Training in progress, step 650000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c444c75d0337de46e35f539ad919e0e13abb76dfe8d15c375255f6a83fa8fd2
+oid sha256:fa92f0e8b9e69e1553d8b13a15bb13ce9949137fccf0723c1cf598ce83f198b0
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5808a95cf4864d9e7dd396fa3d5d75f6fe69b93fbc2376d586a3a7fc3b0fe04
+oid sha256:b48d3a0bd417c9af2fc7e229c4f39167675dca2415013cbeac1e6dc95824f669
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aaf518826c7b02349e0c4043ecb7a38ebc1a14f60809955f00a7944ae21e6fc
+oid sha256:4e055e902e7363a164e2d5682ba553c77cec859581fb13cd45150bf96f1a362c
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcb6ee46cb325ce6d5d0f15d240a67578f4710009ebcab3be0d17117038d01fa
-size 14503
+oid sha256:436765cf8b9dcd2a96469489c52342b1fc2a8edf0ab7af7b53c1cbd1ff9932a6
+size 14439

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7121d5ba757842882faa79dcd7ac54d5b1c2ec66868fe528ff6cebaa506df816
-size 14503
+oid sha256:2ee8f18ff63c361ce90d137b232b2607444382342857d71c811d9abe82e89eeb
+size 14439

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6083d2cad6c63a2b0e7d04c706615465f15ee7e67189e761029a05d0b2f204c9
-size 14439
+oid sha256:106d03af9d874407e7a0086ddb94edb099a500fa25e66c11a4dedce8d45fc7e2
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ba925316c6e59686c34db192a6703d2b94be7f6c9b908cf313be2f93b23828d
+oid sha256:b544465929a51046e9a52e629bd463b9098d69ff8cc60ad2e18003214dae8858
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.772932032311756,
-  "global_step": 640000,
+  "epoch": 9.925634095316628,
+  "global_step": 650000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4742,11 +4742,85 @@
       "eval_samples_per_second": 993.184,
       "eval_steps_per_second": 15.891,
       "step": 640000
+    },
+    {
+      "epoch": 9.79,
+      "learning_rate": 5.3801387994131576e-05,
+      "loss": 0.2501,
+      "step": 641000
+    },
+    {
+      "epoch": 9.8,
+      "learning_rate": 5.358686991636209e-05,
+      "loss": 0.2503,
+      "step": 642000
+    },
+    {
+      "epoch": 9.82,
+      "learning_rate": 5.3372640688351476e-05,
+      "loss": 0.2505,
+      "step": 643000
+    },
+    {
+      "epoch": 9.83,
+      "learning_rate": 5.315870265287618e-05,
+      "loss": 0.2502,
+      "step": 644000
+    },
+    {
+      "epoch": 9.85,
+      "learning_rate": 5.294505814952835e-05,
+      "loss": 0.2501,
+      "step": 645000
+    },
+    {
+      "epoch": 9.85,
+      "eval_runtime": 1.0688,
+      "eval_samples_per_second": 935.652,
+      "eval_steps_per_second": 14.97,
+      "step": 645000
+    },
+    {
+      "epoch": 9.86,
+      "learning_rate": 5.2731709514689995e-05,
+      "loss": 0.2502,
+      "step": 646000
+    },
+    {
+      "epoch": 9.88,
+      "learning_rate": 5.25186590815076e-05,
+      "loss": 0.2501,
+      "step": 647000
+    },
+    {
+      "epoch": 9.9,
+      "learning_rate": 5.2305909179866635e-05,
+      "loss": 0.2495,
+      "step": 648000
+    },
+    {
+      "epoch": 9.91,
+      "learning_rate": 5.209346213636584e-05,
+      "loss": 0.2498,
+      "step": 649000
+    },
+    {
+      "epoch": 9.93,
+      "learning_rate": 5.188132027429215e-05,
+      "loss": 0.2495,
+      "step": 650000
+    },
+    {
+      "epoch": 9.93,
+      "eval_runtime": 1.0361,
+      "eval_samples_per_second": 965.164,
+      "eval_steps_per_second": 15.443,
+      "step": 650000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 4.4864107923288785e+22,
+  "total_flos": 4.556511053359226e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5808a95cf4864d9e7dd396fa3d5d75f6fe69b93fbc2376d586a3a7fc3b0fe04
+oid sha256:b48d3a0bd417c9af2fc7e229c4f39167675dca2415013cbeac1e6dc95824f669
 size 449471589