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:ab7108019882a9bcb4e740fae2009e3225c39d3a92e3686de517715bc317230c
+oid sha256:f56558fb68b1aec79c0de5f50f594d7d89b28dcb4a243521c11b59873c5ee4a2
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f9d7ab5838d5d8d713fe806d539ae63ecb827316a666ad94d991dfcc011112e
+oid sha256:c6bc738de8ed0b5fcad30305c5d4ad8e3d525d4134604f1101e3357434e1e814
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e11b2fc54899c5c578336c5baee5bf3f4fac7f6e1587c40c837ff2007d4d44a2
+oid sha256:70934d06096fe044e7bd400e4671cec5f04206a1114d2419a64071d28a7aa4ad
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c55e9653d4fa0715dd7d5e099ce879c4a703c72e18b04b9cdd0a8b680e0521e3
+oid sha256:0247f1239b901aa70372e10bd907ae420b89c17b8a1f9c6f0f5c1e2342b3ac81
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f453f0cfd2a3cae1cf26949fb8281784822b1b8ef3cdecf57595a2ec3f628843
+oid sha256:e63ee6f67b09f503c7b700988266f95ff6e26126ffbc65abde72953edb858150
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a95ac1b2b03166bde16292859ce77af9ecd6970ea1b936b29b19b8045c0ed806
+oid sha256:740424eec58a03b38091097315fbbe78a7e1850c79050b755611afab51b6353f
 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": 3.281138924648985e-05,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.05650515609549371,
+  "best_metric": 2.119436794600915e-05,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.11301031219098742,
   "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": 16.804,
       "eval_steps_per_second": 4.369,
       "step": 25
+    },
+    {
+      "epoch": 0.05876536233931346,
+      "grad_norm": 0.04972488060593605,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.001,
+      "step": 26
+    },
+    {
+      "epoch": 0.06102556858313321,
+      "grad_norm": 0.048093147575855255,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0006,
+      "step": 27
+    },
+    {
+      "epoch": 0.06328577482695295,
+      "grad_norm": 0.0384451225399971,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0006,
+      "step": 28
+    },
+    {
+      "epoch": 0.06554598107077271,
+      "grad_norm": 0.1282583624124527,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0016,
+      "step": 29
+    },
+    {
+      "epoch": 0.06780618731459245,
+      "grad_norm": 0.02835065871477127,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0009,
+      "step": 30
+    },
+    {
+      "epoch": 0.07006639355841221,
+      "grad_norm": 0.025677639991044998,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0007,
+      "step": 31
+    },
+    {
+      "epoch": 0.07232659980223195,
+      "grad_norm": 0.011029267683625221,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0004,
+      "step": 32
+    },
+    {
+      "epoch": 0.0745868060460517,
+      "grad_norm": 0.029804445803165436,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0008,
+      "step": 33
+    },
+    {
+      "epoch": 0.07684701228987145,
+      "grad_norm": 0.02739046700298786,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0005,
+      "step": 34
+    },
+    {
+      "epoch": 0.0791072185336912,
+      "grad_norm": 0.03442985564470291,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0006,
+      "step": 35
+    },
+    {
+      "epoch": 0.08136742477751095,
+      "grad_norm": 0.011169228702783585,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0004,
+      "step": 36
+    },
+    {
+      "epoch": 0.0836276310213307,
+      "grad_norm": 0.008100761100649834,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0003,
+      "step": 37
+    },
+    {
+      "epoch": 0.08588783726515045,
+      "grad_norm": 0.6260887384414673,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.1661,
+      "step": 38
+    },
+    {
+      "epoch": 0.0881480435089702,
+      "grad_norm": 1.2297857999801636,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0128,
+      "step": 39
+    },
+    {
+      "epoch": 0.09040824975278994,
+      "grad_norm": 1.5309454202651978,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0229,
+      "step": 40
+    },
+    {
+      "epoch": 0.0926684559966097,
+      "grad_norm": 1.832742691040039,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.14,
+      "step": 41
+    },
+    {
+      "epoch": 0.09492866224042944,
+      "grad_norm": 0.0456574372947216,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0007,
+      "step": 42
+    },
+    {
+      "epoch": 0.0971888684842492,
+      "grad_norm": 0.037164654582738876,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0006,
+      "step": 43
+    },
+    {
+      "epoch": 0.09944907472806894,
+      "grad_norm": 0.024082988500595093,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0009,
+      "step": 44
+    },
+    {
+      "epoch": 0.10170928097188868,
+      "grad_norm": 0.009204435162246227,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0005,
+      "step": 45
+    },
+    {
+      "epoch": 0.10396948721570844,
+      "grad_norm": 0.008595156483352184,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0004,
+      "step": 46
+    },
+    {
+      "epoch": 0.10622969345952818,
+      "grad_norm": 0.00714592169970274,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0005,
+      "step": 47
+    },
+    {
+      "epoch": 0.10848989970334794,
+      "grad_norm": 0.016524558886885643,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0004,
+      "step": 48
+    },
+    {
+      "epoch": 0.11075010594716768,
+      "grad_norm": 0.009992051869630814,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0003,
+      "step": 49
+    },
+    {
+      "epoch": 0.11301031219098742,
+      "grad_norm": 0.009089923463761806,
+      "learning_rate": 1e-05,
+      "loss": 0.0004,
+      "step": 50
+    },
+    {
+      "epoch": 0.11301031219098742,
+      "eval_loss": 2.119436794600915e-05,
+      "eval_runtime": 2.9422,
+      "eval_samples_per_second": 16.994,
+      "eval_steps_per_second": 4.419,
+      "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": 2.629578157719552e+17,
+  "total_flos": 5.259156315439104e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null