Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:292a2bfd6f4c3f8cb5e1cfaf6f5855a039f122f73f3b14bccb9aeccce07650de
+oid sha256:ed29e9adef70fe772cd08c83a62acfefb3235dfd9c81ae854e541ddad68c84fd
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:809c712b65bc645c4718e9e02f83227f4841943977e1626dfdb6dbeb8a3a77ad
+oid sha256:4c7de3be56f9b60d3519f3ff1e5fdee53b641252b60d963ec575a5bed7e3b5cf
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e97ead28242dd097af80112cb3bd8d751944021cbf255fca1535e0f2a22344d9
+oid sha256:c5288ed9323916daf49e9e619b5ce81ab40c19e01021e3ee0c12210ac8bab7de
 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": 10.380829811096191,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0002823004665015209,
+  "best_metric": 10.379389762878418,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0005646009330030418,
   "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": 183.396,
       "eval_steps_per_second": 91.704,
       "step": 10
+    },
+    {
+      "epoch": 0.0003387605598018251,
+      "grad_norm": 0.02849678508937359,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 10.3807,
+      "step": 12
+    },
+    {
+      "epoch": 0.00042345069975228137,
+      "grad_norm": 0.02935921773314476,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 10.382,
+      "step": 15
+    },
+    {
+      "epoch": 0.00042345069975228137,
+      "eval_loss": 10.380049705505371,
+      "eval_runtime": 81.6981,
+      "eval_samples_per_second": 182.562,
+      "eval_steps_per_second": 91.287,
+      "step": 15
+    },
+    {
+      "epoch": 0.0005081408397027376,
+      "grad_norm": 0.026194525882601738,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 10.3807,
+      "step": 18
+    },
+    {
+      "epoch": 0.0005646009330030418,
+      "eval_loss": 10.379389762878418,
+      "eval_runtime": 81.5372,
+      "eval_samples_per_second": 182.923,
+      "eval_steps_per_second": 91.467,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 261512232960.0,
+  "total_flos": 523024465920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null