avg_chars_when_correct": 6.03,
-      "chars_saved_per_position": 0.818
-    },
-    "0.2": {
-      "coverage": 0.2506,
-      "precision": 0.4932,
-      "avg_chars_when_correct": 5.83,
-      "chars_saved_per_position": 0.721
-    },
-    "0.35": {
-      "coverage": 0.1418,
-      "precision": 0.6756,
-      "avg_chars_when_correct": 5.59,
-      "chars_saved_per_position": 0.535
-    },
-    "0.5": {
-      "coverage": 0.0894,
-      "precision": 0.8188,
-      "avg_chars_when_correct": 5.53,
-      "chars_saved_per_position": 0.405
-    },
-    "0.7": {
-      "coverage": 0.0512,
-      "precision": 0.9375,
-      "avg_chars_when_correct": 5.12,
-      "chars_saved_per_position": 0.246
-    }
-  },
-  "exports": {
-    "float": {
-      "size_mb": 13.82,
-      "native_cpu_single_thread_step": {
-        "p50_ms": 0.459,
-        "p95_ms": 0.497
-      },
-      "suggestions_1000_positions": {
-        "0.05": {
-          "coverage": 0.569,
-          "precision": 0.2162,
-          "avg_chars_when_correct": 6.09,
-          "chars_saved_per_position": 0.749
-        },
-        "0.1": {
-          "coverage": 0.415,
-          "precision": 0.3373,
-          "avg_chars_when_correct": 5.91,
-          "chars_saved_per_position": 0.827
-        },
-        "0.2": {
-          "coverage": 0.268,
-          "precision": 0.4851,
-          "avg_chars_when_correct": 5.83,
-          "chars_saved_per_position": 0.758
-        },
-        "0.35": {
-          "coverage": 0.151,
-          "precision": 0.6291,
-          "avg_chars_when_correct": 5.56,
-          "chars_saved_per_position": 0.528
-        },
-        "0.5": {
-          "coverage": 0.088,
-          "precision": 0.7727,
-          "avg_chars_when_correct": 5.6,
-          "chars_saved_per_position": 0.381
-        },
-        "0.7": {
-          "coverage": 0.054,
-          "precision": 0.9444,
-          "avg_chars_when_correct": 5.06,
-          "chars_saved_per_position": 0.258
-        }
-      }
-    },
-    "quint8": {
-      "size_mb": 3.5,
-      "native_cpu_single_thread_step": {
-        "p50_ms": 0.132,
-        "p95_ms": 0.192
-      },
-      "suggestions_1000_positions": {
-        "0.05": {
-          "coverage": 0.574,
-          "precision": 0.2108,
-          "avg_chars_when_correct": 6.06,
-          "chars_saved_per_position": 0.733
-        },
-        "0.1": {
-          "coverage": 0.42,
-          "precision": 0.3167,
-          "avg_chars_when_correct": 5.9,
-          "chars_saved_per_position": 0.785
-        },
-        "0.2": {
-          "coverage": 0.262,
-          "precision": 0.4809,
-          "avg_chars_when_correct": 5.73,
-          "chars_saved_per_position": 0.722
-        },
-        "0.35": {
-          "coverage": 0.156,
-          "precision": 0.6346,
-          "avg_chars_when_correct": 5.57,
-          "chars_saved_per_position": 0.551
-        },
-        "0.5": {
-          "coverage": 0.085,
-          "precision": 0.8235,
-          "avg_chars_when_correct": 5.57,
-          "chars_saved_per_position": 0.39
-        },
-        "0.7": {
-          "coverage": 0.052,
-          "precision": 0.9231,
-          "avg_chars_when_correct": 5.17,
-          "chars_saved_per_position": 0.248
-        }
-      }
-    }
-  },
-  "prompt_samples": {
-    "Hi John,\n\nThanks for ": {
-      "continuation": "the message. I will be out of the office on Mond",
-      "suggestion_at_0.2": "the"
-    },
-    "Please let me know if ": {
-      "continuation": "you have any questions.\n\nThanks,\n\nKayI have a c",
-      "suggestion_at_0.2": "you have any questions."
-    },
-    "I will send you ": {
-      "continuation": "a copy of the following products and address and",
-      "suggestion_at_0.2": "a"
-    },
-    "Let me kn": {
-      "continuation": "ow if you have any questions.\n\nThanks,\n\nKayI ha",
-      "suggestion_at_0.2": "ow if you have"
-    },
-    "Thnaks for the ": {
-      "continuation": "attached file. I will be out of the office on Mo",
-      "suggestion_at_0.2": ""
-    },
-    "I look forward to ": {
-      "continuation": "seeing you and I will be out of the office on Mo",
-      "suggestion_at_0.2": ""
-    },
-    "Can we schedule a ": {
-      "continuation": "copy of the following products to the contract a",
-      "suggestion_at_0.2": ""
-    },
-    "Sorry for the dela": {
-      "continuation": "y. I will be out of the office on Monday and we ",
-      "suggestion_at_0.2": "y."
-    },
-    "Plese find attached ": {
-      "continuation": "the following agreements for the Enron Corp. and",
-      "suggestion_at_0.2": "the"
-    },
-    "We need to discuss ": {
-      "continuation": "the contract for the contract and the contract w",
-      "suggestion_at_0.2": "the"
-    }
-  },
-  "held_out_examples": [
-    {
-      "context": "ou trading a book yet? Playing any poker? Bingham was here f",
-      "truth": "or Q-School last week. Didn't go so well.",
-      "suggestion_at_0.2": "or"
-    },
-    {
-      "context": "Please use this model. I had a few change",
-      "truth": "s after talking to the guys in the west. Thanks!",
-      "suggestion_at_0.2": "s to"
-    },
-    {
-      "context": "not open the attachment. Please, send it as a MS Word docume",
-      "truth": "nt or a .pdf file.",
-      "suggestion_at_0.2": "nt"
-    },
-    {
-      "context": "n I do to help. I would also like to visit on status of e*p ",
-      "truth": "group and mariner.",
-      "suggestion_at_0.2": ""
-    },
-    {
-      "context": " complete hourly schedule for June 1, including IBM and inco",
-      "truth": "rporating all known changes confirmed by that ti",
-      "suggestion_at_0.2": "rporated"
-    },
-    {
-      "context": " delivery rights at SoCal/Topock for at least a pro rata por",
-      "truth": "tion of its released capacity.",
-      "suggestion_at_0.2": "tion of"
-    },
-    {
-      "context": "i talked to chris a li",
-      "truth": "ttle bit and he is going to call back tonight at",
-      "suggestion_at_0.2": "ttle"
-    },
-    {
-      "context": " I might be missing something about the way you guys do thes",
-      "truth": "e deals in Canada so I thought I would run this ",
-      "suggestion_at_0.2": "e"
-    },
-    {
-      "context": "Traci,\n\nThanks. This is the best solution given all the unce",
-      "truth": "rtainties we face.",
-      "suggestion_at_0.2": "rtainty"
-    },
-    {
-      "context": "\nAquila,s strategy comes as little surprise to Stuebi. As mu",
-      "truth": "ch success as the company has had, he said he th",
-      "suggestion_at_0.2": "ch"
-    },
-    {
-      "context": "Jim,\n\nWhat about 2 p.m., my time, on Friday, Au",
-      "truth": "gust 17. If this works for you, I shall try to i",
-      "suggestion_at_0.2": "gust"
-    },
-    {
-      "context": "'s and CDD's for Philedelphia, Allentown Washington DC, Balt",
-      "truth": "imore, Pittsburg, Newark, New York City, Cinncin",
-      "suggestion_at_0.2": ""
-    },
-    {
-      "context": " release.\n\nThe company will offer derivatives to hedge volat",
-      "truth": "ile electricity prices.",
-      "suggestion_at_0.2": "ility"
-    },
-    {
-      "context": "day, I need access to West deals in Sitara. At a mininum I s",
-      "truth": "till need access to all Chicago/Midwest deals al",
-      "suggestion_at_0.2": "ent"
-    },
-    {
-      "context": "on, attached for your review is a draft of the First Amendme",
-      "truth": "nt to Master Agreement between Enron North Ameri",
-      "suggestion_at_0.2": "nt"
-    },
-    {
-      "context": "I have provided all the info that Tami Scudder ",
-      "truth": "requested today.",
-      "suggestion_at_0.2": ""
-    },
-    {
-      "context": "ontana Power Company (MPC) System Border for Thursday and Fr",
-      "truth": "iday (July 12, 13) @ $67.85/MWh. Thanks, John",
-      "suggestion_at_0.2": ""
-    },
-    {
-      "context": "e EnBank contracts physical or financial? It seems to me we ",
-      "truth": "should use the same customer profiles - that is ",
-      "suggestion_at_0.2": ""
-    },
-    {
-      "context": "I have an appointment at 1:00 today and should be ",
-      "truth": "back to the office between 2 - 2:30.",
-      "suggestion_at_0.2": ""
-    },
-    {
-      "context": "I'm glad everythi",
-      "truth": "ng worked out for you. Hope you have a great tim",
-      "suggestion_at_0.2": "ng is"
-    },
-    {
-      "context": "o's Line 1100 from Eunice Station to Pecos River Station wil",
-      "truth": "l be out of service for 16 hours Saturday beginn",
-      "suggestion_at_0.2": "l be"
-    },
-    {
-      "context": "rty\" in the second line of paragraph 1. Otherwise they look ",
-      "truth": "great to me.",
-      "suggestion_at_0.2": "forward to"
-    },
-    {
-      "context": "on Houston in the next day or so.\n\nPlease call me if you hav",
-      "truth": "e any questions.",
-      "suggestion_at_0.2": "e any questions."
-    },
-    {
-      "context": "s not guarantee any continuity of support for you.\n\nPlease, ",
-      "truth": "let me know what you decide to do over the next ",
-      "suggestion_at_0.2": "let"
-    },
-    {
-      "context": " tend to agree with you, but Nora Dobin is the lawyer who kn",
-      "truth": "ows the most about the DealBench system - you sh",
-      "suggestion_at_0.2": "ows"
-    }
-  ],
-  "total_seconds": 1805.1
-}

gru-512/best.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8f2a663ad7a697a00ebf6bd15942824fcefa46975f9935c7ac6dd1eceedf3a36
-size 3780287

gru-512/model.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1ccc402ffaa27e6382114ad0d44a2e5a01e9beabe9d81e3c3ae0ad2f9676627b
-size 3780016

gru-512/model_quint8.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:079424a9d2a72b9e5b2d6002c6466b836023c088780b7d292748f37564dc143b
-size 981294

gru-512/report.json

@@ -1,548 +0,0 @@
-{
-  "args": {
-    "hidden": 512,
-    "epochs": 30,
-    "batch": 256,
-    "seq": 256,
-    "burn_in": 32,
-    "lr": 0.0015,
-    "typo_rate": 0.08,
-    "limit_frac": 1.0,
-    "eval_positions": 5000,
-    "context": 128,
-    "horizon": 48,
-    "repo": "cfahlgren1/email-autocomplete-gru",
-    "run_name": "gru-512",
-    "no_push": false
-  },
-  "device": "cuda",
-  "parameters": 944354,
-  "data": {
-    "train": {
-      "emails": 119859,
-      "chars": 40136658
-    },
-    "val": {
-      "emails": 8252,
-      "chars": 2775980
-    },
-    "test": {
-      "emails": 6922,
-      "chars": 2710169
-    }
-  },
-  "history": [
-    {
-      "epoch": 1,
-      "train_loss": 1.7093,
-      "val_loss": 1.3716,
-      "seconds": 23.9,
-      "chars_per_sec": 1678766
-    },
-    {
-      "epoch": 2,
-      "train_loss": 1.2792,
-      "val_loss": 1.2911,
-      "seconds": 23.6,
-      "chars_per_sec": 1701572
-    },
-    {
-      "epoch": 3,
-      "train_loss": 1.2231,
-      "val_loss": 1.2582,
-      "seconds": 23.6,
-      "chars_per_sec": 1700904
-    },
-    {
-      "epoch": 4,
-      "train_loss": 1.195,
-      "val_loss": 1.2396,
-      "seconds": 23.6,
-      "chars_per_sec": 1702926
-    },
-    {
-      "epoch": 5,
-      "train_loss": 1.1768,
-      "val_loss": 1.2254,
-      "seconds": 23.5,
-      "chars_per_sec": 1703932
-    },
-    {
-      "epoch": 6,
-      "train_loss": 1.1639,
-      "val_loss": 1.2171,
-      "seconds": 23.6,
-      "chars_per_sec": 1701905
-    },
-    {
-      "epoch": 7,
-      "train_loss": 1.1538,
-      "val_loss": 1.2087,
-      "seconds": 23.6,
-      "chars_per_sec": 1701450
-    },
-    {
-      "epoch": 8,
-      "train_loss": 1.1456,
-      "val_loss": 1.2043,
-      "seconds": 23.6,
-      "chars_per_sec": 1702601
-    },
-    {
-      "epoch": 9,
-      "train_loss": 1.1388,
-      "val_loss": 1.1969,
-      "seconds": 23.5,
-      "chars_per_sec": 1703175
-    },
-    {
-      "epoch": 10,
-      "train_loss": 1.1327,
-      "val_loss": 1.193,
-      "seconds": 23.6,
-      "chars_per_sec": 1701059
-    },
-    {
-      "epoch": 11,
-      "train_loss": 1.1276,
-      "val_loss": 1.1895,
-      "seconds": 23.6,
-      "chars_per_sec": 1702827
-    },
-    {
-      "epoch": 12,
-      "train_loss": 1.1228,
-      "val_loss": 1.1856,
-      "seconds": 23.6,
-      "chars_per_sec": 1700650
-    },
-    {
-      "epoch": 13,
-      "train_loss": 1.1186,
-      "val_loss": 1.1824,
-      "seconds": 23.5,
-      "chars_per_sec": 1703353
-    },
-    {
-      "epoch": 14,
-      "train_loss": 1.1141,
-      "val_loss": 1.1791,
-      "seconds": 23.6,
-      "chars_per_sec": 1702586
-    },
-    {
-      "epoch": 15,
-      "train_loss": 1.1108,
-      "val_loss": 1.1765,
-      "seconds": 23.6,
-      "chars_per_sec": 1702570
-    },
-    {
-      "epoch": 16,
-      "train_loss": 1.1075,
-      "val_loss": 1.175,
-      "seconds": 23.6,
-      "chars_per_sec": 1702686
-    },
-    {
-      "epoch": 17,
-      "train_loss": 1.1041,
-      "val_loss": 1.1718,
-      "seconds": 23.5,
-      "chars_per_sec": 1703957
-    },
-    {
-      "epoch": 18,
-      "train_loss": 1.1015,
-      "val_loss": 1.17,
-      "seconds": 23.6,
-      "chars_per_sec": 1701778
-    },
-    {
-      "epoch": 19,
-      "train_loss": 1.0985,
-      "val_loss": 1.1678,
-      "seconds": 23.6,
-      "chars_per_sec": 1702612
-    },
-    {
-      "epoch": 20,
-      "train_loss": 1.0959,
-      "val_loss": 1.1659,
-      "seconds": 23.6,
-      "chars_per_sec": 1702960
-    },
-    {
-      "epoch": 21,
-      "train_loss": 1.0935,
-      "val_loss": 1.1642,
-      "seconds": 23.6,
-      "chars_per_sec": 1701776
-    },
-    {
-      "epoch": 22,
-      "train_loss": 1.0913,
-      "val_loss": 1.1632,
-      "seconds": 23.6,
-      "chars_per_sec": 1702317
-    },
-    {
-      "epoch": 23,
-      "train_loss": 1.0896,
-      "val_loss": 1.1624,
-      "seconds": 23.6,
-      "chars_per_sec": 1701215
-    },
-    {
-      "epoch": 24,
-      "train_loss": 1.0874,
-      "val_loss": 1.1613,
-      "seconds": 23.6,
-      "chars_per_sec": 1701278
-    },
-    {
-      "epoch": 25,
-      "train_loss": 1.0863,
-      "val_loss": 1.1606,
-      "seconds": 23.6,
-      "chars_per_sec": 1700749
-    },
-    {
-      "epoch": 26,
-      "train_loss": 1.085,
-      "val_loss": 1.1596,
-      "seconds": 23.6,
-      "chars_per_sec": 1701575
-    },
-    {
-      "epoch": 27,
-      "train_loss": 1.0839,
-      "val_loss": 1.1592,
-      "seconds": 23.6,
-      "chars_per_sec": 1699705
-    },
-    {
-      "epoch": 28,
-      "train_loss": 1.083,
-      "val_loss": 1.1588,
-      "seconds": 23.6,
-      "chars_per_sec": 1700990
-    },
-    {
-      "epoch": 29,
-      "train_loss": 1.0823,
-      "val_loss": 1.1588,
-      "seconds": 23.6,
-      "chars_per_sec": 1702216
-    },
-    {
-      "epoch": 30,
-      "train_loss": 1.0821,
-      "val_loss": 1.1586,
-      "seconds": 23.5,
-      "chars_per_sec": 1704907
-    }
-  ],
-  "best_val_loss": 1.1586,
-  "test_positions": 5000,
-  "held_out_sender_suggestions": {
-    "0.05": {
-      "coverage": 0.624,
-      "precision": 0.2064,
-      "avg_chars_when_correct": 6.93,
-      "chars_saved_per_position": 0.892
-    },
-    "0.1": {
-      "coverage": 0.4622,
-      "precision": 0.3124,
-      "avg_chars_when_correct": 6.41,
-      "chars_saved_per_position": 0.925
-    },
-    "0.2": {
-      "coverage": 0.2974,
-      "precision": 0.4808,
-      "avg_chars_when_correct": 6.03,
-      "chars_saved_per_position": 0.863
-    },
-    "0.35": {
-      "coverage": 0.1796,
-      "precision": 0.6559,
-      "avg_chars_when_correct": 5.8,
-      "chars_saved_per_position": 0.683
-    },
-    "0.5": {
-      "coverage": 0.1114,
-      "precision": 0.7953,
-      "avg_chars_when_correct": 5.64,
-      "chars_saved_per_position": 0.5
-    },
-    "0.7": {
-      "coverage": 0.0694,
-      "precision": 0.8991,
-      "avg_chars_when_correct": 5.4,
-      "chars_saved_per_position": 0.337
-    }
-  },
-  "exports": {
-    "float": {
-      "size_mb": 3.78,
-      "native_cpu_single_thread_step": {
-        "p50_ms": 0.114,
-        "p95_ms": 0.125
-      },
-      "suggestions_1000_positions": {
-        "0.05": {
-          "coverage": 0.638,
-          "precision": 0.2132,
-          "avg_chars_when_correct": 6.7,
-          "chars_saved_per_position": 0.911
-        },
-        "0.1": {
-          "coverage": 0.496,
-          "precision": 0.3085,
-          "avg_chars_when_correct": 6.3,
-          "chars_saved_per_position": 0.964
-        },
-        "0.2": {
-          "coverage": 0.312,
-          "precision": 0.4583,
-          "avg_chars_when_correct": 5.94,
-          "chars_saved_per_position": 0.849
-        },
-        "0.35": {
-          "coverage": 0.202,
-          "precision": 0.604,
-          "avg_chars_when_correct": 5.77,
-          "chars_saved_per_position": 0.704
-        },
-        "0.5": {
-          "coverage": 0.119,
-          "precision": 0.7479,
-          "avg_chars_when_correct": 5.58,
-          "chars_saved_per_position": 0.497
-        },
-        "0.7": {
-          "coverage": 0.078,
-          "precision": 0.8718,
-          "avg_chars_when_correct": 5.21,
-          "chars_saved_per_position": 0.354
-        }
-      }
-    },
-    "quint8": {
-      "size_mb": 0.98,
-      "native_cpu_single_thread_step": {
-        "p50_ms": 0.059,
-        "p95_ms": 0.084
-      },
-      "suggestions_1000_positions": {
-        "0.05": {
-          "coverage": 0.655,
-          "precision": 0.2,
-          "avg_chars_when_correct": 6.83,
-          "chars_saved_per_position": 0.895
-        },
-        "0.1": {
-          "coverage": 0.492,
-          "precision": 0.311,
-          "avg_chars_when_correct": 6.35,
-          "chars_saved_per_position": 0.971
-        },
-        "0.2": {
-          "coverage": 0.318,
-          "precision": 0.4686,
-          "avg_chars_when_correct": 5.97,
-          "chars_saved_per_position": 0.89
-        },
-        "0.35": {
-          "coverage": 0.198,
-          "precision": 0.6414,
-          "avg_chars_when_correct": 5.66,
-          "chars_saved_per_position": 0.719
-        },
-        "0.5": {
-          "coverage": 0.123,
-          "precision": 0.7642,
-          "avg_chars_when_correct": 5.53,
-          "chars_saved_per_position": 0.52
-        },
-        "0.7": {
-          "coverage": 0.081,
-          "precision": 0.8889,
-          "avg_chars_when_correct": 5.42,
-          "chars_saved_per_position": 0.39
-        }
-      }
-    }
-  },
-  "prompt_samples": {
-    "Hi John,\n\nThanks for ": {
-      "continuation": "the info. I will be out of the office tomorrow a",
-      "suggestion_at_0.2": "the"
-    },
-    "Please let me know if ": {
-      "continuation": "you have any questions.\n\nThanks,\n\nKayThe follow",
-      "suggestion_at_0.2": "you have any"
-    },
-    "I will send you ": {
-      "continuation": "a copy of the attached document. I will be out o",
-      "suggestion_at_0.2": "a"
-    },
-    "Let me kn": {
-      "continuation": "ow if you have any questions.\n\nThanks,\n\nKayThe ",
-      "suggestion_at_0.2": "ow if you have"
-    },
-    "Thnaks for the ": {
-      "continuation": "info. I will be out of the office tomorrow and w",
-      "suggestion_at_0.2": ""
-    },
-    "I look forward to ": {
-      "continuation": "seeing you there. I will be out of the office to",
-      "suggestion_at_0.2": ""
-    },
-    "Can we schedule a ": {
-      "continuation": "meeting to discuss the attached spreadsheet for ",
-      "suggestion_at_0.2": "meeting"
-    },
-    "Sorry for the dela": {
-      "continuation": "y. I will be out of the office tomorrow and we w",
-      "suggestion_at_0.2": "y."
-    },
-    "Plese find attached ": {
-      "continuation": "the following contract for the Enron Corp. Gas P",
-      "suggestion_at_0.2": "the"
-    },
-    "We need to discuss ": {
-      "continuation": "the attached spreadsheet for the following dates",
-      "suggestion_at_0.2": "the"
-    }
-  },
-  "held_out_examples": [
-    {
-      "context": "ou trading a book yet? Playing any poker? Bingham was here f",
-      "truth": "or Q-School last week. Didn't go so well.",
-      "suggestion_at_0.2": "or"
-    },
-    {
-      "context": "Please use this model. I had a few change",
-      "truth": "s after talking to the guys in the west. Thanks!",
-      "suggestion_at_0.2": "s to"
-    },
-    {
-      "context": "not open the attachment. Please, send it as a MS Word docume",
-      "truth": "nt or a .pdf file.",
-      "suggestion_at_0.2": "nt."
-    },
-    {
-      "context": "n I do to help. I would also like to visit on status of e*p ",
-      "truth": "group and mariner.",
-      "suggestion_at_0.2": ""
-    },
-    {
-      "context": " complete hourly schedule for June 1, including IBM and inco",
-      "truth": "rporating all known changes confirmed by that ti",
-      "suggestion_at_0.2": "me"
-    },
-    {
-      "context": " delivery rights at SoCal/Topock for at least a pro rata por",
-      "truth": "tion of its released capacity.",
-      "suggestion_at_0.2": "tion of"
-    },
-    {
-      "context": "i talked to chris a li",
-      "truth": "ttle bit and he is going to call back tonight at",
-      "suggestion_at_0.2": "ttle"
-    },
-    {
-      "context": " I might be missing something about the way you guys do thes",
-      "truth": "e deals in Canada so I thought I would run this ",
-      "suggestion_at_0.2": "e"
-    },
-    {
-      "context": "Traci,\n\nThanks. This is the best solution given all the unce",
-      "truth": "rtainties we face.",
-      "suggestion_at_0.2": "rtainty"
-    },
-    {
-      "context": "\nAquila,s strategy comes as little surprise to Stuebi. As mu",
-      "truth": "ch success as the company has had, he said he th",
-      "suggestion_at_0.2": "ch"
-    },
-    {
-      "context": "Jim,\n\nWhat about 2 p.m., my time, on Friday, Au",
-      "truth": "gust 17. If this works for you, I shall try to i",
-      "suggestion_at_0.2": "gust"
-    },
-    {
-      "context": "'s and CDD's for Philedelphia, Allentown Washington DC, Balt",
-      "truth": "imore, Pittsburg, Newark, New York City, Cinncin",
-      "suggestion_at_0.2": "imore"
-    },
-    {
-      "context": " release.\n\nThe company will offer derivatives to hedge volat",
-      "truth": "ile electricity prices.",
-      "suggestion_at_0.2": "ility"
-    },
-    {
-      "context": "day, I need access to West deals in Sitara. At a mininum I s",
-      "truth": "till need access to all Chicago/Midwest deals al",
-      "suggestion_at_0.2": "ent"
-    },
-    {
-      "context": "on, attached for your review is a draft of the First Amendme",
-      "truth": "nt to Master Agreement between Enron North Ameri",
-      "suggestion_at_0.2": "nt to"
-    },
-    {
-      "context": "I have provided all the info that Tami Scudder ",
-      "truth": "requested today.",
-      "suggestion_at_0.2": "is"
-    },
-    {
-      "context": "ontana Power Company (MPC) System Border for Thursday and Fr",
-      "truth": "iday (July 12, 13) @ $67.85/MWh. Thanks, John",
-      "suggestion_at_0.2": "iday"
-    },
-    {
-      "context": "e EnBank contracts physical or financial? It seems to me we ",
-      "truth": "should use the same customer profiles - that is ",
-      "suggestion_at_0.2": ""
-    },
-    {
-      "context": "I have an appointment at 1:00 today and should be ",
-      "truth": "back to the office between 2 - 2:30.",
-      "suggestion_at_0.2": ""
-    },
-    {
-      "context": "I'm glad everythi",
-      "truth": "ng worked out for you. Hope you have a great tim",
-      "suggestion_at_0.2": "ng is"
-    },
-    {
-      "context": "o's Line 1100 from Eunice Station to Pecos River Station wil",
-      "truth": "l be out of service for 16 hours Saturday beginn",
-      "suggestion_at_0.2": "l be"
-    },
-    {
-      "context": "rty\" in the second line of paragraph 1. Otherwise they look ",
-      "truth": "great to me.",
-      "suggestion_at_0.2": ""
-    },
-    {
-      "context": "on Houston in the next day or so.\n\nPlease call me if you hav",
-      "truth": "e any questions.",
-      "suggestion_at_0.2": "e any questions."
-    },
-    {
-      "context": "s not guarantee any continuity of support for you.\n\nPlease, ",
-      "truth": "let me know what you decide to do over the next ",
-      "suggestion_at_0.2": ""
-    },
-    {
-      "context": " tend to agree with you, but Nora Dobin is the lawyer who kn",
-      "truth": "ows the most about the DealBench system - you sh",
-      "suggestion_at_0.2": "ows"
-    }
-  ],
-  "total_seconds": 831.5
-}

gru-512/vocab.json

@@ -1,9 +0,0 @@
-{
-  "pad": 0,
-  "eos": 1,
-  "newline": 2,
-  "first_printable_id": 3,
-  "first_printable_codepoint": 32,
-  "size": 98,
-  "hidden": 512
-}

train.py

@@ -434,7 +434,6 @@ def parse_args():
     parser.add_argument("--context", type=int, default=128)
     parser.add_argument("--horizon", type=int, default=48)
     parser.add_argument("--repo", default="cfahlgren1/enron-autocomplete")
-    parser.add_argument("--run-name", default="gru-512")
     parser.add_argument("--no-push", action="store_true")
     return parser.parse_args()
 
@@ -445,7 +444,7 @@ def main():
     rng = np.random.default_rng(0)
     device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
     print(f"device={device} {torch.cuda.get_device_name(0) if device.type == 'cuda' else ''} args={vars(args)}", flush=True)
-    output = Path("outputs") / args.run_name
+    output = Path("outputs")
     output.mkdir(parents=True, exist_ok=True)
 
     started = time.time()
@@ -550,8 +549,8 @@ def main():
         return
     api = HfApi(token=os.environ["HF_TOKEN"])
     api.create_repo(args.repo, repo_type="model", private=True, exist_ok=True)
-    api.upload_folder(folder_path=str(output), repo_id=args.repo, path_in_repo=args.run_name, repo_type="model")
-    print(f"Uploaded to https://huggingface.co/{args.repo}/tree/main/{args.run_name}", flush=True)
+    api.upload_folder(folder_path=str(output), repo_id=args.repo, repo_type="model")
+    print(f"Uploaded to https://huggingface.co/{args.repo}", flush=True)
 
 
 if __name__ == "__main__":