Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:291043bd750e74876ec805c688a970cd4891d5e54c5d802601b5336d44188976
+oid sha256:b4f34886da9ef5de0b4c8caea31b21ed46539b1044ade656d7cf60782aabf0b0
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6ecbb222469e768c81b8ef94a8b75c6051f82780d7c81e9c4fe3648b87c64be
+oid sha256:bdee419162cadd576af659445bcc70670f4ffb4ef60936833510fb313cbacb85
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbb92ceee37a3625aebc2d35b6d4627b5a6df79ff497d84d5a62fe17d38cea8d
+oid sha256:aa4197d717315536c763bf157df4545293a243ce84417e8380dbdb2a365e10ed
 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": 1.3764064311981201,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.011379800853485065,
+  "best_metric": 1.3719592094421387,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.01422475106685633,
   "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": 6.378,
       "eval_steps_per_second": 3.189,
       "step": 20
+    },
+    {
+      "epoch": 0.011948790896159318,
+      "grad_norm": 2.581949234008789,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 5.8999,
+      "step": 21
+    },
+    {
+      "epoch": 0.01251778093883357,
+      "grad_norm": 2.7319865226745605,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 5.0108,
+      "step": 22
+    },
+    {
+      "epoch": 0.013086770981507824,
+      "grad_norm": 1.8899096250534058,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 3.3853,
+      "step": 23
+    },
+    {
+      "epoch": 0.013655761024182077,
+      "grad_norm": 3.539898633956909,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 8.5112,
+      "step": 24
+    },
+    {
+      "epoch": 0.01422475106685633,
+      "grad_norm": 3.2797906398773193,
+      "learning_rate": 0.0,
+      "loss": 5.732,
+      "step": 25
+    },
+    {
+      "epoch": 0.01422475106685633,
+      "eval_loss": 1.3719592094421387,
+      "eval_runtime": 117.6658,
+      "eval_samples_per_second": 6.289,
+      "eval_steps_per_second": 3.144,
+      "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": 4193987824975872.0,
+  "total_flos": 5415537676910592.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null