Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddfe679c7453b5a128aaa5f137af1a8a9dd5bba14eef7a3d3e34849858646657
+oid sha256:c69cb9afb87611d99fbed2d4d80552405eda0f7e0de1c5109b2a624b081a734e
 size 1342238560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2cb0400a09f8bdd8c594398610fd85e8d48dab530894c711808c4a3d6138ccf
+oid sha256:0347c21690a44cfaee843cce0d9aa1de1ea2595f8a0414542f0b4df760665180
 size 682101396

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d6be1ee61e986469888561dce8de3f492add76f3bf5cc94c3bd31234e25cafc
+oid sha256:161a33e84b4c64fa9febe6f657339b8da5f141eb4edce251ae9e5a98bceac60f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:691263e55c7bb34b6e090bd89cf079f362100d7bd758be475bd3e7091c1a4ed6
+oid sha256:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.035220917314291,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.021090372245070127,
+  "best_metric": 0.005579269025474787,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.042180744490140254,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -93,6 +93,84 @@
       "eval_samples_per_second": 2.823,
       "eval_steps_per_second": 1.412,
       "step": 100
+    },
+    {
+      "epoch": 0.02319940946957714,
+      "grad_norm": 62.70212173461914,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.0896,
+      "step": 110
+    },
+    {
+      "epoch": 0.02530844669408415,
+      "grad_norm": 0.842799723148346,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.1349,
+      "step": 120
+    },
+    {
+      "epoch": 0.027417483918591164,
+      "grad_norm": 166.96304321289062,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.2701,
+      "step": 130
+    },
+    {
+      "epoch": 0.029526521143098176,
+      "grad_norm": 17.788463592529297,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.1667,
+      "step": 140
+    },
+    {
+      "epoch": 0.03163555836760519,
+      "grad_norm": 1.1575299501419067,
+      "learning_rate": 5e-05,
+      "loss": 0.1699,
+      "step": 150
+    },
+    {
+      "epoch": 0.0337445955921122,
+      "grad_norm": 12.75675106048584,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0575,
+      "step": 160
+    },
+    {
+      "epoch": 0.03585363281661921,
+      "grad_norm": 0.6250290870666504,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0638,
+      "step": 170
+    },
+    {
+      "epoch": 0.037962670041126224,
+      "grad_norm": 0.22166423499584198,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0095,
+      "step": 180
+    },
+    {
+      "epoch": 0.040071707265633236,
+      "grad_norm": 0.012423542328178883,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.013,
+      "step": 190
+    },
+    {
+      "epoch": 0.042180744490140254,
+      "grad_norm": 0.02760171703994274,
+      "learning_rate": 0.0,
+      "loss": 0.063,
+      "step": 200
+    },
+    {
+      "epoch": 0.042180744490140254,
+      "eval_loss": 0.005579269025474787,
+      "eval_runtime": 707.9758,
+      "eval_samples_per_second": 2.821,
+      "eval_steps_per_second": 1.411,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -116,12 +194,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.31992081563648e+16,
+  "total_flos": 1.463984163127296e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null