Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:778f2e41fb51bde37b1fa8cf323f6b23ad084249feb2829257fcac247bbfb0cd
+oid sha256:ffe5e38735cccf7b48e4a47d8709f7d192da5380555fa01fef0c080613232996
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eb2e7740fe2519abaa453bc7f6b3fda40260ddd995e993504df962df6897522
+oid sha256:6a5b8255a9b42174c49e1a5aecc929135649d2670e55ec6c0fcb737de1fb085f
 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": 4.309162139892578,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.03714020427112349,
+  "best_metric": 4.180180072784424,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.07428040854224698,
   "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": 17.376,
       "eval_steps_per_second": 8.688,
       "step": 10
+    },
+    {
+      "epoch": 0.04085422469823584,
+      "grad_norm": 34.36117935180664,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 16.0074,
+      "step": 11
+    },
+    {
+      "epoch": 0.04456824512534819,
+      "grad_norm": 45.245521545410156,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 18.3396,
+      "step": 12
+    },
+    {
+      "epoch": 0.04828226555246054,
+      "grad_norm": 46.66457748413086,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 16.1451,
+      "step": 13
+    },
+    {
+      "epoch": 0.051996285979572884,
+      "grad_norm": 77.11463165283203,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 16.7409,
+      "step": 14
+    },
+    {
+      "epoch": 0.055710306406685235,
+      "grad_norm": 41.09373092651367,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 18.2822,
+      "step": 15
+    },
+    {
+      "epoch": 0.055710306406685235,
+      "eval_loss": 4.215371608734131,
+      "eval_runtime": 6.6015,
+      "eval_samples_per_second": 17.269,
+      "eval_steps_per_second": 8.634,
+      "step": 15
+    },
+    {
+      "epoch": 0.059424326833797586,
+      "grad_norm": 39.33907699584961,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 18.2399,
+      "step": 16
+    },
+    {
+      "epoch": 0.06313834726090993,
+      "grad_norm": 51.7769775390625,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 17.3302,
+      "step": 17
+    },
+    {
+      "epoch": 0.06685236768802229,
+      "grad_norm": 41.05906677246094,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 15.5034,
+      "step": 18
+    },
+    {
+      "epoch": 0.07056638811513463,
+      "grad_norm": 47.10402297973633,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 15.3104,
+      "step": 19
+    },
+    {
+      "epoch": 0.07428040854224698,
+      "grad_norm": 37.23863983154297,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 16.3764,
+      "step": 20
+    },
+    {
+      "epoch": 0.07428040854224698,
+      "eval_loss": 4.180180072784424,
+      "eval_runtime": 6.4415,
+      "eval_samples_per_second": 17.698,
+      "eval_steps_per_second": 8.849,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 87728565780480.0,
+  "total_flos": 175457131560960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null