Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b22893dac87d7aea4a92cc5869f5aaa21579f3aaf1c975f04865e7a33ed5c13
+oid sha256:75820bfce164bb15d89b9c4e35c64438fc292e7a33dc1ca5caf4cc4748efd411
 size 390888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c1bbb74fa080470b0a549083e928ec2585691797ba1a498b85055385fcfa31c
+oid sha256:0afc82c250f4d9da7bc8101f83ba44aee749a123c7c60f533c6e84e3bcfcdf03
 size 819770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70b8bee79b642f97d67339860368fe567d9d6c13f2e1cff2d3a0f5387759a60d
+oid sha256:4882a93ba5c11ab81a133169b3d105975783029c16d75b0ec96933a1347e749f
 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": 7.906499862670898,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.10101010101010101,
+  "best_metric": 6.069979190826416,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.20202020202020202,
   "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": 35.141,
       "eval_steps_per_second": 17.571,
       "step": 10
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 11.80984115600586,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 8.8837,
+      "step": 11
+    },
+    {
+      "epoch": 0.12121212121212122,
+      "grad_norm": 14.16118335723877,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 8.1952,
+      "step": 12
+    },
+    {
+      "epoch": 0.13131313131313133,
+      "grad_norm": 13.317045211791992,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 7.6443,
+      "step": 13
+    },
+    {
+      "epoch": 0.1414141414141414,
+      "grad_norm": 10.644977569580078,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 8.1683,
+      "step": 14
+    },
+    {
+      "epoch": 0.15151515151515152,
+      "grad_norm": 12.658942222595215,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 6.9342,
+      "step": 15
+    },
+    {
+      "epoch": 0.15151515151515152,
+      "eval_loss": 6.585737705230713,
+      "eval_runtime": 1.3118,
+      "eval_samples_per_second": 32.017,
+      "eval_steps_per_second": 16.009,
+      "step": 15
+    },
+    {
+      "epoch": 0.16161616161616163,
+      "grad_norm": 10.726329803466797,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 6.4411,
+      "step": 16
+    },
+    {
+      "epoch": 0.1717171717171717,
+      "grad_norm": 12.152200698852539,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 5.4328,
+      "step": 17
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 9.079628944396973,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 5.6252,
+      "step": 18
+    },
+    {
+      "epoch": 0.1919191919191919,
+      "grad_norm": 6.902795314788818,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 6.8476,
+      "step": 19
+    },
+    {
+      "epoch": 0.20202020202020202,
+      "grad_norm": 8.562902450561523,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 6.4595,
+      "step": 20
+    },
+    {
+      "epoch": 0.20202020202020202,
+      "eval_loss": 6.069979190826416,
+      "eval_runtime": 1.2271,
+      "eval_samples_per_second": 34.226,
+      "eval_steps_per_second": 17.113,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1180053798912.0,
+  "total_flos": 2294549053440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null