Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:390da6b7ba682ecf5b18b8e65385c7eb00956d869a776f4e51dee021de2b4982
+oid sha256:a9e738334be2d5a76569b083f10ad7f050fba5a9c183508c665571b4beaf22b3
 size 25192592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bce532ca10f3a9ea4671260f39b1a4ad9db9093afec71a7edff76260801eeb27
+oid sha256:2d98064f0b09df1f9fe47a3e80667a88a117f984ccb0b52e1e7f47c0ea81e40b
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1606aee2938c2615261c3d086ecbb789b221d24803b0725566df5c5d0b1b0eac
+oid sha256:6030e2eec03ac3bd8af1f9fd206c9a2d7d37bd3a2bcfc1cfa963fa848c4476f5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
+oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.0353667736053467,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.04756242568370987,
+  "best_metric": 2.9805502891540527,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.09512485136741974,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 108.309,
       "eval_steps_per_second": 27.382,
       "step": 10
+    },
+    {
+      "epoch": 0.057074910820451845,
+      "grad_norm": 23.035850524902344,
+      "learning_rate": 0.000163742398974869,
+      "loss": 11.4774,
+      "step": 12
+    },
+    {
+      "epoch": 0.0713436385255648,
+      "grad_norm": 21.357481002807617,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 11.6186,
+      "step": 15
+    },
+    {
+      "epoch": 0.0713436385255648,
+      "eval_loss": 3.0080606937408447,
+      "eval_runtime": 1.6384,
+      "eval_samples_per_second": 108.642,
+      "eval_steps_per_second": 27.466,
+      "step": 15
+    },
+    {
+      "epoch": 0.08561236623067776,
+      "grad_norm": 26.94682502746582,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 11.9721,
+      "step": 18
+    },
+    {
+      "epoch": 0.09512485136741974,
+      "eval_loss": 2.9805502891540527,
+      "eval_runtime": 2.0766,
+      "eval_samples_per_second": 85.715,
+      "eval_steps_per_second": 21.67,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 398257469521920.0,
+  "total_flos": 752264109096960.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null