Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:385bc070c7ce28ba0cf03262076b4e2682302370d8f8ff694a25b245b4ed03fb
+oid sha256:9a5b814abbc21efff7481dc0b1e145390a3c2cf5ffcfc904fc7cbc1e2d23496e
 size 32856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:803a1400f3c84076aa31f64cfa7f6512a3df34f873ef6754fc70fd1af5c0c176
+oid sha256:df7dde40d6a3b70a9ae7c0c476ac801cb1e7f95114f5f7fac636737126eb9ee6
 size 71358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df8c6fc31ac199e6c243ffe062905a7862052130540b4f8afa1589a29fe97b6d
+oid sha256:bd53346fd5a654d3e32df025210c49ec943f00f49e54c4d7d1fb40b5ae52d930
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.071589469909668,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.03262642740619902,
+  "best_metric": 11.055357933044434,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.06525285481239804,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 164.528,
       "eval_steps_per_second": 82.264,
       "step": 10
+    },
+    {
+      "epoch": 0.03588907014681892,
+      "grad_norm": 0.9465475082397461,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 44.2657,
+      "step": 11
+    },
+    {
+      "epoch": 0.03915171288743882,
+      "grad_norm": 0.8892057538032532,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 44.2746,
+      "step": 12
+    },
+    {
+      "epoch": 0.04241435562805873,
+      "grad_norm": 0.8875570893287659,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 44.2504,
+      "step": 13
+    },
+    {
+      "epoch": 0.04567699836867863,
+      "grad_norm": 0.9216701984405518,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 44.2465,
+      "step": 14
+    },
+    {
+      "epoch": 0.048939641109298535,
+      "grad_norm": 0.8484591841697693,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 44.2617,
+      "step": 15
+    },
+    {
+      "epoch": 0.048939641109298535,
+      "eval_loss": 11.059526443481445,
+      "eval_runtime": 0.7845,
+      "eval_samples_per_second": 165.72,
+      "eval_steps_per_second": 82.86,
+      "step": 15
+    },
+    {
+      "epoch": 0.052202283849918436,
+      "grad_norm": 0.9152474999427795,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 44.241,
+      "step": 16
+    },
+    {
+      "epoch": 0.05546492659053834,
+      "grad_norm": 0.9288038611412048,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 44.2124,
+      "step": 17
+    },
+    {
+      "epoch": 0.05872756933115824,
+      "grad_norm": 0.9213078618049622,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 44.2012,
+      "step": 18
+    },
+    {
+      "epoch": 0.06199021207177814,
+      "grad_norm": 0.9989335536956787,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 44.2164,
+      "step": 19
+    },
+    {
+      "epoch": 0.06525285481239804,
+      "grad_norm": 0.830315887928009,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 44.2418,
+      "step": 20
+    },
+    {
+      "epoch": 0.06525285481239804,
+      "eval_loss": 11.055357933044434,
+      "eval_runtime": 0.7665,
+      "eval_samples_per_second": 169.595,
+      "eval_steps_per_second": 84.797,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8218214400.0,
+  "total_flos": 16623206400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null