Training in progress, step 15, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:776b10cc848b8c6070e28d564600a854f60f08b863b1e49b2580df8034321cdc
+oid sha256:84ecdbbdb901a233682e7381a8fe31b09c1295968d9d781198fc4a9f288423bf
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ac108aa9eba00358310a4439f789a188dfe5197c585ee0c9b69af254e4ad32c
+oid sha256:4a39a41f912d3765e4194e7bf2d118cba79dcbe423e3417f95fa83853160b690
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01362281822051937,
+  "epoch": 0.020434227330779056,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 71.301,
       "eval_steps_per_second": 35.679,
       "step": 10
+    },
+    {
+      "epoch": 0.014985100042571307,
+      "grad_norm": NaN,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.016347381864623246,
+      "grad_norm": NaN,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.017709663686675182,
+      "grad_norm": NaN,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.01907194550872712,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.020434227330779056,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.020434227330779056,
+      "eval_loss": NaN,
+      "eval_runtime": 17.3499,
+      "eval_samples_per_second": 71.297,
+      "eval_steps_per_second": 35.678,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2174793428238336.0,
+  "total_flos": 3214497304018944.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null