Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ed28385453b1df10c0ba23c10accb3d64ca84b8fc0c76a4d9f360b6d16b5b29
+oid sha256:8d12397d45147bac9e5e6fdae31237e485ac823e0b718654b6c856755fbf1518
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92aef4441e5404668db0b345509d5443345f836801556d588446321513ca9d7b
+oid sha256:02751c23a12d8f9f83a24bf49269fffc7f86ddea9e867a9ef5603c266c38216e
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37233aa18e991825c5f43c12b9134d038265cc954eb63a00df5c7b19a3778eff
+oid sha256:2334bb0640575dd250ddc034f0866b4a4968457b2c304412fc5bfe7daa198c97
 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": 1.1316041946411133,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0005022475578212501,
+  "best_metric": 0.8780689239501953,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0010044951156425001,
   "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": 6.474,
       "eval_steps_per_second": 3.237,
       "step": 10
+    },
+    {
+      "epoch": 0.0006026970693855001,
+      "grad_norm": 1.035812258720398,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 4.4551,
+      "step": 12
+    },
+    {
+      "epoch": 0.0007533713367318751,
+      "grad_norm": 1.1360167264938354,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 3.4879,
+      "step": 15
+    },
+    {
+      "epoch": 0.0007533713367318751,
+      "eval_loss": 0.9610100984573364,
+      "eval_runtime": 1295.3043,
+      "eval_samples_per_second": 6.473,
+      "eval_steps_per_second": 3.236,
+      "step": 15
+    },
+    {
+      "epoch": 0.0009040456040782501,
+      "grad_norm": 1.0687752962112427,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.783,
+      "step": 18
+    },
+    {
+      "epoch": 0.0010044951156425001,
+      "eval_loss": 0.8780689239501953,
+      "eval_runtime": 1295.1323,
+      "eval_samples_per_second": 6.473,
+      "eval_steps_per_second": 3.237,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3085503276515328.0,
+  "total_flos": 6032849689903104.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null