Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07752f8f824d33e5969ebb88cf88efbbeef0cd239ec5655d3832bbba227715b0
+oid sha256:efbf0dccdb814b2d7d2fa13cc5d2c8e81230b0c54483411cb309264084e7150e
 size 78207176

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81a1d369a6c699e3f4a3f42d8d54df7feee285b627e8600204c369be3c35c20e
+oid sha256:cab0c65b01baf01fd0aabb5d5cbc483748638bef85e11eb209aac3b660581e6e
 size 40177764

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1543d263cdd4788ae1417e978dead81d20d5840d1e3b4221fcebdc0828dd8bd1
+oid sha256:de115c072803c252542859e1816fd43f8d4ef7d5909a1cde82f59143886bebba
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8ce05761f46e7cf72fb17a02e3a0ca15c9d25ce3babf590eeb40568923b8bac
+oid sha256:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.44607609510421753,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.14566642388929352,
+  "best_metric": 0.4413750171661377,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.19422189851905802,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -389,6 +389,126 @@
       "eval_samples_per_second": 65.662,
       "eval_steps_per_second": 16.425,
       "step": 150
+    },
+    {
+      "epoch": 0.14857975236707938,
+      "grad_norm": 0.38435041904449463,
+      "learning_rate": 1.435357758543015e-05,
+      "loss": 0.5631,
+      "step": 153
+    },
+    {
+      "epoch": 0.15149308084486526,
+      "grad_norm": 0.33270201086997986,
+      "learning_rate": 1.2658926150792322e-05,
+      "loss": 0.623,
+      "step": 156
+    },
+    {
+      "epoch": 0.15440640932265112,
+      "grad_norm": 0.22977907955646515,
+      "learning_rate": 1.1056136061894384e-05,
+      "loss": 0.4877,
+      "step": 159
+    },
+    {
+      "epoch": 0.157319737800437,
+      "grad_norm": 0.21603785455226898,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.4403,
+      "step": 162
+    },
+    {
+      "epoch": 0.16023306627822287,
+      "grad_norm": 0.209615558385849,
+      "learning_rate": 8.141676086873572e-06,
+      "loss": 0.4224,
+      "step": 165
+    },
+    {
+      "epoch": 0.16314639475600873,
+      "grad_norm": 0.18484285473823547,
+      "learning_rate": 6.837175952121306e-06,
+      "loss": 0.4118,
+      "step": 168
+    },
+    {
+      "epoch": 0.16605972323379461,
+      "grad_norm": 0.18960103392601013,
+      "learning_rate": 5.6388590278194096e-06,
+      "loss": 0.4072,
+      "step": 171
+    },
+    {
+      "epoch": 0.16897305171158047,
+      "grad_norm": 0.16774511337280273,
+      "learning_rate": 4.549673247541875e-06,
+      "loss": 0.366,
+      "step": 174
+    },
+    {
+      "epoch": 0.17188638018936636,
+      "grad_norm": 0.18589498102664948,
+      "learning_rate": 3.5722980755146517e-06,
+      "loss": 0.3681,
+      "step": 177
+    },
+    {
+      "epoch": 0.17479970866715222,
+      "grad_norm": 0.18734581768512726,
+      "learning_rate": 2.7091379149682685e-06,
+      "loss": 0.3482,
+      "step": 180
+    },
+    {
+      "epoch": 0.17771303714493808,
+      "grad_norm": 0.19667771458625793,
+      "learning_rate": 1.962316193157593e-06,
+      "loss": 0.3446,
+      "step": 183
+    },
+    {
+      "epoch": 0.18062636562272397,
+      "grad_norm": 0.2224486619234085,
+      "learning_rate": 1.333670137599713e-06,
+      "loss": 0.3361,
+      "step": 186
+    },
+    {
+      "epoch": 0.18353969410050983,
+      "grad_norm": 0.18418388068675995,
+      "learning_rate": 8.247462563808817e-07,
+      "loss": 0.3035,
+      "step": 189
+    },
+    {
+      "epoch": 0.1864530225782957,
+      "grad_norm": 0.21602746844291687,
+      "learning_rate": 4.367965336512403e-07,
+      "loss": 0.311,
+      "step": 192
+    },
+    {
+      "epoch": 0.18936635105608157,
+      "grad_norm": 0.23305264115333557,
+      "learning_rate": 1.7077534966650766e-07,
+      "loss": 0.2924,
+      "step": 195
+    },
+    {
+      "epoch": 0.19227967953386743,
+      "grad_norm": 0.290690541267395,
+      "learning_rate": 2.7337132953697554e-08,
+      "loss": 0.5002,
+      "step": 198
+    },
+    {
+      "epoch": 0.19422189851905802,
+      "eval_loss": 0.4413750171661377,
+      "eval_runtime": 25.429,
+      "eval_samples_per_second": 68.229,
+      "eval_steps_per_second": 17.067,
+      "step": 200
     }
   ],
   "logging_steps": 3,
@@ -412,12 +532,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4320127639093248.0,
+  "total_flos": 5747809305231360.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null