Training in progress, step 330000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feec96829044f69c5632c270eedd009034bbe0cf717e555992fa10aeea97b864
+oid sha256:54534335b10706006d453ec56a979a5d5c461f57d0f68d1a6ad0a77c57a0aecf
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d15795c67ef8a474ec8269e65cb5cae595586b0dd6a18f0656a533551a730789
+oid sha256:4ea75c11d2eaacb0e2bbd235a00be3c1d10c576c2381b03ccce251e6969bea54
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:001dab7e0bd0507b251f8661de959d0c23f7918aaaae6122c9ffe6e68407c81b
+oid sha256:ca0f29d45171c4938599319a84794d73d3d2336609c8cb89948f6f9bcd906a6a
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:001dab7e0bd0507b251f8661de959d0c23f7918aaaae6122c9ffe6e68407c81b
+oid sha256:ca0f29d45171c4938599319a84794d73d3d2336609c8cb89948f6f9bcd906a6a
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:001dab7e0bd0507b251f8661de959d0c23f7918aaaae6122c9ffe6e68407c81b
+oid sha256:ca0f29d45171c4938599319a84794d73d3d2336609c8cb89948f6f9bcd906a6a
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:001dab7e0bd0507b251f8661de959d0c23f7918aaaae6122c9ffe6e68407c81b
+oid sha256:ca0f29d45171c4938599319a84794d73d3d2336609c8cb89948f6f9bcd906a6a
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:001dab7e0bd0507b251f8661de959d0c23f7918aaaae6122c9ffe6e68407c81b
+oid sha256:ca0f29d45171c4938599319a84794d73d3d2336609c8cb89948f6f9bcd906a6a
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:001dab7e0bd0507b251f8661de959d0c23f7918aaaae6122c9ffe6e68407c81b
+oid sha256:ca0f29d45171c4938599319a84794d73d3d2336609c8cb89948f6f9bcd906a6a
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:001dab7e0bd0507b251f8661de959d0c23f7918aaaae6122c9ffe6e68407c81b
+oid sha256:ca0f29d45171c4938599319a84794d73d3d2336609c8cb89948f6f9bcd906a6a
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:001dab7e0bd0507b251f8661de959d0c23f7918aaaae6122c9ffe6e68407c81b
+oid sha256:ca0f29d45171c4938599319a84794d73d3d2336609c8cb89948f6f9bcd906a6a
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5673377a057c7734bd1a0ee14d972f6f3bfc67bb8208ac49ae618347d18d616b
+oid sha256:636cb28fce30ad56f68aface20193360fd815697da4c2ec39f5ca647b5e6b45b
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.15535960038738,
-  "global_step": 320000,
+  "epoch": 8.410214587899485,
+  "global_step": 330000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6406,11 +6406,211 @@
       "eval_samples_per_second": 802.848,
       "eval_steps_per_second": 12.846,
       "step": 320000
+    },
+    {
+      "epoch": 8.17,
+      "learning_rate": 0.00010073144655927253,
+      "loss": 0.2809,
+      "step": 320500
+    },
+    {
+      "epoch": 8.18,
+      "learning_rate": 0.0001002870876838929,
+      "loss": 0.28,
+      "step": 321000
+    },
+    {
+      "epoch": 8.18,
+      "eval_loss": 0.8134902119636536,
+      "eval_runtime": 1.3191,
+      "eval_samples_per_second": 758.118,
+      "eval_steps_per_second": 12.13,
+      "step": 321000
+    },
+    {
+      "epoch": 8.19,
+      "learning_rate": 9.984332714015662e-05,
+      "loss": 0.2799,
+      "step": 321500
+    },
+    {
+      "epoch": 8.21,
+      "learning_rate": 9.94001697809578e-05,
+      "loss": 0.2796,
+      "step": 322000
+    },
+    {
+      "epoch": 8.21,
+      "eval_loss": 0.8164393305778503,
+      "eval_runtime": 1.2535,
+      "eval_samples_per_second": 797.791,
+      "eval_steps_per_second": 12.765,
+      "step": 322000
+    },
+    {
+      "epoch": 8.22,
+      "learning_rate": 9.895762045259445e-05,
+      "loss": 0.2797,
+      "step": 322500
+    },
+    {
+      "epoch": 8.23,
+      "learning_rate": 9.851568399471498e-05,
+      "loss": 0.2793,
+      "step": 323000
+    },
+    {
+      "epoch": 8.23,
+      "eval_loss": 0.8119146823883057,
+      "eval_runtime": 1.2514,
+      "eval_samples_per_second": 799.097,
+      "eval_steps_per_second": 12.786,
+      "step": 323000
+    },
+    {
+      "epoch": 8.24,
+      "learning_rate": 9.807436524026574e-05,
+      "loss": 0.2797,
+      "step": 323500
+    },
+    {
+      "epoch": 8.26,
+      "learning_rate": 9.763366901543801e-05,
+      "loss": 0.2791,
+      "step": 324000
+    },
+    {
+      "epoch": 8.26,
+      "eval_loss": 0.8064904808998108,
+      "eval_runtime": 1.2268,
+      "eval_samples_per_second": 815.12,
+      "eval_steps_per_second": 13.042,
+      "step": 324000
+    },
+    {
+      "epoch": 8.27,
+      "learning_rate": 9.719360013961495e-05,
+      "loss": 0.2793,
+      "step": 324500
+    },
+    {
+      "epoch": 8.28,
+      "learning_rate": 9.675416342531944e-05,
+      "loss": 0.2793,
+      "step": 325000
+    },
+    {
+      "epoch": 8.28,
+      "eval_loss": 0.8141771554946899,
+      "eval_runtime": 1.2692,
+      "eval_samples_per_second": 787.921,
+      "eval_steps_per_second": 12.607,
+      "step": 325000
+    },
+    {
+      "epoch": 8.3,
+      "learning_rate": 9.631536367816086e-05,
+      "loss": 0.2798,
+      "step": 325500
+    },
+    {
+      "epoch": 8.31,
+      "learning_rate": 9.587720569678299e-05,
+      "loss": 0.2794,
+      "step": 326000
+    },
+    {
+      "epoch": 8.31,
+      "eval_loss": 0.803835391998291,
+      "eval_runtime": 1.24,
+      "eval_samples_per_second": 806.471,
+      "eval_steps_per_second": 12.904,
+      "step": 326000
+    },
+    {
+      "epoch": 8.32,
+      "learning_rate": 9.543969427281131e-05,
+      "loss": 0.2791,
+      "step": 326500
+    },
+    {
+      "epoch": 8.33,
+      "learning_rate": 9.500283419080062e-05,
+      "loss": 0.2792,
+      "step": 327000
+    },
+    {
+      "epoch": 8.33,
+      "eval_loss": 0.81174635887146,
+      "eval_runtime": 1.301,
+      "eval_samples_per_second": 768.659,
+      "eval_steps_per_second": 12.299,
+      "step": 327000
+    },
+    {
+      "epoch": 8.35,
+      "learning_rate": 9.45666302281829e-05,
+      "loss": 0.2787,
+      "step": 327500
+    },
+    {
+      "epoch": 8.36,
+      "learning_rate": 9.413108715521467e-05,
+      "loss": 0.2789,
+      "step": 328000
+    },
+    {
+      "epoch": 8.36,
+      "eval_loss": 0.8118357062339783,
+      "eval_runtime": 1.2706,
+      "eval_samples_per_second": 787.037,
+      "eval_steps_per_second": 12.593,
+      "step": 328000
+    },
+    {
+      "epoch": 8.37,
+      "learning_rate": 9.369620973492525e-05,
+      "loss": 0.2794,
+      "step": 328500
+    },
+    {
+      "epoch": 8.38,
+      "learning_rate": 9.326200272306445e-05,
+      "loss": 0.2793,
+      "step": 329000
+    },
+    {
+      "epoch": 8.38,
+      "eval_loss": 0.809190034866333,
+      "eval_runtime": 1.2623,
+      "eval_samples_per_second": 792.184,
+      "eval_steps_per_second": 12.675,
+      "step": 329000
+    },
+    {
+      "epoch": 8.4,
+      "learning_rate": 9.282847086805059e-05,
+      "loss": 0.2788,
+      "step": 329500
+    },
+    {
+      "epoch": 8.41,
+      "learning_rate": 9.239561891091853e-05,
+      "loss": 0.279,
+      "step": 330000
+    },
+    {
+      "epoch": 8.41,
+      "eval_loss": 0.8081182837486267,
+      "eval_runtime": 1.2445,
+      "eval_samples_per_second": 803.539,
+      "eval_steps_per_second": 12.857,
+      "step": 330000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 1.022348060947964e+22,
+  "total_flos": 1.054296774825414e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d15795c67ef8a474ec8269e65cb5cae595586b0dd6a18f0656a533551a730789
+oid sha256:4ea75c11d2eaacb0e2bbd235a00be3c1d10c576c2381b03ccce251e6969bea54
 size 102501541