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:bfe8c0223b52ba3fe228238bf1d005b3835d4689dcdab164e997f18712f20bb9
+oid sha256:4903eb50dc6c7833612a1f6d403ab256ee2ef24fb1b24612e7b95ebc5da36129
 size 194563400

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3271710e70e63d65182fb89397014f805ae51189daef2173ec339825d30646da
+oid sha256:6e655bbc55e19ccf4d11678292be9728de3e67a42f9ea2a779886075b4e56bb6
 size 99235764

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d982dac13dadc995a80b9a388ea5bc5d7f7d197ecadea97f5d4f0c4b01c54bd
+oid sha256:8a4200de673a560886726f41fc9fabafdd4342fd885d154065fdd86ad3fa782f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5220d0af0ff98b2d6e04334f1c29842da7230747bf3383cf1f883a4d2eb6d4f2
+oid sha256:90c455b2a7603e9003556345290fd0185bd6c6017de2b595e3f9c6216f721e5e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5379198789596558,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.08347245409015025,
+  "best_metric": 1.5319938659667969,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.11129660545353366,
   "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": 22.334,
       "eval_steps_per_second": 5.583,
       "step": 150
+    },
+    {
+      "epoch": 0.08903728436282693,
+      "grad_norm": 1.5008553266525269,
+      "learning_rate": 2.2644444444444443e-06,
+      "loss": 1.5019,
+      "step": 160
+    },
+    {
+      "epoch": 0.09460211463550362,
+      "grad_norm": 1.5986566543579102,
+      "learning_rate": 1.6983333333333333e-06,
+      "loss": 1.5492,
+      "step": 170
+    },
+    {
+      "epoch": 0.1001669449081803,
+      "grad_norm": 2.096254825592041,
+      "learning_rate": 1.1322222222222221e-06,
+      "loss": 1.5176,
+      "step": 180
+    },
+    {
+      "epoch": 0.10573177518085698,
+      "grad_norm": 2.102479934692383,
+      "learning_rate": 5.661111111111111e-07,
+      "loss": 1.5102,
+      "step": 190
+    },
+    {
+      "epoch": 0.11129660545353366,
+      "grad_norm": 2.5668249130249023,
+      "learning_rate": 0.0,
+      "loss": 1.6017,
+      "step": 200
+    },
+    {
+      "epoch": 0.11129660545353366,
+      "eval_loss": 1.5319938659667969,
+      "eval_runtime": 25.4304,
+      "eval_samples_per_second": 22.335,
+      "eval_steps_per_second": 5.584,
+      "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": 1.58554373750784e+16,
+  "total_flos": 2.11405831667712e+16,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null