Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c38eb605f63f62f37f440503f26ac37494823027c2623fc8954b14685eecff9
+oid sha256:8942b30b7801fa39924f99386c0f8f81e3167dcb9e1e21e493ac50f8ef2b05f5
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d8ee7c1cb5ad4fc5cd8cb9174a9ec619b56e094499fea0b58f145ece086cce4
+oid sha256:519d255b6d1962cf798b480dd768a8e95da7a321a3144a8da503d4d43c9c351f
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c8948e82cff156caa3992a032a25840a30041125922cf70845e384ef550b87d
+oid sha256:7a0d1a7e1c5a5fc1f229f7d0941cfdfae6fb887a05c5774dcd6073add989f360
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16d69ac2beb8e330f34449ba996c50f5a61dd8a9dd66a6eb15738df4da44cca1
+oid sha256:fd4836ddf60b44e58a6b1c94aa6a6c90a55c6b9d3781b50bd68866141db98eb6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.325153350830078,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.028425241614553724,
+  "epoch": 0.05685048322910745,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 15.749,
       "eval_steps_per_second": 3.953,
       "step": 50
+    },
+    {
+      "epoch": 0.03411028993746447,
+      "grad_norm": 1.899110198020935,
+      "learning_rate": 0.00020375153312650207,
+      "loss": 2.1988,
+      "step": 60
+    },
+    {
+      "epoch": 0.039795338260375214,
+      "grad_norm": 2.418156385421753,
+      "learning_rate": 0.00020300734301164017,
+      "loss": 1.939,
+      "step": 70
+    },
+    {
+      "epoch": 0.04548038658328596,
+      "grad_norm": 3.028864860534668,
+      "learning_rate": 0.00020177105527484818,
+      "loss": 1.9992,
+      "step": 80
+    },
+    {
+      "epoch": 0.051165434906196704,
+      "grad_norm": 4.271291255950928,
+      "learning_rate": 0.00020004869298570854,
+      "loss": 1.8298,
+      "step": 90
+    },
+    {
+      "epoch": 0.05685048322910745,
+      "grad_norm": 12.00307846069336,
+      "learning_rate": 0.00019784864732016265,
+      "loss": 2.0342,
+      "step": 100
+    },
+    {
+      "epoch": 0.05685048322910745,
+      "eval_loss": 2.5892810821533203,
+      "eval_runtime": 47.1934,
+      "eval_samples_per_second": 15.701,
+      "eval_steps_per_second": 3.941,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -72,7 +115,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9711056163176448.0,
+  "total_flos": 1.9422112326352896e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null