Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6404eb21f64f0fd0495017d0d23caaec61252653ab90a1588bbb3c531463c3c
+oid sha256:9624e9a151663ac191cc4fa232c61bd9caaa5f68fc967bf4426ca5df8971d9b9
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6704fcb92df52ce2a4fd1ee2c475016dae08da655885600db67dc4c7b475ab86
+oid sha256:a7677e032df90eb88721c864579dca479a5b6579e09f8f42cb668edc62cbed8d
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c453a58c4bf4312ef0a30c0b43d19fc75e51ae316fb27c948d9633e8580b938
+oid sha256:ac2a5b05f09b8564f5d7ae67ac0484834ab5096f9c2c5416efc0bd11bed918dd
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e7dff3eab3ccb4a7c3120630c486dd2cff179895632db0ffcb893f2176156c6
+oid sha256:1bdd58a7b31c078fa85d00c7c6485823b15270c30aba6855ca78181731d87134
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a827522647025d34e47663465b058aa44ac5e109e57377e97716e2276fb8fe36
+oid sha256:96335fae8d0428a10bf29ce620e4c16471dfc1c7bc18964f4276730c5e3fa77e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dda0c85b48e6d17862dee43bbd5a51b1e593b03910bbd2f556f8212c0007227e
+oid sha256:0af91e38f8ee05f8cc00ff1294dd2d779b194430a94ac4b05a2cb8d13aa0041e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df19ed1a9610a5422497073697cbf4575f80de47fbb46ef0cdd2779386b031fa
+oid sha256:a5b53655d80c3ade692dacae57cafa4aff84c325b5cb8d0fba89d01b50d41566
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.652353048324585,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.06483770312436682,
+  "best_metric": 0.623828649520874,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.09725655468655023,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 17.021,
       "eval_steps_per_second": 4.426,
       "step": 50
+    },
+    {
+      "epoch": 0.06613445718685415,
+      "grad_norm": 11.396697044372559,
+      "learning_rate": 5.192909139858981e-05,
+      "loss": 32.6268,
+      "step": 51
+    },
+    {
+      "epoch": 0.0674312112493415,
+      "grad_norm": 13.8756742477417,
+      "learning_rate": 5.0398113297608465e-05,
+      "loss": 30.8687,
+      "step": 52
+    },
+    {
+      "epoch": 0.06872796531182883,
+      "grad_norm": 11.302550315856934,
+      "learning_rate": 4.887250079066892e-05,
+      "loss": 20.7947,
+      "step": 53
+    },
+    {
+      "epoch": 0.07002471937431616,
+      "grad_norm": 8.959757804870605,
+      "learning_rate": 4.7354032673710005e-05,
+      "loss": 14.8,
+      "step": 54
+    },
+    {
+      "epoch": 0.0713214734368035,
+      "grad_norm": 9.0787992477417,
+      "learning_rate": 4.584447941263149e-05,
+      "loss": 10.1572,
+      "step": 55
+    },
+    {
+      "epoch": 0.07261822749929084,
+      "grad_norm": 6.953489303588867,
+      "learning_rate": 4.43456010790099e-05,
+      "loss": 6.886,
+      "step": 56
+    },
+    {
+      "epoch": 0.07391498156177817,
+      "grad_norm": 6.784447193145752,
+      "learning_rate": 4.285914529793391e-05,
+      "loss": 10.6766,
+      "step": 57
+    },
+    {
+      "epoch": 0.07521173562426552,
+      "grad_norm": 7.345515251159668,
+      "learning_rate": 4.13868452103516e-05,
+      "loss": 13.2427,
+      "step": 58
+    },
+    {
+      "epoch": 0.07650848968675285,
+      "grad_norm": 10.04677963256836,
+      "learning_rate": 3.9930417452305626e-05,
+      "loss": 15.7304,
+      "step": 59
+    },
+    {
+      "epoch": 0.07780524374924018,
+      "grad_norm": 13.683038711547852,
+      "learning_rate": 3.8491560153412466e-05,
+      "loss": 18.4109,
+      "step": 60
+    },
+    {
+      "epoch": 0.07910199781172753,
+      "grad_norm": 12.892768859863281,
+      "learning_rate": 3.707195095691913e-05,
+      "loss": 22.273,
+      "step": 61
+    },
+    {
+      "epoch": 0.08039875187421486,
+      "grad_norm": 17.1517391204834,
+      "learning_rate": 3.567324506364632e-05,
+      "loss": 32.1346,
+      "step": 62
+    },
+    {
+      "epoch": 0.08169550593670219,
+      "grad_norm": 18.07764434814453,
+      "learning_rate": 3.4297073302098156e-05,
+      "loss": 39.0696,
+      "step": 63
+    },
+    {
+      "epoch": 0.08299225999918954,
+      "grad_norm": 10.018913269042969,
+      "learning_rate": 3.2945040226989244e-05,
+      "loss": 31.6719,
+      "step": 64
+    },
+    {
+      "epoch": 0.08428901406167687,
+      "grad_norm": 9.357498168945312,
+      "learning_rate": 3.16187222484055e-05,
+      "loss": 19.8276,
+      "step": 65
+    },
+    {
+      "epoch": 0.0855857681241642,
+      "grad_norm": 6.495688438415527,
+      "learning_rate": 3.0319665793780648e-05,
+      "loss": 12.7109,
+      "step": 66
+    },
+    {
+      "epoch": 0.08688252218665153,
+      "grad_norm": 6.495363712310791,
+      "learning_rate": 2.9049385504830985e-05,
+      "loss": 10.4677,
+      "step": 67
+    },
+    {
+      "epoch": 0.08817927624913888,
+      "grad_norm": 7.190054416656494,
+      "learning_rate": 2.7809362471550748e-05,
+      "loss": 10.2256,
+      "step": 68
+    },
+    {
+      "epoch": 0.08947603031162621,
+      "grad_norm": 7.307028293609619,
+      "learning_rate": 2.660104250532764e-05,
+      "loss": 14.0544,
+      "step": 69
+    },
+    {
+      "epoch": 0.09077278437411354,
+      "grad_norm": 4.946413516998291,
+      "learning_rate": 2.5425834453191232e-05,
+      "loss": 5.7595,
+      "step": 70
+    },
+    {
+      "epoch": 0.09206953843660089,
+      "grad_norm": 7.481423854827881,
+      "learning_rate": 2.4285108555160577e-05,
+      "loss": 13.2307,
+      "step": 71
+    },
+    {
+      "epoch": 0.09336629249908822,
+      "grad_norm": 9.990346908569336,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 19.5935,
+      "step": 72
+    },
+    {
+      "epoch": 0.09466304656157555,
+      "grad_norm": 9.962550163269043,
+      "learning_rate": 2.2112381607484417e-05,
+      "loss": 20.8605,
+      "step": 73
+    },
+    {
+      "epoch": 0.0959598006240629,
+      "grad_norm": 15.367573738098145,
+      "learning_rate": 2.1082913860268765e-05,
+      "loss": 32.2455,
+      "step": 74
+    },
+    {
+      "epoch": 0.09725655468655023,
+      "grad_norm": 23.091154098510742,
+      "learning_rate": 2.0092991918301108e-05,
+      "loss": 34.7624,
+      "step": 75
+    },
+    {
+      "epoch": 0.09725655468655023,
+      "eval_loss": 0.623828649520874,
+      "eval_runtime": 2.9349,
+      "eval_samples_per_second": 17.036,
+      "eval_steps_per_second": 4.429,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -409,7 +592,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.259926510449459e+17,
+  "total_flos": 7.889478898365235e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null