Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13e89fc0960125356953ac64b9d8b1266f300e052b6da3e71399cecbc26debe2
+oid sha256:6518967041861d18056ba00f5dd72d4116cf6699b6a2a338ed39e971c1183de7
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:924a9ac8b4dc075b2f3666cf0ba142ef3a786d8b323c3cfd5fdb0ec07f33d25f
+oid sha256:26b8fdd0f0d2d9de369f85c0bdaf46b752de230cc656be0fb45c207a513ee078
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f59d59c59b5716db3463db15ea980daadd42e1fda67b9da22c2bc9685969e5af
+oid sha256:4ac59baafb802bccb6ac0dc9e09bd68c955796cdadad910d1ba3b8b6e23f7be6
 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": 0.002865021666726355,
+  "epoch": 0.004297532500089532,
   "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": 7.377,
       "eval_steps_per_second": 3.689,
       "step": 50
+    },
+    {
+      "epoch": 0.0029223221000608817,
+      "grad_norm": 2.3872838020324707,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.6123,
+      "step": 51
+    },
+    {
+      "epoch": 0.002979622533395409,
+      "grad_norm": 2.11433482170105,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 0.7429,
+      "step": 52
+    },
+    {
+      "epoch": 0.0030369229667299357,
+      "grad_norm": 1.9935492277145386,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 0.4261,
+      "step": 53
+    },
+    {
+      "epoch": 0.003094223400064463,
+      "grad_norm": 2.011484146118164,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.5963,
+      "step": 54
+    },
+    {
+      "epoch": 0.0031515238333989903,
+      "grad_norm": 2.5177338123321533,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.4909,
+      "step": 55
+    },
+    {
+      "epoch": 0.003208824266733517,
+      "grad_norm": 2.2302229404449463,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 0.5392,
+      "step": 56
+    },
+    {
+      "epoch": 0.0032661247000680444,
+      "grad_norm": 3.0052223205566406,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4753,
+      "step": 57
+    },
+    {
+      "epoch": 0.003323425133402571,
+      "grad_norm": 2.423661947250366,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.4055,
+      "step": 58
+    },
+    {
+      "epoch": 0.0033807255667370984,
+      "grad_norm": 2.8571395874023438,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.7339,
+      "step": 59
+    },
+    {
+      "epoch": 0.0034380260000716257,
+      "grad_norm": 3.235661268234253,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.7574,
+      "step": 60
+    },
+    {
+      "epoch": 0.0034953264334061525,
+      "grad_norm": 2.264759063720703,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 0.5166,
+      "step": 61
+    },
+    {
+      "epoch": 0.00355262686674068,
+      "grad_norm": 2.731968402862549,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.4679,
+      "step": 62
+    },
+    {
+      "epoch": 0.0036099273000752066,
+      "grad_norm": 2.704561471939087,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.7767,
+      "step": 63
+    },
+    {
+      "epoch": 0.003667227733409734,
+      "grad_norm": 1.7505345344543457,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 0.3995,
+      "step": 64
+    },
+    {
+      "epoch": 0.003724528166744261,
+      "grad_norm": 2.4672224521636963,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 0.6333,
+      "step": 65
+    },
+    {
+      "epoch": 0.003781828600078788,
+      "grad_norm": 3.6237540245056152,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4109,
+      "step": 66
+    },
+    {
+      "epoch": 0.0038391290334133152,
+      "grad_norm": 3.1202926635742188,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.8672,
+      "step": 67
+    },
+    {
+      "epoch": 0.003896429466747842,
+      "grad_norm": 3.3872885704040527,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 0.753,
+      "step": 68
+    },
+    {
+      "epoch": 0.003953729900082369,
+      "grad_norm": 3.216975212097168,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.6849,
+      "step": 69
+    },
+    {
+      "epoch": 0.004011030333416896,
+      "grad_norm": 2.8667757511138916,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 0.5677,
+      "step": 70
+    },
+    {
+      "epoch": 0.004068330766751424,
+      "grad_norm": 4.095630645751953,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.645,
+      "step": 71
+    },
+    {
+      "epoch": 0.004125631200085951,
+      "grad_norm": 3.189215898513794,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.6192,
+      "step": 72
+    },
+    {
+      "epoch": 0.0041829316334204775,
+      "grad_norm": 2.886237144470215,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 0.7971,
+      "step": 73
+    },
+    {
+      "epoch": 0.004240232066755005,
+      "grad_norm": 2.6635372638702393,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 0.6268,
+      "step": 74
+    },
+    {
+      "epoch": 0.004297532500089532,
+      "grad_norm": 2.3732454776763916,
+      "learning_rate": 0.0,
+      "loss": 0.5992,
+      "step": 75
+    },
+    {
+      "epoch": 0.004297532500089532,
+      "eval_loss": 0.14407220482826233,
+      "eval_runtime": 1991.2821,
+      "eval_samples_per_second": 7.381,
+      "eval_steps_per_second": 3.691,
+      "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": 6.57388096978944e+16,
+  "total_flos": 9.86082145468416e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null