Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a353d19c58729037e8776fe0032998338dc19105382e85504c1048be09dbaa5
+oid sha256:82624bb31acdc07bd8d5365cd51c32048469affe22289a2922b11a114df4d392
 size 10636352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9e28428e1c80ae0461fc149de79fc1724cfbe26e64318a6dbfbd1241dc3e605
+oid sha256:1acdea9f6264acfec536e404d70c44d90d13e9be9be12afb4ff6b4321705ef03
 size 21354682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6373adaf45570a44712e1831653b10376337a73b7bdd5bfc75cca8e963e324db
+oid sha256:7b68afb9bb7ee1d59d6ca3378a8fcdaab9d911ac6b25c2201ebc1813e43ad50d
 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": 2.0985138416290283,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.008592910848549946,
+  "best_metric": 2.014415979385376,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.017185821697099892,
   "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": 93.565,
       "eval_steps_per_second": 46.783,
       "step": 10
+    },
+    {
+      "epoch": 0.010311493018259935,
+      "grad_norm": 4.199799537658691,
+      "learning_rate": 0.000163742398974869,
+      "loss": 8.8299,
+      "step": 12
+    },
+    {
+      "epoch": 0.01288936627282492,
+      "grad_norm": 4.125592231750488,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 8.6592,
+      "step": 15
+    },
+    {
+      "epoch": 0.01288936627282492,
+      "eval_loss": 2.04288911819458,
+      "eval_runtime": 5.327,
+      "eval_samples_per_second": 91.983,
+      "eval_steps_per_second": 45.992,
+      "step": 15
+    },
+    {
+      "epoch": 0.015467239527389903,
+      "grad_norm": 3.9506421089172363,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 8.3345,
+      "step": 18
+    },
+    {
+      "epoch": 0.017185821697099892,
+      "eval_loss": 2.014415979385376,
+      "eval_runtime": 5.1833,
+      "eval_samples_per_second": 94.534,
+      "eval_steps_per_second": 47.267,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 47422453579776.0,
+  "total_flos": 92689341087744.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null