Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75ca6a150c626103f52228076c6b111edc06106418af9e0c8f308b91cee077ae
+oid sha256:5de0b5f9d9e76a98c2e6888ea997e7db312eaa8a2fcba275b6b6ded1e0a116c8
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af8d202f83146dfdbc9d848dd09dfd3181779c88714bff86cee41acd1a6bc276
+oid sha256:7f39fa5338c97b5d5557e8e9567f8db6e2e0d56b17bbad34aea4907992e36042
 size 27273018

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e760d17c569b3c68c5ec1d35f03d9fdf514d8a453c6d5f4a44fe43e3fabc183
+oid sha256:5a90f2ed015b8c5680f7df68fc79d87a6cf38bf3907db297738d34c64d5c9635
 size 14960

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": 0.1440922190201729,
+  "epoch": 0.2881844380403458,
   "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": 4.163,
       "step": 25
+    },
+    {
+      "epoch": 0.14985590778097982,
+      "grad_norm": 1.5801705121994019,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 4.3659,
+      "step": 26
+    },
+    {
+      "epoch": 0.15561959654178675,
+      "grad_norm": 3.451111316680908,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 4.3982,
+      "step": 27
+    },
+    {
+      "epoch": 0.15561959654178675,
+      "eval_loss": 4.300004005432129,
+      "eval_runtime": 0.8515,
+      "eval_samples_per_second": 684.681,
+      "eval_steps_per_second": 22.314,
+      "step": 27
+    },
+    {
+      "epoch": 0.16138328530259366,
+      "grad_norm": 1.6136767864227295,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 4.3207,
+      "step": 28
+    },
+    {
+      "epoch": 0.16714697406340057,
+      "grad_norm": 1.5284059047698975,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 4.2439,
+      "step": 29
+    },
+    {
+      "epoch": 0.1729106628242075,
+      "grad_norm": 1.335671305656433,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 3.9352,
+      "step": 30
+    },
+    {
+      "epoch": 0.1786743515850144,
+      "grad_norm": 2.7042202949523926,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 4.0291,
+      "step": 31
+    },
+    {
+      "epoch": 0.1844380403458213,
+      "grad_norm": 2.1285061836242676,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 3.9501,
+      "step": 32
+    },
+    {
+      "epoch": 0.19020172910662825,
+      "grad_norm": 1.8937512636184692,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 3.7774,
+      "step": 33
+    },
+    {
+      "epoch": 0.19596541786743515,
+      "grad_norm": 1.931766152381897,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 3.7974,
+      "step": 34
+    },
+    {
+      "epoch": 0.2017291066282421,
+      "grad_norm": 1.651713490486145,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 3.8174,
+      "step": 35
+    },
+    {
+      "epoch": 0.207492795389049,
+      "grad_norm": 1.7000616788864136,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 3.8321,
+      "step": 36
+    },
+    {
+      "epoch": 0.207492795389049,
+      "eval_loss": 3.770657777786255,
+      "eval_runtime": 0.8553,
+      "eval_samples_per_second": 681.651,
+      "eval_steps_per_second": 22.215,
+      "step": 36
+    },
+    {
+      "epoch": 0.2132564841498559,
+      "grad_norm": 1.4033437967300415,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 3.7747,
+      "step": 37
+    },
+    {
+      "epoch": 0.21902017291066284,
+      "grad_norm": 2.2183494567871094,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 3.7118,
+      "step": 38
+    },
+    {
+      "epoch": 0.22478386167146974,
+      "grad_norm": 1.5647684335708618,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 3.6716,
+      "step": 39
+    },
+    {
+      "epoch": 0.23054755043227665,
+      "grad_norm": 1.6753904819488525,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 3.4879,
+      "step": 40
+    },
+    {
+      "epoch": 0.23631123919308358,
+      "grad_norm": 1.5152138471603394,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 3.4866,
+      "step": 41
+    },
+    {
+      "epoch": 0.2420749279538905,
+      "grad_norm": 1.228210210800171,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 3.4079,
+      "step": 42
+    },
+    {
+      "epoch": 0.2478386167146974,
+      "grad_norm": 1.3091694116592407,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 3.7129,
+      "step": 43
+    },
+    {
+      "epoch": 0.25360230547550433,
+      "grad_norm": 1.4786443710327148,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 3.3594,
+      "step": 44
+    },
+    {
+      "epoch": 0.25936599423631124,
+      "grad_norm": 1.6930687427520752,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 3.4402,
+      "step": 45
+    },
+    {
+      "epoch": 0.25936599423631124,
+      "eval_loss": 3.5291929244995117,
+      "eval_runtime": 0.8391,
+      "eval_samples_per_second": 694.79,
+      "eval_steps_per_second": 22.643,
+      "step": 45
+    },
+    {
+      "epoch": 0.26512968299711814,
+      "grad_norm": 1.3388841152191162,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 3.2864,
+      "step": 46
+    },
+    {
+      "epoch": 0.27089337175792505,
+      "grad_norm": 1.3085576295852661,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 3.5233,
+      "step": 47
+    },
+    {
+      "epoch": 0.276657060518732,
+      "grad_norm": 1.5007169246673584,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 3.4159,
+      "step": 48
+    },
+    {
+      "epoch": 0.2824207492795389,
+      "grad_norm": 1.2105474472045898,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 3.4101,
+      "step": 49
+    },
+    {
+      "epoch": 0.2881844380403458,
+      "grad_norm": 1.4784791469573975,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 3.3902,
+      "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