Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c2c4d0171d0a24ec3811bf679d1c641ec4a190b5d8d9cacb146e38adc4d04af
+oid sha256:0f7b80e76eaf2b214debd9342e2d49bf23dd8ad065157125f54aabf719c688cd
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdcb18789d2342e70ea3f72c48eaa74a10ad443581b27f2ece2120cb2eeb8feb
+oid sha256:b8c22866452c76bd090d6a76c1091367cbaa7973fbea01217836cb2cafa88156
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49de370ac54225c7243186cc559aced1036fab31ef98861b24fe84d7ec44bd0b
+oid sha256:83eb5cdc8dd621b9d3b7cf06b9b893f32eef10d148e5187947364f07998add5d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2736992835998535,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.003021490350115194,
+  "best_metric": 1.2466561794281006,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0045322355251727914,
   "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": 4.698,
       "eval_steps_per_second": 2.35,
       "step": 20
+    },
+    {
+      "epoch": 0.003172564867620954,
+      "grad_norm": 0.5693583488464355,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 1.3048,
+      "step": 21
+    },
+    {
+      "epoch": 0.0036257884201382332,
+      "grad_norm": 0.7350389361381531,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 1.2515,
+      "step": 24
+    },
+    {
+      "epoch": 0.003776862937643993,
+      "eval_loss": 1.2513402700424194,
+      "eval_runtime": 589.867,
+      "eval_samples_per_second": 4.725,
+      "eval_steps_per_second": 2.363,
+      "step": 25
+    },
+    {
+      "epoch": 0.004079011972655512,
+      "grad_norm": 0.6812828779220581,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 1.2245,
+      "step": 27
+    },
+    {
+      "epoch": 0.0045322355251727914,
+      "grad_norm": 0.6246094107627869,
+      "learning_rate": 0.0,
+      "loss": 1.1205,
+      "step": 30
+    },
+    {
+      "epoch": 0.0045322355251727914,
+      "eval_loss": 1.2466561794281006,
+      "eval_runtime": 588.4502,
+      "eval_samples_per_second": 4.736,
+      "eval_steps_per_second": 2.369,
+      "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": 7418872835604480.0,
+  "total_flos": 1.112830925340672e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null