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:fcfdd85f653319038f128c7ff241c38127e8d7ac26f881d678a9a88622e067b1
+oid sha256:281c49daa01c6e669e56501706811091de663f98b62454b1dc7522d7344b0227
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efe210c4173606903b195784de9d8f69055b82be5b028a1dc0d089f02cda7a4a
+oid sha256:70ff40579434c44f87c5018d14d4f889c6ba6fa752828ef988e0732a02468f55
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05db6b3703f656e0db66b032e0185fd50565c34feed18f347061030838adc6f0
+oid sha256:e5f6c911a1fdf7efae2b2eb6adeeb0e47e33ceec08ad7b3629d90824192f3289
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5074851512908936,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0014855254117690751,
+  "best_metric": 1.478926658630371,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0022282881176536127,
   "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": 7.795,
       "eval_steps_per_second": 3.898,
       "step": 20
+    },
+    {
+      "epoch": 0.0015598016823575288,
+      "grad_norm": 8.454328536987305,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 6.3236,
+      "step": 21
+    },
+    {
+      "epoch": 0.00178263049412289,
+      "grad_norm": 6.996322154998779,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 6.3287,
+      "step": 24
+    },
+    {
+      "epoch": 0.001856906764711344,
+      "eval_loss": 1.4847581386566162,
+      "eval_runtime": 728.1195,
+      "eval_samples_per_second": 7.786,
+      "eval_steps_per_second": 3.894,
+      "step": 25
+    },
+    {
+      "epoch": 0.002005459305888251,
+      "grad_norm": 9.126077651977539,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 6.1673,
+      "step": 27
+    },
+    {
+      "epoch": 0.0022282881176536127,
+      "grad_norm": 8.678947448730469,
+      "learning_rate": 0.0,
+      "loss": 5.3701,
+      "step": 30
+    },
+    {
+      "epoch": 0.0022282881176536127,
+      "eval_loss": 1.478926658630371,
+      "eval_runtime": 726.7085,
+      "eval_samples_per_second": 7.801,
+      "eval_steps_per_second": 3.901,
+      "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": 7382868191870976.0,
+  "total_flos": 1.1074302287806464e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null