Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c76aa68b0dfb935310e37904e573fa53a87808e43bcff8bb71bbec11b91d49b
+oid sha256:4c76ac5a2633bd3aee0f330f842973055dd0255b2b43fd8dc8877bdf4cd9947a
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d76b0505bc6f2352ee27f0cb7a749382fec9ebe1ab13992ab66d16f0473ed1bb
+oid sha256:4cce04706435958ead9891f71030c34c744516eeac3d57e5309264cf8a71e4e1
 size 325340244

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:641ccbea056a1efd23f98e262e590ac8fcc4ad1b6b9ff16c4024e39e19c73f47
+oid sha256:c03b57fce19476462d13e0d7cc32cd4ec24586678f59ff5533dc6754e7878d95
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb0db0205cf37887636e31665ab1051856b2efe4ed0485b1a8cad32db1f6dfbb
+oid sha256:1173c3cbf86b725051d7e94252382f4f9be9dc9f6afe0d4b01afed08d5bf2028
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.1467157006263733,
   "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.3991130820399113,
+  "epoch": 0.4434589800443459,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 12.295,
       "eval_steps_per_second": 3.08,
       "step": 450
+    },
+    {
+      "epoch": 0.4079822616407982,
+      "grad_norm": 0.6651077270507812,
+      "learning_rate": 3.9513070142914725e-06,
+      "loss": 0.1562,
+      "step": 460
+    },
+    {
+      "epoch": 0.41685144124168516,
+      "grad_norm": 1.4017401933670044,
+      "learning_rate": 2.2289447251518195e-06,
+      "loss": 0.1808,
+      "step": 470
+    },
+    {
+      "epoch": 0.42572062084257206,
+      "grad_norm": 0.4009847640991211,
+      "learning_rate": 9.92656988359823e-07,
+      "loss": 0.1463,
+      "step": 480
+    },
+    {
+      "epoch": 0.43458980044345896,
+      "grad_norm": 0.2714759409427643,
+      "learning_rate": 2.4846687349793185e-07,
+      "loss": 0.11,
+      "step": 490
+    },
+    {
+      "epoch": 0.4434589800443459,
+      "grad_norm": 1.1573147773742676,
+      "learning_rate": 0.0,
+      "loss": 0.0943,
+      "step": 500
+    },
+    {
+      "epoch": 0.4434589800443459,
+      "eval_loss": 0.14757481217384338,
+      "eval_runtime": 38.3424,
+      "eval_samples_per_second": 12.388,
+      "eval_steps_per_second": 3.104,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -416,7 +459,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.1231202659165798e+17,
+  "total_flos": 1.2480978011081933e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null