Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d364eb38a8be050b253d95fb9bb96a3cca85c934f5694fdf28af039b0f831af
+oid sha256:777110b9885805d05b54b83c0078c17d2c3f56f401f8d414b249c230762358bb
 size 140815952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86177b2d4721c68d5e890ce7ce966763b55e655be1b7686c76b23550228c8c19
+oid sha256:8bd299fcb2d78913771ba672fc903a33ad3ee1376e8feba78832d4267d4cbedd
 size 281829907

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c87752ccee056791ab2999ec7c3dec0f8bae82b1dfd073feafe2df524ed5926c
+oid sha256:17c4ae54d27cbe43b4c5fa652d71ae90547dadc724f75624e3d3c44e35870949
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d8f1711fa5a9b936955c6d8224082844929d47bb03fce797eceac8f3a3a5313
+oid sha256:d74ad02c6868c7927ba45f4229ae211aa9e779d68ecfa33c6fcfa330a9d67a76
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.1333333333333333,
+  "epoch": 2.6666666666666665,
   "eval_steps": 100,
-  "global_step": 160,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -240,6 +240,70 @@
       "learning_rate": 0.00012053759377541865,
       "loss": 0.4102,
       "step": 160
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.11487775295972824,
+      "learning_rate": 0.00010431474098842477,
+      "loss": 0.3926,
+      "step": 165
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 0.110216423869133,
+      "learning_rate": 8.897239713740058e-05,
+      "loss": 0.4028,
+      "step": 170
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.12020918726921082,
+      "learning_rate": 7.460329000380586e-05,
+      "loss": 0.4216,
+      "step": 175
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.11179473251104355,
+      "learning_rate": 6.12942652116858e-05,
+      "loss": 0.4194,
+      "step": 180
+    },
+    {
+      "epoch": 2.466666666666667,
+      "grad_norm": 0.1162172257900238,
+      "learning_rate": 4.912576134033106e-05,
+      "loss": 0.3448,
+      "step": 185
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 0.12591737508773804,
+      "learning_rate": 3.8171323760555655e-05,
+      "loss": 0.3779,
+      "step": 190
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.12023098766803741,
+      "learning_rate": 2.8497160132921336e-05,
+      "loss": 0.3846,
+      "step": 195
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.12184033542871475,
+      "learning_rate": 2.0161740254440898e-05,
+      "loss": 0.3998,
+      "step": 200
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "eval_loss": 0.5051587224006653,
+      "eval_runtime": 45.0327,
+      "eval_samples_per_second": 0.378,
+      "eval_steps_per_second": 0.378,
+      "step": 200
     }
   ],
   "logging_steps": 5,
@@ -259,7 +323,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5289180164259840.0,
+  "total_flos": 6611475205324800.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null