Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ad79f895cf2dbe58ddbfaca459ea7f155d66a659d961f8dbb0b8f6bf0dd3210
+oid sha256:cc13d28bff34345c0546b0d558e9e80a12e35222f2757a8429f7cabebd63af97
 size 78207176

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32153e93287f0535fea7ca689b492842a8ff7975249cf5c4b3b2a5728eabe127
+oid sha256:c7446fa3c185a344f201c613bf8339b6cfd8a992c1083ad4581a110ff3c4ebcb
 size 40177764

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a331aa86290b4656b841dbd6967ddc605092f3cf189dcf6a422c67d7f4a79bfa
+oid sha256:ab35dd70a8a3b1415963451e9e08c8788bb36ab8d5da119cebd6ed06e8e7e4de
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb15fdd4c0ab874f4afa0ea95fae119cbc74554df5fbe92ab825fe27063eaa04
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3771291971206665,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.005332480136511492,
+  "best_metric": 1.3475680351257324,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.010664960273022984,
   "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": 116.075,
       "eval_steps_per_second": 14.509,
       "step": 25
+    },
+    {
+      "epoch": 0.0055457793419719514,
+      "grad_norm": 0.3569680452346802,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.497,
+      "step": 26
+    },
+    {
+      "epoch": 0.005759078547432411,
+      "grad_norm": 0.3587609827518463,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.4024,
+      "step": 27
+    },
+    {
+      "epoch": 0.0059723777528928705,
+      "grad_norm": 0.3989461362361908,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.5467,
+      "step": 28
+    },
+    {
+      "epoch": 0.00618567695835333,
+      "grad_norm": 0.3418835699558258,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.4541,
+      "step": 29
+    },
+    {
+      "epoch": 0.00639897616381379,
+      "grad_norm": 0.3659650981426239,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.5464,
+      "step": 30
+    },
+    {
+      "epoch": 0.006612275369274249,
+      "grad_norm": 0.4786025285720825,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.6205,
+      "step": 31
+    },
+    {
+      "epoch": 0.0068255745747347095,
+      "grad_norm": 0.4017328917980194,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.3343,
+      "step": 32
+    },
+    {
+      "epoch": 0.007038873780195169,
+      "grad_norm": 0.5265333652496338,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.8905,
+      "step": 33
+    },
+    {
+      "epoch": 0.007252172985655629,
+      "grad_norm": 0.3608676791191101,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.3683,
+      "step": 34
+    },
+    {
+      "epoch": 0.007465472191116088,
+      "grad_norm": 0.4353957772254944,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.6015,
+      "step": 35
+    },
+    {
+      "epoch": 0.007678771396576548,
+      "grad_norm": 0.3937820792198181,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.2824,
+      "step": 36
+    },
+    {
+      "epoch": 0.007892070602037008,
+      "grad_norm": 0.39776891469955444,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.9932,
+      "step": 37
+    },
+    {
+      "epoch": 0.008105369807497468,
+      "grad_norm": 0.42103254795074463,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.0356,
+      "step": 38
+    },
+    {
+      "epoch": 0.008318669012957927,
+      "grad_norm": 0.4416367709636688,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.1976,
+      "step": 39
+    },
+    {
+      "epoch": 0.008531968218418387,
+      "grad_norm": 0.35231977701187134,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.0434,
+      "step": 40
+    },
+    {
+      "epoch": 0.008745267423878846,
+      "grad_norm": 0.41201403737068176,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.9915,
+      "step": 41
+    },
+    {
+      "epoch": 0.008958566629339306,
+      "grad_norm": 0.4073962867259979,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.1811,
+      "step": 42
+    },
+    {
+      "epoch": 0.009171865834799765,
+      "grad_norm": 0.365858256816864,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.8872,
+      "step": 43
+    },
+    {
+      "epoch": 0.009385165040260225,
+      "grad_norm": 0.36499106884002686,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.1054,
+      "step": 44
+    },
+    {
+      "epoch": 0.009598464245720684,
+      "grad_norm": 0.33799082040786743,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.1389,
+      "step": 45
+    },
+    {
+      "epoch": 0.009811763451181144,
+      "grad_norm": 0.3514730632305145,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.1157,
+      "step": 46
+    },
+    {
+      "epoch": 0.010025062656641603,
+      "grad_norm": 0.3646899163722992,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.088,
+      "step": 47
+    },
+    {
+      "epoch": 0.010238361862102063,
+      "grad_norm": 0.38466212153434753,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.08,
+      "step": 48
+    },
+    {
+      "epoch": 0.010451661067562523,
+      "grad_norm": 0.4186328053474426,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.1221,
+      "step": 49
+    },
+    {
+      "epoch": 0.010664960273022984,
+      "grad_norm": 0.5278308987617493,
+      "learning_rate": 0.0,
+      "loss": 0.9967,
+      "step": 50
+    },
+    {
+      "epoch": 0.010664960273022984,
+      "eval_loss": 1.3475680351257324,
+      "eval_runtime": 67.9728,
+      "eval_samples_per_second": 116.164,
+      "eval_steps_per_second": 14.521,
+      "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": 618044011315200.0,
+  "total_flos": 1087757459914752.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null