Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de03416ba17490c30243827f6363c051fc3e3477f440387554f185d96b22f602
+oid sha256:e55d85c3deb71092521c6516303dedf1cd8fe3a519a084d8a47d5b1d1863970b
 size 66103768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85bba7333f63b029d485d6cc01e2eb78d52d5e77ae121b4a1f559aae96490803
+oid sha256:dc9131438817001c7c1d455c167f4550457509a96081de6e3533b625623b6afa
 size 33939412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0afd2f913064bcf9361f6e9f2b0862d10c1c7d62a9bec3954c4d41b201de7d4
+oid sha256:dda39a3481844c408ce6d6d055e10c11c78433412aa423c5d22ce3a7455ed2b9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0562341213226318,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.006167129201356768,
+  "best_metric": 0.6391462087631226,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.012334258402713537,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 3.061,
       "eval_steps_per_second": 1.533,
       "step": 10
+    },
+    {
+      "epoch": 0.0067838421214924454,
+      "grad_norm": 13.483577728271484,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 5.2826,
+      "step": 11
+    },
+    {
+      "epoch": 0.0074005550416281225,
+      "grad_norm": 4.335202693939209,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 3.606,
+      "step": 12
+    },
+    {
+      "epoch": 0.008017267961763799,
+      "grad_norm": 4.800070285797119,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 2.6771,
+      "step": 13
+    },
+    {
+      "epoch": 0.008633980881899476,
+      "grad_norm": 5.31058931350708,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 2.963,
+      "step": 14
+    },
+    {
+      "epoch": 0.009250693802035153,
+      "grad_norm": 5.45186185836792,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 4.2725,
+      "step": 15
+    },
+    {
+      "epoch": 0.009250693802035153,
+      "eval_loss": 0.7318894863128662,
+      "eval_runtime": 225.8884,
+      "eval_samples_per_second": 3.024,
+      "eval_steps_per_second": 1.514,
+      "step": 15
+    },
+    {
+      "epoch": 0.009867406722170829,
+      "grad_norm": 5.0472636222839355,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.6359,
+      "step": 16
+    },
+    {
+      "epoch": 0.010484119642306507,
+      "grad_norm": 5.589927673339844,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 4.3154,
+      "step": 17
+    },
+    {
+      "epoch": 0.011100832562442183,
+      "grad_norm": 4.973724842071533,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 2.4276,
+      "step": 18
+    },
+    {
+      "epoch": 0.01171754548257786,
+      "grad_norm": 4.498130798339844,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 2.0461,
+      "step": 19
+    },
+    {
+      "epoch": 0.012334258402713537,
+      "grad_norm": 5.219486713409424,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 3.6739,
+      "step": 20
+    },
+    {
+      "epoch": 0.012334258402713537,
+      "eval_loss": 0.6391462087631226,
+      "eval_runtime": 225.9951,
+      "eval_samples_per_second": 3.022,
+      "eval_steps_per_second": 1.513,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2160585604177920.0,
+  "total_flos": 4105112647938048.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null