Training in progress, step 68, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:face95f531991d1c4ebc8ae39b39d8db4111d815f0a30edbf3c7d0e93d644be1
+oid sha256:5fec14f6a01d61272bacee525bac8b5fbe0d1cc5cfe555534176434a00372067
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1707c9ccf7c6746c4a9c679bcbea2dd0711edc333e819eb762e01abed56271bb
+oid sha256:9c72d9f3ca2f0dee1e321d24a425433f913801087616a40c32e828d954463375
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c86702c0a3caad6c51746e54805a7289de03dff9cc5abc148a58966cf1f4d339
+oid sha256:3f4e77fd2a3bb3f08929494d77da2f57f8781f91a45852bcf8f71a5777dd088c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05604010713549894,
+  "epoch": 0.07472014284733192,
   "eval_steps": 50,
-  "global_step": 51,
+  "global_step": 68,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -380,6 +380,125 @@
       "learning_rate": 0.00013928754755265842,
       "loss": 0.0,
       "step": 51
+    },
+    {
+      "epoch": 0.057138932765606755,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013860360721173193,
+      "loss": 0.0,
+      "step": 52
+    },
+    {
+      "epoch": 0.05823775839571458,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001379002925959068,
+      "loss": 0.0,
+      "step": 53
+    },
+    {
+      "epoch": 0.059336584025822404,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001371778179416281,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.06043540965593022,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013643640332167438,
+      "loss": 0.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.06153423528603805,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013567627457812106,
+      "loss": 0.0,
+      "step": 56
+    },
+    {
+      "epoch": 0.06263306091614587,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013489766325354695,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.0637318865462537,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013410080652050412,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 0.06483071217636151,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001332859471092728,
+      "loss": 0.0,
+      "step": 59
+    },
+    {
+      "epoch": 0.06592953780646933,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013245333323392333,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.06702836343657716,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001316032185167079,
+      "loss": 0.0,
+      "step": 61
+    },
+    {
+      "epoch": 0.06812718906668498,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013073586191080457,
+      "loss": 0.0,
+      "step": 62
+    },
+    {
+      "epoch": 0.0692260146967928,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012985152762143778,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.07032484032690063,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012895048502539882,
+      "loss": 0.0,
+      "step": 64
+    },
+    {
+      "epoch": 0.07142366595700844,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012803300858899104,
+      "loss": 0.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.07252249158711627,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001270993777844248,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.07362131721722409,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001261498770046874,
+      "loss": 0.0,
+      "step": 67
+    },
+    {
+      "epoch": 0.07472014284733192,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012518479547691435,
+      "loss": 0.0,
+      "step": 68
     }
   ],
   "logging_steps": 1,
@@ -399,7 +518,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.0075800178917376e+17,
+  "total_flos": 4.0051762314765926e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null