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:b7ca3336f15d605038abf7095f24147f319c28773db4c0634dcaeb299f68f6bc
+oid sha256:f5a3f3ea31dc522e15511e13f328dd1acae383413cfe419f75675ab172ff7a61
 size 56662456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ff9f52dd6dd0674843354b1343fc83e7fb3703ddba400809ef7e4580eba4131
+oid sha256:3a6a3a904cccb132a52af3ac1c3b64e130fdd27a79fa98a307aec665c9f963a5
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:693d65ff7d3abbbb13c7ee57d38fa6e7fa5181ebaaabad321dd22b54929bbad4
+oid sha256:40dab678f8341cb1f6a50c07bf4f3f2e6d7185a7a6a288def2d3180b15023b3f
 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": 1.0550651550292969,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.10526315789473684,
+  "best_metric": 0.930294394493103,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.21052631578947367,
   "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": 17.805,
       "eval_steps_per_second": 8.902,
       "step": 10
+    },
+    {
+      "epoch": 0.12631578947368421,
+      "grad_norm": 1.3418906927108765,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 4.3085,
+      "step": 12
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 1.4580527544021606,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 3.7404,
+      "step": 15
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "eval_loss": 0.9724666476249695,
+      "eval_runtime": 2.2464,
+      "eval_samples_per_second": 17.806,
+      "eval_steps_per_second": 8.903,
+      "step": 15
+    },
+    {
+      "epoch": 0.18947368421052632,
+      "grad_norm": 1.5179438591003418,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.975,
+      "step": 18
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "eval_loss": 0.930294394493103,
+      "eval_runtime": 2.2497,
+      "eval_samples_per_second": 17.78,
+      "eval_steps_per_second": 8.89,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 600937731194880.0,
+  "total_flos": 1201875462389760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null