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:ada68f5fcb94fc327144416670f792f2c185afbb80f6e235d841fad29eaa529a
+oid sha256:aed2c82186f0eb6457408b87f4b2e272f5a4397d94be3934dd60f96cfa04bd17
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b28318783f39df7eaf33a13a9b6c8d79166c46bffe69108f73785d1984300e1d
+oid sha256:efce45376183a728eb6c42126e71a694aaf95a67d6b7bcacb863d99cc4049245
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9a7d173356aca7df300d5b82886319b025b46d71c92da2a3de7d1ca16a554f9
+oid sha256:aa7afc0abd82d7254faf4024835247231e6f83d118e050d2a5e1a94ae5d01c04
 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": 0.012790995139421847,
+  "epoch": 0.025581990278843694,
   "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": 1.4226,
       "step": 25
+    },
+    {
+      "epoch": 0.01330263494499872,
+      "grad_norm": 1.8918830156326294,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 1.3571,
+      "step": 26
+    },
+    {
+      "epoch": 0.013814274750575594,
+      "grad_norm": 2.5752553939819336,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 1.2146,
+      "step": 27
+    },
+    {
+      "epoch": 0.013814274750575594,
+      "eval_loss": 0.7836452126502991,
+      "eval_runtime": 274.2003,
+      "eval_samples_per_second": 6.003,
+      "eval_steps_per_second": 0.751,
+      "step": 27
+    },
+    {
+      "epoch": 0.014325914556152468,
+      "grad_norm": 2.8034920692443848,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.6562,
+      "step": 28
+    },
+    {
+      "epoch": 0.014837554361729342,
+      "grad_norm": 2.0168240070343018,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 1.3663,
+      "step": 29
+    },
+    {
+      "epoch": 0.015349194167306216,
+      "grad_norm": 3.294177770614624,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 1.5281,
+      "step": 30
+    },
+    {
+      "epoch": 0.01586083397288309,
+      "grad_norm": 2.886345624923706,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 1.5451,
+      "step": 31
+    },
+    {
+      "epoch": 0.016372473778459965,
+      "grad_norm": 1.7247331142425537,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 1.0179,
+      "step": 32
+    },
+    {
+      "epoch": 0.01688411358403684,
+      "grad_norm": 1.886189579963684,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 1.3923,
+      "step": 33
+    },
+    {
+      "epoch": 0.017395753389613713,
+      "grad_norm": 2.080334424972534,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 1.2178,
+      "step": 34
+    },
+    {
+      "epoch": 0.017907393195190587,
+      "grad_norm": 2.708214282989502,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 1.2374,
+      "step": 35
+    },
+    {
+      "epoch": 0.01841903300076746,
+      "grad_norm": 2.5027191638946533,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 1.0007,
+      "step": 36
+    },
+    {
+      "epoch": 0.01841903300076746,
+      "eval_loss": 0.7541875243186951,
+      "eval_runtime": 274.1248,
+      "eval_samples_per_second": 6.005,
+      "eval_steps_per_second": 0.751,
+      "step": 36
+    },
+    {
+      "epoch": 0.018930672806344334,
+      "grad_norm": 1.938878059387207,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.2976,
+      "step": 37
+    },
+    {
+      "epoch": 0.019442312611921208,
+      "grad_norm": 2.1836838722229004,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 1.5049,
+      "step": 38
+    },
+    {
+      "epoch": 0.019953952417498082,
+      "grad_norm": 2.365196704864502,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 1.2362,
+      "step": 39
+    },
+    {
+      "epoch": 0.020465592223074956,
+      "grad_norm": 1.9262018203735352,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.7173,
+      "step": 40
+    },
+    {
+      "epoch": 0.02097723202865183,
+      "grad_norm": 2.8925254344940186,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 1.3671,
+      "step": 41
+    },
+    {
+      "epoch": 0.021488871834228703,
+      "grad_norm": 1.5692651271820068,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 1.1358,
+      "step": 42
+    },
+    {
+      "epoch": 0.022000511639805577,
+      "grad_norm": 2.8360183238983154,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 1.3804,
+      "step": 43
+    },
+    {
+      "epoch": 0.02251215144538245,
+      "grad_norm": 1.7869185209274292,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 1.2711,
+      "step": 44
+    },
+    {
+      "epoch": 0.023023791250959325,
+      "grad_norm": 2.3221404552459717,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 1.7126,
+      "step": 45
+    },
+    {
+      "epoch": 0.023023791250959325,
+      "eval_loss": 0.7342292070388794,
+      "eval_runtime": 274.1224,
+      "eval_samples_per_second": 6.005,
+      "eval_steps_per_second": 0.751,
+      "step": 45
+    },
+    {
+      "epoch": 0.0235354310565362,
+      "grad_norm": 4.136687278747559,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.7686,
+      "step": 46
+    },
+    {
+      "epoch": 0.024047070862113072,
+      "grad_norm": 2.2173714637756348,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 1.2285,
+      "step": 47
+    },
+    {
+      "epoch": 0.024558710667689946,
+      "grad_norm": 2.4053614139556885,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 1.4621,
+      "step": 48
+    },
+    {
+      "epoch": 0.02507035047326682,
+      "grad_norm": 2.109034299850464,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 1.4664,
+      "step": 49
+    },
+    {
+      "epoch": 0.025581990278843694,
+      "grad_norm": 1.8373016119003296,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 1.2307,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.30085064245248e+16,
+  "total_flos": 6.60170128490496e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null