Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd1a699c899c66c3483c0bc61a46da1b71da65594636ee6e96eab0e20556bab9
+oid sha256:465edf459713c37dfae8eb3dfc80654d5f2409fa2d7b4c8918fba4621be6829a
 size 203456160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:338ab50d96effecf99a67c36fac532876cb2c07f93b975c541c4e91b5e2d4b4a
+oid sha256:359b2841cd5283cc4f0148dc1305cfd10a1e734583541f70e33d6e221967660f
 size 407121750

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e9254c9a7c8d26ee556f3a0f80928865acf8ebd0e485e4445b3a5b7eb0994e4
+oid sha256:d44ea2c53d70d08247a4563dcedc504c0453212c9b040cd093f77037398a5116
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef593f391c66ba3ea6e8dea3b2aa8e19ae1f574e3c6a18c96ee14293016120aa
+oid sha256:0f6003820aa1d9b0e6aa1d70309948568223b16abb8759408bc4ed8976518161
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1519756838905775,
+  "epoch": 0.22796352583586627,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 3.72,
       "eval_steps_per_second": 1.873,
       "step": 50
+    },
+    {
+      "epoch": 0.15501519756838905,
+      "grad_norm": 17.6353759765625,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 1.4377,
+      "step": 51
+    },
+    {
+      "epoch": 0.1580547112462006,
+      "grad_norm": 15.932900428771973,
+      "learning_rate": 1.1567509791329401e-05,
+      "loss": 1.1834,
+      "step": 52
+    },
+    {
+      "epoch": 0.16109422492401215,
+      "grad_norm": 13.163067817687988,
+      "learning_rate": 1.0660589091223855e-05,
+      "loss": 1.5885,
+      "step": 53
+    },
+    {
+      "epoch": 0.1641337386018237,
+      "grad_norm": 11.45263385772705,
+      "learning_rate": 9.780964274781984e-06,
+      "loss": 0.9741,
+      "step": 54
+    },
+    {
+      "epoch": 0.16717325227963525,
+      "grad_norm": 8.3353910446167,
+      "learning_rate": 8.930309757836517e-06,
+      "loss": 0.6441,
+      "step": 55
+    },
+    {
+      "epoch": 0.1702127659574468,
+      "grad_norm": 7.865023612976074,
+      "learning_rate": 8.110244809608495e-06,
+      "loss": 0.658,
+      "step": 56
+    },
+    {
+      "epoch": 0.17325227963525835,
+      "grad_norm": 6.3831095695495605,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.8165,
+      "step": 57
+    },
+    {
+      "epoch": 0.1762917933130699,
+      "grad_norm": 5.159278869628906,
+      "learning_rate": 6.568066579746901e-06,
+      "loss": 0.665,
+      "step": 58
+    },
+    {
+      "epoch": 0.17933130699088146,
+      "grad_norm": 4.828774452209473,
+      "learning_rate": 5.848888922025553e-06,
+      "loss": 0.647,
+      "step": 59
+    },
+    {
+      "epoch": 0.182370820668693,
+      "grad_norm": 5.115424156188965,
+      "learning_rate": 5.166166492719124e-06,
+      "loss": 0.47,
+      "step": 60
+    },
+    {
+      "epoch": 0.18541033434650456,
+      "grad_norm": 3.0081770420074463,
+      "learning_rate": 4.521198892775203e-06,
+      "loss": 0.4042,
+      "step": 61
+    },
+    {
+      "epoch": 0.1884498480243161,
+      "grad_norm": 3.4292054176330566,
+      "learning_rate": 3.9152138546778625e-06,
+      "loss": 0.5876,
+      "step": 62
+    },
+    {
+      "epoch": 0.19148936170212766,
+      "grad_norm": 5.665149211883545,
+      "learning_rate": 3.3493649053890326e-06,
+      "loss": 0.6981,
+      "step": 63
+    },
+    {
+      "epoch": 0.1945288753799392,
+      "grad_norm": 5.063657283782959,
+      "learning_rate": 2.8247291705444575e-06,
+      "loss": 0.8123,
+      "step": 64
+    },
+    {
+      "epoch": 0.19756838905775076,
+      "grad_norm": 5.569523334503174,
+      "learning_rate": 2.3423053240837515e-06,
+      "loss": 0.7608,
+      "step": 65
+    },
+    {
+      "epoch": 0.2006079027355623,
+      "grad_norm": 5.494087219238281,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 0.6362,
+      "step": 66
+    },
+    {
+      "epoch": 0.20364741641337386,
+      "grad_norm": 3.7691006660461426,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 0.4503,
+      "step": 67
+    },
+    {
+      "epoch": 0.2066869300911854,
+      "grad_norm": 2.7975122928619385,
+      "learning_rate": 1.1570762312943295e-06,
+      "loss": 0.5325,
+      "step": 68
+    },
+    {
+      "epoch": 0.20972644376899696,
+      "grad_norm": 5.918449401855469,
+      "learning_rate": 8.51854342773295e-07,
+      "loss": 0.5773,
+      "step": 69
+    },
+    {
+      "epoch": 0.2127659574468085,
+      "grad_norm": 5.920218467712402,
+      "learning_rate": 5.925998220016659e-07,
+      "loss": 0.731,
+      "step": 70
+    },
+    {
+      "epoch": 0.21580547112462006,
+      "grad_norm": 6.536037445068359,
+      "learning_rate": 3.7980617469479953e-07,
+      "loss": 0.6718,
+      "step": 71
+    },
+    {
+      "epoch": 0.2188449848024316,
+      "grad_norm": 6.299208164215088,
+      "learning_rate": 2.1387846565474045e-07,
+      "loss": 0.7229,
+      "step": 72
+    },
+    {
+      "epoch": 0.22188449848024316,
+      "grad_norm": 6.822452545166016,
+      "learning_rate": 9.513254770636137e-08,
+      "loss": 0.7534,
+      "step": 73
+    },
+    {
+      "epoch": 0.22492401215805471,
+      "grad_norm": 7.545007705688477,
+      "learning_rate": 2.3794460453555047e-08,
+      "loss": 0.7793,
+      "step": 74
+    },
+    {
+      "epoch": 0.22796352583586627,
+      "grad_norm": 8.794013977050781,
+      "learning_rate": 0.0,
+      "loss": 0.8974,
+      "step": 75
+    },
+    {
+      "epoch": 0.22796352583586627,
+      "eval_loss": 0.7993611693382263,
+      "eval_runtime": 37.3913,
+      "eval_samples_per_second": 3.717,
+      "eval_steps_per_second": 1.872,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -395,12 +578,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.6588433522688e+16,
+  "total_flos": 2.4882650284032e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null