Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11fe44fe8c83218998d60f6d45c46ba671810dc9968ccc81b1ee690d225a83e3
+oid sha256:625c92a0537632f8fa388819114a4e4c824c5c807538d0f6ea2c5cf6b7bc189a
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3591edc03454ccc3f8357bf58af5ed63716f0aa30d9251b6831ba0aa490d74d5
+oid sha256:4c867bc1e31e0493ff1e33186af3f77e699b3dc7ae68db07ecf171d53fcd0b52
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46fd0e0638d103d958d3a11581fa241a723e98e74de4a1c1eca4f2d49a3e1552
+oid sha256:58eb4e700095adf182456abd6778d04d29fb76a2a104cc5491951b57b3551746
 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": 3.345660924911499,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0027324270783523463,
+  "best_metric": 3.3368725776672363,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0034155338479404333,
   "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": 11.318,
       "eval_steps_per_second": 5.659,
       "step": 20
+    },
+    {
+      "epoch": 0.0028690484322699637,
+      "grad_norm": 0.5123682022094727,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 3.3068,
+      "step": 21
+    },
+    {
+      "epoch": 0.003005669786187581,
+      "grad_norm": 0.4870153069496155,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 3.3925,
+      "step": 22
+    },
+    {
+      "epoch": 0.0031422911401051985,
+      "grad_norm": 0.5168713927268982,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 3.3663,
+      "step": 23
+    },
+    {
+      "epoch": 0.003278912494022816,
+      "grad_norm": 0.4930650293827057,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 3.3488,
+      "step": 24
+    },
+    {
+      "epoch": 0.0034155338479404333,
+      "grad_norm": 0.28963905572891235,
+      "learning_rate": 0.0,
+      "loss": 3.2502,
+      "step": 25
+    },
+    {
+      "epoch": 0.0034155338479404333,
+      "eval_loss": 3.3368725776672363,
+      "eval_runtime": 272.0598,
+      "eval_samples_per_second": 11.328,
+      "eval_steps_per_second": 5.664,
+      "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": 1010378314088448.0,
+  "total_flos": 1266170292338688.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null