Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58dd2dd7a31cf38cc48378c11b297b700772d2ae0503ffe823b3a73bd96cb7d2
+oid sha256:6765f4c00aa8deaacc591bfd1b2b4d53dae9e5101e54d5a4efe8753e2750c3c0
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1efb42f87131f42ece2fbb83f6c80814849fc58d36cc62e09e8414a9d263442a
+oid sha256:88c4e5fb9fdc0c4aebbf2bc7e44bb056d7b4d50aa85e6d2cd9ab0bbe891aca9f
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dace3653fe0e7343aeff78961da71266f92cc83f6bc7a8561cfa91c303e54dba
+oid sha256:5c4b2018b52c1fc9332cfebf7c5c719d3cfb18d97200dec86a051dd64d3a14d3
 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": 10.377450942993164,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.03508771929824561,
+  "best_metric": 10.377095222473145,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.05263157894736842,
   "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": 292.462,
       "eval_steps_per_second": 146.231,
       "step": 20
+    },
+    {
+      "epoch": 0.03684210526315789,
+      "grad_norm": 0.05487305298447609,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 10.3788,
+      "step": 21
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "grad_norm": 0.03941920027136803,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 10.3797,
+      "step": 24
+    },
+    {
+      "epoch": 0.043859649122807015,
+      "eval_loss": 10.377154350280762,
+      "eval_runtime": 0.8114,
+      "eval_samples_per_second": 295.802,
+      "eval_steps_per_second": 147.901,
+      "step": 25
+    },
+    {
+      "epoch": 0.04736842105263158,
+      "grad_norm": 0.0346779003739357,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 10.3777,
+      "step": 27
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 0.034802936017513275,
+      "learning_rate": 0.0,
+      "loss": 10.3793,
+      "step": 30
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "eval_loss": 10.377095222473145,
+      "eval_runtime": 1.0472,
+      "eval_samples_per_second": 229.187,
+      "eval_steps_per_second": 114.593,
+      "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": 542637883392.0,
+  "total_flos": 823763533824.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null