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:f426b0494820fe7c4e3846c8d736186b42e9fb6aa8767ceade086ac571743760
+oid sha256:62baa7baacfae6d4fcf7992addb8c75824ffde9e2f97700d0f6f13ce21c1d284
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb1011b2a4c32f863edb40e28e651f582f2c16f5365504b2a43e42389839eb50
+oid sha256:c7633eda5e6b319899d9b843190cc30cd572ef352899c1531d90ff42a7734990
 size 212298

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3682b8eea806d5bf68e4d42abb8d07090a7034f42dbb560fe9267880cf5e1882
+oid sha256:570a26a08435d5455e015431d16f49d5eaf2f3d7a751da2f813688e059e70842
 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": 0.05911038865080538,
+  "epoch": 0.08866558297620807,
   "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": 64.448,
       "eval_steps_per_second": 32.269,
       "step": 50
+    },
+    {
+      "epoch": 0.06029259642382149,
+      "grad_norm": 0.35565540194511414,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3027,
+      "step": 51
+    },
+    {
+      "epoch": 0.061474804196837596,
+      "grad_norm": 0.3417057991027832,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 10.3046,
+      "step": 52
+    },
+    {
+      "epoch": 0.0626570119698537,
+      "grad_norm": 0.33912089467048645,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 10.3053,
+      "step": 53
+    },
+    {
+      "epoch": 0.06383921974286981,
+      "grad_norm": 0.3465961813926697,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 10.3034,
+      "step": 54
+    },
+    {
+      "epoch": 0.06502142751588591,
+      "grad_norm": 0.3403364419937134,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 10.302,
+      "step": 55
+    },
+    {
+      "epoch": 0.06620363528890202,
+      "grad_norm": 0.33106306195259094,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 10.3076,
+      "step": 56
+    },
+    {
+      "epoch": 0.06738584306191814,
+      "grad_norm": 0.3448447287082672,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.2994,
+      "step": 57
+    },
+    {
+      "epoch": 0.06856805083493424,
+      "grad_norm": 0.33323007822036743,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 10.3026,
+      "step": 58
+    },
+    {
+      "epoch": 0.06975025860795035,
+      "grad_norm": 0.32261210680007935,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 10.3058,
+      "step": 59
+    },
+    {
+      "epoch": 0.07093246638096645,
+      "grad_norm": 0.33051347732543945,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 10.2994,
+      "step": 60
+    },
+    {
+      "epoch": 0.07211467415398257,
+      "grad_norm": 0.3287923038005829,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 10.3033,
+      "step": 61
+    },
+    {
+      "epoch": 0.07329688192699867,
+      "grad_norm": 0.33598190546035767,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 10.3011,
+      "step": 62
+    },
+    {
+      "epoch": 0.07447908970001478,
+      "grad_norm": 0.318424791097641,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3029,
+      "step": 63
+    },
+    {
+      "epoch": 0.07566129747303088,
+      "grad_norm": 0.32850056886672974,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 10.3013,
+      "step": 64
+    },
+    {
+      "epoch": 0.076843505246047,
+      "grad_norm": 0.31445056200027466,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 10.3032,
+      "step": 65
+    },
+    {
+      "epoch": 0.0780257130190631,
+      "grad_norm": 0.3170875608921051,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3019,
+      "step": 66
+    },
+    {
+      "epoch": 0.07920792079207921,
+      "grad_norm": 0.3237294852733612,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.2993,
+      "step": 67
+    },
+    {
+      "epoch": 0.08039012856509531,
+      "grad_norm": 0.3161391019821167,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 10.3023,
+      "step": 68
+    },
+    {
+      "epoch": 0.08157233633811142,
+      "grad_norm": 0.3209376931190491,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.3021,
+      "step": 69
+    },
+    {
+      "epoch": 0.08275454411112754,
+      "grad_norm": 0.31894317269325256,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 10.3016,
+      "step": 70
+    },
+    {
+      "epoch": 0.08393675188414364,
+      "grad_norm": 0.372801810503006,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 10.3076,
+      "step": 71
+    },
+    {
+      "epoch": 0.08511895965715975,
+      "grad_norm": 0.36965852975845337,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 10.2996,
+      "step": 72
+    },
+    {
+      "epoch": 0.08630116743017585,
+      "grad_norm": 0.3338715136051178,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 10.2972,
+      "step": 73
+    },
+    {
+      "epoch": 0.08748337520319197,
+      "grad_norm": 0.34212973713874817,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 10.2959,
+      "step": 74
+    },
+    {
+      "epoch": 0.08866558297620807,
+      "grad_norm": 0.32610419392585754,
+      "learning_rate": 0.0,
+      "loss": 10.2986,
+      "step": 75
+    },
+    {
+      "epoch": 0.08866558297620807,
+      "eval_loss": 10.29992389678955,
+      "eval_runtime": 11.0509,
+      "eval_samples_per_second": 64.52,
+      "eval_steps_per_second": 32.305,
+      "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": 10692014899200.0,
+  "total_flos": 16038022348800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null