Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:547c917db58de51b098d49e3a84bdbf9ea9050521e16d26061bebf4b90eb38b4
+oid sha256:e446e25b8f0815eea7aaf774df14fba870c0e51aa06caed2df64e298ffa8b913
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:840b02fc900fd966e2da1e898e1a34ae9b4746fab84cbb533f41b3bc40f83fbf
+oid sha256:add5871092596407eada28a95b636bff2ea110118f46f6b4029809bb8150b213
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45aa182b328bfe02d781c42616bdb5443d5352aa5d5ba6c53863c2f340c940a8
+oid sha256:bc045242530a55f97e8c9426fcd38ba66445e0f6d809d7700c07d1a8763b79c9
 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": 0.6928964853286743,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.007357674974707992,
+  "best_metric": 0.6772711277008057,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.00919709371838499,
   "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": 7.405,
       "eval_steps_per_second": 3.706,
       "step": 20
+    },
+    {
+      "epoch": 0.0077255587234433916,
+      "grad_norm": 3.7068471908569336,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.8884,
+      "step": 21
+    },
+    {
+      "epoch": 0.008093442472178792,
+      "grad_norm": 3.6140143871307373,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.6753,
+      "step": 22
+    },
+    {
+      "epoch": 0.008461326220914191,
+      "grad_norm": 3.1367030143737793,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.7285,
+      "step": 23
+    },
+    {
+      "epoch": 0.00882920996964959,
+      "grad_norm": 3.196237802505493,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.6392,
+      "step": 24
+    },
+    {
+      "epoch": 0.00919709371838499,
+      "grad_norm": 3.408621311187744,
+      "learning_rate": 0.0,
+      "loss": 0.7336,
+      "step": 25
+    },
+    {
+      "epoch": 0.00919709371838499,
+      "eval_loss": 0.6772711277008057,
+      "eval_runtime": 159.0853,
+      "eval_samples_per_second": 7.197,
+      "eval_steps_per_second": 3.602,
+      "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": 1000194661416960.0,
+  "total_flos": 1250243326771200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null