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:ef9ea5fb59afcf4c0a5b464f64c4ed2ff47b021679f5fd20e37ecf3d7cc96396
+oid sha256:009e1bc73910a745f34601db5f80073ca11774551630a6c37cc2a20acc90a38e
 size 78207176

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adb7ecfe07fd43c240641cdf114bc48661df3bbe0511dc9d2dcea1e349dd7a84
+oid sha256:8b4b6f5a98fc7b6f812581c28b428e8c7494df274825547a91e851ede8137307
 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 sha256:91a0ef1d02a9130afe0eacfbf3807cf09429d5af22043c04cdef3112613fbdc5
+oid sha256:32a464ce10d602752c2d832542614c675cb29b487a662ae579b6976dbb08d498
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.226397156715393,
   "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": 47.404,
       "eval_steps_per_second": 11.966,
       "step": 200
+    },
+    {
+      "epoch": 0.860655737704918,
+      "grad_norm": 0.3445681929588318,
+      "learning_rate": 1.4852209222575098e-05,
+      "loss": 1.2071,
+      "step": 210
+    },
+    {
+      "epoch": 0.9016393442622951,
+      "grad_norm": 0.3245381712913513,
+      "learning_rate": 7.495166420908236e-06,
+      "loss": 1.1919,
+      "step": 220
+    },
+    {
+      "epoch": 0.9426229508196722,
+      "grad_norm": 0.3444859981536865,
+      "learning_rate": 2.571742272983936e-06,
+      "loss": 1.1797,
+      "step": 230
+    },
+    {
+      "epoch": 0.9836065573770492,
+      "grad_norm": 0.328487366437912,
+      "learning_rate": 2.107659631099793e-07,
+      "loss": 1.2562,
+      "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