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:cf6f5f3dbea8b8176bcc9852bb0bf1beaee40807ac5bed55df3c1b775e91b6d1
+oid sha256:ab00d460ae7c27877f2abf9d4ce28c3199cacee465382f7f31cd2fd91fc6c6f1
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12cdec3a0e616afbfd6eb1c8e1597029f22292b3a9ba4679df6ec6eef9c6b379
+oid sha256:97bf462ef9f2760fe9ae06cc0022897a7ed8b6d36b98f4a52d85690b0ab28627
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89699f0b3577d72b5b6de2d71d0ef276004d62fe3404dae5160b3a000e6359ef
+oid sha256:bf3ceebf978e809865452756b511eb6528c30b1e4c0884e35cd933a532901f35
 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": 2.2870724201202393,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.025023459493274947,
+  "best_metric": 2.1618664264678955,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.03753518923991242,
   "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": 19.006,
       "eval_steps_per_second": 9.531,
       "step": 20
+    },
+    {
+      "epoch": 0.026274632467938694,
+      "grad_norm": 1.7266687154769897,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.2876,
+      "step": 21
+    },
+    {
+      "epoch": 0.030028151391929936,
+      "grad_norm": 2.26924467086792,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.247,
+      "step": 24
+    },
+    {
+      "epoch": 0.03127932436659368,
+      "eval_loss": 2.1842119693756104,
+      "eval_runtime": 17.8552,
+      "eval_samples_per_second": 18.874,
+      "eval_steps_per_second": 9.465,
+      "step": 25
+    },
+    {
+      "epoch": 0.03378167031592118,
+      "grad_norm": 1.735610008239746,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.289,
+      "step": 27
+    },
+    {
+      "epoch": 0.03753518923991242,
+      "grad_norm": 2.1275014877319336,
+      "learning_rate": 0.0,
+      "loss": 2.3015,
+      "step": 30
+    },
+    {
+      "epoch": 0.03753518923991242,
+      "eval_loss": 2.1618664264678955,
+      "eval_runtime": 17.7533,
+      "eval_samples_per_second": 18.982,
+      "eval_steps_per_second": 9.519,
+      "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": 6990386933268480.0,
+  "total_flos": 1.048558039990272e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null