Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5df9ee217b31015ce546cdd59bb3a40c003fc73cdeeeaf861216e10d4fd80383
+oid sha256:42342791e96e430e4263f565eb06e3c405aac168794630f9a285ce8365642b8b
 size 25192592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:261843b99f6f325448c2ccaafb6e76e6baa5de976d68755a1f1f6eca2825d664
+oid sha256:a2ae8d1ee21a9d43016e79b18856557e3e79fda42bc2044f636231df47db5b51
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f84b7eed8ce383f213fa2c01c69e8fe6d926bcb9bee31ed27ce8dad8d9e48e50
+oid sha256:8ac9ef8a8d750dd06f1b2f32aa7dc4ccd0792acf7e63e2006163d178a7597fee
 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": 4.367871284484863,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.03714020427112349,
+  "best_metric": 4.013300895690918,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.07428040854224698,
   "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": 73.97,
       "eval_steps_per_second": 36.985,
       "step": 10
+    },
+    {
+      "epoch": 0.04456824512534819,
+      "grad_norm": 67.70091247558594,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 17.368,
+      "step": 12
+    },
+    {
+      "epoch": 0.055710306406685235,
+      "grad_norm": 54.72442626953125,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 16.9793,
+      "step": 15
+    },
+    {
+      "epoch": 0.055710306406685235,
+      "eval_loss": 4.158687591552734,
+      "eval_runtime": 1.6037,
+      "eval_samples_per_second": 71.087,
+      "eval_steps_per_second": 35.543,
+      "step": 15
+    },
+    {
+      "epoch": 0.06685236768802229,
+      "grad_norm": 56.00122833251953,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 16.5656,
+      "step": 18
+    },
+    {
+      "epoch": 0.07428040854224698,
+      "eval_loss": 4.013300895690918,
+      "eval_runtime": 1.5399,
+      "eval_samples_per_second": 74.033,
+      "eval_steps_per_second": 37.016,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 177003319787520.0,
+  "total_flos": 354006639575040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null