Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c73abcc7477e9be70a3f019997dc02f580eed37a2cfe7486ea1c208987f5cb6
+oid sha256:54f8c2dfcbc0ab7629e58b2abff3faf775aab8a5811c9d7a4b6731aa8d5bcfe2
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b8a7bc2d94c9ea0ffe071c75457ac74606476afd6b9369de8934d48de51f969
+oid sha256:6e68bec7e5538b088fe835e8b3fa07629ac045e5f72cfaec32ef3dcc6e2b3618
 size 101184122

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f302da87234d60be2732930a367f7b678905c7b7dabfefb0c922f3ce081e531
+oid sha256:87d0232b9ccff07686cfc810ec869769f203462f49e711f71027440d829ee580
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74bd2159125d0f907db16bbcac1721766456bd376415594212d2347f8417e92e
+oid sha256:da58c16ff4044ab803801ef38f08c583eaf5db01211f9109b9c9a6d6b1533ded
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:102b7033be1746e3436dc55ed1b2ec55cee011e51f513564ad09f6ed1963a535
+oid sha256:f4a33f582f8be3b5e163b7e3e4e25f954414d05c290f00ab0b23182a29c2d18a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f764f48945785d61e1926877c9eb9b8dced79b9923fd18d60c995acb5d36dcd5
+oid sha256:2ca70537e176d98e3af0ed7ec7090d20b849a4d977ef176a82942c5ef1fe44d8
 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": 0.032658393207054215,
+  "epoch": 0.06531678641410843,
   "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": 1.1165,
       "step": 25
+    },
+    {
+      "epoch": 0.033964728935336384,
+      "grad_norm": 0.38914942741394043,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 1.052,
+      "step": 26
+    },
+    {
+      "epoch": 0.03527106466361855,
+      "grad_norm": 0.31749430298805237,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 1.0732,
+      "step": 27
+    },
+    {
+      "epoch": 0.03527106466361855,
+      "eval_loss": 1.076000452041626,
+      "eval_runtime": 9.4827,
+      "eval_samples_per_second": 271.862,
+      "eval_steps_per_second": 8.542,
+      "step": 27
+    },
+    {
+      "epoch": 0.036577400391900716,
+      "grad_norm": 0.32451197504997253,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.0701,
+      "step": 28
+    },
+    {
+      "epoch": 0.037883736120182886,
+      "grad_norm": 0.32556551694869995,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 1.1153,
+      "step": 29
+    },
+    {
+      "epoch": 0.039190071848465055,
+      "grad_norm": 0.34510084986686707,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 1.0123,
+      "step": 30
+    },
+    {
+      "epoch": 0.040496407576747225,
+      "grad_norm": 0.39450201392173767,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 1.1092,
+      "step": 31
+    },
+    {
+      "epoch": 0.041802743305029394,
+      "grad_norm": 0.31846481561660767,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 1.0717,
+      "step": 32
+    },
+    {
+      "epoch": 0.04310907903331156,
+      "grad_norm": 0.27703917026519775,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 1.0751,
+      "step": 33
+    },
+    {
+      "epoch": 0.04441541476159373,
+      "grad_norm": 0.3374369144439697,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 1.0965,
+      "step": 34
+    },
+    {
+      "epoch": 0.045721750489875895,
+      "grad_norm": 0.3880363404750824,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 1.0428,
+      "step": 35
+    },
+    {
+      "epoch": 0.047028086218158065,
+      "grad_norm": 0.3148273229598999,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 1.0309,
+      "step": 36
+    },
+    {
+      "epoch": 0.047028086218158065,
+      "eval_loss": 1.0441398620605469,
+      "eval_runtime": 9.4448,
+      "eval_samples_per_second": 272.954,
+      "eval_steps_per_second": 8.576,
+      "step": 36
+    },
+    {
+      "epoch": 0.048334421946440234,
+      "grad_norm": 0.2607744336128235,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.0598,
+      "step": 37
+    },
+    {
+      "epoch": 0.049640757674722404,
+      "grad_norm": 0.5195264220237732,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 1.0636,
+      "step": 38
+    },
+    {
+      "epoch": 0.05094709340300457,
+      "grad_norm": 0.31607645750045776,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 1.0021,
+      "step": 39
+    },
+    {
+      "epoch": 0.05225342913128674,
+      "grad_norm": 0.3106956481933594,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.0262,
+      "step": 40
+    },
+    {
+      "epoch": 0.05355976485956891,
+      "grad_norm": 0.29179874062538147,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 1.0262,
+      "step": 41
+    },
+    {
+      "epoch": 0.054866100587851074,
+      "grad_norm": 0.3367427885532379,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 1.0069,
+      "step": 42
+    },
+    {
+      "epoch": 0.056172436316133244,
+      "grad_norm": 0.2948434352874756,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 1.025,
+      "step": 43
+    },
+    {
+      "epoch": 0.05747877204441541,
+      "grad_norm": 0.2905190885066986,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.996,
+      "step": 44
+    },
+    {
+      "epoch": 0.05878510777269758,
+      "grad_norm": 0.3415267765522003,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.9931,
+      "step": 45
+    },
+    {
+      "epoch": 0.05878510777269758,
+      "eval_loss": 1.0246894359588623,
+      "eval_runtime": 9.4671,
+      "eval_samples_per_second": 272.311,
+      "eval_steps_per_second": 8.556,
+      "step": 45
+    },
+    {
+      "epoch": 0.06009144350097975,
+      "grad_norm": 0.28528183698654175,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.0149,
+      "step": 46
+    },
+    {
+      "epoch": 0.06139777922926192,
+      "grad_norm": 0.28322818875312805,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 1.0145,
+      "step": 47
+    },
+    {
+      "epoch": 0.06270411495754409,
+      "grad_norm": 0.31846946477890015,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 1.0618,
+      "step": 48
+    },
+    {
+      "epoch": 0.06401045068582625,
+      "grad_norm": 0.3214743137359619,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 1.0372,
+      "step": 49
+    },
+    {
+      "epoch": 0.06531678641410843,
+      "grad_norm": 0.30648520588874817,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.9778,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.02936877203456e+16,
+  "total_flos": 2.05873754406912e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null