Training in progress, step 70, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a296213106b39423eb0ac1fe490129891fc3f1d7bdb00e45d0ac1e06d11ebc20
+oid sha256:558f5c765d834c73a0a74252b42c4960a495ceae1e7ee111ebd7638beb8f0b9a
 size 194563400

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:484f9e05b53b9fe5704f87120690fd54cdfd358b3ba30ecefafafaa2847108bd
+oid sha256:dd601d76e084da3463a0c22255e254a8f53d1a216bf2fdb3571858ae7f941efc
 size 99235764

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3fc42d49e32e12c6f7f951e821ec52062e026214ebb0bbcd1194c3b74d7856b
+oid sha256:afb6677a99266b3ab610cba32f712f9ef76ee588ccc7083679beb11bc0553e3e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54b996514a941dd419a3f7869454171b960cb51cf1b91d9b10dbdcf1b1e50a10
+oid sha256:1074437c4c638775a20a86de2e689d1a14d0ff4e4137df2ddeb45e94a776caef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8120850920677185,
-  "best_model_checkpoint": "miner_id_24/checkpoint-60",
-  "epoch": 0.1431980906921241,
+  "best_metric": 0.8046614527702332,
+  "best_model_checkpoint": "miner_id_24/checkpoint-70",
+  "epoch": 0.16706443914081145,
   "eval_steps": 5,
-  "global_step": 60,
+  "global_step": 70,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -531,6 +531,92 @@
       "eval_samples_per_second": 3.366,
       "eval_steps_per_second": 1.692,
       "step": 60
+    },
+    {
+      "epoch": 0.14558472553699284,
+      "grad_norm": 0.4957926273345947,
+      "learning_rate": 0.00019470159657616215,
+      "loss": 0.5649,
+      "step": 61
+    },
+    {
+      "epoch": 0.14797136038186157,
+      "grad_norm": 0.8247906565666199,
+      "learning_rate": 0.00019449372563954293,
+      "loss": 1.1628,
+      "step": 62
+    },
+    {
+      "epoch": 0.15035799522673032,
+      "grad_norm": 0.502251148223877,
+      "learning_rate": 0.0001942819704359693,
+      "loss": 0.7712,
+      "step": 63
+    },
+    {
+      "epoch": 0.15274463007159905,
+      "grad_norm": 0.3308824300765991,
+      "learning_rate": 0.00019406633966986828,
+      "loss": 0.5516,
+      "step": 64
+    },
+    {
+      "epoch": 0.15513126491646778,
+      "grad_norm": 0.5597787499427795,
+      "learning_rate": 0.00019384684220497605,
+      "loss": 0.556,
+      "step": 65
+    },
+    {
+      "epoch": 0.15513126491646778,
+      "eval_loss": 0.8096857666969299,
+      "eval_runtime": 52.5376,
+      "eval_samples_per_second": 3.369,
+      "eval_steps_per_second": 1.694,
+      "step": 65
+    },
+    {
+      "epoch": 0.1575178997613365,
+      "grad_norm": 0.6705149412155151,
+      "learning_rate": 0.00019362348706397373,
+      "loss": 1.0559,
+      "step": 66
+    },
+    {
+      "epoch": 0.15990453460620524,
+      "grad_norm": 0.5521374940872192,
+      "learning_rate": 0.00019339628342811632,
+      "loss": 0.7597,
+      "step": 67
+    },
+    {
+      "epoch": 0.162291169451074,
+      "grad_norm": 0.5938752293586731,
+      "learning_rate": 0.0001931652406368554,
+      "loss": 0.8473,
+      "step": 68
+    },
+    {
+      "epoch": 0.16467780429594273,
+      "grad_norm": 0.5228351950645447,
+      "learning_rate": 0.0001929303681874552,
+      "loss": 0.7279,
+      "step": 69
+    },
+    {
+      "epoch": 0.16706443914081145,
+      "grad_norm": 0.6063805818557739,
+      "learning_rate": 0.0001926916757346022,
+      "loss": 1.2009,
+      "step": 70
+    },
+    {
+      "epoch": 0.16706443914081145,
+      "eval_loss": 0.8046614527702332,
+      "eval_runtime": 52.6343,
+      "eval_samples_per_second": 3.363,
+      "eval_steps_per_second": 1.691,
+      "step": 70
     }
   ],
   "logging_steps": 1,
@@ -559,7 +645,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.382493306683392e+16,
+  "total_flos": 3.946242191130624e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null