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:a4b30f6ed6becf97218da1feda387f4738183f0773e4e1dec1f0c0fcf0c3b433
+oid sha256:558547eab990a9ec848bac0d6f62a167eee764f402c908d5eb672e66f3588487
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee5d11d22dd37d728284ed3f5ecdb95d5e43f7265e1cdd2bc61df351631bc43f
+oid sha256:08b5898f35b9fdce93eb801d70b901080a7ff1b8e2a50ac8aa6c6bc0a98f69ff
 size 56088148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37a7b1eefc0898a8d01ccd457dcb62891acd5769ebfaef6b5416f953f1df19c1
+oid sha256:55789a6898f66a16b91372d09ab313ad8afe1fe5b75eb18a2af91d811729cd83
 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": 0.6956700682640076,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.011379800853485065,
+  "best_metric": 0.6874585747718811,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.01422475106685633,
   "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": 3.49,
       "eval_steps_per_second": 1.745,
       "step": 20
+    },
+    {
+      "epoch": 0.011948790896159318,
+      "grad_norm": 0.6049901247024536,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.6489,
+      "step": 21
+    },
+    {
+      "epoch": 0.01251778093883357,
+      "grad_norm": 0.7815760970115662,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.7723,
+      "step": 22
+    },
+    {
+      "epoch": 0.013086770981507824,
+      "grad_norm": 0.7972508668899536,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.5945,
+      "step": 23
+    },
+    {
+      "epoch": 0.013655761024182077,
+      "grad_norm": 0.7516416907310486,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.6266,
+      "step": 24
+    },
+    {
+      "epoch": 0.01422475106685633,
+      "grad_norm": 0.5937511324882507,
+      "learning_rate": 0.0,
+      "loss": 0.6435,
+      "step": 25
+    },
+    {
+      "epoch": 0.01422475106685633,
+      "eval_loss": 0.6874585747718811,
+      "eval_runtime": 209.631,
+      "eval_samples_per_second": 3.53,
+      "eval_steps_per_second": 1.765,
+      "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": 8448730831257600.0,
+  "total_flos": 1.0560913539072e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null