Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fdc23f1213146453a075053e93bc4cbc4caf0d1904286b8e30e0dbf5b4795b1
+oid sha256:dc12462ca7c2eb2783f06292be272b881128aab149a1183517a244410a60fce9
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3386e4d9cbb35b7a15e6a94f035e296499d252beb243cb2aa31b83947ceb5d8
+oid sha256:a0e92c2f48c55889e13bd9bcab7e50be4a35183b119582b1bae835ec25200975
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ddb7b575b177a0f4a3c1bf5ad5c41eb95c3cd6853ac85a61ebf5719b0e442ff
+oid sha256:5f6869356922108343853dceb1e71746d53aa03e85331228bc0aabfff29bb927
 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": 1.443589687347412,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.023682652457075192,
+  "best_metric": 1.441811203956604,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.02960331557134399,
   "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": 6.362,
       "eval_steps_per_second": 3.181,
       "step": 20
+    },
+    {
+      "epoch": 0.02486678507992895,
+      "grad_norm": 0.8491754531860352,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.5677,
+      "step": 21
+    },
+    {
+      "epoch": 0.02605091770278271,
+      "grad_norm": 0.9003405570983887,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.6864,
+      "step": 22
+    },
+    {
+      "epoch": 0.027235050325636473,
+      "grad_norm": 0.6072733402252197,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.6922,
+      "step": 23
+    },
+    {
+      "epoch": 0.028419182948490232,
+      "grad_norm": 1.0873887538909912,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.8884,
+      "step": 24
+    },
+    {
+      "epoch": 0.02960331557134399,
+      "grad_norm": 1.862977147102356,
+      "learning_rate": 0.0,
+      "loss": 1.9757,
+      "step": 25
+    },
+    {
+      "epoch": 0.02960331557134399,
+      "eval_loss": 1.441811203956604,
+      "eval_runtime": 55.8826,
+      "eval_samples_per_second": 6.371,
+      "eval_steps_per_second": 3.185,
+      "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": 276018307792896.0,
+  "total_flos": 347248838836224.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null