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:fb276611db3566ffa0598c8e3202ab83d93fa2fff87da8519eb01f727c43f6e0
+oid sha256:a60e6f99741fbceebd2a9909036f92b38418d4a7b14cadd66d23e1b943463281
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:482d7ca14eb907ce0cdf19560648226144f7f69b63a8b8ee17775b96b896e5d9
+oid sha256:a82c30fe2548ee0b0e9a6d9a19edc42d87553c4c443a1f7a8bf11bc9e3abdf5a
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8d0ca5f94c74be21f7e258f478e4f1bcf339ab697a95d852a0fd9b800d39d6b
+oid sha256:0cd0f468fa70a1cf7fad818916de3bad4e117e8ec50f05116c03d5cfd88dd0a8
 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": 0.8007434606552124,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.011981428785382657,
+  "best_metric": 0.7949571013450623,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.014976785981728321,
   "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": 5.17,
       "eval_steps_per_second": 2.589,
       "step": 20
+    },
+    {
+      "epoch": 0.01258050022465179,
+      "grad_norm": 0.24885857105255127,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.808,
+      "step": 21
+    },
+    {
+      "epoch": 0.013179571663920923,
+      "grad_norm": 0.2443242073059082,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.7911,
+      "step": 22
+    },
+    {
+      "epoch": 0.013778643103190056,
+      "grad_norm": 0.24952025711536407,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.8286,
+      "step": 23
+    },
+    {
+      "epoch": 0.014377714542459188,
+      "grad_norm": 0.3030417263507843,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.8526,
+      "step": 24
+    },
+    {
+      "epoch": 0.014976785981728321,
+      "grad_norm": 0.2920050024986267,
+      "learning_rate": 0.0,
+      "loss": 0.8023,
+      "step": 25
+    },
+    {
+      "epoch": 0.014976785981728321,
+      "eval_loss": 0.7949571013450623,
+      "eval_runtime": 132.7035,
+      "eval_samples_per_second": 5.298,
+      "eval_steps_per_second": 2.653,
+      "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": 6591291693465600.0,
+  "total_flos": 8197919043747840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null