Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6615f91b16735134a0a8f855baba69ff9c22d83794bcce12c03eaff9cff96d2b
+oid sha256:0b9b35a9d9ba93abce23de00bd868a765a44c10e35e19db5eea793fbebf0bb0d
 size 239536272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b2330aab9b95bec6ac323604ebf25f43905e0ec18899bcce03ec8cb92594ed4
+oid sha256:eb654f67b4f1db68451da32e5b2b43d8bb2a43b4bc72e4d18ea4898679595a79
 size 479362682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a78bba421cdebd0ac0ebf8ac8f712dca66b2639ca4ab7783674a95bba8eddab
+oid sha256:c4ae37e588f32169c8baeeb564cffaf0c2e803a8b480803a24a536e1e25206ab
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:314cd2d242b645ad34e70f38ab9fe070ce4e569c009c4514e03ac07e340e2352
+oid sha256:151393d576d0e2b75f0072b32440db1cc07439be6e8573f88d299ed1642a1fac
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d3ce56892ffad947c6cddfee20d92a7d98143426b3a0b37bc17aaa45960d9e8
+oid sha256:402da88e27404b69f53a420f22c45132094ffd90017cec393d4ddd90ad0d7274
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b340da5339fb654bf96f0269de5901d2699cda91a1e6799304229233baf7342c
+oid sha256:003bfa6e354539851b23ba440aa90eb1a15a1e5e99867c72e4afaa3afeb2c406
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.1342406272888184,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.01613228473482557,
+  "best_metric": 3.0954277515411377,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03226456946965114,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 43.326,
       "eval_steps_per_second": 11.265,
       "step": 25
+    },
+    {
+      "epoch": 0.016777576124218593,
+      "grad_norm": 0.24213682115077972,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 3.0755,
+      "step": 26
+    },
+    {
+      "epoch": 0.017422867513611617,
+      "grad_norm": 0.2518942952156067,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 3.0893,
+      "step": 27
+    },
+    {
+      "epoch": 0.018068158903004637,
+      "grad_norm": 0.2834096848964691,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 3.0998,
+      "step": 28
+    },
+    {
+      "epoch": 0.01871345029239766,
+      "grad_norm": 0.30936554074287415,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 3.0854,
+      "step": 29
+    },
+    {
+      "epoch": 0.019358741681790685,
+      "grad_norm": 0.3345261216163635,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 3.0937,
+      "step": 30
+    },
+    {
+      "epoch": 0.020004033071183706,
+      "grad_norm": 0.35885950922966003,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 3.1281,
+      "step": 31
+    },
+    {
+      "epoch": 0.02064932446057673,
+      "grad_norm": 0.3998109698295593,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 3.1258,
+      "step": 32
+    },
+    {
+      "epoch": 0.021294615849969754,
+      "grad_norm": 0.4201498329639435,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 3.1414,
+      "step": 33
+    },
+    {
+      "epoch": 0.021939907239362774,
+      "grad_norm": 0.5526490807533264,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 3.237,
+      "step": 34
+    },
+    {
+      "epoch": 0.022585198628755798,
+      "grad_norm": 0.5647488236427307,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 3.314,
+      "step": 35
+    },
+    {
+      "epoch": 0.02323049001814882,
+      "grad_norm": 0.5095055103302002,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 3.3306,
+      "step": 36
+    },
+    {
+      "epoch": 0.023875781407541843,
+      "grad_norm": 0.8741942048072815,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 3.3814,
+      "step": 37
+    },
+    {
+      "epoch": 0.024521072796934867,
+      "grad_norm": 0.34626221656799316,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 3.1175,
+      "step": 38
+    },
+    {
+      "epoch": 0.025166364186327887,
+      "grad_norm": 0.44862890243530273,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 3.1147,
+      "step": 39
+    },
+    {
+      "epoch": 0.02581165557572091,
+      "grad_norm": 0.4688248038291931,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 3.0424,
+      "step": 40
+    },
+    {
+      "epoch": 0.026456946965113935,
+      "grad_norm": 0.46559861302375793,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 3.0405,
+      "step": 41
+    },
+    {
+      "epoch": 0.027102238354506956,
+      "grad_norm": 0.5473563075065613,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 3.0519,
+      "step": 42
+    },
+    {
+      "epoch": 0.02774752974389998,
+      "grad_norm": 0.4109938144683838,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 3.0851,
+      "step": 43
+    },
+    {
+      "epoch": 0.028392821133293004,
+      "grad_norm": 0.34564486145973206,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 3.1156,
+      "step": 44
+    },
+    {
+      "epoch": 0.029038112522686024,
+      "grad_norm": 0.3452329933643341,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 3.0701,
+      "step": 45
+    },
+    {
+      "epoch": 0.02968340391207905,
+      "grad_norm": 0.3867616057395935,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 3.1635,
+      "step": 46
+    },
+    {
+      "epoch": 0.030328695301472072,
+      "grad_norm": 0.6041641235351562,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 3.359,
+      "step": 47
+    },
+    {
+      "epoch": 0.030973986690865093,
+      "grad_norm": 0.5437290668487549,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 3.3044,
+      "step": 48
+    },
+    {
+      "epoch": 0.03161927808025811,
+      "grad_norm": 1.059544563293457,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 3.3853,
+      "step": 49
+    },
+    {
+      "epoch": 0.03226456946965114,
+      "grad_norm": 1.154407262802124,
+      "learning_rate": 1e-05,
+      "loss": 3.4564,
+      "step": 50
+    },
+    {
+      "epoch": 0.03226456946965114,
+      "eval_loss": 3.0954277515411377,
+      "eval_runtime": 1.144,
+      "eval_samples_per_second": 43.706,
+      "eval_steps_per_second": 11.363,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.114626154561536e+17,
+  "total_flos": 2.229252309123072e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null