Training in progress, step 2000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c2f40d58562647fcfba8d16d7dbd10f38e675cf2ef968a6edcb3ae166f4689d
+oid sha256:9c223867a54003574441075cb1c2f7cf35a5f5d21c1b65f662fd6798e4d4a007
 size 42002584

last-checkpoint/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c49902c81a6dcc2e849480ea21c30986c3b4e4d380b2c0751058ef86be78d73
+size 251710672

last-checkpoint/global_step2000/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f14756e6336f379701f8203b5a82466933e6c72bda35d65de3883d4c0684d5d
+size 153747385

last-checkpoint/latest

@@ -1 +1 @@
-global_step1500
+global_step2000

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9f5d56c1ca14011dd7b001c1386b904a9bf2bc098727c58e8a26a0f73e026d3
+oid sha256:227788b816b8b06d238c8c63acd422670703268e5b2b75d7dc2a5e755c8acbb5
 size 14244

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.547008547008547,
+  "epoch": 11.396011396011396,
   "eval_steps": 1000,
-  "global_step": 1500,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -224,6 +224,76 @@
       "learning_rate": 0.00012522522522522524,
       "loss": 0.1031,
       "step": 1500
+    },
+    {
+      "epoch": 8.831908831908832,
+      "grad_norm": 2.925875663757324,
+      "learning_rate": 0.00012272272272272273,
+      "loss": 0.1098,
+      "step": 1550
+    },
+    {
+      "epoch": 9.116809116809117,
+      "grad_norm": 2.593219757080078,
+      "learning_rate": 0.00012022022022022023,
+      "loss": 0.0979,
+      "step": 1600
+    },
+    {
+      "epoch": 9.401709401709402,
+      "grad_norm": 2.457099199295044,
+      "learning_rate": 0.00011771771771771771,
+      "loss": 0.0917,
+      "step": 1650
+    },
+    {
+      "epoch": 9.686609686609687,
+      "grad_norm": 2.513124465942383,
+      "learning_rate": 0.00011521521521521521,
+      "loss": 0.0884,
+      "step": 1700
+    },
+    {
+      "epoch": 9.971509971509972,
+      "grad_norm": 0.9835783243179321,
+      "learning_rate": 0.00011271271271271271,
+      "loss": 0.0891,
+      "step": 1750
+    },
+    {
+      "epoch": 10.256410256410255,
+      "grad_norm": 1.4291648864746094,
+      "learning_rate": 0.0001102102102102102,
+      "loss": 0.0792,
+      "step": 1800
+    },
+    {
+      "epoch": 10.54131054131054,
+      "grad_norm": 0.974391758441925,
+      "learning_rate": 0.00010770770770770771,
+      "loss": 0.0834,
+      "step": 1850
+    },
+    {
+      "epoch": 10.826210826210826,
+      "grad_norm": 2.3604581356048584,
+      "learning_rate": 0.0001052052052052052,
+      "loss": 0.0829,
+      "step": 1900
+    },
+    {
+      "epoch": 11.11111111111111,
+      "grad_norm": 1.6176166534423828,
+      "learning_rate": 0.0001027027027027027,
+      "loss": 0.08,
+      "step": 1950
+    },
+    {
+      "epoch": 11.396011396011396,
+      "grad_norm": 1.9266570806503296,
+      "learning_rate": 0.0001002002002002002,
+      "loss": 0.0763,
+      "step": 2000
     }
   ],
   "logging_steps": 50,
@@ -243,7 +313,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.542048423326515e+16,
+  "total_flos": 6.055886956213043e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null