Training in progress, step 170000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4f4809e2011942e3338585ff5c56a9ec0e0deb79d986f6cdaa31e9d5dd3ce1d
+oid sha256:57dee83a189d98be49bec5f74817fff8657797a917a6717ceea36d9c18ae6862
 size 995605445

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2316b204782da72135ffb03278561a92f4394e61a9305152e8eeab4641dd7f78
+oid sha256:f42dbd9b35415ba34033be719191148beaa9e62794b2440aac238f33a11f2b47
 size 510398013

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1b939d2e70c1f81096e974bf777610988aba5447e2428d8d8376b2a12518acf
+oid sha256:0560bfc1efbba55157929955ba0396617b61df4e817669f59453ff7efb93f22b
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f70738e8d0afd98e53a66e39804f7d18bae2eb18420522bd49d0963e24799863
+oid sha256:178dabfccbd230719cf675b65dfa8a438486e62518bee396fdb95743a820c1ad
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.7882375224926603,
-  "global_step": 160000,
+  "epoch": 4.025002367648452,
+  "global_step": 170000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2060,11 +2060,139 @@
       "eval_samples_per_second": 166.561,
       "eval_steps_per_second": 20.825,
       "step": 160000
+    },
+    {
+      "epoch": 3.8,
+      "learning_rate": 1.886706443160653e-05,
+      "loss": 2.7213,
+      "step": 160500
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 1.8803927139564987e-05,
+      "loss": 2.7193,
+      "step": 161000
+    },
+    {
+      "epoch": 3.82,
+      "learning_rate": 1.8740789847523442e-05,
+      "loss": 2.7288,
+      "step": 161500
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 1.8677652555481897e-05,
+      "loss": 2.7379,
+      "step": 162000
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 1.8614515263440352e-05,
+      "loss": 2.7309,
+      "step": 162500
+    },
+    {
+      "epoch": 3.86,
+      "learning_rate": 1.8551377971398807e-05,
+      "loss": 2.7283,
+      "step": 163000
+    },
+    {
+      "epoch": 3.87,
+      "learning_rate": 1.8488240679357263e-05,
+      "loss": 2.7326,
+      "step": 163500
+    },
+    {
+      "epoch": 3.88,
+      "learning_rate": 1.8425103387315718e-05,
+      "loss": 2.7326,
+      "step": 164000
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 1.8361966095274176e-05,
+      "loss": 2.7295,
+      "step": 164500
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 1.829882880323263e-05,
+      "loss": 2.7498,
+      "step": 165000
+    },
+    {
+      "epoch": 3.92,
+      "learning_rate": 1.8235691511191086e-05,
+      "loss": 2.7174,
+      "step": 165500
+    },
+    {
+      "epoch": 3.93,
+      "learning_rate": 1.817255421914954e-05,
+      "loss": 2.7268,
+      "step": 166000
+    },
+    {
+      "epoch": 3.94,
+      "learning_rate": 1.8109416927108e-05,
+      "loss": 2.7283,
+      "step": 166500
+    },
+    {
+      "epoch": 3.95,
+      "learning_rate": 1.804627963506645e-05,
+      "loss": 2.7312,
+      "step": 167000
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 1.798314234302491e-05,
+      "loss": 2.7393,
+      "step": 167500
+    },
+    {
+      "epoch": 3.98,
+      "learning_rate": 1.7920005050983365e-05,
+      "loss": 2.7335,
+      "step": 168000
+    },
+    {
+      "epoch": 3.99,
+      "learning_rate": 1.785686775894182e-05,
+      "loss": 2.7394,
+      "step": 168500
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.7793730466900276e-05,
+      "loss": 2.7243,
+      "step": 169000
+    },
+    {
+      "epoch": 4.01,
+      "learning_rate": 1.7730593174858734e-05,
+      "loss": 2.6166,
+      "step": 169500
+    },
+    {
+      "epoch": 4.03,
+      "learning_rate": 1.766745588281719e-05,
+      "loss": 2.6252,
+      "step": 170000
+    },
+    {
+      "epoch": 4.03,
+      "eval_loss": 3.1331186294555664,
+      "eval_runtime": 112.7793,
+      "eval_samples_per_second": 166.449,
+      "eval_steps_per_second": 20.811,
+      "step": 170000
     }
   ],
   "max_steps": 633540,
   "num_train_epochs": 15,
-  "total_flos": 3.3942647411712e+16,
+  "total_flos": 3.6054596397312e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2316b204782da72135ffb03278561a92f4394e61a9305152e8eeab4641dd7f78
+oid sha256:f42dbd9b35415ba34033be719191148beaa9e62794b2440aac238f33a11f2b47
 size 510398013