Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ba7c4a5b7cbd2efca1a00977aa6bf02a04b45cec11057c2b133c05fc4000ac9
+oid sha256:93e8d0b8582cdf105cff0d5429efff299d8199f7846a96e84ab63a4432c1cf22
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb7c543e51fda7b323244464e14abd59d26637348d81eeade8fad77fdc016598
+oid sha256:e863557a450d56812b1a43294e92952a4ff8180e74b03bb0f144d172028a746e
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8d0ca5f94c74be21f7e258f478e4f1bcf339ab697a95d852a0fd9b800d39d6b
+oid sha256:c06cc185129710fbc4aefbd4aecab61cbe55d72872505d4a12d4f40835976880
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.7654892206192017,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.003772161448509996,
+  "best_metric": 1.7209789752960205,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.005658242172764994,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 10.173,
       "eval_steps_per_second": 5.089,
       "step": 20
+    },
+    {
+      "epoch": 0.003960769520935496,
+      "grad_norm": 12.274673461914062,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 7.4814,
+      "step": 21
+    },
+    {
+      "epoch": 0.004526593738211996,
+      "grad_norm": 7.784275531768799,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 7.0215,
+      "step": 24
+    },
+    {
+      "epoch": 0.004715201810637495,
+      "eval_loss": 1.7311782836914062,
+      "eval_runtime": 219.4743,
+      "eval_samples_per_second": 10.174,
+      "eval_steps_per_second": 5.089,
+      "step": 25
+    },
+    {
+      "epoch": 0.005092417955488495,
+      "grad_norm": 9.455221176147461,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 7.0132,
+      "step": 27
+    },
+    {
+      "epoch": 0.005658242172764994,
+      "grad_norm": 8.590954780578613,
+      "learning_rate": 0.0,
+      "loss": 6.7812,
+      "step": 30
+    },
+    {
+      "epoch": 0.005658242172764994,
+      "eval_loss": 1.7209789752960205,
+      "eval_runtime": 219.4545,
+      "eval_samples_per_second": 10.175,
+      "eval_steps_per_second": 5.09,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7031294986813440.0,
+  "total_flos": 1.054694248022016e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null