Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6193329017da43ac368c047060ea7a27ceca3f2f8458b13924217bb9157c228e
+oid sha256:d9f74008d31285ba8940ac64ccb09cb461c9cc8b5527a8b5181986576071d1b9
 size 5327744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:440bfe7844165950b800dd3f1d0c3b06945b385c7613d09405ebe0be239aa0c8
+oid sha256:0f8caed7545ee35182ec98eda7d7cdf67899ed835a84d98d945f7901626590bd
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae11cf21e04a8ba1c4027ccb79461cc37c22ade2957b5f96edbbda227a268217
+oid sha256:a22fc57ea43b046bef99fc671d5fb7dac414c32e2197e9d670ba859570a0675b
 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": 2.539055585861206,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0006162093879500255,
+  "best_metric": 2.532271385192871,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0007702617349375318,
   "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": 26.698,
       "eval_steps_per_second": 13.349,
       "step": 20
+    },
+    {
+      "epoch": 0.0006470198573475267,
+      "grad_norm": 7.9703145027160645,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 9.5349,
+      "step": 21
+    },
+    {
+      "epoch": 0.000677830326745028,
+      "grad_norm": 8.338407516479492,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 9.5837,
+      "step": 22
+    },
+    {
+      "epoch": 0.0007086407961425293,
+      "grad_norm": 8.587491035461426,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 10.2255,
+      "step": 23
+    },
+    {
+      "epoch": 0.0007394512655400305,
+      "grad_norm": 7.686610698699951,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 11.9067,
+      "step": 24
+    },
+    {
+      "epoch": 0.0007702617349375318,
+      "grad_norm": 7.370700836181641,
+      "learning_rate": 0.0,
+      "loss": 11.1744,
+      "step": 25
+    },
+    {
+      "epoch": 0.0007702617349375318,
+      "eval_loss": 2.532271385192871,
+      "eval_runtime": 528.8853,
+      "eval_samples_per_second": 25.839,
+      "eval_steps_per_second": 12.92,
+      "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": 54135254679552.0,
+  "total_flos": 65811486081024.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null