Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44b13c6f630aa2beb59468833d38c529427b5f746b7de85995eb82c29cae174e
+oid sha256:67f9c1dae02e80d9a8a72a314c2999f4d2a2bfabf184eeb697dead534da68dc8
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3760bdda6da915b795e4774a6ec7994c149684c5a0becd8dcc91521927065bb8
+oid sha256:7fc8059390d3236f30be98eefdc130e6cf1389db620af8450dfaea6a2e88a594
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e48edcebabf5e5f11375e5ac67145183527090086d1b3209c2358749ad54019d
+oid sha256:7dedab70212eddb2b980ebeec8a6b9ca41d6b8f39c40109ba92a09284e0291d8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.715874195098877,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.02274019329164298,
+  "best_metric": 2.6250178813934326,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.03411028993746447,
   "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": 6.93,
       "eval_steps_per_second": 1.739,
       "step": 20
+    },
+    {
+      "epoch": 0.023877202956225127,
+      "grad_norm": 2.694730281829834,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 2.5534,
+      "step": 21
+    },
+    {
+      "epoch": 0.027288231949971573,
+      "grad_norm": 2.9070112705230713,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.4852,
+      "step": 24
+    },
+    {
+      "epoch": 0.028425241614553724,
+      "eval_loss": 2.633150815963745,
+      "eval_runtime": 106.8832,
+      "eval_samples_per_second": 6.933,
+      "eval_steps_per_second": 1.74,
+      "step": 25
+    },
+    {
+      "epoch": 0.030699260943718023,
+      "grad_norm": 2.6632487773895264,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 2.2376,
+      "step": 27
+    },
+    {
+      "epoch": 0.03411028993746447,
+      "grad_norm": 2.7979321479797363,
+      "learning_rate": 0.0,
+      "loss": 2.2537,
+      "step": 30
+    },
+    {
+      "epoch": 0.03411028993746447,
+      "eval_loss": 2.6250178813934326,
+      "eval_runtime": 107.086,
+      "eval_samples_per_second": 6.92,
+      "eval_steps_per_second": 1.737,
+      "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": 1.5529610821238784e+16,
+  "total_flos": 2.3198554436665344e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null