Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08bcb3e0d7d1538bec63a22b5d2da9b1b93237b14e10e8beadd2d16ad6cf090f
+oid sha256:a74b748933bd703d51fbbaad5ee7c4cff2f7e3349785291c3523455190823f43
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11639c2b6218ad71f4f0b47557961921d15b426a6aa7979ba1745ba066aace8d
+oid sha256:73dba353e58dc6780ad26bb5e22cf152d53e6a0ec7d51fb3c1542f90dc92f056
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e797fb6926c3f4c2d2ccdbadbc6dfe459305f1a0db203359f9ee011767ae82a5
+oid sha256:bc815ac006f84205e1a46c9f874750bf2e86b13d6a4fe2f474151cb4ed03338a
 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": 1.0186785459518433,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.5063291139240507,
+  "best_metric": 1.0137192010879517,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.6329113924050633,
   "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": 4.402,
       "eval_steps_per_second": 2.33,
       "step": 20
+    },
+    {
+      "epoch": 0.5316455696202531,
+      "grad_norm": 16.88188362121582,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 4.3946,
+      "step": 21
+    },
+    {
+      "epoch": 0.5569620253164557,
+      "grad_norm": 15.035842895507812,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 4.1136,
+      "step": 22
+    },
+    {
+      "epoch": 0.5822784810126582,
+      "grad_norm": 15.598001480102539,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 4.5961,
+      "step": 23
+    },
+    {
+      "epoch": 0.6075949367088608,
+      "grad_norm": 13.525558471679688,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 3.6972,
+      "step": 24
+    },
+    {
+      "epoch": 0.6329113924050633,
+      "grad_norm": 11.98470687866211,
+      "learning_rate": 0.0,
+      "loss": 3.5662,
+      "step": 25
+    },
+    {
+      "epoch": 0.6329113924050633,
+      "eval_loss": 1.0137192010879517,
+      "eval_runtime": 3.7701,
+      "eval_samples_per_second": 4.509,
+      "eval_steps_per_second": 2.387,
+      "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": 3505339571896320.0,
+  "total_flos": 4381674464870400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null