Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f11e4bef9d6460828b3a5690226999a69b5c863523be5cee9572047a35deb7b
+oid sha256:4f40eb937045386e9194b26b24dfd32d8ba8d8fb73ed41be3416a25c25e5b528
 size 104902272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fbc08072ecdcb1087e36bf92c6b091cf9d945b267c27e6c82081237cb631b0e
+oid sha256:c9f86696cdee92f722363298f681d74198fb73860d1e815c09035ecc9cc3068c
 size 53622996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa475f51346237b604de04dfb5849998c82ad8e092cda930a1bc5b8d1fca410b
+oid sha256:54000a22ed1e03e617e8ef255fb82f30282946acb9d4f185597661be658960f2
 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": 0.6784063577651978,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0211864406779661,
+  "best_metric": 0.6718564629554749,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.026483050847457626,
   "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": 6.91,
       "eval_steps_per_second": 3.455,
       "step": 20
+    },
+    {
+      "epoch": 0.022245762711864406,
+      "grad_norm": 3.1567599773406982,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 2.4357,
+      "step": 21
+    },
+    {
+      "epoch": 0.023305084745762712,
+      "grad_norm": 2.2508251667022705,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 2.3443,
+      "step": 22
+    },
+    {
+      "epoch": 0.024364406779661018,
+      "grad_norm": 3.499087333679199,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 2.6937,
+      "step": 23
+    },
+    {
+      "epoch": 0.025423728813559324,
+      "grad_norm": 2.6742749214172363,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.9363,
+      "step": 24
+    },
+    {
+      "epoch": 0.026483050847457626,
+      "grad_norm": 3.4136910438537598,
+      "learning_rate": 0.0,
+      "loss": 2.5089,
+      "step": 25
+    },
+    {
+      "epoch": 0.026483050847457626,
+      "eval_loss": 0.6718564629554749,
+      "eval_runtime": 57.9273,
+      "eval_samples_per_second": 6.871,
+      "eval_steps_per_second": 3.435,
+      "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": 6274650262732800.0,
+  "total_flos": 7843312828416000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null