Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07e4428ecd48851b3986c67f5b4cde5aa902ea16bcce61652fdc100660ba18df
+oid sha256:806bfe5ee9e9132b7ebe0fc687e1fc6f790005c90a489396d855551f48febe20
 size 28351000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cd5e784b93b6245fdb262d3e228d0c161bbec698284ea5ef7222c22660ab3b5
+oid sha256:5021bf55407e4b4add21007ce970528d2de0efc5cee9e71eb3a8a9ed51c8cd80
 size 56864954

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98c73acd1611361430c952163a5deb283e868c1eb83d40cd71e9806df85439f5
+oid sha256:bedb7013b67bbf8795c3720bde1f34a8ff4e2e48d689b7a981a2be83bc43f9b0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2d5f342d4229a407b143249c0b0919abc73174c3fbf690cf4dd4451580b8e09
+oid sha256:41e83f307180ac8f488ffa5d12e6485869ba276842bbc2776b54d5f280df42a5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.0528807640075684,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.004839685420447671,
+  "best_metric": 2.0509567260742188,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.006049606775559589,
   "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": 12.153,
       "eval_steps_per_second": 6.076,
       "step": 20
+    },
+    {
+      "epoch": 0.005081669691470054,
+      "grad_norm": 3.4139227867126465,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 8.1117,
+      "step": 21
+    },
+    {
+      "epoch": 0.005323653962492438,
+      "grad_norm": 2.6773757934570312,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 7.8244,
+      "step": 22
+    },
+    {
+      "epoch": 0.0055656382335148216,
+      "grad_norm": 2.016263246536255,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 6.493,
+      "step": 23
+    },
+    {
+      "epoch": 0.005807622504537205,
+      "grad_norm": 3.0851123332977295,
+      "learning_rate": 2.1852399266194312e-07,
+      "loss": 8.3326,
+      "step": 24
+    },
+    {
+      "epoch": 0.006049606775559589,
+      "grad_norm": 2.296729803085327,
+      "learning_rate": 0.0,
+      "loss": 7.2057,
+      "step": 25
+    },
+    {
+      "epoch": 0.006049606775559589,
+      "eval_loss": 2.0509567260742188,
+      "eval_runtime": 94.4647,
+      "eval_samples_per_second": 18.42,
+      "eval_steps_per_second": 9.21,
+      "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": 761852388704256.0,
+  "total_flos": 978457479610368.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null