Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13032aab77aa5a9ec4a194bf2d391b85d3e6eca5779fd4f0f2d11528eea58f50
+oid sha256:0fed9830d3eab6ddef1068d253ea27dd77ccce3c3ea2be70aeff114275923284
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c5bdfc0f361961a993ba6ddd236298a757c9fc50048551fbee63d2ba588eeee
+oid sha256:edbd2f752fc70b56f8749a19bbaca17b9831a40ef0e076f73401fd4634efcfbb
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39ccd5622448d5b4793f7c0320456317dd3c53025e79a98eaa0b1029556f2441
+oid sha256:49859fd65550fc3d94748874ab6a3d346b6b7fe947c09a0f4eb1fdf4fea495ee
 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": 2.9242584705352783,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.023121387283236993,
+  "best_metric": 2.8908660411834717,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.028901734104046242,
   "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": 8.793,
       "eval_steps_per_second": 4.408,
       "step": 20
+    },
+    {
+      "epoch": 0.024277456647398842,
+      "grad_norm": 10.60115909576416,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 3.2212,
+      "step": 21
+    },
+    {
+      "epoch": 0.025433526011560695,
+      "grad_norm": 6.316830635070801,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.8785,
+      "step": 22
+    },
+    {
+      "epoch": 0.026589595375722544,
+      "grad_norm": 5.971985340118408,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 2.141,
+      "step": 23
+    },
+    {
+      "epoch": 0.027745664739884393,
+      "grad_norm": 7.20245885848999,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 2.9188,
+      "step": 24
+    },
+    {
+      "epoch": 0.028901734104046242,
+      "grad_norm": 6.70047664642334,
+      "learning_rate": 0.0,
+      "loss": 2.8176,
+      "step": 25
+    },
+    {
+      "epoch": 0.028901734104046242,
+      "eval_loss": 2.8908660411834717,
+      "eval_runtime": 41.6166,
+      "eval_samples_per_second": 8.771,
+      "eval_steps_per_second": 4.397,
+      "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": 180302281703424.0,
+  "total_flos": 227047317700608.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null