Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a84deee13dd315e8fcbcb28d22e374b4e919e8d119644daac24c63ee4b326580
+oid sha256:ebf24e1bf62bae17c3e161bca0770f55c82c7c4085ecace43a9d47b1c064ae27
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ab33aabb23561c4a90afb5ee894e1faaf2a53a68f4feafcc5727886b373b7cf
+oid sha256:4dad4b57dadf9775150401312c0fcb2799d7d6f020292d3017cdaa17644865c1
 size 46057082

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d8414ba48354825ad20b0a3d80cc23ff1d239366d3e0da53cb9bbe2c2455ccc
+oid sha256:b83137896c579d86619217aca9c0b81561f6e1913616a6fe74d20b7182e4287f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:321b462a2538632d6d720f0cf198c8f471dee11f51db9b50cc50d1fa7f132bbe
+oid sha256:60663a94a33586da5717f6f80de424ce9fe5b18a8c8d13d4ca09aa40f102443b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.7350926399230957,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0056477232615601836,
+  "best_metric": 1.6901509761810303,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.008471584892340275,
   "eval_steps": 10,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -171,6 +171,84 @@
       "eval_samples_per_second": 5.569,
       "eval_steps_per_second": 5.569,
       "step": 20
+    },
+    {
+      "epoch": 0.005930109424638193,
+      "grad_norm": 0.876990020275116,
+      "learning_rate": 0.00019975141040730207,
+      "loss": 1.2469,
+      "step": 21
+    },
+    {
+      "epoch": 0.006212495587716202,
+      "grad_norm": 1.1722772121429443,
+      "learning_rate": 0.0001997041811497882,
+      "loss": 2.2798,
+      "step": 22
+    },
+    {
+      "epoch": 0.006494881750794211,
+      "grad_norm": 0.9232650995254517,
+      "learning_rate": 0.00019965285344390184,
+      "loss": 2.5319,
+      "step": 23
+    },
+    {
+      "epoch": 0.00677726791387222,
+      "grad_norm": 1.6948198080062866,
+      "learning_rate": 0.00019959742939952392,
+      "loss": 1.6864,
+      "step": 24
+    },
+    {
+      "epoch": 0.0070596540769502295,
+      "grad_norm": 1.277117133140564,
+      "learning_rate": 0.00019953791129491983,
+      "loss": 2.1785,
+      "step": 25
+    },
+    {
+      "epoch": 0.007342040240028239,
+      "grad_norm": 3.347221851348877,
+      "learning_rate": 0.00019947430157664576,
+      "loss": 1.5917,
+      "step": 26
+    },
+    {
+      "epoch": 0.007624426403106248,
+      "grad_norm": 1.2190711498260498,
+      "learning_rate": 0.00019940660285944803,
+      "loss": 2.3655,
+      "step": 27
+    },
+    {
+      "epoch": 0.007906812566184257,
+      "grad_norm": 1.9080499410629272,
+      "learning_rate": 0.00019933481792615583,
+      "loss": 2.0602,
+      "step": 28
+    },
+    {
+      "epoch": 0.008189198729262267,
+      "grad_norm": 1.5589416027069092,
+      "learning_rate": 0.0001992589497275665,
+      "loss": 1.9817,
+      "step": 29
+    },
+    {
+      "epoch": 0.008471584892340275,
+      "grad_norm": 2.701538562774658,
+      "learning_rate": 0.0001991790013823246,
+      "loss": 1.434,
+      "step": 30
+    },
+    {
+      "epoch": 0.008471584892340275,
+      "eval_loss": 1.6901509761810303,
+      "eval_runtime": 134.7409,
+      "eval_samples_per_second": 5.537,
+      "eval_steps_per_second": 5.537,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -199,7 +277,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1957607170375680.0,
+  "total_flos": 2936410755563520.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null