Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61645a2cc19e9fef2f495a9d2d3afea5c7d033ca4104e47b789e1d936051ae50
+oid sha256:dae952559dbd5d5f65187611fa5d8ddd64f95f8b49e9147b7c31afb13ffd4fe0
 size 28350504

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c0412a5698147e337708e873d737c598e3f03fcbffd32a2ca2c631c6d23fdab
+oid sha256:b5cbdd89d21d3379a80f494baf21d32fc7ce1bccb3f2909e8bd1f1d02dadf1b9
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:720bb0c5a83360dc4fc50fb4143e0cdd514576224bde50c8b9e06050df7f3cd7
+oid sha256:8c7be3ec8d831c1a603e9dfc1252a2ad7b9e331aa21842faf41df48c7b7deedc
 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": 0.3827160894870758,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.21052631578947367,
+  "best_metric": 0.36690789461135864,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.2631578947368421,
   "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": 10.034,
       "eval_steps_per_second": 5.017,
       "step": 20
+    },
+    {
+      "epoch": 0.22105263157894736,
+      "grad_norm": 1.524560809135437,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.3287,
+      "step": 21
+    },
+    {
+      "epoch": 0.23157894736842105,
+      "grad_norm": 1.800046682357788,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.7179,
+      "step": 22
+    },
+    {
+      "epoch": 0.24210526315789474,
+      "grad_norm": 1.430746078491211,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.2868,
+      "step": 23
+    },
+    {
+      "epoch": 0.25263157894736843,
+      "grad_norm": 1.7906553745269775,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.5813,
+      "step": 24
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 1.4507813453674316,
+      "learning_rate": 0.0,
+      "loss": 1.409,
+      "step": 25
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "eval_loss": 0.36690789461135864,
+      "eval_runtime": 3.9921,
+      "eval_samples_per_second": 10.02,
+      "eval_steps_per_second": 5.01,
+      "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": 597458807685120.0,
+  "total_flos": 746823509606400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null