Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4820c374cb99efcc178a7b82c28d7c04d6efb631c00cead4860c325da63e8b61
+oid sha256:157721e82bf15671ad9675f39c52a69e6fc7cfe6e9015ac95cbb8b07f2b3bea3
 size 871457448

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6d7c633bf928af7da38d621121227ff93323caf74288bfc0dd2cdd856f69371
+oid sha256:574432611cc8141a41e7ef0ebfb1dbc7dd2f5aeefff73915bd4bac718e7a525e
 size 443280340

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f0f71647f5bc6f9024953930b7fa27a3046085cbda2d4d937def3adc4c42ca9
+oid sha256:8307217e06e1987ccd435274b9aac0d79f8d820155ca98c15e5e38f16a87c83f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc5ca798be35724c06196ae6a578bea8311f00bc0b9cfd909c56a0ebc80aea57
+oid sha256:c690d6f2396e52ee620192e6153c703ba870cd541fd4dd25642b8aee51276dfa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3517159223556519,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.0027010236879777437,
+  "best_metric": 1.3310236930847168,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.005402047375955487,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 8.46,
       "eval_steps_per_second": 0.265,
       "step": 50
+    },
+    {
+      "epoch": 0.005402047375955487,
+      "grad_norm": 0.8316030502319336,
+      "learning_rate": 0.000201,
+      "loss": 1.2478,
+      "step": 100
+    },
+    {
+      "epoch": 0.005402047375955487,
+      "eval_loss": 1.3310236930847168,
+      "eval_runtime": 1844.5642,
+      "eval_samples_per_second": 8.451,
+      "eval_steps_per_second": 0.265,
+      "step": 100
     }
   ],
   "logging_steps": 50,
@@ -58,7 +73,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.31805475848192e+16,
+  "total_flos": 8.63610951696384e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null