Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d12397d45147bac9e5e6fdae31237e485ac823e0b718654b6c856755fbf1518
+oid sha256:603b53e1da057aba7610d570a4130c066304791bfcf8154c9dbb400f9644fbfc
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02751c23a12d8f9f83a24bf49269fffc7f86ddea9e867a9ef5603c266c38216e
+oid sha256:4bc36c8c5096e7b18eff858396e5bc149ab7975de1faedbbdc6aa767b2b66d44
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2334bb0640575dd250ddc034f0866b4a4968457b2c304412fc5bfe7daa198c97
+oid sha256:35f0137b849c03395474ca0dd71f16bff6b7fbd0049e6137a02e7b0d861804fb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8780689239501953,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0010044951156425001,
+  "best_metric": 0.8393291234970093,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0015067426734637502,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 6.473,
       "eval_steps_per_second": 3.237,
       "step": 20
+    },
+    {
+      "epoch": 0.0010547198714246251,
+      "grad_norm": 1.8058075904846191,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 3.4074,
+      "step": 21
+    },
+    {
+      "epoch": 0.0012053941387710002,
+      "grad_norm": 1.1432996988296509,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.8904,
+      "step": 24
+    },
+    {
+      "epoch": 0.0012556188945531252,
+      "eval_loss": 0.8457621932029724,
+      "eval_runtime": 1295.6909,
+      "eval_samples_per_second": 6.471,
+      "eval_steps_per_second": 3.235,
+      "step": 25
+    },
+    {
+      "epoch": 0.0013560684061173752,
+      "grad_norm": 0.801946222782135,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 4.3029,
+      "step": 27
+    },
+    {
+      "epoch": 0.0015067426734637502,
+      "grad_norm": 2.0867886543273926,
+      "learning_rate": 0.0,
+      "loss": 3.3963,
+      "step": 30
+    },
+    {
+      "epoch": 0.0015067426734637502,
+      "eval_loss": 0.8393291234970093,
+      "eval_runtime": 1295.3608,
+      "eval_samples_per_second": 6.472,
+      "eval_steps_per_second": 3.236,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6032849689903104.0,
+  "total_flos": 9164405254127616.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null