Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86f47c450a1995e838a819befe36ce24eb46eb1129b7657f3b2d43939298cdd6
+oid sha256:051dc480eaf49a0fab1df53f8791b39df3f8c02744133ff3afc65369bce53d89
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:808a00a352481b869caf172f904e1f4bd23ee70ee07962c150bb1da1bd88b021
+oid sha256:94ea1d2312f4689baa9c291ac72845be188183548db92937ccb24ef510b593e9
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efdd87dee97878b58ceed2a779f198a7e00f729ad50220d3f01eff765616fa59
+oid sha256:096129140daec591efbe04c9118470e2cf7edd82cf8ec75604fcc30b13518c4c
 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": 1.790372371673584,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0847457627118644,
+  "best_metric": 1.7713760137557983,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.1271186440677966,
   "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": 7.187,
       "eval_steps_per_second": 3.594,
       "step": 20
+    },
+    {
+      "epoch": 0.08898305084745763,
+      "grad_norm": 0.27250492572784424,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 1.5709,
+      "step": 21
+    },
+    {
+      "epoch": 0.1016949152542373,
+      "grad_norm": 0.4483605623245239,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.7697,
+      "step": 24
+    },
+    {
+      "epoch": 0.1059322033898305,
+      "eval_loss": 1.7753188610076904,
+      "eval_runtime": 13.9223,
+      "eval_samples_per_second": 7.183,
+      "eval_steps_per_second": 3.591,
+      "step": 25
+    },
+    {
+      "epoch": 0.11440677966101695,
+      "grad_norm": 0.5262288451194763,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.7965,
+      "step": 27
+    },
+    {
+      "epoch": 0.1271186440677966,
+      "grad_norm": 0.4244944751262665,
+      "learning_rate": 0.0,
+      "loss": 1.8369,
+      "step": 30
+    },
+    {
+      "epoch": 0.1271186440677966,
+      "eval_loss": 1.7713760137557983,
+      "eval_runtime": 13.9241,
+      "eval_samples_per_second": 7.182,
+      "eval_steps_per_second": 3.591,
+      "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": 7272035285729280.0,
+  "total_flos": 1.090805292859392e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null