Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:824e9d4e2b8a12779f165162f6c213f8894db74c814a642b75c2bfff4d53cf91
+oid sha256:8291dd835e653d635ca52191e85717c765050760e679717c4c3a865b4dcc016b
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c90cb751c3b8c0f940e58666d7d1a16211c2e03650a7c6bd574fdd437691117
+oid sha256:703b427a1c5109fbe88f30362a59a97eb654261919f4a71158a4d7c5e7515963
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ac9ef8a8d750dd06f1b2f32aa7dc4ccd0792acf7e63e2006163d178a7597fee
+oid sha256:07ef33ef8c9bd3eab93359c523362a448c809b01d08be76655d89dddb1772720
 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": 0.0014264764031395316,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.47904191616766467,
+  "best_metric": 0.0013156335335224867,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.5988023952095808,
   "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": 6.571,
       "eval_steps_per_second": 3.286,
       "step": 20
+    },
+    {
+      "epoch": 0.5029940119760479,
+      "grad_norm": 0.03260622173547745,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.0014,
+      "step": 21
+    },
+    {
+      "epoch": 0.5269461077844312,
+      "grad_norm": 0.028929762542247772,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0012,
+      "step": 22
+    },
+    {
+      "epoch": 0.5508982035928144,
+      "grad_norm": 0.025760218501091003,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.0011,
+      "step": 23
+    },
+    {
+      "epoch": 0.5748502994011976,
+      "grad_norm": 0.023113111034035683,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.0011,
+      "step": 24
+    },
+    {
+      "epoch": 0.5988023952095808,
+      "grad_norm": 0.022324662655591965,
+      "learning_rate": 0.0,
+      "loss": 0.0011,
+      "step": 25
+    },
+    {
+      "epoch": 0.5988023952095808,
+      "eval_loss": 0.0013156335335224867,
+      "eval_runtime": 3.108,
+      "eval_samples_per_second": 5.791,
+      "eval_steps_per_second": 2.896,
+      "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": 178076327608320.0,
+  "total_flos": 222595409510400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null