Training in progress, step 297, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7834c455c515f458d4121a16ed8e5aaa76213c023c4cf9cf0c1527c90b2acf2c
+oid sha256:7afaf8d7157d5a3ae8197685da84b0759d8085a9dcdb6f66e34652560391e7e7
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fdf2d44d541dfb2b65b6027fb1c8a290e6bc81cc24c81b9d8d6af3abe6bf51c
-size 341314196
+oid sha256:b795f152a2cc9673a96f6ff59cbc4ad6b7aeab3d122a5e9706c528a5b27db27e
+size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08e91a46f38b06c7b3b705ce5135ca39798fe4adbd5eb74d820319662adf9418
+oid sha256:7d7735dbf51d8cabf9bd2081060c0d6ef7fd7ca898f5d5afa2d16e7150618565
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd1267a2646d761da0fecb8a9cf70405fcd2c7f7d7d7efc1acd9fcafa940a8dd
+oid sha256:e0ad0674ca10de7ba44e6cb20244d1cd30ddabcc01a689348cef1303e171287d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.3283424377441406,
   "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.8431703204047217,
+  "epoch": 1.0016863406408094,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 297,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,34 @@
       "eval_samples_per_second": 16.3,
       "eval_steps_per_second": 4.173,
       "step": 250
+    },
+    {
+      "epoch": 0.8768971332209107,
+      "grad_norm": 9.572172164916992,
+      "learning_rate": 1.1468371252345698e-05,
+      "loss": 2.6681,
+      "step": 260
+    },
+    {
+      "epoch": 0.9106239460370995,
+      "grad_norm": 10.537660598754883,
+      "learning_rate": 6.1600396923948206e-06,
+      "loss": 2.9342,
+      "step": 270
+    },
+    {
+      "epoch": 0.9443507588532883,
+      "grad_norm": 12.349285125732422,
+      "learning_rate": 2.4565944197665027e-06,
+      "loss": 2.8006,
+      "step": 280
+    },
+    {
+      "epoch": 0.9780775716694773,
+      "grad_norm": 12.332365036010742,
+      "learning_rate": 4.178664281060491e-07,
+      "loss": 2.7451,
+      "step": 290
     }
   ],
   "logging_steps": 10,
@@ -253,12 +281,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.4718687780864e+16,
+  "total_flos": 5.312580108366643e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null