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:f4c203f19086334c9de1a5b2058f64fe7b4a1596b21e8f287d684b28e5608136
+oid sha256:ae942d37eedf5051d4284e6b101c205ff62067e12afb464b5f400d5b67f4e5b9
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:199e52e529ce01316f03305c8e6af8e88e608de19d3d78f8780e7aa5aed20eee
+oid sha256:dc691e7a2a6cdd407a1e7dc2ebdda2642eb7f99c62a3541edd243d9f173d8502
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1220ba00c1f2dd5abd7cf374a8575654b945f7674928bf0cc1765b63a4620fdd
+oid sha256:943637ce3b1c2680799f713ec6990baccdc12047a9c513f31997c3a1d99b2c1e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.0383806228637695,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.014272970561998216,
+  "best_metric": 2.0195255279541016,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.021409455842997322,
   "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": 3.504,
       "eval_steps_per_second": 1.752,
       "step": 20
+    },
+    {
+      "epoch": 0.014986619090098127,
+      "grad_norm": 1.3492414951324463,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 8.193,
+      "step": 21
+    },
+    {
+      "epoch": 0.01712756467439786,
+      "grad_norm": 0.8906028270721436,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 8.0867,
+      "step": 24
+    },
+    {
+      "epoch": 0.01784121320249777,
+      "eval_loss": 2.0230188369750977,
+      "eval_runtime": 168.4697,
+      "eval_samples_per_second": 3.502,
+      "eval_steps_per_second": 1.751,
+      "step": 25
+    },
+    {
+      "epoch": 0.01926851025869759,
+      "grad_norm": 0.8579123020172119,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 7.9533,
+      "step": 27
+    },
+    {
+      "epoch": 0.021409455842997322,
+      "grad_norm": 0.9165276288986206,
+      "learning_rate": 0.0,
+      "loss": 8.1795,
+      "step": 30
+    },
+    {
+      "epoch": 0.021409455842997322,
+      "eval_loss": 2.0195255279541016,
+      "eval_runtime": 168.4856,
+      "eval_samples_per_second": 3.502,
+      "eval_steps_per_second": 1.751,
+      "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": 1.1353948195651584e+16,
+  "total_flos": 1.6826714592116736e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null