Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:349091c27abf61dddc91caca3bf61d36a7be649f0be25f5b9b0fabe4c4f4cdc7
+oid sha256:5d82d13a9ddbecdea53e626447682b1ed873378bc9a5756f91725290d5f64fd6
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d57c1ef7a47a818cf2910ea5a575887d2cfc8dceb1839bbd63b0db90e085deb5
+oid sha256:55a6ea662c0bbef3d0d13de39786a1df1308d62e33fa0a1ea529541f93d2dc93
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ba1e94f53ea11b3c061d5464baa3a78fb58bc8a06770a21f1f1d2978c8aa8a1
+oid sha256:86556344de920fe43d329034bb740375cf66aadfaa5e1fd459c34bcf3d2b4c77
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f70f2c234472a0c9d4bb243d4395ef7f272e90b616f0f91bd6f8be11d27dd70c
+oid sha256:3be56923d6a9d5cea3456e8f309490172a5ad932fdf15a749e294eb6a809ef7f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a02686d7c9c441da9f3d6621000ee6fb90320ecfa596fb2884762ec27074c0ba
+oid sha256:1479f80d61560df7dac391de081439d95b89699f831bcc28065d8345f554ac31
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dbbcaf8d7aa7bbb8e3660bcb34138b3acda17b80ed43a1655ce3cb440b0ba3c
+oid sha256:68aa51309bb9546620e0e7ccd79f0563fc0a682244573ba0d1f3c63a101cc612
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.930267333984375,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06284861340246681,
+  "best_metric": 11.929398536682129,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.12569722680493361,
   "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": 197.011,
       "eval_steps_per_second": 51.223,
       "step": 25
+    },
+    {
+      "epoch": 0.06536255793856548,
+      "grad_norm": 0.025449182838201523,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.931,
+      "step": 26
+    },
+    {
+      "epoch": 0.06787650247466415,
+      "grad_norm": 0.03068012185394764,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.9312,
+      "step": 27
+    },
+    {
+      "epoch": 0.07039044701076283,
+      "grad_norm": 0.026767347007989883,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.9317,
+      "step": 28
+    },
+    {
+      "epoch": 0.0729043915468615,
+      "grad_norm": 0.025178169831633568,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.9317,
+      "step": 29
+    },
+    {
+      "epoch": 0.07541833608296017,
+      "grad_norm": 0.03514225035905838,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.9309,
+      "step": 30
+    },
+    {
+      "epoch": 0.07793228061905884,
+      "grad_norm": 0.03260508179664612,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 11.9319,
+      "step": 31
+    },
+    {
+      "epoch": 0.08044622515515751,
+      "grad_norm": 0.040161751210689545,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.9295,
+      "step": 32
+    },
+    {
+      "epoch": 0.08296016969125619,
+      "grad_norm": 0.04335453361272812,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 11.9302,
+      "step": 33
+    },
+    {
+      "epoch": 0.08547411422735486,
+      "grad_norm": 0.04472953453660011,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.9298,
+      "step": 34
+    },
+    {
+      "epoch": 0.08798805876345353,
+      "grad_norm": 0.047546010464429855,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 11.9285,
+      "step": 35
+    },
+    {
+      "epoch": 0.0905020032995522,
+      "grad_norm": 0.07338829338550568,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.9262,
+      "step": 36
+    },
+    {
+      "epoch": 0.09301594783565087,
+      "grad_norm": 0.08542904257774353,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 11.9253,
+      "step": 37
+    },
+    {
+      "epoch": 0.09552989237174955,
+      "grad_norm": 0.04177666828036308,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.9309,
+      "step": 38
+    },
+    {
+      "epoch": 0.09804383690784822,
+      "grad_norm": 0.03181887045502663,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.9304,
+      "step": 39
+    },
+    {
+      "epoch": 0.10055778144394689,
+      "grad_norm": 0.03152301162481308,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.9316,
+      "step": 40
+    },
+    {
+      "epoch": 0.10307172598004556,
+      "grad_norm": 0.03929756209254265,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.9312,
+      "step": 41
+    },
+    {
+      "epoch": 0.10558567051614423,
+      "grad_norm": 0.042001765221357346,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.9309,
+      "step": 42
+    },
+    {
+      "epoch": 0.10809961505224291,
+      "grad_norm": 0.040411677211523056,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 11.9297,
+      "step": 43
+    },
+    {
+      "epoch": 0.11061355958834158,
+      "grad_norm": 0.039004117250442505,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.9291,
+      "step": 44
+    },
+    {
+      "epoch": 0.11312750412444025,
+      "grad_norm": 0.04640093818306923,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 11.9294,
+      "step": 45
+    },
+    {
+      "epoch": 0.11564144866053892,
+      "grad_norm": 0.05690125748515129,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.9288,
+      "step": 46
+    },
+    {
+      "epoch": 0.11815539319663759,
+      "grad_norm": 0.05605897307395935,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 11.9292,
+      "step": 47
+    },
+    {
+      "epoch": 0.12066933773273628,
+      "grad_norm": 0.08062251657247543,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.9273,
+      "step": 48
+    },
+    {
+      "epoch": 0.12318328226883495,
+      "grad_norm": 0.07040993124246597,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 11.9273,
+      "step": 49
+    },
+    {
+      "epoch": 0.12569722680493361,
+      "grad_norm": 0.08358202874660492,
+      "learning_rate": 1e-05,
+      "loss": 11.9257,
+      "step": 50
+    },
+    {
+      "epoch": 0.12569722680493361,
+      "eval_loss": 11.929398536682129,
+      "eval_runtime": 0.2521,
+      "eval_samples_per_second": 198.37,
+      "eval_steps_per_second": 51.576,
+      "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": 521247129600.0,
+  "total_flos": 1042494259200.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null