Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bf014d1a50f271c41f7422261b08ca5ec84dc1faabd04c29231ef2836d36445
+oid sha256:e41d69019d421204220964865c9c89fc7bacb60a8411908a8b29c0a12114b94a
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9606721fc8617b61d2e0dc2ec8042ef4e6afb22d62a62595ce9ec2026c0ad30
+oid sha256:1928572a9ac56c6d98ea8953c7a7a8fdca570b8a20a3959f47990cc5be36ddc3
 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": 0.8169272541999817,
-  "best_model_checkpoint": "miner_id_besimray/checkpoint-20",
-  "epoch": 0.2572347266881029,
+  "best_metric": 0.7905269861221313,
+  "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": 28.427,
       "eval_steps_per_second": 2.947,
       "step": 20
+    },
+    {
+      "epoch": 0.27009646302250806,
+      "grad_norm": 0.20886819064617157,
+      "learning_rate": 0.0001969689520376687,
+      "loss": 0.7039,
+      "step": 21
+    },
+    {
+      "epoch": 0.2829581993569132,
+      "grad_norm": 0.2352903187274933,
+      "learning_rate": 0.00019639628606958533,
+      "loss": 0.77,
+      "step": 22
+    },
+    {
+      "epoch": 0.2958199356913183,
+      "grad_norm": 0.2201235145330429,
+      "learning_rate": 0.00019577508166849304,
+      "loss": 0.7533,
+      "step": 23
+    },
+    {
+      "epoch": 0.3086816720257235,
+      "grad_norm": 0.20297250151634216,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.7303,
+      "step": 24
+    },
+    {
+      "epoch": 0.3215434083601286,
+      "grad_norm": 0.20995450019836426,
+      "learning_rate": 0.00019438833303083678,
+      "loss": 0.8122,
+      "step": 25
+    },
+    {
+      "epoch": 0.33440514469453375,
+      "grad_norm": 0.21005098521709442,
+      "learning_rate": 0.00019362348706397373,
+      "loss": 0.8264,
+      "step": 26
+    },
+    {
+      "epoch": 0.34726688102893893,
+      "grad_norm": 0.22008338570594788,
+      "learning_rate": 0.0001928114988519039,
+      "loss": 0.8181,
+      "step": 27
+    },
+    {
+      "epoch": 0.36012861736334406,
+      "grad_norm": 0.20176909863948822,
+      "learning_rate": 0.0001919527772551451,
+      "loss": 0.7487,
+      "step": 28
+    },
+    {
+      "epoch": 0.3729903536977492,
+      "grad_norm": 0.22451724112033844,
+      "learning_rate": 0.00019104775466588161,
+      "loss": 0.8272,
+      "step": 29
+    },
+    {
+      "epoch": 0.3858520900321543,
+      "grad_norm": 0.2383953183889389,
+      "learning_rate": 0.0001900968867902419,
+      "loss": 0.8406,
+      "step": 30
+    },
+    {
+      "epoch": 0.3987138263665595,
+      "grad_norm": 0.23490720987319946,
+      "learning_rate": 0.0001891006524188368,
+      "loss": 0.8325,
+      "step": 31
+    },
+    {
+      "epoch": 0.4115755627009646,
+      "grad_norm": 0.22093895077705383,
+      "learning_rate": 0.0001880595531856738,
+      "loss": 0.789,
+      "step": 32
+    },
+    {
+      "epoch": 0.42443729903536975,
+      "grad_norm": 0.2193409502506256,
+      "learning_rate": 0.00018697411331556956,
+      "loss": 0.7841,
+      "step": 33
+    },
+    {
+      "epoch": 0.43729903536977494,
+      "grad_norm": 0.2156234085559845,
+      "learning_rate": 0.00018584487936018661,
+      "loss": 0.7614,
+      "step": 34
+    },
+    {
+      "epoch": 0.45016077170418006,
+      "grad_norm": 0.20940746366977692,
+      "learning_rate": 0.00018467241992282843,
+      "loss": 0.7969,
+      "step": 35
+    },
+    {
+      "epoch": 0.4630225080385852,
+      "grad_norm": 0.21839483082294464,
+      "learning_rate": 0.00018345732537213027,
+      "loss": 0.7881,
+      "step": 36
+    },
+    {
+      "epoch": 0.4758842443729904,
+      "grad_norm": 0.2568162977695465,
+      "learning_rate": 0.00018220020754479102,
+      "loss": 0.9168,
+      "step": 37
+    },
+    {
+      "epoch": 0.4887459807073955,
+      "grad_norm": 0.21982234716415405,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.8394,
+      "step": 38
+    },
+    {
+      "epoch": 0.5016077170418006,
+      "grad_norm": 0.22966712713241577,
+      "learning_rate": 0.00017956245488817812,
+      "loss": 0.8205,
+      "step": 39
+    },
+    {
+      "epoch": 0.5144694533762058,
+      "grad_norm": 0.22293612360954285,
+      "learning_rate": 0.000178183148246803,
+      "loss": 0.7895,
+      "step": 40
+    },
+    {
+      "epoch": 0.5144694533762058,
+      "eval_loss": 0.7905269861221313,
+      "eval_runtime": 7.4631,
+      "eval_samples_per_second": 21.975,
+      "eval_steps_per_second": 2.278,
+      "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