Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:362e2a98fe0857e2a72e2ae7f30f159a07659a0e80a74d95c070f1fc10ca19ae
+oid sha256:3a10e11e0f210331b251c0572816ea087e7ac7d3473df36e077db91e68d245f7
 size 25192592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8139771901c4ef4dcef238de1d46301c6a8a3c3aaceadd8647988b3f89622ab
+oid sha256:0d2e1c3cab2ae40cb82d8f2da3a0cb38effed7db497ceca14409b5d4029461af
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a80a3e579a3578339ad82c7db2683bb137027e6bff46ee48b2584907b433862
+oid sha256:c71b23074cf3d2127dae3b4b82ebe253426ae74641bdd31703102620152bfe99
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3011465072631836,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.00909194226616661,
+  "best_metric": 1.1472958326339722,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.013637913399249914,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 77.243,
       "eval_steps_per_second": 38.663,
       "step": 20
+    },
+    {
+      "epoch": 0.00954653937947494,
+      "grad_norm": 98.85890197753906,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 5.2552,
+      "step": 21
+    },
+    {
+      "epoch": 0.010910330719399931,
+      "grad_norm": 139.17727661132812,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 5.2514,
+      "step": 24
+    },
+    {
+      "epoch": 0.011364927832708262,
+      "eval_loss": 1.1740113496780396,
+      "eval_runtime": 12.1359,
+      "eval_samples_per_second": 76.385,
+      "eval_steps_per_second": 38.234,
+      "step": 25
+    },
+    {
+      "epoch": 0.012274122059324924,
+      "grad_norm": 111.79165649414062,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 4.7038,
+      "step": 27
+    },
+    {
+      "epoch": 0.013637913399249914,
+      "grad_norm": 103.4673080444336,
+      "learning_rate": 0.0,
+      "loss": 5.0908,
+      "step": 30
+    },
+    {
+      "epoch": 0.013637913399249914,
+      "eval_loss": 1.1472958326339722,
+      "eval_runtime": 12.0796,
+      "eval_samples_per_second": 76.741,
+      "eval_steps_per_second": 38.412,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 354006639575040.0,
+  "total_flos": 531009959362560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null