Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f0c9ebc7a9955a8a59569fb1cde4c8fc78b0fcaa55376d733060759616cfbf1
+oid sha256:d63d878b28ec23898586c712cc5ebf783db454992a1b1b8b89bdba567bb98df5
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac237a465b6cc3ba27429decdb199d42febc47a26afd3c247565fa994810882b
+oid sha256:dfefadc329ddaa3e0c4c7bd49da6532ad4cf45e5c9b0fb04645a6ee2d8c0340b
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72f325d3bbc0eca2000d1479ce5af80d912e3644a10c0325e24322608d0c32cb
+oid sha256:b9ddd5509226bc63d0a4eee1a570d81e205525aefc25e7af1fa9738062c09bbf
 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": 3.9761948585510254,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.003361627027481301,
+  "best_metric": 3.9313950538635254,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.005042440541221951,
   "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": 43.238,
       "eval_steps_per_second": 21.628,
       "step": 20
+    },
+    {
+      "epoch": 0.003529708378855366,
+      "grad_norm": 0.8214964270591736,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 3.8518,
+      "step": 21
+    },
+    {
+      "epoch": 0.004033952432977561,
+      "grad_norm": 0.7705588936805725,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 3.9388,
+      "step": 24
+    },
+    {
+      "epoch": 0.004202033784351626,
+      "eval_loss": 3.9394900798797607,
+      "eval_runtime": 58.05,
+      "eval_samples_per_second": 43.152,
+      "eval_steps_per_second": 21.585,
+      "step": 25
+    },
+    {
+      "epoch": 0.004538196487099756,
+      "grad_norm": 0.7781285047531128,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 4.0402,
+      "step": 27
+    },
+    {
+      "epoch": 0.005042440541221951,
+      "grad_norm": 1.2990456819534302,
+      "learning_rate": 0.0,
+      "loss": 4.078,
+      "step": 30
+    },
+    {
+      "epoch": 0.005042440541221951,
+      "eval_loss": 3.9313950538635254,
+      "eval_runtime": 57.9877,
+      "eval_samples_per_second": 43.199,
+      "eval_steps_per_second": 21.608,
+      "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": 1029368772034560.0,
+  "total_flos": 1544053158051840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null