Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0f4a0f657c152b12943f4d6b56a5884dfdb2f54bc45b81342cc7a303a4f7a5a
+oid sha256:3288eafa5bb4cdf6a2491d9643e804cadecb9db86fa73542d4a00d0160bb07e5
 size 6614970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:652365ff63294ffff01ffedb52e831cc2560ab06b5699bca21d63e81dd0efbe7
+oid sha256:2edc13c60910e9acd555e90579b2ee1807926bb393c7c79b1e24163c3f5bfc9f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.021949417847972143,
+  "epoch": 0.028140279292271975,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 179.838,
       "eval_steps_per_second": 89.949,
       "step": 39
+    },
+    {
+      "epoch": 0.02251222343381758,
+      "grad_norm": Infinity,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 100.5625,
+      "step": 40
+    },
+    {
+      "epoch": 0.02307502901966302,
+      "grad_norm": Infinity,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 275.5,
+      "step": 41
+    },
+    {
+      "epoch": 0.02363783460550846,
+      "grad_norm": Infinity,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 131.8438,
+      "step": 42
+    },
+    {
+      "epoch": 0.0242006401913539,
+      "grad_norm": Infinity,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 103.7188,
+      "step": 43
+    },
+    {
+      "epoch": 0.024763445777199338,
+      "grad_norm": Infinity,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 104.8125,
+      "step": 44
+    },
+    {
+      "epoch": 0.02532625136304478,
+      "grad_norm": Infinity,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 104.0938,
+      "step": 45
+    },
+    {
+      "epoch": 0.025889056948890217,
+      "grad_norm": Infinity,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 103.3125,
+      "step": 46
+    },
+    {
+      "epoch": 0.026451862534735658,
+      "grad_norm": Infinity,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 105.625,
+      "step": 47
+    },
+    {
+      "epoch": 0.027014668120581096,
+      "grad_norm": Infinity,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 100.4688,
+      "step": 48
+    },
+    {
+      "epoch": 0.027577473706426537,
+      "grad_norm": Infinity,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 101.25,
+      "step": 49
+    },
+    {
+      "epoch": 0.028140279292271975,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0,
+      "loss": 100.2812,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1171086586675200.0,
+  "total_flos": 1501393059840000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null