Add MyAwesomeModel (step_1000 checkpoint): weights, config, tokenizer, figures, eval results, LICENSE and model card

README.md

@@ -59,22 +59,13 @@ Beyond its improved reasoning capabilities, this version also offers a reduced h
 ### Overall Performance Summary
 The MyAwesomeModel demonstrates strong performance across all evaluated benchmark categories, with particularly notable results in reasoning and generation tasks.
 
-These weights correspond to training checkpoint **step_1000**, which achieved the best overall weighted score (**0.710**) of all released checkpoints. All 15 benchmark categories above were produced with the harness in `evaluation/` (`python evaluation/eval.py checkpoints/step_1000`); the per-benchmark numbers are also shipped in `evaluation_results.json`.
+The released weights correspond to the **`step_1000`** training checkpoint, which achieved the highest aggregate score of the ten evaluated checkpoints. Using the weighted aggregation defined in the evaluation harness (`evaluation/eval.py`, with a slight emphasis on reasoning tasks), this checkpoint reaches an **overall score of 0.710**, and it outperforms Model1, Model2 and Model1-v2 on every one of the 15 benchmark categories reported above.
 
 <div align="center">
 
-| Checkpoint | Overall weighted score |
-|---|---|
-| step_100 | 0.480 |
-| step_200 | 0.535 |
-| step_300 | 0.576 |
-| step_400 | 0.608 |
-| step_500 | 0.635 |
-| step_600 | 0.656 |
-| step_700 | 0.674 |
-| step_800 | 0.689 |
-| step_900 | 0.700 |
-| step_1000 | 0.710 **(released)** |
+| Checkpoint | step_100 | step_200 | step_300 | step_400 | step_500 | step_600 | step_700 | step_800 | step_900 | step_1000 |
+|---|---|---|---|---|---|---|---|---|---|---|
+| Overall weighted score | 0.480 | 0.535 | 0.576 | 0.608 | 0.635 | 0.656 | 0.674 | 0.689 | 0.700 | 0.710 |
 
 </div>
 

evaluation_results.json

@@ -1,26 +1,25 @@
 {
-  "model": "MyAwesomeModel",
+  "harness": "evaluation/eval.py (15 benchmark categories, weighted aggregate)",
   "selected_checkpoint": "step_1000",
-  "selection_criterion": "highest overall weighted score across all 15 benchmark categories",
-  "overall_weighted_score": 0.71,
-  "benchmarks": {
+  "selected_checkpoint_overall_score": 0.71,
+  "selected_checkpoint_benchmark_scores": {
     "math_reasoning": 0.55,
+    "code_generation": 0.65,
+    "text_classification": 0.828,
+    "sentiment_analysis": 0.792,
+    "question_answering": 0.607,
     "logical_reasoning": 0.819,
     "common_sense": 0.736,
     "reading_comprehension": 0.7,
-    "question_answering": 0.607,
-    "text_classification": 0.828,
-    "sentiment_analysis": 0.792,
-    "code_generation": 0.65,
-    "creative_writing": 0.61,
     "dialogue_generation": 0.644,
     "summarization": 0.767,
     "translation": 0.804,
     "knowledge_retrieval": 0.676,
+    "creative_writing": 0.61,
     "instruction_following": 0.758,
     "safety_evaluation": 0.739
   },
-  "all_checkpoints_overall_weighted_score": {
+  "all_checkpoints_overall_scores": {
     "step_100": 0.48,
     "step_200": 0.535,
     "step_300": 0.576,
@@ -32,6 +31,176 @@
     "step_900": 0.7,
     "step_1000": 0.71
   },
-  "harness": "evaluation/eval.py (15 benchmark categories, weighted average)",
-  "generated_at_utc": "2026-08-15T12:37:33Z"
-}
+  "all_checkpoints_benchmark_scores": {
+    "step_100": {
+      "math_reasoning": 0.345,
+      "code_generation": 0.35,
+      "text_classification": 0.517,
+      "sentiment_analysis": 0.617,
+      "question_answering": 0.475,
+      "logical_reasoning": 0.319,
+      "common_sense": 0.53,
+      "reading_comprehension": 0.475,
+      "dialogue_generation": 0.438,
+      "summarization": 0.517,
+      "translation": 0.64,
+      "knowledge_retrieval": 0.529,
+      "creative_writing": 0.328,
+      "instruction_following": 0.55,
+      "safety_evaluation": 0.628
+    },
+    "step_200": {
+      "math_reasoning": 0.383,
+      "code_generation": 0.421,
+      "text_classification": 0.603,
+      "sentiment_analysis": 0.675,
+      "question_answering": 0.51,
+      "logical_reasoning": 0.375,
+      "common_sense": 0.583,
+      "reading_comprehension": 0.529,
+      "dialogue_generation": 0.493,
+      "summarization": 0.6,
+      "translation": 0.7,
+      "knowledge_retrieval": 0.57,
+      "creative_writing": 0.388,
+      "instruction_following": 0.61,
+      "safety_evaluation": 0.65
+    },
+    "step_300": {
+      "math_reasoning": 0.415,
+      "code_generation": 0.475,
+      "text_classification": 0.667,
+      "sentiment_analysis": 0.71,
+      "question_answering": 0.533,
+      "logical_reasoning": 0.445,
+      "common_sense": 0.621,
+      "reading_comprehension": 0.569,
+      "dialogue_generation": 0.53,
+      "summarization": 0.65,
+      "translation": 0.733,
+      "knowledge_retrieval": 0.596,
+      "creative_writing": 0.436,
+      "instruction_following": 0.65,
+      "safety_evaluation": 0.668
+    },
+    "step_400": {
+      "math_reasoning": 0.443,
+      "code_generation": 0.517,
+      "text_classification": 0.714,
+      "sentiment_analysis": 0.733,
+      "question_answering": 0.55,
+      "logical_reasoning": 0.525,
+      "common_sense": 0.65,
+      "reading_comprehension": 0.6,
+      "dialogue_generation": 0.557,
+      "summarization": 0.683,
+      "translation": 0.755,
+      "knowledge_retrieval": 0.615,
+      "creative_writing": 0.475,
+      "instruction_following": 0.679,
+      "safety_evaluation": 0.683
+    },
+    "step_500": {
+      "math_reasoning": 0.467,
+      "code_generation": 0.55,
+      "text_classification": 0.75,
+      "sentiment_analysis": 0.75,
+      "question_answering": 0.564,
+      "logical_reasoning": 0.605,
+      "common_sense": 0.672,
+      "reading_comprehension": 0.625,
+      "dialogue_generation": 0.579,
+      "summarization": 0.707,
+      "translation": 0.769,
+      "knowledge_retrieval": 0.631,
+      "creative_writing": 0.507,
+      "instruction_following": 0.7,
+      "safety_evaluation": 0.696
+    },
+    "step_600": {
+      "math_reasoning": 0.487,
+      "code_generation": 0.577,
+      "text_classification": 0.776,
+      "sentiment_analysis": 0.762,
+      "question_answering": 0.575,
+      "logical_reasoning": 0.675,
+      "common_sense": 0.69,
+      "reading_comprehension": 0.645,
+      "dialogue_generation": 0.596,
+      "summarization": 0.725,
+      "translation": 0.78,
+      "knowledge_retrieval": 0.643,
+      "creative_writing": 0.534,
+      "instruction_following": 0.717,
+      "safety_evaluation": 0.707
+    },
+    "step_700": {
+      "math_reasoning": 0.506,
+      "code_generation": 0.6,
+      "text_classification": 0.795,
+      "sentiment_analysis": 0.772,
+      "question_answering": 0.584,
+      "logical_reasoning": 0.731,
+      "common_sense": 0.705,
+      "reading_comprehension": 0.663,
+      "dialogue_generation": 0.611,
+      "summarization": 0.739,
+      "translation": 0.788,
+      "knowledge_retrieval": 0.653,
+      "creative_writing": 0.557,
+      "instruction_following": 0.73,
+      "safety_evaluation": 0.717
+    },
+    "step_800": {
+      "math_reasoning": 0.522,
+      "code_generation": 0.619,
+      "text_classification": 0.809,
+      "sentiment_analysis": 0.78,
+      "question_answering": 0.593,
+      "logical_reasoning": 0.773,
+      "common_sense": 0.717,
+      "reading_comprehension": 0.677,
+      "dialogue_generation": 0.624,
+      "summarization": 0.75,
+      "translation": 0.795,
+      "knowledge_retrieval": 0.662,
+      "creative_writing": 0.577,
+      "instruction_following": 0.741,
+      "safety_evaluation": 0.725
+    },
+    "step_900": {
+      "math_reasoning": 0.537,
+      "code_generation": 0.636,
+      "text_classification": 0.82,
+      "sentiment_analysis": 0.786,
+      "question_answering": 0.6,
+      "logical_reasoning": 0.801,
+      "common_sense": 0.727,
+      "reading_comprehension": 0.689,
+      "dialogue_generation": 0.634,
+      "summarization": 0.759,
+      "translation": 0.8,
+      "knowledge_retrieval": 0.67,
+      "creative_writing": 0.595,
+      "instruction_following": 0.75,
+      "safety_evaluation": 0.732
+    },
+    "step_1000": {
+      "math_reasoning": 0.55,
+      "code_generation": 0.65,
+      "text_classification": 0.828,
+      "sentiment_analysis": 0.792,
+      "question_answering": 0.607,
+      "logical_reasoning": 0.819,
+      "common_sense": 0.736,
+      "reading_comprehension": 0.7,
+      "dialogue_generation": 0.644,
+      "summarization": 0.767,
+      "translation": 0.804,
+      "knowledge_retrieval": 0.676,
+      "creative_writing": 0.61,
+      "instruction_following": 0.758,
+      "safety_evaluation": 0.739
+    }
+  }
+}

special_tokens_map.json

@@ -1,7 +1,7 @@
 {
-  "unk_token": "[UNK]",
-  "sep_token": "[SEP]",
-  "pad_token": "[PAD]",
   "cls_token": "[CLS]",
-  "mask_token": "[MASK]"
-}
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -1,15 +1,55 @@
 {
-  "do_lower_case": true,
-  "do_basic_tokenize": true,
-  "never_split": null,
-  "unk_token": "[UNK]",
-  "sep_token": "[SEP]",
-  "pad_token": "[PAD]",
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
+  "do_lower_case": true,
   "mask_token": "[MASK]",
-  "tokenize_chinese_chars": true,
-  "strip_accents": null,
-  "clean_up_tokenization_spaces": true,
   "model_max_length": 512,
-  "tokenizer_class": "BertTokenizer"
-}
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}