Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fd5d3a4fdc0611979a191ed0900edc430d075b5b714be46f865dc774dc32ba6
+oid sha256:b5782c9b3286c6570da4737600cbe55cd186d8210b2570ee39fe88bee509675f
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be341cb6434a4c13dfb34b56a97dadb3a3f811596abc213d6d5360c5217c630e
+oid sha256:93d1083323a1de708d61a946b1188fd482382bb42254e755db09e95733fa6321
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32d70b924c02cacaf61ed121feaa2846076bc8c635c10b9cc5a7670f536d1222
+oid sha256:be3088e2277f875a70fbcd011f6f800d718e4d362f116d9a4fe2df0405e1b0ed
 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": 1.7444088459014893,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.021299254526091587,
+  "best_metric": 1.6150790452957153,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.042598509052183174,
   "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": 6.198,
       "eval_steps_per_second": 1.55,
       "step": 10
+    },
+    {
+      "epoch": 0.025559105431309903,
+      "grad_norm": 0.6345270872116089,
+      "learning_rate": 0.000163742398974869,
+      "loss": 1.3598,
+      "step": 12
+    },
+    {
+      "epoch": 0.03194888178913738,
+      "grad_norm": 0.6768683791160583,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.4482,
+      "step": 15
+    },
+    {
+      "epoch": 0.03194888178913738,
+      "eval_loss": 1.6697704792022705,
+      "eval_runtime": 63.6964,
+      "eval_samples_per_second": 6.217,
+      "eval_steps_per_second": 1.554,
+      "step": 15
+    },
+    {
+      "epoch": 0.038338658146964855,
+      "grad_norm": 0.7733621001243591,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 1.5471,
+      "step": 18
+    },
+    {
+      "epoch": 0.042598509052183174,
+      "eval_loss": 1.6150790452957153,
+      "eval_runtime": 63.6836,
+      "eval_samples_per_second": 6.218,
+      "eval_steps_per_second": 1.555,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8531703760945152.0,
+  "total_flos": 1.5950576596549632e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null