Training in progress, step 660000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa92f0e8b9e69e1553d8b13a15bb13ce9949137fccf0723c1cf598ce83f198b0
+oid sha256:6d1b9c3dadef4c83eaa6444ae31d8e46ec85073c61b37dd61844f05913236e16
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b48d3a0bd417c9af2fc7e229c4f39167675dca2415013cbeac1e6dc95824f669
+oid sha256:c2fc5b645a51764da4f8ff98e3c407a8e3b54b7f2ebf4044514e81a387a44685
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e055e902e7363a164e2d5682ba553c77cec859581fb13cd45150bf96f1a362c
+oid sha256:cdc9f2d6c7b188b0a4e60257b0a8bd84c335d50dfde13a7917d3ec48da9a1694
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:436765cf8b9dcd2a96469489c52342b1fc2a8edf0ab7af7b53c1cbd1ff9932a6
-size 14439
+oid sha256:f55bf132d9f9827e3128928d8dd16bab60642cd4846a79818e1304f0d9048138
+size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ee8f18ff63c361ce90d137b232b2607444382342857d71c811d9abe82e89eeb
-size 14439
+oid sha256:c250144fe49ffdfe7647f695a0d687d07a9a35cdce7fa106343ed4f42beb24af
+size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:106d03af9d874407e7a0086ddb94edb099a500fa25e66c11a4dedce8d45fc7e2
-size 14503
+oid sha256:9d99a97fa7df68e7130dee285dc72156e57930a619ecb49b136dff7611919aa2
+size 14439

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b544465929a51046e9a52e629bd463b9098d69ff8cc60ad2e18003214dae8858
+oid sha256:1e668d5f010f36e9bc3681300c074ae1cd82ec8d3466f5c0bcb0eb7c6db53f6b
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.925634095316628,
-  "global_step": 650000,
+  "epoch": 10.078336158321498,
+  "global_step": 660000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4816,11 +4816,85 @@
       "eval_samples_per_second": 965.164,
       "eval_steps_per_second": 15.443,
       "step": 650000
+    },
+    {
+      "epoch": 9.94,
+      "learning_rate": 5.166948591359489e-05,
+      "loss": 0.2493,
+      "step": 651000
+    },
+    {
+      "epoch": 9.96,
+      "learning_rate": 5.145796137086076e-05,
+      "loss": 0.2493,
+      "step": 652000
+    },
+    {
+      "epoch": 9.97,
+      "learning_rate": 5.124674895928823e-05,
+      "loss": 0.2493,
+      "step": 653000
+    },
+    {
+      "epoch": 9.99,
+      "learning_rate": 5.103585098866237e-05,
+      "loss": 0.2491,
+      "step": 654000
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 5.082526976532968e-05,
+      "loss": 0.249,
+      "step": 655000
+    },
+    {
+      "epoch": 10.0,
+      "eval_runtime": 1.0267,
+      "eval_samples_per_second": 974.027,
+      "eval_steps_per_second": 15.584,
+      "step": 655000
+    },
+    {
+      "epoch": 10.02,
+      "learning_rate": 5.061500759217261e-05,
+      "loss": 0.2494,
+      "step": 656000
+    },
+    {
+      "epoch": 10.03,
+      "learning_rate": 5.04050667685846e-05,
+      "loss": 0.2487,
+      "step": 657000
+    },
+    {
+      "epoch": 10.05,
+      "learning_rate": 5.01954495904449e-05,
+      "loss": 0.2485,
+      "step": 658000
+    },
+    {
+      "epoch": 10.06,
+      "learning_rate": 4.998615835009339e-05,
+      "loss": 0.2488,
+      "step": 659000
+    },
+    {
+      "epoch": 10.08,
+      "learning_rate": 4.97771953363055e-05,
+      "loss": 0.2489,
+      "step": 660000
+    },
+    {
+      "epoch": 10.08,
+      "eval_runtime": 1.0445,
+      "eval_samples_per_second": 957.361,
+      "eval_steps_per_second": 15.318,
+      "step": 660000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 4.556511053359226e+22,
+  "total_flos": 4.626610657321424e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b48d3a0bd417c9af2fc7e229c4f39167675dca2415013cbeac1e6dc95824f669
+oid sha256:c2fc5b645a51764da4f8ff98e3c407a8e3b54b7f2ebf4044514e81a387a44685
 size 449471589