Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c564bc190ce252e7a29f20f133ebee63f41f5b40866b49cbe3cde56fdf01f32
+oid sha256:597798ff3f904b0649eecd612da8136b39eaf44e0db765e5c1622dbc60e7a16d
 size 619632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1664532094afb5cee94be5e411daf0ac834666580caf5ecdb772935662918a1
+oid sha256:34571fedef1818ebe179d22e406350c17f466bb40f5e22fedac5f31bb68e44cb
 size 1389562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b156083f33d0dbcf46e139dffefdd9767208d702848055291ecd8869c56ab594
+oid sha256:e825d3fa134c8fd3704e54a274c755812b515cc2ef88c16e34a4777008c5e297
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008090614886731391,
+  "epoch": 0.016181229773462782,
   "eval_steps": 5,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,221 @@
       "eval_samples_per_second": 29.873,
       "eval_steps_per_second": 3.741,
       "step": 25
+    },
+    {
+      "epoch": 0.008414239482200648,
+      "grad_norm": 0.1864924430847168,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 11.9232,
+      "step": 26
+    },
+    {
+      "epoch": 0.008737864077669903,
+      "grad_norm": 0.16649341583251953,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 11.9255,
+      "step": 27
+    },
+    {
+      "epoch": 0.009061488673139158,
+      "grad_norm": 0.17214755713939667,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 11.923,
+      "step": 28
+    },
+    {
+      "epoch": 0.009385113268608414,
+      "grad_norm": 0.1947617083787918,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 11.922,
+      "step": 29
+    },
+    {
+      "epoch": 0.009708737864077669,
+      "grad_norm": 0.18796387314796448,
+      "learning_rate": 5e-05,
+      "loss": 11.9239,
+      "step": 30
+    },
+    {
+      "epoch": 0.009708737864077669,
+      "eval_loss": 11.91930866241455,
+      "eval_runtime": 87.8376,
+      "eval_samples_per_second": 29.634,
+      "eval_steps_per_second": 3.711,
+      "step": 30
+    },
+    {
+      "epoch": 0.010032362459546926,
+      "grad_norm": 0.24459634721279144,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 11.9133,
+      "step": 31
+    },
+    {
+      "epoch": 0.010355987055016181,
+      "grad_norm": 0.22615985572338104,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 11.9116,
+      "step": 32
+    },
+    {
+      "epoch": 0.010679611650485437,
+      "grad_norm": 0.16150665283203125,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 11.9235,
+      "step": 33
+    },
+    {
+      "epoch": 0.011003236245954692,
+      "grad_norm": 0.17121870815753937,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 11.912,
+      "step": 34
+    },
+    {
+      "epoch": 0.011326860841423949,
+      "grad_norm": 0.19549013674259186,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.923,
+      "step": 35
+    },
+    {
+      "epoch": 0.011326860841423949,
+      "eval_loss": 11.917806625366211,
+      "eval_runtime": 87.432,
+      "eval_samples_per_second": 29.772,
+      "eval_steps_per_second": 3.729,
+      "step": 35
+    },
+    {
+      "epoch": 0.011650485436893204,
+      "grad_norm": 0.17008088529109955,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 11.926,
+      "step": 36
+    },
+    {
+      "epoch": 0.01197411003236246,
+      "grad_norm": 0.2503155469894409,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 11.9188,
+      "step": 37
+    },
+    {
+      "epoch": 0.012297734627831715,
+      "grad_norm": 0.22915363311767578,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 11.9154,
+      "step": 38
+    },
+    {
+      "epoch": 0.01262135922330097,
+      "grad_norm": 0.18122562766075134,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 11.924,
+      "step": 39
+    },
+    {
+      "epoch": 0.012944983818770227,
+      "grad_norm": 0.2280999720096588,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.9169,
+      "step": 40
+    },
+    {
+      "epoch": 0.012944983818770227,
+      "eval_loss": 11.916872024536133,
+      "eval_runtime": 86.9487,
+      "eval_samples_per_second": 29.937,
+      "eval_steps_per_second": 3.749,
+      "step": 40
+    },
+    {
+      "epoch": 0.013268608414239482,
+      "grad_norm": 0.16677942872047424,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 11.9163,
+      "step": 41
+    },
+    {
+      "epoch": 0.013592233009708738,
+      "grad_norm": 0.15079186856746674,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 11.9181,
+      "step": 42
+    },
+    {
+      "epoch": 0.013915857605177993,
+      "grad_norm": 0.20892250537872314,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 11.9135,
+      "step": 43
+    },
+    {
+      "epoch": 0.01423948220064725,
+      "grad_norm": 0.21506153047084808,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 11.9196,
+      "step": 44
+    },
+    {
+      "epoch": 0.014563106796116505,
+      "grad_norm": 0.1728731095790863,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.9183,
+      "step": 45
+    },
+    {
+      "epoch": 0.014563106796116505,
+      "eval_loss": 11.91650104522705,
+      "eval_runtime": 87.0569,
+      "eval_samples_per_second": 29.9,
+      "eval_steps_per_second": 3.745,
+      "step": 45
+    },
+    {
+      "epoch": 0.01488673139158576,
+      "grad_norm": 0.22333945333957672,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 11.918,
+      "step": 46
+    },
+    {
+      "epoch": 0.015210355987055016,
+      "grad_norm": 0.2123495489358902,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 11.9145,
+      "step": 47
+    },
+    {
+      "epoch": 0.015533980582524271,
+      "grad_norm": 0.1823579967021942,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 11.9195,
+      "step": 48
+    },
+    {
+      "epoch": 0.015857605177993526,
+      "grad_norm": 0.225151926279068,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 11.9077,
+      "step": 49
+    },
+    {
+      "epoch": 0.016181229773462782,
+      "grad_norm": 0.18992595374584198,
+      "learning_rate": 0.0,
+      "loss": 11.9227,
+      "step": 50
+    },
+    {
+      "epoch": 0.016181229773462782,
+      "eval_loss": 11.916434288024902,
+      "eval_runtime": 87.8313,
+      "eval_samples_per_second": 29.636,
+      "eval_steps_per_second": 3.712,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -244,12 +459,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 13710746714112.0,
+  "total_flos": 27421493428224.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null