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:c9da86b1d8e7c84b109bf26a82bbb7b911658e02832d29dd0bbebb65b0f3d3b9
+oid sha256:f9639f76be304e91bf9aa5950e951b9363e7a0c123c2ec94bc515ad1abec91b3
 size 47235968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58a0d07b241190cc61ee1e0f9865fd2a244bbcebefcad14421321c1baf065030
+oid sha256:540f54430475a93d2261fd9f459f22faa2811d347aa9ad985022f9de50d81cd8
 size 24410836

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4311e0827e6853fc156c2d828430a1dd0fbcb9fbaa48ecfe44315c5e760b341
+oid sha256:74b03b492b125f9c57d72a3bb1731e05e8b2a2ed32844a00f45c14a8afc38860
 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": 1.9303518533706665,
   "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.006811409110259685,
+  "epoch": 0.008514261387824606,
   "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": 3.388,
       "eval_steps_per_second": 1.695,
       "step": 20
+    },
+    {
+      "epoch": 0.007151979565772669,
+      "grad_norm": 4.142763614654541,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.8279,
+      "step": 21
+    },
+    {
+      "epoch": 0.0074925500212856535,
+      "grad_norm": 26.084022521972656,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.8288,
+      "step": 22
+    },
+    {
+      "epoch": 0.007833120476798638,
+      "grad_norm": 5.616507530212402,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.9997,
+      "step": 23
+    },
+    {
+      "epoch": 0.008173690932311623,
+      "grad_norm": 4.470533847808838,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.9749,
+      "step": 24
+    },
+    {
+      "epoch": 0.008514261387824606,
+      "grad_norm": 3.6379683017730713,
+      "learning_rate": 0.0,
+      "loss": 0.953,
+      "step": 25
+    },
+    {
+      "epoch": 0.008514261387824606,
+      "eval_loss": 1.9331988096237183,
+      "eval_runtime": 357.497,
+      "eval_samples_per_second": 3.46,
+      "eval_steps_per_second": 1.731,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -201,7 +244,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2549905600020480.0,
+  "total_flos": 3187382000025600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null