Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:833c455003c863b1873f1f687d47669a635ef439dfd1558c5c5015c028cf224e
+oid sha256:2aa7f78d3340c0022472df4aefd425145227be31f7992e1a7214d43a33a87495
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c09c7673bbbb2c44b9f27571591c20e2962972740d031740d8f36a60635292f2
+oid sha256:d8ba8eb77dbc5ca18781fa7036e15dd0e4e6374b53c2eb4881000940fc288b6f
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1de8ffa4e68861768ec884661d7ea07eb208d429b52aea67e7a768c295c99f53
+oid sha256:dbf734b68e3503fe93b2735d0f538007f5a0ed7252838966085261c8c4865a6f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:486f46bd1fa3cb47d493c0990f0de2794e69f8e62b15391ceb661567ee15faa7
+oid sha256:411a6523b1ea1c97a18cf27029885e52981e94465426108c1914a722785340a3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbf68da084ef0d146c64cc0f28955d69d4234438289fa90811268d7043e06332
+oid sha256:3a0b2027e6d905eef4998efa47065c510590e0cd95b716a67313155ca726cc41
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daa8be3883fee3a550df0d00fbbe8c541615e4547feb9b44efe959793eb64740
+oid sha256:e2a458419408263ac2d015acabfb10656bebc458ca7b06e1011f2c864c6bf9c3
 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": 1.0651795864105225,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.954653937947494,
+  "best_metric": 1.0433918237686157,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.9093078758949882,
   "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": 14.321,
       "eval_steps_per_second": 3.723,
       "step": 25
+    },
+    {
+      "epoch": 0.9928400954653938,
+      "grad_norm": 0.22500985860824585,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.0603,
+      "step": 26
+    },
+    {
+      "epoch": 1.0310262529832936,
+      "grad_norm": 0.4766336977481842,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.0533,
+      "step": 27
+    },
+    {
+      "epoch": 1.0692124105011933,
+      "grad_norm": 0.2036180943250656,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.0609,
+      "step": 28
+    },
+    {
+      "epoch": 1.107398568019093,
+      "grad_norm": 0.1957828253507614,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.0562,
+      "step": 29
+    },
+    {
+      "epoch": 1.1455847255369929,
+      "grad_norm": 0.199952632188797,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.0406,
+      "step": 30
+    },
+    {
+      "epoch": 1.1837708830548925,
+      "grad_norm": 0.20388226211071014,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.0644,
+      "step": 31
+    },
+    {
+      "epoch": 1.2219570405727924,
+      "grad_norm": 0.21528272330760956,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.0359,
+      "step": 32
+    },
+    {
+      "epoch": 1.260143198090692,
+      "grad_norm": 0.21346765756607056,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.0727,
+      "step": 33
+    },
+    {
+      "epoch": 1.2983293556085918,
+      "grad_norm": 0.2118886560201645,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.0475,
+      "step": 34
+    },
+    {
+      "epoch": 1.3365155131264916,
+      "grad_norm": 0.2171202301979065,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.0706,
+      "step": 35
+    },
+    {
+      "epoch": 1.3747016706443915,
+      "grad_norm": 0.2041509449481964,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.0409,
+      "step": 36
+    },
+    {
+      "epoch": 1.4128878281622912,
+      "grad_norm": 0.19373871386051178,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.0167,
+      "step": 37
+    },
+    {
+      "epoch": 1.4510739856801909,
+      "grad_norm": 0.2035079449415207,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.0841,
+      "step": 38
+    },
+    {
+      "epoch": 1.4892601431980907,
+      "grad_norm": 0.22423155605793,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.0604,
+      "step": 39
+    },
+    {
+      "epoch": 1.5274463007159904,
+      "grad_norm": 0.19593113660812378,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.0352,
+      "step": 40
+    },
+    {
+      "epoch": 1.5656324582338903,
+      "grad_norm": 0.19927962124347687,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.0087,
+      "step": 41
+    },
+    {
+      "epoch": 1.60381861575179,
+      "grad_norm": 0.19032032787799835,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.0021,
+      "step": 42
+    },
+    {
+      "epoch": 1.6420047732696896,
+      "grad_norm": 0.2027662694454193,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.9654,
+      "step": 43
+    },
+    {
+      "epoch": 1.6801909307875895,
+      "grad_norm": 0.20297980308532715,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.035,
+      "step": 44
+    },
+    {
+      "epoch": 1.7183770883054894,
+      "grad_norm": 0.23470035195350647,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.0552,
+      "step": 45
+    },
+    {
+      "epoch": 1.756563245823389,
+      "grad_norm": 0.22237010300159454,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.0851,
+      "step": 46
+    },
+    {
+      "epoch": 1.7947494033412887,
+      "grad_norm": 0.2051822692155838,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.0682,
+      "step": 47
+    },
+    {
+      "epoch": 1.8329355608591884,
+      "grad_norm": 0.19624276459217072,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.0594,
+      "step": 48
+    },
+    {
+      "epoch": 1.8711217183770883,
+      "grad_norm": 0.19812841713428497,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.0042,
+      "step": 49
+    },
+    {
+      "epoch": 1.9093078758949882,
+      "grad_norm": 0.1921299695968628,
+      "learning_rate": 1e-05,
+      "loss": 1.0595,
+      "step": 50
+    },
+    {
+      "epoch": 1.9093078758949882,
+      "eval_loss": 1.0433918237686157,
+      "eval_runtime": 3.5223,
+      "eval_samples_per_second": 14.195,
+      "eval_steps_per_second": 3.691,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null