Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27c51daaf5429d7ba9e2500efeedace5e0d4f1dd7f93efa88f9bba406b67c906
+oid sha256:f29b18ae32356ff4b10f18956077fad3eb3a0bfafc78d672e7fb71bca4a28786
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca45096163afb88f6d2ef81069504804af9d7c38a16fb5edb4e9ce83878291b2
+oid sha256:cd15b8025eb1b880a79952a20c5e37026eacd1f98ecfcaac3be7ba7fc8eecd20
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88089b75d6b623f34c98becff8927336b43ddcda017bf8dd6cdbc2ddbbe5dcbc
+oid sha256:9428953a082ef7fb8f13d1f4889d09763e06b75a7c250785d2590da27fb48013
 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": 2.2350587844848633,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.003464103230276262,
+  "best_metric": 2.205273389816284,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.005196154845414394,
   "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": 3.93,
       "eval_steps_per_second": 1.966,
       "step": 20
+    },
+    {
+      "epoch": 0.0036373083917900753,
+      "grad_norm": 1.9875291585922241,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 2.0286,
+      "step": 21
+    },
+    {
+      "epoch": 0.004156923876331515,
+      "grad_norm": 1.7483538389205933,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.3018,
+      "step": 24
+    },
+    {
+      "epoch": 0.004330129037845328,
+      "eval_loss": 2.2109057903289795,
+      "eval_runtime": 617.9201,
+      "eval_samples_per_second": 3.934,
+      "eval_steps_per_second": 1.968,
+      "step": 25
+    },
+    {
+      "epoch": 0.004676539360872954,
+      "grad_norm": 3.080596446990967,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 2.1834,
+      "step": 27
+    },
+    {
+      "epoch": 0.005196154845414394,
+      "grad_norm": 1.67843496799469,
+      "learning_rate": 0.0,
+      "loss": 1.9795,
+      "step": 30
+    },
+    {
+      "epoch": 0.005196154845414394,
+      "eval_loss": 2.205273389816284,
+      "eval_runtime": 617.5665,
+      "eval_samples_per_second": 3.936,
+      "eval_steps_per_second": 1.969,
+      "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": 7668943615426560.0,
+  "total_flos": 1.150341542313984e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null