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:dca7a4d811e5fd1acf5583130351f3746b11414e340d3ee675f35d95ba19ae21
+oid sha256:40036922f1e7df72dee2acde736221bcaa5f6db46b2746ea07589efcab0dfcc2
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d372096d3086628af41bc846dec7f0d898f7061bd8a1798e2574770ca8cd84f9
+oid sha256:955fd79f159eff89d13073ef45b2e78a520b25de551dd975acfe84681744276b
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7ebc16af5a149f8a362bfc4725a6d41208c858b496412deafdf2092c1f5647c
+oid sha256:68055b474b3b2442673234480a1bf12418501770e25beda0f2fe0c40fb6a4ce5
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d87fe98ab23aa12194b307f626d70788d1ba0bb6609743cfba76bfcf26e27bd
+oid sha256:d66a4cdd6890097c176649e7f8c73731d709335b76278295f41d2268c1f93822
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:075f9af08cadb62d15d2331d5f2343b25ab3caaeceb96704352cc9ff075ab3e5
+oid sha256:7a82a049a06c3a137ef0c4311989ca495363642c3f39b67f39c80d3e512c4e43
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51433d57ebb6ba2641cfd29d799c31694a6eea4d92f653b05ecffb1c9b8a41f4
+oid sha256:699db422634a218339ee699f847e7a0a7f11e04570005968f4fe6b4dbd896b97
 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": 0.9214932918548584,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.33585222502099077,
+  "best_metric": 0.9084668755531311,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6717044500419815,
   "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": 66.968,
       "eval_steps_per_second": 17.412,
       "step": 25
+    },
+    {
+      "epoch": 0.3492863140218304,
+      "grad_norm": 0.2771437466144562,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.9501,
+      "step": 26
+    },
+    {
+      "epoch": 0.36272040302267,
+      "grad_norm": 0.2764880955219269,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.9396,
+      "step": 27
+    },
+    {
+      "epoch": 0.37615449202350965,
+      "grad_norm": 0.24223656952381134,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.9147,
+      "step": 28
+    },
+    {
+      "epoch": 0.3895885810243493,
+      "grad_norm": 0.24211497604846954,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.9259,
+      "step": 29
+    },
+    {
+      "epoch": 0.40302267002518893,
+      "grad_norm": 0.22469313442707062,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.8902,
+      "step": 30
+    },
+    {
+      "epoch": 0.4164567590260285,
+      "grad_norm": 0.2251465618610382,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.9032,
+      "step": 31
+    },
+    {
+      "epoch": 0.42989084802686817,
+      "grad_norm": 0.2130904495716095,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.9317,
+      "step": 32
+    },
+    {
+      "epoch": 0.4433249370277078,
+      "grad_norm": 0.2265763282775879,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.8936,
+      "step": 33
+    },
+    {
+      "epoch": 0.45675902602854745,
+      "grad_norm": 0.24248380959033966,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.8983,
+      "step": 34
+    },
+    {
+      "epoch": 0.47019311502938704,
+      "grad_norm": 0.24923619627952576,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.9229,
+      "step": 35
+    },
+    {
+      "epoch": 0.4836272040302267,
+      "grad_norm": 0.23115158081054688,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.8954,
+      "step": 36
+    },
+    {
+      "epoch": 0.49706129303106633,
+      "grad_norm": 0.255435585975647,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.8836,
+      "step": 37
+    },
+    {
+      "epoch": 0.5104953820319059,
+      "grad_norm": 0.22626522183418274,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.9098,
+      "step": 38
+    },
+    {
+      "epoch": 0.5239294710327456,
+      "grad_norm": 0.20505741238594055,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.9165,
+      "step": 39
+    },
+    {
+      "epoch": 0.5373635600335852,
+      "grad_norm": 0.2080068439245224,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.9177,
+      "step": 40
+    },
+    {
+      "epoch": 0.5507976490344249,
+      "grad_norm": 0.2057790458202362,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.9319,
+      "step": 41
+    },
+    {
+      "epoch": 0.5642317380352645,
+      "grad_norm": 0.20780308544635773,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.8765,
+      "step": 42
+    },
+    {
+      "epoch": 0.5776658270361041,
+      "grad_norm": 0.20456816256046295,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.8815,
+      "step": 43
+    },
+    {
+      "epoch": 0.5910999160369438,
+      "grad_norm": 0.20141682028770447,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.9079,
+      "step": 44
+    },
+    {
+      "epoch": 0.6045340050377834,
+      "grad_norm": 0.2008521854877472,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.8941,
+      "step": 45
+    },
+    {
+      "epoch": 0.617968094038623,
+      "grad_norm": 0.212819442152977,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.8951,
+      "step": 46
+    },
+    {
+      "epoch": 0.6314021830394626,
+      "grad_norm": 0.20845483243465424,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.8793,
+      "step": 47
+    },
+    {
+      "epoch": 0.6448362720403022,
+      "grad_norm": 0.21866247057914734,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.9227,
+      "step": 48
+    },
+    {
+      "epoch": 0.6582703610411419,
+      "grad_norm": 0.22729778289794922,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.8741,
+      "step": 49
+    },
+    {
+      "epoch": 0.6717044500419815,
+      "grad_norm": 0.2767520248889923,
+      "learning_rate": 1e-05,
+      "loss": 0.9384,
+      "step": 50
+    },
+    {
+      "epoch": 0.6717044500419815,
+      "eval_loss": 0.9084668755531311,
+      "eval_runtime": 0.7392,
+      "eval_samples_per_second": 67.644,
+      "eval_steps_per_second": 17.588,
+      "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": 1.47650456322048e+16,
+  "total_flos": 2.95300912644096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null