Training in progress, step 39, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d88836b9df77eeafa71ebd1be49569120733ab9444d4f7b9fce08e0fa809f9c
+oid sha256:c093c82a80b44aad4018105775c5ab08ab2f814a46e5423bf2edd975bfac53ef
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2971cbe0f61f3a458c833915f8f877a317595f1d6fd358e7da6a072617671769
+oid sha256:c391aa98e97daf78d824ae77b4e701c0f06685954079726e5bfd48e9b1e9ff6f
 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": 0.057617728531855955,
+  "epoch": 0.08642659279778393,
   "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": 36.716,
       "eval_steps_per_second": 18.358,
       "step": 26
+    },
+    {
+      "epoch": 0.059833795013850416,
+      "grad_norm": NaN,
+      "learning_rate": 3.083613409639764e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.06204986149584488,
+      "grad_norm": NaN,
+      "learning_rate": 2.8910861626005776e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.06426592797783934,
+      "grad_norm": NaN,
+      "learning_rate": 2.6961477393196126e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.0664819944598338,
+      "grad_norm": NaN,
+      "learning_rate": 2.5e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.06869806094182826,
+      "grad_norm": NaN,
+      "learning_rate": 2.303852260680388e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.07091412742382272,
+      "grad_norm": NaN,
+      "learning_rate": 2.1089138373994223e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.07313019390581718,
+      "grad_norm": NaN,
+      "learning_rate": 1.9163865903602374e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.07534626038781163,
+      "grad_norm": NaN,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.07756232686980609,
+      "grad_norm": NaN,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.07977839335180055,
+      "grad_norm": NaN,
+      "learning_rate": 1.3650237506511331e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.08199445983379501,
+      "grad_norm": NaN,
+      "learning_rate": 1.1937535882101281e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.08421052631578947,
+      "grad_norm": NaN,
+      "learning_rate": 1.0305368692688174e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.08642659279778393,
+      "grad_norm": NaN,
+      "learning_rate": 8.763798791745411e-06,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.08642659279778393,
+      "eval_loss": NaN,
+      "eval_runtime": 5.1777,
+      "eval_samples_per_second": 36.696,
+      "eval_steps_per_second": 18.348,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1686350944272384.0,
+  "total_flos": 2529526416408576.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null