Training in progress, step 19, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15e1d6282255c53301b22902d7ebd29fa852b504682c366dc65e6f753b31b644
+oid sha256:2e2277b9b528c1c9f8bd7e622cad6c80092ce54f6dfbe60517ff5ae088d71f18
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de67c3013ecdd00f67fdd1d0bcdea5c818ac2a8669f483cc9d93ff022be16887
+oid sha256:3516beb162147f9c0071765d8d02b0d388f839b860ca75736dc4ff03a8dff099
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61630a9df826f43c43e9d9f3f658b33939478e91788026e7879f5a1c25f3bc5a
+oid sha256:c29b7e2b68557abec6d537788c826fc285fa31805cf008a22adaa84cb4a0d16c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:2d53e3efb96f3d3e8a6297fb701bdadfea260fdcffdcd69ab736f197d82e8827
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7437593340873718,
   "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.5333333333333333,
+  "epoch": 1.0266666666666666,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 19,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,77 @@
       "eval_samples_per_second": 7.653,
       "eval_steps_per_second": 3.827,
       "step": 10
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 4.308557033538818,
+      "learning_rate": 0.00019396926207859084,
+      "loss": 1.0522,
+      "step": 11
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 4.9355010986328125,
+      "learning_rate": 0.0001766044443118978,
+      "loss": 0.9547,
+      "step": 12
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 5.842991352081299,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.0311,
+      "step": 13
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 4.299498081207275,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 0.6983,
+      "step": 14
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 6.725227355957031,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 0.7981,
+      "step": 15
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 0.43270689249038696,
+      "eval_runtime": 1.0468,
+      "eval_samples_per_second": 7.643,
+      "eval_steps_per_second": 3.821,
+      "step": 15
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 4.609326362609863,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.5653,
+      "step": 16
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 4.444565296173096,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 0.5661,
+      "step": 17
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 5.373607635498047,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 0.6943,
+      "step": 18
+    },
+    {
+      "epoch": 1.0266666666666666,
+      "grad_norm": 7.283926486968994,
+      "learning_rate": 0.0,
+      "loss": 0.7013,
+      "step": 19
     }
   ],
   "logging_steps": 1,
@@ -124,12 +195,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 324298258513920.0,
+  "total_flos": 616166691176448.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null