Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14031c653a57d33e7b2b4ff7d51522b10ba7d7046a696abec3cda3edd8f90f84
+oid sha256:6479ec72c8f1206bdfd9d581bb3218a1bddf7b5a04b726b2c98097e661ce316f
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58ec429beae1e3a30f70359b5400904ce0660f7831df1cb8a415d339f156d107
+oid sha256:8436d94b05886fd959053a51ae1f16565051a8ce5e859c88dc35c0428d34302b
 size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81a5b53134b063241a2f678dedea3ac5cf592fc2cd2f4de35c80d0b0c3843de9
+oid sha256:f3eaa19ba43099819858ff8ce6bda4ed48198286b1fe326bf69b7dcfc17eb091
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe3012fb121cd84e6e41f718fd33de9e34ed33145ada7b055f7e25e49408431d
+oid sha256:71a96715f430c2eb0d6104363f54769b2c1bdb005671dc81f0d67833a84ba743
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5094099044799805,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.3865979381443299,
+  "best_metric": 1.5063753128051758,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.42955326460481097,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 17.742,
       "eval_steps_per_second": 4.454,
       "step": 450
+    },
+    {
+      "epoch": 0.3951890034364261,
+      "grad_norm": 0.8970940709114075,
+      "learning_rate": 4.22247514272324e-06,
+      "loss": 1.6966,
+      "step": 460
+    },
+    {
+      "epoch": 0.40378006872852235,
+      "grad_norm": 0.8676711320877075,
+      "learning_rate": 2.38191152001518e-06,
+      "loss": 1.5938,
+      "step": 470
+    },
+    {
+      "epoch": 0.41237113402061853,
+      "grad_norm": 1.022979736328125,
+      "learning_rate": 1.0607805071688306e-06,
+      "loss": 1.5255,
+      "step": 480
+    },
+    {
+      "epoch": 0.4209621993127148,
+      "grad_norm": 1.4544559717178345,
+      "learning_rate": 2.655185216791625e-07,
+      "loss": 1.3489,
+      "step": 490
+    },
+    {
+      "epoch": 0.42955326460481097,
+      "grad_norm": 2.9970974922180176,
+      "learning_rate": 0.0,
+      "loss": 1.3885,
+      "step": 500
+    },
+    {
+      "epoch": 0.42955326460481097,
+      "eval_loss": 1.5063753128051758,
+      "eval_runtime": 27.5708,
+      "eval_samples_per_second": 17.772,
+      "eval_steps_per_second": 4.461,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.9981238550528e+16,
+  "total_flos": 8.886804283392e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null