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:a76fd8bc00b2bd9c5986ae4896c81016bb43e1ab798b5781ecffbf75551a431b
+oid sha256:884007447842c719ab4ed3cb6077b40fbe807c943a3a7ee321ff46388137e49a
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab453e560b26a2266fd7222425041f5d9f87fc9ded4eb43f8e9a52e73fbad972
+oid sha256:aeed0f14485a64cb549eeb246009031d78634165148756a7250374e77f53be95
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc0dae5243831e89c8a2d4c71488ab8f4f047997bc5f1ec828f6d436ca1fcbcd
+oid sha256:154f6982a2fa54c56e7d0e5d99d9685584de68b37acc55950f335553af10e3e5
 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": 0.013470734828584898,
+  "epoch": 0.02020610224287735,
   "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": 2.133,
       "eval_steps_per_second": 1.067,
       "step": 50
+    },
+    {
+      "epoch": 0.013740149525156597,
+      "grad_norm": 0.23592382669448853,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8445,
+      "step": 51
+    },
+    {
+      "epoch": 0.014009564221728296,
+      "grad_norm": 0.22146673500537872,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 0.8461,
+      "step": 52
+    },
+    {
+      "epoch": 0.014278978918299993,
+      "grad_norm": 0.20355774462223053,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 0.6487,
+      "step": 53
+    },
+    {
+      "epoch": 0.014548393614871691,
+      "grad_norm": 0.20058169960975647,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.7887,
+      "step": 54
+    },
+    {
+      "epoch": 0.014817808311443388,
+      "grad_norm": 0.23074696958065033,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.7751,
+      "step": 55
+    },
+    {
+      "epoch": 0.015087223008015087,
+      "grad_norm": 0.21907417476177216,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 0.9226,
+      "step": 56
+    },
+    {
+      "epoch": 0.015356637704586786,
+      "grad_norm": 0.21107719838619232,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8582,
+      "step": 57
+    },
+    {
+      "epoch": 0.015626052401158483,
+      "grad_norm": 0.24479110538959503,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.8669,
+      "step": 58
+    },
+    {
+      "epoch": 0.01589546709773018,
+      "grad_norm": 0.21114766597747803,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.7536,
+      "step": 59
+    },
+    {
+      "epoch": 0.01616488179430188,
+      "grad_norm": 0.2191285490989685,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.7675,
+      "step": 60
+    },
+    {
+      "epoch": 0.016434296490873575,
+      "grad_norm": 0.21771937608718872,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 0.742,
+      "step": 61
+    },
+    {
+      "epoch": 0.016703711187445274,
+      "grad_norm": 0.22942110896110535,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.812,
+      "step": 62
+    },
+    {
+      "epoch": 0.016973125884016973,
+      "grad_norm": 0.21573947370052338,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.7358,
+      "step": 63
+    },
+    {
+      "epoch": 0.01724254058058867,
+      "grad_norm": 0.2270616739988327,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 0.8433,
+      "step": 64
+    },
+    {
+      "epoch": 0.01751195527716037,
+      "grad_norm": 0.23190170526504517,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 0.9071,
+      "step": 65
+    },
+    {
+      "epoch": 0.017781369973732065,
+      "grad_norm": 0.22806090116500854,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.9525,
+      "step": 66
+    },
+    {
+      "epoch": 0.018050784670303764,
+      "grad_norm": 0.2513931691646576,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.8363,
+      "step": 67
+    },
+    {
+      "epoch": 0.018320199366875463,
+      "grad_norm": 0.18584202229976654,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 0.7216,
+      "step": 68
+    },
+    {
+      "epoch": 0.01858961406344716,
+      "grad_norm": 0.4081839323043823,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.9696,
+      "step": 69
+    },
+    {
+      "epoch": 0.01885902876001886,
+      "grad_norm": 0.22010080516338348,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 0.7513,
+      "step": 70
+    },
+    {
+      "epoch": 0.019128443456590555,
+      "grad_norm": 0.23679286241531372,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.9157,
+      "step": 71
+    },
+    {
+      "epoch": 0.019397858153162254,
+      "grad_norm": 0.21368712186813354,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.7911,
+      "step": 72
+    },
+    {
+      "epoch": 0.019667272849733953,
+      "grad_norm": 0.2136588990688324,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 0.7197,
+      "step": 73
+    },
+    {
+      "epoch": 0.01993668754630565,
+      "grad_norm": 0.22520920634269714,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 0.8448,
+      "step": 74
+    },
+    {
+      "epoch": 0.02020610224287735,
+      "grad_norm": 0.22236621379852295,
+      "learning_rate": 0.0,
+      "loss": 0.9822,
+      "step": 75
+    },
+    {
+      "epoch": 0.02020610224287735,
+      "eval_loss": 0.7994694709777832,
+      "eval_runtime": 1465.6119,
+      "eval_samples_per_second": 2.133,
+      "eval_steps_per_second": 1.066,
+      "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": 1.327978237573202e+17,
+  "total_flos": 2.008659820239913e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null