Training in progress, step 75, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:316aba2930a94308e4d1089240557ace753e60365be956e20a6ddbf0ef1dfb77
+oid sha256:f055d269d8e7c9b578ee761d7d16f4fdc17e3d6a9e2792fdc0f724dd2c9195e3
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87f0e2407d179965d787b2279a15aa2d551e9fb96b47dcd427c868bf47913b56
+oid sha256:be7eebdff0930537621e4dd5c14cea8a32371d047edcec30d48c3e2257acf8fd
 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": 0.07944389275074479,
+  "epoch": 0.11916583912611718,
   "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": 4.203,
       "eval_steps_per_second": 2.102,
       "step": 50
+    },
+    {
+      "epoch": 0.08103277060575968,
+      "grad_norm": NaN,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 0.08262164846077458,
+      "grad_norm": NaN,
+      "learning_rate": 4.6270039165317605e-05,
+      "loss": 0.0,
+      "step": 52
+    },
+    {
+      "epoch": 0.08421052631578947,
+      "grad_norm": NaN,
+      "learning_rate": 4.264235636489542e-05,
+      "loss": 0.0,
+      "step": 53
+    },
+    {
+      "epoch": 0.08579940417080437,
+      "grad_norm": NaN,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.08738828202581926,
+      "grad_norm": NaN,
+      "learning_rate": 3.5721239031346066e-05,
+      "loss": 0.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.08897715988083416,
+      "grad_norm": NaN,
+      "learning_rate": 3.244097923843398e-05,
+      "loss": 0.0,
+      "step": 56
+    },
+    {
+      "epoch": 0.09056603773584905,
+      "grad_norm": NaN,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.09215491559086396,
+      "grad_norm": NaN,
+      "learning_rate": 2.6272266318987603e-05,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 0.09374379344587885,
+      "grad_norm": NaN,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 0.0,
+      "step": 59
+    },
+    {
+      "epoch": 0.09533267130089375,
+      "grad_norm": NaN,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.09692154915590864,
+      "grad_norm": NaN,
+      "learning_rate": 1.808479557110081e-05,
+      "loss": 0.0,
+      "step": 61
+    },
+    {
+      "epoch": 0.09851042701092354,
+      "grad_norm": NaN,
+      "learning_rate": 1.566085541871145e-05,
+      "loss": 0.0,
+      "step": 62
+    },
+    {
+      "epoch": 0.10009930486593843,
+      "grad_norm": NaN,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.10168818272095333,
+      "grad_norm": NaN,
+      "learning_rate": 1.129891668217783e-05,
+      "loss": 0.0,
+      "step": 64
+    },
+    {
+      "epoch": 0.10327706057596822,
+      "grad_norm": NaN,
+      "learning_rate": 9.369221296335006e-06,
+      "loss": 0.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.10486593843098312,
+      "grad_norm": NaN,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.10645481628599801,
+      "grad_norm": NaN,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 0.0,
+      "step": 67
+    },
+    {
+      "epoch": 0.1080436941410129,
+      "grad_norm": NaN,
+      "learning_rate": 4.628304925177318e-06,
+      "loss": 0.0,
+      "step": 68
+    },
+    {
+      "epoch": 0.1096325719960278,
+      "grad_norm": NaN,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.1112214498510427,
+      "grad_norm": NaN,
+      "learning_rate": 2.3703992880066638e-06,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.1128103277060576,
+      "grad_norm": NaN,
+      "learning_rate": 1.5192246987791981e-06,
+      "loss": 0.0,
+      "step": 71
+    },
+    {
+      "epoch": 0.1143992055610725,
+      "grad_norm": NaN,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.11598808341608739,
+      "grad_norm": NaN,
+      "learning_rate": 3.805301908254455e-07,
+      "loss": 0.0,
+      "step": 73
+    },
+    {
+      "epoch": 0.11757696127110229,
+      "grad_norm": NaN,
+      "learning_rate": 9.517784181422019e-08,
+      "loss": 0.0,
+      "step": 74
+    },
+    {
+      "epoch": 0.11916583912611718,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.11916583912611718,
+      "eval_loss": NaN,
+      "eval_runtime": 126.0102,
+      "eval_samples_per_second": 4.206,
+      "eval_steps_per_second": 2.103,
+      "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": 6.926661208296653e+16,
+  "total_flos": 1.038999181244498e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null