Training in progress, step 66288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4df6baefe0df3845a28abe9fc6e812fd755b1eb716adddecc1deedd7aca8278d
-size 2401461253
+oid sha256:f2992361efcf4770d4c6602bb67d93320a187287e7fc6dc44519cbf03c5dd8d1
+size 2401461637

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:612baa21561bf04530d6eb5804833e6f0b56599c78fd0a39bacd3ac335e650d3
+oid sha256:b4071ac5bc82e1943cce385333b946af39ce630c568c0ddebfc504245d7448e1
 size 1200739717

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:274f4675622b5854821912e67212d43584ebb6ec4a78ba0fa35ff9cd87e972c2
+oid sha256:e52dd293318f93d0d24ab2680c6a46204bbcb9dee0ba0954189329cd5f7d5e2e
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b09dba34704dde96f55673b0cc5c41d0a0ce45d83ad2015625ba94df43f96a45
+oid sha256:3c0312d2c26f50db24e7fa24aa7f3be59f0d2b84dcf88829a4f490d4d99de93a
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8217547826604386,
-  "global_step": 55240,
+  "epoch": 0.9861057391925263,
+  "global_step": 66288,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -666,11 +666,143 @@
       "learning_rate": 1.4545436513839717e-05,
       "loss": 3.0787,
       "step": 55000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4495849573056442e-05,
+      "loss": 3.0755,
+      "step": 55500
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4446262632273165e-05,
+      "loss": 3.066,
+      "step": 56000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.439667569148989e-05,
+      "loss": 3.0695,
+      "step": 56500
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.4347088750706615e-05,
+      "loss": 3.059,
+      "step": 57000
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.429750180992334e-05,
+      "loss": 3.0628,
+      "step": 57500
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.4247914869140065e-05,
+      "loss": 3.0733,
+      "step": 58000
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.419832792835679e-05,
+      "loss": 3.0591,
+      "step": 58500
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.4148740987573514e-05,
+      "loss": 3.0468,
+      "step": 59000
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.4099154046790237e-05,
+      "loss": 3.0265,
+      "step": 59500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.4049567106006963e-05,
+      "loss": 3.0282,
+      "step": 60000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.3999980165223688e-05,
+      "loss": 3.0222,
+      "step": 60500
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.3950393224440413e-05,
+      "loss": 3.0275,
+      "step": 61000
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.3900806283657138e-05,
+      "loss": 3.0277,
+      "step": 61500
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.3851219342873862e-05,
+      "loss": 3.0551,
+      "step": 62000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.3801632402090585e-05,
+      "loss": 3.0205,
+      "step": 62500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.375204546130731e-05,
+      "loss": 3.023,
+      "step": 63000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.3702458520524036e-05,
+      "loss": 3.0244,
+      "step": 63500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.365287157974076e-05,
+      "loss": 3.0116,
+      "step": 64000
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.3603284638957486e-05,
+      "loss": 3.0141,
+      "step": 64500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.355369769817421e-05,
+      "loss": 3.0284,
+      "step": 65000
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.3504110757390933e-05,
+      "loss": 3.0236,
+      "step": 65500
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.3454523816607659e-05,
+      "loss": 3.013,
+      "step": 66000
     }
   ],
   "max_steps": 201666,
   "num_train_epochs": 3,
-  "total_flos": 6.497219068615066e+16,
+  "total_flos": 7.793968305851597e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:612baa21561bf04530d6eb5804833e6f0b56599c78fd0a39bacd3ac335e650d3
+oid sha256:b4071ac5bc82e1943cce385333b946af39ce630c568c0ddebfc504245d7448e1
 size 1200739717

runs/Feb07_05-04-07_5214b674e698/events.out.tfevents.1675746342.5214b674e698.342.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b5afd134e7190bfca227464f177ede39b4d5a435161a2a45582286c96ae5885
-size 21621
+oid sha256:16d94d99a4243783f2c4751209b7f4a0753cff0f06dbbcb869acc91381ecb224
+size 25141