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:a0b3b7b9e0bd1dbc015c8628149684c07991b899e0f83f8156387ccf521aa3f5
+oid sha256:7bff68cc2acb35d26607a76ff4d040bfdaed72a31abc162d2a934fb3f10ff0ff
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea07c6e96ef1215de375aab7bcaf0f4ca15799d313a3b29fd7afe14cd7f11e19
+oid sha256:aa29e6c1f5171a37bc35dacd35f5987c3a25268adbe8cdcae7c14f5564c1e23d
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25f689c1179044f001267698e58b970a0d93b77d7f57350edc2052e8798cdbb5
+oid sha256:284a348415ffc9ab987fafdd274c718d637f1489d0fa0ed4c2e3a40b80880b7b
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b70a49ab35d6782eaeda662774ab1c15729950ba60f8ab927c56784272859a2
+oid sha256:825e318ec73bb811619445e525d229c6fe2216264df40feb406d5c859f2121ef
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed4d1ef8c0e69d5dac483003132bd7b872ea328570777f4561cf403cc6a9f267
+oid sha256:04d3f03983e63c408e208d2cbe56c797863c8656776455ef2f7bf11f460b0787
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d95cbc6ae6f2d4f4cc7224231e84c85d72740372be19f0283cd0390464984e42
+oid sha256:ea18e613ed84f4035f1be6f734ddd93d5afa20f0199facd633f6dd086adbd25a
 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": 11.928428649902344,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.05738880918220947,
+  "best_metric": 11.92774772644043,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.11477761836441894,
   "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": 371.984,
       "eval_steps_per_second": 96.716,
       "step": 25
+    },
+    {
+      "epoch": 0.05968436154949785,
+      "grad_norm": 0.030939413234591484,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.9311,
+      "step": 26
+    },
+    {
+      "epoch": 0.06197991391678623,
+      "grad_norm": 0.030720077455043793,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.9305,
+      "step": 27
+    },
+    {
+      "epoch": 0.0642754662840746,
+      "grad_norm": 0.029229579493403435,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.9319,
+      "step": 28
+    },
+    {
+      "epoch": 0.06657101865136299,
+      "grad_norm": 0.02834383025765419,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.9316,
+      "step": 29
+    },
+    {
+      "epoch": 0.06886657101865136,
+      "grad_norm": 0.03144960105419159,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.9308,
+      "step": 30
+    },
+    {
+      "epoch": 0.07116212338593975,
+      "grad_norm": 0.03125367313623428,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 11.9311,
+      "step": 31
+    },
+    {
+      "epoch": 0.07345767575322812,
+      "grad_norm": 0.030726848170161247,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.9302,
+      "step": 32
+    },
+    {
+      "epoch": 0.0757532281205165,
+      "grad_norm": 0.029451433569192886,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 11.9302,
+      "step": 33
+    },
+    {
+      "epoch": 0.07804878048780488,
+      "grad_norm": 0.028316278010606766,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.9303,
+      "step": 34
+    },
+    {
+      "epoch": 0.08034433285509325,
+      "grad_norm": 0.023046843707561493,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 11.9309,
+      "step": 35
+    },
+    {
+      "epoch": 0.08263988522238164,
+      "grad_norm": 0.018658028915524483,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.9302,
+      "step": 36
+    },
+    {
+      "epoch": 0.08493543758967001,
+      "grad_norm": 0.021122856065630913,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 11.9311,
+      "step": 37
+    },
+    {
+      "epoch": 0.0872309899569584,
+      "grad_norm": 0.03167968988418579,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.9314,
+      "step": 38
+    },
+    {
+      "epoch": 0.08952654232424677,
+      "grad_norm": 0.041138049215078354,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.9303,
+      "step": 39
+    },
+    {
+      "epoch": 0.09182209469153516,
+      "grad_norm": 0.03652139753103256,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.9302,
+      "step": 40
+    },
+    {
+      "epoch": 0.09411764705882353,
+      "grad_norm": 0.032850828021764755,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.9304,
+      "step": 41
+    },
+    {
+      "epoch": 0.09641319942611191,
+      "grad_norm": 0.03657353296875954,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.9312,
+      "step": 42
+    },
+    {
+      "epoch": 0.09870875179340029,
+      "grad_norm": 0.03682245686650276,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 11.931,
+      "step": 43
+    },
+    {
+      "epoch": 0.10100430416068866,
+      "grad_norm": 0.03354611247777939,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.9306,
+      "step": 44
+    },
+    {
+      "epoch": 0.10329985652797705,
+      "grad_norm": 0.0355108417570591,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 11.9296,
+      "step": 45
+    },
+    {
+      "epoch": 0.10559540889526542,
+      "grad_norm": 0.02785145863890648,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.9298,
+      "step": 46
+    },
+    {
+      "epoch": 0.1078909612625538,
+      "grad_norm": 0.02927231416106224,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 11.9309,
+      "step": 47
+    },
+    {
+      "epoch": 0.11018651362984218,
+      "grad_norm": 0.027248775586485863,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.9298,
+      "step": 48
+    },
+    {
+      "epoch": 0.11248206599713056,
+      "grad_norm": 0.019637739285826683,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 11.9318,
+      "step": 49
+    },
+    {
+      "epoch": 0.11477761836441894,
+      "grad_norm": 0.027051644399762154,
+      "learning_rate": 1e-05,
+      "loss": 11.9307,
+      "step": 50
+    },
+    {
+      "epoch": 0.11477761836441894,
+      "eval_loss": 11.92774772644043,
+      "eval_runtime": 0.1326,
+      "eval_samples_per_second": 377.161,
+      "eval_steps_per_second": 98.062,
+      "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": 522550247424.0,
+  "total_flos": 1044448935936.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null