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:d3284d0978393758b0922b1f4966e1a411b5e0c368dc62312a087ffcf68877c0
+oid sha256:f347d6f5f78aa10507f91dd2aa08a9c0fd510519d53937655f513a09085abc38
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05ba7e72622a71b6a0084cc7137cbb094513342d50e18ba18067bd1013b8b083
+oid sha256:1c7cae9db963badd03c0433695fad625f6825d67ba10e6ecbd84a7736f1366a4
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c9c90db431b6b7631c9f6f36d7a9f8e6cce0bcf0ce5264d2d120fd3e9671e0b
+oid sha256:019b308f45c7af9e678aee77b9c2e71dec9d5cc7433144da063c6bbb02b03df6
 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": 1.1747561693191528,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0003216106260150835,
+  "best_metric": 1.0564022064208984,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.000643221252030167,
   "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": 7.778,
       "eval_steps_per_second": 3.889,
       "step": 10
+    },
+    {
+      "epoch": 0.0003537716886165919,
+      "grad_norm": 0.5287800431251526,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 1.018,
+      "step": 11
+    },
+    {
+      "epoch": 0.0003859327512181002,
+      "grad_norm": 0.38879427313804626,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.7467,
+      "step": 12
+    },
+    {
+      "epoch": 0.0004180938138196086,
+      "grad_norm": 0.40861812233924866,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.7441,
+      "step": 13
+    },
+    {
+      "epoch": 0.00045025487642111697,
+      "grad_norm": 0.5427682399749756,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.9505,
+      "step": 14
+    },
+    {
+      "epoch": 0.0004824159390226253,
+      "grad_norm": 0.7218433618545532,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.0734,
+      "step": 15
+    },
+    {
+      "epoch": 0.0004824159390226253,
+      "eval_loss": 1.1031818389892578,
+      "eval_runtime": 1651.3755,
+      "eval_samples_per_second": 7.928,
+      "eval_steps_per_second": 3.964,
+      "step": 15
+    },
+    {
+      "epoch": 0.0005145770016241337,
+      "grad_norm": 0.5867312550544739,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.9614,
+      "step": 16
+    },
+    {
+      "epoch": 0.000546738064225642,
+      "grad_norm": 0.5200360417366028,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.8451,
+      "step": 17
+    },
+    {
+      "epoch": 0.0005788991268271504,
+      "grad_norm": 0.5184641480445862,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.0232,
+      "step": 18
+    },
+    {
+      "epoch": 0.0006110601894286587,
+      "grad_norm": 0.6201175451278687,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.2448,
+      "step": 19
+    },
+    {
+      "epoch": 0.000643221252030167,
+      "grad_norm": 0.46350809931755066,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.8938,
+      "step": 20
+    },
+    {
+      "epoch": 0.000643221252030167,
+      "eval_loss": 1.0564022064208984,
+      "eval_runtime": 1666.9912,
+      "eval_samples_per_second": 7.854,
+      "eval_steps_per_second": 3.927,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 902053531484160.0,
+  "total_flos": 2009119229214720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null