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:d7e3c579d0a611f07e9b160213f82f1cee0644b7f60ca470afcd2b1025cb0b01
+oid sha256:c562be141155c5dc368fb95c64c517a45f2af2b74bd5ca085dd6423aa454a29f
 size 50358592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5c1e590028d8717e5020760af181c5d9ae41243449b16909ecd87b1c8954875
+oid sha256:a0625e37566d481f7226e998a45b2dc308a3557652797070481b6e63f4533f2d
 size 100824826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93b38d202478112ab0615144043cc4e3a2ebf4c7497c8d9a8be8c3c3f5256209
+oid sha256:b594640797ddb245a015f7373668279188936d40a1a9fb9eff1b4d0be0ff8018
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
+oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05684240443370755,
+  "epoch": 0.08526360665056132,
   "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": 19.401,
       "eval_steps_per_second": 9.714,
       "step": 50
+    },
+    {
+      "epoch": 0.057979252522381695,
+      "grad_norm": 31.600948333740234,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 20.401,
+      "step": 51
+    },
+    {
+      "epoch": 0.05911610061105585,
+      "grad_norm": 23.095199584960938,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 16.3515,
+      "step": 52
+    },
+    {
+      "epoch": 0.06025294869973,
+      "grad_norm": 19.465106964111328,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 11.0436,
+      "step": 53
+    },
+    {
+      "epoch": 0.06138979678840415,
+      "grad_norm": 24.496065139770508,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 15.2372,
+      "step": 54
+    },
+    {
+      "epoch": 0.0625266448770783,
+      "grad_norm": 19.609771728515625,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 12.5162,
+      "step": 55
+    },
+    {
+      "epoch": 0.06366349296575245,
+      "grad_norm": 15.845856666564941,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 15.2344,
+      "step": 56
+    },
+    {
+      "epoch": 0.0648003410544266,
+      "grad_norm": 19.62835693359375,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 16.5892,
+      "step": 57
+    },
+    {
+      "epoch": 0.06593718914310075,
+      "grad_norm": 14.156807899475098,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 13.7909,
+      "step": 58
+    },
+    {
+      "epoch": 0.06707403723177491,
+      "grad_norm": 16.480527877807617,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 11.8879,
+      "step": 59
+    },
+    {
+      "epoch": 0.06821088532044906,
+      "grad_norm": 11.38010311126709,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 13.3756,
+      "step": 60
+    },
+    {
+      "epoch": 0.0693477334091232,
+      "grad_norm": 10.232706069946289,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 15.2605,
+      "step": 61
+    },
+    {
+      "epoch": 0.07048458149779736,
+      "grad_norm": 11.701848983764648,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 19.6999,
+      "step": 62
+    },
+    {
+      "epoch": 0.07162142958647151,
+      "grad_norm": 11.662482261657715,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 18.2158,
+      "step": 63
+    },
+    {
+      "epoch": 0.07275827767514566,
+      "grad_norm": 11.12790584564209,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 17.7721,
+      "step": 64
+    },
+    {
+      "epoch": 0.0738951257638198,
+      "grad_norm": 8.93850040435791,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 16.637,
+      "step": 65
+    },
+    {
+      "epoch": 0.07503197385249397,
+      "grad_norm": 9.515388488769531,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 15.8094,
+      "step": 66
+    },
+    {
+      "epoch": 0.07616882194116811,
+      "grad_norm": 10.64154052734375,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 15.4739,
+      "step": 67
+    },
+    {
+      "epoch": 0.07730567002984226,
+      "grad_norm": 11.352025032043457,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 18.6491,
+      "step": 68
+    },
+    {
+      "epoch": 0.07844251811851641,
+      "grad_norm": 10.24422550201416,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 17.2373,
+      "step": 69
+    },
+    {
+      "epoch": 0.07957936620719057,
+      "grad_norm": 9.423773765563965,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 15.38,
+      "step": 70
+    },
+    {
+      "epoch": 0.08071621429586472,
+      "grad_norm": 9.517950057983398,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 12.7865,
+      "step": 71
+    },
+    {
+      "epoch": 0.08185306238453886,
+      "grad_norm": 9.021355628967285,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 17.7134,
+      "step": 72
+    },
+    {
+      "epoch": 0.08298991047321301,
+      "grad_norm": 9.259770393371582,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 17.2819,
+      "step": 73
+    },
+    {
+      "epoch": 0.08412675856188717,
+      "grad_norm": 11.53695011138916,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 15.3022,
+      "step": 74
+    },
+    {
+      "epoch": 0.08526360665056132,
+      "grad_norm": 8.795744895935059,
+      "learning_rate": 0.0,
+      "loss": 17.66,
+      "step": 75
+    },
+    {
+      "epoch": 0.08526360665056132,
+      "eval_loss": 1.7146401405334473,
+      "eval_runtime": 38.162,
+      "eval_samples_per_second": 19.417,
+      "eval_steps_per_second": 9.722,
+      "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": 3103296306806784.0,
+  "total_flos": 4666552800509952.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null