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:d3d3618a6549bfada4acfab50184a00e8169ef527f9fd2d6299b8877447758cb
+oid sha256:a31cb8fd392f2131e4bf934e5cfc6c725cef9d5daaa800fec946c0c6bb095c87
 size 98088784

last-checkpoint/global_step3151/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19fed4d1e68e884c33108eb4a6d195216062c7261df3be3f1284ee1dfa7f661b
+size 73939813

last-checkpoint/global_step3151/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:fe7c11b224504d4b7ce92dcd86eeac367b83fed77a084e0ca74be6e3f15c087c
+size 73939813

last-checkpoint/global_step3151/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70f041e6e4c2fcd5847cb26f89b7e393ed9654a02c6c3e1e64c356157c74568f
+size 73939877

last-checkpoint/global_step3151/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:864c9d0a4a6a6df9e106685e32c07abf56966577d2f2ac54cfcdbefffe092ac4
+size 73939877

last-checkpoint/global_step3151/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01fe20a677165e10008e664a981608bcd879f3dd7e16388edee6794e047fb6c8
+size 564993061

last-checkpoint/latest

@@ -1 +1 @@
-global_step3101
+global_step3151

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c9f2639515e9a4dbb73442f973fea9b0c88c20b795038a946c56e0e2493ca27
+oid sha256:ff6d22752bf6918604c195c68c726c5f986752b1c7745bc126a895fa5378f563
 size 15429

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecc1dea28e987710088b449c94c516228a22c7362dc59c8c30f086a46639bae7
+oid sha256:b418cf94798b0605942c9f00109a5edef50c6b4d7c3fa15f7ef19ea7a3218590
 size 15429

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5887804b4b795f7a573283c1b112d762af0778415a90f4dd264b13d8ce6b6e73
+oid sha256:5ea4486e4c7872a12462ac87ce32aa65944ed660174e541883f84fbec5d08986
 size 15429

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d19ad5422c32a302e30ca2b15abb40a89c5c32a5565cad1734400f2ab8b8c060
+oid sha256:f803476ab2d8569ffcfe385fec2e225f971e23d78b9f9bb3450d35d825e9ea35
 size 15429

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40dddd77817570d823fe2af41de3280b2532f2b28178ec1ba2cdd4222f46c420
+oid sha256:49b27670a16b804d5788140685f115d1185aa03128bfff2551a4cdbedd7bc74b
 size 1401

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
   "best_global_step": null,
-  "best_metric": 0.620843768119812,
+  "best_metric": 0.6195825934410095,
   "best_model_checkpoint": null,
-  "epoch": 3.039191671769749,
+  "epoch": 3.0881812614819353,
   "eval_steps": 50,
-  "global_step": 3100,
+  "global_step": 3150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4844,6 +4844,84 @@
       "eval_samples_per_second": 127.13,
       "eval_steps_per_second": 15.899,
       "step": 3100
+    },
+    {
+      "epoch": 3.0440906307409676,
+      "grad_norm": 0.20413470268249512,
+      "learning_rate": 3.6132616490418216e-05,
+      "loss": 0.652,
+      "step": 3105
+    },
+    {
+      "epoch": 3.0489895897121864,
+      "grad_norm": 0.23027652502059937,
+      "learning_rate": 3.5966209323531355e-05,
+      "loss": 0.6431,
+      "step": 3110
+    },
+    {
+      "epoch": 3.0538885486834046,
+      "grad_norm": 0.24030309915542603,
+      "learning_rate": 3.5800001854923e-05,
+      "loss": 0.6301,
+      "step": 3115
+    },
+    {
+      "epoch": 3.0587875076546234,
+      "grad_norm": 0.24044173955917358,
+      "learning_rate": 3.563399579263203e-05,
+      "loss": 0.6547,
+      "step": 3120
+    },
+    {
+      "epoch": 3.063686466625842,
+      "grad_norm": 0.2295493483543396,
+      "learning_rate": 3.546819284262758e-05,
+      "loss": 0.6483,
+      "step": 3125
+    },
+    {
+      "epoch": 3.068585425597061,
+      "grad_norm": 0.2551316022872925,
+      "learning_rate": 3.53025947087915e-05,
+      "loss": 0.6436,
+      "step": 3130
+    },
+    {
+      "epoch": 3.073484384568279,
+      "grad_norm": 0.22237151861190796,
+      "learning_rate": 3.513720309290082e-05,
+      "loss": 0.638,
+      "step": 3135
+    },
+    {
+      "epoch": 3.078383343539498,
+      "grad_norm": 0.20863863825798035,
+      "learning_rate": 3.497201969461032e-05,
+      "loss": 0.6661,
+      "step": 3140
+    },
+    {
+      "epoch": 3.0832823025107166,
+      "grad_norm": 0.25886034965515137,
+      "learning_rate": 3.480704621143496e-05,
+      "loss": 0.6538,
+      "step": 3145
+    },
+    {
+      "epoch": 3.0881812614819353,
+      "grad_norm": 0.24331150949001312,
+      "learning_rate": 3.464228433873255e-05,
+      "loss": 0.6569,
+      "step": 3150
+    },
+    {
+      "epoch": 3.0881812614819353,
+      "eval_loss": 0.6195825934410095,
+      "eval_runtime": 15.4247,
+      "eval_samples_per_second": 127.004,
+      "eval_steps_per_second": 15.884,
+      "step": 3150
     }
   ],
   "logging_steps": 5,
@@ -4872,7 +4950,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5987517748506788e+18,
+  "total_flos": 1.6246141644313723e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null