Training in progress, step 300000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3a8513b0368f6cb2e3381f928e0aa14b5dd1d4d6e81f16afa2b1f5c07381ace
+oid sha256:2ce18f0748d256d97c3ffa8fd0dca4af493eeb80a1e3c680178d29c9ddddf382
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34882c0a1ec238c2b1ad9048809a8c4ec0fe4694d212fa9d7361294be70895cf
+oid sha256:674942f3a22b761c6237130c7c1c65ef4ae9c18ea51c2e94629488e89aee1787
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53d2183906572577bb72529bb7cea14ccb3598c2ad81bd496d1690556b2c2fad
-size 14503
+oid sha256:79632fe258ae9bf0159b29eb8f75054c68c6d067b87a65bb1e5ce3d8111e8b99
+size 14439

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e47c84ee1a7263145bb05e6bd38ff747cca1ce76d180b5d014131790082d04ac
+oid sha256:30038ba0292443919b51298718047b6773e6d7e41921e311f8e57713dd04b046
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5654423abeb0cd8c1ac599d51c54b19e61e2cbf655685c7b1d094b3f86c3ae14
+oid sha256:d6c3448ae7122fabd57f3afe7b464dea056b6f69fb30306ac34573daa9a6e577
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75741429273458049dfadf451049de4bb7af88e4bb53df1b8babe07272a17a27
+oid sha256:2edb4ed6c12c84109dcab5c035479f8f5be0a6003c13da100daa3666a0ffbb98
 size 14439

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43486ecf7953ead4f44fd0913517d08c2421c80bd01545c2aa6edfd9bc952a2c
+oid sha256:09aaf2baea19ad11e593b229d87541fdc460178a4ce9400acb0896ac15b65425
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.428359827141264,
-  "global_step": 290000,
+  "epoch": 4.5810618901461355,
+  "global_step": 300000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2152,11 +2152,85 @@
       "eval_samples_per_second": 985.898,
       "eval_steps_per_second": 15.774,
       "step": 290000
+    },
+    {
+      "epoch": 4.44,
+      "learning_rate": 0.00012892127400441228,
+      "loss": 0.2923,
+      "step": 291000
+    },
+    {
+      "epoch": 4.46,
+      "learning_rate": 0.00012875543811453576,
+      "loss": 0.2919,
+      "step": 292000
+    },
+    {
+      "epoch": 4.47,
+      "learning_rate": 0.0001285890690429993,
+      "loss": 0.2931,
+      "step": 293000
+    },
+    {
+      "epoch": 4.49,
+      "learning_rate": 0.00012842216860918846,
+      "loss": 0.292,
+      "step": 294000
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 0.0001282547386382996,
+      "loss": 0.2914,
+      "step": 295000
+    },
+    {
+      "epoch": 4.5,
+      "eval_runtime": 1.0329,
+      "eval_samples_per_second": 968.135,
+      "eval_steps_per_second": 15.49,
+      "step": 295000
+    },
+    {
+      "epoch": 4.52,
+      "learning_rate": 0.0001280867809613201,
+      "loss": 0.2919,
+      "step": 296000
+    },
+    {
+      "epoch": 4.54,
+      "learning_rate": 0.0001279182974150082,
+      "loss": 0.2915,
+      "step": 297000
+    },
+    {
+      "epoch": 4.55,
+      "learning_rate": 0.00012774928984187297,
+      "loss": 0.2914,
+      "step": 298000
+    },
+    {
+      "epoch": 4.57,
+      "learning_rate": 0.00012757976009015413,
+      "loss": 0.2908,
+      "step": 299000
+    },
+    {
+      "epoch": 4.58,
+      "learning_rate": 0.0001274097100138019,
+      "loss": 0.2909,
+      "step": 300000
+    },
+    {
+      "epoch": 4.58,
+      "eval_runtime": 1.0054,
+      "eval_samples_per_second": 994.612,
+      "eval_steps_per_second": 15.914,
+      "step": 300000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 2.032904941607472e+22,
+  "total_flos": 2.1030052026378193e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34882c0a1ec238c2b1ad9048809a8c4ec0fe4694d212fa9d7361294be70895cf
+oid sha256:674942f3a22b761c6237130c7c1c65ef4ae9c18ea51c2e94629488e89aee1787
 size 449471589