Upload checkpoints/math_operations/base_model_eval
Browse files- .gitattributes +1 -0
- checkpoints/math_operations/base_model_eval/eval_results_easy_ops/balanced_test_alpaca_converted.jsonl +0 -0
- checkpoints/math_operations/base_model_eval/eval_results_easy_ops/balanced_test_alpaca_results.jsonl +3 -0
- checkpoints/math_operations/base_model_eval/eval_results_easy_ops/eval_results.csv +2 -0
- checkpoints/math_operations/base_model_eval/eval_results_easy_ops/eval_summary.json +133 -0
.gitattributes
CHANGED
|
@@ -62,3 +62,4 @@ checkpoints/knowledge/atomic_full_then_2step_full_sft_t20260305/checkpoint-710/t
|
|
| 62 |
checkpoints/knowledge/lora_sft_atomic_50ep_t20260305/checkpoint-1248/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 63 |
checkpoints/knowledge/lora_sft_atomic_50ep_t20260305/checkpoint-1274/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 64 |
checkpoints/knowledge/lora_sft_atomic_50ep_t20260305/checkpoint-1300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 62 |
checkpoints/knowledge/lora_sft_atomic_50ep_t20260305/checkpoint-1248/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 63 |
checkpoints/knowledge/lora_sft_atomic_50ep_t20260305/checkpoint-1274/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 64 |
checkpoints/knowledge/lora_sft_atomic_50ep_t20260305/checkpoint-1300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 65 |
+
checkpoints/math_operations/base_model_eval/eval_results_easy_ops/balanced_test_alpaca_results.jsonl filter=lfs diff=lfs merge=lfs -text
|
checkpoints/math_operations/base_model_eval/eval_results_easy_ops/balanced_test_alpaca_converted.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/math_operations/base_model_eval/eval_results_easy_ops/balanced_test_alpaca_results.jsonl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fa82938ac18adb04d956ffed23da0b3f07a79e3692c2989432a310eab98ab4c
|
| 3 |
+
size 11059849
|
checkpoints/math_operations/base_model_eval/eval_results_easy_ops/eval_results.csv
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
category,filename,total,correct,accuracy,format_found,format_accuracy,errors_count
|
| 2 |
+
math_operations,balanced_test_alpaca_results,500,413,82.60,425,85.00,87
|
checkpoints/math_operations/base_model_eval/eval_results_easy_ops/eval_summary.json
ADDED
|
@@ -0,0 +1,133 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"overall": {
|
| 3 |
+
"total": 500,
|
| 4 |
+
"correct": 413,
|
| 5 |
+
"accuracy": 82.6,
|
| 6 |
+
"format_found": 425,
|
| 7 |
+
"format_accuracy": 85.0
|
| 8 |
+
},
|
| 9 |
+
"per_operation": {
|
| 10 |
+
"a": {
|
| 11 |
+
"total": 25,
|
| 12 |
+
"correct": 25,
|
| 13 |
+
"accuracy": 100.0,
|
| 14 |
+
"format_found": 25
|
| 15 |
+
},
|
| 16 |
+
"b": {
|
| 17 |
+
"total": 25,
|
| 18 |
+
"correct": 17,
|
| 19 |
+
"accuracy": 68.0,
|
| 20 |
+
"format_found": 25
|
| 21 |
+
},
|
| 22 |
+
"c": {
|
| 23 |
+
"total": 25,
|
| 24 |
+
"correct": 25,
|
| 25 |
+
"accuracy": 100.0,
|
| 26 |
+
"format_found": 25
|
| 27 |
+
},
|
| 28 |
+
"d": {
|
| 29 |
+
"total": 25,
|
| 30 |
+
"correct": 25,
|
| 31 |
+
"accuracy": 100.0,
|
| 32 |
+
"format_found": 25
|
| 33 |
+
},
|
| 34 |
+
"e": {
|
| 35 |
+
"total": 25,
|
| 36 |
+
"correct": 13,
|
| 37 |
+
"accuracy": 52.0,
|
| 38 |
+
"format_found": 11
|
| 39 |
+
},
|
| 40 |
+
"f": {
|
| 41 |
+
"total": 25,
|
| 42 |
+
"correct": 25,
|
| 43 |
+
"accuracy": 100.0,
|
| 44 |
+
"format_found": 25
|
| 45 |
+
},
|
| 46 |
+
"g": {
|
| 47 |
+
"total": 25,
|
| 48 |
+
"correct": 25,
|
| 49 |
+
"accuracy": 100.0,
|
| 50 |
+
"format_found": 25
|
| 51 |
+
},
|
| 52 |
+
"h": {
|
| 53 |
+
"total": 25,
|
| 54 |
+
"correct": 3,
|
| 55 |
+
"accuracy": 12.0,
|
| 56 |
+
"format_found": 2
|
| 57 |
+
},
|
| 58 |
+
"i": {
|
| 59 |
+
"total": 25,
|
| 60 |
+
"correct": 25,
|
| 61 |
+
"accuracy": 100.0,
|
| 62 |
+
"format_found": 25
|
| 63 |
+
},
|
| 64 |
+
"j": {
|
| 65 |
+
"total": 25,
|
| 66 |
+
"correct": 4,
|
| 67 |
+
"accuracy": 16.0,
|
| 68 |
+
"format_found": 2
|
| 69 |
+
},
|
| 70 |
+
"k": {
|
| 71 |
+
"total": 25,
|
| 72 |
+
"correct": 25,
|
| 73 |
+
"accuracy": 100.0,
|
| 74 |
+
"format_found": 25
|
| 75 |
+
},
|
| 76 |
+
"l": {
|
| 77 |
+
"total": 25,
|
| 78 |
+
"correct": 23,
|
| 79 |
+
"accuracy": 92.0,
|
| 80 |
+
"format_found": 24
|
| 81 |
+
},
|
| 82 |
+
"m": {
|
| 83 |
+
"total": 25,
|
| 84 |
+
"correct": 25,
|
| 85 |
+
"accuracy": 100.0,
|
| 86 |
+
"format_found": 25
|
| 87 |
+
},
|
| 88 |
+
"n": {
|
| 89 |
+
"total": 25,
|
| 90 |
+
"correct": 24,
|
| 91 |
+
"accuracy": 96.0,
|
| 92 |
+
"format_found": 24
|
| 93 |
+
},
|
| 94 |
+
"o": {
|
| 95 |
+
"total": 25,
|
| 96 |
+
"correct": 25,
|
| 97 |
+
"accuracy": 100.0,
|
| 98 |
+
"format_found": 25
|
| 99 |
+
},
|
| 100 |
+
"p": {
|
| 101 |
+
"total": 25,
|
| 102 |
+
"correct": 22,
|
| 103 |
+
"accuracy": 88.0,
|
| 104 |
+
"format_found": 22
|
| 105 |
+
},
|
| 106 |
+
"q": {
|
| 107 |
+
"total": 25,
|
| 108 |
+
"correct": 15,
|
| 109 |
+
"accuracy": 60.0,
|
| 110 |
+
"format_found": 15
|
| 111 |
+
},
|
| 112 |
+
"r": {
|
| 113 |
+
"total": 25,
|
| 114 |
+
"correct": 17,
|
| 115 |
+
"accuracy": 68.0,
|
| 116 |
+
"format_found": 25
|
| 117 |
+
},
|
| 118 |
+
"s": {
|
| 119 |
+
"total": 25,
|
| 120 |
+
"correct": 25,
|
| 121 |
+
"accuracy": 100.0,
|
| 122 |
+
"format_found": 25
|
| 123 |
+
},
|
| 124 |
+
"t": {
|
| 125 |
+
"total": 25,
|
| 126 |
+
"correct": 25,
|
| 127 |
+
"accuracy": 100.0,
|
| 128 |
+
"format_found": 25
|
| 129 |
+
}
|
| 130 |
+
},
|
| 131 |
+
"n_errors": 87,
|
| 132 |
+
"results_file": "/home/jiaruil5/math_rl/mix_teachers/r3lit_rl/mix_teachers/checkpoints/math_operations/base_model_eval/eval_results_easy_ops/balanced_test_alpaca_results.jsonl"
|
| 133 |
+
}
|