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:b0231b86cc713006c3c5996c2907e1295643250df0a35978260b20f654876056
+oid sha256:8ae498e182638fef68ad672230770d9a49f56b106c0d336ab2435ad881784f02
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b39bc52d57b13350b0e3b4a3c15c7bbd2ad9fb2d44e81c0f4bc4408340f0da66
+oid sha256:731099ee4a0c607874df4619e32799223273a9d4870848c5033c2288be250b0e
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddc46dafdcd478911a2d112b886f5f6b51a01f701c9711feedb0d870982ec3d6
+oid sha256:ebe4f46029212195effcfa5f442db2f56dce773cf2e1968d8497240b1d9c41ff
 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": 1.27484130859375,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.08629989212513485,
+  "best_metric": 1.2255871295928955,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.12944983818770225,
   "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": 11.985,
       "eval_steps_per_second": 3.012,
       "step": 20
+    },
+    {
+      "epoch": 0.09061488673139159,
+      "grad_norm": 0.6437024474143982,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.2405,
+      "step": 21
+    },
+    {
+      "epoch": 0.10355987055016182,
+      "grad_norm": 0.5667445063591003,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.2117,
+      "step": 24
+    },
+    {
+      "epoch": 0.10787486515641856,
+      "eval_loss": 1.231518268585205,
+      "eval_runtime": 16.2792,
+      "eval_samples_per_second": 11.978,
+      "eval_steps_per_second": 3.01,
+      "step": 25
+    },
+    {
+      "epoch": 0.11650485436893204,
+      "grad_norm": 0.7320000529289246,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.2416,
+      "step": 27
+    },
+    {
+      "epoch": 0.12944983818770225,
+      "grad_norm": 0.7870640754699707,
+      "learning_rate": 0.0,
+      "loss": 1.2514,
+      "step": 30
+    },
+    {
+      "epoch": 0.12944983818770225,
+      "eval_loss": 1.2255871295928955,
+      "eval_runtime": 16.2717,
+      "eval_samples_per_second": 11.984,
+      "eval_steps_per_second": 3.011,
+      "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": 2.5391158788096e+16,
+  "total_flos": 3.8086738182144e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null