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:dcd87195ea42d3c2231e613d3ad1e797b75e86d0315064051b8643058ebfea1f
+oid sha256:60f49b40c81c858ad6522f0cf7748f16b894c554ba988689e3f9c9f073abb0a3
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ac4a3e1d0206cf9337f269274d4f18d07b8163db6c78c39f35bbd63a8213647
+oid sha256:6e9d18b1207cc7fd41255fac17ecd41ef9a5f8decc55007c83cdefd24ec0094b
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec8cb72c21dfc752948b51ccf08f696191881d8612dad8f6316ef83eebfa4e41
+oid sha256:857a2a586ed608f83bf352a986492eec050149ec0d039c66ced3a37fd23f88d8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1339696645736694,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.015717092337917484,
+  "best_metric": 1.0949171781539917,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.023575638506876228,
   "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": 6.821,
       "eval_steps_per_second": 1.705,
       "step": 20
+    },
+    {
+      "epoch": 0.016502946954813358,
+      "grad_norm": 0.6046103239059448,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.0452,
+      "step": 21
+    },
+    {
+      "epoch": 0.018860510805500982,
+      "grad_norm": 0.5752077698707581,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.112,
+      "step": 24
+    },
+    {
+      "epoch": 0.019646365422396856,
+      "eval_loss": 1.1043939590454102,
+      "eval_runtime": 158.6594,
+      "eval_samples_per_second": 6.757,
+      "eval_steps_per_second": 1.689,
+      "step": 25
+    },
+    {
+      "epoch": 0.021218074656188603,
+      "grad_norm": 0.6900656223297119,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.0785,
+      "step": 27
+    },
+    {
+      "epoch": 0.023575638506876228,
+      "grad_norm": 0.8871800303459167,
+      "learning_rate": 0.0,
+      "loss": 1.0869,
+      "step": 30
+    },
+    {
+      "epoch": 0.023575638506876228,
+      "eval_loss": 1.0949171781539917,
+      "eval_runtime": 157.1684,
+      "eval_samples_per_second": 6.821,
+      "eval_steps_per_second": 1.705,
+      "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": 2.207114668592333e+16,
+  "total_flos": 2.949001952152781e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null