Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7276c6c6b1c82e9ac9adcb8071efabe9d6403ea71bce9e614de2ddfa8e9da999
+oid sha256:af1f51810989d47954fb84c071c62cfbc75f167ebaa428d0d51473c2d2cca937
 size 180385008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8223c38a3bd9512aab359703cdeea80e50f0deab87444d44c511a35aa25a9a3b
+oid sha256:c60ac4f89d2ed5a573d3bd749e6c20e3233e71af081936f48cc5fd11b26dd7ce
 size 91850362

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b202187c87a83cf67b64ba9fe2bfec485327f87ec105c2cc9fd2354d68fe406
+oid sha256:c48134bf128dc3a6d94f0fad3bb2077e97a0b649e7d7eb5b552313c3d950ea12
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4ffe1cc6011db9bcd26d2a5ee9a2f60bf90f43b3c6aed165ee32997fe344b31
+oid sha256:c41568ec8d15c28a2145796b65c5977bed142a18699c02f8db4b41d7a5440c4c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.7373805046081543,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.02478929102627665,
+  "best_metric": 2.5573222637176514,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.03305238803503553,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 58.457,
       "eval_steps_per_second": 14.614,
       "step": 150
+    },
+    {
+      "epoch": 0.026441910428028424,
+      "grad_norm": 2.0548884868621826,
+      "learning_rate": 0.00018740803823691298,
+      "loss": 2.4033,
+      "step": 160
+    },
+    {
+      "epoch": 0.028094529829780203,
+      "grad_norm": 2.9234230518341064,
+      "learning_rate": 0.00018193523609311556,
+      "loss": 2.2948,
+      "step": 170
+    },
+    {
+      "epoch": 0.029747149231531978,
+      "grad_norm": 3.7016618251800537,
+      "learning_rate": 0.00017610710081049675,
+      "loss": 2.3234,
+      "step": 180
+    },
+    {
+      "epoch": 0.03139976863328375,
+      "grad_norm": 5.965432643890381,
+      "learning_rate": 0.00016995202647831142,
+      "loss": 2.2832,
+      "step": 190
+    },
+    {
+      "epoch": 0.03305238803503553,
+      "grad_norm": 17.460437774658203,
+      "learning_rate": 0.00016350000000000002,
+      "loss": 3.0321,
+      "step": 200
+    },
+    {
+      "epoch": 0.03305238803503553,
+      "eval_loss": 2.5573222637176514,
+      "eval_runtime": 43.5955,
+      "eval_samples_per_second": 58.446,
+      "eval_steps_per_second": 14.612,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -172,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3791157272248320.0,
+  "total_flos": 5042364292792320.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null