Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e2462279e810da2ab6c6f230426ebc65933f72960626945c933ac18875ea99d
+oid sha256:d511ae9bb17f9754f4d252122b830c934e1f416ad56acf0e2d679c7e051b8d04
 size 10636352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a155c6d32fd2fd273d1f826c2ced481707c1ea1e2445590de1bea48079ce2c05
+oid sha256:814bb54982748a27db1977387f4dc5e4276d448e86a24221cdc54abf08f670fb
 size 21354682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f22434267f1127919976a49ec9facfadf9efdde86e7ee63ffd8f51a85a98c563
+oid sha256:da4ea92489abadb375fea2c0245634ba6aca6196e68d86fd107ec7d2ccd7b29e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.7870981693267822,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.001223091976516634,
+  "best_metric": 1.759916067123413,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.001834637964774951,
   "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": 137.763,
       "eval_steps_per_second": 34.443,
       "step": 20
+    },
+    {
+      "epoch": 0.0012842465753424657,
+      "grad_norm": 5.096099376678467,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 7.3437,
+      "step": 21
+    },
+    {
+      "epoch": 0.0014677103718199608,
+      "grad_norm": 5.4232940673828125,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 7.1224,
+      "step": 24
+    },
+    {
+      "epoch": 0.0015288649706457925,
+      "eval_loss": 1.764245867729187,
+      "eval_runtime": 99.8998,
+      "eval_samples_per_second": 137.848,
+      "eval_steps_per_second": 34.465,
+      "step": 25
+    },
+    {
+      "epoch": 0.0016511741682974559,
+      "grad_norm": 5.302820205688477,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 6.951,
+      "step": 27
+    },
+    {
+      "epoch": 0.001834637964774951,
+      "grad_norm": 5.506922245025635,
+      "learning_rate": 0.0,
+      "loss": 6.8557,
+      "step": 30
+    },
+    {
+      "epoch": 0.001834637964774951,
+      "eval_loss": 1.759916067123413,
+      "eval_runtime": 100.2307,
+      "eval_samples_per_second": 137.393,
+      "eval_steps_per_second": 34.351,
+      "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": 174600851816448.0,
+  "total_flos": 260823494688768.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null