Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e2bcc956227f41b0d79e968ed9c348cd435b2388841e5677e64d7af68efa391
+oid sha256:f31386f60ead97121458c9002a3b20697fbb2ae6e5d06627fda4bc1133ec1166
 size 216151256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:857cfcda8ed5ddc4f623876ce0fe1a73009dc6960d85535ce806f7d2258db696
+oid sha256:9388084f5846c66a28d7608ad550443ef348d4aef4111340704615b9d284c364
 size 432640054

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a2e3fad14d26f6ea46fe94037ced4fe638b7477bf22902c419eb7b02cb0ada5
+oid sha256:4e9cb4244ad970c616e7fbbb6b5313e00d285d065081e924bdda8bad952daa5a
 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": 4.8530731201171875,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0023399338968674134,
+  "best_metric": 4.81268310546875,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.00350990084530112,
   "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": 3.665,
       "eval_steps_per_second": 1.833,
       "step": 20
+    },
+    {
+      "epoch": 0.002456930591710784,
+      "grad_norm": 0.9035254120826721,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 4.9397,
+      "step": 21
+    },
+    {
+      "epoch": 0.0028079206762408964,
+      "grad_norm": 0.9409571290016174,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 4.8538,
+      "step": 24
+    },
+    {
+      "epoch": 0.002924917371084267,
+      "eval_loss": 4.822070121765137,
+      "eval_runtime": 983.2653,
+      "eval_samples_per_second": 3.66,
+      "eval_steps_per_second": 1.831,
+      "step": 25
+    },
+    {
+      "epoch": 0.0031589107607710083,
+      "grad_norm": 1.012995719909668,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 5.014,
+      "step": 27
+    },
+    {
+      "epoch": 0.00350990084530112,
+      "grad_norm": 1.2105016708374023,
+      "learning_rate": 0.0,
+      "loss": 4.8381,
+      "step": 30
+    },
+    {
+      "epoch": 0.00350990084530112,
+      "eval_loss": 4.81268310546875,
+      "eval_runtime": 982.856,
+      "eval_samples_per_second": 3.662,
+      "eval_steps_per_second": 1.831,
+      "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": 8339076988010496.0,
+  "total_flos": 1.2457139698139136e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null