Training in progress, step 78, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3602329bd72c4bc7d7035981265e06f1edfb5211a4083e7fd15078f6a7d9692
+oid sha256:d6138e065bbf5f35bb4e7ea0e645aa53354daeddcda74842d0828aefc1ec2526
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb6e0bcf276e9cbbb5d72b33e03c8f56d2f62331cab326cc4ad0507e87869de2
+oid sha256:a3f4b16a9a9a1d7605740d43ee5492db97488cf1703fdc44be717be716e56bbe
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4a3601f8844e7ab32a4644619f42a8227203297da80aabaae0736b5539f3d83
+oid sha256:ecbfb36a7253df6962ac8cefe189943c7ca955effae3ee4630b92f7dd5b48a83
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:682f5abefb1236694fe47369e37ffb133c44ec9a3bf18f99e54ae8f8321b7af9
+oid sha256:35b29f1ebf08a95ecd70414867b6fba965129f49d762b76942f7d90c35c7e22d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6424a09b2f47614ee2c725aa9c9628d6b6c0b4b1f8ca165a64d0caf97802f360
+oid sha256:85c7f3e110087448a2156a3ff96f1c73a1964d71ed298816572c8026a4a6bd57
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fedc3cad0aa03f8801a7e9223a2db57782ae74d77871e0164eac2bfaffee3167
+oid sha256:ae6ab874ffcab262002f5c5af7d4608f5d663fa062fd3c3cb833cc2b38a14418
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99251af86dff5cdd07ffb4381c5f5ed245c06ff68fa0bbf9042270b45f720631
+oid sha256:7b3f38153cb818c9337b18af3c6dd4e2e52775739e88f251c7f5c612bc494a97
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.925721168518066,
   "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 2.9161603888213854,
+  "epoch": 3.0328068043742404,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 78,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,27 @@
       "eval_samples_per_second": 296.041,
       "eval_steps_per_second": 76.971,
       "step": 75
+    },
+    {
+      "epoch": 2.9550425273390037,
+      "grad_norm": 0.0674208551645279,
+      "learning_rate": 1.0157821333772305e-05,
+      "loss": 12.5571,
+      "step": 76
+    },
+    {
+      "epoch": 2.993924665856622,
+      "grad_norm": 0.07669148594141006,
+      "learning_rate": 1.0039472645551373e-05,
+      "loss": 14.3253,
+      "step": 77
+    },
+    {
+      "epoch": 3.0328068043742404,
+      "grad_norm": 0.06346745043992996,
+      "learning_rate": 1e-05,
+      "loss": 12.3142,
+      "step": 78
     }
   ],
   "logging_steps": 1,
@@ -587,12 +608,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1563741388800.0,
+  "total_flos": 1626291044352.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null