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:b6338bb0f62bf9308723dea6cde721437ea8f6a4b2ad4cb67c84234361eaca4f
+oid sha256:d01504d58a4c54c6f4fdcec44a83dee7b924459f4969afd2169a7d404da5a1ee
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b9fcadaff7138d9b455fb48d1a62da86b530c1696dfb76318077e2775ac98ca
+oid sha256:88d5756fc9bdefc9edc1dc71a61855e2348d49783067c2ab51c4f7350c41f486
 size 68874

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e32f10154a5b77b0c925a53d1da7325b4357fe6698098b50190974355eeaec1b
+oid sha256:71902d51fda8e7c9a8cae64df26f2f6029253bd41570883ef9cf6a7a121be7e6
 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": 11.93227481842041,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.017057569296375266,
+  "best_metric": 11.932273864746094,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0255863539445629,
   "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": 77.818,
       "eval_steps_per_second": 19.454,
       "step": 20
+    },
+    {
+      "epoch": 0.01791044776119403,
+      "grad_norm": 0.016151631250977516,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 11.9323,
+      "step": 21
+    },
+    {
+      "epoch": 0.02046908315565032,
+      "grad_norm": 0.014312547631561756,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 11.9322,
+      "step": 24
+    },
+    {
+      "epoch": 0.021321961620469083,
+      "eval_loss": 11.932249069213867,
+      "eval_runtime": 12.4207,
+      "eval_samples_per_second": 79.545,
+      "eval_steps_per_second": 19.886,
+      "step": 25
+    },
+    {
+      "epoch": 0.02302771855010661,
+      "grad_norm": 0.014438067562878132,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 11.9332,
+      "step": 27
+    },
+    {
+      "epoch": 0.0255863539445629,
+      "grad_norm": 0.013778905384242535,
+      "learning_rate": 0.0,
+      "loss": 11.9314,
+      "step": 30
+    },
+    {
+      "epoch": 0.0255863539445629,
+      "eval_loss": 11.932273864746094,
+      "eval_runtime": 12.6251,
+      "eval_samples_per_second": 78.257,
+      "eval_steps_per_second": 19.564,
+      "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": 15176761344.0,
+  "total_flos": 22671458304.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null