Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dd05d93b93e040698b0ad9d4b70f539875fd6162d46a444b2934815ed3fa35e
+oid sha256:41016c28e22aa7e4c61c57d2b9f97ce778494f79840477c6a0f6093deaf6a241
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44d8f467c8e41d92d74a7029e5256064ae6dc011c27c883e73b94b536c4cd51d
+oid sha256:7c366c4c2cb4e19e8661d021d841bd1f0d7a0b5c40d92eb30463f5cc67f33f67
 size 56088148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1ee992f6be602c0b2674b934ade6dffe5615c0f0f6fc60f649029af878d4abf
+oid sha256:5b65a3cff5730f6b3792e6180642fe02ba01c1869d91aad63a83938f8c222c9d
 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": 1.9750728607177734,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0007845136995704787,
+  "best_metric": 1.7211201190948486,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0015690273991409574,
   "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": 2.998,
       "eval_steps_per_second": 1.499,
       "step": 10
+    },
+    {
+      "epoch": 0.0008629650695275266,
+      "grad_norm": 0.8262554407119751,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 2.0639,
+      "step": 11
+    },
+    {
+      "epoch": 0.0009414164394845745,
+      "grad_norm": 1.002493143081665,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 1.8902,
+      "step": 12
+    },
+    {
+      "epoch": 0.0010198678094416223,
+      "grad_norm": 0.8235588073730469,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.8743,
+      "step": 13
+    },
+    {
+      "epoch": 0.0010983191793986703,
+      "grad_norm": 0.91981041431427,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 1.9061,
+      "step": 14
+    },
+    {
+      "epoch": 0.0011767705493557182,
+      "grad_norm": 0.7380278706550598,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.9508,
+      "step": 15
+    },
+    {
+      "epoch": 0.0011767705493557182,
+      "eval_loss": 1.8117865324020386,
+      "eval_runtime": 1768.5844,
+      "eval_samples_per_second": 3.035,
+      "eval_steps_per_second": 1.518,
+      "step": 15
+    },
+    {
+      "epoch": 0.001255221919312766,
+      "grad_norm": 0.757776141166687,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.7871,
+      "step": 16
+    },
+    {
+      "epoch": 0.001333673289269814,
+      "grad_norm": 0.7072300314903259,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 1.6816,
+      "step": 17
+    },
+    {
+      "epoch": 0.0014121246592268617,
+      "grad_norm": 0.7770305871963501,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.566,
+      "step": 18
+    },
+    {
+      "epoch": 0.0014905760291839096,
+      "grad_norm": 0.8346571326255798,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.6497,
+      "step": 19
+    },
+    {
+      "epoch": 0.0015690273991409574,
+      "grad_norm": 0.7390028238296509,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.8454,
+      "step": 20
+    },
+    {
+      "epoch": 0.0015690273991409574,
+      "eval_loss": 1.7211201190948486,
+      "eval_runtime": 1788.6648,
+      "eval_samples_per_second": 3.001,
+      "eval_steps_per_second": 1.501,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3960342577152000.0,
+  "total_flos": 8131903425085440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null