Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:541594b1bb3783158067e6bf3915f669c2b137c13af1b19ca6c2b936769eeecd
+oid sha256:207a048a38876070aa53dbad27e69a8474c9620c8fd75fea6e4a106b7a399c33
 size 249439848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d70d40ea697381e2e252e1a76031dca19ca270c2ea788967dae5637b129cf8e
+oid sha256:41eff9f2d39685ef6ea621cc0c4b5dcbe2da2df747bd1ef1f85bed9f1301a0aa
 size 499202402

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37ff7ffa3daee9d7bde499f50887e0f48f8d48e3b4d50d89012500add55768a6
+oid sha256:49984bb1acbeaf71cf255dc3c268cdc658d49a0e97d60a0ed1515654fc6e54ac
 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": 2.026219367980957,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0021158423697434543,
+  "best_metric": 1.8435406684875488,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.004231684739486909,
   "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": 4.022,
       "eval_steps_per_second": 2.011,
       "step": 10
+    },
+    {
+      "epoch": 0.0025390108436921448,
+      "grad_norm": 0.6258363723754883,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 2.0216,
+      "step": 12
+    },
+    {
+      "epoch": 0.003173763554615181,
+      "grad_norm": 0.4679494798183441,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 1.8766,
+      "step": 15
+    },
+    {
+      "epoch": 0.003173763554615181,
+      "eval_loss": 1.9061535596847534,
+      "eval_runtime": 494.7695,
+      "eval_samples_per_second": 4.022,
+      "eval_steps_per_second": 2.011,
+      "step": 15
+    },
+    {
+      "epoch": 0.0038085162655382174,
+      "grad_norm": 0.48406657576560974,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.9025,
+      "step": 18
+    },
+    {
+      "epoch": 0.004231684739486909,
+      "eval_loss": 1.8435406684875488,
+      "eval_runtime": 494.7878,
+      "eval_samples_per_second": 4.022,
+      "eval_steps_per_second": 2.011,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.223121419894784e+16,
+  "total_flos": 2.380128168443904e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null