Training in progress, step 2500, checkpoint

last-checkpoint/global_step2500/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0778872ba3a3b2838dbb6059a85d9cf106f5e30d9c995febfa18cecd2708d1cf
+size 77125

last-checkpoint/global_step2500/zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80f002e2c45336cf148722e1664647ddf9685a243a713a1ae9ccc747ae4bcdab
+size 181523565

last-checkpoint/global_step2500/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a2619140c44e72108a6b99c86b4a357f5116a31e04a9991e21bed934948b801
+size 76997

last-checkpoint/global_step2500/zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b0136ed43d1d8b3edb63882e832e4e1a7de6ad5e02eaac692aa2652ca0bacde
+size 181523565

last-checkpoint/global_step2500/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bdefcd3f3bf9c2535c5c417662abe5e951214e4080a08bcfa629c44cbb84595
+size 76997

last-checkpoint/global_step2500/zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2059843e7d77d4449b407d0ac6a2cff3d4012f0d9fd3f671a31fdee32d040612
+size 181523565

last-checkpoint/global_step2500/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f45673134f2666e936895060472a512546b53dd5515da1b41d6221efed09d08f
+size 76997

last-checkpoint/global_step2500/zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54d035b95ec7fd6a7d4b5d5771556825209b53f6205aaf9247d9c2254ff6fef4
+size 181523565

last-checkpoint/latest

@@ -1 +1 @@
-global_step2000
+global_step2500

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17769a6403d15a70cb9712603c4ec5dd4be70332def23aa0b13ea3bda8a1a7a1
+oid sha256:3e900f2592c656975f9b9d90061c0ece3aeaa6ac10bfa8b689c5c752e0e1b22b
 size 242070038

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9f6b0d8f8f3c7c672a3e4ec564e590a67d25f6a49a376b2b9d0d8236bb5ca89
+oid sha256:70b1fee1a60477fdfb37fe442104a5be1d94b9aa2faa90b681407bb84aa0b5b6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:077d38406025d335a1423c2a3b5123be5c0cbb86249376bb98772d98985b4106
+oid sha256:d58ce42605b8fed10a20d163f8befeb1455bc204e34fdb098df937a29c667f0f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86e2e9b2214a9712f049f41b02d665d19d9548d57de7aee006787e9507288ac8
+oid sha256:0469f49ee1a31e6c95bee835b8fd70a89c1c7492a85f2a3e27479d0023352b45
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bb3902c2fcdb3573e92153da7d553c4d6b893a789269e48961d6e7c05faeacc
+oid sha256:60b3ac292cfaee329c617a744e6a245f290a629973a48a421885f424abc14c41
 size 15024

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.0,
+  "epoch": 10.0,
   "eval_steps": 500,
-  "global_step": 2000,
+  "global_step": 2500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -31,13 +31,19 @@
       "learning_rate": 0.01,
       "loss": 0.1537,
       "step": 2000
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.01,
+      "loss": 0.1332,
+      "step": 2500
     }
   ],
   "logging_steps": 500,
   "max_steps": 2500,
   "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 338064310272.0,
+  "total_flos": 422580387840.0,
   "trial_name": null,
   "trial_params": null
 }