Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76ab3a057bcc4a8707198b1bd8f0bef1dc2c2f075955118fe47486fd845a4475
+oid sha256:a21c27882cbfc9a8e782e4e0694d8a1c67ea3345c6b5c3ee95c9b6dbcede07fc
 size 12609416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:788f3bbaaa34d01b1e788a1ea5cf910fa3d97b916776053c2c877ba0046fdd0a
+oid sha256:f80d26debb74eccbc50d57cd14ab58f764353e86e84ee1d87f4625f0a162a9d7
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c9a75f108334a418a7a60fec99e44fa186e26e0cb2561fc9cb4a7566e3c595c
+oid sha256:c8195f5f8ab0a2152863fee8331a14f0c6fd922ebfbe0783423b8278beeaadd3
 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": 3.2310242652893066,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00019502586530538614,
+  "best_metric": 2.781816005706787,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0003900517306107723,
   "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": 16.371,
       "eval_steps_per_second": 8.185,
       "step": 10
+    },
+    {
+      "epoch": 0.00021452845183592473,
+      "grad_norm": 11.555283546447754,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 14.2327,
+      "step": 11
+    },
+    {
+      "epoch": 0.00023403103836646335,
+      "grad_norm": 11.541330337524414,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 12.3214,
+      "step": 12
+    },
+    {
+      "epoch": 0.00025353362489700194,
+      "grad_norm": 10.01172161102295,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 13.4483,
+      "step": 13
+    },
+    {
+      "epoch": 0.00027303621142754056,
+      "grad_norm": 10.464963912963867,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 12.3316,
+      "step": 14
+    },
+    {
+      "epoch": 0.0002925387979580792,
+      "grad_norm": 10.74640941619873,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 10.129,
+      "step": 15
+    },
+    {
+      "epoch": 0.0002925387979580792,
+      "eval_loss": 2.8842618465423584,
+      "eval_runtime": 1311.7155,
+      "eval_samples_per_second": 16.459,
+      "eval_steps_per_second": 8.23,
+      "step": 15
+    },
+    {
+      "epoch": 0.0003120413844886178,
+      "grad_norm": 11.440065383911133,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 11.6759,
+      "step": 16
+    },
+    {
+      "epoch": 0.0003315439710191564,
+      "grad_norm": 10.98075008392334,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 12.2028,
+      "step": 17
+    },
+    {
+      "epoch": 0.00035104655754969504,
+      "grad_norm": 12.294601440429688,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 9.749,
+      "step": 18
+    },
+    {
+      "epoch": 0.00037054914408023366,
+      "grad_norm": 14.96569538116455,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 11.7882,
+      "step": 19
+    },
+    {
+      "epoch": 0.0003900517306107723,
+      "grad_norm": 12.162907600402832,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 11.2294,
+      "step": 20
+    },
+    {
+      "epoch": 0.0003900517306107723,
+      "eval_loss": 2.781816005706787,
+      "eval_runtime": 1316.6534,
+      "eval_samples_per_second": 16.398,
+      "eval_steps_per_second": 8.199,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 75069652992000.0,
+  "total_flos": 150139305984000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null