Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62d4920c04ba3b2b4ae098e1c4c76358b18b0a9eb981a63c69c20447ad78296c
+oid sha256:c6643a2bdfc73cf943b58e14af9c9894f5ce67f979b23932b497016617c9824a
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82a2e9dddac146ac0928df6a2d88798f0cc31582c00b17a6dbade36548687ded
+oid sha256:05695c587d6c3f5c053ad27d7dc75ed355a1de3b0a940a6448e7d16dfe6193bf
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94eb3af0be59b8022e591483a56634de67b6ec709d4a7976205940027b927a1a
+oid sha256:a8d0ca5f94c74be21f7e258f478e4f1bcf339ab697a95d852a0fd9b800d39d6b
 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": 1.2502100467681885,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.04975124378109453,
+  "best_metric": 1.0692726373672485,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.09950248756218906,
   "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": 8.498,
       "eval_steps_per_second": 4.299,
       "step": 10
+    },
+    {
+      "epoch": 0.05970149253731343,
+      "grad_norm": 1.160507082939148,
+      "learning_rate": 0.000163742398974869,
+      "loss": 1.2655,
+      "step": 12
+    },
+    {
+      "epoch": 0.07462686567164178,
+      "grad_norm": 0.9718839526176453,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.225,
+      "step": 15
+    },
+    {
+      "epoch": 0.07462686567164178,
+      "eval_loss": 1.110392451286316,
+      "eval_runtime": 10.021,
+      "eval_samples_per_second": 8.482,
+      "eval_steps_per_second": 4.291,
+      "step": 15
+    },
+    {
+      "epoch": 0.08955223880597014,
+      "grad_norm": 1.174685001373291,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 1.0562,
+      "step": 18
+    },
+    {
+      "epoch": 0.09950248756218906,
+      "eval_loss": 1.0692726373672485,
+      "eval_runtime": 10.0762,
+      "eval_samples_per_second": 8.436,
+      "eval_steps_per_second": 4.267,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3267291009515520.0,
+  "total_flos": 6534582019031040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null