Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03c2a65430bd61253928bfe33868cdcdaea814b96e59c61a1fb1640ebc23e7b3
+oid sha256:5a31f0c9838d4dc73562adc582186ea0ae7baf081a7fd8d98269559df9583556
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af6a5f216b5971d55102bfa27cc50a519f9be6d38671859049b12fce15fb23f3
+oid sha256:ae97483be59fafbe1c59c5051466bc20527f4bdc60de77b11a02c26f7e082b57
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93c5dbfca96fbc3be73f639441958a2b5dec3618a60f8720413295565cbd6752
+oid sha256:5ecfaaaaee50e5a2c100aa8fa1460946ceca21c43c0d6895685b68857feb90b1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4c9c807f0681c8b7e53ada9b6ec3dba530d303de7da0d0a0562a3d8d0bbba08
+oid sha256:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.668142318725586,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.0143448012049633,
+  "best_metric": 2.528531074523926,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.019126401606617736,
   "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": 13.417,
       "eval_steps_per_second": 3.354,
       "step": 150
+    },
+    {
+      "epoch": 0.015301121285294188,
+      "grad_norm": 6.281269550323486,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 10.05,
+      "step": 160
+    },
+    {
+      "epoch": 0.016257441365625076,
+      "grad_norm": 8.143268585205078,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 9.996,
+      "step": 170
+    },
+    {
+      "epoch": 0.01721376144595596,
+      "grad_norm": 10.60354232788086,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.0405,
+      "step": 180
+    },
+    {
+      "epoch": 0.01817008152628685,
+      "grad_norm": 13.499201774597168,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 10.43,
+      "step": 190
+    },
+    {
+      "epoch": 0.019126401606617736,
+      "grad_norm": 48.44270706176758,
+      "learning_rate": 0.0,
+      "loss": 11.0191,
+      "step": 200
+    },
+    {
+      "epoch": 0.019126401606617736,
+      "eval_loss": 2.528531074523926,
+      "eval_runtime": 1311.7316,
+      "eval_samples_per_second": 13.427,
+      "eval_steps_per_second": 3.357,
+      "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": 2.1679644236945818e+17,
+  "total_flos": 2.887041732543775e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null