Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4127c980eac77587c0b1933e69073451354b8e54e1c703136a15d202bbf91d94
+oid sha256:1e69a9addc50e85000c84fe3cc9cb394ff28d79ebf01fdb1374d03415ae4d548
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd692111081981e02c5c09410e65782c8bad3042b9ee4750aeeb4e0abc09c950
+oid sha256:b2eca54df4f107a1e09c0f071cc5bd5746f6372053b1b176905838eea5411905
 size 243802484

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2851e8f92f874eb01944fbbf64bc99a585e3bb3d42c7469979757e5ce1fc45d
+oid sha256:b8ebc859d3b6aea770d4ec9e058aa76309f7c69a9871d10444f1ef5ff0af920d
 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": 1.3861536979675293,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.01588057805304113,
+  "best_metric": 1.379766821861267,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.021174104070721508,
   "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": 21.083,
       "eval_steps_per_second": 5.271,
       "step": 150
+    },
+    {
+      "epoch": 0.016198189614101955,
+      "grad_norm": 0.32772377133369446,
+      "learning_rate": 1.435357758543015e-05,
+      "loss": 1.7939,
+      "step": 153
+    },
+    {
+      "epoch": 0.016515801175162777,
+      "grad_norm": 0.3464511036872864,
+      "learning_rate": 1.2658926150792322e-05,
+      "loss": 1.6867,
+      "step": 156
+    },
+    {
+      "epoch": 0.0168334127362236,
+      "grad_norm": 0.34471413493156433,
+      "learning_rate": 1.1056136061894384e-05,
+      "loss": 1.7035,
+      "step": 159
+    },
+    {
+      "epoch": 0.01715102429728442,
+      "grad_norm": 0.36518341302871704,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.6862,
+      "step": 162
+    },
+    {
+      "epoch": 0.017468635858345245,
+      "grad_norm": 0.3403802514076233,
+      "learning_rate": 8.141676086873572e-06,
+      "loss": 1.5212,
+      "step": 165
+    },
+    {
+      "epoch": 0.017786247419406067,
+      "grad_norm": 0.4222329556941986,
+      "learning_rate": 6.837175952121306e-06,
+      "loss": 1.6224,
+      "step": 168
+    },
+    {
+      "epoch": 0.01810385898046689,
+      "grad_norm": 0.3984784483909607,
+      "learning_rate": 5.6388590278194096e-06,
+      "loss": 1.5183,
+      "step": 171
+    },
+    {
+      "epoch": 0.01842147054152771,
+      "grad_norm": 0.40187868475914,
+      "learning_rate": 4.549673247541875e-06,
+      "loss": 1.6794,
+      "step": 174
+    },
+    {
+      "epoch": 0.018739082102588536,
+      "grad_norm": 0.5658180713653564,
+      "learning_rate": 3.5722980755146517e-06,
+      "loss": 1.6408,
+      "step": 177
+    },
+    {
+      "epoch": 0.019056693663649357,
+      "grad_norm": 0.46127259731292725,
+      "learning_rate": 2.7091379149682685e-06,
+      "loss": 1.5629,
+      "step": 180
+    },
+    {
+      "epoch": 0.01937430522471018,
+      "grad_norm": 0.4690566062927246,
+      "learning_rate": 1.962316193157593e-06,
+      "loss": 1.6688,
+      "step": 183
+    },
+    {
+      "epoch": 0.019691916785771,
+      "grad_norm": 0.8716459274291992,
+      "learning_rate": 1.333670137599713e-06,
+      "loss": 1.5046,
+      "step": 186
+    },
+    {
+      "epoch": 0.020009528346831826,
+      "grad_norm": 0.9283012747764587,
+      "learning_rate": 8.247462563808817e-07,
+      "loss": 1.1988,
+      "step": 189
+    },
+    {
+      "epoch": 0.020327139907892647,
+      "grad_norm": 1.0773875713348389,
+      "learning_rate": 4.367965336512403e-07,
+      "loss": 0.7527,
+      "step": 192
+    },
+    {
+      "epoch": 0.02064475146895347,
+      "grad_norm": 1.0661638975143433,
+      "learning_rate": 1.7077534966650766e-07,
+      "loss": 0.8329,
+      "step": 195
+    },
+    {
+      "epoch": 0.02096236303001429,
+      "grad_norm": 0.9259282946586609,
+      "learning_rate": 2.7337132953697554e-08,
+      "loss": 0.6728,
+      "step": 198
+    },
+    {
+      "epoch": 0.021174104070721508,
+      "eval_loss": 1.379766821861267,
+      "eval_runtime": 754.2612,
+      "eval_samples_per_second": 21.091,
+      "eval_steps_per_second": 5.273,
+      "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": 8.550478613210726e+16,
+  "total_flos": 1.1395895788988006e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null