Training in progress, step 15, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b9a75f32be63387c28153328a1b0691f9e49ee128269c6ff2216dcfebb420ad
+oid sha256:03a0a3336547a47bdfc6a8dd5e2e5239f4d20da2eca8e885ef3d03c4fe74b91a
 size 41119636

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": 0.007555723460521345,
+  "epoch": 0.011333585190782017,
   "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": 11.532,
       "eval_steps_per_second": 5.766,
       "step": 10
+    },
+    {
+      "epoch": 0.00831129580657348,
+      "grad_norm": NaN,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 85.5864,
+      "step": 11
+    },
+    {
+      "epoch": 0.009066868152625614,
+      "grad_norm": NaN,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.009822440498677748,
+      "grad_norm": NaN,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.0735,
+      "step": 13
+    },
+    {
+      "epoch": 0.010578012844729883,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 6.7404,
+      "step": 14
+    },
+    {
+      "epoch": 0.011333585190782017,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 171.2843,
+      "step": 15
+    },
+    {
+      "epoch": 0.011333585190782017,
+      "eval_loss": NaN,
+      "eval_runtime": 173.033,
+      "eval_samples_per_second": 12.888,
+      "eval_steps_per_second": 6.444,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2134181853200384e+16,
+  "total_flos": 1.8038397855596544e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null