Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58eba2295aa59eaaaf1e8cab5a76df021e9d147fb75e3514f155e34a786c5a25
+oid sha256:a1002fb196860165d76b91d1bf5bc49eea509cace1f4841595d9b56518b6c8ec
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d294b7add7659ee47712ba99a93c40c294a0b70e00fc83a8109e2b8a913c2bc4
+oid sha256:44cdd576e547d8c700fc5dc026198c948dce18b460fc53109567c5d7f5c50507
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ef478262fdad1eef4d24ea689c7527a913041936810e0ef87a887ec073842b3
+oid sha256:e46a546b518d0d00b9d5c56e7acabd663fa01c61eb6fd1b38d3334ff91b70b1d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 10.375664710998535,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.02274019329164298,
+  "best_metric": 10.375311851501465,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.03411028993746447,
   "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": 163.323,
       "eval_steps_per_second": 40.996,
       "step": 20
+    },
+    {
+      "epoch": 0.023877202956225127,
+      "grad_norm": 0.049262672662734985,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 10.3759,
+      "step": 21
+    },
+    {
+      "epoch": 0.027288231949971573,
+      "grad_norm": 0.04128611460328102,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 10.3746,
+      "step": 24
+    },
+    {
+      "epoch": 0.028425241614553724,
+      "eval_loss": 10.375368118286133,
+      "eval_runtime": 4.6223,
+      "eval_samples_per_second": 160.311,
+      "eval_steps_per_second": 40.24,
+      "step": 25
+    },
+    {
+      "epoch": 0.030699260943718023,
+      "grad_norm": 0.04697146639227867,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 10.375,
+      "step": 27
+    },
+    {
+      "epoch": 0.03411028993746447,
+      "grad_norm": 0.050780996680259705,
+      "learning_rate": 0.0,
+      "loss": 10.3761,
+      "step": 30
+    },
+    {
+      "epoch": 0.03411028993746447,
+      "eval_loss": 10.375311851501465,
+      "eval_runtime": 4.5568,
+      "eval_samples_per_second": 162.614,
+      "eval_steps_per_second": 40.818,
+      "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": 1059124543488.0,
+  "total_flos": 1582149009408.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null