Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:687159b1891350cc0837e4056ffe615bb7526fbf604298dc124d013bf5fbd3ad
+oid sha256:790c5e970b3b6258b84934e72f3c97b4aa9d8acd03a9dc2200f1a0483a25be10
 size 28351000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42fb45d3e8eb9e0573024f335433c9713a867a7947fe5e3c77b6e63048f876ac
+oid sha256:4035f1d1f90c4b82a6c9439c3e991f5e462fe3c37c8ec9fcc9c14994c0fbb845
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b03384e6c87abd5ba54bff1717d946571936ef32e15c48eb05be7d308b93fc1
+oid sha256:d0da1474ec3a90cfdcf6f54df3477ef58bcaad845216d78bc90d6c2765665f38
 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": 0.7890741229057312,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.01132342533616419,
+  "best_metric": 0.7112417817115784,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.014154281670205236,
   "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": 10.534,
       "eval_steps_per_second": 5.267,
       "step": 20
+    },
+    {
+      "epoch": 0.0118895966029724,
+      "grad_norm": 7.1569929122924805,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 3.4385,
+      "step": 21
+    },
+    {
+      "epoch": 0.012455767869780608,
+      "grad_norm": 6.962759494781494,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 3.2144,
+      "step": 22
+    },
+    {
+      "epoch": 0.013021939136588818,
+      "grad_norm": 6.44915246963501,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 3.2704,
+      "step": 23
+    },
+    {
+      "epoch": 0.013588110403397028,
+      "grad_norm": 6.162975788116455,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 4.0834,
+      "step": 24
+    },
+    {
+      "epoch": 0.014154281670205236,
+      "grad_norm": 6.5062994956970215,
+      "learning_rate": 0.0,
+      "loss": 2.7477,
+      "step": 25
+    },
+    {
+      "epoch": 0.014154281670205236,
+      "eval_loss": 0.7112417817115784,
+      "eval_runtime": 73.5084,
+      "eval_samples_per_second": 10.121,
+      "eval_steps_per_second": 5.061,
+      "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": 612469567389696.0,
+  "total_flos": 769321529769984.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null