Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:295ab602c1d0de1af4bb8d1b0ce9cb5469855a46ad48fc8fef2a482b7f1ceee7
+oid sha256:bae1fa019f47abe44c4648f4cfa2b9012b2c3872fdf7c961e1dfef6dc75dd352
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:142e7ae99a472b7a404c25ccc9709d3bf88d35847ac5ecdafeff52fc931be412
+oid sha256:bee16ed540d0f11897b7c02986102a0b3fe6de398141e8698a1227e67779230d
 size 27273018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf02400deed1f594fcb98f8ad14af650410294031918ab28e43c3efd817c223c
+oid sha256:b8f0568c42ae597f07515ceef30e5cf43dd213155ef34bfcd58b0db95bc12e49
 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": 0.052083333333333336,
+  "epoch": 0.10416666666666667,
   "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": 3.4153,
       "step": 25
+    },
+    {
+      "epoch": 0.05416666666666667,
+      "grad_norm": 2.485572099685669,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 3.4914,
+      "step": 26
+    },
+    {
+      "epoch": 0.05625,
+      "grad_norm": 2.5699574947357178,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 3.1668,
+      "step": 27
+    },
+    {
+      "epoch": 0.05625,
+      "eval_loss": 3.3760266304016113,
+      "eval_runtime": 7.3085,
+      "eval_samples_per_second": 55.415,
+      "eval_steps_per_second": 6.978,
+      "step": 27
+    },
+    {
+      "epoch": 0.058333333333333334,
+      "grad_norm": 2.5762226581573486,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 3.1,
+      "step": 28
+    },
+    {
+      "epoch": 0.06041666666666667,
+      "grad_norm": 2.518932819366455,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 3.0839,
+      "step": 29
+    },
+    {
+      "epoch": 0.0625,
+      "grad_norm": 2.558347463607788,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 3.0345,
+      "step": 30
+    },
+    {
+      "epoch": 0.06458333333333334,
+      "grad_norm": 2.8206636905670166,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 2.8389,
+      "step": 31
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 2.4276182651519775,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 3.0512,
+      "step": 32
+    },
+    {
+      "epoch": 0.06875,
+      "grad_norm": 2.0624449253082275,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 2.8569,
+      "step": 33
+    },
+    {
+      "epoch": 0.07083333333333333,
+      "grad_norm": 2.290245532989502,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 2.9446,
+      "step": 34
+    },
+    {
+      "epoch": 0.07291666666666667,
+      "grad_norm": 2.596433162689209,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 2.8816,
+      "step": 35
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 2.742198944091797,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 3.0495,
+      "step": 36
+    },
+    {
+      "epoch": 0.075,
+      "eval_loss": 2.7696404457092285,
+      "eval_runtime": 7.2384,
+      "eval_samples_per_second": 55.952,
+      "eval_steps_per_second": 7.046,
+      "step": 36
+    },
+    {
+      "epoch": 0.07708333333333334,
+      "grad_norm": 3.0168638229370117,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 2.9035,
+      "step": 37
+    },
+    {
+      "epoch": 0.07916666666666666,
+      "grad_norm": 2.419011354446411,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 2.6274,
+      "step": 38
+    },
+    {
+      "epoch": 0.08125,
+      "grad_norm": 2.704653263092041,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 2.5635,
+      "step": 39
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "grad_norm": 2.1320738792419434,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 2.5515,
+      "step": 40
+    },
+    {
+      "epoch": 0.08541666666666667,
+      "grad_norm": 2.665830135345459,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 2.6788,
+      "step": 41
+    },
+    {
+      "epoch": 0.0875,
+      "grad_norm": 2.480651617050171,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 2.5316,
+      "step": 42
+    },
+    {
+      "epoch": 0.08958333333333333,
+      "grad_norm": 2.5246286392211914,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 2.3854,
+      "step": 43
+    },
+    {
+      "epoch": 0.09166666666666666,
+      "grad_norm": 2.1733431816101074,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 2.5616,
+      "step": 44
+    },
+    {
+      "epoch": 0.09375,
+      "grad_norm": 2.5621912479400635,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 2.5194,
+      "step": 45
+    },
+    {
+      "epoch": 0.09375,
+      "eval_loss": 2.5489118099212646,
+      "eval_runtime": 7.2386,
+      "eval_samples_per_second": 55.95,
+      "eval_steps_per_second": 7.046,
+      "step": 45
+    },
+    {
+      "epoch": 0.09583333333333334,
+      "grad_norm": 2.836992025375366,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.3388,
+      "step": 46
+    },
+    {
+      "epoch": 0.09791666666666667,
+      "grad_norm": 2.6127188205718994,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 2.3638,
+      "step": 47
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.9710822105407715,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 2.3855,
+      "step": 48
+    },
+    {
+      "epoch": 0.10208333333333333,
+      "grad_norm": 2.2118475437164307,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 2.3853,
+      "step": 49
+    },
+    {
+      "epoch": 0.10416666666666667,
+      "grad_norm": 2.0311408042907715,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 2.2054,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 694187930419200.0,
+  "total_flos": 1388375860838400.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null