Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b3e6706e7ba74b34f60e7aa8125d8bb2167802f702a439f7aff23408969c39f
+oid sha256:a1a2cc29063650055fd0aa4b28e6f8da886cf7c3b1dd5bfcd66abc8ded5180f9
 size 102812592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27dcc2625bea101bf1ec50ead300c76ad34338a6257130b9b1db707022cf2be3
+oid sha256:9bb01ec79b5a091672aa722701a8d39da40d1ed070f9e356a0d0bfced2670f87
 size 205850474

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:108143b83974316a68742cb8b0e3f295e18e25269298bf09cb4166fe7abbc04c
+oid sha256:e833d61a5e72e10de50e8663f8aef186a3e7fe1a13b88ccae88995beffe105ce
 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": 1.8830574750900269,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0005084142559357365,
+  "best_metric": 1.7433966398239136,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.001016828511871473,
   "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": 10.485,
       "eval_steps_per_second": 5.245,
       "step": 10
+    },
+    {
+      "epoch": 0.0006100971071228837,
+      "grad_norm": 5.50850248336792,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 1.7119,
+      "step": 12
+    },
+    {
+      "epoch": 0.0007626213839036047,
+      "grad_norm": 5.362881660461426,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.7223,
+      "step": 15
+    },
+    {
+      "epoch": 0.0007626213839036047,
+      "eval_loss": 1.785104513168335,
+      "eval_runtime": 197.7279,
+      "eval_samples_per_second": 10.474,
+      "eval_steps_per_second": 5.24,
+      "step": 15
+    },
+    {
+      "epoch": 0.0009151456606843256,
+      "grad_norm": 7.011434078216553,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.7238,
+      "step": 18
+    },
+    {
+      "epoch": 0.001016828511871473,
+      "eval_loss": 1.7433966398239136,
+      "eval_runtime": 197.499,
+      "eval_samples_per_second": 10.486,
+      "eval_steps_per_second": 5.246,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 381994433249280.0,
+  "total_flos": 763988866498560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null