Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c77bd252404343d59fa47e11d87b9d7494bdc0ce74fb6444c47871aca36d1f6
+oid sha256:e566ffe60098290503a9ade5d78567948f2deaadfc78dc21f93166a51762f317
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65cf1d6e092f1f2385667e8efd41a0118af57063735c60905ff65cddd11c6b83
+oid sha256:570d269b8daf52937ab82de45e6ccea0b05f7c7f282daecde87024f41199f500
 size 46057082

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:597c452dbb6d2e2055a44445aa9e337aa4085eacd11fcbc7213a5eb6f6055867
+oid sha256:63c9cc0f3c04b2c00adeda1f5d60d230e61e99e3404c96ea1e859f8d4e96fa90
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7803647d52fbd7429a283dc695ba7cf653ff890c06d5c50f67d0a09610438889
+oid sha256:23b27ab0ae2b9af6f3d4c84cdaf8b0fc887acf71f8f726b270a3bce2845000a9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.617271900177002,
   "best_model_checkpoint": "miner_id_24/checkpoint-80",
-  "epoch": 0.022590893046240734,
+  "epoch": 0.025414754677020826,
   "eval_steps": 10,
-  "global_step": 80,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -639,6 +639,84 @@
       "eval_samples_per_second": 5.528,
       "eval_steps_per_second": 5.528,
       "step": 80
+    },
+    {
+      "epoch": 0.022873279209318743,
+      "grad_norm": 0.908437192440033,
+      "learning_rate": 0.0001898168561213419,
+      "loss": 1.9605,
+      "step": 81
+    },
+    {
+      "epoch": 0.02315566537239675,
+      "grad_norm": 0.8091934323310852,
+      "learning_rate": 0.0001895331334332753,
+      "loss": 1.5024,
+      "step": 82
+    },
+    {
+      "epoch": 0.023438051535474763,
+      "grad_norm": 1.5132545232772827,
+      "learning_rate": 0.0001892457303887706,
+      "loss": 1.0696,
+      "step": 83
+    },
+    {
+      "epoch": 0.02372043769855277,
+      "grad_norm": 1.2116718292236328,
+      "learning_rate": 0.0001889546588018412,
+      "loss": 1.7115,
+      "step": 84
+    },
+    {
+      "epoch": 0.02400282386163078,
+      "grad_norm": 0.8074257969856262,
+      "learning_rate": 0.00018865993063730004,
+      "loss": 2.7291,
+      "step": 85
+    },
+    {
+      "epoch": 0.02428521002470879,
+      "grad_norm": 1.1341824531555176,
+      "learning_rate": 0.00018836155801026753,
+      "loss": 1.8977,
+      "step": 86
+    },
+    {
+      "epoch": 0.024567596187786797,
+      "grad_norm": 1.9230746030807495,
+      "learning_rate": 0.0001880595531856738,
+      "loss": 1.5919,
+      "step": 87
+    },
+    {
+      "epoch": 0.02484998235086481,
+      "grad_norm": 0.9849350452423096,
+      "learning_rate": 0.00018775392857775432,
+      "loss": 2.8404,
+      "step": 88
+    },
+    {
+      "epoch": 0.025132368513942818,
+      "grad_norm": 2.4642324447631836,
+      "learning_rate": 0.00018744469674953956,
+      "loss": 1.2864,
+      "step": 89
+    },
+    {
+      "epoch": 0.025414754677020826,
+      "grad_norm": 1.7967941761016846,
+      "learning_rate": 0.00018713187041233896,
+      "loss": 1.8635,
+      "step": 90
+    },
+    {
+      "epoch": 0.025414754677020826,
+      "eval_loss": 1.6206018924713135,
+      "eval_runtime": 134.6331,
+      "eval_samples_per_second": 5.541,
+      "eval_steps_per_second": 5.541,
+      "step": 90
     }
   ],
   "logging_steps": 1,
@@ -653,7 +731,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -667,7 +745,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7830428681502720.0,
+  "total_flos": 8809232266690560.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null