Training in progress, step 5000, checkpoint

last-checkpoint/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d78c12c945e5fcb9c639c770a4e4f00430ece4b7fb6cb44feb0d796c2c4df01
+oid sha256:ffbc24d23529af8af58002eafbfdb64c2a781bf66b0719975cfff0945fd2ff68
 size 19744138

last-checkpoint/global_step5000/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b72cafcd98a035b2a3b5a61d62d3e4f3f83f0aeabd67ddc6bd9f4035c3bbf585
+size 6508458036

last-checkpoint/global_step5000/zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b29ae6ff817af5ebb5e83e17100d02cef546f6f622fc1b7eedac4fb34aed11bd
+size 29495149

last-checkpoint/global_step5000/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b2d361ec26a001dc6db84b60aa6477bcc988754b718ff8016a7fa57622c48dc
+size 6508458036

last-checkpoint/global_step5000/zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b59806db956177a4b1672e76efb1ff9ede774c227ed9037dde44000da15ebf7
+size 29495149

last-checkpoint/global_step5000/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57ae99b71628000244c5471c84eb4a5b785cc97d8a51db8a4abb85674d9b3477
+size 6508458036

last-checkpoint/global_step5000/zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a45d35aea5ce3610a047a969a6a855504aeac3fdcb34d14405a5e22e00979b2a
+size 29495149

last-checkpoint/global_step5000/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47c29d23a8de4915647e2d9db13464e39fc71d866d477be37a86b5728a0d87ad
+size 6508458036

last-checkpoint/global_step5000/zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba461e42a784b1b9e5809cf90e977fcff7a4d3819162223c50a1d1c46222d463
+size 29495149

last-checkpoint/latest

@@ -1 +1 @@
-global_step4500
+global_step5000

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94222b0d851841afa61b6aafcea0bff04917dffca319ac60be1b7888470e4549
+oid sha256:856870ac2f25ace5a84f27e317129901b4ed17c9dc7320e4029c4b82423d5656
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eb7e27f4429243bc102257eec60825acb13cbb47a2667ad973c02b4b2dc57aa
+oid sha256:ab79bc6f0461a8e513578650799fc17047d99f83ccbabaf66e937b791f79620d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0caa8a8996d3cb7ae233c1902bff89eb356bf1170533c424be993eaf5748b7e9
+oid sha256:ca99fcf04653e8f1e27181a35aa710186a4259c4b45f8b79ef9c5ed1e4d100e2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cafc79dc7941f6eb3a98f0b8b14f36db6f3be67545040d9683537528c3545459
+oid sha256:01cbaf32cc3aaa1caa94c373857611f4262dec7a3d93ef26de5cde9cffbb4972
 size 15024

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.897133220910624,
+  "epoch": 2.1079258010118043,
   "eval_steps": 500,
-  "global_step": 4500,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2707,13 +2707,313 @@
       "learning_rate": 1e-05,
       "loss": 0.6637,
       "step": 4500
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1e-05,
+      "loss": 0.6336,
+      "step": 4510
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1e-05,
+      "loss": 0.7105,
+      "step": 4520
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1e-05,
+      "loss": 0.6647,
+      "step": 4530
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1e-05,
+      "loss": 0.6898,
+      "step": 4540
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1e-05,
+      "loss": 0.6854,
+      "step": 4550
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1e-05,
+      "loss": 0.6788,
+      "step": 4560
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1e-05,
+      "loss": 0.6794,
+      "step": 4570
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1e-05,
+      "loss": 0.6683,
+      "step": 4580
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1e-05,
+      "loss": 0.641,
+      "step": 4590
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1e-05,
+      "loss": 0.6193,
+      "step": 4600
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1e-05,
+      "loss": 0.7397,
+      "step": 4610
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1e-05,
+      "loss": 0.6435,
+      "step": 4620
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1e-05,
+      "loss": 0.6489,
+      "step": 4630
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1e-05,
+      "loss": 0.622,
+      "step": 4640
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1e-05,
+      "loss": 0.6476,
+      "step": 4650
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1e-05,
+      "loss": 0.6058,
+      "step": 4660
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 1e-05,
+      "loss": 0.6626,
+      "step": 4670
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 1e-05,
+      "loss": 0.6546,
+      "step": 4680
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1e-05,
+      "loss": 0.6935,
+      "step": 4690
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1e-05,
+      "loss": 0.6579,
+      "step": 4700
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1e-05,
+      "loss": 0.6239,
+      "step": 4710
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1e-05,
+      "loss": 0.6109,
+      "step": 4720
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1e-05,
+      "loss": 0.6751,
+      "step": 4730
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1e-05,
+      "loss": 0.6457,
+      "step": 4740
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1e-05,
+      "loss": 0.6619,
+      "step": 4750
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 1e-05,
+      "loss": 0.6195,
+      "step": 4760
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 1e-05,
+      "loss": 0.6394,
+      "step": 4770
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 1e-05,
+      "loss": 0.6168,
+      "step": 4780
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 1e-05,
+      "loss": 0.6742,
+      "step": 4790
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 1e-05,
+      "loss": 0.6864,
+      "step": 4800
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 1e-05,
+      "loss": 0.6678,
+      "step": 4810
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 1e-05,
+      "loss": 0.6452,
+      "step": 4820
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 1e-05,
+      "loss": 0.6478,
+      "step": 4830
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 1e-05,
+      "loss": 0.6388,
+      "step": 4840
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 1e-05,
+      "loss": 0.7307,
+      "step": 4850
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1e-05,
+      "loss": 0.6212,
+      "step": 4860
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1e-05,
+      "loss": 0.6104,
+      "step": 4870
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 1e-05,
+      "loss": 0.6343,
+      "step": 4880
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 1e-05,
+      "loss": 0.564,
+      "step": 4890
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 1e-05,
+      "loss": 0.6071,
+      "step": 4900
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 1e-05,
+      "loss": 0.6524,
+      "step": 4910
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 1e-05,
+      "loss": 0.6491,
+      "step": 4920
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 1e-05,
+      "loss": 0.6814,
+      "step": 4930
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 1e-05,
+      "loss": 0.6735,
+      "step": 4940
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 1e-05,
+      "loss": 0.6388,
+      "step": 4950
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 1e-05,
+      "loss": 0.6337,
+      "step": 4960
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 1e-05,
+      "loss": 0.6233,
+      "step": 4970
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 1e-05,
+      "loss": 0.5838,
+      "step": 4980
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 1e-05,
+      "loss": 0.5723,
+      "step": 4990
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 1e-05,
+      "loss": 0.5832,
+      "step": 5000
     }
   ],
   "logging_steps": 10,
   "max_steps": 5000,
   "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 1131517606625280.0,
+  "total_flos": 1257157857116160.0,
   "trial_name": null,
   "trial_params": null
 }