Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:953be3a656373376c66a6830714687bf84fd7d7d7cb55019b7aba47fc9665150
+oid sha256:4f315408a26120922332452f6c84ac4c7783ea08f9b679fe04a848ba2d785cad
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8426979b814d0ed0bfb1e9b46084cb08c2086115d8bcd50f4855198958ddb7ff
+oid sha256:11e06ea34c9debb1c0ed08c766ad44682d56cef852dea2b0bfe37431690c1cfd
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7997d407d530053dc265970b89da31e783b48e60cf7d581555906a0d35844b5e
+oid sha256:fb2c8d71d0efd6e93322d8f63cd9a7be0c68810d7b3e048410058b278e34c772
 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": 1.3281397819519043,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.049049662783568364,
+  "best_metric": 1.3211456537246704,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.061312078479460456,
   "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": 4.683,
       "eval_steps_per_second": 2.341,
       "step": 20
+    },
+    {
+      "epoch": 0.05150214592274678,
+      "grad_norm": 1.299329161643982,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.9771,
+      "step": 21
+    },
+    {
+      "epoch": 0.0539546290619252,
+      "grad_norm": 1.4647064208984375,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.0974,
+      "step": 22
+    },
+    {
+      "epoch": 0.056407112201103615,
+      "grad_norm": 1.6498510837554932,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.2246,
+      "step": 23
+    },
+    {
+      "epoch": 0.05885959534028203,
+      "grad_norm": 1.297864317893982,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.0874,
+      "step": 24
+    },
+    {
+      "epoch": 0.061312078479460456,
+      "grad_norm": 1.972848892211914,
+      "learning_rate": 0.0,
+      "loss": 1.5734,
+      "step": 25
+    },
+    {
+      "epoch": 0.061312078479460456,
+      "eval_loss": 1.3211456537246704,
+      "eval_runtime": 36.4113,
+      "eval_samples_per_second": 4.724,
+      "eval_steps_per_second": 2.362,
+      "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": 6352059230060544.0,
+  "total_flos": 7858637380780032.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null