Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:440520052f31c0a29112837855e6363ab86d151525b850cb30d7caccfea5627d
+oid sha256:4ddd62920c920e2ff0c0fc5ee5f565dfee2f7f507c4f2062f6becc465f5b0c32
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03b1462ef8ec0711c50e87b70d30dc24bf343b1c598f2461d5153d177a788d1f
+oid sha256:bfd1dff9ab0a7c85539f0503f091761c8ab18a876b8ec3cc884b530be430142a
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b493b863b6181972a0fd4d4d3e2649671dd1a1cbd9865f922e7ab18a1988e1c6
+oid sha256:a39ed17a65b4c97f0de96db76cf0c8be1f1118759a975579bac6f49af09bbd38
 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": 0.7646981477737427,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.05082592121982211,
+  "best_metric": 0.7207484245300293,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.06353240152477764,
   "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": 6.592,
       "eval_steps_per_second": 3.296,
       "step": 20
+    },
+    {
+      "epoch": 0.053367217280813214,
+      "grad_norm": 4.5308027267456055,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.7881,
+      "step": 21
+    },
+    {
+      "epoch": 0.05590851334180432,
+      "grad_norm": 5.688116550445557,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.0006,
+      "step": 22
+    },
+    {
+      "epoch": 0.05844980940279543,
+      "grad_norm": 4.038796901702881,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.5519,
+      "step": 23
+    },
+    {
+      "epoch": 0.060991105463786534,
+      "grad_norm": 4.334105491638184,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.5561,
+      "step": 24
+    },
+    {
+      "epoch": 0.06353240152477764,
+      "grad_norm": 4.820201396942139,
+      "learning_rate": 0.0,
+      "loss": 0.6645,
+      "step": 25
+    },
+    {
+      "epoch": 0.06353240152477764,
+      "eval_loss": 0.7207484245300293,
+      "eval_runtime": 26.4772,
+      "eval_samples_per_second": 6.27,
+      "eval_steps_per_second": 3.135,
+      "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": 3976632389861376.0,
+  "total_flos": 4993910443081728.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null