Training in progress, step 353, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07d192aa1c9ce20fd264be177399627c549841ba4a3dcbe785cfdc6ff6e4acf4
+oid sha256:2d3ff58eeee3ae62a711e0314c27c55314de64205003fdc4a75183fa55bd3d27
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a08f49a47f3ea1d7622dfb86c37c67c48b24de609d9cf949a91fafec68666c5
+oid sha256:dd3e50bf67e76265b0c210bffafe99b94ceaeff1658dc42160a448a7e28b1a80
 size 170920532

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:616d5591fe2815fb845a002baa0bbc69990e73ea586e4a98cd405180dd111c49
+oid sha256:06d6141e0b9d9f5f984794ce954b9078957203871211247fa1b668ae6e0e521b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35792e2ed51bf6bc8a2a5bf1bcfa90fe1bca1ed12b3ff3e83b15d68253c4d18f
+oid sha256:0646e2d3555f1eaa1a9314ce40f829334a461b68ebc04a7605c70254bd9b820b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7150752544403076,
   "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 2.5531914893617023,
+  "epoch": 3.0042553191489363,
   "eval_steps": 50,
-  "global_step": 300,
+  "global_step": 353,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,49 @@
       "eval_samples_per_second": 13.255,
       "eval_steps_per_second": 3.347,
       "step": 300
+    },
+    {
+      "epoch": 2.6382978723404253,
+      "grad_norm": 1.1086422204971313,
+      "learning_rate": 7.655920535292682e-06,
+      "loss": 0.4461,
+      "step": 310
+    },
+    {
+      "epoch": 2.723404255319149,
+      "grad_norm": 1.3774492740631104,
+      "learning_rate": 4.5331549815317174e-06,
+      "loss": 0.3016,
+      "step": 320
+    },
+    {
+      "epoch": 2.8085106382978724,
+      "grad_norm": 0.9642128944396973,
+      "learning_rate": 2.2107034853789288e-06,
+      "loss": 0.6109,
+      "step": 330
+    },
+    {
+      "epoch": 2.8936170212765955,
+      "grad_norm": 1.332884669303894,
+      "learning_rate": 7.080355346981815e-07,
+      "loss": 0.375,
+      "step": 340
+    },
+    {
+      "epoch": 2.978723404255319,
+      "grad_norm": 1.325518250465393,
+      "learning_rate": 3.774823882738421e-08,
+      "loss": 0.3026,
+      "step": 350
+    },
+    {
+      "epoch": 2.978723404255319,
+      "eval_loss": 0.7016637921333313,
+      "eval_runtime": 14.9416,
+      "eval_samples_per_second": 13.252,
+      "eval_steps_per_second": 3.346,
+      "step": 350
     }
   ],
   "logging_steps": 10,
@@ -296,12 +339,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.5087006702698496e+17,
+  "total_flos": 5.304600571422966e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null