Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37cb6fcf2118031e6820a7b387e23bfcf61dea09ea261198966377915ac16552
+oid sha256:0787b2b6f52668751bd29ff1f0d13d967dd5ee1773e44663d27b2b14f99ca702
 size 60599872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a7b43d2c9b9d703709ab8c11696b1ca400338181547aedb4a1bfbe694997399
+oid sha256:8531d15a40fdc5e02f43819b35ade565d2106270f3ae26a3e1f2164dbd57766c
 size 121392706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdba78271966214ad12a9e8576500a185ab1e7c7454e11290b4c8ee2de6f42b8
+oid sha256:e95f7e1c9e69adea370cab0284c559f4d5ade5b8e331920b0767e4027e0aab12
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cee0cb9c0ea0a8e740a72af738d4a4a23903da5e212c564519ff916fdbeb6026
+oid sha256:f4e046768ed8fcb6e220a34cb2683c8daef20866154f86108e88f8effdbaa4aa
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0ce96ebff4349fb324d052f4b3320140cfcb06aede2f7737f0bdfdb0660ce66
+oid sha256:a742b1fd4f546493b4d3219eea107f1799cf2f9edd058196f1e7f71644be0b89
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef2aef5beeef544c54e463f62d2c91ca8fa3e92710652cdd38433100b2826eb9
+oid sha256:2135788b798e2cb1ca1dee32d2b4f9f2e554cda03427b773d6a6e3c3ba1513fd
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:370cee31176b8bff781da8f054b9870dc93c63a8623674218a84718aa7abd3af
+oid sha256:051dee7dfbeecb34b46e8409ffafec324501f465585234624669bc8c9e863ae4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.9584548473358154,
-  "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.03865169986955051,
+  "best_metric": 1.9432753324508667,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.05153559982606735,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,189 @@
       "eval_samples_per_second": 105.648,
       "eval_steps_per_second": 27.468,
       "step": 75
+    },
+    {
+      "epoch": 0.03916705586781118,
+      "grad_norm": 0.6455321311950684,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.9549,
+      "step": 76
+    },
+    {
+      "epoch": 0.03968241186607186,
+      "grad_norm": 0.6703755259513855,
+      "learning_rate": 2.215611672859741e-05,
+      "loss": 1.7557,
+      "step": 77
+    },
+    {
+      "epoch": 0.04019776786433253,
+      "grad_norm": 0.7443282008171082,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.8299,
+      "step": 78
+    },
+    {
+      "epoch": 0.04071312386259321,
+      "grad_norm": 0.7544194459915161,
+      "learning_rate": 2.0214529598676836e-05,
+      "loss": 2.032,
+      "step": 79
+    },
+    {
+      "epoch": 0.04122847986085388,
+      "grad_norm": 0.7718132138252258,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.8646,
+      "step": 80
+    },
+    {
+      "epoch": 0.04174383585911456,
+      "grad_norm": 0.8127806186676025,
+      "learning_rate": 1.842189919337732e-05,
+      "loss": 2.0232,
+      "step": 81
+    },
+    {
+      "epoch": 0.04225919185737523,
+      "grad_norm": 0.7979803681373596,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 2.04,
+      "step": 82
+    },
+    {
+      "epoch": 0.0427745478556359,
+      "grad_norm": 1.0075422525405884,
+      "learning_rate": 1.6785901831303956e-05,
+      "loss": 2.2471,
+      "step": 83
+    },
+    {
+      "epoch": 0.043289903853896576,
+      "grad_norm": 0.9252327680587769,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 2.3283,
+      "step": 84
+    },
+    {
+      "epoch": 0.04380525985215725,
+      "grad_norm": 1.0584813356399536,
+      "learning_rate": 1.531354310432403e-05,
+      "loss": 2.3342,
+      "step": 85
+    },
+    {
+      "epoch": 0.044320615850417924,
+      "grad_norm": 1.0674748420715332,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 2.3349,
+      "step": 86
+    },
+    {
+      "epoch": 0.044835971848678595,
+      "grad_norm": 1.1149811744689941,
+      "learning_rate": 1.4011127878547087e-05,
+      "loss": 2.496,
+      "step": 87
+    },
+    {
+      "epoch": 0.045351327846939266,
+      "grad_norm": 0.8089895844459534,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.8868,
+      "step": 88
+    },
+    {
+      "epoch": 0.04586668384519994,
+      "grad_norm": 0.7371775507926941,
+      "learning_rate": 1.2884233295920353e-05,
+      "loss": 1.9132,
+      "step": 89
+    },
+    {
+      "epoch": 0.046382039843460614,
+      "grad_norm": 0.7362411618232727,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.8683,
+      "step": 90
+    },
+    {
+      "epoch": 0.04689739584172129,
+      "grad_norm": 0.750278651714325,
+      "learning_rate": 1.1937684892050604e-05,
+      "loss": 1.9239,
+      "step": 91
+    },
+    {
+      "epoch": 0.04741275183998196,
+      "grad_norm": 0.8272152543067932,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 2.0319,
+      "step": 92
+    },
+    {
+      "epoch": 0.04792810783824263,
+      "grad_norm": 0.850062370300293,
+      "learning_rate": 1.1175535932519987e-05,
+      "loss": 1.8686,
+      "step": 93
+    },
+    {
+      "epoch": 0.04844346383650331,
+      "grad_norm": 0.8906591534614563,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 2.0806,
+      "step": 94
+    },
+    {
+      "epoch": 0.04895881983476398,
+      "grad_norm": 0.877006471157074,
+      "learning_rate": 1.0601050056180447e-05,
+      "loss": 2.0558,
+      "step": 95
+    },
+    {
+      "epoch": 0.04947417583302466,
+      "grad_norm": 1.0203922986984253,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 2.1596,
+      "step": 96
+    },
+    {
+      "epoch": 0.04998953183128533,
+      "grad_norm": 0.8805986046791077,
+      "learning_rate": 1.0216687299751144e-05,
+      "loss": 2.1993,
+      "step": 97
+    },
+    {
+      "epoch": 0.05050488782954601,
+      "grad_norm": 0.9580576419830322,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 2.2289,
+      "step": 98
+    },
+    {
+      "epoch": 0.05102024382780668,
+      "grad_norm": 1.0123631954193115,
+      "learning_rate": 1.0024093563563546e-05,
+      "loss": 2.264,
+      "step": 99
+    },
+    {
+      "epoch": 0.05153559982606735,
+      "grad_norm": 1.3854719400405884,
+      "learning_rate": 1e-05,
+      "loss": 2.4363,
+      "step": 100
+    },
+    {
+      "epoch": 0.05153559982606735,
+      "eval_loss": 1.9432753324508667,
+      "eval_runtime": 0.4737,
+      "eval_samples_per_second": 105.542,
+      "eval_steps_per_second": 27.441,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -587,12 +770,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.81668108009472e+16,
+  "total_flos": 5.08890810679296e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null