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:f347d6f5f78aa10507f91dd2aa08a9c0fd510519d53937655f513a09085abc38
+oid sha256:29c141da3b43e65153bc0022c2d6be423f075f488b8975c78220f09112cfe83c
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c7cae9db963badd03c0433695fad625f6825d67ba10e6ecbd84a7736f1366a4
+oid sha256:75000eb20bb0ab2fab5c280e2e99d03a80a8d37986b76257f7a1371cfe967f84
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:019b308f45c7af9e678aee77b9c2e71dec9d5cc7433144da063c6bbb02b03df6
+oid sha256:18bee1f11df067472063341ab4b2e8fa593e863cc556df509b699d9c7cab4a42
 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": 1.0564022064208984,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.000643221252030167,
+  "best_metric": 1.0483996868133545,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0008040265650377089,
   "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": 7.854,
       "eval_steps_per_second": 3.927,
       "step": 20
+    },
+    {
+      "epoch": 0.0006753823146316754,
+      "grad_norm": 0.5676132440567017,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.2814,
+      "step": 21
+    },
+    {
+      "epoch": 0.0007075433772331837,
+      "grad_norm": 0.6557759642601013,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.2221,
+      "step": 22
+    },
+    {
+      "epoch": 0.0007397044398346921,
+      "grad_norm": 0.44837722182273865,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.7067,
+      "step": 23
+    },
+    {
+      "epoch": 0.0007718655024362004,
+      "grad_norm": 0.5179129242897034,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.872,
+      "step": 24
+    },
+    {
+      "epoch": 0.0008040265650377089,
+      "grad_norm": 0.41822654008865356,
+      "learning_rate": 0.0,
+      "loss": 0.9805,
+      "step": 25
+    },
+    {
+      "epoch": 0.0008040265650377089,
+      "eval_loss": 1.0483996868133545,
+      "eval_runtime": 1653.5958,
+      "eval_samples_per_second": 7.917,
+      "eval_steps_per_second": 3.959,
+      "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": 2009119229214720.0,
+  "total_flos": 2501148428206080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null