Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1acf3939fb1f5be84724451813a01351f223db206056f56952acc6f360f2d077
+oid sha256:0be9b921e9c80b479bf7e84ea6e5618f8e72dc497718bd6cd120088a99f60081
 size 295488936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35e1d97602ad4c7c6ba48772105b06b3151092fdc9f0952527e5e13d05d94030
+oid sha256:728f6947bde3d2b21da8d22a6a0df66fe750eacd5428ef9543c3366dd8c19554
 size 150486964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a459e56ec53e1f25bbfe69bd5df7458031b3ee232ec90887c6771d8a751f7fa
+oid sha256:f57a3e51db2b3dc4b89fad6f11a4372cb098c15352d8e447f013ababfa41a537
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6299423575401306,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.2829854969932791,
+  "best_metric": 0.6227372288703918,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.5659709939865581,
   "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": 16.996,
       "eval_steps_per_second": 4.256,
       "step": 25
+    },
+    {
+      "epoch": 0.29430491687301025,
+      "grad_norm": 0.17492617666721344,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.5798,
+      "step": 26
+    },
+    {
+      "epoch": 0.3056243367527414,
+      "grad_norm": 0.1557742953300476,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 0.5768,
+      "step": 27
+    },
+    {
+      "epoch": 0.3169437566324726,
+      "grad_norm": 0.1721125692129135,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 0.6407,
+      "step": 28
+    },
+    {
+      "epoch": 0.32826317651220377,
+      "grad_norm": 0.1632377654314041,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 0.5845,
+      "step": 29
+    },
+    {
+      "epoch": 0.3395825963919349,
+      "grad_norm": 0.16640470921993256,
+      "learning_rate": 5e-05,
+      "loss": 0.6397,
+      "step": 30
+    },
+    {
+      "epoch": 0.35090201627166606,
+      "grad_norm": 0.16340287029743195,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 0.5962,
+      "step": 31
+    },
+    {
+      "epoch": 0.36222143615139724,
+      "grad_norm": 0.17924903333187103,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.6759,
+      "step": 32
+    },
+    {
+      "epoch": 0.3735408560311284,
+      "grad_norm": 0.157784104347229,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 0.5472,
+      "step": 33
+    },
+    {
+      "epoch": 0.3848602759108596,
+      "grad_norm": 0.15475068986415863,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.6402,
+      "step": 34
+    },
+    {
+      "epoch": 0.39617969579059076,
+      "grad_norm": 0.16885007917881012,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.6343,
+      "step": 35
+    },
+    {
+      "epoch": 0.4074991156703219,
+      "grad_norm": 0.15856143832206726,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.6374,
+      "step": 36
+    },
+    {
+      "epoch": 0.41881853555005305,
+      "grad_norm": 0.16886891424655914,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 0.6216,
+      "step": 37
+    },
+    {
+      "epoch": 0.4301379554297842,
+      "grad_norm": 0.1408165693283081,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.5616,
+      "step": 38
+    },
+    {
+      "epoch": 0.4414573753095154,
+      "grad_norm": 0.14798948168754578,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 0.5386,
+      "step": 39
+    },
+    {
+      "epoch": 0.4527767951892466,
+      "grad_norm": 0.1555565744638443,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.6052,
+      "step": 40
+    },
+    {
+      "epoch": 0.4640962150689777,
+      "grad_norm": 0.1494063436985016,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 0.563,
+      "step": 41
+    },
+    {
+      "epoch": 0.47541563494870887,
+      "grad_norm": 0.1517692655324936,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.5936,
+      "step": 42
+    },
+    {
+      "epoch": 0.48673505482844004,
+      "grad_norm": 0.15942981839179993,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 0.6579,
+      "step": 43
+    },
+    {
+      "epoch": 0.4980544747081712,
+      "grad_norm": 0.1566431224346161,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.5599,
+      "step": 44
+    },
+    {
+      "epoch": 0.5093738945879024,
+      "grad_norm": 0.16016413271427155,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5862,
+      "step": 45
+    },
+    {
+      "epoch": 0.5206933144676336,
+      "grad_norm": 0.1653357744216919,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.663,
+      "step": 46
+    },
+    {
+      "epoch": 0.5320127343473647,
+      "grad_norm": 0.16749340295791626,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 0.6119,
+      "step": 47
+    },
+    {
+      "epoch": 0.5433321542270959,
+      "grad_norm": 0.1556142419576645,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.5916,
+      "step": 48
+    },
+    {
+      "epoch": 0.554651574106827,
+      "grad_norm": 0.14963436126708984,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 0.597,
+      "step": 49
+    },
+    {
+      "epoch": 0.5659709939865581,
+      "grad_norm": 0.1515038013458252,
+      "learning_rate": 0.0,
+      "loss": 0.5536,
+      "step": 50
+    },
+    {
+      "epoch": 0.5659709939865581,
+      "eval_loss": 0.6227372288703918,
+      "eval_runtime": 34.964,
+      "eval_samples_per_second": 17.017,
+      "eval_steps_per_second": 4.262,
+      "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": 5.463305468510208e+16,
+  "total_flos": 1.091980731875328e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null