Training in progress, step 13000, checkpoint

last-checkpoint/global_step13000/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:488e228a4503b07d31600c6fc34d9e4dcdfd1c0edb8df30951259cd70f4dea95
+size 197282509

last-checkpoint/global_step13000/zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21a074cab7f4520aba1bea822b4c6eb2ae78325b72b358f571cfa3c79f427b32
+size 180416968

last-checkpoint/global_step13000/zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03abd228e691df8ea298ffd419a6085a310407b622086d5974736842ba1d68b2
+size 180416776

last-checkpoint/global_step13000/zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f473e4454c8b2f6c226ae1a052b478582b28329176ed7d40ad1c13f9e1fb9ac
+size 180416776

last-checkpoint/global_step13000/zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97fafb51040b95e8722f698a7d6c7c96f8ef343ef342b31dbf024b985a4d0203
+size 180416904

last-checkpoint/global_step13000/zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ae77d6243abc24f502e84a7dfa974bfd534e8e0e2e6092cca1c86d331a92feb
+size 180416712

last-checkpoint/global_step13000/zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2731373ed333090d33307845614de0ceb7c4801994bb510d9b7d314c9ba9c3fc
+size 180417096

last-checkpoint/latest

@@ -1 +1 @@
-global_step12500
+global_step13000

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24b88f70912df99acfaa93c847d111588238f2f3c89f9126b68e97bd70f7fbb5
+oid sha256:cb3a1e9e47c99adfe500fb835894520b7c059723ec12d0b5c3b213b5abcd1317
 size 188836816

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:271c89ce6ee409be2ea9aa3bf701ff66e7a7cb9264b73eefc11e757372a91e5e
-size 15472
+oid sha256:7d04a169cf2982f509d1e70c2875d15850c8a295df9d25a10583af4a6620aace
+size 15536

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41eea4946eeaa383e314ebd734ddda2972689f784d350627374fb05cf2b160ab
+oid sha256:7b392962a432829581445eb66569f5c253a5f4402091ee1c888360756bf75dba
 size 15536

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eccd0e35b1a3fb6b4961836705b55374915efc0fe4aa8bbcd2fcc5652edb5192
-size 15472
+oid sha256:5b512900906613ef0f04eb73d34400f97b08f4c039321f9ac221708eace092d8
+size 15536

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1155b24d828f1b4cc9581115f945c46af6cafa8b0dcd3abce9639d3f64bf6fa7
+oid sha256:53ccb60fcf3ca7eceb0b80ebe18f98c61dcbc16cbd901ff799879f93c2f7b2fa
 size 15472

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d24951e84bf84c9244c0763d9d797270b2b1f7662cfade2d3d2824db197031c1
-size 15472
+oid sha256:321ef3d7319f595a979f92a4d5a2b22f67d7151d29d806ac21b6aa5bf1526b12
+size 15536

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baa66995193ecfcc4672c56a227acadd5b4de025d048272586e219600d9fb650
+oid sha256:c6f029978317513a75b132acfe770e4407b66033b569f2b348840dd418eb9ad3
 size 15472

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f500d7068793f6d489446a9d3939e8a5fbc68fd372f8eeb2605b20dd2e2ab5a
+oid sha256:8622d057215dd0c5696157bc814be5556499cc78ff660d38a4b53b41d24eea4d
 size 1256

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 337.8378378378378,
+  "epoch": 351.35135135135135,
   "eval_steps": 1500,
-  "global_step": 12500,
+  "global_step": 13000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1820,6 +1820,76 @@
       "learning_rate": 0.0001,
       "loss": 0.0153,
       "step": 12500
+    },
+    {
+      "epoch": 339.18918918918916,
+      "grad_norm": 0.2785622179508209,
+      "learning_rate": 0.0001,
+      "loss": 0.0152,
+      "step": 12550
+    },
+    {
+      "epoch": 340.5405405405405,
+      "grad_norm": 0.25130748748779297,
+      "learning_rate": 0.0001,
+      "loss": 0.0148,
+      "step": 12600
+    },
+    {
+      "epoch": 341.8918918918919,
+      "grad_norm": 0.3330935835838318,
+      "learning_rate": 0.0001,
+      "loss": 0.0147,
+      "step": 12650
+    },
+    {
+      "epoch": 343.2432432432432,
+      "grad_norm": 0.2657862901687622,
+      "learning_rate": 0.0001,
+      "loss": 0.0156,
+      "step": 12700
+    },
+    {
+      "epoch": 344.5945945945946,
+      "grad_norm": 0.3090120553970337,
+      "learning_rate": 0.0001,
+      "loss": 0.0145,
+      "step": 12750
+    },
+    {
+      "epoch": 345.94594594594594,
+      "grad_norm": 0.31333035230636597,
+      "learning_rate": 0.0001,
+      "loss": 0.0137,
+      "step": 12800
+    },
+    {
+      "epoch": 347.2972972972973,
+      "grad_norm": 0.33461394906044006,
+      "learning_rate": 0.0001,
+      "loss": 0.0139,
+      "step": 12850
+    },
+    {
+      "epoch": 348.64864864864865,
+      "grad_norm": 0.21069389581680298,
+      "learning_rate": 0.0001,
+      "loss": 0.0138,
+      "step": 12900
+    },
+    {
+      "epoch": 350.0,
+      "grad_norm": 0.23119139671325684,
+      "learning_rate": 0.0001,
+      "loss": 0.0142,
+      "step": 12950
+    },
+    {
+      "epoch": 351.35135135135135,
+      "grad_norm": 0.23619785904884338,
+      "learning_rate": 0.0001,
+      "loss": 0.0131,
+      "step": 13000
     }
   ],
   "logging_steps": 50,
@@ -1839,7 +1909,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.5089183189071246e+20,
+  "total_flos": 3.649166002320069e+20,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null