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:d30c4a142008d1667738f04274603af896c576b8d94962f3509b91db33b6dee6
+oid sha256:c7f5b57a6979cc8598b4eb4b07cb5a3fa06bcb301af6a3658d05e7d862a58122
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74eba59faffd18054385adeac319f0c57a79e79f6037276aeb46e3e5a153dcae
+oid sha256:618dd0e2e181e5169068569ad975179052bfda71f70c889b6723803db6b1d5a5
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b1cfff1f8bcf6ed37b27b73a75e4bacc6bd5f25aace99c77698a0e827c23340
+oid sha256:ff389126b2d5d6a6a1560333f1c3e5f1dd4e03b84a4458ad9982b33e6dab6ccd
 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": 0.4184398353099823,
   "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0011861340924591525,
+  "epoch": 0.0014826676155739406,
   "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": 6.541,
       "eval_steps_per_second": 3.271,
       "step": 20
+    },
+    {
+      "epoch": 0.0012454407970821102,
+      "grad_norm": 1.3536689281463623,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.3067,
+      "step": 21
+    },
+    {
+      "epoch": 0.0013047475017050677,
+      "grad_norm": 1.3476461172103882,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.3582,
+      "step": 22
+    },
+    {
+      "epoch": 0.0013640542063280254,
+      "grad_norm": 0.9846263527870178,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.2339,
+      "step": 23
+    },
+    {
+      "epoch": 0.001423360910950983,
+      "grad_norm": 0.764580488204956,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.2296,
+      "step": 24
+    },
+    {
+      "epoch": 0.0014826676155739406,
+      "grad_norm": 1.3171172142028809,
+      "learning_rate": 0.0,
+      "loss": 0.359,
+      "step": 25
+    },
+    {
+      "epoch": 0.0014826676155739406,
+      "eval_loss": 0.4272419810295105,
+      "eval_runtime": 1060.7447,
+      "eval_samples_per_second": 6.693,
+      "eval_steps_per_second": 3.347,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -201,7 +244,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3930324027310080.0,
+  "total_flos": 4901345257586688.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null