Training in progress, step 1650, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc0563610e9795da6193abe9970ea5bdd798757bad57849692ef086caa273f7d
+oid sha256:de088b2de1ee181bd71f905f8d5857efe95f9d48787209fce8bc6015c4c58137
 size 1101095848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3284ff4276b76c44987eb43330358b6c7c1a8f3bf83a04fd1796b7d3c6aac59c
+oid sha256:647ed4da156e09a8fd511aca2fdf0669f08f7f5c5d40e062eafcfb42b63efa62
 size 559894868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3681057530ddf641436a54f3c5d867353c0b63200499627cd2751802959141cc
+oid sha256:cf99c4a322b12e03b16f1e7ad8423bdee73f9697406f3e5b3166adc0a2af306b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:befb5de8641401f08357d93e09a6b263a413b6c62f0e4dc381df697735030b77
+oid sha256:090e504a81765b504142cff403afcf92b817f0e48945f0e4e014e79a6565dad0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.826446294784546,
   "best_model_checkpoint": "miner_id_24/checkpoint-1350",
-  "epoch": 1.0871534698314913,
+  "epoch": 1.1958688168146403,
   "eval_steps": 150,
-  "global_step": 1500,
+  "global_step": 1650,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -305,6 +305,35 @@
       "eval_samples_per_second": 13.401,
       "eval_steps_per_second": 3.356,
       "step": 1500
+    },
+    {
+      "epoch": 1.1233919188258743,
+      "grad_norm": 0.8776970505714417,
+      "learning_rate": 9.733794785622253e-05,
+      "loss": 1.3963,
+      "step": 1550
+    },
+    {
+      "epoch": 1.1596303678202573,
+      "grad_norm": 0.9756889939308167,
+      "learning_rate": 9.202138944469168e-05,
+      "loss": 1.393,
+      "step": 1600
+    },
+    {
+      "epoch": 1.1958688168146403,
+      "grad_norm": 0.8379771113395691,
+      "learning_rate": 8.672744727162781e-05,
+      "loss": 1.4002,
+      "step": 1650
+    },
+    {
+      "epoch": 1.1958688168146403,
+      "eval_loss": 1.837064504623413,
+      "eval_runtime": 86.6691,
+      "eval_samples_per_second": 13.407,
+      "eval_steps_per_second": 3.358,
+      "step": 1650
     }
   ],
   "logging_steps": 50,
@@ -319,7 +348,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -328,12 +357,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.0828424646607503e+18,
+  "total_flos": 1.1904824490055434e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null