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:d9ac58a0f8c8d5e8d20630153039d6e18a1d82ef9ec86f21946eceb591127ca5
+oid sha256:e7e91640d35fad9cee939c9a7830fbc58b778428a0e4a3acdf09a83124b7fd05
 size 32856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f79c999348abc4d033904783646869cdecd9f5fbf8950ee3e8c54d9d5527c29
+oid sha256:bc42c5522d8e58efd850c3d093975239203fc937febba92f82e4ac06968538aa
 size 71358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea24ba22f005ab5531315a7c25fe17ce3b0d82d32e4d057cd4a8d9beeaa0eb4
+oid sha256:299d23360d7a54a8825a43f53dabca9fdb8881a0bbe18cb34ee611999db10cca
 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": 11.0792875289917,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.012391573729863693,
+  "best_metric": 11.07884407043457,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.015489467162329617,
   "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": 85.512,
       "eval_steps_per_second": 42.756,
       "step": 20
+    },
+    {
+      "epoch": 0.013011152416356878,
+      "grad_norm": 0.4977034330368042,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 22.1334,
+      "step": 21
+    },
+    {
+      "epoch": 0.013630731102850062,
+      "grad_norm": 0.5370666980743408,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 22.1515,
+      "step": 22
+    },
+    {
+      "epoch": 0.014250309789343246,
+      "grad_norm": 0.490833580493927,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 22.1616,
+      "step": 23
+    },
+    {
+      "epoch": 0.01486988847583643,
+      "grad_norm": 0.5239782929420471,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 22.1252,
+      "step": 24
+    },
+    {
+      "epoch": 0.015489467162329617,
+      "grad_norm": 0.4305998980998993,
+      "learning_rate": 0.0,
+      "loss": 22.1351,
+      "step": 25
+    },
+    {
+      "epoch": 0.015489467162329617,
+      "eval_loss": 11.07884407043457,
+      "eval_runtime": 4.4846,
+      "eval_samples_per_second": 75.816,
+      "eval_steps_per_second": 37.908,
+      "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": 7471104000.0,
+  "total_flos": 9338880000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null