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:ba9163ff1ede9cca73b3e7b595c6a73863d65959c2716a18fc995c128805bc2f
+oid sha256:7dd9852c74de32adb6a77906b82caaed269f2ca9f53c0f0781a7738ef3366bac
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1e204a92151c9618403054317a88a1d67c04a036e149d5feffac4fd464bf803
+oid sha256:921013ee7103e94041fefde644bc206151bfdf422b39ac5eb54f385135e99596
 size 509176980

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e83217f58e4c8c814fb91bcc7abe42d1590c1590b60c325bddfe19add1903beb
+oid sha256:5bade1e9aa034973e99b5d7924a7d98faf3dcd0eb3d5b95fad6f98cb29320cb8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20b846236f686f34a315088700cd866bd66ffc165610b7eec245275ac6103428
+oid sha256:0b764a7feea336c9409f04ca3df4d8b4349bea019384446d21739ad3565001bd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.6119084358215332,
-  "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.03377807802736024,
+  "best_metric": 1.601406216621399,
+  "best_model_checkpoint": "miner_id_24/checkpoint-250",
+  "epoch": 0.0422225975342003,
   "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": 11.131,
       "eval_steps_per_second": 2.785,
       "step": 200
+    },
+    {
+      "epoch": 0.035466981928728256,
+      "grad_norm": 2.715378761291504,
+      "learning_rate": 0.00015390571270643128,
+      "loss": 2.6685,
+      "step": 210
+    },
+    {
+      "epoch": 0.03715588583009627,
+      "grad_norm": 3.9339587688446045,
+      "learning_rate": 0.0001470829054955026,
+      "loss": 3.3036,
+      "step": 220
+    },
+    {
+      "epoch": 0.03884478973146428,
+      "grad_norm": 4.110659122467041,
+      "learning_rate": 0.00014006481839811937,
+      "loss": 3.3478,
+      "step": 230
+    },
+    {
+      "epoch": 0.04053369363283229,
+      "grad_norm": 4.37723970413208,
+      "learning_rate": 0.00013288564282916442,
+      "loss": 3.2481,
+      "step": 240
+    },
+    {
+      "epoch": 0.0422225975342003,
+      "grad_norm": 5.84151554107666,
+      "learning_rate": 0.00012558035501036158,
+      "loss": 3.5592,
+      "step": 250
+    },
+    {
+      "epoch": 0.0422225975342003,
+      "eval_loss": 1.601406216621399,
+      "eval_runtime": 226.5276,
+      "eval_samples_per_second": 11.01,
+      "eval_steps_per_second": 2.755,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -215,7 +258,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.4401180721152e+16,
+  "total_flos": 8.050147590144e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null