Training in progress, step 120, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60f390a9c9026f29af31317a5435777aba56fa026baad7e8fbd25b0b70943158
+oid sha256:f1e8f5f2e88e6302d25cf87eed12d39f8a9b7dceaecac4f92ca58a0e89ad70d6
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:726bf7fb7a6398770c278d473ba23020f68711fbcd79591c98a7f1a72ef20a0c
+oid sha256:6e87da96d15b53e4b7f7d48ccd4bfd7fcd6c213b1c629faeec9a8153b0f3e746
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4e6470455f66907a19173307202d571c6c3f1f8cd4ddcc5b663dc15013ec0cd
+oid sha256:5b37c228faac27493d5dc2700eeaf67fe98afdbd0e55a68eaf314f21f0aea103
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d445cf5235925cca1a6d5e57200162b082b481744bf739a511d532ac296ab841
+oid sha256:ba16893b2c4735e8eaf86592331a8dda9b3bcccecd302e828000513277487239
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05623815636652607,
+  "epoch": 0.05868329359985329,
   "eval_steps": 34,
-  "global_step": 115,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -844,6 +844,41 @@
       "learning_rate": 0.0001,
       "loss": 1.077,
       "step": 115
+    },
+    {
+      "epoch": 0.056727183813191515,
+      "grad_norm": 0.2759286165237427,
+      "learning_rate": 9.815210950408704e-05,
+      "loss": 1.0208,
+      "step": 116
+    },
+    {
+      "epoch": 0.05721621125985696,
+      "grad_norm": 0.35885995626449585,
+      "learning_rate": 9.630485006108553e-05,
+      "loss": 0.8758,
+      "step": 117
+    },
+    {
+      "epoch": 0.0577052387065224,
+      "grad_norm": 0.3405105471611023,
+      "learning_rate": 9.4458852508403e-05,
+      "loss": 1.012,
+      "step": 118
+    },
+    {
+      "epoch": 0.058194266153187846,
+      "grad_norm": 0.3069765865802765,
+      "learning_rate": 9.261474725251261e-05,
+      "loss": 1.0491,
+      "step": 119
+    },
+    {
+      "epoch": 0.05868329359985329,
+      "grad_norm": 0.4522247016429901,
+      "learning_rate": 9.077316405366981e-05,
+      "loss": 0.9517,
+      "step": 120
     }
   ],
   "logging_steps": 1,
@@ -863,7 +898,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.104797324882739e+17,
+  "total_flos": 5.3267450346602496e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null