Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bda35945962061652d59a8e4ad59deb48591939ccc12682cf63a96577b24525
+oid sha256:9ba7c4a5b7cbd2efca1a00977aa6bf02a04b45cec11057c2b133c05fc4000ac9
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87d47ddd2a36e2fb5639c61d569a349ecf35403668873bffbbd0ff7d0b49f5d2
+oid sha256:bb7c543e51fda7b323244464e14abd59d26637348d81eeade8fad77fdc016598
 size 335922386

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:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.8578988313674927,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.001886080724254998,
+  "best_metric": 1.7654892206192017,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.003772161448509996,
   "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": 10.173,
       "eval_steps_per_second": 5.089,
       "step": 10
+    },
+    {
+      "epoch": 0.002263296869105998,
+      "grad_norm": 10.256269454956055,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 7.4496,
+      "step": 12
+    },
+    {
+      "epoch": 0.002829121086382497,
+      "grad_norm": 8.768625259399414,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 7.4924,
+      "step": 15
+    },
+    {
+      "epoch": 0.002829121086382497,
+      "eval_loss": 1.8249664306640625,
+      "eval_runtime": 219.5536,
+      "eval_samples_per_second": 10.171,
+      "eval_steps_per_second": 5.088,
+      "step": 15
+    },
+    {
+      "epoch": 0.0033949453036589967,
+      "grad_norm": 8.699506759643555,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 6.9111,
+      "step": 18
+    },
+    {
+      "epoch": 0.003772161448509996,
+      "eval_loss": 1.7654892206192017,
+      "eval_runtime": 219.5093,
+      "eval_samples_per_second": 10.173,
+      "eval_steps_per_second": 5.089,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3515647493406720.0,
+  "total_flos": 7031294986813440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null