Training in progress, step 384, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:049ec0ada0813997e586979480e5c26282234a3e55448657344416c90be4b443
+oid sha256:828e147d9ff7975c4ca7c16170146341a6a759ca1f988565f9e589d2342596e7
 size 550593856

last-checkpoint/global_step384/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f8f60cdf5cebb4daa2f28f924d5c9318b3777550815a0ba772278ef5535d933
+size 243591168

last-checkpoint/global_step384/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:844f1851799e607c6ad4d775043828dc2f91b441207d791befa00fb241d1d1d1
+size 243591168

last-checkpoint/global_step384/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a1e584f2e224ec2d8f3d405c1d312fdfc47b25c276fbcf4eaee3afa5d987046
+size 243591168

last-checkpoint/global_step384/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9fad8287caeaa77d0ff5f44667b715f08908d365e038e733623a2ff6022f47b
+size 243591168

last-checkpoint/global_step384/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37048fdc490efbb022bf06314e1894edff374a7f2abba775f59ab786ba8f836f
+size 243591168

last-checkpoint/global_step384/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fe4faad056364943f3e792c90d82e5b07076b53da596716271de53bd331fd0f
+size 243591168

last-checkpoint/global_step384/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:968d8da0a6beb74a1df7b2691968c7454779920a8c3221bb09c9816d338b4771
+size 243591168

last-checkpoint/global_step384/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e48b6d107738efb23d8b852cd0af0a2d023774fbddf1701a9de926df2cc894de
+size 243591168

last-checkpoint/global_step384/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0914c773585179b34764f2673fc67e49623cdd6822a6d8ec833c94a3423428aa
+size 211435686

last-checkpoint/global_step384/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b778bda5eacb772d5df0240212b9044f6f244f394acfab72de78de9975bb909
+size 211435686

last-checkpoint/global_step384/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b206a7c3fa96d0e6709760946ef32bbdff70be3c8a2a0ec9535d79279fb2c55
+size 211435686

last-checkpoint/global_step384/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48effcfd8c2b0a240bfd246675fa4a91f0a902ab85b70fe66f696e3cce72375d
+size 211435686

last-checkpoint/global_step384/zero_pp_rank_4_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5220a261af9a068f3fab41351433fdfc667efd51f1979926167c85889b90a0
+size 211435686

last-checkpoint/global_step384/zero_pp_rank_5_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2181df8b256ef1dfeb6d295701ed0622d0093a8769b287ff9ee7b114523ee9a
+size 211435686

last-checkpoint/global_step384/zero_pp_rank_6_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b9ae0e0c8c98cf4c1ffb9db17ed41419c57d6454cb5c1d5cf66b762cf98a86e
+size 211435686

last-checkpoint/global_step384/zero_pp_rank_7_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6561b825f679c503e6a2afea2e51d929d33613f2e4c7392df0b08575068c90ca
+size 211435686

last-checkpoint/latest

@@ -1 +1 @@
-global_step351
+global_step384

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fec0d859a8870bb3863562a0fbaa6ebb33536c9a365b6abc0e8f09aacd3377c
+oid sha256:58ef1ab595d05fdcb3a0f87e7a491ca7682d5949ef8b0cbdedbf09bf8ed365a4
 size 15920

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:212dc5192b40486002c7fe7e08f770847069213c90b44b8eeb5c8c552aa09d2d
+oid sha256:caddd1ed4e1057c456fac63072b0c612a6f306480858eb596ab6dd3fe30a1182
 size 15920

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef0f0879c31278fe1422ca799f1e946f52627895e6b6b450451e9b838670c583
+oid sha256:0b20c72304878735b6ef72d389e6b3baf3f585d11a83f82a05bbe943f2cb45ed
 size 15920

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66c283d16fff6ad5c32bb8063ebb0876ab2d3331a701287a5518f6611da12f69
+oid sha256:c9da521bf7f407fc83ada516499e58838cbeaa21ed14e1017b59a2027e1b6412
 size 15920

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d45b771d912fd42fd57bf4de4aad3e9035242ea784f2ed87aba4c621e5cd51a
+oid sha256:d100c791f147455c9629cfb40b4b4f249844a25d6f2eb446a9e4f8b3fcd45fc8
 size 15920

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5016a6096b206da65160f901789323144aa46e697f4c7af7e972b16bb657ce2c
+oid sha256:98bb3946a7aa42bfd85cf5de7aa4d59dcae0fbaaee932e73a3cd6d0b02a487b4
 size 15920

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b70b7d3a0a245937c94c1dfab4a674840cffae712e68cd2ec85b8111cd19b6ae
+oid sha256:09dbc1442190c2bd85ae2e07a2140c70024d933bd92a92b55672e8cba2fc8ad4
 size 15920

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:894e3dc130b31d1ff09091d3fba8c4756c7829f76a26489876f6acf7ddf58730
+oid sha256:9713ea8276ee3c304acb4a6c1c3f39b86b13faba6b17609fddc996c3bf4350a0
 size 15920

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77a901e68fe508c580838a0a83e25dcc491921acb23119eaf14194c3e5bc3346
+oid sha256:fb2118b619b8caea9c3657ac3db8db82c41ee9a909354d950dc1bb914eb2c8f3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9140625,
+  "epoch": 1.0,
   "eval_steps": 39,
-  "global_step": 351,
+  "global_step": 384,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2544,6 +2544,237 @@
       "eval_samples_per_second": 1.228,
       "eval_steps_per_second": 0.154,
       "step": 351
+    },
+    {
+      "epoch": 0.9166666666666666,
+      "grad_norm": 0.17312639183632889,
+      "learning_rate": 1.1705364107037981e-05,
+      "loss": 2.4481,
+      "step": 352
+    },
+    {
+      "epoch": 0.9192708333333334,
+      "grad_norm": 0.17233940633090827,
+      "learning_rate": 1.1601071028553371e-05,
+      "loss": 2.4747,
+      "step": 353
+    },
+    {
+      "epoch": 0.921875,
+      "grad_norm": 0.13057391845213812,
+      "learning_rate": 1.1500010708805123e-05,
+      "loss": 2.3276,
+      "step": 354
+    },
+    {
+      "epoch": 0.9244791666666666,
+      "grad_norm": 0.15218005054913405,
+      "learning_rate": 1.1402190675712448e-05,
+      "loss": 2.4584,
+      "step": 355
+    },
+    {
+      "epoch": 0.9270833333333334,
+      "grad_norm": 0.1405908251620449,
+      "learning_rate": 1.130761821582766e-05,
+      "loss": 2.3576,
+      "step": 356
+    },
+    {
+      "epoch": 0.9296875,
+      "grad_norm": 0.15487043477366738,
+      "learning_rate": 1.1216300373793417e-05,
+      "loss": 2.3773,
+      "step": 357
+    },
+    {
+      "epoch": 0.9322916666666666,
+      "grad_norm": 0.15092606814376955,
+      "learning_rate": 1.1128243951817937e-05,
+      "loss": 2.2986,
+      "step": 358
+    },
+    {
+      "epoch": 0.9348958333333334,
+      "grad_norm": 0.1484173556255145,
+      "learning_rate": 1.1043455509168339e-05,
+      "loss": 2.2237,
+      "step": 359
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 0.14235753907847776,
+      "learning_rate": 1.0961941361682013e-05,
+      "loss": 2.4375,
+      "step": 360
+    },
+    {
+      "epoch": 0.9401041666666666,
+      "grad_norm": 0.14142558045399545,
+      "learning_rate": 1.0883707581296196e-05,
+      "loss": 2.5165,
+      "step": 361
+    },
+    {
+      "epoch": 0.9427083333333334,
+      "grad_norm": 0.13890140092039985,
+      "learning_rate": 1.080875999559564e-05,
+      "loss": 2.477,
+      "step": 362
+    },
+    {
+      "epoch": 0.9453125,
+      "grad_norm": 0.149033997441562,
+      "learning_rate": 1.0737104187378542e-05,
+      "loss": 2.386,
+      "step": 363
+    },
+    {
+      "epoch": 0.9479166666666666,
+      "grad_norm": 0.15829792856388608,
+      "learning_rate": 1.066874549424068e-05,
+      "loss": 2.2997,
+      "step": 364
+    },
+    {
+      "epoch": 0.9505208333333334,
+      "grad_norm": 0.14793151985278888,
+      "learning_rate": 1.0603689008177822e-05,
+      "loss": 2.4599,
+      "step": 365
+    },
+    {
+      "epoch": 0.953125,
+      "grad_norm": 0.1556260763161562,
+      "learning_rate": 1.0541939575206412e-05,
+      "loss": 2.2611,
+      "step": 366
+    },
+    {
+      "epoch": 0.9557291666666666,
+      "grad_norm": 0.16684067808748887,
+      "learning_rate": 1.0483501795002612e-05,
+      "loss": 2.4216,
+      "step": 367
+    },
+    {
+      "epoch": 0.9583333333333334,
+      "grad_norm": 0.14213262998853762,
+      "learning_rate": 1.0428380020559658e-05,
+      "loss": 2.4624,
+      "step": 368
+    },
+    {
+      "epoch": 0.9609375,
+      "grad_norm": 0.16542015576320396,
+      "learning_rate": 1.0376578357863627e-05,
+      "loss": 2.087,
+      "step": 369
+    },
+    {
+      "epoch": 0.9635416666666666,
+      "grad_norm": 0.16312011726686781,
+      "learning_rate": 1.0328100665587574e-05,
+      "loss": 2.3865,
+      "step": 370
+    },
+    {
+      "epoch": 0.9661458333333334,
+      "grad_norm": 0.14758591702174165,
+      "learning_rate": 1.0282950554804085e-05,
+      "loss": 2.3726,
+      "step": 371
+    },
+    {
+      "epoch": 0.96875,
+      "grad_norm": 0.1316294327416778,
+      "learning_rate": 1.0241131388716332e-05,
+      "loss": 2.4155,
+      "step": 372
+    },
+    {
+      "epoch": 0.9713541666666666,
+      "grad_norm": 0.14988844894688882,
+      "learning_rate": 1.0202646282407505e-05,
+      "loss": 2.3134,
+      "step": 373
+    },
+    {
+      "epoch": 0.9739583333333334,
+      "grad_norm": 0.16468705638317635,
+      "learning_rate": 1.016749810260881e-05,
+      "loss": 2.3345,
+      "step": 374
+    },
+    {
+      "epoch": 0.9765625,
+      "grad_norm": 0.16639080943133064,
+      "learning_rate": 1.01356894674859e-05,
+      "loss": 2.1808,
+      "step": 375
+    },
+    {
+      "epoch": 0.9791666666666666,
+      "grad_norm": 0.1537739755991523,
+      "learning_rate": 1.0107222746443862e-05,
+      "loss": 2.3806,
+      "step": 376
+    },
+    {
+      "epoch": 0.9817708333333334,
+      "grad_norm": 0.1582641580303379,
+      "learning_rate": 1.0082100059950713e-05,
+      "loss": 2.4064,
+      "step": 377
+    },
+    {
+      "epoch": 0.984375,
+      "grad_norm": 0.16490051463401306,
+      "learning_rate": 1.0060323279379476e-05,
+      "loss": 2.3932,
+      "step": 378
+    },
+    {
+      "epoch": 0.9869791666666666,
+      "grad_norm": 0.14677990127698765,
+      "learning_rate": 1.0041894026868732e-05,
+      "loss": 2.3932,
+      "step": 379
+    },
+    {
+      "epoch": 0.9895833333333334,
+      "grad_norm": 0.17686734833911588,
+      "learning_rate": 1.0026813675201832e-05,
+      "loss": 2.2527,
+      "step": 380
+    },
+    {
+      "epoch": 0.9921875,
+      "grad_norm": 0.15542797613175577,
+      "learning_rate": 1.0015083347704623e-05,
+      "loss": 2.4111,
+      "step": 381
+    },
+    {
+      "epoch": 0.9947916666666666,
+      "grad_norm": 0.1559166935312072,
+      "learning_rate": 1.0006703918161775e-05,
+      "loss": 2.4522,
+      "step": 382
+    },
+    {
+      "epoch": 0.9973958333333334,
+      "grad_norm": 0.14284208961058514,
+      "learning_rate": 1.000167601075169e-05,
+      "loss": 2.3575,
+      "step": 383
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.14031951339304571,
+      "learning_rate": 1e-05,
+      "loss": 2.3152,
+      "step": 384
     }
   ],
   "logging_steps": 1,
@@ -2558,12 +2789,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 116032970686464.0,
+  "total_flos": 126942053400576.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null