Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55786c0993d85e7a4a1785b058fcadc0ee222177403dd86e3d0422fd6660146d
+oid sha256:b24bbe774f0d17debed0b6849f76e217e797f9f1bf0a056b11ff44a7f42c5cb6
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bff8d18e6d630f7ff98d754dffbcd35479147566c5dc07ba1ca0e52bdadd548e
+oid sha256:c266486906ca1441079e6ae5892f8c44ea161f03f0edfcebde86fe4fcc3b16a6
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d755d5c040b6e3cdaaef4521c6499acce4c2354a0d81cb6941308c683712a33
+oid sha256:10b0f4f9d935debe1754d2bcdf6836577fd7f75677fdbebc826454f63e3fb737
 size 14244

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": 0.0005615516796010736,
+  "epoch": 0.0011231033592021473,
   "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": 4.0075,
       "step": 25
+    },
+    {
+      "epoch": 0.0005840137467851166,
+      "grad_norm": 2.525400400161743,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 3.4141,
+      "step": 26
+    },
+    {
+      "epoch": 0.0006064758139691596,
+      "grad_norm": 3.1710431575775146,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 3.5087,
+      "step": 27
+    },
+    {
+      "epoch": 0.0006064758139691596,
+      "eval_loss": 1.780084252357483,
+      "eval_runtime": 1632.5434,
+      "eval_samples_per_second": 22.964,
+      "eval_steps_per_second": 2.871,
+      "step": 27
+    },
+    {
+      "epoch": 0.0006289378811532026,
+      "grad_norm": 2.813370704650879,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 3.8044,
+      "step": 28
+    },
+    {
+      "epoch": 0.0006513999483372455,
+      "grad_norm": 2.058415174484253,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 3.2233,
+      "step": 29
+    },
+    {
+      "epoch": 0.0006738620155212885,
+      "grad_norm": 1.962506890296936,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 3.5407,
+      "step": 30
+    },
+    {
+      "epoch": 0.0006963240827053314,
+      "grad_norm": 2.352518320083618,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 3.8538,
+      "step": 31
+    },
+    {
+      "epoch": 0.0007187861498893744,
+      "grad_norm": 2.3428025245666504,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 3.6797,
+      "step": 32
+    },
+    {
+      "epoch": 0.0007412482170734173,
+      "grad_norm": 1.7835075855255127,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 3.832,
+      "step": 33
+    },
+    {
+      "epoch": 0.0007637102842574603,
+      "grad_norm": 1.6647694110870361,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 3.4723,
+      "step": 34
+    },
+    {
+      "epoch": 0.0007861723514415032,
+      "grad_norm": 2.274492025375366,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 3.0918,
+      "step": 35
+    },
+    {
+      "epoch": 0.0008086344186255461,
+      "grad_norm": 3.1563773155212402,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 3.5549,
+      "step": 36
+    },
+    {
+      "epoch": 0.0008086344186255461,
+      "eval_loss": 1.7567815780639648,
+      "eval_runtime": 1632.074,
+      "eval_samples_per_second": 22.971,
+      "eval_steps_per_second": 2.872,
+      "step": 36
+    },
+    {
+      "epoch": 0.0008310964858095891,
+      "grad_norm": 2.0984981060028076,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 3.4193,
+      "step": 37
+    },
+    {
+      "epoch": 0.000853558552993632,
+      "grad_norm": 1.842602252960205,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 3.5343,
+      "step": 38
+    },
+    {
+      "epoch": 0.000876020620177675,
+      "grad_norm": 1.6959556341171265,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 3.3391,
+      "step": 39
+    },
+    {
+      "epoch": 0.0008984826873617179,
+      "grad_norm": 1.5816162824630737,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 2.8507,
+      "step": 40
+    },
+    {
+      "epoch": 0.0009209447545457609,
+      "grad_norm": 1.8995237350463867,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 3.7906,
+      "step": 41
+    },
+    {
+      "epoch": 0.0009434068217298038,
+      "grad_norm": 1.9689886569976807,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 4.1076,
+      "step": 42
+    },
+    {
+      "epoch": 0.0009658688889138468,
+      "grad_norm": 2.290149450302124,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 3.3636,
+      "step": 43
+    },
+    {
+      "epoch": 0.0009883309560978896,
+      "grad_norm": 2.0681443214416504,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 2.7999,
+      "step": 44
+    },
+    {
+      "epoch": 0.0010107930232819327,
+      "grad_norm": 1.7715750932693481,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 3.1144,
+      "step": 45
+    },
+    {
+      "epoch": 0.0010107930232819327,
+      "eval_loss": 1.7513365745544434,
+      "eval_runtime": 1632.0626,
+      "eval_samples_per_second": 22.971,
+      "eval_steps_per_second": 2.872,
+      "step": 45
+    },
+    {
+      "epoch": 0.0010332550904659755,
+      "grad_norm": 1.7227574586868286,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 3.4745,
+      "step": 46
+    },
+    {
+      "epoch": 0.0010557171576500185,
+      "grad_norm": 1.5659047365188599,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 3.3294,
+      "step": 47
+    },
+    {
+      "epoch": 0.0010781792248340614,
+      "grad_norm": 1.7313659191131592,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 2.6789,
+      "step": 48
+    },
+    {
+      "epoch": 0.0011006412920181044,
+      "grad_norm": 1.6729196310043335,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 3.0046,
+      "step": 49
+    },
+    {
+      "epoch": 0.0011231033592021473,
+      "grad_norm": 1.5939840078353882,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 3.185,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.63364550475776e+16,
+  "total_flos": 3.26729100951552e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null