Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32fc76f8d855e0d9dbe809614a0e0079dff8691cd1531c297b7959e514311b1e
+oid sha256:34873289a69d95dd03e68fee973c7b642782c3918c3b8ea959f6763c5946dea8
 size 1157746040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3122b4b0c363b7e10d4affa8d39055b7b96c812ac70c6f76b5aae46449e68487
+oid sha256:1e3ed6d9149a7bc56acca7c63d4ebf114fe924e5da3ee3affd4e0307d15ffca2
 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:db8287a4e3b9ef10f63afa9fbb14ef771e3148548ab75efa98b4ac9026c4b7f4
+oid sha256:e231c2c515a5ff10f1e544b2aa46a8eaae94bd71a11db0123cabe0d1726bb1ba
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.2476589679718018,
   "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": 5.268,
       "eval_steps_per_second": 1.317,
       "step": 50
+    },
+    {
+      "epoch": 0.010186757215619695,
+      "grad_norm": 0.7924010753631592,
+      "learning_rate": 0.00020674787920189178,
+      "loss": 1.222,
+      "step": 60
+    },
+    {
+      "epoch": 0.011884550084889643,
+      "grad_norm": 0.8740193247795105,
+      "learning_rate": 0.00020599274511475253,
+      "loss": 1.2045,
+      "step": 70
+    },
+    {
+      "epoch": 0.013582342954159592,
+      "grad_norm": 0.8409563899040222,
+      "learning_rate": 0.00020473827667594888,
+      "loss": 1.2077,
+      "step": 80
+    },
+    {
+      "epoch": 0.015280135823429542,
+      "grad_norm": 1.0255435705184937,
+      "learning_rate": 0.00020299058552961598,
+      "loss": 1.2556,
+      "step": 90
+    },
+    {
+      "epoch": 0.01697792869269949,
+      "grad_norm": 1.3903775215148926,
+      "learning_rate": 0.00020075818625134152,
+      "loss": 1.303,
+      "step": 100
+    },
+    {
+      "epoch": 0.01697792869269949,
+      "eval_loss": 1.3105939626693726,
+      "eval_runtime": 235.3286,
+      "eval_samples_per_second": 5.269,
+      "eval_steps_per_second": 1.317,
+      "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