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:f3704a02e69d43bbf24ccf73d008dc8ac74320a182ff2012db5aaed0458f9185
+oid sha256:bc2c1e816d4870fffde36c4b068229ad00e10498aebed3a40da5b1dd318ae115
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4669655a34d119afe92d5514a4d4687c7a5b5a384ee18931d7f90e91379f2c1c
+oid sha256:d2260b46538e47baa3dbcd7ba295e7ac265cdd4613cba72dd4761bad077f81c9
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bfe8b3574114a4b78e34aef09eb36bffde8eb10418fac748c2c7b754105548f
+oid sha256:8a52731fcd7f1184448d105e6f375134109b8b3026d297f4869a2e107d0e7fa7
 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": 1.4427205324172974,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.023682652457075192,
+  "best_metric": 1.4391453266143799,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.02960331557134399,
   "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": 4.307,
       "eval_steps_per_second": 2.154,
       "step": 20
+    },
+    {
+      "epoch": 0.02486678507992895,
+      "grad_norm": 0.8581761121749878,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.5749,
+      "step": 21
+    },
+    {
+      "epoch": 0.02605091770278271,
+      "grad_norm": 0.8760268688201904,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.6816,
+      "step": 22
+    },
+    {
+      "epoch": 0.027235050325636473,
+      "grad_norm": 0.6158702969551086,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.6894,
+      "step": 23
+    },
+    {
+      "epoch": 0.028419182948490232,
+      "grad_norm": 1.123356580734253,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.8956,
+      "step": 24
+    },
+    {
+      "epoch": 0.02960331557134399,
+      "grad_norm": 1.8370057344436646,
+      "learning_rate": 0.0,
+      "loss": 1.9829,
+      "step": 25
+    },
+    {
+      "epoch": 0.02960331557134399,
+      "eval_loss": 1.4391453266143799,
+      "eval_runtime": 85.2663,
+      "eval_samples_per_second": 4.175,
+      "eval_steps_per_second": 2.088,
+      "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": 276018307792896.0,
+  "total_flos": 347248838836224.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null