Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e530fb5666a8e9931ed39eebf117cb7e0f8057a80042ec2e3fa3377419656d7
+oid sha256:216d2b60ae53eeb9c2d2358ea478a0f8578316177382ecb0e18176468600f5c4
 size 10636352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fd452e947d5cc6ab9bc84f92d57b0152199b1d426c274ab3736cea18abe8c38
+oid sha256:49a22ce3a1df7ae704baf8dc8c84291ddd7388d6f221d9533b60daee28bdade7
 size 21354682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45269856b728fac5cfaac138cf7e3724e79e6314de3916255f142a0124689bc9
+oid sha256:0f4f875ef0d4996733cdaa17309c172da8982959b1daa83aa12a098a3df66345
 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": 1.565661072731018,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.023168259484506227,
+  "best_metric": 1.5479834079742432,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.03475238922675934,
   "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": 119.563,
       "eval_steps_per_second": 59.781,
       "step": 20
+    },
+    {
+      "epoch": 0.02432667245873154,
+      "grad_norm": 3.117314338684082,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 6.6441,
+      "step": 21
+    },
+    {
+      "epoch": 0.02780191138140747,
+      "grad_norm": 2.933971881866455,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 6.4136,
+      "step": 24
+    },
+    {
+      "epoch": 0.028960324355632783,
+      "eval_loss": 1.5526163578033447,
+      "eval_runtime": 3.1354,
+      "eval_samples_per_second": 116.095,
+      "eval_steps_per_second": 58.048,
+      "step": 25
+    },
+    {
+      "epoch": 0.03127715030408341,
+      "grad_norm": 3.571547746658325,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 6.5279,
+      "step": 27
+    },
+    {
+      "epoch": 0.03475238922675934,
+      "grad_norm": 2.7521469593048096,
+      "learning_rate": 0.0,
+      "loss": 6.3489,
+      "step": 30
+    },
+    {
+      "epoch": 0.03475238922675934,
+      "eval_loss": 1.5479834079742432,
+      "eval_runtime": 3.0454,
+      "eval_samples_per_second": 119.523,
+      "eval_steps_per_second": 59.762,
+      "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": 86222642872320.0,
+  "total_flos": 129333964308480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null