Training in progress, step 440, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7712264348621d2796ac99b058407d20d1f274b63402d0eeba4a340e5bd587fa
+oid sha256:5c9779fb5aa80e5aa5419bba076caa89514a108718bdd23116ef4bf476d3b9c8
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:727841171ff5f34ef140ffe70848bd8331fb68b20625106122760e6059e4075d
+oid sha256:391bfb6ac94c63f7d6128408c737f45e0c7892c2a2b949443e80fa50e52edcff
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec0087350e1d3e07cf35072a33646a3f291d5eea076f7982b6b16b781d9ae3a1
+oid sha256:d22180da8d1636aa73032f3645d9cd1697f1e0443328b03f72dfc859c0ada238
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a464cebc8678b774c25802e284c2c583021f5904cc055f0a604f89809d70325
+oid sha256:63ede706d34f67ff27af705e3a217dd4b9f1e883ef465d130d62c35a9e9452d7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5629246198641217,
+  "epoch": 0.5693950177935944,
   "eval_steps": 386,
-  "global_step": 435,
+  "global_step": 440,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3068,6 +3068,41 @@
       "learning_rate": 9.750160633557627e-05,
       "loss": 0.9424,
       "step": 435
+    },
+    {
+      "epoch": 0.5642186994500161,
+      "grad_norm": 0.8522469401359558,
+      "learning_rate": 9.748872070222625e-05,
+      "loss": 0.8151,
+      "step": 436
+    },
+    {
+      "epoch": 0.5655127790359107,
+      "grad_norm": 0.862091064453125,
+      "learning_rate": 9.747580278094352e-05,
+      "loss": 1.0131,
+      "step": 437
+    },
+    {
+      "epoch": 0.5668068586218052,
+      "grad_norm": 0.8809049725532532,
+      "learning_rate": 9.746285258051104e-05,
+      "loss": 0.9092,
+      "step": 438
+    },
+    {
+      "epoch": 0.5681009382076998,
+      "grad_norm": 0.8506961464881897,
+      "learning_rate": 9.744987010973377e-05,
+      "loss": 0.8756,
+      "step": 439
+    },
+    {
+      "epoch": 0.5693950177935944,
+      "grad_norm": 0.7440844774246216,
+      "learning_rate": 9.743685537743856e-05,
+      "loss": 0.7948,
+      "step": 440
     }
   ],
   "logging_steps": 1,
@@ -3087,7 +3122,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.863026696867021e+17,
+  "total_flos": 4.918923555451699e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null