Training in progress, step 39, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2730b88a73a2362066f6e4f2925f06171b1117a01f02240a2d454b3f08ea22bd
+oid sha256:b65be0c3933fc5d4c39484739d7493938b5d55d925deaa4c6e7288754ed7cf11
 size 18763860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ebefa66f685e689769adaafd457264ae6777a954ae0a77f34d7684be2682c30
+oid sha256:a6a629bcc4d1cf05d0ed241ade838414811cac61f7bea2bcdb22033b753ca109
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa0fde01e60897f55f4ebaca5a490a1a483a2c53b2ae8e7543860a62c5b3298c
+oid sha256:28418a35cb7e15ebbce37743b08fd366c25ee320167b307a3e449a74781d02de
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0021938614070245756,
+  "epoch": 0.0032907921105368634,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,6 +213,105 @@
       "eval_samples_per_second": 61.599,
       "eval_steps_per_second": 30.8,
       "step": 26
+    },
+    {
+      "epoch": 0.002278240691910136,
+      "grad_norm": NaN,
+      "learning_rate": 3.083613409639764e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.0023626199767956967,
+      "grad_norm": NaN,
+      "learning_rate": 2.8910861626005776e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.0024469992616812574,
+      "grad_norm": NaN,
+      "learning_rate": 2.6961477393196126e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.0025313785465668178,
+      "grad_norm": NaN,
+      "learning_rate": 2.5e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.0026157578314523785,
+      "grad_norm": NaN,
+      "learning_rate": 2.303852260680388e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.002700137116337939,
+      "grad_norm": NaN,
+      "learning_rate": 2.1089138373994223e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.0027845164012234996,
+      "grad_norm": NaN,
+      "learning_rate": 1.9163865903602374e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.0028688956861090604,
+      "grad_norm": NaN,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.0029532749709946207,
+      "grad_norm": NaN,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.0030376542558801815,
+      "grad_norm": NaN,
+      "learning_rate": 1.3650237506511331e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.003122033540765742,
+      "grad_norm": NaN,
+      "learning_rate": 1.1937535882101281e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.0032064128256513026,
+      "grad_norm": NaN,
+      "learning_rate": 1.0305368692688174e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.0032907921105368634,
+      "grad_norm": NaN,
+      "learning_rate": 8.763798791745411e-06,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.0032907921105368634,
+      "eval_loss": NaN,
+      "eval_runtime": 81.0874,
+      "eval_samples_per_second": 61.539,
+      "eval_steps_per_second": 30.769,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1034985884614656.0,
+  "total_flos": 1552478826921984.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null