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:f8c4968c672670a06883e83bd5392eae53f5a037c822904fa009b8b4372a9507
+oid sha256:a76e626eeeaf2317394fd5a3e58f41daf9b53b58ca780a8dbe65869184a4c539
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b259ba46e7099a298017da5718c8823f5c8ef2c0ac895cd6dd97e80cb05d8078
+oid sha256:7c2813182a829d4dc6e4a5fdb1889f6f7568ef288c2d64468c7b00213b0e2e5b
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e336ffb4f2385fe7817a79ed4d3cfcc71e6b65eaf2fdf9bb2447eedac0e09f6
+oid sha256:6bfe317d44b8f3bf2eb130aa26c2579199f2fbb7a32f4bcba4bfcd17b18d14b2
 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": 1.1928067207336426,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.008487163165711862,
+  "best_metric": 1.1751959323883057,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.012730744748567792,
   "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": 7.682,
       "eval_steps_per_second": 3.845,
       "step": 20
+    },
+    {
+      "epoch": 0.008911521323997454,
+      "grad_norm": 0.5210100412368774,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.1578,
+      "step": 21
+    },
+    {
+      "epoch": 0.010184595798854232,
+      "grad_norm": 0.5522451996803284,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.1488,
+      "step": 24
+    },
+    {
+      "epoch": 0.010608953957139827,
+      "eval_loss": 1.1779961585998535,
+      "eval_runtime": 129.2539,
+      "eval_samples_per_second": 7.683,
+      "eval_steps_per_second": 3.845,
+      "step": 25
+    },
+    {
+      "epoch": 0.011457670273711012,
+      "grad_norm": 0.5235723853111267,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.1235,
+      "step": 27
+    },
+    {
+      "epoch": 0.012730744748567792,
+      "grad_norm": 0.5206447243690491,
+      "learning_rate": 0.0,
+      "loss": 1.0994,
+      "step": 30
+    },
+    {
+      "epoch": 0.012730744748567792,
+      "eval_loss": 1.1751959323883057,
+      "eval_runtime": 129.2843,
+      "eval_samples_per_second": 7.681,
+      "eval_steps_per_second": 3.844,
+      "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": 7511608746049536.0,
+  "total_flos": 1.1221045163851776e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null