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:eb1111ddc7078adffcb6e576a04ba543b0b3c88325b3dc240094c12d27cdf647
+oid sha256:d069391417e05a785cdf33dc8a65cfded43eeb9d8145e6f2d789b79dd7525f57
 size 755015736

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15977995594987c6c8a1b5815dff1bc33a5799f32dc7558de55d318e949c2ca3
+oid sha256:5b0a7e606ced773ea5a4c5e38ca69c5f50b2c1624594d3d76d05a2b7a68c7899
 size 383724628

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3955cecb11d83931f03203ed20de052e3630e60bca6c5dcad6472d6af5600ab9
+oid sha256:c18679a31fb5ae364e36c6ee83677b746879ab660e5cd87bf7a59a9ada882583
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7708307d1b959a393541df6c657dca87476d08205aaca5feb82f751cfc227436
+oid sha256:93a4031351d40494c6fa2a2ab0690336e71553ec331e91c1b2ab832fe81468d8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.1609840393066406,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.005004629282085929,
+  "best_metric": 2.03886079788208,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.010009258564171859,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -93,6 +93,84 @@
       "eval_samples_per_second": 8.35,
       "eval_steps_per_second": 4.175,
       "step": 100
+    },
+    {
+      "epoch": 0.005505092210294523,
+      "grad_norm": 18.81438636779785,
+      "learning_rate": 2.7500000000000004e-05,
+      "loss": 8.4712,
+      "step": 110
+    },
+    {
+      "epoch": 0.006005555138503115,
+      "grad_norm": 16.96966552734375,
+      "learning_rate": 3e-05,
+      "loss": 8.4061,
+      "step": 120
+    },
+    {
+      "epoch": 0.006506018066711708,
+      "grad_norm": 18.02526092529297,
+      "learning_rate": 3.2500000000000004e-05,
+      "loss": 8.3852,
+      "step": 130
+    },
+    {
+      "epoch": 0.007006480994920301,
+      "grad_norm": 13.94727611541748,
+      "learning_rate": 3.5e-05,
+      "loss": 8.2849,
+      "step": 140
+    },
+    {
+      "epoch": 0.007506943923128894,
+      "grad_norm": 13.599745750427246,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 7.4514,
+      "step": 150
+    },
+    {
+      "epoch": 0.008007406851337487,
+      "grad_norm": 15.027945518493652,
+      "learning_rate": 4e-05,
+      "loss": 8.1085,
+      "step": 160
+    },
+    {
+      "epoch": 0.00850786977954608,
+      "grad_norm": 11.868462562561035,
+      "learning_rate": 4.25e-05,
+      "loss": 8.9385,
+      "step": 170
+    },
+    {
+      "epoch": 0.009008332707754673,
+      "grad_norm": 15.937177658081055,
+      "learning_rate": 4.5e-05,
+      "loss": 8.7974,
+      "step": 180
+    },
+    {
+      "epoch": 0.009508795635963267,
+      "grad_norm": 14.528044700622559,
+      "learning_rate": 4.75e-05,
+      "loss": 7.9633,
+      "step": 190
+    },
+    {
+      "epoch": 0.010009258564171859,
+      "grad_norm": 17.103893280029297,
+      "learning_rate": 5e-05,
+      "loss": 8.3624,
+      "step": 200
+    },
+    {
+      "epoch": 0.010009258564171859,
+      "eval_loss": 2.03886079788208,
+      "eval_runtime": 996.4987,
+      "eval_samples_per_second": 8.444,
+      "eval_steps_per_second": 4.222,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -116,12 +194,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.15735711973376e+17,
+  "total_flos": 2.31471423946752e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null