Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91a3b29856143aecc3a1fd76b949ca0dd86fb486460a8825bb04011135aea6da
+oid sha256:e54408fb2a33f5c91595c277d43af9ca7442d78555f6734133f909076eb5ee0b
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efdd3a8541cf52ef664e6919d0834665f7aee03a1cc90078eecd7f50255b8cf0
+oid sha256:ef3fcc665ceb8166c03b90dbe8b812cc65aef67e5c4040511438f0bcec2d036b
 size 46057082

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63c9cc0f3c04b2c00adeda1f5d60d230e61e99e3404c96ea1e859f8d4e96fa90
+oid sha256:8e023d57ffc9febc8fefa58b1faee1161f6172e0c816bc8ad1dc30d22145a166
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23b27ab0ae2b9af6f3d4c84cdaf8b0fc887acf71f8f726b270a3bce2845000a9
+oid sha256:d5c84ec0ff3c8c6aa13b25568668096db118f67ce80a9fa015a625446606f15d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.602448582649231,
-  "best_model_checkpoint": "miner_id_24/checkpoint-80",
-  "epoch": 0.025414754677020826,
+  "best_metric": 1.6011497974395752,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.028238616307800918,
   "eval_steps": 10,
-  "global_step": 90,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -717,6 +717,84 @@
       "eval_samples_per_second": 5.584,
       "eval_steps_per_second": 5.584,
       "step": 90
+    },
+    {
+      "epoch": 0.025697140840098835,
+      "grad_norm": 1.4146398305892944,
+      "learning_rate": 0.00018681546242521786,
+      "loss": 1.1993,
+      "step": 91
+    },
+    {
+      "epoch": 0.025979527003176843,
+      "grad_norm": 2.2005670070648193,
+      "learning_rate": 0.00018649548579446936,
+      "loss": 1.9517,
+      "step": 92
+    },
+    {
+      "epoch": 0.026261913166254855,
+      "grad_norm": 1.241758108139038,
+      "learning_rate": 0.0001861719536730795,
+      "loss": 2.0892,
+      "step": 93
+    },
+    {
+      "epoch": 0.026544299329332863,
+      "grad_norm": 1.4617339372634888,
+      "learning_rate": 0.00018584487936018661,
+      "loss": 2.2815,
+      "step": 94
+    },
+    {
+      "epoch": 0.026826685492410872,
+      "grad_norm": 1.677581548690796,
+      "learning_rate": 0.00018551427630053463,
+      "loss": 1.75,
+      "step": 95
+    },
+    {
+      "epoch": 0.02710907165548888,
+      "grad_norm": 3.2750422954559326,
+      "learning_rate": 0.00018518015808392045,
+      "loss": 1.8473,
+      "step": 96
+    },
+    {
+      "epoch": 0.02739145781856689,
+      "grad_norm": 1.7410293817520142,
+      "learning_rate": 0.00018484253844463526,
+      "loss": 1.2498,
+      "step": 97
+    },
+    {
+      "epoch": 0.0276738439816449,
+      "grad_norm": 1.0431251525878906,
+      "learning_rate": 0.00018450143126090015,
+      "loss": 2.3196,
+      "step": 98
+    },
+    {
+      "epoch": 0.02795623014472291,
+      "grad_norm": 2.758586883544922,
+      "learning_rate": 0.00018415685055429533,
+      "loss": 1.9701,
+      "step": 99
+    },
+    {
+      "epoch": 0.028238616307800918,
+      "grad_norm": 1.7685903310775757,
+      "learning_rate": 0.00018380881048918405,
+      "loss": 1.4758,
+      "step": 100
+    },
+    {
+      "epoch": 0.028238616307800918,
+      "eval_loss": 1.6011497974395752,
+      "eval_runtime": 133.8006,
+      "eval_samples_per_second": 5.575,
+      "eval_steps_per_second": 5.575,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -731,7 +809,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -745,7 +823,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8809232266690560.0,
+  "total_flos": 9788035851878400.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null