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:bd1e3267ec8349af281152e9369b50ad690fe7b02b651b83b6d45c8c2ad0df72
+oid sha256:c1864becdb4b173cbb1c0e64b6ca58ee66ece2d049dc0b0d894ceeca098717ba
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b7d1b0fad7e8790e7703eea4a1a4b269e56e627c03cdceaf99bb5a1d3921461
+oid sha256:284855d0ce69888835409430b2a66beb47cbe404008e15545380a4e871f66557
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4329764fc299dd85a84b7a55661e86fcab9bb1b815145a2c18430ce0fa85af0f
+oid sha256:e04d45842b4f57f7bc47c4b705d580a46ba323787f21a23ed4c2131d727599bb
 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": 0.673650860786438,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0004145271023001073,
+  "best_metric": 0.6515164971351624,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.000518158877875134,
   "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": 5.287,
       "eval_steps_per_second": 2.644,
       "step": 20
+    },
+    {
+      "epoch": 0.0004352534574151126,
+      "grad_norm": 6.2658281326293945,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 4.2788,
+      "step": 21
+    },
+    {
+      "epoch": 0.00045597981253011797,
+      "grad_norm": 2.940730571746826,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.2236,
+      "step": 22
+    },
+    {
+      "epoch": 0.00047670616764512334,
+      "grad_norm": 6.151371002197266,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 2.7089,
+      "step": 23
+    },
+    {
+      "epoch": 0.0004974325227601287,
+      "grad_norm": 7.25663423538208,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 2.9291,
+      "step": 24
+    },
+    {
+      "epoch": 0.000518158877875134,
+      "grad_norm": 11.405837059020996,
+      "learning_rate": 0.0,
+      "loss": 5.4171,
+      "step": 25
+    },
+    {
+      "epoch": 0.000518158877875134,
+      "eval_loss": 0.6515164971351624,
+      "eval_runtime": 3699.6936,
+      "eval_samples_per_second": 5.491,
+      "eval_steps_per_second": 2.746,
+      "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": 3257498484080640.0,
+  "total_flos": 4071873105100800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null