Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdd8dd8d069dd5c75a3e424b85f4d13382b6c86bc05cc911ebf92da15f8a1fe0
+oid sha256:4ee4b1ce48768e5344496a44dc56cd29753ef9bf73f9468321446431c2fbcb3b
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5504ebdbd2f7e9cf940369b990abe257dfe79e6dd7545676351f27ccbf8ee600
+oid sha256:0222bb52b2ce67f679285e4001db5ae1bd3c566584ea848eef1fd32e56f7b0bd
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7577594cb2e923f0986dcd66099d06bc38653ca89937b5665a0cf443b5a214d8
+oid sha256:ed4fa3443e28c3061ef70b82b3361b3c366300745782c921cc5ff4d66bdea1d8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6da36b358afefa2fe6fe8e3889efc77dfb89ac577ed7bb55c631123a9ebe149
+oid sha256:56e06160672e234a504b2a9f8fb3d80ed8c221e80fde36a5548d37e259bd5bc6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.571736454963684,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.12886597938144329,
+  "best_metric": 1.5677101612091064,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.1718213058419244,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 20.402,
       "eval_steps_per_second": 5.121,
       "step": 150
+    },
+    {
+      "epoch": 0.13745704467353953,
+      "grad_norm": 0.5671700239181519,
+      "learning_rate": 2.2444444444444445e-06,
+      "loss": 1.4621,
+      "step": 160
+    },
+    {
+      "epoch": 0.14604810996563575,
+      "grad_norm": 0.6307945847511292,
+      "learning_rate": 1.6833333333333332e-06,
+      "loss": 1.5589,
+      "step": 170
+    },
+    {
+      "epoch": 0.15463917525773196,
+      "grad_norm": 0.6016616225242615,
+      "learning_rate": 1.1222222222222222e-06,
+      "loss": 1.5354,
+      "step": 180
+    },
+    {
+      "epoch": 0.16323024054982818,
+      "grad_norm": 0.6347000598907471,
+      "learning_rate": 5.611111111111111e-07,
+      "loss": 1.5171,
+      "step": 190
+    },
+    {
+      "epoch": 0.1718213058419244,
+      "grad_norm": 1.540158987045288,
+      "learning_rate": 0.0,
+      "loss": 1.5985,
+      "step": 200
+    },
+    {
+      "epoch": 0.1718213058419244,
+      "eval_loss": 1.5677101612091064,
+      "eval_runtime": 24.0604,
+      "eval_samples_per_second": 20.365,
+      "eval_steps_per_second": 5.112,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -167,12 +210,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.4914993790976e+16,
+  "total_flos": 5.9886658387968e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null