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:d3be3595694aee48516db4d130f56814c74ec80dba52232817d447134181fe49
+oid sha256:59f022225ea2baae6e983413057cf1b7f1843e054f3f639d462bb2948fe3905c
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6012dd04db19a05ace29ef32386128e9fa552071c3d3d09069b9304dfdcaaa76
+oid sha256:ca4b4f2c98c9f87e86b21525657458a81dfe0a5b6df4fb136ca732561c1a31f5
 size 68874

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5288ed9323916daf49e9e619b5ce81ab40c19e01021e3ee0c12210ac8bab7de
+oid sha256:4542ee77b862586921f712605c9da4a157f7c6fb74687d0b6cef8d69e7a87363
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.930218696594238,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0018859473349206724,
+  "best_metric": 11.930188179016113,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0028289210023810085,
   "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": 34.405,
       "eval_steps_per_second": 17.203,
       "step": 20
+    },
+    {
+      "epoch": 0.001980244701666706,
+      "grad_norm": 0.010103181004524231,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 11.9325,
+      "step": 21
+    },
+    {
+      "epoch": 0.0022631368019048067,
+      "grad_norm": 0.008972418494522572,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 11.9303,
+      "step": 24
+    },
+    {
+      "epoch": 0.0023574341686508405,
+      "eval_loss": 11.930191040039062,
+      "eval_runtime": 129.6099,
+      "eval_samples_per_second": 34.457,
+      "eval_steps_per_second": 17.229,
+      "step": 25
+    },
+    {
+      "epoch": 0.0025460289021429078,
+      "grad_norm": 0.016690155491232872,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 11.9294,
+      "step": 27
+    },
+    {
+      "epoch": 0.0028289210023810085,
+      "grad_norm": 0.009384451434016228,
+      "learning_rate": 0.0,
+      "loss": 11.9296,
+      "step": 30
+    },
+    {
+      "epoch": 0.0028289210023810085,
+      "eval_loss": 11.930188179016113,
+      "eval_runtime": 129.6679,
+      "eval_samples_per_second": 34.442,
+      "eval_steps_per_second": 17.221,
+      "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": 14989393920.0,
+  "total_flos": 22484090880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null