Training in progress, step 2000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8db8e1780aa1f5379b069d27cd706489731330715d3ec022290f4098047f2633
+oid sha256:191771906b693f26eaaf37eb809bddc257b2bca60bf5a3fe6c35bc8614988bc2
 size 295488936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca46b57c8f5af494bb292db6f734ba81d2e9c1f6bb712bea760a8daa0098df9e
+oid sha256:13efac562a97f93c7a5cd1f9576811bbf8c2099e9f3172e965aefb8f5937f023
 size 591208618

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:581539d10de68a5f8609571cd5e2933cbb0a46f9572ab1cf6bfe8998bffe8e72
+oid sha256:1880de2339eb48528ded673276ade6154d35fafd44969780a2aa8c8707f09e4a
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ae5aa8c222d60d4c2ef4c3c0a76f26aef5832f53f30f2bf99243a3cbc4528ae
+oid sha256:e41eb445440bedef5fa52127a8517f1a8bdc2715f21a9c0725cf1b30d35f4d7f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.19417718052864075,
-  "best_model_checkpoint": "miner_id_24/checkpoint-1500",
-  "epoch": 1.3280230113950657,
+  "best_metric": 0.18882454931735992,
+  "best_model_checkpoint": "miner_id_24/checkpoint-2000",
+  "epoch": 1.770549839584025,
   "eval_steps": 500,
-  "global_step": 1500,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -249,6 +249,84 @@
       "eval_samples_per_second": 24.181,
       "eval_steps_per_second": 6.048,
       "step": 1500
+    },
+    {
+      "epoch": 1.3722756942139618,
+      "grad_norm": 0.3608824908733368,
+      "learning_rate": 2.8409679602638354e-05,
+      "loss": 0.1521,
+      "step": 1550
+    },
+    {
+      "epoch": 1.4165283770328576,
+      "grad_norm": 0.3812834918498993,
+      "learning_rate": 2.2667395239887702e-05,
+      "loss": 0.1422,
+      "step": 1600
+    },
+    {
+      "epoch": 1.4607810598517534,
+      "grad_norm": 0.37747815251350403,
+      "learning_rate": 1.750460358677818e-05,
+      "loss": 0.1497,
+      "step": 1650
+    },
+    {
+      "epoch": 1.5050337426706495,
+      "grad_norm": 0.3156684339046478,
+      "learning_rate": 1.2956571745302437e-05,
+      "loss": 0.1518,
+      "step": 1700
+    },
+    {
+      "epoch": 1.5492864254895453,
+      "grad_norm": 0.30725404620170593,
+      "learning_rate": 9.054367384581317e-06,
+      "loss": 0.1473,
+      "step": 1750
+    },
+    {
+      "epoch": 1.5935391083084411,
+      "grad_norm": 0.48353010416030884,
+      "learning_rate": 5.824646517181777e-06,
+      "loss": 0.1464,
+      "step": 1800
+    },
+    {
+      "epoch": 1.637791791127337,
+      "grad_norm": 0.30902764201164246,
+      "learning_rate": 3.2894714115219847e-06,
+      "loss": 0.1512,
+      "step": 1850
+    },
+    {
+      "epoch": 1.682044473946233,
+      "grad_norm": 0.32157230377197266,
+      "learning_rate": 1.4661598842073503e-06,
+      "loss": 0.1458,
+      "step": 1900
+    },
+    {
+      "epoch": 1.7262971567651288,
+      "grad_norm": 0.37534651160240173,
+      "learning_rate": 3.6716700178299143e-07,
+      "loss": 0.1484,
+      "step": 1950
+    },
+    {
+      "epoch": 1.770549839584025,
+      "grad_norm": 0.3747284710407257,
+      "learning_rate": 0.0,
+      "loss": 0.1498,
+      "step": 2000
+    },
+    {
+      "epoch": 1.770549839584025,
+      "eval_loss": 0.18882454931735992,
+      "eval_runtime": 81.211,
+      "eval_samples_per_second": 23.433,
+      "eval_steps_per_second": 5.861,
+      "step": 2000
     }
   ],
   "logging_steps": 50,
@@ -272,12 +350,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.0821709602816e+17,
+  "total_flos": 5.4428946137088e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null