Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaaf6dccd7e53556b9896536674a6f93b1b87303cdb3e4d1780fdc8def332fd8
+oid sha256:83a790fbefd45352a41d0f9d732dae2391878b4839c7ac9ba079d4a840d39354
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50853924a5b6418f51f14b5b682b6250ac64083fa21dcda2a1212748a75b41a3
+oid sha256:5e9f2672dea3d251f2d283d1617ab8c6c9dfe1ab93396650560491dfa9a5b8d2
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8195f5f8ab0a2152863fee8331a14f0c6fd922ebfbe0783423b8278beeaadd3
+oid sha256:89ffcad5a84b06fde95717df10413749838a6b711ecc83f3ebee00a93d200145
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.6764440536499023,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.003429355281207133,
+  "best_metric": 3.657539129257202,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0042866941015089165,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 11.904,
       "eval_steps_per_second": 5.952,
       "step": 20
+    },
+    {
+      "epoch": 0.00360082304526749,
+      "grad_norm": 67.11266326904297,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 12.8917,
+      "step": 21
+    },
+    {
+      "epoch": 0.0037722908093278463,
+      "grad_norm": 72.69898223876953,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 13.5694,
+      "step": 22
+    },
+    {
+      "epoch": 0.003943758573388203,
+      "grad_norm": 55.905399322509766,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 15.623,
+      "step": 23
+    },
+    {
+      "epoch": 0.00411522633744856,
+      "grad_norm": 71.50740814208984,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 12.5749,
+      "step": 24
+    },
+    {
+      "epoch": 0.0042866941015089165,
+      "grad_norm": 76.84934997558594,
+      "learning_rate": 0.0,
+      "loss": 15.4344,
+      "step": 25
+    },
+    {
+      "epoch": 0.0042866941015089165,
+      "eval_loss": 3.657539129257202,
+      "eval_runtime": 206.8471,
+      "eval_samples_per_second": 11.874,
+      "eval_steps_per_second": 5.937,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 175457131560960.0,
+  "total_flos": 219321414451200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null