Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e373ceb1b303d4f632eae8678d583ae5edd85ca6db994cb3593331350657870
+oid sha256:a729f1359f85fad427f9376c806658d9005d595f64809718ef5ed4ab5751bcd6
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c042bee5f0d509a137b3981c467bac1a73cbd747e5ce53e15d3a1f3b215d4fb
+oid sha256:68f035e970bff955c4374832c929ed0f268e0b4850954eef7523af10c5a66237
 size 56088148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89d2532ec83c7ae696ead5d4adffb468726f575389e25890063e72f8c8bce5d9
+oid sha256:3ce24057a5ba39f6bb8e65b69b5d8d23e014a623d505ecfe88ab29560bdf006b
 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": 3.0200448036193848,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.03740065451145395,
+  "best_metric": 2.9981603622436523,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.04675081813931744,
   "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": 3.286,
       "eval_steps_per_second": 1.643,
       "step": 20
+    },
+    {
+      "epoch": 0.03927068723702665,
+      "grad_norm": 2.3286995887756348,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 2.697,
+      "step": 21
+    },
+    {
+      "epoch": 0.04114071996259935,
+      "grad_norm": 3.739103078842163,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 2.941,
+      "step": 22
+    },
+    {
+      "epoch": 0.043010752688172046,
+      "grad_norm": 1.9473609924316406,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 2.9033,
+      "step": 23
+    },
+    {
+      "epoch": 0.04488078541374474,
+      "grad_norm": 1.9453413486480713,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 2.614,
+      "step": 24
+    },
+    {
+      "epoch": 0.04675081813931744,
+      "grad_norm": 3.785376787185669,
+      "learning_rate": 0.0,
+      "loss": 3.4354,
+      "step": 25
+    },
+    {
+      "epoch": 0.04675081813931744,
+      "eval_loss": 2.9981603622436523,
+      "eval_runtime": 68.574,
+      "eval_samples_per_second": 3.296,
+      "eval_steps_per_second": 1.648,
+      "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": 4224365415628800.0,
+  "total_flos": 5280456769536000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null