Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6163afcedb32f30822319079f53d463765a093a3f2431b5c82d739f19ed1436b
+oid sha256:250fc3759fff61e84e146d6c3bd16c94c6f944952dafb2f9205a70c473c962e2
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:680c4bc8cfc5f9745c7f469e594b66ac1133407a0e862528dcad536c4cabcd63
+oid sha256:471d93129bcd02d6c6af00d36c8fb9d70329418b8a9d5723c4d6265ab7fe222a
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9da626cfd75938739bb71ce0bcc89458f5734acc3e36ff945e02f49adeacfba
+oid sha256:9795c5ae678d05e9e1d200c8c48172e717b8b0016868766324e0e229567119a2
 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": 0.7995980381965637,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.04975124378109453,
+  "best_metric": 0.7601059079170227,
+  "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": 8.608,
       "eval_steps_per_second": 2.177,
       "step": 10
+    },
+    {
+      "epoch": 0.05970149253731343,
+      "grad_norm": 0.20222985744476318,
+      "learning_rate": 0.000163742398974869,
+      "loss": 0.7887,
+      "step": 12
+    },
+    {
+      "epoch": 0.07462686567164178,
+      "grad_norm": 0.19999514520168304,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.7424,
+      "step": 15
+    },
+    {
+      "epoch": 0.07462686567164178,
+      "eval_loss": 0.7731540203094482,
+      "eval_runtime": 19.7843,
+      "eval_samples_per_second": 8.593,
+      "eval_steps_per_second": 2.173,
+      "step": 15
+    },
+    {
+      "epoch": 0.08955223880597014,
+      "grad_norm": 0.2041771560907364,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 0.7451,
+      "step": 18
+    },
+    {
+      "epoch": 0.09950248756218906,
+      "eval_loss": 0.7601059079170227,
+      "eval_runtime": 19.811,
+      "eval_samples_per_second": 8.581,
+      "eval_steps_per_second": 2.171,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7165146606600192.0,
+  "total_flos": 1.4155533539868672e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null