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:c2ea1e6a39b9b019bb68f8bcb9e4113a9450d3a145c326c3d17c60e7914f4870
+oid sha256:928ab8d5d9685166fb9c05f8f86ac5f339a74761031699b7431cbf196cf665d3
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa015a1e42d23eb4a3ea0fa718ceb403d42f019d9d2191fa6d5727830e4b7375
+oid sha256:84fbbb689aff7e3534c9a2e784632a8255256d5a987752f30d6cf1c49956a3cb
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e691a6f9c4d5048643b02e3232a9cfa061e68f527f466d35a53bb462800e4b3
+oid sha256:6d3c2b9368de43a9e6d513b33bec2ad97c83367d98632cf5067c5665823b83ed
 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": 0.3471006155014038,
-  "best_model_checkpoint": "miner_id_besimray/checkpoint-20",
-  "epoch": 0.2572347266881029,
+  "best_metric": 0.12474175542593002,
+  "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": 28.61,
       "eval_steps_per_second": 2.966,
       "step": 20
+    },
+    {
+      "epoch": 0.27009646302250806,
+      "grad_norm": 4.2755913734436035,
+      "learning_rate": 0.0001969689520376687,
+      "loss": 0.2866,
+      "step": 21
+    },
+    {
+      "epoch": 0.2829581993569132,
+      "grad_norm": 3.4531168937683105,
+      "learning_rate": 0.00019639628606958533,
+      "loss": 0.3498,
+      "step": 22
+    },
+    {
+      "epoch": 0.2958199356913183,
+      "grad_norm": 2.804391384124756,
+      "learning_rate": 0.00019577508166849304,
+      "loss": 0.2479,
+      "step": 23
+    },
+    {
+      "epoch": 0.3086816720257235,
+      "grad_norm": 3.1008567810058594,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.2555,
+      "step": 24
+    },
+    {
+      "epoch": 0.3215434083601286,
+      "grad_norm": 3.5834286212921143,
+      "learning_rate": 0.00019438833303083678,
+      "loss": 0.2781,
+      "step": 25
+    },
+    {
+      "epoch": 0.33440514469453375,
+      "grad_norm": 2.518784761428833,
+      "learning_rate": 0.00019362348706397373,
+      "loss": 0.3046,
+      "step": 26
+    },
+    {
+      "epoch": 0.34726688102893893,
+      "grad_norm": 3.2778635025024414,
+      "learning_rate": 0.0001928114988519039,
+      "loss": 0.2022,
+      "step": 27
+    },
+    {
+      "epoch": 0.36012861736334406,
+      "grad_norm": 5.756374359130859,
+      "learning_rate": 0.0001919527772551451,
+      "loss": 0.3736,
+      "step": 28
+    },
+    {
+      "epoch": 0.3729903536977492,
+      "grad_norm": 1.6510024070739746,
+      "learning_rate": 0.00019104775466588161,
+      "loss": 0.2021,
+      "step": 29
+    },
+    {
+      "epoch": 0.3858520900321543,
+      "grad_norm": 1.2776992321014404,
+      "learning_rate": 0.0001900968867902419,
+      "loss": 0.1522,
+      "step": 30
+    },
+    {
+      "epoch": 0.3987138263665595,
+      "grad_norm": 4.784623622894287,
+      "learning_rate": 0.0001891006524188368,
+      "loss": 0.281,
+      "step": 31
+    },
+    {
+      "epoch": 0.4115755627009646,
+      "grad_norm": 2.4799091815948486,
+      "learning_rate": 0.0001880595531856738,
+      "loss": 0.265,
+      "step": 32
+    },
+    {
+      "epoch": 0.42443729903536975,
+      "grad_norm": 3.5380313396453857,
+      "learning_rate": 0.00018697411331556956,
+      "loss": 0.2719,
+      "step": 33
+    },
+    {
+      "epoch": 0.43729903536977494,
+      "grad_norm": 4.498678684234619,
+      "learning_rate": 0.00018584487936018661,
+      "loss": 0.281,
+      "step": 34
+    },
+    {
+      "epoch": 0.45016077170418006,
+      "grad_norm": 2.152132749557495,
+      "learning_rate": 0.00018467241992282843,
+      "loss": 0.2009,
+      "step": 35
+    },
+    {
+      "epoch": 0.4630225080385852,
+      "grad_norm": 1.9886168241500854,
+      "learning_rate": 0.00018345732537213027,
+      "loss": 0.2086,
+      "step": 36
+    },
+    {
+      "epoch": 0.4758842443729904,
+      "grad_norm": 1.2660861015319824,
+      "learning_rate": 0.00018220020754479102,
+      "loss": 0.1168,
+      "step": 37
+    },
+    {
+      "epoch": 0.4887459807073955,
+      "grad_norm": 2.2614033222198486,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.2217,
+      "step": 38
+    },
+    {
+      "epoch": 0.5016077170418006,
+      "grad_norm": 2.7346444129943848,
+      "learning_rate": 0.00017956245488817812,
+      "loss": 0.1719,
+      "step": 39
+    },
+    {
+      "epoch": 0.5144694533762058,
+      "grad_norm": 2.3081042766571045,
+      "learning_rate": 0.000178183148246803,
+      "loss": 0.2618,
+      "step": 40
+    },
+    {
+      "epoch": 0.5144694533762058,
+      "eval_loss": 0.12474175542593002,
+      "eval_runtime": 7.5726,
+      "eval_samples_per_second": 21.657,
+      "eval_steps_per_second": 2.245,
+      "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