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:db93db9a24c68d18fe54ecf2b5d2a454d20ca4073081276aa372b54e9e22ed7a
+oid sha256:fe3f76e6a61154286a69a8844a3db62e56420cc48d72845b1c71df7b342e3731
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92dc2d59506dec059b21359d3cdead817086bf7eae7542a04dad435c8067a143
+oid sha256:e9a84d77b792ff9d61e2db029a1abdbc4bd9a6191cc5d9b64f6954cd88aac2e6
 size 68874

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": 11.947105407714844,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.009038526720144616,
+  "best_metric": 11.946277618408203,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.013557790080216925,
   "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": 32.399,
       "eval_steps_per_second": 16.199,
       "step": 20
+    },
+    {
+      "epoch": 0.009490453056151846,
+      "grad_norm": 0.08155731111764908,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 11.9477,
+      "step": 21
+    },
+    {
+      "epoch": 0.01084623206417354,
+      "grad_norm": 0.08816022425889969,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 11.9463,
+      "step": 24
+    },
+    {
+      "epoch": 0.011298158400180771,
+      "eval_loss": 11.946414947509766,
+      "eval_runtime": 28.8235,
+      "eval_samples_per_second": 32.335,
+      "eval_steps_per_second": 16.167,
+      "step": 25
+    },
+    {
+      "epoch": 0.012202011072195233,
+      "grad_norm": 0.08092248439788818,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 11.9461,
+      "step": 27
+    },
+    {
+      "epoch": 0.013557790080216925,
+      "grad_norm": 0.08714073896408081,
+      "learning_rate": 0.0,
+      "loss": 11.9473,
+      "step": 30
+    },
+    {
+      "epoch": 0.013557790080216925,
+      "eval_loss": 11.946277618408203,
+      "eval_runtime": 28.6642,
+      "eval_samples_per_second": 32.514,
+      "eval_steps_per_second": 16.257,
+      "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": 12366249984.0,
+  "total_flos": 18455691264.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null