Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dba2557abfa827ec2d27344c81d3c199fc70089424cb151d08ba0e91ba8b068
+oid sha256:a78f654f462dc9df2252c3718fc50144778fdfe3c95dbff08273ed433f1b2ca9
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e10ce82f1d9a45fcd0a3c95d4fb92d096d5cb16dab8d29cb24dea2d4c3e486c1
-size 325339796
+oid sha256:d59ff0881f079faec9f758eeb514a69a74a3235d37dc4f151455391287b82b86
+size 325340244

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bad33dac4afa5f0e3e14d5b89de86fa7b7baba858c291a864a9d2c10c0f81e4a
+oid sha256:10c4a3da32766d583d2c98e34adc4c07a624f05f813c04ed434c77e11704d9c5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9b2510d4f3300d86de2c5b705a4b3113b18ea2234bf5e3432bd4dee5175a4db
+oid sha256:e79d8c81c28cccecf62c97d7dd656ff3c70055cc3d5608fb5051fff0516dc264
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.914474606513977,
-  "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.09206407659731172,
+  "best_metric": 0.8697930574417114,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.11047689191677408,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,49 @@
       "eval_samples_per_second": 10.889,
       "eval_steps_per_second": 2.722,
       "step": 250
+    },
+    {
+      "epoch": 0.0957466396612042,
+      "grad_norm": 1.1317609548568726,
+      "learning_rate": 0.00011210963902166683,
+      "loss": 1.867,
+      "step": 260
+    },
+    {
+      "epoch": 0.09942920272509667,
+      "grad_norm": 1.1235476732254028,
+      "learning_rate": 0.00010504229891530386,
+      "loss": 1.8936,
+      "step": 270
+    },
+    {
+      "epoch": 0.10311176578898913,
+      "grad_norm": 1.1461458206176758,
+      "learning_rate": 9.795770108469618e-05,
+      "loss": 1.8071,
+      "step": 280
+    },
+    {
+      "epoch": 0.1067943288528816,
+      "grad_norm": 1.1431809663772583,
+      "learning_rate": 9.08903609783332e-05,
+      "loss": 1.8178,
+      "step": 290
+    },
+    {
+      "epoch": 0.11047689191677408,
+      "grad_norm": 1.3735449314117432,
+      "learning_rate": 8.387470996680658e-05,
+      "loss": 1.6099,
+      "step": 300
+    },
+    {
+      "epoch": 0.11047689191677408,
+      "eval_loss": 0.8697930574417114,
+      "eval_runtime": 104.9151,
+      "eval_samples_per_second": 10.904,
+      "eval_steps_per_second": 2.726,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -258,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.525616723165184e+16,
+  "total_flos": 9.039055666387354e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null