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:d3568678d20869f937076f80feb30ec267b475584548f7b3ba485f9fcb66a8c7
+oid sha256:b6499f93ee3b478b177c90a21e841cc8624801275f8227f236b4a980ae1ac5c2
 size 550593184

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b265bf48f11d9dddf0e78cdde848536f8df055a66fcd7972a65db3eeaae5277
+oid sha256:acdc9d3dea007f7f1cff09d114ec86579ce955c0c9880c66283108547580a66a
 size 1101572914

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9fdee88efd91cfa6340433c2635a8637a32ae79ac7151d1484742aabd142dda
+oid sha256:ce4475831cf0968316cfe714b6ff0782c5d4defa565b6986bea8c91753c39146
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
+oid sha256:0b823f3900a3c8aa20bff7ce05b4e552f6bc019793f00b0bb20027204b5c704a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001703780689349667,
+  "epoch": 0.0025556710340245005,
   "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": 2.377,
       "eval_steps_per_second": 1.188,
       "step": 50
+    },
+    {
+      "epoch": 0.0017378563031366602,
+      "grad_norm": 4.004736423492432,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.4785,
+      "step": 51
+    },
+    {
+      "epoch": 0.0017719319169236536,
+      "grad_norm": 0.8578753471374512,
+      "learning_rate": 3.082151762439293e-05,
+      "loss": 0.0086,
+      "step": 52
+    },
+    {
+      "epoch": 0.001806007530710647,
+      "grad_norm": 1.8137702941894531,
+      "learning_rate": 2.9189060364202943e-05,
+      "loss": 0.0333,
+      "step": 53
+    },
+    {
+      "epoch": 0.0018400831444976404,
+      "grad_norm": 0.4614853262901306,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0078,
+      "step": 54
+    },
+    {
+      "epoch": 0.0018741587582846336,
+      "grad_norm": 0.09576446563005447,
+      "learning_rate": 2.6074557564105727e-05,
+      "loss": 0.0015,
+      "step": 55
+    },
+    {
+      "epoch": 0.001908234372071627,
+      "grad_norm": 0.09370886534452438,
+      "learning_rate": 2.459844065729529e-05,
+      "loss": 0.0019,
+      "step": 56
+    },
+    {
+      "epoch": 0.0019423099858586204,
+      "grad_norm": 0.4553550183773041,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0037,
+      "step": 57
+    },
+    {
+      "epoch": 0.0019763855996456138,
+      "grad_norm": 0.11098048835992813,
+      "learning_rate": 2.1822519843544424e-05,
+      "loss": 0.0025,
+      "step": 58
+    },
+    {
+      "epoch": 0.002010461213432607,
+      "grad_norm": 0.11278193444013596,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 0.0022,
+      "step": 59
+    },
+    {
+      "epoch": 0.0020445368272196,
+      "grad_norm": 1.5145128965377808,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.042,
+      "step": 60
+    },
+    {
+      "epoch": 0.0020786124410065937,
+      "grad_norm": 0.15734955668449402,
+      "learning_rate": 1.8138158006995364e-05,
+      "loss": 0.0031,
+      "step": 61
+    },
+    {
+      "epoch": 0.002112688054793587,
+      "grad_norm": 0.16131563484668732,
+      "learning_rate": 1.7047384938420154e-05,
+      "loss": 0.0041,
+      "step": 62
+    },
+    {
+      "epoch": 0.00214676366858058,
+      "grad_norm": 1.3162636756896973,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.017,
+      "step": 63
+    },
+    {
+      "epoch": 0.0021808392823675737,
+      "grad_norm": 0.5748438239097595,
+      "learning_rate": 1.5084512506980026e-05,
+      "loss": 0.0109,
+      "step": 64
+    },
+    {
+      "epoch": 0.002214914896154567,
+      "grad_norm": 1.6675885915756226,
+      "learning_rate": 1.4216149583350754e-05,
+      "loss": 0.0192,
+      "step": 65
+    },
+    {
+      "epoch": 0.0022489905099415605,
+      "grad_norm": 0.22785191237926483,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0039,
+      "step": 66
+    },
+    {
+      "epoch": 0.0022830661237285537,
+      "grad_norm": 0.2156006395816803,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 0.0043,
+      "step": 67
+    },
+    {
+      "epoch": 0.002317141737515547,
+      "grad_norm": 1.7005534172058105,
+      "learning_rate": 1.2082737216329794e-05,
+      "loss": 0.0998,
+      "step": 68
+    },
+    {
+      "epoch": 0.0023512173513025405,
+      "grad_norm": 0.23563118278980255,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0034,
+      "step": 69
+    },
+    {
+      "epoch": 0.0023852929650895337,
+      "grad_norm": 0.18278473615646362,
+      "learning_rate": 1.1066679679603e-05,
+      "loss": 0.0037,
+      "step": 70
+    },
+    {
+      "epoch": 0.002419368578876527,
+      "grad_norm": 2.191817045211792,
+      "learning_rate": 1.0683651114450641e-05,
+      "loss": 0.0575,
+      "step": 71
+    },
+    {
+      "epoch": 0.0024534441926635205,
+      "grad_norm": 0.29528528451919556,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0046,
+      "step": 72
+    },
+    {
+      "epoch": 0.0024875198064505137,
+      "grad_norm": 0.05887974426150322,
+      "learning_rate": 1.017123858587145e-05,
+      "loss": 0.0012,
+      "step": 73
+    },
+    {
+      "epoch": 0.002521595420237507,
+      "grad_norm": 0.8336066603660583,
+      "learning_rate": 1.00428300288164e-05,
+      "loss": 0.0193,
+      "step": 74
+    },
+    {
+      "epoch": 0.0025556710340245005,
+      "grad_norm": 0.5219399333000183,
+      "learning_rate": 1e-05,
+      "loss": 0.0082,
+      "step": 75
+    },
+    {
+      "epoch": 0.0025556710340245005,
+      "eval_loss": 0.019740475341677666,
+      "eval_runtime": 5200.5985,
+      "eval_samples_per_second": 2.376,
+      "eval_steps_per_second": 1.188,
+      "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": 1.3958909501689037e+17,
+  "total_flos": 2.1111982529917747e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null