Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e65d73ee5700e18382279e7bf5e39729a8ad001d8ce0a6b438a9d61c10a32b7
+oid sha256:55d905c68a0a631af4230eb3cd3b82332cd23a6999a71ba8bf0a91a17595a38b
 size 188784440

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e82af5b637f3ca77854d9039d5481f2f2d4a2911b6b5157df1a26fd9dc677f8
+oid sha256:836b13b925bce873a0c2e2442f78469b0beb4cbed9f6af3161f5166bfd479f85
 size 377730170

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:041ab80aab1926234a1817a2e6683af490412f19394e52af1cc660a175db20f5
+oid sha256:ab113dd6b34c5e40abe76cb5c9662714bc0e4a97f5b37d5134da6a412a688812
 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": 1.3834524154663086,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0015083240634250269,
+  "best_metric": 1.3420805931091309,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0022624860951375404,
   "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": 3.483,
       "eval_steps_per_second": 1.741,
       "step": 20
+    },
+    {
+      "epoch": 0.0015837402665962782,
+      "grad_norm": 1.5678207874298096,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 5.5249,
+      "step": 21
+    },
+    {
+      "epoch": 0.0018099888761100322,
+      "grad_norm": 1.3521682024002075,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 5.4037,
+      "step": 24
+    },
+    {
+      "epoch": 0.0018854050792812835,
+      "eval_loss": 1.3494175672531128,
+      "eval_runtime": 1603.9666,
+      "eval_samples_per_second": 3.481,
+      "eval_steps_per_second": 1.741,
+      "step": 25
+    },
+    {
+      "epoch": 0.002036237485623786,
+      "grad_norm": 1.3864684104919434,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 5.4599,
+      "step": 27
+    },
+    {
+      "epoch": 0.0022624860951375404,
+      "grad_norm": 1.4341297149658203,
+      "learning_rate": 0.0,
+      "loss": 5.2536,
+      "step": 30
+    },
+    {
+      "epoch": 0.0022624860951375404,
+      "eval_loss": 1.3420805931091309,
+      "eval_runtime": 1606.6325,
+      "eval_samples_per_second": 3.476,
+      "eval_steps_per_second": 1.738,
+      "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": 2.015315512786944e+16,
+  "total_flos": 3.044412795912192e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null