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:be05f447e835f72bd4abc1ac4d0deb3669febf5d0eb1cbf239c28d6722e9dfba
+oid sha256:0d764cc9e190b9bfcbc23eb52a7965777e0a1c51dcc0f0579af51b704b3a53fd
 size 28351000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6228d4b20960f4fad2ab027bba4f85f721c80cb34776064de4230dd30ec2d8a
+oid sha256:7f76ebd531dfc389ee4a2c6e1bc259e63fd87a45b3d73864fb2b0c535ceb7457
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e814cc3f585a61efeed95c6a32e65ae0a360d8346fd2c6098567e0dbf515e859
+oid sha256:c6eacaf126875d012a3f9f4bdf60d2fff46f053b87a7d5774e37ae5621d3495b
 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": 1.3001285791397095,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.008438818565400843,
+  "best_metric": 1.1878825426101685,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.016877637130801686,
   "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": 9.795,
       "eval_steps_per_second": 4.907,
       "step": 10
+    },
+    {
+      "epoch": 0.009282700421940928,
+      "grad_norm": 1.998062014579773,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 5.1065,
+      "step": 11
+    },
+    {
+      "epoch": 0.010126582278481013,
+      "grad_norm": 2.0567452907562256,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 5.0806,
+      "step": 12
+    },
+    {
+      "epoch": 0.010970464135021098,
+      "grad_norm": 2.400956153869629,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 5.499,
+      "step": 13
+    },
+    {
+      "epoch": 0.01181434599156118,
+      "grad_norm": 2.553539991378784,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 5.1545,
+      "step": 14
+    },
+    {
+      "epoch": 0.012658227848101266,
+      "grad_norm": 2.5420608520507812,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 5.5475,
+      "step": 15
+    },
+    {
+      "epoch": 0.012658227848101266,
+      "eval_loss": 1.226226568222046,
+      "eval_runtime": 50.6579,
+      "eval_samples_per_second": 9.85,
+      "eval_steps_per_second": 4.935,
+      "step": 15
+    },
+    {
+      "epoch": 0.01350210970464135,
+      "grad_norm": 2.7176949977874756,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 5.1463,
+      "step": 16
+    },
+    {
+      "epoch": 0.014345991561181435,
+      "grad_norm": 2.3419106006622314,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 5.0369,
+      "step": 17
+    },
+    {
+      "epoch": 0.015189873417721518,
+      "grad_norm": 2.250117063522339,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 4.8538,
+      "step": 18
+    },
+    {
+      "epoch": 0.016033755274261603,
+      "grad_norm": 2.4466376304626465,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 4.7334,
+      "step": 19
+    },
+    {
+      "epoch": 0.016877637130801686,
+      "grad_norm": 2.1515731811523438,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 4.627,
+      "step": 20
+    },
+    {
+      "epoch": 0.016877637130801686,
+      "eval_loss": 1.1878825426101685,
+      "eval_runtime": 50.5519,
+      "eval_samples_per_second": 9.871,
+      "eval_steps_per_second": 4.945,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 597531285258240.0,
+  "total_flos": 1195062570516480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null