Training in progress, step 244, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b502f9c515556c6b616b256b147e14533b166bcacae7a1399615becf441c3c76
+oid sha256:121ae803c81341167be8b80bcefc6be769a5feedd86fd19b9ea546bcabc79723
 size 78207176

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bea00ae054168c118dc5a495550a086e6b5ea16f1a665269f4ae3532e66d77b9
+oid sha256:da04c7621c2bf2647d4fa7716aea04c3f6e492cb2524ce9cb8353b38c7b6674d
 size 40177764

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:730ecea7bef67b24e9ef56be6b878ba1d9ea94367e32a3fc3d97184830677f77
+oid sha256:83bdd2393075b8af399916cfa87898b615d22a9d5775910e81f7d395c1951ff3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24c57ef3b16e53cab7f6cfb8bea0a5df6b0851902a78971ae63e6c5055ac17f4
+oid sha256:4cb0c08bc38b71a6e83e5082c51ffd1be496abf510467575d796445b72a732d3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.2219525575637817,
   "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.819672131147541,
+  "epoch": 1.0,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 244,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,34 @@
       "eval_samples_per_second": 49.855,
       "eval_steps_per_second": 12.585,
       "step": 200
+    },
+    {
+      "epoch": 0.860655737704918,
+      "grad_norm": 0.33350831270217896,
+      "learning_rate": 1.559112510429525e-05,
+      "loss": 1.203,
+      "step": 210
+    },
+    {
+      "epoch": 0.9016393442622951,
+      "grad_norm": 0.3176622688770294,
+      "learning_rate": 7.868060272694714e-06,
+      "loss": 1.1872,
+      "step": 220
+    },
+    {
+      "epoch": 0.9426229508196722,
+      "grad_norm": 0.33727821707725525,
+      "learning_rate": 2.699689649749306e-06,
+      "loss": 1.1757,
+      "step": 230
+    },
+    {
+      "epoch": 0.9836065573770492,
+      "grad_norm": 0.32050246000289917,
+      "learning_rate": 2.2125183192142107e-07,
+      "loss": 1.2519,
+      "step": 240
     }
   ],
   "logging_steps": 10,
@@ -210,12 +238,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1236088022630400.0,
+  "total_flos": 1507254832594944.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null