Training in progress, step 19000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:845c13e137da03553b05598129da4a8674d9e0b1a7f13d45b2029c4e560c0674
+oid sha256:18542fb0f0ca8c5209e2b93103f1880c50a53c82c7835aa17cc9be5a52878bde
 size 2847145157

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98e64d9e3ec5e4e45f03e6e983897c802b870e1747cae8af2c34bdeb835bbcbe
+oid sha256:a55bd617d7f0551be9aa43e265f8d49f618cdf19eed0897711e26055a6662e99
 size 1524261149

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8906e4503e5e52d1eb508d6d922f99d3cb6d5caafa2b7778f4a4873479d6785
+oid sha256:5ec49eaf93dbcc4a7020eab69f82e4825b6de00732c3380cc93bef441b24d358
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2364d0eed038a9d0d4a87a052e7a1739b5247b2fbf2962d4f2b4b62f09c6e9d9
+oid sha256:3ebdd7eec22dd0eaa942c09b9d66a5b538c98524805051b53c9cae7c97f8241a
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.698246140008994,
-  "global_step": 18000,
+  "epoch": 2.848148703342827,
+  "global_step": 19000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -422,11 +422,39 @@
       "learning_rate": 3.6508769299955035e-05,
       "loss": 2.1897,
       "step": 18000
+    },
+    {
+      "epoch": 2.73,
+      "eval_loss": 2.646106719970703,
+      "eval_runtime": 209.741,
+      "eval_samples_per_second": 16.84,
+      "eval_steps_per_second": 5.616,
+      "step": 18200
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 3.613401289162045e-05,
+      "loss": 2.181,
+      "step": 18500
+    },
+    {
+      "epoch": 2.83,
+      "eval_loss": 2.6370952129364014,
+      "eval_runtime": 210.1426,
+      "eval_samples_per_second": 16.808,
+      "eval_steps_per_second": 5.606,
+      "step": 18900
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 3.5759256483285864e-05,
+      "loss": 2.2077,
+      "step": 19000
     }
   ],
   "max_steps": 66710,
   "num_train_epochs": 10,
-  "total_flos": 2.4486318409728e+16,
+  "total_flos": 2.5846719817728e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98e64d9e3ec5e4e45f03e6e983897c802b870e1747cae8af2c34bdeb835bbcbe
+oid sha256:a55bd617d7f0551be9aa43e265f8d49f618cdf19eed0897711e26055a6662e99
 size 1524261149

runs/Mar11_11-28-52_b25631785753/events.out.tfevents.1678534153.b25631785753.957.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54e79f5a2b923c081ea13c8772ce423bd840d2defafdbe1fa34fff717394491c
-size 7092
+oid sha256:f2c6ce822c57a865d868ca2b1ccf414559c129b6fe06a79313875782f814b876
+size 7964