Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66ae35d54eadc05b0cc2e4c63799d4aa3ee7f09b5011558c4ee362c661bc370f
+oid sha256:3dd3dd7526d98801fefa7f1af5f44984d0b49463e6fe3b6d86b2402f9886abf4
 size 598799664

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cb89a57283f79f07cb71f0e9f0c78af5f17fdd954d58987850117d5895e6165
+oid sha256:4f474944acdf5e547cedc4a4b73d51c6c8984fa33d385af8a90d4e0f32c5151e
 size 167987322

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35065c6e466e3b1a6e927aae2bc007780adcfae5e57fb17b718b3e1e775e7d48
+oid sha256:ecb4b92126ccce52af63e1b3c0b799b1c3fffc85eedcccf39957c001ee1de29c
 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": 2.3386573791503906,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.022592487997740753,
+  "best_metric": 2.3060646057128906,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.033888731996611125,
   "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": 36.273,
       "eval_steps_per_second": 9.093,
       "step": 20
+    },
+    {
+      "epoch": 0.02372211239762779,
+      "grad_norm": 2.5795583724975586,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 8.1209,
+      "step": 21
+    },
+    {
+      "epoch": 0.027110985597288903,
+      "grad_norm": 3.074751138687134,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 8.8405,
+      "step": 24
+    },
+    {
+      "epoch": 0.02824060999717594,
+      "eval_loss": 2.3135273456573486,
+      "eval_runtime": 20.7121,
+      "eval_samples_per_second": 36.018,
+      "eval_steps_per_second": 9.029,
+      "step": 25
+    },
+    {
+      "epoch": 0.030499858796950014,
+      "grad_norm": 3.1419811248779297,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 8.4288,
+      "step": 27
+    },
+    {
+      "epoch": 0.033888731996611125,
+      "grad_norm": 3.825042247772217,
+      "learning_rate": 0.0,
+      "loss": 9.2565,
+      "step": 30
+    },
+    {
+      "epoch": 0.033888731996611125,
+      "eval_loss": 2.3060646057128906,
+      "eval_runtime": 20.6441,
+      "eval_samples_per_second": 36.136,
+      "eval_steps_per_second": 9.058,
+      "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": 5440868324474880.0,
+  "total_flos": 8062973541089280.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null