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:e23660ba2fa1618409a7b84c5d1067041470516483d6068834392acef9100d4b
+oid sha256:547c917db58de51b098d49e3a84bdbf9ea9050521e16d26061bebf4b90eb38b4
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec2718c93d9c827a9a55d10f8a748054add900c50200df247831e51f3d8a3248
+oid sha256:840b02fc900fd966e2da1e898e1a34ae9b4746fab84cbb533f41b3bc40f83fbf
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e00e749000557b1014539a7bbdab1432f4856d3e423d8a50564c8090e2b3077
+oid sha256:45aa182b328bfe02d781c42616bdb5443d5352aa5d5ba6c53863c2f340c940a8
 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": 1.2735178470611572,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.003678837487353996,
+  "best_metric": 0.6928964853286743,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.007357674974707992,
   "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": 7.312,
       "eval_steps_per_second": 3.659,
       "step": 10
+    },
+    {
+      "epoch": 0.004046721236089396,
+      "grad_norm": 4.377835750579834,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 1.2754,
+      "step": 11
+    },
+    {
+      "epoch": 0.004414604984824795,
+      "grad_norm": 3.609360933303833,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.9183,
+      "step": 12
+    },
+    {
+      "epoch": 0.004782488733560195,
+      "grad_norm": 3.6163525581359863,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.9236,
+      "step": 13
+    },
+    {
+      "epoch": 0.005150372482295594,
+      "grad_norm": 3.1708669662475586,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.8382,
+      "step": 14
+    },
+    {
+      "epoch": 0.005518256231030994,
+      "grad_norm": 2.7939131259918213,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.6538,
+      "step": 15
+    },
+    {
+      "epoch": 0.005518256231030994,
+      "eval_loss": 0.7443342804908752,
+      "eval_runtime": 153.8448,
+      "eval_samples_per_second": 7.443,
+      "eval_steps_per_second": 3.725,
+      "step": 15
+    },
+    {
+      "epoch": 0.005886139979766394,
+      "grad_norm": 4.013178825378418,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.8417,
+      "step": 16
+    },
+    {
+      "epoch": 0.006254023728501794,
+      "grad_norm": 3.8191921710968018,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.8894,
+      "step": 17
+    },
+    {
+      "epoch": 0.006621907477237193,
+      "grad_norm": 3.4114315509796143,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.7048,
+      "step": 18
+    },
+    {
+      "epoch": 0.006989791225972593,
+      "grad_norm": 2.447831153869629,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.4686,
+      "step": 19
+    },
+    {
+      "epoch": 0.007357674974707992,
+      "grad_norm": 4.075280666351318,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.7533,
+      "step": 20
+    },
+    {
+      "epoch": 0.007357674974707992,
+      "eval_loss": 0.6928964853286743,
+      "eval_runtime": 154.6256,
+      "eval_samples_per_second": 7.405,
+      "eval_steps_per_second": 3.706,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 500097330708480.0,
+  "total_flos": 1000194661416960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null