Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e011658e707b037c502f22c3d75078b2c42b9056c8cb99e6cba26e1092533a78
+oid sha256:fbd21d5116765904cf935c8689bdef56b87b540b4dac2216ce10eeef9c46c355
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2abd7c6407979dc3bb6d6be963ee2bbae91fad2576a4c2abbad56374d061cf16
+oid sha256:af4cdc086c439127c9de03d2d5f8b84b1939ec72983b8e08a641dd7325dffb58
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e52247e9e681d82939fcf97817f493c54cbec08ed9d356bb0e512a6579a0498f
+oid sha256:8ea6603682b38b3b1ef562d100c6a596ce7f2e69662e8ac88db01758f4164624
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.7000869512557983,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0016875856977112118,
+  "best_metric": 1.6812231540679932,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.002109482122139015,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 7.666,
       "eval_steps_per_second": 3.833,
       "step": 20
+    },
+    {
+      "epoch": 0.0017719649825967724,
+      "grad_norm": 2.9439198970794678,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.8969,
+      "step": 21
+    },
+    {
+      "epoch": 0.0018563442674823332,
+      "grad_norm": 2.2414660453796387,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.9756,
+      "step": 22
+    },
+    {
+      "epoch": 0.0019407235523678937,
+      "grad_norm": 1.903572678565979,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.321,
+      "step": 23
+    },
+    {
+      "epoch": 0.0020251028372534545,
+      "grad_norm": 3.2975940704345703,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.421,
+      "step": 24
+    },
+    {
+      "epoch": 0.002109482122139015,
+      "grad_norm": 2.134070873260498,
+      "learning_rate": 0.0,
+      "loss": 1.6586,
+      "step": 25
+    },
+    {
+      "epoch": 0.002109482122139015,
+      "eval_loss": 1.6812231540679932,
+      "eval_runtime": 658.7929,
+      "eval_samples_per_second": 7.574,
+      "eval_steps_per_second": 3.787,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 648596517027840.0,
+  "total_flos": 818853102747648.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null