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:a1323af51047d8fbbbd3b528f85ed404654e354c2606d6463f1e68796ebcfbf9
+oid sha256:fb2676f249729b693b4f5b1a288be4e52f0b32879178c6bf6e9471159968ea6e
 size 247944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f5167e0bb6eba45f98823fb30f732bd56f4c942b45e862a2f07f8486adb3bd3
+oid sha256:61440d5b78b9c77bbb742f07f02778ca0438d26bfe747325308e7618a63b02cb
 size 505518

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:514659fe6587e5a360c1da77a9bf3d5a140023fc4c9c6193d1463a71ec2ba65e
+oid sha256:54ccaa53d2d8ec06c1ee34cc01a5fe264fe9af0525bcf751771ab98a9dbdd66d
 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": 11.031575202941895,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.12345679012345678,
+  "best_metric": 11.018196105957031,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.18518518518518517,
   "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": 194.253,
       "eval_steps_per_second": 98.534,
       "step": 20
+    },
+    {
+      "epoch": 0.12962962962962962,
+      "grad_norm": 1.6233855485916138,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 44.1295,
+      "step": 21
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 1.518567681312561,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 44.1,
+      "step": 24
+    },
+    {
+      "epoch": 0.15432098765432098,
+      "eval_loss": 11.02023983001709,
+      "eval_runtime": 0.3468,
+      "eval_samples_per_second": 198.98,
+      "eval_steps_per_second": 100.932,
+      "step": 25
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 1.5110942125320435,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 44.0644,
+      "step": 27
+    },
+    {
+      "epoch": 0.18518518518518517,
+      "grad_norm": 1.5533232688903809,
+      "learning_rate": 0.0,
+      "loss": 44.0723,
+      "step": 30
+    },
+    {
+      "epoch": 0.18518518518518517,
+      "eval_loss": 11.018196105957031,
+      "eval_runtime": 0.3627,
+      "eval_samples_per_second": 190.225,
+      "eval_steps_per_second": 96.491,
+      "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": 415991070720.0,
+  "total_flos": 623986606080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null