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:cdce8db0a46688aefd26693558bcf5d41d053a79f8a5b8503eb68f5fbf4ba001
+oid sha256:848aa0dfd8d5684fb32503ca577729c310ea5b449bbabfd0297ca45fe7c733fe
 size 51431872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43b7fdc3edb0f3d8048b002243dd76db11e317c81a3d0282081c8112bae98854
+oid sha256:5f05c36ca560a8830911459dc846ce79ca6cb33c598d07965f07ee0754a8a22f
 size 26550260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc46e58008fcfaf26de2fc50b7a399e2d6e44f2214266c62484151ce8f2a61a1
+oid sha256:6f2ec64b5bc1a5dee2c141e3e217e5feaa4634a87a716b0ea918096c3fa7861f
 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": 1.3025113344192505,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.004067314047485892,
+  "best_metric": 1.297785758972168,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.005084142559357364,
   "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": 9.374,
       "eval_steps_per_second": 4.689,
       "step": 20
+    },
+    {
+      "epoch": 0.004270679749860186,
+      "grad_norm": 1.1468011140823364,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.2028,
+      "step": 21
+    },
+    {
+      "epoch": 0.004474045452234481,
+      "grad_norm": 1.34481680393219,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.3829,
+      "step": 22
+    },
+    {
+      "epoch": 0.004677411154608775,
+      "grad_norm": 1.1907427310943604,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.3303,
+      "step": 23
+    },
+    {
+      "epoch": 0.0048807768569830694,
+      "grad_norm": 1.314353346824646,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.3435,
+      "step": 24
+    },
+    {
+      "epoch": 0.005084142559357364,
+      "grad_norm": 1.2799979448318481,
+      "learning_rate": 0.0,
+      "loss": 1.2447,
+      "step": 25
+    },
+    {
+      "epoch": 0.005084142559357364,
+      "eval_loss": 1.297785758972168,
+      "eval_runtime": 215.0958,
+      "eval_samples_per_second": 9.628,
+      "eval_steps_per_second": 4.816,
+      "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": 1540684932710400.0,
+  "total_flos": 1921100965478400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null