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:a7ab37ae96312b6de3105f73994327c8daba6310ba0749ac451c169168f93aac
+oid sha256:8dc501f71775007b603f124d508ecf0b7843814c19edfbb1c93ad0ebdd949208
 size 28351000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e107cd94a1a6a221afd3bf79c2f348d23e4c48413144c035d6f351a52ba9cb4c
+oid sha256:4992cd2e4dc1d9898cc42f9a345d34456d763cc09a5e11b27b41af37ff7a39dc
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5384c868ad4f5eba08060c410e7ba96c949c8f1932d335231a37a2203cd8d3d8
+oid sha256:f1c42c5533b631e30616c09bafafff6d5dd44c37f3ea17757c3363a8fc82a396
 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": 1.7785707712173462,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00014421118285617458,
+  "best_metric": 1.5233994722366333,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.00028842236571234917,
   "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": 7.965,
       "eval_steps_per_second": 3.982,
       "step": 10
+    },
+    {
+      "epoch": 0.00015863230114179205,
+      "grad_norm": 6.472969055175781,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 6.2931,
+      "step": 11
+    },
+    {
+      "epoch": 0.0001730534194274095,
+      "grad_norm": 7.8940019607543945,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 6.2547,
+      "step": 12
+    },
+    {
+      "epoch": 0.00018747453771302696,
+      "grad_norm": 5.983705043792725,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 6.1572,
+      "step": 13
+    },
+    {
+      "epoch": 0.0002018956559986444,
+      "grad_norm": 8.07612133026123,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 7.1022,
+      "step": 14
+    },
+    {
+      "epoch": 0.00021631677428426188,
+      "grad_norm": 8.90300464630127,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 8.0417,
+      "step": 15
+    },
+    {
+      "epoch": 0.00021631677428426188,
+      "eval_loss": 1.5895220041275024,
+      "eval_runtime": 3680.7157,
+      "eval_samples_per_second": 7.932,
+      "eval_steps_per_second": 3.966,
+      "step": 15
+    },
+    {
+      "epoch": 0.00023073789256987932,
+      "grad_norm": 8.367533683776855,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 7.8652,
+      "step": 16
+    },
+    {
+      "epoch": 0.0002451590108554968,
+      "grad_norm": 8.038274765014648,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 5.8632,
+      "step": 17
+    },
+    {
+      "epoch": 0.00025958012914111423,
+      "grad_norm": 7.587454795837402,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 5.6483,
+      "step": 18
+    },
+    {
+      "epoch": 0.0002740012474267317,
+      "grad_norm": 7.905844688415527,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 6.3027,
+      "step": 19
+    },
+    {
+      "epoch": 0.00028842236571234917,
+      "grad_norm": 7.693328380584717,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 6.7746,
+      "step": 20
+    },
+    {
+      "epoch": 0.00028842236571234917,
+      "eval_loss": 1.5233994722366333,
+      "eval_runtime": 4086.5435,
+      "eval_samples_per_second": 7.145,
+      "eval_steps_per_second": 3.572,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 298765642629120.0,
+  "total_flos": 597531285258240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null