Training in progress, step 75, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37d9c71ac3d800d944de48fc24526c6bf509ee615645ae325c0b875de9df0587
+oid sha256:cba8426497481beab224db256cc46c14599d46449f3e3955597a9dd6ee7d0be4
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71a870412de3416d48ae39ff1c8c8aa5faac6d41465f73ce8d3fe37a494a73c2
+oid sha256:b624a84d02a25ae8586362578702f2509fdc5e1ec0461f9d3f2d15632d98c9b2
 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": 0.00602364279798208,
+  "epoch": 0.00903546419697312,
   "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": 4.415,
       "eval_steps_per_second": 2.208,
       "step": 50
+    },
+    {
+      "epoch": 0.006144115653941721,
+      "grad_norm": NaN,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 0.006264588509901363,
+      "grad_norm": NaN,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 0.0,
+      "step": 52
+    },
+    {
+      "epoch": 0.006385061365861005,
+      "grad_norm": NaN,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 0.0,
+      "step": 53
+    },
+    {
+      "epoch": 0.006505534221820646,
+      "grad_norm": NaN,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.006626007077780288,
+      "grad_norm": NaN,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.006746479933739929,
+      "grad_norm": NaN,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 0.0,
+      "step": 56
+    },
+    {
+      "epoch": 0.0068669527896995704,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.006987425645659212,
+      "grad_norm": NaN,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 0.007107898501618854,
+      "grad_norm": NaN,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0,
+      "step": 59
+    },
+    {
+      "epoch": 0.007228371357578495,
+      "grad_norm": NaN,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.007348844213538137,
+      "grad_norm": NaN,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 0.0,
+      "step": 61
+    },
+    {
+      "epoch": 0.007469317069497779,
+      "grad_norm": NaN,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.0,
+      "step": 62
+    },
+    {
+      "epoch": 0.00758978992545742,
+      "grad_norm": NaN,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.007710262781417062,
+      "grad_norm": NaN,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 0.0,
+      "step": 64
+    },
+    {
+      "epoch": 0.007830735637376704,
+      "grad_norm": NaN,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 0.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.007951208493336345,
+      "grad_norm": NaN,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.008071681349295987,
+      "grad_norm": NaN,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0,
+      "step": 67
+    },
+    {
+      "epoch": 0.008192154205255629,
+      "grad_norm": NaN,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 0.0,
+      "step": 68
+    },
+    {
+      "epoch": 0.00831262706121527,
+      "grad_norm": NaN,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.008433099917174912,
+      "grad_norm": NaN,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.008553572773134554,
+      "grad_norm": NaN,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0,
+      "step": 71
+    },
+    {
+      "epoch": 0.008674045629094195,
+      "grad_norm": NaN,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.008794518485053837,
+      "grad_norm": NaN,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 0.0,
+      "step": 73
+    },
+    {
+      "epoch": 0.008914991341013478,
+      "grad_norm": NaN,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 0.0,
+      "step": 74
+    },
+    {
+      "epoch": 0.00903546419697312,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.00903546419697312,
+      "eval_loss": NaN,
+      "eval_runtime": 1582.0311,
+      "eval_samples_per_second": 4.418,
+      "eval_steps_per_second": 2.209,
+      "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": 6.946606583434445e+16,
+  "total_flos": 1.0494515435116954e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null