Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c359efedc812d1fd8b721e589ab1b579033ae969bbf173988507f9a5fe20bf4
+oid sha256:b9bedfd24a8550fc3f47b1a863d0278d46a101c066d6ff702924917a83503e01
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30dd8213f9fc66b6aad28b223e481e2444828d09d3390adcafe3d65162f38a67
+oid sha256:d28e2cd47bbc9ba3abddc9581e2843a642b023f70433ff5369e7efbdf468ee7e
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5288ed9323916daf49e9e619b5ce81ab40c19e01021e3ee0c12210ac8bab7de
+oid sha256:4542ee77b862586921f712605c9da4a157f7c6fb74687d0b6cef8d69e7a87363
 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": 10.379790306091309,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.05319148936170213,
+  "best_metric": 10.379435539245605,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0797872340425532,
   "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": 162.469,
       "eval_steps_per_second": 81.745,
       "step": 20
+    },
+    {
+      "epoch": 0.05585106382978723,
+      "grad_norm": 0.03025800548493862,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 10.3818,
+      "step": 21
+    },
+    {
+      "epoch": 0.06382978723404255,
+      "grad_norm": 0.021211761981248856,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 10.3791,
+      "step": 24
+    },
+    {
+      "epoch": 0.06648936170212766,
+      "eval_loss": 10.379490852355957,
+      "eval_runtime": 0.9852,
+      "eval_samples_per_second": 161.395,
+      "eval_steps_per_second": 81.205,
+      "step": 25
+    },
+    {
+      "epoch": 0.07180851063829788,
+      "grad_norm": 0.04403116926550865,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 10.3816,
+      "step": 27
+    },
+    {
+      "epoch": 0.0797872340425532,
+      "grad_norm": 0.04409431666135788,
+      "learning_rate": 0.0,
+      "loss": 10.3788,
+      "step": 30
+    },
+    {
+      "epoch": 0.0797872340425532,
+      "eval_loss": 10.379435539245605,
+      "eval_runtime": 0.9827,
+      "eval_samples_per_second": 161.792,
+      "eval_steps_per_second": 81.405,
+      "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": 634167164928.0,
+  "total_flos": 934906232832.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null