Training in progress, step 690000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44b0820fc6b350986b719e550b35d09a69f533f4c17c09f1fc4dcc51eee4deaf
+oid sha256:03c116c94691fe83930a5993880bd8c0998a3e0ec38012be8fad0b40e1c29568
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bad34c9686a45968effd10ffe093593240a68e27baf1e992462f0c39c5a1154f
+oid sha256:b2b586adc3a504918e31f8a9a7e0f4be94f03956b7f0114b4da9476acb22a6ef
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5303f8d69702e89a1f09b78b9ce543e8c95fc0bc0f0edba191465caf3a91d92a
+oid sha256:33a77fe6605383afb833ca53fc48599ad56cfe3eec3e43ed5ccdec337bfa0ca8
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ef09cba59e3953ac0ff77371a062cedb407170faeac834b4f4e7690a6546000
+oid sha256:815de40461412919a5889eec61609965c9d2866910047894a4dc0f6b20abb0b4
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b74b641ea212d2246cddaeb018c081c477c99608fb3a2c0685286bdcc4bf7cde
+oid sha256:f4ae17687fd76755d54219d89fc11c8946b10678e74c0c01048fa01e50274084
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e039e987a11ac43b108942b16a0127488a54c01eff95956d54d2613b30129dbd
+oid sha256:c17905fc96ebc0f02fa95bfe12b431ac787bae4299fa05067fe9a564d5bb62cc
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d737cb5c8a42fd478f2f6309865787d8315dbe8632150ec0b5dc4840a67a78da
+oid sha256:b4ee1c07d4ce16af70500d9164050fdd6814fe5b1c70d5ddc9dc0d403bb72893
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.38374028433124,
-  "global_step": 680000,
+  "epoch": 10.536442347336113,
+  "global_step": 690000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5038,11 +5038,85 @@
       "eval_samples_per_second": 1352.617,
       "eval_steps_per_second": 21.642,
       "step": 680000
+    },
+    {
+      "epoch": 10.4,
+      "learning_rate": 4.546880660622845e-05,
+      "loss": 0.2463,
+      "step": 681000
+    },
+    {
+      "epoch": 10.41,
+      "learning_rate": 4.5267636108191036e-05,
+      "loss": 0.2466,
+      "step": 682000
+    },
+    {
+      "epoch": 10.43,
+      "learning_rate": 4.5066845437720555e-05,
+      "loss": 0.2462,
+      "step": 683000
+    },
+    {
+      "epoch": 10.44,
+      "learning_rate": 4.4866436790631564e-05,
+      "loss": 0.2463,
+      "step": 684000
+    },
+    {
+      "epoch": 10.46,
+      "learning_rate": 4.4666412358560955e-05,
+      "loss": 0.2461,
+      "step": 685000
+    },
+    {
+      "epoch": 10.46,
+      "eval_runtime": 0.7931,
+      "eval_samples_per_second": 1260.883,
+      "eval_steps_per_second": 20.174,
+      "step": 685000
+    },
+    {
+      "epoch": 10.48,
+      "learning_rate": 4.4466774328943796e-05,
+      "loss": 0.2462,
+      "step": 686000
+    },
+    {
+      "epoch": 10.49,
+      "learning_rate": 4.426752488498972e-05,
+      "loss": 0.2462,
+      "step": 687000
+    },
+    {
+      "epoch": 10.51,
+      "learning_rate": 4.406866620565862e-05,
+      "loss": 0.2459,
+      "step": 688000
+    },
+    {
+      "epoch": 10.52,
+      "learning_rate": 4.3870200465637164e-05,
+      "loss": 0.2471,
+      "step": 689000
+    },
+    {
+      "epoch": 10.54,
+      "learning_rate": 4.3672129835314955e-05,
+      "loss": 0.2481,
+      "step": 690000
+    },
+    {
+      "epoch": 10.54,
+      "eval_runtime": 0.8338,
+      "eval_samples_per_second": 1199.26,
+      "eval_steps_per_second": 19.188,
+      "step": 690000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 4.766811179382118e+22,
+  "total_flos": 4.8369114404124654e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bad34c9686a45968effd10ffe093593240a68e27baf1e992462f0c39c5a1154f
+oid sha256:b2b586adc3a504918e31f8a9a7e0f4be94f03956b7f0114b4da9476acb22a6ef
 size 449471589