Training in progress, step 310000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e419578f524e1611c3d5902d97ccf8efc92603d3b33f13949516891bb5476e00
+oid sha256:588b078274eaf2af1b331e1cd70a9be61bfe018939162cd4041561fac059b8c0
 size 893441530

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3926e99c54fb7c961027b62d11498ced043c43266a692f441538601c7a5f10f7
+oid sha256:f9ba1aac81f5af9078e69f687c5c373f267f4525e96f7d4ff79814a56c1216cb
 size 454197066

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c42cb907bbd858ffd2b5bae4767d672ae3b753bd7ac85cb51990a0992d4df69a
-size 14308
+oid sha256:f1483cb709e4146d94296c64449eb045d3f6821657b2815235b2d1e5f2c693e9
+size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08b25c62270eb67709cff9418808f83a4a7710e7ce508a964ce593dde6417e23
+oid sha256:746b61609316d06785a028aa9340563cf7c6dcbeb2edf456b62699aedb8c3a07
 size 1064

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3,
-  "global_step": 300000,
+  "epoch": 0.31,
+  "global_step": 310000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2226,11 +2226,85 @@
       "eval_samples_per_second": 108.487,
       "eval_steps_per_second": 13.561,
       "step": 300000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.732744634202854e-05,
+      "loss": 0.3579,
+      "step": 301000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.731675352071429e-05,
+      "loss": 0.3569,
+      "step": 302000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.7306028528854846e-05,
+      "loss": 0.3561,
+      "step": 303000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.7295271483737004e-05,
+      "loss": 0.3563,
+      "step": 304000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.7284482502998086e-05,
+      "loss": 0.3567,
+      "step": 305000
+    },
+    {
+      "epoch": 0.3,
+      "eval_runtime": 3353.5685,
+      "eval_samples_per_second": 101.281,
+      "eval_steps_per_second": 12.66,
+      "step": 305000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.7273661704624656e-05,
+      "loss": 0.3559,
+      "step": 306000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.7262809206951228e-05,
+      "loss": 0.355,
+      "step": 307000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.725192512865898e-05,
+      "loss": 0.3576,
+      "step": 308000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.7241009588774453e-05,
+      "loss": 0.3555,
+      "step": 309000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.7230062706668237e-05,
+      "loss": 0.3523,
+      "step": 310000
+    },
+    {
+      "epoch": 0.31,
+      "eval_runtime": 3333.1448,
+      "eval_samples_per_second": 101.901,
+      "eval_steps_per_second": 12.738,
+      "step": 310000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 9223372036854775807,
-  "total_flos": 2.656383051969331e+21,
+  "total_flos": 2.744929153701642e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3926e99c54fb7c961027b62d11498ced043c43266a692f441538601c7a5f10f7
+oid sha256:f9ba1aac81f5af9078e69f687c5c373f267f4525e96f7d4ff79814a56c1216cb
 size 454197066