Training in progress, step 170, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1f826ff0deb5ca760bab1688322cba096707f0f6506ea0db49e64851b1b6e1b
+oid sha256:0336951ec883d6b5de72b925d727ecd4ca0ac6440aa667a10a1cb852d4a63fae
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:304ef3fb9b06f4e634b17acfe8df2622465f353a24e78010c8336da55dc22a2d
+oid sha256:7d23e380a2d27ccc3f0d359f7f0c38883537fc47cda2a0ef980473b32d1f6a5a
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6728ffdf9bf59bf13703e6ecc746855ce34369dd62dc3ca69a894e5a32ceaccd
+oid sha256:82e3dacf2b05874132bf6fb4325d351a4ab2ba13cd877561594093394c8a7acc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9d255475980828d00dffcac4a69741da74c7e5ef4f645ab21d69e57306e3317
+oid sha256:963abeacc51d2fd967b0d854376103780952d47675257465be60a3612cecb103
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08068952869979827,
+  "epoch": 0.08313466593312549,
   "eval_steps": 34,
-  "global_step": 165,
+  "global_step": 170,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1202,6 +1202,49 @@
       "learning_rate": 2.0198277271976052e-05,
       "loss": 1.0062,
       "step": 165
+    },
+    {
+      "epoch": 0.08117855614646372,
+      "grad_norm": 0.45435985922813416,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.8418,
+      "step": 166
+    },
+    {
+      "epoch": 0.08166758359312916,
+      "grad_norm": 0.37857669591903687,
+      "learning_rate": 1.8025951709277898e-05,
+      "loss": 1.0043,
+      "step": 167
+    },
+    {
+      "epoch": 0.0821566110397946,
+      "grad_norm": 0.3529188930988312,
+      "learning_rate": 1.6981596918444953e-05,
+      "loss": 1.1446,
+      "step": 168
+    },
+    {
+      "epoch": 0.08264563848646005,
+      "grad_norm": 0.40138813853263855,
+      "learning_rate": 1.5965592836210743e-05,
+      "loss": 1.0077,
+      "step": 169
+    },
+    {
+      "epoch": 0.08313466593312549,
+      "grad_norm": 0.3948013186454773,
+      "learning_rate": 1.4978286427038601e-05,
+      "loss": 0.843,
+      "step": 170
+    },
+    {
+      "epoch": 0.08313466593312549,
+      "eval_loss": 0.9932751059532166,
+      "eval_runtime": 1360.6949,
+      "eval_samples_per_second": 1.898,
+      "eval_steps_per_second": 0.633,
+      "step": 170
     }
   ],
   "logging_steps": 1,
@@ -1221,7 +1264,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.324274422657843e+17,
+  "total_flos": 7.546222132435354e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null