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:e31d059a58523abaae0ddeffb76c2da6a9df97bfffce2108437948f4878269ae
+oid sha256:1977fd80fd84d71be673f1eefc1d8d744db55a097bdc08d15fe617de39b63e00
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56cbbbe9a53e2a859952aefba5201bd5aefa0db1573234ec941bfa33b1c6661a
+oid sha256:fed31eba2e0d464fd5f8acd4fa6654237323e5642e19f093d5f82f1075911dcf
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:647617a5b8873881ec555b7bbc314145999492030dd45fc0b6e58c2f7c8f80a1
+oid sha256:9da5a813961377a63b3b595b381c172f72283276ff92e706eca229e08c9f946b
 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": 1.1164677143096924,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.040160642570281124,
+  "best_metric": 1.1069023609161377,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.050200803212851405,
   "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": 5.115,
       "eval_steps_per_second": 2.558,
       "step": 20
+    },
+    {
+      "epoch": 0.04216867469879518,
+      "grad_norm": 0.7288839817047119,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.1363,
+      "step": 21
+    },
+    {
+      "epoch": 0.04417670682730924,
+      "grad_norm": 0.81972736120224,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.0716,
+      "step": 22
+    },
+    {
+      "epoch": 0.04618473895582329,
+      "grad_norm": 0.6999672055244446,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.0502,
+      "step": 23
+    },
+    {
+      "epoch": 0.04819277108433735,
+      "grad_norm": 0.7532836198806763,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.0596,
+      "step": 24
+    },
+    {
+      "epoch": 0.050200803212851405,
+      "grad_norm": 0.6574884057044983,
+      "learning_rate": 0.0,
+      "loss": 0.9523,
+      "step": 25
+    },
+    {
+      "epoch": 0.050200803212851405,
+      "eval_loss": 1.1069023609161377,
+      "eval_runtime": 40.9698,
+      "eval_samples_per_second": 5.126,
+      "eval_steps_per_second": 2.563,
+      "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": 4346475983142912.0,
+  "total_flos": 5317497213419520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null