Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ce696d44c1f070d241d18260dc7bd8653b63a09ee21e2d01db44c29c2286933
+oid sha256:d76c78af0c0eadece1af0d29991a7c439e88cfb14c8f00fc3b01f2ec440dac8b
 size 528526760

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a86eca76b288fc988e2a59fe97d29b81e9009fd55dc23e9f9a332c3add0f1b64
+oid sha256:4ab99dce802006591bdcabdf749deaa66a6b3ed1220444529b9d829469815fdc
 size 268765332

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb3f225a79b6369dd206df86385b51dcba83d276cb6d9450815d5fc6522d8c4e
+oid sha256:57955a9008c7bdfb00a83dbc1b0aefb9714d870c6bb616093bfc39ebd7ee6400
 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": 0.5927267074584961,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.5154639175257731,
+  "best_metric": 0.5911697745323181,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.6872852233676976,
   "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": 9.221,
       "eval_steps_per_second": 2.315,
       "step": 150
+    },
+    {
+      "epoch": 0.5257731958762887,
+      "grad_norm": 0.4825039803981781,
+      "learning_rate": 1.435357758543015e-05,
+      "loss": 1.2003,
+      "step": 153
+    },
+    {
+      "epoch": 0.5360824742268041,
+      "grad_norm": 0.5744404196739197,
+      "learning_rate": 1.2658926150792322e-05,
+      "loss": 2.461,
+      "step": 156
+    },
+    {
+      "epoch": 0.5463917525773195,
+      "grad_norm": 0.6095325350761414,
+      "learning_rate": 1.1056136061894384e-05,
+      "loss": 2.5401,
+      "step": 159
+    },
+    {
+      "epoch": 0.5567010309278351,
+      "grad_norm": 0.6706549525260925,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.2518,
+      "step": 162
+    },
+    {
+      "epoch": 0.5670103092783505,
+      "grad_norm": 0.6379284262657166,
+      "learning_rate": 8.141676086873572e-06,
+      "loss": 2.214,
+      "step": 165
+    },
+    {
+      "epoch": 0.5773195876288659,
+      "grad_norm": 0.7004604339599609,
+      "learning_rate": 6.837175952121306e-06,
+      "loss": 2.2514,
+      "step": 168
+    },
+    {
+      "epoch": 0.5876288659793815,
+      "grad_norm": 0.6915513873100281,
+      "learning_rate": 5.6388590278194096e-06,
+      "loss": 2.4767,
+      "step": 171
+    },
+    {
+      "epoch": 0.5979381443298969,
+      "grad_norm": 0.7965708374977112,
+      "learning_rate": 4.549673247541875e-06,
+      "loss": 2.3281,
+      "step": 174
+    },
+    {
+      "epoch": 0.6082474226804123,
+      "grad_norm": 0.8681992292404175,
+      "learning_rate": 3.5722980755146517e-06,
+      "loss": 2.399,
+      "step": 177
+    },
+    {
+      "epoch": 0.6185567010309279,
+      "grad_norm": 0.9099557995796204,
+      "learning_rate": 2.7091379149682685e-06,
+      "loss": 2.2624,
+      "step": 180
+    },
+    {
+      "epoch": 0.6288659793814433,
+      "grad_norm": 0.971269965171814,
+      "learning_rate": 1.962316193157593e-06,
+      "loss": 2.4042,
+      "step": 183
+    },
+    {
+      "epoch": 0.6391752577319587,
+      "grad_norm": 1.0734204053878784,
+      "learning_rate": 1.333670137599713e-06,
+      "loss": 2.2968,
+      "step": 186
+    },
+    {
+      "epoch": 0.6494845360824743,
+      "grad_norm": 1.0781867504119873,
+      "learning_rate": 8.247462563808817e-07,
+      "loss": 2.4744,
+      "step": 189
+    },
+    {
+      "epoch": 0.6597938144329897,
+      "grad_norm": 1.2936267852783203,
+      "learning_rate": 4.367965336512403e-07,
+      "loss": 2.7197,
+      "step": 192
+    },
+    {
+      "epoch": 0.6701030927835051,
+      "grad_norm": 1.4144686460494995,
+      "learning_rate": 1.7077534966650766e-07,
+      "loss": 2.801,
+      "step": 195
+    },
+    {
+      "epoch": 0.6804123711340206,
+      "grad_norm": 1.5016579627990723,
+      "learning_rate": 2.7337132953697554e-08,
+      "loss": 3.0585,
+      "step": 198
+    },
+    {
+      "epoch": 0.6872852233676976,
+      "eval_loss": 0.5911697745323181,
+      "eval_runtime": 52.716,
+      "eval_samples_per_second": 9.295,
+      "eval_steps_per_second": 2.333,
+      "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": 1.9975701915697152e+17,
+  "total_flos": 2.6702813296130458e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null