CMU-AIR2
/

satvik_evaluation_results

Model card Files Files and versions Community

satvik-dixit commited on May 29

Commit

2879958

•

1 Parent(s): 5c1ff4d

Uploaded Curriculum

Browse files

This view is limited to 50 files because it contains too many changes. See raw diff

Files changed (50) hide show

Curriculum_eval_results_Meta_Llama_3_8B_Vanilla_test.json +0 -0
Curriculum_eval_results_math_llama3_instruct_MWP2K_Vanilla_test.json +0 -0
Curriculum_eval_results_math_llama3_instruct_MWP2K_Vanilla_val.json +0 -0
Curriculum_eval_results_math_llama3_instruct_MWP4K_Vanilla_test.json +0 -0
Curriculum_eval_results_math_llama3_instruct_MWP4K_Vanilla_val.json +0 -0
Curriculum_eval_results_math_llama_3_LORA_Arithmetic_10k_Vanilla_test.json +0 -0
Curriculum_eval_results_math_llama_3_LORA_Arithmetic_10k_Vanilla_val.json +0 -0
Curriculum_eval_results_math_llama_3_LORA_Arithmetic_2k_Vanilla_test.json +0 -0
Curriculum_eval_results_math_llama_3_LORA_Arithmetic_2k_Vanilla_val.json +0 -0
Curriculum_eval_results_math_llama_3_LORA_Arithmetic_4k_Vanilla_test.json +0 -0
Curriculum_eval_results_math_llama_3_LORA_Arithmetic_4k_Vanilla_val.json +0 -0
Curriculum_eval_results_math_llama_3_LORA_Arithmetic_6k_Vanilla_test.json +0 -0
Curriculum_eval_results_math_llama_3_LORA_Arithmetic_6k_Vanilla_val.json +0 -0
Curriculum_eval_results_math_llama_3_LORA_Arithmetic_8k_MWPMix_10k_Vanilla_test.json +0 -0
Curriculum_eval_results_math_llama_3_LORA_Arithmetic_8k_MWPMix_10k_Vanilla_val.json +0 -0
Curriculum_eval_results_math_llama_3_LORA_Arithmetic_8k_MWPMix_6k_Vanilla_test.json +0 -0
Curriculum_eval_results_math_llama_3_LORA_Arithmetic_8k_MWPMix_6k_Vanilla_val.json +0 -0
Curriculum_eval_results_math_llama_3_LORA_Arithmetic_8k_MWPMix_8k_Vanilla_test.json +0 -0
Curriculum_eval_results_math_llama_3_LORA_Arithmetic_8k_MWPMix_8k_Vanilla_val.json +0 -0
Curriculum_eval_results_math_llama_3_LORA_Arithmetic_8k_Vanilla_test.json +0 -0
Curriculum_eval_results_math_llama_3_LORA_Arithmetic_8k_Vanilla_val.json +0 -0
Curriculum_eval_results_math_llama_3_instruct_model_arith_10k_Vanilla_test.json +0 -0
Curriculum_eval_results_math_llama_3_instruct_model_arith_10k_Vanilla_val.json +0 -0
Curriculum_eval_results_math_llama_3_instruct_model_arith_2k_Vanilla_test.json +0 -0
Curriculum_eval_results_math_llama_3_instruct_model_arith_2k_Vanilla_val.json +0 -0
Curriculum_eval_results_math_llama_3_instruct_model_arith_4k_Vanilla_test.json +0 -0
Curriculum_eval_results_math_llama_3_instruct_model_arith_4k_Vanilla_val.json +0 -0
Curriculum_eval_results_math_llama_3_instruct_model_arith_6k_Vanilla_test.json +0 -0
Curriculum_eval_results_math_llama_3_instruct_model_arith_6k_Vanilla_val.json +0 -0
Curriculum_eval_results_math_llama_3_instruct_model_arith_8k_Vanilla_test.json +0 -0
Curriculum_eval_results_math_llama_3_instruct_model_arith_8k_Vanilla_val.json +0 -0
Curriculum_math_llama3_instruct_MWP2K_Vanilla_test_metrics.json +16 -0
Curriculum_math_llama3_instruct_MWP2K_Vanilla_val_metrics.json +16 -0
Curriculum_math_llama3_instruct_MWP4K_Vanilla_test_metrics.json +16 -0
Curriculum_math_llama3_instruct_MWP4K_Vanilla_val_metrics.json +16 -0
Curriculum_math_llama_3_LORA_Arithmetic_10k_Vanilla_test_metrics.json +16 -0
Curriculum_math_llama_3_LORA_Arithmetic_10k_Vanilla_val_metrics.json +16 -0
Curriculum_math_llama_3_LORA_Arithmetic_2k_Vanilla_test_metrics.json +16 -0
Curriculum_math_llama_3_LORA_Arithmetic_2k_Vanilla_val_metrics.json +16 -0
Curriculum_math_llama_3_LORA_Arithmetic_4k_Vanilla_test_metrics.json +16 -0
Curriculum_math_llama_3_LORA_Arithmetic_4k_Vanilla_val_metrics.json +16 -0
Curriculum_math_llama_3_LORA_Arithmetic_6k_Vanilla_test_metrics.json +16 -0
Curriculum_math_llama_3_LORA_Arithmetic_6k_Vanilla_val_metrics.json +16 -0
Curriculum_math_llama_3_LORA_Arithmetic_8k_MWPMix_10k_Vanilla_test_metrics.json +16 -0
Curriculum_math_llama_3_LORA_Arithmetic_8k_MWPMix_10k_Vanilla_val_metrics.json +16 -0
Curriculum_math_llama_3_LORA_Arithmetic_8k_MWPMix_6k_Vanilla_test_metrics.json +16 -0
Curriculum_math_llama_3_LORA_Arithmetic_8k_MWPMix_6k_Vanilla_val_metrics.json +16 -0
Curriculum_math_llama_3_LORA_Arithmetic_8k_MWPMix_8k_Vanilla_test_metrics.json +16 -0
Curriculum_math_llama_3_LORA_Arithmetic_8k_MWPMix_8k_Vanilla_val_metrics.json +16 -0
Curriculum_math_llama_3_LORA_Arithmetic_8k_Vanilla_test_metrics.json +16 -0

Curriculum_eval_results_Meta_Llama_3_8B_Vanilla_test.json ADDED Viewed

The diff for this file is too large to render. See raw diff

Curriculum_eval_results_math_llama3_instruct_MWP2K_Vanilla_test.json ADDED Viewed

The diff for this file is too large to render. See raw diff

Curriculum_eval_results_math_llama3_instruct_MWP2K_Vanilla_val.json ADDED Viewed

The diff for this file is too large to render. See raw diff

Curriculum_eval_results_math_llama3_instruct_MWP4K_Vanilla_test.json ADDED Viewed

The diff for this file is too large to render. See raw diff

Curriculum_eval_results_math_llama3_instruct_MWP4K_Vanilla_val.json ADDED Viewed

The diff for this file is too large to render. See raw diff

Curriculum_eval_results_math_llama_3_LORA_Arithmetic_10k_Vanilla_test.json ADDED Viewed

The diff for this file is too large to render. See raw diff

Curriculum_eval_results_math_llama_3_LORA_Arithmetic_10k_Vanilla_val.json ADDED Viewed

The diff for this file is too large to render. See raw diff

Curriculum_eval_results_math_llama_3_LORA_Arithmetic_2k_Vanilla_test.json ADDED Viewed

The diff for this file is too large to render. See raw diff

Curriculum_eval_results_math_llama_3_LORA_Arithmetic_2k_Vanilla_val.json ADDED Viewed

The diff for this file is too large to render. See raw diff

Curriculum_eval_results_math_llama_3_LORA_Arithmetic_4k_Vanilla_test.json ADDED Viewed

The diff for this file is too large to render. See raw diff

Curriculum_eval_results_math_llama_3_LORA_Arithmetic_4k_Vanilla_val.json ADDED Viewed

The diff for this file is too large to render. See raw diff

Curriculum_eval_results_math_llama_3_LORA_Arithmetic_6k_Vanilla_test.json ADDED Viewed

The diff for this file is too large to render. See raw diff

Curriculum_eval_results_math_llama_3_LORA_Arithmetic_6k_Vanilla_val.json ADDED Viewed

The diff for this file is too large to render. See raw diff

Curriculum_eval_results_math_llama_3_LORA_Arithmetic_8k_MWPMix_10k_Vanilla_test.json ADDED Viewed

The diff for this file is too large to render. See raw diff

Curriculum_eval_results_math_llama_3_LORA_Arithmetic_8k_MWPMix_10k_Vanilla_val.json ADDED Viewed

The diff for this file is too large to render. See raw diff

Curriculum_eval_results_math_llama_3_LORA_Arithmetic_8k_MWPMix_6k_Vanilla_test.json ADDED Viewed

The diff for this file is too large to render. See raw diff

Curriculum_eval_results_math_llama_3_LORA_Arithmetic_8k_MWPMix_6k_Vanilla_val.json ADDED Viewed

The diff for this file is too large to render. See raw diff

Curriculum_eval_results_math_llama_3_LORA_Arithmetic_8k_MWPMix_8k_Vanilla_test.json ADDED Viewed

The diff for this file is too large to render. See raw diff

Curriculum_eval_results_math_llama_3_LORA_Arithmetic_8k_MWPMix_8k_Vanilla_val.json ADDED Viewed

The diff for this file is too large to render. See raw diff

Curriculum_eval_results_math_llama_3_LORA_Arithmetic_8k_Vanilla_test.json ADDED Viewed

The diff for this file is too large to render. See raw diff

Curriculum_eval_results_math_llama_3_LORA_Arithmetic_8k_Vanilla_val.json ADDED Viewed

The diff for this file is too large to render. See raw diff

Curriculum_eval_results_math_llama_3_instruct_model_arith_10k_Vanilla_test.json ADDED Viewed

The diff for this file is too large to render. See raw diff

Curriculum_eval_results_math_llama_3_instruct_model_arith_10k_Vanilla_val.json ADDED Viewed

The diff for this file is too large to render. See raw diff

Curriculum_eval_results_math_llama_3_instruct_model_arith_2k_Vanilla_test.json ADDED Viewed

The diff for this file is too large to render. See raw diff

Curriculum_eval_results_math_llama_3_instruct_model_arith_2k_Vanilla_val.json ADDED Viewed

The diff for this file is too large to render. See raw diff

Curriculum_eval_results_math_llama_3_instruct_model_arith_4k_Vanilla_test.json ADDED Viewed

The diff for this file is too large to render. See raw diff

Curriculum_eval_results_math_llama_3_instruct_model_arith_4k_Vanilla_val.json ADDED Viewed

The diff for this file is too large to render. See raw diff

Curriculum_eval_results_math_llama_3_instruct_model_arith_6k_Vanilla_test.json ADDED Viewed

The diff for this file is too large to render. See raw diff

Curriculum_eval_results_math_llama_3_instruct_model_arith_6k_Vanilla_val.json ADDED Viewed

The diff for this file is too large to render. See raw diff

Curriculum_eval_results_math_llama_3_instruct_model_arith_8k_Vanilla_test.json ADDED Viewed

The diff for this file is too large to render. See raw diff

Curriculum_eval_results_math_llama_3_instruct_model_arith_8k_Vanilla_val.json ADDED Viewed

The diff for this file is too large to render. See raw diff

Curriculum_math_llama3_instruct_MWP2K_Vanilla_test_metrics.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+    "total_count": 2160,
+    "none_count": 0,
+    "match_count": 204,
+    "wrong_count": 1956,
+    "acc": 0.09444444444444444,
+    "avg_error": 5.616682130077772e+189,
+    "var_error": Infinity,
+    "mse": Infinity,
+    "vse": Infinity,
+    "mpe": 4.618319750152281e+171,
+    "vpe": Infinity,
+    "pass_at_1": null,
+    "ttr": 0.012804913378527145,
+    "entropy": 7.028671490219006
+}

Curriculum_math_llama3_instruct_MWP2K_Vanilla_val_metrics.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+    "total_count": 2160,
+    "none_count": 1,
+    "match_count": 652,
+    "wrong_count": 1507,
+    "acc": 0.30185185185185187,
+    "avg_error": 5.146415521589214e+187,
+    "var_error": Infinity,
+    "mse": 8.326508267078813e+304,
+    "vse": Infinity,
+    "mpe": 5.1464155215892134e+190,
+    "vpe": Infinity,
+    "pass_at_1": null,
+    "ttr": 0.008738425925925926,
+    "entropy": 5.190855468404559
+}

Curriculum_math_llama3_instruct_MWP4K_Vanilla_test_metrics.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+    "total_count": 2160,
+    "none_count": 0,
+    "match_count": 192,
+    "wrong_count": 1968,
+    "acc": 0.08888888888888889,
+    "avg_error": 4.071264763292613e+189,
+    "var_error": Infinity,
+    "mse": Infinity,
+    "vse": Infinity,
+    "mpe": 4.689228636126781e+172,
+    "vpe": Infinity,
+    "pass_at_1": null,
+    "ttr": 0.01227282600825429,
+    "entropy": 6.90205202173977
+}

Curriculum_math_llama3_instruct_MWP4K_Vanilla_val_metrics.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+    "total_count": 2160,
+    "none_count": 0,
+    "match_count": 627,
+    "wrong_count": 1533,
+    "acc": 0.2902777777777778,
+    "avg_error": 1.2745884773662552e+92,
+    "var_error": 3.507459123344596e+187,
+    "mse": 3.50908369913123e+187,
+    "vse": Infinity,
+    "mpe": -5.982995116305566e+79,
+    "vpe": 7.728406178278855e+162,
+    "pass_at_1": null,
+    "ttr": 0.00861545138888889,
+    "entropy": 5.384155831142046
+}

Curriculum_math_llama_3_LORA_Arithmetic_10k_Vanilla_test_metrics.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+    "total_count": 2160,
+    "none_count": 0,
+    "match_count": 396,
+    "wrong_count": 1764,
+    "acc": 0.18333333333333332,
+    "avg_error": 1.4032777777777778e+189,
+    "var_error": Infinity,
+    "mse": Infinity,
+    "vse": Infinity,
+    "mpe": 9.915285070575362e+170,
+    "vpe": Infinity,
+    "pass_at_1": null,
+    "ttr": 0.10221021136955892,
+    "entropy": 6.4392100361924545
+}

Curriculum_math_llama_3_LORA_Arithmetic_10k_Vanilla_val_metrics.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+    "total_count": 2160,
+    "none_count": 0,
+    "match_count": 743,
+    "wrong_count": 1417,
+    "acc": 0.3439814814814815,
+    "avg_error": -140973754299483.12,
+    "var_error": 4.291224315746973e+31,
+    "mse": 4.293211675687104e+31,
+    "vse": 3.979396756529488e+66,
+    "mpe": 6024.610757526451,
+    "vpe": 43895294489.4146,
+    "pass_at_1": null,
+    "ttr": 0.14054153619451096,
+    "entropy": 5.416380862616709
+}

Curriculum_math_llama_3_LORA_Arithmetic_2k_Vanilla_test_metrics.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+    "total_count": 2160,
+    "none_count": 0,
+    "match_count": 385,
+    "wrong_count": 1775,
+    "acc": 0.17824074074074073,
+    "avg_error": 1.210185185185185e+189,
+    "var_error": Infinity,
+    "mse": Infinity,
+    "vse": Infinity,
+    "mpe": 5.091730293284713e+167,
+    "vpe": Infinity,
+    "pass_at_1": null,
+    "ttr": 0.11367673179396093,
+    "entropy": 6.554592188868327
+}

Curriculum_math_llama_3_LORA_Arithmetic_2k_Vanilla_val_metrics.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+    "total_count": 2160,
+    "none_count": 0,
+    "match_count": 727,
+    "wrong_count": 1433,
+    "acc": 0.3365740740740741,
+    "avg_error": -140934063106490.0,
+    "var_error": 4.2912259689610905e+31,
+    "mse": 4.293212209975465e+31,
+    "vse": 3.979396756070794e+66,
+    "mpe": 55461.0563656412,
+    "vpe": 6636951408951.518,
+    "pass_at_1": null,
+    "ttr": 0.13636363636363635,
+    "entropy": 5.263913468908822
+}

Curriculum_math_llama_3_LORA_Arithmetic_4k_Vanilla_test_metrics.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+    "total_count": 2160,
+    "none_count": 0,
+    "match_count": 393,
+    "wrong_count": 1767,
+    "acc": 0.18194444444444444,
+    "avg_error": 1.2497233342592593e+189,
+    "var_error": Infinity,
+    "mse": Infinity,
+    "vse": Infinity,
+    "mpe": 1.9452414325632677e+168,
+    "vpe": Infinity,
+    "pass_at_1": null,
+    "ttr": 0.1115919629057187,
+    "entropy": 6.784684446529436
+}

Curriculum_math_llama_3_LORA_Arithmetic_4k_Vanilla_val_metrics.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+    "total_count": 2160,
+    "none_count": 0,
+    "match_count": 731,
+    "wrong_count": 1429,
+    "acc": 0.3384259259259259,
+    "avg_error": -140981271425810.9,
+    "var_error": 4.291224090103069e+31,
+    "mse": 4.2932116619923545e+31,
+    "vse": 3.979396756541245e+66,
+    "mpe": 1129.4876436687503,
+    "vpe": 1324937235.6857886,
+    "pass_at_1": null,
+    "ttr": 0.14141978759083287,
+    "entropy": 5.352818129373723
+}

Curriculum_math_llama_3_LORA_Arithmetic_6k_Vanilla_test_metrics.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+    "total_count": 2160,
+    "none_count": 0,
+    "match_count": 398,
+    "wrong_count": 1762,
+    "acc": 0.18425925925925926,
+    "avg_error": 1.6762690746301857e+189,
+    "var_error": Infinity,
+    "mse": Infinity,
+    "vse": Infinity,
+    "mpe": 4.541545149151995e+162,
+    "vpe": Infinity,
+    "pass_at_1": null,
+    "ttr": 0.10695134061569017,
+    "entropy": 6.73971045647783
+}

Curriculum_math_llama_3_LORA_Arithmetic_6k_Vanilla_val_metrics.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+    "total_count": 2160,
+    "none_count": 0,
+    "match_count": 734,
+    "wrong_count": 1426,
+    "acc": 0.3398148148148148,
+    "avg_error": -140981026030063.3,
+    "var_error": 4.291224096739589e+31,
+    "mse": 4.293211661709641e+31,
+    "vse": 3.979396756541489e+66,
+    "mpe": 4834.195309575507,
+    "vpe": 40631470456.149704,
+    "pass_at_1": null,
+    "ttr": 0.14211406279026564,
+    "entropy": 5.395096266869767
+}

Curriculum_math_llama_3_LORA_Arithmetic_8k_MWPMix_10k_Vanilla_test_metrics.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+    "total_count": 2160,
+    "none_count": 0,
+    "match_count": 401,
+    "wrong_count": 1759,
+    "acc": 0.18564814814814815,
+    "avg_error": 3.692215216512346e+189,
+    "var_error": Infinity,
+    "mse": Infinity,
+    "vse": Infinity,
+    "mpe": -1.1574074074074075e+188,
+    "vpe": Infinity,
+    "pass_at_1": null,
+    "ttr": 0.06564885496183206,
+    "entropy": 7.278446099742158
+}

Curriculum_math_llama_3_LORA_Arithmetic_8k_MWPMix_10k_Vanilla_val_metrics.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+    "total_count": 2160,
+    "none_count": 0,
+    "match_count": 752,
+    "wrong_count": 1408,
+    "acc": 0.34814814814814815,
+    "avg_error": -140414372883907.27,
+    "var_error": 4.291287238301365e+31,
+    "mse": 4.293258857912603e+31,
+    "vse": 3.979396716479524e+66,
+    "mpe": 6917.35793587359,
+    "vpe": 51383846068.49652,
+    "pass_at_1": null,
+    "ttr": 0.06228567865827046,
+    "entropy": 6.543151155783696
+}

Curriculum_math_llama_3_LORA_Arithmetic_8k_MWPMix_6k_Vanilla_test_metrics.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+    "total_count": 2160,
+    "none_count": 0,
+    "match_count": 406,
+    "wrong_count": 1754,
+    "acc": 0.18796296296296297,
+    "avg_error": 2.961113072993827e+189,
+    "var_error": Infinity,
+    "mse": Infinity,
+    "vse": Infinity,
+    "mpe": -1.2203703703703704e+188,
+    "vpe": Infinity,
+    "pass_at_1": null,
+    "ttr": 0.07898080652711831,
+    "entropy": 7.184033252728473
+}

Curriculum_math_llama_3_LORA_Arithmetic_8k_MWPMix_6k_Vanilla_val_metrics.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+    "total_count": 2160,
+    "none_count": 0,
+    "match_count": 764,
+    "wrong_count": 1396,
+    "acc": 0.3537037037037037,
+    "avg_error": -140470420031222.45,
+    "var_error": 4.291285215005026e+31,
+    "mse": 4.2932584088954035e+31,
+    "vse": 3.979396716865031e+66,
+    "mpe": 6917.484537931135,
+    "vpe": 51383845229.859825,
+    "pass_at_1": null,
+    "ttr": 0.0746025591314463,
+    "entropy": 6.437822505397191
+}

Curriculum_math_llama_3_LORA_Arithmetic_8k_MWPMix_8k_Vanilla_test_metrics.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+    "total_count": 2160,
+    "none_count": 0,
+    "match_count": 402,
+    "wrong_count": 1758,
+    "acc": 0.18611111111111112,
+    "avg_error": 3.943071482407408e+189,
+    "var_error": Infinity,
+    "mse": Infinity,
+    "vse": Infinity,
+    "mpe": -1.1574074074074075e+188,
+    "vpe": Infinity,
+    "pass_at_1": null,
+    "ttr": 0.06736594121606462,
+    "entropy": 7.249353734435205
+}

Curriculum_math_llama_3_LORA_Arithmetic_8k_MWPMix_8k_Vanilla_val_metrics.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+    "total_count": 2160,
+    "none_count": 0,
+    "match_count": 754,
+    "wrong_count": 1406,
+    "acc": 0.3490740740740741,
+    "avg_error": -140469233772431.44,
+    "var_error": 4.2912852490802965e+31,
+    "mse": 4.293258409643957e+31,
+    "vse": 3.979396716864392e+66,
+    "mpe": 6918.673170334994,
+    "vpe": 51383829442.65376,
+    "pass_at_1": null,
+    "ttr": 0.06512508981644784,
+    "entropy": 6.534206821455875
+}

Curriculum_math_llama_3_LORA_Arithmetic_8k_Vanilla_test_metrics.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+    "total_count": 2160,
+    "none_count": 0,
+    "match_count": 393,
+    "wrong_count": 1767,
+    "acc": 0.18194444444444444,
+    "avg_error": 1.6635089181486113e+189,
+    "var_error": Infinity,
+    "mse": Infinity,
+    "vse": Infinity,
+    "mpe": 1.037829848896136e+171,
+    "vpe": Infinity,
+    "pass_at_1": null,
+    "ttr": 0.10583580613254204,
+    "entropy": 6.574374474108696
+}