Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:448e208972f3d77b5b6ed9574ce2e98578d76e81da9f92826a8181f2648f8b2c
+oid sha256:72a5190688ae446a7f9dde03a8247311fe808442e84f88c8a8c11e00609c329f
 size 27153960

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4b8d48e619e3215fc5c1043fac4296789919416e7cd98850ea60e816af48ae3
+oid sha256:e09af8811ee247375c006e44f095322917d14212df1465ddc4e9b5fd52e9677a
 size 54405050

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88121a8f2323707ff9cb977b8063eb3b3ab1256107c96f98551b97376a0ac92f
+oid sha256:53c951f9715126baf76ce2edad8e8d001217d1022539dfc32d55c99528ac1875
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:602b71f0bdd753776f1e94ab44ef93f98a4aca57d02a09d9dd930da766204ad9
+oid sha256:eb41327a930056c7451a3ff14723e6ad04af9e7c9b87d2a5ba504253c7f66c2d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27d508f1b74c430365481dc35c2c88ef82804680a5200f4cb5045f8754f17ea5
+oid sha256:ebd44e60a26111c8ac62f713e769a4d1c58fcc480c6c24128061fb2023b31f9c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:028221c36d0d50d2c72b113ce2debe5a2568dc168c7e0de3e8eaa99cc49080c9
+oid sha256:ba4603212b851f9298b382df4fffd110cc9cdcf95bf5526c57dc479b9b5966b0
 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": 4.23311710357666,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.4184397163120568,
+  "best_metric": 4.0566020011901855,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.8368794326241136,
   "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": 181.552,
       "eval_steps_per_second": 47.204,
       "step": 25
+    },
+    {
+      "epoch": 1.475177304964539,
+      "grad_norm": 0.7314615845680237,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.7435,
+      "step": 26
+    },
+    {
+      "epoch": 1.5319148936170213,
+      "grad_norm": 1.0433201789855957,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 5.0956,
+      "step": 27
+    },
+    {
+      "epoch": 1.5886524822695036,
+      "grad_norm": 0.746428906917572,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 3.7831,
+      "step": 28
+    },
+    {
+      "epoch": 1.645390070921986,
+      "grad_norm": 0.6522514820098877,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 4.0897,
+      "step": 29
+    },
+    {
+      "epoch": 1.702127659574468,
+      "grad_norm": 0.7004417777061462,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 3.0653,
+      "step": 30
+    },
+    {
+      "epoch": 1.7588652482269502,
+      "grad_norm": 1.14938485622406,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 4.9702,
+      "step": 31
+    },
+    {
+      "epoch": 1.8156028368794326,
+      "grad_norm": 0.6156283617019653,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 3.7304,
+      "step": 32
+    },
+    {
+      "epoch": 1.872340425531915,
+      "grad_norm": 0.7247022986412048,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 4.0414,
+      "step": 33
+    },
+    {
+      "epoch": 1.9290780141843973,
+      "grad_norm": 1.0603649616241455,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 4.3681,
+      "step": 34
+    },
+    {
+      "epoch": 1.9858156028368794,
+      "grad_norm": 0.9114518761634827,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 4.6263,
+      "step": 35
+    },
+    {
+      "epoch": 2.0425531914893615,
+      "grad_norm": 0.7863532304763794,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 4.4911,
+      "step": 36
+    },
+    {
+      "epoch": 2.099290780141844,
+      "grad_norm": 0.5520997047424316,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 3.6769,
+      "step": 37
+    },
+    {
+      "epoch": 2.1560283687943262,
+      "grad_norm": 0.6328124403953552,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 3.9725,
+      "step": 38
+    },
+    {
+      "epoch": 2.2127659574468086,
+      "grad_norm": 1.0409072637557983,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 4.3605,
+      "step": 39
+    },
+    {
+      "epoch": 2.269503546099291,
+      "grad_norm": 0.9518616795539856,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 3.566,
+      "step": 40
+    },
+    {
+      "epoch": 2.326241134751773,
+      "grad_norm": 0.5669155716896057,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 3.8253,
+      "step": 41
+    },
+    {
+      "epoch": 2.382978723404255,
+      "grad_norm": 0.582383930683136,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 3.8881,
+      "step": 42
+    },
+    {
+      "epoch": 2.4397163120567376,
+      "grad_norm": 0.7730618715286255,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 4.1901,
+      "step": 43
+    },
+    {
+      "epoch": 2.49645390070922,
+      "grad_norm": 0.5056310892105103,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 3.2627,
+      "step": 44
+    },
+    {
+      "epoch": 2.5531914893617023,
+      "grad_norm": 0.6426616311073303,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 4.1911,
+      "step": 45
+    },
+    {
+      "epoch": 2.6099290780141846,
+      "grad_norm": 0.5883984565734863,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 3.8893,
+      "step": 46
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.7146794199943542,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 4.0799,
+      "step": 47
+    },
+    {
+      "epoch": 2.723404255319149,
+      "grad_norm": 0.47517043352127075,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.7926,
+      "step": 48
+    },
+    {
+      "epoch": 2.780141843971631,
+      "grad_norm": 1.140823483467102,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 5.6299,
+      "step": 49
+    },
+    {
+      "epoch": 2.8368794326241136,
+      "grad_norm": 0.5396044254302979,
+      "learning_rate": 1e-05,
+      "loss": 3.7497,
+      "step": 50
+    },
+    {
+      "epoch": 2.8368794326241136,
+      "eval_loss": 4.0566020011901855,
+      "eval_runtime": 0.2873,
+      "eval_samples_per_second": 174.023,
+      "eval_steps_per_second": 45.246,
+      "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": 5686862177894400.0,
+  "total_flos": 1.13737243557888e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null