Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7681dcf33e4a3764bebeefb8fa0fba2ee8f3acb9875109778363b66d75c678b9
+oid sha256:1e6a73f08b7e1f5e941a80f7ebf55d215cbb6b75a1ac6c4e13fc8ef7cd392c9f
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3045366b307950658dab0e4e641ce0706a627102e01d92b61cf4149e6b1d053d
+oid sha256:3b8f9fc6579b84a71c64b3d4d3cdd471925b0884c536973e2a6d61191edeb5e0
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:309ae5284f0eab6e59937f47a0594dd123863a474cdfe6d07a7dbf6403c77da0
+oid sha256:7569190b3d76ee2af1a25230a6b2f36227432159f4ba9b48f67ded6a1d8e43ac
 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": 3.565016269683838,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.01805869074492099,
+  "best_metric": 3.5254595279693604,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.022573363431151242,
   "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": 6.41,
       "eval_steps_per_second": 3.212,
       "step": 20
+    },
+    {
+      "epoch": 0.018961625282167043,
+      "grad_norm": 1.2683284282684326,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 3.4791,
+      "step": 21
+    },
+    {
+      "epoch": 0.019864559819413093,
+      "grad_norm": 1.385071873664856,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 3.6829,
+      "step": 22
+    },
+    {
+      "epoch": 0.02076749435665914,
+      "grad_norm": 1.4484951496124268,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 3.4422,
+      "step": 23
+    },
+    {
+      "epoch": 0.02167042889390519,
+      "grad_norm": 1.30351722240448,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 3.6403,
+      "step": 24
+    },
+    {
+      "epoch": 0.022573363431151242,
+      "grad_norm": 1.307582974433899,
+      "learning_rate": 0.0,
+      "loss": 3.5491,
+      "step": 25
+    },
+    {
+      "epoch": 0.022573363431151242,
+      "eval_loss": 3.5254595279693604,
+      "eval_runtime": 72.7632,
+      "eval_samples_per_second": 6.418,
+      "eval_steps_per_second": 3.216,
+      "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": 3659535696789504.0,
+  "total_flos": 4530853719834624.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null