Training in progress, step 35000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b82214f5a6da233cbde612bdd1f848ffc727475d410f23d11d0ef77869df202
+oid sha256:5afbb7db2024c06e7168cd07934240d81acfb417a962c3f9b27c2c5cac74f5f3
 size 893438545

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72a1a14ed7bf6bc0725bb876cb7a38064b9cb2a4e01a8c1e6ca520325a13a6e9
+oid sha256:795fa208c4655907c54892ea46d5deef3057c257b0f29b327c60d57aebb752ef
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b911e5c773c97f0b6494ffc61a4bccbd0595e2f25c8540a15cd988ed7205ecc7
+oid sha256:607b5c5487d5dccaf4d249f748d9be7bab5e418ed2dbdf5e21e48a8763bb2292
 size 15587

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be94e3813e8e1c0f62960e0a57904cf2dbed90df3bbe70219beb6f9114fec94f
+oid sha256:e833ce90acecedfbd8d212ba971de16be51f612497919359e2315f9ed22fdccf
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32b016f83d2aca2db829c6d70c41861d7f94941040995a7638b751ed5d1d2359
+oid sha256:86e9753a509961ebb704900ef39dcda0523410f768cfe662fee4e7f583c2197f
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.611875326484416,
-  "global_step": 30000,
+  "epoch": 3.047187880898485,
+  "global_step": 35000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -414,11 +414,79 @@
       "eval_samples_per_second": 287.576,
       "eval_steps_per_second": 4.544,
       "step": 30000
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 8.150447097896683e-05,
+      "loss": 0.431,
+      "step": 30500
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 8.091809189852956e-05,
+      "loss": 0.4312,
+      "step": 31000
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 8.032541429761075e-05,
+      "loss": 0.4306,
+      "step": 31500
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 7.972778811233862e-05,
+      "loss": 0.4306,
+      "step": 32000
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 7.912296555205017e-05,
+      "loss": 0.431,
+      "step": 32500
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 7.851228739184511e-05,
+      "loss": 0.4298,
+      "step": 33000
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 7.789590430742172e-05,
+      "loss": 0.4291,
+      "step": 33500
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 7.727396838208297e-05,
+      "loss": 0.4302,
+      "step": 34000
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 7.664663306921218e-05,
+      "loss": 0.4291,
+      "step": 34500
+    },
+    {
+      "epoch": 3.05,
+      "learning_rate": 7.601405315441079e-05,
+      "loss": 0.4289,
+      "step": 35000
+    },
+    {
+      "epoch": 3.05,
+      "eval_loss": 0.4092726707458496,
+      "eval_runtime": 16.8388,
+      "eval_samples_per_second": 296.933,
+      "eval_steps_per_second": 4.692,
+      "step": 35000
     }
   ],
   "max_steps": 100000,
   "num_train_epochs": 9,
-  "total_flos": 1.4129211634244282e+21,
+  "total_flos": 1.648395610407119e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72a1a14ed7bf6bc0725bb876cb7a38064b9cb2a4e01a8c1e6ca520325a13a6e9
+oid sha256:795fa208c4655907c54892ea46d5deef3057c257b0f29b327c60d57aebb752ef
 size 449471589