Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9b8ed5bd2b484501ed9a9750ab3c46606b53a398ada09af49075cb9868a1dbd
+oid sha256:8afdd40294379d1dcf8fa826f72105b7ae2a04934f6f3e04c73e44139fd8683c
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:873e123d716b4e3681b7bdcf8b6d4024d99e642a789148deeef040a213b7988f
+oid sha256:c156322d8fd224fc583aa0961d9a3a3d9095c3243790fe54c6712cb71d236ec1
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55974460331ed68231a1ad9dc00a5262b80738898a81bf122859c075aa9b16c2
+oid sha256:0944a3edc8124518b8a6cb208c614a99c44e0e66bdc642a03f43a707b184da2c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:574ab12ec5e33abca7f4c7bc83b682560fcb2b9d98fc4110c6edb18204a6e3fe
+oid sha256:981f3fda4f937bab1069c5a15164015d61f2e8dc63af50b10838f184e1a549af
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.12293756065998059,
+  "epoch": 0.12940795858945325,
   "eval_steps": 386,
-  "global_step": 95,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -680,6 +680,41 @@
       "learning_rate": 9.996558363482277e-05,
       "loss": 0.855,
       "step": 95
+    },
+    {
+      "epoch": 0.12423164024587512,
+      "grad_norm": 0.8604567050933838,
+      "learning_rate": 9.996403720828449e-05,
+      "loss": 0.9485,
+      "step": 96
+    },
+    {
+      "epoch": 0.12552571983176966,
+      "grad_norm": 1.020851492881775,
+      "learning_rate": 9.996245681082748e-05,
+      "loss": 1.0024,
+      "step": 97
+    },
+    {
+      "epoch": 0.1268197994176642,
+      "grad_norm": 1.0704892873764038,
+      "learning_rate": 9.996084244352623e-05,
+      "loss": 0.9246,
+      "step": 98
+    },
+    {
+      "epoch": 0.12811387900355872,
+      "grad_norm": 0.8441987037658691,
+      "learning_rate": 9.99591941074784e-05,
+      "loss": 1.0343,
+      "step": 99
+    },
+    {
+      "epoch": 0.12940795858945325,
+      "grad_norm": 1.0280612707138062,
+      "learning_rate": 9.995751180380466e-05,
+      "loss": 0.9644,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -699,7 +734,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0620403131088896e+17,
+  "total_flos": 1.117937171693568e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null