Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cda792a384931a10a183b64edc925bceb042ddfa01d654d05ee17cd9d79b950
+oid sha256:ac187a685dadc1a711931d8cae57cd474d8b573687bc1211b08445914d8a8954
 size 47235968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bbddee9d3d9714d89f0a57e61aeb77963cf8c71a3b1fcf9977d4a9acb0770f5
+oid sha256:1affe048130586fa1f5f74c65695f5304e59664c8920e99c7f3f933b120d2591
 size 24410836

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7d5d48fcecd9394f8d62915f39f3e40d4f388910a340ed933c710b1001075f5
+oid sha256:8cd93b6e1737c240d4d01c3b7853912688e306646040515ddfc68fa5cd434e16
 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": 1.4445966482162476,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.025196850393700787,
+  "best_metric": 1.442267894744873,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.031496062992125984,
   "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": 6.14,
       "eval_steps_per_second": 3.079,
       "step": 20
+    },
+    {
+      "epoch": 0.026456692913385826,
+      "grad_norm": 2.4844489097595215,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.5382,
+      "step": 21
+    },
+    {
+      "epoch": 0.027716535433070868,
+      "grad_norm": 2.4937453269958496,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.4439,
+      "step": 22
+    },
+    {
+      "epoch": 0.028976377952755906,
+      "grad_norm": 2.5819883346557617,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.5551,
+      "step": 23
+    },
+    {
+      "epoch": 0.030236220472440945,
+      "grad_norm": 3.7339110374450684,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.5928,
+      "step": 24
+    },
+    {
+      "epoch": 0.031496062992125984,
+      "grad_norm": 2.678384304046631,
+      "learning_rate": 0.0,
+      "loss": 1.5929,
+      "step": 25
+    },
+    {
+      "epoch": 0.031496062992125984,
+      "eval_loss": 1.442267894744873,
+      "eval_runtime": 54.2131,
+      "eval_samples_per_second": 6.179,
+      "eval_steps_per_second": 3.099,
+      "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": 2598942246174720.0,
+  "total_flos": 3252764194897920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null