Training in progress, step 81, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:523d69da257f0c85429a4ac40227e30f692220895a6861332b60df44372fd2ba
+oid sha256:37c912bb5d83edee2139227ce07a747d94f46f4244f92e2b75a2cf32ad0aa135
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f2fb1bb1538078e71fda652609cd9e6c24d406e49aae111fc74c94390e545cf
+oid sha256:297634343be7a9bc6c9d93adea82a9c4bc9fd9453bb20ce9aff0eb62512979e2
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a1c1ca2eb2d63320002b57411b027dbb181001114302d8b335c26f8674b2007
+oid sha256:6afe91f92ca570ec00fc0046b49d53bdab62ad236d2d8202ed8b87546871392c
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d222eced2b5b34720eced06dd5e0608c4941e9c1353fd156035abd0e5cf7b7ac
+oid sha256:66970dc56e78d2d5e63f5fbb36b724c778ac0af6cc13990a5b7eb3eebb254a9d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:365729cdf68ba37e104e3c2d3021719ddcc569e3182cc6bc5243308e3d833e68
+oid sha256:c1b0f5d80f65e193095ce4aa52e70a0ead54bfd122929297ea8fdb2494e13cdb
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f44433a75e833bf28f18de1fb528eecd83ec14d73c346ae4ca18620fb6ee9df
+oid sha256:34c3c5787d72bf3b7ae0cfd936603b63e32f8cf1738300895a5f8328e31811bf
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:766d4898d9bcfdf7ea7b5b0fed47e9adbde3f4862283013c7956a2674af670bf
+oid sha256:0afdbd8ef2f5fe06163b573a80024a95f2ec653cc655cd639ecb8cceae52c1bb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.4470236301422119,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 1.2402169701666022,
+  "epoch": 2.009298721425804,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 81,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,231 @@
       "eval_samples_per_second": 31.875,
       "eval_steps_per_second": 8.287,
       "step": 50
+    },
+    {
+      "epoch": 1.2650135606354127,
+      "grad_norm": 1.0695531368255615,
+      "learning_rate": 0.00011520337018925895,
+      "loss": 0.4534,
+      "step": 51
+    },
+    {
+      "epoch": 1.289810151104223,
+      "grad_norm": 0.326072633266449,
+      "learning_rate": 0.00011025408169024583,
+      "loss": 0.4319,
+      "step": 52
+    },
+    {
+      "epoch": 1.3146067415730336,
+      "grad_norm": 0.3365119993686676,
+      "learning_rate": 0.00010539135774085195,
+      "loss": 0.4362,
+      "step": 53
+    },
+    {
+      "epoch": 1.3394033320418441,
+      "grad_norm": 0.4222407042980194,
+      "learning_rate": 0.0001006228873071517,
+      "loss": 0.43,
+      "step": 54
+    },
+    {
+      "epoch": 1.3641999225106547,
+      "grad_norm": 0.35905617475509644,
+      "learning_rate": 9.595621032103801e-05,
+      "loss": 0.427,
+      "step": 55
+    },
+    {
+      "epoch": 1.3889965129794652,
+      "grad_norm": 0.26657891273498535,
+      "learning_rate": 9.139870575803991e-05,
+      "loss": 0.4208,
+      "step": 56
+    },
+    {
+      "epoch": 1.4137931034482758,
+      "grad_norm": 0.2459261119365692,
+      "learning_rate": 8.695757996964544e-05,
+      "loss": 0.4123,
+      "step": 57
+    },
+    {
+      "epoch": 1.4385896939170864,
+      "grad_norm": 0.3061677813529968,
+      "learning_rate": 8.263985528857921e-05,
+      "loss": 0.429,
+      "step": 58
+    },
+    {
+      "epoch": 1.463386284385897,
+      "grad_norm": 0.4884737432003021,
+      "learning_rate": 7.845235892505033e-05,
+      "loss": 0.4428,
+      "step": 59
+    },
+    {
+      "epoch": 1.4881828748547075,
+      "grad_norm": 0.3974491059780121,
+      "learning_rate": 7.440171217153001e-05,
+      "loss": 0.4357,
+      "step": 60
+    },
+    {
+      "epoch": 1.512979465323518,
+      "grad_norm": 0.31677502393722534,
+      "learning_rate": 7.049431993312759e-05,
+      "loss": 0.4063,
+      "step": 61
+    },
+    {
+      "epoch": 1.5377760557923286,
+      "grad_norm": 0.5034978985786438,
+      "learning_rate": 6.67363606001183e-05,
+      "loss": 0.416,
+      "step": 62
+    },
+    {
+      "epoch": 1.5625726462611391,
+      "grad_norm": 0.3409871757030487,
+      "learning_rate": 6.313377627863891e-05,
+      "loss": 0.406,
+      "step": 63
+    },
+    {
+      "epoch": 1.5873692367299497,
+      "grad_norm": 0.2753334939479828,
+      "learning_rate": 5.9692263394996376e-05,
+      "loss": 0.3993,
+      "step": 64
+    },
+    {
+      "epoch": 1.6121658271987602,
+      "grad_norm": 0.4815467596054077,
+      "learning_rate": 5.641726368844675e-05,
+      "loss": 0.4139,
+      "step": 65
+    },
+    {
+      "epoch": 1.6369624176675708,
+      "grad_norm": 0.42127665877342224,
+      "learning_rate": 5.3313955606687296e-05,
+      "loss": 0.4155,
+      "step": 66
+    },
+    {
+      "epoch": 1.6617590081363813,
+      "grad_norm": 0.29522252082824707,
+      "learning_rate": 5.038724611766585e-05,
+      "loss": 0.4038,
+      "step": 67
+    },
+    {
+      "epoch": 1.6865555986051919,
+      "grad_norm": 0.3209092319011688,
+      "learning_rate": 4.764176295065636e-05,
+      "loss": 0.4012,
+      "step": 68
+    },
+    {
+      "epoch": 1.7113521890740024,
+      "grad_norm": 0.4263613820075989,
+      "learning_rate": 4.508184727886723e-05,
+      "loss": 0.4195,
+      "step": 69
+    },
+    {
+      "epoch": 1.736148779542813,
+      "grad_norm": 0.42666929960250854,
+      "learning_rate": 4.271154685515435e-05,
+      "loss": 0.4198,
+      "step": 70
+    },
+    {
+      "epoch": 1.7609453700116235,
+      "grad_norm": 0.29947665333747864,
+      "learning_rate": 4.0534609611692115e-05,
+      "loss": 0.3954,
+      "step": 71
+    },
+    {
+      "epoch": 1.785741960480434,
+      "grad_norm": 0.3265860676765442,
+      "learning_rate": 3.855447773372175e-05,
+      "loss": 0.402,
+      "step": 72
+    },
+    {
+      "epoch": 1.8105385509492444,
+      "grad_norm": 0.4390391707420349,
+      "learning_rate": 3.6774282216749336e-05,
+      "loss": 0.3979,
+      "step": 73
+    },
+    {
+      "epoch": 1.835335141418055,
+      "grad_norm": 0.28207874298095703,
+      "learning_rate": 3.519683791579824e-05,
+      "loss": 0.3837,
+      "step": 74
+    },
+    {
+      "epoch": 1.8601317318868655,
+      "grad_norm": 0.3026869297027588,
+      "learning_rate": 3.382463909454464e-05,
+      "loss": 0.3973,
+      "step": 75
+    },
+    {
+      "epoch": 1.8601317318868655,
+      "eval_loss": 0.39713945984840393,
+      "eval_runtime": 1.5675,
+      "eval_samples_per_second": 31.898,
+      "eval_steps_per_second": 8.294,
+      "step": 75
+    },
+    {
+      "epoch": 1.884928322355676,
+      "grad_norm": 0.25843551754951477,
+      "learning_rate": 3.265985548137413e-05,
+      "loss": 0.3886,
+      "step": 76
+    },
+    {
+      "epoch": 1.9097249128244866,
+      "grad_norm": 0.23140764236450195,
+      "learning_rate": 3.1704328838595e-05,
+      "loss": 0.3856,
+      "step": 77
+    },
+    {
+      "epoch": 1.9345215032932972,
+      "grad_norm": 0.34332171082496643,
+      "learning_rate": 3.0959570050233586e-05,
+      "loss": 0.3945,
+      "step": 78
+    },
+    {
+      "epoch": 1.9593180937621077,
+      "grad_norm": 0.3156374990940094,
+      "learning_rate": 3.0426756733016063e-05,
+      "loss": 0.3956,
+      "step": 79
+    },
+    {
+      "epoch": 1.9841146842309183,
+      "grad_norm": 0.34009358286857605,
+      "learning_rate": 3.010673137431425e-05,
+      "loss": 0.4036,
+      "step": 80
+    },
+    {
+      "epoch": 2.009298721425804,
+      "grad_norm": 0.43867069482803345,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 0.6494,
+      "step": 81
     }
   ],
   "logging_steps": 1,
@@ -404,12 +629,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.1938032281232343e+18,
+  "total_flos": 1.9339388490004562e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null