Training in progress, step 288, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:877f3a8fcc78e5546bf55e912fb49995dd4888e04b69fa1179ef815dc514dc08
+oid sha256:bdcad25513543b0946baa7fda4b46ba9229d1a8f96220cd051d69e996c75e749
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0812750347011757ac8a85ad004f987ca93c762af2c5b916e28944e39c8a799b
-size 41119636
+oid sha256:8f6c6c98b2a790a680ff01e4e4c8af077460a396a2c0c1973d24aeb91441cc95
+size 41120084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edfa161081f25360ef999094cd406d4c7aba4d6f417a122659b6869958b9e162
+oid sha256:796fed4ae78473246ec6ea5ff7463f48a15195cc2e6401e8a6c0f547f5fb5fac
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c838d9e0012b59184c191237b58d821c094b7da772daafc5185514fe73e9c8a
+oid sha256:a2ab543e9bca11ff75da3c524dc0c5f427563e97ea08ded9c78794ecfed3681c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9115006923675537,
-  "best_model_checkpoint": "miner_id_24/checkpoint-192",
-  "epoch": 1.032258064516129,
+  "best_metric": 0.8627253174781799,
+  "best_model_checkpoint": "miner_id_24/checkpoint-288",
+  "epoch": 1.5483870967741935,
   "eval_steps": 96,
-  "global_step": 192,
+  "global_step": 288,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 22.995,
       "eval_steps_per_second": 0.732,
       "step": 192
+    },
+    {
+      "epoch": 1.5483870967741935,
+      "grad_norm": 1.7862235307693481,
+      "learning_rate": 0.00039989808570615163,
+      "loss": 1.4055,
+      "step": 288
+    },
+    {
+      "epoch": 1.5483870967741935,
+      "eval_loss": 0.8627253174781799,
+      "eval_runtime": 6.8612,
+      "eval_samples_per_second": 22.882,
+      "eval_steps_per_second": 0.729,
+      "step": 288
     }
   ],
   "logging_steps": 96,
@@ -73,7 +88,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.250325216329728e+16,
+  "total_flos": 9.377523761047142e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null