Training in progress, step 2633, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0a522ed20fbdcfb113dac066fed8d5b62b7ac84e9b723a4d5198b0889376683
+oid sha256:249855c09c45849f7c73a6e694c5b1ef53724d710c791981cb8a57e2e47d8bb0
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82d998e6f69f3908d5c4ad510978d8ef138168d04280863066e625fc1c9faf28
+oid sha256:fb86dc30259e5769411b56c74f8cfbbc600b1b6d0721871505a9b32b9f758a58
 size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bec98415c91702db8febabe5fa4b06fa655e77182dea80a3c11ffa1ab4776c8
+oid sha256:d0ec212340c0f9a97e8e05869b4820cabc71039c05580684b502c1f1e5bdf06e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8edf9ab4b0b1e6233954c0a1ce2a991dbd70522c8d64dd611a655fbe0011ac0d
+oid sha256:033d2edcf91400e7e05df9655654c43012ce54b45d76ed7b95e8c0821772d728
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.2001230716705322,
   "best_model_checkpoint": "miner_id_24/checkpoint-2550",
-  "epoch": 0.9685689868008737,
+  "epoch": 1.000094957743804,
   "eval_steps": 150,
-  "global_step": 2550,
+  "global_step": 2633,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1936,6 +1936,62 @@
       "eval_samples_per_second": 26.423,
       "eval_steps_per_second": 6.609,
       "step": 2550
+    },
+    {
+      "epoch": 0.9723672965530339,
+      "grad_norm": 1.9546929597854614,
+      "learning_rate": 1.969478955326509e-07,
+      "loss": 1.3771,
+      "step": 2560
+    },
+    {
+      "epoch": 0.9761656063051942,
+      "grad_norm": 2.411525249481201,
+      "learning_rate": 1.4670994081297795e-07,
+      "loss": 1.2084,
+      "step": 2570
+    },
+    {
+      "epoch": 0.9799639160573544,
+      "grad_norm": 2.34065580368042,
+      "learning_rate": 1.0384660197125806e-07,
+      "loss": 1.0336,
+      "step": 2580
+    },
+    {
+      "epoch": 0.9837622258095148,
+      "grad_norm": 3.2528553009033203,
+      "learning_rate": 6.836421962531648e-08,
+      "loss": 1.1792,
+      "step": 2590
+    },
+    {
+      "epoch": 0.987560535561675,
+      "grad_norm": 3.4945614337921143,
+      "learning_rate": 4.026804255491401e-08,
+      "loss": 1.0964,
+      "step": 2600
+    },
+    {
+      "epoch": 0.9913588453138353,
+      "grad_norm": 2.077958106994629,
+      "learning_rate": 1.9562226925340378e-08,
+      "loss": 1.3392,
+      "step": 2610
+    },
+    {
+      "epoch": 0.9951571550659957,
+      "grad_norm": 2.580904722213745,
+      "learning_rate": 6.249835672594851e-09,
+      "loss": 1.1596,
+      "step": 2620
+    },
+    {
+      "epoch": 0.9989554648181559,
+      "grad_norm": 3.186758279800415,
+      "learning_rate": 3.328380502876094e-10,
+      "loss": 1.1276,
+      "step": 2630
     }
   ],
   "logging_steps": 10,
@@ -1959,12 +2015,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.812908073811968e+18,
+  "total_flos": 1.8718053692001485e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null