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:d582bd7822fba803e418e7abf920e6aafaff5c40bd901d823c735cefb34cd898
+oid sha256:9954a1685a6e981d2cbcb7fef450b316454356d9bfc228ca35b8663590f631fa
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9f9982f98cde8bd8042c524224a1e219e9ea5666d5d11b2faaf39f414fbabc7
+oid sha256:c48d0d6028a95807aaf6e350329fcc46fe1e2797b38ebec016d7bc6bae1641dc
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80a914b55977d11403cf505f4500435fb21205e3cb9d74c7567cbef803df00b5
+oid sha256:06433e1beb51c034458d1b227ee25690394f4c8d72f8fe8edad932bedf1cad65
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99fc9c0ec571f76cf9b6d1229601c5173899cd18104e487c5627f5f4c56c6e8a
+oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.22148394241417496,
+  "epoch": 0.4429678848283499,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 2.874,
       "eval_steps_per_second": 1.452,
       "step": 25
+    },
+    {
+      "epoch": 0.23034330011074197,
+      "grad_norm": 9.847829818725586,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 1.8953,
+      "step": 26
+    },
+    {
+      "epoch": 0.23920265780730898,
+      "grad_norm": 12.596794128417969,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 2.5057,
+      "step": 27
+    },
+    {
+      "epoch": 0.24806201550387597,
+      "grad_norm": 14.005389213562012,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 2.6737,
+      "step": 28
+    },
+    {
+      "epoch": 0.25692137320044295,
+      "grad_norm": 6.553339004516602,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 1.1646,
+      "step": 29
+    },
+    {
+      "epoch": 0.26578073089701,
+      "grad_norm": 7.477066516876221,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.5723,
+      "step": 30
+    },
+    {
+      "epoch": 0.27464008859357697,
+      "grad_norm": 6.714325428009033,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.9372,
+      "step": 31
+    },
+    {
+      "epoch": 0.28349944629014395,
+      "grad_norm": 5.366620063781738,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 0.9127,
+      "step": 32
+    },
+    {
+      "epoch": 0.292358803986711,
+      "grad_norm": 5.267599582672119,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 0.9486,
+      "step": 33
+    },
+    {
+      "epoch": 0.301218161683278,
+      "grad_norm": 5.721604824066162,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 1.0115,
+      "step": 34
+    },
+    {
+      "epoch": 0.31007751937984496,
+      "grad_norm": 9.588211059570312,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 1.5512,
+      "step": 35
+    },
+    {
+      "epoch": 0.31893687707641194,
+      "grad_norm": 8.468229293823242,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 2.0242,
+      "step": 36
+    },
+    {
+      "epoch": 0.327796234772979,
+      "grad_norm": 7.019147872924805,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 1.4333,
+      "step": 37
+    },
+    {
+      "epoch": 0.33665559246954596,
+      "grad_norm": 7.140212535858154,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 1.4574,
+      "step": 38
+    },
+    {
+      "epoch": 0.34551495016611294,
+      "grad_norm": 7.104815483093262,
+      "learning_rate": 5e-05,
+      "loss": 1.6285,
+      "step": 39
+    },
+    {
+      "epoch": 0.35437430786268,
+      "grad_norm": 7.665496349334717,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 1.7756,
+      "step": 40
+    },
+    {
+      "epoch": 0.36323366555924697,
+      "grad_norm": 5.0741448402404785,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 0.7064,
+      "step": 41
+    },
+    {
+      "epoch": 0.37209302325581395,
+      "grad_norm": 6.9342145919799805,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.5397,
+      "step": 42
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 11.797982215881348,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.0307,
+      "step": 43
+    },
+    {
+      "epoch": 0.38981173864894797,
+      "grad_norm": 8.055065155029297,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 1.4454,
+      "step": 44
+    },
+    {
+      "epoch": 0.39867109634551495,
+      "grad_norm": 6.281280040740967,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.0751,
+      "step": 45
+    },
+    {
+      "epoch": 0.40753045404208194,
+      "grad_norm": 7.641656875610352,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 0.9188,
+      "step": 46
+    },
+    {
+      "epoch": 0.416389811738649,
+      "grad_norm": 6.952744960784912,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 1.0005,
+      "step": 47
+    },
+    {
+      "epoch": 0.42524916943521596,
+      "grad_norm": 8.935934066772461,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.0907,
+      "step": 48
+    },
+    {
+      "epoch": 0.43410852713178294,
+      "grad_norm": 6.720633506774902,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 0.9396,
+      "step": 49
+    },
+    {
+      "epoch": 0.4429678848283499,
+      "grad_norm": 7.035938262939453,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 1.2922,
+      "step": 50
+    },
+    {
+      "epoch": 0.4429678848283499,
+      "eval_loss": 0.16461199522018433,
+      "eval_runtime": 33.0376,
+      "eval_samples_per_second": 2.876,
+      "eval_steps_per_second": 1.453,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.53626333642752e+16,
+  "total_flos": 7.07252667285504e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null