Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94e89ed119b98ff0080a6fe6fe19747ec9992367bef66e0be2def92205eae8b1
+oid sha256:7ddb3e6b5c398523f013b1c4b951af87e2d5631f07ecc848c3dfecf228711479
 size 1157746040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:125f559630b7a6eee6b4dc4526b48f0bb5b8a36db6fda22fec945999ee653a68
+oid sha256:78abf80de248a0c0f65847789552563819cb1c754bc8844491f1f7be1277de3e
 size 588699796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71a7512092f77679e8c13fc5f80ef673e4bbff5c1358c34064ef76a87f10ce26
+oid sha256:1ccd1c6ca381034486ac9d3bd5b155e1c2fee70137075805fcdf59b77d7b2b55
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f05a07b776abc173978a0e887e7c70d773d3b63ce9e1342d6d78880c1684ac0
+oid sha256:a760ba92960f08f363394eee4df1edc2c66e6b8b22489dbac9e6aa0f5ae478e1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.2455830574035645,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.008488964346349746,
+  "epoch": 0.01697792869269949,
   "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": 5.227,
       "eval_steps_per_second": 1.307,
       "step": 50
+    },
+    {
+      "epoch": 0.010186757215619695,
+      "grad_norm": 0.7842703461647034,
+      "learning_rate": 0.0002057490971767619,
+      "loss": 1.2212,
+      "step": 60
+    },
+    {
+      "epoch": 0.011884550084889643,
+      "grad_norm": 0.8670001029968262,
+      "learning_rate": 0.00020499761108038175,
+      "loss": 1.2051,
+      "step": 70
+    },
+    {
+      "epoch": 0.013582342954159592,
+      "grad_norm": 0.8176340460777283,
+      "learning_rate": 0.00020374920287558198,
+      "loss": 1.209,
+      "step": 80
+    },
+    {
+      "epoch": 0.015280135823429542,
+      "grad_norm": 1.0117417573928833,
+      "learning_rate": 0.00020200995468164684,
+      "loss": 1.2546,
+      "step": 90
+    },
+    {
+      "epoch": 0.01697792869269949,
+      "grad_norm": 1.4239269495010376,
+      "learning_rate": 0.00019978833994094855,
+      "loss": 1.3016,
+      "step": 100
+    },
+    {
+      "epoch": 0.01697792869269949,
+      "eval_loss": 1.3394960165023804,
+      "eval_runtime": 236.5162,
+      "eval_samples_per_second": 5.243,
+      "eval_steps_per_second": 1.311,
+      "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": 1.65049251397632e+16,
+  "total_flos": 3.193703014544179e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null