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:afbe529f63f112a26ae509bc8ef4a13b2fa17a4b7e29eb45120e79325c15e340
+oid sha256:7869395e54479768fb7a9b899dc438b5baac32e48f0cc680e38f1c9dfed833bf
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bca7a949d965604c43341b303fc67209ea2e164114fda0f799cb2e091e184c4d
+oid sha256:db1c6e1565834742855a8706ed363573e888926d1d6cc6ba32aedbd853a7a975
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dac6304c3d282c68b3b54b02e10f7ccb87b4af7f30bf7c763231322312d8a778
+oid sha256:4f474396eecfe9e2fdb32279c7633ecfaa4a13ca05fa0d113fea1216d0a56fc5
 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": 1.2818273305892944,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0032550758839565447,
+  "best_metric": 1.2690883874893188,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0040688448549456805,
   "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": 7.066,
       "eval_steps_per_second": 3.533,
       "step": 20
+    },
+    {
+      "epoch": 0.003417829678154372,
+      "grad_norm": 0.7662570476531982,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.2233,
+      "step": 21
+    },
+    {
+      "epoch": 0.003580583472352199,
+      "grad_norm": 0.8125593066215515,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.2485,
+      "step": 22
+    },
+    {
+      "epoch": 0.0037433372665500266,
+      "grad_norm": 0.6410349011421204,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.2007,
+      "step": 23
+    },
+    {
+      "epoch": 0.003906091060747854,
+      "grad_norm": 0.6851560473442078,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.2007,
+      "step": 24
+    },
+    {
+      "epoch": 0.0040688448549456805,
+      "grad_norm": 0.494051992893219,
+      "learning_rate": 0.0,
+      "loss": 1.0691,
+      "step": 25
+    },
+    {
+      "epoch": 0.0040688448549456805,
+      "eval_loss": 1.2690883874893188,
+      "eval_runtime": 360.8957,
+      "eval_samples_per_second": 7.171,
+      "eval_steps_per_second": 3.586,
+      "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": 3257466271825920.0,
+  "total_flos": 4071832839782400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null