Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cc1a1217204e52fdad0e5f7e6d91124a346c39f556163756c296d1f2751a608
+oid sha256:3d3d9a0d4af70579cc7d416e48094f46e6d792226b735a4ec418fd6a5799b413
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96c6285fd972f63e6d1f9c9f03f912ba05da0e1233b2a10636760d6c23fe25d5
+oid sha256:d8c178c7ba51191e6f979efc088afb7cd77001bc460923ab4598e8fb9b6eb917
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:392d94d3acb0b66fb1c3dab39d3e9e44137c67f588e6391c4cd8effb0aa77252
+oid sha256:eae4a00498eae213a9ac94811fd6e10f603c3fc5770db8c2d81ab447acaae8a3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
+oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005047445992327882,
+  "epoch": 0.007571168988491823,
   "eval_steps": 9,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -405,6 +405,205 @@
       "learning_rate": 5.868240888334653e-05,
       "loss": 2.1617,
       "step": 50
+    },
+    {
+      "epoch": 0.00514839491217444,
+      "grad_norm": 0.34431248903274536,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 2.1716,
+      "step": 51
+    },
+    {
+      "epoch": 0.005249343832020997,
+      "grad_norm": 0.2910543382167816,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 2.1826,
+      "step": 52
+    },
+    {
+      "epoch": 0.005350292751867555,
+      "grad_norm": 0.21696153283119202,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 2.164,
+      "step": 53
+    },
+    {
+      "epoch": 0.005451241671714113,
+      "grad_norm": 0.2520364224910736,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 2.178,
+      "step": 54
+    },
+    {
+      "epoch": 0.005451241671714113,
+      "eval_loss": 2.168518543243408,
+      "eval_runtime": 836.9008,
+      "eval_samples_per_second": 9.968,
+      "eval_steps_per_second": 1.246,
+      "step": 54
+    },
+    {
+      "epoch": 0.0055521905915606705,
+      "grad_norm": 0.23974812030792236,
+      "learning_rate": 5e-05,
+      "loss": 2.168,
+      "step": 55
+    },
+    {
+      "epoch": 0.005653139511407228,
+      "grad_norm": 0.2293047308921814,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 2.1621,
+      "step": 56
+    },
+    {
+      "epoch": 0.005754088431253785,
+      "grad_norm": 0.19091089069843292,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 2.1491,
+      "step": 57
+    },
+    {
+      "epoch": 0.005855037351100343,
+      "grad_norm": 0.23644797503948212,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 2.1517,
+      "step": 58
+    },
+    {
+      "epoch": 0.005955986270946901,
+      "grad_norm": 0.20270752906799316,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 2.1575,
+      "step": 59
+    },
+    {
+      "epoch": 0.0060569351907934586,
+      "grad_norm": 0.3651578724384308,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 2.1877,
+      "step": 60
+    },
+    {
+      "epoch": 0.006157884110640016,
+      "grad_norm": 0.2750738859176636,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 2.1686,
+      "step": 61
+    },
+    {
+      "epoch": 0.0062588330304865734,
+      "grad_norm": 0.23219722509384155,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 2.1544,
+      "step": 62
+    },
+    {
+      "epoch": 0.006359781950333132,
+      "grad_norm": 0.26596349477767944,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 2.1497,
+      "step": 63
+    },
+    {
+      "epoch": 0.006359781950333132,
+      "eval_loss": 2.166980743408203,
+      "eval_runtime": 837.3556,
+      "eval_samples_per_second": 9.962,
+      "eval_steps_per_second": 1.246,
+      "step": 63
+    },
+    {
+      "epoch": 0.006460730870179689,
+      "grad_norm": 0.23465655744075775,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.1973,
+      "step": 64
+    },
+    {
+      "epoch": 0.006561679790026247,
+      "grad_norm": 0.226127028465271,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 2.1708,
+      "step": 65
+    },
+    {
+      "epoch": 0.006662628709872804,
+      "grad_norm": 0.23844251036643982,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 2.177,
+      "step": 66
+    },
+    {
+      "epoch": 0.006763577629719362,
+      "grad_norm": 0.31955665349960327,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 2.1675,
+      "step": 67
+    },
+    {
+      "epoch": 0.00686452654956592,
+      "grad_norm": 0.2359679788351059,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 2.1804,
+      "step": 68
+    },
+    {
+      "epoch": 0.006965475469412477,
+      "grad_norm": 0.2088335007429123,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 2.1771,
+      "step": 69
+    },
+    {
+      "epoch": 0.007066424389259035,
+      "grad_norm": 0.21319451928138733,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.1654,
+      "step": 70
+    },
+    {
+      "epoch": 0.007167373309105592,
+      "grad_norm": 0.22512580454349518,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 2.1664,
+      "step": 71
+    },
+    {
+      "epoch": 0.0072683222289521504,
+      "grad_norm": 0.23601970076560974,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 2.1307,
+      "step": 72
+    },
+    {
+      "epoch": 0.0072683222289521504,
+      "eval_loss": 2.1660921573638916,
+      "eval_runtime": 836.8568,
+      "eval_samples_per_second": 9.968,
+      "eval_steps_per_second": 1.246,
+      "step": 72
+    },
+    {
+      "epoch": 0.007369271148798708,
+      "grad_norm": 0.27343568205833435,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.1712,
+      "step": 73
+    },
+    {
+      "epoch": 0.007470220068645265,
+      "grad_norm": 0.2502886950969696,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 2.1687,
+      "step": 74
+    },
+    {
+      "epoch": 0.007571168988491823,
+      "grad_norm": 0.25393420457839966,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 2.1572,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.048051600392192e+16,
+  "total_flos": 1.0572077400588288e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null