Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0706a868954d7a29426b3241a47ca1de0103fa7e96f59ad733da10d8c97e29be
+oid sha256:882bb77443624a31bc80e7fb03f162346810c77b0eb9dc6fbb71010dda301a9f
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d6a727d253c55d1f0fd2de265963667b905cb81e8e4efbba880722890c6be78
+oid sha256:495954ec494ed7945c9bc76faee800607f6970a0f53c522dc796dc5c44ea3950
 size 203713238

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39850a061b78f9ac2cbb942062480bf6a458ffde15f86fc9d96e78816bdcff5d
+oid sha256:41f4ff8d311715382874f19d1bf368a79012e9dfc976240b4d7fce5c0655c09d
 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": 1.344356894493103,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0030677199171715622,
+  "best_metric": 1.3131598234176636,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.004601579875757343,
   "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": 7.169,
       "eval_steps_per_second": 1.793,
       "step": 20
+    },
+    {
+      "epoch": 0.0032211059130301404,
+      "grad_norm": 0.38638386130332947,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.4712,
+      "step": 21
+    },
+    {
+      "epoch": 0.0036812639006058748,
+      "grad_norm": 0.37634310126304626,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.3726,
+      "step": 24
+    },
+    {
+      "epoch": 0.003834649896464453,
+      "eval_loss": 1.3181897401809692,
+      "eval_runtime": 764.1563,
+      "eval_samples_per_second": 7.184,
+      "eval_steps_per_second": 1.797,
+      "step": 25
+    },
+    {
+      "epoch": 0.004141421888181609,
+      "grad_norm": 0.4122856855392456,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.3468,
+      "step": 27
+    },
+    {
+      "epoch": 0.004601579875757343,
+      "grad_norm": 0.3992947041988373,
+      "learning_rate": 0.0,
+      "loss": 1.3247,
+      "step": 30
+    },
+    {
+      "epoch": 0.004601579875757343,
+      "eval_loss": 1.3131598234176636,
+      "eval_runtime": 762.4523,
+      "eval_samples_per_second": 7.2,
+      "eval_steps_per_second": 1.801,
+      "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": 6667701316485120.0,
+  "total_flos": 9960393324625920.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null