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:a0dc74a5f5166ce05ec315144993e76948917641d17ef339a1308c0f2051922b
+oid sha256:bde632ffcff2b7bfc8427f0cfc7367389ac5fe2df01f369cb13f8f928f8a5623
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7104c26f7c2d56240dfb0dd84e81bcb94b2093d19873e23302fd6302e47fa698
+oid sha256:86dd03c9eac661d4567700b1b6dd0c48cbad2f30f7f447cc92ddc046528091c3
 size 166439638

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02eba3114678197c652ff8ec3d2f89bacdf62eaf6e94caac908d89c83ce5ca48
+oid sha256:59dccbcd6e5d4694689dd3655d38cda4e38e65878a371ef0b6c906c0c871ff8e
 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": 1.0517429113388062,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.09345794392523364,
+  "best_metric": 0.9378935098648071,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.18691588785046728,
   "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": 26.793,
       "eval_steps_per_second": 6.847,
       "step": 10
+    },
+    {
+      "epoch": 0.11214953271028037,
+      "grad_norm": 0.7828400731086731,
+      "learning_rate": 0.000163742398974869,
+      "loss": 0.8625,
+      "step": 12
+    },
+    {
+      "epoch": 0.14018691588785046,
+      "grad_norm": 0.8065340518951416,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.8771,
+      "step": 15
+    },
+    {
+      "epoch": 0.14018691588785046,
+      "eval_loss": 0.989932656288147,
+      "eval_runtime": 3.3614,
+      "eval_samples_per_second": 26.774,
+      "eval_steps_per_second": 6.842,
+      "step": 15
+    },
+    {
+      "epoch": 0.16822429906542055,
+      "grad_norm": 0.8578646183013916,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 0.9057,
+      "step": 18
+    },
+    {
+      "epoch": 0.18691588785046728,
+      "eval_loss": 0.9378935098648071,
+      "eval_runtime": 3.3635,
+      "eval_samples_per_second": 26.758,
+      "eval_steps_per_second": 6.838,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2060861495574528.0,
+  "total_flos": 4071458076622848.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null