Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57904bc4bae2c4738a4e02ccd7f63e2fc267113d1758dffde8f3110f7fe89e8a
+oid sha256:2af915294105af09d2611ac8be194c400c730054111130675aff6294eacd4474
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bed931fd2330bcf5cf25d0afd59e4f684f82426214ca877e2c266c940db58737
+oid sha256:c67c9c8ffe31e4e00d0f1dde531c6451c45a669e865cdf04d2e0b81ac13c6da3
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b5a3b2d7e749c8c173823820628146ae941b76fcf39dff153f36eb58eb3a16f
+oid sha256:b6050baa6f0450a55f55d1eb7448f6fe645bd37c9b5787f14dd55bb747cbc86f
 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": 2.3949928283691406,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.009900990099009901,
+  "best_metric": 2.3391101360321045,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.01485148514851485,
   "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": 41.665,
       "eval_steps_per_second": 20.857,
       "step": 20
+    },
+    {
+      "epoch": 0.010396039603960397,
+      "grad_norm": 0.8455501794815063,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.4478,
+      "step": 21
+    },
+    {
+      "epoch": 0.011881188118811881,
+      "grad_norm": 0.7899941205978394,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.4047,
+      "step": 24
+    },
+    {
+      "epoch": 0.012376237623762377,
+      "eval_loss": 2.348778486251831,
+      "eval_runtime": 20.4392,
+      "eval_samples_per_second": 41.636,
+      "eval_steps_per_second": 20.842,
+      "step": 25
+    },
+    {
+      "epoch": 0.013366336633663366,
+      "grad_norm": 0.7957627773284912,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.3724,
+      "step": 27
+    },
+    {
+      "epoch": 0.01485148514851485,
+      "grad_norm": 0.6960504651069641,
+      "learning_rate": 0.0,
+      "loss": 2.3079,
+      "step": 30
+    },
+    {
+      "epoch": 0.01485148514851485,
+      "eval_loss": 2.3391101360321045,
+      "eval_runtime": 20.4205,
+      "eval_samples_per_second": 41.674,
+      "eval_steps_per_second": 20.861,
+      "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": 1067970100985856.0,
+  "total_flos": 1608388706304000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null