Training in progress, step 75, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d93ec8d2a1e913cd4e8ec03aac54923626b35716b53a6e34f08ddda55428e14b
+oid sha256:b14305ff8670630b73d43b1ff95b6be8d195d8f3fd224a463e8fb614aeb4624c
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58b14309b3685facd462070072dcbf2c924f69066f5f72ca840eddd0eb325e00
+oid sha256:a051f3a96420776a89027df7ec4df152943df681b8d761659909a35d612d3152
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef593f391c66ba3ea6e8dea3b2aa8e19ae1f574e3c6a18c96ee14293016120aa
+oid sha256:0f6003820aa1d9b0e6aa1d70309948568223b16abb8759408bc4ed8976518161
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.18552875695732837,
+  "epoch": 0.2782931354359926,
   "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": 9.512,
       "eval_steps_per_second": 4.756,
       "step": 50
+    },
+    {
+      "epoch": 0.18923933209647495,
+      "grad_norm": NaN,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 0.19294990723562153,
+      "grad_norm": NaN,
+      "learning_rate": 1.1567509791329401e-05,
+      "loss": 0.0,
+      "step": 52
+    },
+    {
+      "epoch": 0.19666048237476808,
+      "grad_norm": NaN,
+      "learning_rate": 1.0660589091223855e-05,
+      "loss": 0.0,
+      "step": 53
+    },
+    {
+      "epoch": 0.20037105751391465,
+      "grad_norm": NaN,
+      "learning_rate": 9.780964274781984e-06,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.20408163265306123,
+      "grad_norm": NaN,
+      "learning_rate": 8.930309757836517e-06,
+      "loss": 0.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.2077922077922078,
+      "grad_norm": NaN,
+      "learning_rate": 8.110244809608495e-06,
+      "loss": 0.0,
+      "step": 56
+    },
+    {
+      "epoch": 0.21150278293135436,
+      "grad_norm": NaN,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.21521335807050093,
+      "grad_norm": NaN,
+      "learning_rate": 6.568066579746901e-06,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 0.2189239332096475,
+      "grad_norm": NaN,
+      "learning_rate": 5.848888922025553e-06,
+      "loss": 0.0,
+      "step": 59
+    },
+    {
+      "epoch": 0.22263450834879406,
+      "grad_norm": NaN,
+      "learning_rate": 5.166166492719124e-06,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.22634508348794063,
+      "grad_norm": NaN,
+      "learning_rate": 4.521198892775203e-06,
+      "loss": 0.0,
+      "step": 61
+    },
+    {
+      "epoch": 0.2300556586270872,
+      "grad_norm": NaN,
+      "learning_rate": 3.9152138546778625e-06,
+      "loss": 0.0,
+      "step": 62
+    },
+    {
+      "epoch": 0.23376623376623376,
+      "grad_norm": NaN,
+      "learning_rate": 3.3493649053890326e-06,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.23747680890538034,
+      "grad_norm": NaN,
+      "learning_rate": 2.8247291705444575e-06,
+      "loss": 0.0,
+      "step": 64
+    },
+    {
+      "epoch": 0.24118738404452691,
+      "grad_norm": NaN,
+      "learning_rate": 2.3423053240837515e-06,
+      "loss": 0.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.24489795918367346,
+      "grad_norm": NaN,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.24860853432282004,
+      "grad_norm": NaN,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 0.0,
+      "step": 67
+    },
+    {
+      "epoch": 0.2523191094619666,
+      "grad_norm": NaN,
+      "learning_rate": 1.1570762312943295e-06,
+      "loss": 0.0,
+      "step": 68
+    },
+    {
+      "epoch": 0.2560296846011132,
+      "grad_norm": NaN,
+      "learning_rate": 8.51854342773295e-07,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.2597402597402597,
+      "grad_norm": NaN,
+      "learning_rate": 5.925998220016659e-07,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.2634508348794063,
+      "grad_norm": NaN,
+      "learning_rate": 3.7980617469479953e-07,
+      "loss": 0.0,
+      "step": 71
+    },
+    {
+      "epoch": 0.26716141001855287,
+      "grad_norm": NaN,
+      "learning_rate": 2.1387846565474045e-07,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.27087198515769945,
+      "grad_norm": NaN,
+      "learning_rate": 9.513254770636137e-08,
+      "loss": 0.0,
+      "step": 73
+    },
+    {
+      "epoch": 0.274582560296846,
+      "grad_norm": NaN,
+      "learning_rate": 2.3794460453555047e-08,
+      "loss": 0.0,
+      "step": 74
+    },
+    {
+      "epoch": 0.2782931354359926,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.2782931354359926,
+      "eval_loss": NaN,
+      "eval_runtime": 11.9772,
+      "eval_samples_per_second": 9.518,
+      "eval_steps_per_second": 4.759,
+      "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": 3.53780952465408e+16,
+  "total_flos": 5.30671428698112e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null