Training in progress, step 140000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16b5536ca8a6e377f81e58375b1a7ad0f81c77249b2b140bbeb9ba4baedae79d
+oid sha256:a7f5c98114bb03a0107e9edbb2aa57590411cc0a9aced01e13efc323f9c7511d
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba517ef097f30eafaab51fcd07596ea1dc064b2e4ffa07b172ca6b443b8d5c50
+oid sha256:1151081009ac294a44ef99911473d89538dee75ada188d7d9e2d8f1a9b3231fc
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6905d0008e40eff2d80ae3e67e781129af6c787e6082983c24f27be53737707
+oid sha256:c91cc3747c6b314cba53effe7863cb06ebbb2887876cfc49af2ce3563922b45f
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6905d0008e40eff2d80ae3e67e781129af6c787e6082983c24f27be53737707
+oid sha256:c91cc3747c6b314cba53effe7863cb06ebbb2887876cfc49af2ce3563922b45f
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6905d0008e40eff2d80ae3e67e781129af6c787e6082983c24f27be53737707
+oid sha256:c91cc3747c6b314cba53effe7863cb06ebbb2887876cfc49af2ce3563922b45f
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6905d0008e40eff2d80ae3e67e781129af6c787e6082983c24f27be53737707
+oid sha256:c91cc3747c6b314cba53effe7863cb06ebbb2887876cfc49af2ce3563922b45f
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6905d0008e40eff2d80ae3e67e781129af6c787e6082983c24f27be53737707
+oid sha256:c91cc3747c6b314cba53effe7863cb06ebbb2887876cfc49af2ce3563922b45f
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6905d0008e40eff2d80ae3e67e781129af6c787e6082983c24f27be53737707
+oid sha256:c91cc3747c6b314cba53effe7863cb06ebbb2887876cfc49af2ce3563922b45f
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6905d0008e40eff2d80ae3e67e781129af6c787e6082983c24f27be53737707
+oid sha256:c91cc3747c6b314cba53effe7863cb06ebbb2887876cfc49af2ce3563922b45f
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6905d0008e40eff2d80ae3e67e781129af6c787e6082983c24f27be53737707
+oid sha256:c91cc3747c6b314cba53effe7863cb06ebbb2887876cfc49af2ce3563922b45f
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1c3de3c2d66025eca4b56b8d5efacb781ba1e9b4daae40acd9c92c0f7cbe98c
+oid sha256:f9522f343e5b1c37fe7e600f7b39d619e850350d8948dc240940a440582a0eb9
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.313114837657373,
-  "global_step": 130000,
+  "epoch": 3.5679698251694787,
+  "global_step": 140000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2606,11 +2606,211 @@
       "eval_samples_per_second": 766.596,
       "eval_steps_per_second": 12.266,
       "step": 130000
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 0.0002661106834948409,
+      "loss": 0.3058,
+      "step": 130500
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 0.0002658019908268041,
+      "loss": 0.3048,
+      "step": 131000
+    },
+    {
+      "epoch": 3.34,
+      "eval_loss": 0.8294724822044373,
+      "eval_runtime": 1.2682,
+      "eval_samples_per_second": 788.537,
+      "eval_steps_per_second": 12.617,
+      "step": 131000
+    },
+    {
+      "epoch": 3.35,
+      "learning_rate": 0.00026549208644594766,
+      "loss": 0.305,
+      "step": 131500
+    },
+    {
+      "epoch": 3.36,
+      "learning_rate": 0.00026518097374133627,
+      "loss": 0.3051,
+      "step": 132000
+    },
+    {
+      "epoch": 3.36,
+      "eval_loss": 0.8296982049942017,
+      "eval_runtime": 1.3247,
+      "eval_samples_per_second": 754.912,
+      "eval_steps_per_second": 12.079,
+      "step": 132000
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 0.00026486865611524853,
+      "loss": 0.3045,
+      "step": 132500
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 0.00026455513698314003,
+      "loss": 0.3045,
+      "step": 133000
+    },
+    {
+      "epoch": 3.39,
+      "eval_loss": 0.8295329213142395,
+      "eval_runtime": 1.3528,
+      "eval_samples_per_second": 739.189,
+      "eval_steps_per_second": 11.827,
+      "step": 133000
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 0.0002642404197736058,
+      "loss": 0.3045,
+      "step": 133500
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 0.0002639245079283428,
+      "loss": 0.3043,
+      "step": 134000
+    },
+    {
+      "epoch": 3.42,
+      "eval_loss": 0.8244909644126892,
+      "eval_runtime": 1.3196,
+      "eval_samples_per_second": 757.824,
+      "eval_steps_per_second": 12.125,
+      "step": 134000
+    },
+    {
+      "epoch": 3.43,
+      "learning_rate": 0.00026360740490211234,
+      "loss": 0.3038,
+      "step": 134500
+    },
+    {
+      "epoch": 3.44,
+      "learning_rate": 0.0002632891141627023,
+      "loss": 0.3037,
+      "step": 135000
+    },
+    {
+      "epoch": 3.44,
+      "eval_loss": 0.8188607096672058,
+      "eval_runtime": 1.2963,
+      "eval_samples_per_second": 771.439,
+      "eval_steps_per_second": 12.343,
+      "step": 135000
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 0.00026296963919088923,
+      "loss": 0.304,
+      "step": 135500
+    },
+    {
+      "epoch": 3.47,
+      "learning_rate": 0.00026264898348040024,
+      "loss": 0.3042,
+      "step": 136000
+    },
+    {
+      "epoch": 3.47,
+      "eval_loss": 0.8286353349685669,
+      "eval_runtime": 1.3187,
+      "eval_samples_per_second": 758.324,
+      "eval_steps_per_second": 12.133,
+      "step": 136000
+    },
+    {
+      "epoch": 3.48,
+      "learning_rate": 0.0002623271505378748,
+      "loss": 0.3038,
+      "step": 136500
+    },
+    {
+      "epoch": 3.49,
+      "learning_rate": 0.00026200414388282637,
+      "loss": 0.3038,
+      "step": 137000
+    },
+    {
+      "epoch": 3.49,
+      "eval_loss": 0.8326404690742493,
+      "eval_runtime": 1.3251,
+      "eval_samples_per_second": 754.645,
+      "eval_steps_per_second": 12.074,
+      "step": 137000
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 0.00026167996704760406,
+      "loss": 0.3058,
+      "step": 137500
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 0.00026135462357735375,
+      "loss": 0.3033,
+      "step": 138000
+    },
+    {
+      "epoch": 3.52,
+      "eval_loss": 0.8183851838111877,
+      "eval_runtime": 1.3581,
+      "eval_samples_per_second": 736.344,
+      "eval_steps_per_second": 11.782,
+      "step": 138000
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 0.0002610281170299795,
+      "loss": 0.3035,
+      "step": 138500
+    },
+    {
+      "epoch": 3.54,
+      "learning_rate": 0.00026070045097610465,
+      "loss": 0.3035,
+      "step": 139000
+    },
+    {
+      "epoch": 3.54,
+      "eval_loss": 0.8135998249053955,
+      "eval_runtime": 1.309,
+      "eval_samples_per_second": 763.92,
+      "eval_steps_per_second": 12.223,
+      "step": 139000
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 0.0002603716289990326,
+      "loss": 0.3026,
+      "step": 139500
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 0.00026004165469470787,
+      "loss": 0.3027,
+      "step": 140000
+    },
+    {
+      "epoch": 3.57,
+      "eval_loss": 0.8287385106086731,
+      "eval_runtime": 1.2779,
+      "eval_samples_per_second": 782.532,
+      "eval_steps_per_second": 12.521,
+      "step": 140000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 4.153292367329365e+21,
+  "total_flos": 4.472779506103865e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba517ef097f30eafaab51fcd07596ea1dc064b2e4ffa07b172ca6b443b8d5c50
+oid sha256:1151081009ac294a44ef99911473d89538dee75ada188d7d9e2d8f1a9b3231fc
 size 102501541