Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:901a644c37f000568b037c51fec255ceb3855ab3ad663c3ad3f5747767f157db
+oid sha256:0c0b2ed0f81d738a03a3eeacf2ca1d7972a36dc50318beab1da94d1770cb4032
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c41c0c181cb5038c5f622d0a3f3906d5d1b0b29066f42979dec48e94a5545d0
+oid sha256:43aad10fa560aaafd5efc833bb3ebdc0e7d3c7f3b24bbfbb32f736711a6c6e8e
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:490faae3574e0545627c6c066345113a5ec4be88337cd4484537a0d75c6be16a
+oid sha256:8e565442590f72e02c81245f841f0d570f0816c276d51ef5abfd2bed9cc00d28
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c297c5cf11a27c75d9f99f1df69752f78c3ad41b0275adf50cdd1b67f9d0bb3
+oid sha256:062016b917f4cd81cef6ab15bfe81df4e94586c0afba8905b655deaa6fff468f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8176891803741455,
-  "best_model_checkpoint": "miner_id_besimray/checkpoint-20",
-  "epoch": 0.2572347266881029,
+  "best_metric": 0.790475070476532,
+  "best_model_checkpoint": "miner_id_besimray/checkpoint-40",
+  "epoch": 0.5144694533762058,
   "eval_steps": 20,
-  "global_step": 20,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -163,6 +163,154 @@
       "eval_samples_per_second": 28.358,
       "eval_steps_per_second": 2.94,
       "step": 20
+    },
+    {
+      "epoch": 0.27009646302250806,
+      "grad_norm": 0.21167340874671936,
+      "learning_rate": 0.0001969689520376687,
+      "loss": 0.7046,
+      "step": 21
+    },
+    {
+      "epoch": 0.2829581993569132,
+      "grad_norm": 0.23888267576694489,
+      "learning_rate": 0.00019639628606958533,
+      "loss": 0.769,
+      "step": 22
+    },
+    {
+      "epoch": 0.2958199356913183,
+      "grad_norm": 0.2215345799922943,
+      "learning_rate": 0.00019577508166849304,
+      "loss": 0.7524,
+      "step": 23
+    },
+    {
+      "epoch": 0.3086816720257235,
+      "grad_norm": 0.2053850293159485,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.7305,
+      "step": 24
+    },
+    {
+      "epoch": 0.3215434083601286,
+      "grad_norm": 0.21348363161087036,
+      "learning_rate": 0.00019438833303083678,
+      "loss": 0.8105,
+      "step": 25
+    },
+    {
+      "epoch": 0.33440514469453375,
+      "grad_norm": 0.21149109303951263,
+      "learning_rate": 0.00019362348706397373,
+      "loss": 0.8249,
+      "step": 26
+    },
+    {
+      "epoch": 0.34726688102893893,
+      "grad_norm": 0.22312600910663605,
+      "learning_rate": 0.0001928114988519039,
+      "loss": 0.8205,
+      "step": 27
+    },
+    {
+      "epoch": 0.36012861736334406,
+      "grad_norm": 0.20689311623573303,
+      "learning_rate": 0.0001919527772551451,
+      "loss": 0.7488,
+      "step": 28
+    },
+    {
+      "epoch": 0.3729903536977492,
+      "grad_norm": 0.22930146753787994,
+      "learning_rate": 0.00019104775466588161,
+      "loss": 0.8267,
+      "step": 29
+    },
+    {
+      "epoch": 0.3858520900321543,
+      "grad_norm": 0.24117408692836761,
+      "learning_rate": 0.0001900968867902419,
+      "loss": 0.8412,
+      "step": 30
+    },
+    {
+      "epoch": 0.3987138263665595,
+      "grad_norm": 0.23889240622520447,
+      "learning_rate": 0.0001891006524188368,
+      "loss": 0.8336,
+      "step": 31
+    },
+    {
+      "epoch": 0.4115755627009646,
+      "grad_norm": 0.22367344796657562,
+      "learning_rate": 0.0001880595531856738,
+      "loss": 0.7905,
+      "step": 32
+    },
+    {
+      "epoch": 0.42443729903536975,
+      "grad_norm": 0.22343823313713074,
+      "learning_rate": 0.00018697411331556956,
+      "loss": 0.7842,
+      "step": 33
+    },
+    {
+      "epoch": 0.43729903536977494,
+      "grad_norm": 0.21874739229679108,
+      "learning_rate": 0.00018584487936018661,
+      "loss": 0.7624,
+      "step": 34
+    },
+    {
+      "epoch": 0.45016077170418006,
+      "grad_norm": 0.21489335596561432,
+      "learning_rate": 0.00018467241992282843,
+      "loss": 0.7956,
+      "step": 35
+    },
+    {
+      "epoch": 0.4630225080385852,
+      "grad_norm": 0.2225746512413025,
+      "learning_rate": 0.00018345732537213027,
+      "loss": 0.788,
+      "step": 36
+    },
+    {
+      "epoch": 0.4758842443729904,
+      "grad_norm": 0.25866109132766724,
+      "learning_rate": 0.00018220020754479102,
+      "loss": 0.9176,
+      "step": 37
+    },
+    {
+      "epoch": 0.4887459807073955,
+      "grad_norm": 0.2253965586423874,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.837,
+      "step": 38
+    },
+    {
+      "epoch": 0.5016077170418006,
+      "grad_norm": 0.23456409573554993,
+      "learning_rate": 0.00017956245488817812,
+      "loss": 0.8215,
+      "step": 39
+    },
+    {
+      "epoch": 0.5144694533762058,
+      "grad_norm": 0.22983534634113312,
+      "learning_rate": 0.000178183148246803,
+      "loss": 0.7865,
+      "step": 40
+    },
+    {
+      "epoch": 0.5144694533762058,
+      "eval_loss": 0.790475070476532,
+      "eval_runtime": 7.5635,
+      "eval_samples_per_second": 21.683,
+      "eval_steps_per_second": 2.248,
+      "step": 40
     }
   ],
   "logging_steps": 1,
@@ -191,7 +339,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5141026150809600.0,
+  "total_flos": 1.012328531755008e+16,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null