Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa59e152ccfa4fa7e446966eb46d969fa386778441364096c7557bc87e810ebe
+oid sha256:572a44df50931ba9b6e28f843bd0a479943a7c8926299433c6aedf3aeefcc0e2
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe1e58e7eaae69037abdd2fb7887b57c25cefa92c4da7266c43e5bb7e6a3d5b0
+oid sha256:9372d0dbcf7010cd76b277c7a2b45ea9b25e2de212ffd9775eed437154517a0a
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94eb3af0be59b8022e591483a56634de67b6ec709d4a7976205940027b927a1a
+oid sha256:a8d0ca5f94c74be21f7e258f478e4f1bcf339ab697a95d852a0fd9b800d39d6b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8945090770721436,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0025143000817147527,
+  "best_metric": 0.7647151947021484,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.005028600163429505,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 11.803,
       "eval_steps_per_second": 5.905,
       "step": 10
+    },
+    {
+      "epoch": 0.003017160098057703,
+      "grad_norm": 1.0146321058273315,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.9425,
+      "step": 12
+    },
+    {
+      "epoch": 0.003771450122572129,
+      "grad_norm": 0.5241138339042664,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.8438,
+      "step": 15
+    },
+    {
+      "epoch": 0.003771450122572129,
+      "eval_loss": 0.7839879989624023,
+      "eval_runtime": 141.9579,
+      "eval_samples_per_second": 11.799,
+      "eval_steps_per_second": 5.903,
+      "step": 15
+    },
+    {
+      "epoch": 0.004525740147086555,
+      "grad_norm": 0.33658936619758606,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.6818,
+      "step": 18
+    },
+    {
+      "epoch": 0.005028600163429505,
+      "eval_loss": 0.7647151947021484,
+      "eval_runtime": 141.8458,
+      "eval_samples_per_second": 11.809,
+      "eval_steps_per_second": 5.908,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3709436417802240.0,
+  "total_flos": 7418872835604480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null