Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60821203767823a3bb73dff7db3002d133386536e2a11a2f04116afa1d3d0392
+oid sha256:b07fd4ca4b40a1d776db5c0aca17e1347ab8fabdcfc14104b16ca78db241079a
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:062ae9e8524b7da50f29fb2ce2653452c455afa827330c31a00a1bd33d923b24
+oid sha256:61011cd3485e114ee310f579180055b42574257e7a48f0cc19d2646e57aac6b0
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e901f8113bf58f681f95b30c12afd00f5df473bbfa8c419fdec6b3a4e43830be
+oid sha256:9827acb5724dcff666ad9d8e1a99fdd806027902b7bd91dbcce7886db5462728
 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": 1.2398513555526733,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0006903574325607083,
+  "best_metric": 1.106920838356018,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0013807148651214167,
   "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": 7.24,
       "eval_steps_per_second": 3.621,
       "step": 10
+    },
+    {
+      "epoch": 0.0008284289190728499,
+      "grad_norm": 0.8861536979675293,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 1.0794,
+      "step": 12
+    },
+    {
+      "epoch": 0.0010355361488410624,
+      "grad_norm": 1.037650465965271,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 1.0982,
+      "step": 15
+    },
+    {
+      "epoch": 0.0010355361488410624,
+      "eval_loss": 1.1215226650238037,
+      "eval_runtime": 841.4678,
+      "eval_samples_per_second": 7.248,
+      "eval_steps_per_second": 3.625,
+      "step": 15
+    },
+    {
+      "epoch": 0.0012426433786092749,
+      "grad_norm": 0.8788531422615051,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.0643,
+      "step": 18
+    },
+    {
+      "epoch": 0.0013807148651214167,
+      "eval_loss": 1.106920838356018,
+      "eval_runtime": 841.147,
+      "eval_samples_per_second": 7.251,
+      "eval_steps_per_second": 3.626,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3987713405485056.0,
+  "total_flos": 7697214247796736.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null