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:e29034eea91acc30e317255de8de7cde98f564731e38bf821143d6486da3e619
+oid sha256:66681b2dcbe5d912bd842f593cf238133db526e609029fd08c09338b78d53ceb
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:602949b8f3787ae7539156d7d343942f9b365ef21404e969d51ec0e4d9b6d0c3
+oid sha256:a43178824f5e3bd4f656082b2892fb0705d2d3b0b1c28f9d357c3e80cb5a47c8
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8080d838ff199c055d8fdfbac0b743832528f3bed5c636607beb4b966705f0e
+oid sha256:01814cb81162b8611233369b867799028071d2c6a0269ee4a16db7343ba80bd4
 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": 1.108259916305542,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0006005329730135495,
+  "best_metric": 1.077322244644165,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0007506662162669369,
   "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": 4.666,
       "eval_steps_per_second": 2.333,
       "step": 20
+    },
+    {
+      "epoch": 0.000630559621664227,
+      "grad_norm": 2.9704768657684326,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.0222,
+      "step": 21
+    },
+    {
+      "epoch": 0.0006605862703149045,
+      "grad_norm": 2.5651001930236816,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.9873,
+      "step": 22
+    },
+    {
+      "epoch": 0.000690612918965582,
+      "grad_norm": 2.4585671424865723,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.8469,
+      "step": 23
+    },
+    {
+      "epoch": 0.0007206395676162595,
+      "grad_norm": 2.9926390647888184,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.0686,
+      "step": 24
+    },
+    {
+      "epoch": 0.0007506662162669369,
+      "grad_norm": 3.01412034034729,
+      "learning_rate": 0.0,
+      "loss": 1.1191,
+      "step": 25
+    },
+    {
+      "epoch": 0.0007506662162669369,
+      "eval_loss": 1.077322244644165,
+      "eval_runtime": 2962.2095,
+      "eval_samples_per_second": 4.734,
+      "eval_steps_per_second": 2.367,
+      "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": 8548751266283520.0,
+  "total_flos": 1.044847376990208e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null