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:dcd1ef9e0aec6f4713c3cd4386a5dc8ccd7df9ddd42900158b299fa7fe2eeb06
+oid sha256:f4c203f19086334c9de1a5b2058f64fe7b4a1596b21e8f287d684b28e5608136
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b71b1a30ec0f9739374ec4ba24eb8fd6a0e5373fe5774f4610e5c9d720b0c68f
+oid sha256:199e52e529ce01316f03305c8e6af8e88e608de19d3d78f8780e7aa5aed20eee
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4d0f46032f0e4a6e77b62412e0a9bf6977ad7f3b55d6d40566ac3fc09620126
+oid sha256:1220ba00c1f2dd5abd7cf374a8575654b945f7674928bf0cc1765b63a4620fdd
 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": 2.0631089210510254,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.007136485280999108,
+  "best_metric": 2.0383806228637695,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.014272970561998216,
   "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": 3.507,
       "eval_steps_per_second": 1.753,
       "step": 10
+    },
+    {
+      "epoch": 0.00856378233719893,
+      "grad_norm": 26.971921920776367,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 8.2353,
+      "step": 12
+    },
+    {
+      "epoch": 0.010704727921498661,
+      "grad_norm": 15.235742568969727,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 8.2829,
+      "step": 15
+    },
+    {
+      "epoch": 0.010704727921498661,
+      "eval_loss": 2.049189329147339,
+      "eval_runtime": 168.2105,
+      "eval_samples_per_second": 3.508,
+      "eval_steps_per_second": 1.754,
+      "step": 15
+    },
+    {
+      "epoch": 0.012845673505798395,
+      "grad_norm": 3.738413095474243,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 8.0633,
+      "step": 18
+    },
+    {
+      "epoch": 0.014272970561998216,
+      "eval_loss": 2.0383806228637695,
+      "eval_runtime": 168.3892,
+      "eval_samples_per_second": 3.504,
+      "eval_steps_per_second": 1.752,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5309400235376640.0,
+  "total_flos": 1.1353948195651584e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null