Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0dfcfd6c1a9979993fc0973b9bf41185fe001389cbdfc56c72e6415d3a2df67
+oid sha256:c048a07517bafd7ece4ff51baf4a7c003eeefe4cdf881def088a3b96a4c272a4
 size 186962

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98a0d874f8c0c1aa35b2e704f5c128a3bc84dfce7c2070c3e65834eb03df51fa
+oid sha256:270c1f503e95ee788beaff5d2b585d663b5f203659e7f7d9bd4f466589570127
 size 121430

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b73b43b2e6e7654f681327fbc9d8864ac66d7432ad9f407444f6bf6170764eb9
+oid sha256:57f103553ccd91c62a5573bcd9df27b1afa1a11876221074b56904954f3a1852
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 6.934159755706787,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.001766433350261653,
+  "best_metric": 6.932753086090088,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0026496500253924793,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 218.188,
       "eval_steps_per_second": 109.094,
       "step": 20
+    },
+    {
+      "epoch": 0.0018547550177747355,
+      "grad_norm": 0.09853053092956543,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 6.9372,
+      "step": 21
+    },
+    {
+      "epoch": 0.0021197200203139834,
+      "grad_norm": 0.0869535282254219,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 6.9341,
+      "step": 24
+    },
+    {
+      "epoch": 0.002208041687827066,
+      "eval_loss": 6.932971000671387,
+      "eval_runtime": 21.6757,
+      "eval_samples_per_second": 219.97,
+      "eval_steps_per_second": 109.985,
+      "step": 25
+    },
+    {
+      "epoch": 0.0023846850228532316,
+      "grad_norm": 0.08586609363555908,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 6.9328,
+      "step": 27
+    },
+    {
+      "epoch": 0.0026496500253924793,
+      "grad_norm": 0.09244760870933533,
+      "learning_rate": 0.0,
+      "loss": 6.9335,
+      "step": 30
+    },
+    {
+      "epoch": 0.0026496500253924793,
+      "eval_loss": 6.932753086090088,
+      "eval_runtime": 21.673,
+      "eval_samples_per_second": 219.997,
+      "eval_steps_per_second": 109.998,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 112704196608.0,
+  "total_flos": 167951351808.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null