Training in progress, step 10000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4112e8e9dc23cb1f7536f3eb76469acface21f23e45de82fb7032dccfefbcc9b
+oid sha256:ae0b06e97f7375d3c463012a0154e6c9d8ce59a64253b7d38b8e7eaf160efcff
 size 995654149

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc0011ff74c2a560ea18822f2b33d18d266eb182404ad11e97d8a0929b1762f9
+oid sha256:fef899874d9a26f54345ba20a4e90494ffcc0dd889e0572fa334421094aa7d69
 size 497813341

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6c38db4387a36e2ad70be6de6346c8072392db912ef970812aef3c708739e0f
+oid sha256:94d4f3dfba7c476528350a112afc2eb29ca025fdb99df6a6d058dd017e77721e
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8846bb95f8928ebc17412b6a7f15b0cd04a2aeba69a1f3a91482aec2592920f9
+oid sha256:f42c1b679744a42399dc6c4b3d13d32a0f7023f208a865b3c1cc1bb8f2e1860f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.7860686644175432,
+  "epoch": 1.9845207382417147,
   "eval_steps": 200,
-  "global_step": 9000,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -475,13 +475,65 @@
       "eval_samples_per_second": 947.096,
       "eval_steps_per_second": 3.7,
       "step": 9000
+    },
+    {
+      "epoch": 1.83,
+      "eval_loss": 0.11026974767446518,
+      "eval_runtime": 151.187,
+      "eval_samples_per_second": 948.071,
+      "eval_steps_per_second": 3.704,
+      "step": 9200
+    },
+    {
+      "epoch": 1.87,
+      "eval_loss": 0.11021895706653595,
+      "eval_runtime": 151.1765,
+      "eval_samples_per_second": 948.137,
+      "eval_steps_per_second": 3.704,
+      "step": 9400
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 2.867632466759278e-06,
+      "loss": 0.111,
+      "step": 9500
+    },
+    {
+      "epoch": 1.91,
+      "eval_loss": 0.11018586158752441,
+      "eval_runtime": 151.3213,
+      "eval_samples_per_second": 947.229,
+      "eval_steps_per_second": 3.701,
+      "step": 9600
+    },
+    {
+      "epoch": 1.94,
+      "eval_loss": 0.11020087450742722,
+      "eval_runtime": 151.3699,
+      "eval_samples_per_second": 946.925,
+      "eval_steps_per_second": 3.7,
+      "step": 9800
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 3.869815439571344e-07,
+      "loss": 0.1109,
+      "step": 10000
+    },
+    {
+      "epoch": 1.98,
+      "eval_loss": 0.11018609255552292,
+      "eval_runtime": 151.328,
+      "eval_samples_per_second": 947.187,
+      "eval_steps_per_second": 3.701,
+      "step": 10000
     }
   ],
   "logging_steps": 500,
   "max_steps": 10078,
   "num_train_epochs": 2,
   "save_steps": 1000,
-  "total_flos": 1.50504210432e+17,
+  "total_flos": 1.6722690048e+17,
   "trial_name": null,
   "trial_params": null
 }