Training in progress, step 100000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0946b4af042d0003be776279dd8dec310d85422ca12c683daea7163fdc14f58f
+oid sha256:10ce2f9aa9d5627458e5c26c0c8c1f447307afa57aad3f361bb6eeb7f577533f
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:886c14bc146e35ddb8b43369943fdd5ae148eef1a89bed83206fbfc7c2a327ef
+oid sha256:0d6ee7a4f983bd49941cf45454fc26eedf52c2df44891b73ef7378899f037b91
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3ab37f55295b05256b0aeab0c9118d1e91676146a55f40c6459b8bea2a5ccfb
+oid sha256:40e63f9b2799078475c6fffe20b9cb0c8afc8f9b68799aea89478ba54d8b5f9a
 size 15523

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fd1d30ec6a85b35de8f6aedadaea7484a7f1c0d94891107a63ad388e3781007
+oid sha256:96c80f44742a8b293db0b2ae4807850db50b76531a4a9c1e49d9708ec4e2c11e
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f61de41cc564c25462ca0290993ffba1d92f72b28f091680e90a006d4be7a958
+oid sha256:bbda746b03062a6d3e95bcd90c26d65c91a4557dd86831395f573a0b3bba8af0
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.8376730819472264,
-  "global_step": 90000,
+  "epoch": 8.70852564660803,
+  "global_step": 100000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1230,11 +1230,147 @@
       "eval_samples_per_second": 64.646,
       "eval_steps_per_second": 1.021,
       "step": 90000
+    },
+    {
+      "epoch": 7.88,
+      "learning_rate": 1.20196015019827e-05,
+      "loss": 0.3811,
+      "step": 90500
+    },
+    {
+      "epoch": 7.92,
+      "learning_rate": 1.1814648074431392e-05,
+      "loss": 0.3802,
+      "step": 91000
+    },
+    {
+      "epoch": 7.97,
+      "learning_rate": 1.1620446367145134e-05,
+      "loss": 0.3808,
+      "step": 91500
+    },
+    {
+      "epoch": 8.01,
+      "learning_rate": 1.1437400292071077e-05,
+      "loss": 0.3807,
+      "step": 92000
+    },
+    {
+      "epoch": 8.06,
+      "learning_rate": 1.1265155682572145e-05,
+      "loss": 0.3799,
+      "step": 92500
+    },
+    {
+      "epoch": 8.1,
+      "learning_rate": 1.1103442333401839e-05,
+      "loss": 0.3794,
+      "step": 93000
+    },
+    {
+      "epoch": 8.14,
+      "learning_rate": 1.0952656183871172e-05,
+      "loss": 0.3796,
+      "step": 93500
+    },
+    {
+      "epoch": 8.19,
+      "learning_rate": 1.0812834438206289e-05,
+      "loss": 0.3805,
+      "step": 94000
+    },
+    {
+      "epoch": 8.23,
+      "learning_rate": 1.0684011595330725e-05,
+      "loss": 0.3814,
+      "step": 94500
+    },
+    {
+      "epoch": 8.27,
+      "learning_rate": 1.0566443996265343e-05,
+      "loss": 0.3809,
+      "step": 95000
+    },
+    {
+      "epoch": 8.27,
+      "eval_loss": 0.3615710437297821,
+      "eval_runtime": 63.8854,
+      "eval_samples_per_second": 78.265,
+      "eval_steps_per_second": 1.237,
+      "step": 95000
+    },
+    {
+      "epoch": 8.32,
+      "learning_rate": 1.0459689445942448e-05,
+      "loss": 0.3801,
+      "step": 95500
+    },
+    {
+      "epoch": 8.36,
+      "learning_rate": 1.036402093165149e-05,
+      "loss": 0.3808,
+      "step": 96000
+    },
+    {
+      "epoch": 8.4,
+      "learning_rate": 1.0279462058166865e-05,
+      "loss": 0.3796,
+      "step": 96500
+    },
+    {
+      "epoch": 8.45,
+      "learning_rate": 1.0206033689125313e-05,
+      "loss": 0.379,
+      "step": 97000
+    },
+    {
+      "epoch": 8.49,
+      "learning_rate": 1.0143753941878168e-05,
+      "loss": 0.3782,
+      "step": 97500
+    },
+    {
+      "epoch": 8.53,
+      "learning_rate": 1.0092638183021144e-05,
+      "loss": 0.3797,
+      "step": 98000
+    },
+    {
+      "epoch": 8.58,
+      "learning_rate": 1.0052699024602892e-05,
+      "loss": 0.3793,
+      "step": 98500
+    },
+    {
+      "epoch": 8.62,
+      "learning_rate": 1.0023946321013112e-05,
+      "loss": 0.3799,
+      "step": 99000
+    },
+    {
+      "epoch": 8.66,
+      "learning_rate": 1.0006387166551193e-05,
+      "loss": 0.3795,
+      "step": 99500
+    },
+    {
+      "epoch": 8.71,
+      "learning_rate": 1.0000025893675746e-05,
+      "loss": 0.3796,
+      "step": 100000
+    },
+    {
+      "epoch": 8.71,
+      "eval_loss": 0.36024102568626404,
+      "eval_runtime": 72.9389,
+      "eval_samples_per_second": 68.551,
+      "eval_steps_per_second": 1.083,
+      "step": 100000
     }
   ],
   "max_steps": 100000,
   "num_train_epochs": 9,
-  "total_flos": 4.238631778453049e+21,
+  "total_flos": 4.7095831368807633e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:886c14bc146e35ddb8b43369943fdd5ae148eef1a89bed83206fbfc7c2a327ef
+oid sha256:0d6ee7a4f983bd49941cf45454fc26eedf52c2df44891b73ef7378899f037b91
 size 449471589