Training in progress, step 3500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d68bcc11de96c82cc302aacd29d6f456247d63f2f4d39307769746456f2d36d
+oid sha256:5c2daf94e67a402aba974312ff99a669e5dcbffb99717ae00d0646b838a479df
 size 42002584

last-checkpoint/global_step3500/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:e3a15607644f09940b16d9a686c6970d247e5ab5505d5df9f79e020811ff1d74
+size 251710672

last-checkpoint/global_step3500/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85302cb8c5b8b44f532f11cc6124f01954264ccc8cda5ac9805eeb1961a7132b
+size 153747385

last-checkpoint/latest

@@ -1 +1 @@
-global_step3000
+global_step3500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bfa14c5410b710fcae3d8fcfac63a80363ede0d2705f50a4f85d135deef8000
+oid sha256:ff3e76396f70d39c4ab50031685ac2fc3f2b68f98254d9bc8fd8a09838383894
 size 14244

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 17.094017094017094,
+  "epoch": 19.943019943019944,
   "eval_steps": 1000,
-  "global_step": 3000,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -434,6 +434,76 @@
       "learning_rate": 5.015015015015015e-05,
       "loss": 0.0586,
       "step": 3000
+    },
+    {
+      "epoch": 17.37891737891738,
+      "grad_norm": 0.09752911329269409,
+      "learning_rate": 4.764764764764765e-05,
+      "loss": 0.058,
+      "step": 3050
+    },
+    {
+      "epoch": 17.663817663817664,
+      "grad_norm": 0.11784069985151291,
+      "learning_rate": 4.5145145145145146e-05,
+      "loss": 0.0595,
+      "step": 3100
+    },
+    {
+      "epoch": 17.94871794871795,
+      "grad_norm": 0.461434006690979,
+      "learning_rate": 4.264264264264264e-05,
+      "loss": 0.061,
+      "step": 3150
+    },
+    {
+      "epoch": 18.233618233618234,
+      "grad_norm": 0.13216863572597504,
+      "learning_rate": 4.014014014014014e-05,
+      "loss": 0.0602,
+      "step": 3200
+    },
+    {
+      "epoch": 18.51851851851852,
+      "grad_norm": 0.078556589782238,
+      "learning_rate": 3.763763763763764e-05,
+      "loss": 0.058,
+      "step": 3250
+    },
+    {
+      "epoch": 18.803418803418804,
+      "grad_norm": 0.09973672032356262,
+      "learning_rate": 3.513513513513514e-05,
+      "loss": 0.0578,
+      "step": 3300
+    },
+    {
+      "epoch": 19.08831908831909,
+      "grad_norm": 0.08268678188323975,
+      "learning_rate": 3.263263263263263e-05,
+      "loss": 0.0599,
+      "step": 3350
+    },
+    {
+      "epoch": 19.373219373219374,
+      "grad_norm": 0.12324529886245728,
+      "learning_rate": 3.013013013013013e-05,
+      "loss": 0.059,
+      "step": 3400
+    },
+    {
+      "epoch": 19.65811965811966,
+      "grad_norm": 0.11340611428022385,
+      "learning_rate": 2.762762762762763e-05,
+      "loss": 0.0572,
+      "step": 3450
+    },
+    {
+      "epoch": 19.943019943019944,
+      "grad_norm": 0.08004830777645111,
+      "learning_rate": 2.5125125125125126e-05,
+      "loss": 0.0597,
+      "step": 3500
     }
   ],
   "logging_steps": 50,
@@ -453,7 +523,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.09931874049065e+16,
+  "total_flos": 1.0604175892781466e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null