Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b7555d630424fa972fd8d56c18280f066e0a372f91afd244f63eee297a5bfd7
+oid sha256:e0e7a1cc2f984491337cc93f8f078db449938995279d3456ad481ad5c2a60fca
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:210536711ffe95f40ee45fd67d5aa9adea4b86f57a6e671a39a01a617040866b
+oid sha256:89a7ed62fc316ebe2e945b7ad07627243752f56f599729a81d6413e2af2686b8
 size 27273018

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24dbb7eec220c13de71bffe99dff5438a1f594ce18e2886e93e45665b8ac914f
+oid sha256:17e1f0fd2d004d6caaae844aa17b92356b2e2f60ef5bfaf5353e49ccd0051ffa
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19f7e1e2b46d20cd957e0e95bcb2e067d758e535289dbb0bf8ff56fe10e1df41
+oid sha256:981bbea8034bbbae85baf44fc3a7f5bd1463eae4931e71f483cdca42e7a37e82
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06215c771b27617bf1429ea562d72f5914b0ae3cab53c2da36b5aa306d7c747e
+oid sha256:6cca749a55d863ce18a73bc0ef2f3abbffa81b687698aff70716c9f05ebb977e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96ec17834f290c890763449aed1337a9467d9173b2ddc32416f4f24d4954a63b
+oid sha256:ce143f3192cb1b2e626d251c64dac68350718e07c33521f586159568d189c078
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c931ece4da598a541d357f6c98f67481603252e193960022d37ddd49c584b1f
+oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1488095238095238,
+  "epoch": 0.2976190476190476,
   "eval_steps": 9,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -206,6 +206,205 @@
       "learning_rate": 9.330127018922194e-05,
       "loss": 1.4277,
       "step": 25
+    },
+    {
+      "epoch": 0.15476190476190477,
+      "grad_norm": 2.925053834915161,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 1.3428,
+      "step": 26
+    },
+    {
+      "epoch": 0.16071428571428573,
+      "grad_norm": 2.3791446685791016,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 1.3196,
+      "step": 27
+    },
+    {
+      "epoch": 0.16071428571428573,
+      "eval_loss": 1.1837644577026367,
+      "eval_runtime": 0.749,
+      "eval_samples_per_second": 754.302,
+      "eval_steps_per_second": 24.031,
+      "step": 27
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 1.918161392211914,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.078,
+      "step": 28
+    },
+    {
+      "epoch": 0.17261904761904762,
+      "grad_norm": 1.787397027015686,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 1.0918,
+      "step": 29
+    },
+    {
+      "epoch": 0.17857142857142858,
+      "grad_norm": 1.718632459640503,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 1.0613,
+      "step": 30
+    },
+    {
+      "epoch": 0.18452380952380953,
+      "grad_norm": 1.6407841444015503,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.9426,
+      "step": 31
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 1.6310867071151733,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.9499,
+      "step": 32
+    },
+    {
+      "epoch": 0.19642857142857142,
+      "grad_norm": 1.6535135507583618,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.8009,
+      "step": 33
+    },
+    {
+      "epoch": 0.20238095238095238,
+      "grad_norm": 1.7860593795776367,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.698,
+      "step": 34
+    },
+    {
+      "epoch": 0.20833333333333334,
+      "grad_norm": 1.6134707927703857,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 0.6973,
+      "step": 35
+    },
+    {
+      "epoch": 0.21428571428571427,
+      "grad_norm": 1.5818922519683838,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.6982,
+      "step": 36
+    },
+    {
+      "epoch": 0.21428571428571427,
+      "eval_loss": 0.591748058795929,
+      "eval_runtime": 0.7267,
+      "eval_samples_per_second": 777.438,
+      "eval_steps_per_second": 24.768,
+      "step": 36
+    },
+    {
+      "epoch": 0.22023809523809523,
+      "grad_norm": 1.3319734334945679,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.6164,
+      "step": 37
+    },
+    {
+      "epoch": 0.2261904761904762,
+      "grad_norm": 1.2683157920837402,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.5391,
+      "step": 38
+    },
+    {
+      "epoch": 0.23214285714285715,
+      "grad_norm": 1.0097771883010864,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.49,
+      "step": 39
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": 1.0080583095550537,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.4928,
+      "step": 40
+    },
+    {
+      "epoch": 0.24404761904761904,
+      "grad_norm": 0.8241538405418396,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 0.4672,
+      "step": 41
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.8907387852668762,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.4678,
+      "step": 42
+    },
+    {
+      "epoch": 0.25595238095238093,
+      "grad_norm": 0.8545511364936829,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.3988,
+      "step": 43
+    },
+    {
+      "epoch": 0.2619047619047619,
+      "grad_norm": 0.8012543320655823,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.4446,
+      "step": 44
+    },
+    {
+      "epoch": 0.26785714285714285,
+      "grad_norm": 0.6742522716522217,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.3976,
+      "step": 45
+    },
+    {
+      "epoch": 0.26785714285714285,
+      "eval_loss": 0.393344908952713,
+      "eval_runtime": 0.731,
+      "eval_samples_per_second": 772.887,
+      "eval_steps_per_second": 24.623,
+      "step": 45
+    },
+    {
+      "epoch": 0.27380952380952384,
+      "grad_norm": 0.6675676107406616,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.3466,
+      "step": 46
+    },
+    {
+      "epoch": 0.27976190476190477,
+      "grad_norm": 0.7589141726493835,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.3242,
+      "step": 47
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.872429370880127,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.3272,
+      "step": 48
+    },
+    {
+      "epoch": 0.2916666666666667,
+      "grad_norm": 0.5737527012825012,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.3232,
+      "step": 49
+    },
+    {
+      "epoch": 0.2976190476190476,
+      "grad_norm": 0.8787867426872253,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.3176,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1388375860838400.0,
+  "total_flos": 2776751721676800.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null