Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a537a03114abb57ed76ef38bd1ea3121bf621ddc4170e7b9b5566ca857eafed4
+oid sha256:8e7b8eb478dee398996e46b5ca61429b5e0276dd3e558ebb59905b7d7d2bbbc7
 size 30322120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31a5451386280cab644fd7e441a00d7a40e52fd15e520eac6ccfc547622e39da
+oid sha256:b2235febfe01e8fa55790f6801f745956fd4d8341709470b0c0f88802ad23dff
 size 60837186

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:914b0e915d627347d5ae389ee59720105fb3aee3c113997add51f7119ff0d2fe
+oid sha256:df671da0647ad751ae2dccc6766dc5c327b7edaf01aa92e7029489aace41976b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
+oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.118781328201294,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.07339449541284404,
+  "best_metric": 2.697143793106079,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.14678899082568808,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 42.665,
       "eval_steps_per_second": 10.759,
       "step": 10
+    },
+    {
+      "epoch": 0.08807339449541285,
+      "grad_norm": 1.8563435077667236,
+      "learning_rate": 0.000163742398974869,
+      "loss": 2.9979,
+      "step": 12
+    },
+    {
+      "epoch": 0.11009174311926606,
+      "grad_norm": 1.7265347242355347,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.8441,
+      "step": 15
+    },
+    {
+      "epoch": 0.11009174311926606,
+      "eval_loss": 2.881464719772339,
+      "eval_runtime": 2.7172,
+      "eval_samples_per_second": 42.323,
+      "eval_steps_per_second": 10.673,
+      "step": 15
+    },
+    {
+      "epoch": 0.13211009174311927,
+      "grad_norm": 1.7133402824401855,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 2.9017,
+      "step": 18
+    },
+    {
+      "epoch": 0.14678899082568808,
+      "eval_loss": 2.697143793106079,
+      "eval_runtime": 2.7176,
+      "eval_samples_per_second": 42.316,
+      "eval_steps_per_second": 10.671,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 318381118980096.0,
+  "total_flos": 628996844814336.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null