Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bf639cfcf4863ff58b77396554b14a1545cf589a43e22aae4740a215e05b35f
+oid sha256:454f3274b145d17cadea3470ce753691d6aad3964cb68202452ed9de78a09ca0
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:add97aa780f339a3b9bfce8763f908728caf9fdb7831a8a6c7c2a60bda642e54
+oid sha256:bf23d039687488ae25ee7c01bab34847197ca990d264d3d4e0bf7ec427931140
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26af93fa51efe49b9e2140f982834d8563ac9574eccc808ced055984b884ad08
+oid sha256:222b56b9f8df0f0e53f193b41fb7b31d9e4883bc8c3809d0e1455a3588234cfb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db8287a4e3b9ef10f63afa9fbb14ef771e3148548ab75efa98b4ac9026c4b7f4
+oid sha256:e231c2c515a5ff10f1e544b2aa46a8eaae94bd71a11db0123cabe0d1726bb1ba
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.383007764816284,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.07256894049346879,
+  "best_metric": 2.3279521465301514,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.14513788098693758,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 11.79,
       "eval_steps_per_second": 2.968,
       "step": 50
+    },
+    {
+      "epoch": 0.08708272859216255,
+      "grad_norm": 1.2386906147003174,
+      "learning_rate": 0.00020674787920189178,
+      "loss": 2.2268,
+      "step": 60
+    },
+    {
+      "epoch": 0.10159651669085631,
+      "grad_norm": 1.256988525390625,
+      "learning_rate": 0.00020599274511475253,
+      "loss": 2.1518,
+      "step": 70
+    },
+    {
+      "epoch": 0.11611030478955008,
+      "grad_norm": 1.7277191877365112,
+      "learning_rate": 0.00020473827667594888,
+      "loss": 2.1788,
+      "step": 80
+    },
+    {
+      "epoch": 0.13062409288824384,
+      "grad_norm": 1.7233295440673828,
+      "learning_rate": 0.00020299058552961598,
+      "loss": 2.1713,
+      "step": 90
+    },
+    {
+      "epoch": 0.14513788098693758,
+      "grad_norm": 3.663735866546631,
+      "learning_rate": 0.00020075818625134152,
+      "loss": 2.1251,
+      "step": 100
+    },
+    {
+      "epoch": 0.14513788098693758,
+      "eval_loss": 2.3279521465301514,
+      "eval_runtime": 24.3674,
+      "eval_samples_per_second": 11.901,
+      "eval_steps_per_second": 2.996,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.319949381402624e+16,
+  "total_flos": 2.611614133203763e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null