Training in progress, step 75, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44916a55f1c4ff512526a1b1ced6f059a71e4900b2c56dd30794d85c9fda6ed0
+oid sha256:734a046834e3f586b427a55d6fb213892f1094bf724644051d641004e60a40ea
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f165c4110688c7d11211f732ca4faee5be8a6769d48fc8c8358e14159b19405
+oid sha256:54ed80f52c4ca807d964c39d0d637b6bc33c78f3ebd681a59a63af391895a491
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d914dc409ae93ac75985631a9974025ebaa397f621307eef226e7d6e1076a1f6
+oid sha256:babd43118aa66a4f5266d730539cf7f09611158b169d9e63dbcb83f6bbaa8626
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04253056884635832,
+  "epoch": 0.06379585326953748,
   "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": 3.987,
       "eval_steps_per_second": 1.994,
       "step": 50
+    },
+    {
+      "epoch": 0.043381180223285486,
+      "grad_norm": NaN,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 0.04423179160021265,
+      "grad_norm": NaN,
+      "learning_rate": 4.6270039165317605e-05,
+      "loss": 0.0,
+      "step": 52
+    },
+    {
+      "epoch": 0.04508240297713982,
+      "grad_norm": NaN,
+      "learning_rate": 4.264235636489542e-05,
+      "loss": 0.0,
+      "step": 53
+    },
+    {
+      "epoch": 0.045933014354066985,
+      "grad_norm": NaN,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.04678362573099415,
+      "grad_norm": NaN,
+      "learning_rate": 3.5721239031346066e-05,
+      "loss": 0.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.04763423710792132,
+      "grad_norm": NaN,
+      "learning_rate": 3.244097923843398e-05,
+      "loss": 0.0,
+      "step": 56
+    },
+    {
+      "epoch": 0.048484848484848485,
+      "grad_norm": NaN,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.04933545986177565,
+      "grad_norm": NaN,
+      "learning_rate": 2.6272266318987603e-05,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 0.05018607123870282,
+      "grad_norm": NaN,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 0.0,
+      "step": 59
+    },
+    {
+      "epoch": 0.051036682615629984,
+      "grad_norm": NaN,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.05188729399255715,
+      "grad_norm": NaN,
+      "learning_rate": 1.808479557110081e-05,
+      "loss": 0.0,
+      "step": 61
+    },
+    {
+      "epoch": 0.05273790536948432,
+      "grad_norm": NaN,
+      "learning_rate": 1.566085541871145e-05,
+      "loss": 0.0,
+      "step": 62
+    },
+    {
+      "epoch": 0.053588516746411484,
+      "grad_norm": NaN,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.05443912812333865,
+      "grad_norm": NaN,
+      "learning_rate": 1.129891668217783e-05,
+      "loss": 0.0,
+      "step": 64
+    },
+    {
+      "epoch": 0.05528973950026582,
+      "grad_norm": NaN,
+      "learning_rate": 9.369221296335006e-06,
+      "loss": 0.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.056140350877192984,
+      "grad_norm": NaN,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.05699096225412015,
+      "grad_norm": NaN,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 0.0,
+      "step": 67
+    },
+    {
+      "epoch": 0.05784157363104731,
+      "grad_norm": NaN,
+      "learning_rate": 4.628304925177318e-06,
+      "loss": 0.0,
+      "step": 68
+    },
+    {
+      "epoch": 0.05869218500797448,
+      "grad_norm": NaN,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.05954279638490165,
+      "grad_norm": NaN,
+      "learning_rate": 2.3703992880066638e-06,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.06039340776182881,
+      "grad_norm": NaN,
+      "learning_rate": 1.5192246987791981e-06,
+      "loss": 0.0,
+      "step": 71
+    },
+    {
+      "epoch": 0.06124401913875598,
+      "grad_norm": NaN,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.06209463051568315,
+      "grad_norm": NaN,
+      "learning_rate": 3.805301908254455e-07,
+      "loss": 0.0,
+      "step": 73
+    },
+    {
+      "epoch": 0.06294524189261032,
+      "grad_norm": NaN,
+      "learning_rate": 9.517784181422019e-08,
+      "loss": 0.0,
+      "step": 74
+    },
+    {
+      "epoch": 0.06379585326953748,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.06379585326953748,
+      "eval_loss": NaN,
+      "eval_runtime": 248.2077,
+      "eval_samples_per_second": 3.989,
+      "eval_steps_per_second": 1.994,
+      "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": 7.611381181946266e+16,
+  "total_flos": 1.1513752134352896e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null