Training in progress, step 920000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcd026b7ddbbed9854cf4a848e8d10565ecae8551444b93cf80516c2a3075094
+oid sha256:37962abda8557285d298a4265c60f4356df61e7cc10bd44c3063d910102d66d3
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c1213c78566dba45a4dbe4cbf12671b2071e92687a82a7bd671a18dd4693188
+oid sha256:47f1c4302a150ebf621ef207481964f3a7603e3f271a1522dc7c4f830b5f8ea8
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23bff7c83371f4786566c176465b52f06fe8e3280f8cace7df94d70a8a5b2164
-size 14503
+oid sha256:14f7de72f01c7df685d896df6cd18118f7cd962784b86c13c1ec4716f711fe5e
+size 14439

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7220d15ed34c785cde537b4220883e048554a1408ecd7fe46faf0069997fc88e
+oid sha256:7ce3ab5e3a6adf4b5050188a365eda6e65d45b5f880ed022a630511122a962d8
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52361dad9976f354f626771e1b0dbf34f1017e0982c95cf304b85aa55d90473b
+oid sha256:dac1435372cea6f546c378b27a4b5fc759dcb93ae36e129dcb0cfa5374977cc3
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:242dcb89ecc86bf6b74de9a6782f0aca020ba83ca594d7f0c60637dcb70148d3
+oid sha256:7314965ea42ee1f19abe451e572b5d6938b7b63a561ae48af7903b9728329e39
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68bd93c5df85b9ef6b8dfb004005413abc49b194d979c692716ee25211f1498f
+oid sha256:7df508c344c1f04d3b388cef9605593fbfd129cd18e2830701d3110873541479
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 13.89588773344328,
-  "global_step": 910000,
+  "epoch": 14.04858979644815,
+  "global_step": 920000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6740,11 +6740,85 @@
       "eval_samples_per_second": 1377.03,
       "eval_steps_per_second": 22.032,
       "step": 910000
+    },
+    {
+      "epoch": 13.91,
+      "learning_rate": 1.3009978131197669e-05,
+      "loss": 0.2314,
+      "step": 911000
+    },
+    {
+      "epoch": 13.93,
+      "learning_rate": 1.2943193561946762e-05,
+      "loss": 0.2304,
+      "step": 912000
+    },
+    {
+      "epoch": 13.94,
+      "learning_rate": 1.2877142315187628e-05,
+      "loss": 0.2299,
+      "step": 913000
+    },
+    {
+      "epoch": 13.96,
+      "learning_rate": 1.28118251132461e-05,
+      "loss": 0.23,
+      "step": 914000
+    },
+    {
+      "epoch": 13.97,
+      "learning_rate": 1.274724267042063e-05,
+      "loss": 0.2299,
+      "step": 915000
+    },
+    {
+      "epoch": 13.97,
+      "eval_runtime": 0.795,
+      "eval_samples_per_second": 1257.794,
+      "eval_steps_per_second": 20.125,
+      "step": 915000
+    },
+    {
+      "epoch": 13.99,
+      "learning_rate": 1.2683395692974472e-05,
+      "loss": 0.23,
+      "step": 916000
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 1.2620284879127947e-05,
+      "loss": 0.23,
+      "step": 917000
+    },
+    {
+      "epoch": 14.02,
+      "learning_rate": 1.2557910919050803e-05,
+      "loss": 0.2295,
+      "step": 918000
+    },
+    {
+      "epoch": 14.03,
+      "learning_rate": 1.2496274494854666e-05,
+      "loss": 0.2296,
+      "step": 919000
+    },
+    {
+      "epoch": 14.05,
+      "learning_rate": 1.24353762805856e-05,
+      "loss": 0.2297,
+      "step": 920000
+    },
+    {
+      "epoch": 14.05,
+      "eval_runtime": 0.7692,
+      "eval_samples_per_second": 1300.053,
+      "eval_steps_per_second": 20.801,
+      "step": 920000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 6.379115211875656e+22,
+  "total_flos": 6.449214815837855e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c1213c78566dba45a4dbe4cbf12671b2071e92687a82a7bd671a18dd4693188
+oid sha256:47f1c4302a150ebf621ef207481964f3a7603e3f271a1522dc7c4f830b5f8ea8
 size 449471589