Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f90b285528c4139a2b8dfbc6004fbf9aad5ee7fe384e6ad29dc24951f5c4eed
+oid sha256:e10dba89c04ac6f1eee5efac3127c967681fd031be65f21e60033b46c77c715c
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce0dcedeee1742949057b9bdf502142b14e4100824942530cfcddc3e3683a08e
+oid sha256:abf38fc870c3d48b112e2d968a1ea26c938502ccc1cc2922da1a2c893b9aedf9
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d23c2be57bb03cccc374606355ef9daaddb73c34786ebdf1fe14fc1cda13ca07
+oid sha256:3a33ef9caf09bdac3c94e32c9b99781677b48252ac670dda42eed1fedbfeca65
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6da9db9fb6671f70d2a4e7001f6523f325b24520bef80a5a7ba3fc8703a924b
+oid sha256:d1acf7518eaa83a30405413555139e93a2eb8b9085597afc9a51f69cd1ccf771
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.953998565673828,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0015971570604324302,
+  "best_metric": 2.9304051399230957,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0023957355906486454,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 15.797,
       "eval_steps_per_second": 3.95,
       "step": 20
+    },
+    {
+      "epoch": 0.0016770149134540519,
+      "grad_norm": 1.8426966667175293,
+      "learning_rate": 1.4355517710873184e-05,
+      "loss": 11.4498,
+      "step": 21
+    },
+    {
+      "epoch": 0.0019165884725189162,
+      "grad_norm": 1.598758339881897,
+      "learning_rate": 6.775784314464717e-06,
+      "loss": 12.2368,
+      "step": 24
+    },
+    {
+      "epoch": 0.001996446325540538,
+      "eval_loss": 2.9336705207824707,
+      "eval_runtime": 667.4639,
+      "eval_samples_per_second": 15.799,
+      "eval_steps_per_second": 3.951,
+      "step": 25
+    },
+    {
+      "epoch": 0.002156162031583781,
+      "grad_norm": 1.5937288999557495,
+      "learning_rate": 1.7555878527937164e-06,
+      "loss": 11.484,
+      "step": 27
+    },
+    {
+      "epoch": 0.0023957355906486454,
+      "grad_norm": 1.7225185632705688,
+      "learning_rate": 0.0,
+      "loss": 11.8112,
+      "step": 30
+    },
+    {
+      "epoch": 0.0023957355906486454,
+      "eval_loss": 2.9304051399230957,
+      "eval_runtime": 667.4276,
+      "eval_samples_per_second": 15.799,
+      "eval_steps_per_second": 3.951,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.310772340293632e+16,
+  "total_flos": 3.451894483648512e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null