Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e562e4cbe7239dafc73ce0ef2ca39882f69ae4eafd4fa66daa8a5b9a42e1b30
+oid sha256:c6d32515f9c0e438a0de7814b83179501a06707201483599b6f0363d11586b03
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:956a7888f7c05098132baf8193a4c9631e91dc8f945e530a7f01aeec16d6fd4b
+oid sha256:2d7b824cbc19e9004f55020fe52940d308bcefa6d06d35ebc262547bb2723ddb
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7790a06b1e5a941b9971134c8654af479028e765a91da6e3508950abba1b168
+oid sha256:fdb349cfd5e4bc7dc6b1427841c22b82f8c8fe454b47b791bdf4748e397dcc60
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 4.139446258544922,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0007838526357044876,
+  "best_metric": 4.056199073791504,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0011757789535567313,
   "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": 8.25,
       "eval_steps_per_second": 4.125,
       "step": 20
+    },
+    {
+      "epoch": 0.0008230452674897119,
+      "grad_norm": 0.9166094064712524,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 4.1357,
+      "step": 21
+    },
+    {
+      "epoch": 0.0009406231628453851,
+      "grad_norm": 0.720608115196228,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 3.9637,
+      "step": 24
+    },
+    {
+      "epoch": 0.0009798157946306093,
+      "eval_loss": 4.068421363830566,
+      "eval_runtime": 1301.9749,
+      "eval_samples_per_second": 8.252,
+      "eval_steps_per_second": 4.126,
+      "step": 25
+    },
+    {
+      "epoch": 0.0010582010582010583,
+      "grad_norm": 0.7923865914344788,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 3.9462,
+      "step": 27
+    },
+    {
+      "epoch": 0.0011757789535567313,
+      "grad_norm": 0.7229490876197815,
+      "learning_rate": 0.0,
+      "loss": 3.885,
+      "step": 30
+    },
+    {
+      "epoch": 0.0011757789535567313,
+      "eval_loss": 4.056199073791504,
+      "eval_runtime": 1302.02,
+      "eval_samples_per_second": 8.252,
+      "eval_steps_per_second": 4.126,
+      "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": 6990386933268480.0,
+  "total_flos": 1.048558039990272e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null