Training in progress, epoch 3, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8b3014121d2999e58c820537a87f14596d3db178b5b9895693af3ced2922be4
+oid sha256:4a133eb15a2b5d26e2c38a5a0fda62ce4247962f4ed1a4a204e2229947327790
 size 252471152

last-checkpoint/global_step200/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c24d873bd19cf73d89986f9fe6f43f5201bed9743ebffa74cd2a1c4685114de
+size 378676165

last-checkpoint/global_step200/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:e2ffc30065dfddfc4f5cc1d52bed7e843c0b2fafdeab5d469573e0a8376050cc
+size 378676165

last-checkpoint/global_step200/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:dfad9d782d0d4ce6ce59973ccd82305b51b99d2563e16454575125b82b14e303
+size 378676229

last-checkpoint/global_step200/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:a34a383c6da85c1147916ad68d4fd50cab3222b97cea587f8559e076013f61aa
+size 378676229

last-checkpoint/global_step200/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:646ff9316598f39dbe8e757b400a8c8639491d8246432cbfa065c6f1397ae429
+size 453936805

last-checkpoint/latest

@@ -1 +1 @@
-global_step150
+global_step200

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2720f877f6e402f1b7156d32f6307ef276b1a93ab35274f8d5d41a6e896bd89f
+oid sha256:f91bb48f0371a87d6d05b5e2fa5c78832171cb1a5a1f1da749e6f90076b585d3
 size 15429

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5f8a349c7c83469f77b5f348d95944c0c14a9feda17208cb9c267fe0cbf12f6
+oid sha256:a72064d91b87d8dd314aac8fa71e6d4617a8cadc4fdeac7980a01a11509bdd52
 size 15429

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b04dd004f93199c321e12a1f623ece8bcd0a7183a44d55ace3afd5ce248c27d
+oid sha256:10dcbec5bc2953f49fa8a8cf0a4c8a813635e9cd4f8d19de9eee3fa4532f2cd3
 size 15429

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa0b3a7b014f9ed1b37cb5ef6df4bd0840321edf48131dbfdddd7220604874e2
+oid sha256:16180053357b049f5aca90aa1c3a83e63b402df64035877a8e0a42bcf1c728fe
 size 15429

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c30a4dd0cfdb859330b5b6f7e58dd76410ef635bd253f1d8e69255655851e99a
+oid sha256:85be9302f314e558c6f05b96b2aae8dce9eb9e0f05cfdb5da60bc86adc836369
 size 1401

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
   "best_global_step": null,
-  "best_metric": 1.9774006605148315,
+  "best_metric": 1.8936641216278076,
   "best_model_checkpoint": null,
-  "epoch": 2.7777777777777777,
+  "epoch": 3.7037037037037037,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -242,6 +242,84 @@
       "eval_samples_per_second": 404.599,
       "eval_steps_per_second": 3.163,
       "step": 150
+    },
+    {
+      "epoch": 2.8703703703703702,
+      "grad_norm": 0.19505934417247772,
+      "learning_rate": 5.2466760173030665e-06,
+      "loss": 1.937,
+      "step": 155
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": 0.21480995416641235,
+      "learning_rate": 5.417022641241478e-06,
+      "loss": 1.9304,
+      "step": 160
+    },
+    {
+      "epoch": 3.0555555555555554,
+      "grad_norm": 0.18316428363323212,
+      "learning_rate": 5.587369265179889e-06,
+      "loss": 1.8796,
+      "step": 165
+    },
+    {
+      "epoch": 3.148148148148148,
+      "grad_norm": 0.16919249296188354,
+      "learning_rate": 5.757715889118301e-06,
+      "loss": 1.9536,
+      "step": 170
+    },
+    {
+      "epoch": 3.240740740740741,
+      "grad_norm": 0.17040272057056427,
+      "learning_rate": 5.928062513056712e-06,
+      "loss": 1.9335,
+      "step": 175
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.17666751146316528,
+      "learning_rate": 6.098409136995123e-06,
+      "loss": 1.8776,
+      "step": 180
+    },
+    {
+      "epoch": 3.425925925925926,
+      "grad_norm": 0.16416528820991516,
+      "learning_rate": 5.9475616097243135e-06,
+      "loss": 1.8559,
+      "step": 185
+    },
+    {
+      "epoch": 3.5185185185185186,
+      "grad_norm": 0.1508936882019043,
+      "learning_rate": 5.234397783794937e-06,
+      "loss": 1.896,
+      "step": 190
+    },
+    {
+      "epoch": 3.611111111111111,
+      "grad_norm": 0.19308550655841827,
+      "learning_rate": 4.114954812111669e-06,
+      "loss": 1.8197,
+      "step": 195
+    },
+    {
+      "epoch": 3.7037037037037037,
+      "grad_norm": 0.17440949380397797,
+      "learning_rate": 2.7989988732810543e-06,
+      "loss": 1.8662,
+      "step": 200
+    },
+    {
+      "epoch": 3.7037037037037037,
+      "eval_loss": 1.8936641216278076,
+      "eval_runtime": 3.8316,
+      "eval_samples_per_second": 400.615,
+      "eval_steps_per_second": 3.132,
+      "step": 200
     }
   ],
   "logging_steps": 5,
@@ -270,7 +348,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.0756517426823168e+17,
+  "total_flos": 2.747890773566423e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null