Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:926a18649a7331b056e65017a04dd5ff0c0b7543a26034787a77a9e85d788be4
+oid sha256:bd6a91dde1f16050d5709de9b869f02e4ccdd6c86a314771d7bba99a91ad2232
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:462d1301202a0c307eac68f301f443d6c5d6d8b9f7bff8941f7acec2bbcd270d
+oid sha256:ccbe7f82eaf9c77b1b6aafff47d237dfaeb04a9dcb944a6fa4e677b1d99d790b
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07bbac5e8a5858343709d6b6733abe1b886e9963e7bd7875a565f04038d32852
+oid sha256:1bcfa19231d15070493ee31c334b85fdd1d4dc308828e4bb1e8f323a2d24cb81
 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": 1.0318337678909302,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.01100715465052284,
+  "best_metric": 0.8469862937927246,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.02201430930104568,
   "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": 5.587,
       "eval_steps_per_second": 2.801,
       "step": 10
+    },
+    {
+      "epoch": 0.013208585580627407,
+      "grad_norm": 0.7510042786598206,
+      "learning_rate": 0.000163742398974869,
+      "loss": 0.9583,
+      "step": 12
+    },
+    {
+      "epoch": 0.01651073197578426,
+      "grad_norm": 0.24181640148162842,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.7886,
+      "step": 15
+    },
+    {
+      "epoch": 0.01651073197578426,
+      "eval_loss": 0.9011569619178772,
+      "eval_runtime": 68.6475,
+      "eval_samples_per_second": 5.579,
+      "eval_steps_per_second": 2.797,
+      "step": 15
+    },
+    {
+      "epoch": 0.01981287837094111,
+      "grad_norm": 0.5233681201934814,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 0.8176,
+      "step": 18
+    },
+    {
+      "epoch": 0.02201430930104568,
+      "eval_loss": 0.8469862937927246,
+      "eval_runtime": 68.6503,
+      "eval_samples_per_second": 5.579,
+      "eval_steps_per_second": 2.797,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3430655559991296.0,
+  "total_flos": 6779628844744704.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null