Training in progress, step 64, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f93a63e14808f4fb8796bfee59c2aec42f1f763e0b87b6acbad3862d1a89e285
+oid sha256:4c4a5e2add8c903d966ce8710e97157c591e27dae3825fe3c2d2fd8594e8da90
 size 763470136

last-checkpoint/global_step64/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92d59b2ea36fcbff4d400d7a6d97a08df15abb1fab7b3a53ed2baef3e6299c8c
+size 385019984

last-checkpoint/global_step64/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:f6c3dd6b462b8c642ee1dc032673ca7fd8f128abc1b700f29dda8aa369a40818
+size 385019984

last-checkpoint/global_step64/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52640372a5513c97d334e9d46bd8b22c987d408bdea6ba59a8b6d17eba955bf7
+size 385019984

last-checkpoint/global_step64/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e9e1e72911ca34595ce725c2fc34988602b415ae5b8af5cb3a1d60a3f2831af
+size 385019984

last-checkpoint/global_step64/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97ecd7fc3eb06f9aa7e9f6b97eef6fc30a4f2f2a91e0ddfd1c913d72a9cd27ae
+size 385019984

last-checkpoint/global_step64/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:a451857e56e5cc7e85bd127b8dfb9ce06f7b3f0fe96a96812aaaf4bacd3fcc5f
+size 385019984

last-checkpoint/global_step64/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a35e3c42bd7ddb58dbc3918ad0ce08559884e570cdb88a617147d22794ad8fa
+size 348711830

last-checkpoint/global_step64/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb15c1b1563377f8819ab2c2ed488d7121d4550da26be6ab93315c21735e6596
+size 348711830

last-checkpoint/global_step64/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bc34689cd7e6fe48e8b3d60f807a1006b902c0dffc54f9e2f1327cd1819d88d
+size 348711830

last-checkpoint/global_step64/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5812e6507f1ea48112526773e62580fc180d9f08a600a1e87af383479a5ad39
+size 348711830

last-checkpoint/global_step64/zero_pp_rank_4_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a92e1b4608c8d5b0dc90ce6a5566ee2b206227ea1b4e3e2849612c0c0d7cb1c9
+size 348711830

last-checkpoint/global_step64/zero_pp_rank_5_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd60fa3e28ed6e7018ff4254ae6ecb4680c77bc757d5d7b7ae089d5ba3c7eda2
+size 348711830

last-checkpoint/latest

@@ -1 +1 @@
-global_step32
+global_step64

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:209082c7ec67ad2302547279eea5672d76db463111ccc7907295c1dffc2d0554
+oid sha256:c1d2706b93a662ac3d076f62ac0cc0bf9da89b22f28d7aedb79e2d221480bf22
 size 15472

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d63b43a592d0f5adb1c3c42dd2f2a1f20ea2b975ee53d9fb58f4772f27827678
+oid sha256:2e012a473e8960670cde6d00f32b72516b3b678ea6c28d0bc75a8a6872b87726
 size 15472

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:925b0596f22fe033048eb9eed4e0f905f366c896c87135745ca146c4b066c337
+oid sha256:2d15d65d436172526002aa34da5c198ac75a338a871f9c7b229bad29a0998f16
 size 15472

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b80bba3e1b968e7784b8400499fc3f63bae29b9e916fd5a91c5e12d6185561f0
+oid sha256:82fade3599ddd40984f8a744d9e09f0f5ed5dde67c4de699c5efada15e9b546c
 size 15472

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03c4d953a373e811507c90319b24c4bee64215c12d9faaf731e7c5cda0af9ac8
+oid sha256:3553f81d93560a998b742fcb2c39d12dae1b25a8fe484f0f025ea17be9815aeb
 size 15472

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3f12c39d7ff66e2673924cac80d0b7652d34eed1ee692b83e85062c9b8a27a0
+oid sha256:f45b6ba5697e78673c882ff2682372ece017522f58d35821dcf57b76881f3694
 size 15472

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48a6ed7273225f52284b5e3fb6e9946f0660ed9da3208e6da559967a13c51929
+oid sha256:3db122c9205c73d5e7e1d59359a230de2aae1e7f2b50ca89f28123120a2430ad
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2064516129032258,
+  "epoch": 0.4129032258064516,
   "eval_steps": 32,
-  "global_step": 32,
+  "global_step": 64,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,238 @@
       "eval_samples_per_second": 1.622,
       "eval_steps_per_second": 0.065,
       "step": 32
+    },
+    {
+      "epoch": 0.2129032258064516,
+      "grad_norm": 0.44925759222205974,
+      "learning_rate": 4.8993079950479305e-05,
+      "loss": 1.1968,
+      "step": 33
+    },
+    {
+      "epoch": 0.21935483870967742,
+      "grad_norm": 0.4304874702516527,
+      "learning_rate": 4.883361457079673e-05,
+      "loss": 1.1706,
+      "step": 34
+    },
+    {
+      "epoch": 0.22580645161290322,
+      "grad_norm": 0.3646005763538535,
+      "learning_rate": 4.8662765920480274e-05,
+      "loss": 1.2714,
+      "step": 35
+    },
+    {
+      "epoch": 0.23225806451612904,
+      "grad_norm": 0.3568923781906157,
+      "learning_rate": 4.8480625161598e-05,
+      "loss": 1.175,
+      "step": 36
+    },
+    {
+      "epoch": 0.23870967741935484,
+      "grad_norm": 0.37794009122137584,
+      "learning_rate": 4.8287289481503954e-05,
+      "loss": 1.2415,
+      "step": 37
+    },
+    {
+      "epoch": 0.24516129032258063,
+      "grad_norm": 0.35188090283951096,
+      "learning_rate": 4.808286204098047e-05,
+      "loss": 1.3385,
+      "step": 38
+    },
+    {
+      "epoch": 0.25161290322580643,
+      "grad_norm": 0.3863530195041696,
+      "learning_rate": 4.7867451919193346e-05,
+      "loss": 1.2419,
+      "step": 39
+    },
+    {
+      "epoch": 0.25806451612903225,
+      "grad_norm": 0.3746461776891942,
+      "learning_rate": 4.764117405548891e-05,
+      "loss": 1.2624,
+      "step": 40
+    },
+    {
+      "epoch": 0.2645161290322581,
+      "grad_norm": 0.34991236825502203,
+      "learning_rate": 4.740414918806425e-05,
+      "loss": 1.307,
+      "step": 41
+    },
+    {
+      "epoch": 0.2709677419354839,
+      "grad_norm": 0.4011683523629512,
+      "learning_rate": 4.715650378954331e-05,
+      "loss": 1.357,
+      "step": 42
+    },
+    {
+      "epoch": 0.27741935483870966,
+      "grad_norm": 0.3457706023597712,
+      "learning_rate": 4.689836999949314e-05,
+      "loss": 1.3757,
+      "step": 43
+    },
+    {
+      "epoch": 0.2838709677419355,
+      "grad_norm": 0.2938536081434768,
+      "learning_rate": 4.662988555391632e-05,
+      "loss": 1.3486,
+      "step": 44
+    },
+    {
+      "epoch": 0.2903225806451613,
+      "grad_norm": 0.33377012573731674,
+      "learning_rate": 4.635119371175731e-05,
+      "loss": 1.1417,
+      "step": 45
+    },
+    {
+      "epoch": 0.2967741935483871,
+      "grad_norm": 0.5099149644951235,
+      "learning_rate": 4.60624431784618e-05,
+      "loss": 1.2184,
+      "step": 46
+    },
+    {
+      "epoch": 0.3032258064516129,
+      "grad_norm": 0.4651969988328567,
+      "learning_rate": 4.576378802662989e-05,
+      "loss": 1.2518,
+      "step": 47
+    },
+    {
+      "epoch": 0.3096774193548387,
+      "grad_norm": 0.3453144809110264,
+      "learning_rate": 4.5455387613805396e-05,
+      "loss": 1.4111,
+      "step": 48
+    },
+    {
+      "epoch": 0.3161290322580645,
+      "grad_norm": 0.3338451350111794,
+      "learning_rate": 4.513740649744536e-05,
+      "loss": 1.2129,
+      "step": 49
+    },
+    {
+      "epoch": 0.3225806451612903,
+      "grad_norm": 0.36687031408807524,
+      "learning_rate": 4.4810014347114784e-05,
+      "loss": 1.2703,
+      "step": 50
+    },
+    {
+      "epoch": 0.32903225806451614,
+      "grad_norm": 0.38881877032764534,
+      "learning_rate": 4.4473385853953693e-05,
+      "loss": 1.2997,
+      "step": 51
+    },
+    {
+      "epoch": 0.33548387096774196,
+      "grad_norm": 0.34976100346234607,
+      "learning_rate": 4.4127700637464834e-05,
+      "loss": 1.0796,
+      "step": 52
+    },
+    {
+      "epoch": 0.3419354838709677,
+      "grad_norm": 0.3696068140674995,
+      "learning_rate": 4.3773143149671576e-05,
+      "loss": 1.3098,
+      "step": 53
+    },
+    {
+      "epoch": 0.34838709677419355,
+      "grad_norm": 0.3168263761372888,
+      "learning_rate": 4.340990257669732e-05,
+      "loss": 1.2894,
+      "step": 54
+    },
+    {
+      "epoch": 0.3548387096774194,
+      "grad_norm": 0.3442048604805361,
+      "learning_rate": 4.303817273781886e-05,
+      "loss": 1.3385,
+      "step": 55
+    },
+    {
+      "epoch": 0.36129032258064514,
+      "grad_norm": 0.38003699951922426,
+      "learning_rate": 4.2658151982047536e-05,
+      "loss": 1.2548,
+      "step": 56
+    },
+    {
+      "epoch": 0.36774193548387096,
+      "grad_norm": 0.5065610455915895,
+      "learning_rate": 4.2270043082293463e-05,
+      "loss": 1.2496,
+      "step": 57
+    },
+    {
+      "epoch": 0.3741935483870968,
+      "grad_norm": 0.3259412922642011,
+      "learning_rate": 4.1874053127169126e-05,
+      "loss": 1.1696,
+      "step": 58
+    },
+    {
+      "epoch": 0.38064516129032255,
+      "grad_norm": 0.33390560015814696,
+      "learning_rate": 4.147039341049036e-05,
+      "loss": 1.3276,
+      "step": 59
+    },
+    {
+      "epoch": 0.3870967741935484,
+      "grad_norm": 0.3161062426181486,
+      "learning_rate": 4.105927931853327e-05,
+      "loss": 1.258,
+      "step": 60
+    },
+    {
+      "epoch": 0.3935483870967742,
+      "grad_norm": 0.37939625630824414,
+      "learning_rate": 4.0640930215107725e-05,
+      "loss": 1.3119,
+      "step": 61
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.3447410882628537,
+      "learning_rate": 4.021556932450832e-05,
+      "loss": 1.1337,
+      "step": 62
+    },
+    {
+      "epoch": 0.4064516129032258,
+      "grad_norm": 0.33262503192755777,
+      "learning_rate": 3.978342361240553e-05,
+      "loss": 1.3684,
+      "step": 63
+    },
+    {
+      "epoch": 0.4129032258064516,
+      "grad_norm": 0.4082167906853653,
+      "learning_rate": 3.9344723664740506e-05,
+      "loss": 1.1973,
+      "step": 64
+    },
+    {
+      "epoch": 0.4129032258064516,
+      "eval_loss": 1.0707180500030518,
+      "eval_runtime": 62.1751,
+      "eval_samples_per_second": 1.608,
+      "eval_steps_per_second": 0.064,
+      "step": 64
     }
   ],
   "logging_steps": 1,
@@ -266,7 +498,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 65519726100480.0,
+  "total_flos": 131039452200960.0,
   "train_batch_size": 5,
   "trial_name": null,
   "trial_params": null