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:e987a4c2f37f41f0bd87554d870522b144aded5174289142e8b65970c83f69ab
+oid sha256:e19fcb29b5d7ab4662b15b63d4a81edf9d856b2bbabf16b366e4c7c53d9d907f
 size 209760536

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d05d75b0818cab54901e11506514a11dee9d73a66dafeca591bb5c9abc676503
+oid sha256:041e9da0826e45c3642ed1a83ba3705255e323cf9b13fbc44c9d7bdd5241f264
 size 419700154

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d1b8821978c7450bd2cb49e068182933549eb330933b29022697a95533c47a4
+oid sha256:fd0556fd141e38b6c049be180b325f90c359cc0dc60bd66e562a406dcc3480a8
 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": 1.3349263668060303,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0005195344970906068,
+  "best_metric": 1.0497976541519165,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0010390689941812137,
   "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": 3.184,
       "eval_steps_per_second": 1.592,
       "step": 10
+    },
+    {
+      "epoch": 0.0006234413965087282,
+      "grad_norm": 1.9805951118469238,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 5.1102,
+      "step": 12
+    },
+    {
+      "epoch": 0.0007793017456359103,
+      "grad_norm": 1.0474853515625,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 4.9768,
+      "step": 15
+    },
+    {
+      "epoch": 0.0007793017456359103,
+      "eval_loss": 1.1523114442825317,
+      "eval_runtime": 2547.2055,
+      "eval_samples_per_second": 3.182,
+      "eval_steps_per_second": 1.591,
+      "step": 15
+    },
+    {
+      "epoch": 0.0009351620947630922,
+      "grad_norm": 0.9892725348472595,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 4.5857,
+      "step": 18
+    },
+    {
+      "epoch": 0.0010390689941812137,
+      "eval_loss": 1.0497976541519165,
+      "eval_runtime": 2546.9723,
+      "eval_samples_per_second": 3.182,
+      "eval_steps_per_second": 1.591,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.131756329631744e+16,
+  "total_flos": 2.310669172998144e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null