Training in progress, step 15, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5f5cc161a91512901a16d0451aed799071f29b93aba05163a0f58ec74d8efec
+oid sha256:38a69eea60ae2c511a6a8a453007dc0ae54463f09a21478cf573a6cb04903739
 size 160284754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77820273899338f3cb44d8b61f14d2376760c84be6dcbd25e712a3423d224d4a
+oid sha256:e0c99adfd3842a16f78adc954f43d1319a31e4bf74797a8fd450f6ab3f8c288b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4abdd3b29509160214335978cbd2a63c87f2b7769a5608c5e772a6c51d699b65
+oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.019157088122605363,
+  "epoch": 0.028735632183908046,
   "eval_steps": 3,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -109,6 +109,57 @@
       "learning_rate": 8.535533905932738e-05,
       "loss": 0.0,
       "step": 10
+    },
+    {
+      "epoch": 0.0210727969348659,
+      "grad_norm": NaN,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.022988505747126436,
+      "grad_norm": NaN,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.022988505747126436,
+      "eval_loss": NaN,
+      "eval_runtime": 24.9093,
+      "eval_samples_per_second": 8.832,
+      "eval_steps_per_second": 4.416,
+      "step": 12
+    },
+    {
+      "epoch": 0.02490421455938697,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.02681992337164751,
+      "grad_norm": NaN,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.028735632183908046,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.028735632183908046,
+      "eval_loss": NaN,
+      "eval_runtime": 24.7137,
+      "eval_samples_per_second": 8.902,
+      "eval_steps_per_second": 4.451,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -128,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3286328452055040.0,
+  "total_flos": 4929492678082560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null