Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8861081c8d652eb8e785766f199a97a083f8a75e701c1965b969e2bebf43e171
+oid sha256:e68d5d35c933f55c217bfa873647a85d9ce572ebe7380a75ecde8e2c9523c6f6
 size 25192688

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:707f2177f98fe8c4ec5cd61a2dec8b265321bb579ae51fe9d3c5a9808b16971b
+oid sha256:b02703e85b56562d35299aee20d206dc9fc155e3851c5b1f8ea17caa43614456
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:326b940c26441f9cc805b55861d6ba1368323749e2ade38b0a118c4c7d409c57
+oid sha256:705deedf796b313cb76cd6c14cb7b94da899d809f9d9c1109db82fbb592f3b6c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.47520112991333,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.08056394763343404,
+  "best_metric": 2.418942451477051,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.12084592145015106,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 27.688,
       "eval_steps_per_second": 13.976,
       "step": 20
+    },
+    {
+      "epoch": 0.08459214501510574,
+      "grad_norm": 6.26775598526001,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 9.9183,
+      "step": 21
+    },
+    {
+      "epoch": 0.09667673716012085,
+      "grad_norm": 6.464348793029785,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 9.9804,
+      "step": 24
+    },
+    {
+      "epoch": 0.10070493454179255,
+      "eval_loss": 2.425276041030884,
+      "eval_runtime": 3.586,
+      "eval_samples_per_second": 29.281,
+      "eval_steps_per_second": 14.78,
+      "step": 25
+    },
+    {
+      "epoch": 0.10876132930513595,
+      "grad_norm": 6.798356056213379,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 9.5835,
+      "step": 27
+    },
+    {
+      "epoch": 0.12084592145015106,
+      "grad_norm": 6.155633449554443,
+      "learning_rate": 0.0,
+      "loss": 10.0792,
+      "step": 30
+    },
+    {
+      "epoch": 0.12084592145015106,
+      "eval_loss": 2.418942451477051,
+      "eval_runtime": 3.5968,
+      "eval_samples_per_second": 29.193,
+      "eval_steps_per_second": 14.735,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 303370988421120.0,
+  "total_flos": 455056482631680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null