Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06eda2cafef271e06d9a4085ccbc3a97f184a6b2730a8be885903a2150496b2a
+oid sha256:988d25394f6d2eb7deb7bf6ef5d92af863fb201078d7924a6ed8113c3b88c593
 size 338298

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05a21fd6ce335b07ba69a8fa00edd57913eb9c053a3fa3eaf1335ad2e9a562eb
+oid sha256:56da0fa8cdcd6a52459814ab88a39813185ef53aa148fed37e61966e6f426f77
 size 418030

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c10e2d53728a771186d6fda9768e46c47919b7ab630313acb560cb6162f649c
+oid sha256:11cc396d23cc0c797eef3b46c1c4ba411a5bf39be2d859cb355d8fb7cb1cc0ad
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb15fdd4c0ab874f4afa0ea95fae119cbc74554df5fbe92ab825fe27063eaa04
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 6.845968723297119,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.048520135856380396,
+  "best_metric": 6.82717752456665,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.09704027171276079,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 780.565,
       "eval_steps_per_second": 98.02,
       "step": 25
+    },
+    {
+      "epoch": 0.050460941290635615,
+      "grad_norm": 0.3800520598888397,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 6.8659,
+      "step": 26
+    },
+    {
+      "epoch": 0.05240174672489083,
+      "grad_norm": 0.3933583199977875,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 6.8616,
+      "step": 27
+    },
+    {
+      "epoch": 0.054342552159146046,
+      "grad_norm": 0.392612099647522,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 6.8581,
+      "step": 28
+    },
+    {
+      "epoch": 0.056283357593401265,
+      "grad_norm": 0.3887704610824585,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 6.8503,
+      "step": 29
+    },
+    {
+      "epoch": 0.05822416302765648,
+      "grad_norm": 0.40148013830184937,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 6.8447,
+      "step": 30
+    },
+    {
+      "epoch": 0.060164968461911696,
+      "grad_norm": 0.4260031282901764,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 6.835,
+      "step": 31
+    },
+    {
+      "epoch": 0.06210577389616691,
+      "grad_norm": 0.45738375186920166,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 6.8297,
+      "step": 32
+    },
+    {
+      "epoch": 0.06404657933042213,
+      "grad_norm": 0.4704289138317108,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 6.8261,
+      "step": 33
+    },
+    {
+      "epoch": 0.06598738476467735,
+      "grad_norm": 1.8486711978912354,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 6.8248,
+      "step": 34
+    },
+    {
+      "epoch": 0.06792819019893255,
+      "grad_norm": 1.8247312307357788,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 6.8195,
+      "step": 35
+    },
+    {
+      "epoch": 0.06986899563318777,
+      "grad_norm": 1.824609398841858,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 6.8183,
+      "step": 36
+    },
+    {
+      "epoch": 0.07180980106744299,
+      "grad_norm": 1.818076491355896,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 6.8166,
+      "step": 37
+    },
+    {
+      "epoch": 0.07375060650169821,
+      "grad_norm": 1.8075848817825317,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 6.8126,
+      "step": 38
+    },
+    {
+      "epoch": 0.07569141193595343,
+      "grad_norm": 1.8067516088485718,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 6.8117,
+      "step": 39
+    },
+    {
+      "epoch": 0.07763221737020863,
+      "grad_norm": 1.7904020547866821,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 6.8094,
+      "step": 40
+    },
+    {
+      "epoch": 0.07957302280446385,
+      "grad_norm": 1.7809354066848755,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 6.8063,
+      "step": 41
+    },
+    {
+      "epoch": 0.08151382823871907,
+      "grad_norm": 1.7745388746261597,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 6.8041,
+      "step": 42
+    },
+    {
+      "epoch": 0.08345463367297429,
+      "grad_norm": 1.7754625082015991,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 6.8052,
+      "step": 43
+    },
+    {
+      "epoch": 0.0853954391072295,
+      "grad_norm": 1.7673497200012207,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 6.8,
+      "step": 44
+    },
+    {
+      "epoch": 0.08733624454148471,
+      "grad_norm": 1.7607613801956177,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 6.8005,
+      "step": 45
+    },
+    {
+      "epoch": 0.08927704997573993,
+      "grad_norm": 1.7717316150665283,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 6.8023,
+      "step": 46
+    },
+    {
+      "epoch": 0.09121785540999515,
+      "grad_norm": 1.7622549533843994,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 6.7996,
+      "step": 47
+    },
+    {
+      "epoch": 0.09315866084425037,
+      "grad_norm": 1.7542312145233154,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 6.798,
+      "step": 48
+    },
+    {
+      "epoch": 0.09509946627850557,
+      "grad_norm": 1.7608698606491089,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 6.7981,
+      "step": 49
+    },
+    {
+      "epoch": 0.09704027171276079,
+      "grad_norm": 1.7583149671554565,
+      "learning_rate": 0.0,
+      "loss": 6.7971,
+      "step": 50
+    },
+    {
+      "epoch": 0.09704027171276079,
+      "eval_loss": 6.82717752456665,
+      "eval_runtime": 1.1162,
+      "eval_samples_per_second": 777.614,
+      "eval_steps_per_second": 97.65,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 480564019200.0,
+  "total_flos": 961128038400.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null