Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6a96fe0fa1193840a93cf68852b26b9ef4b83c26aed1c1aa27cbb92a1114463
+oid sha256:c2a09056ef466ee6413c43c97a91bbba2c37c219249c325c5f769be885a3f86a
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fcc1b30614d6509167f9fbe16fbb1244d4bc76b0b282440332ec26b019a16ff
+oid sha256:ed5cc88322c559a9e7474327b76d7025cfd3cc3a93cf2b3c88a46b40acdb3dc1
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a96d304a9a82c9caeab768c763cc12aade78e0014f3034a310c7ad68f23d7ec
+oid sha256:229aac640b9a407615a4129cc901eaad483b99fee2a74c0046a310bfa0b84aec
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1164ae497156bc73ad6aea2c09c8b9bf103d80abc111b82a8d3df6753edffe06
+oid sha256:eb9254c45787266aeb2f2d77203ac5705f2dafc0eddb0332e9ac78a896bc3b27
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.4248692989349365,
-  "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.07247689798876608,
+  "best_metric": 2.3869099617004395,
+  "best_model_checkpoint": "miner_id_24/checkpoint-250",
+  "epoch": 0.0905961224859576,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 15.66,
       "eval_steps_per_second": 3.922,
       "step": 200
+    },
+    {
+      "epoch": 0.07610074288820438,
+      "grad_norm": 1.2383389472961426,
+      "learning_rate": 0.00014815222811927496,
+      "loss": 2.2746,
+      "step": 210
+    },
+    {
+      "epoch": 0.07972458778764269,
+      "grad_norm": 1.7436312437057495,
+      "learning_rate": 0.00014158447912183896,
+      "loss": 2.403,
+      "step": 220
+    },
+    {
+      "epoch": 0.08334843268708099,
+      "grad_norm": 1.832153081893921,
+      "learning_rate": 0.00013482875042061958,
+      "loss": 2.3621,
+      "step": 230
+    },
+    {
+      "epoch": 0.08697227758651929,
+      "grad_norm": 2.1388401985168457,
+      "learning_rate": 0.00012791795524676576,
+      "loss": 2.2489,
+      "step": 240
+    },
+    {
+      "epoch": 0.0905961224859576,
+      "grad_norm": 5.763660430908203,
+      "learning_rate": 0.00012088576229969385,
+      "loss": 2.17,
+      "step": 250
+    },
+    {
+      "epoch": 0.0905961224859576,
+      "eval_loss": 2.3869099617004395,
+      "eval_runtime": 73.9921,
+      "eval_samples_per_second": 15.704,
+      "eval_steps_per_second": 3.933,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -215,7 +258,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.884422465270579e+16,
+  "total_flos": 4.846099871721062e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null