Training in progress, step 290, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bff5ea59540fe9486298d16b1c5e07e830cb7454df8e49fb5701941042f38970
+oid sha256:d7e2e87355763edd3d8d8fc9f16426a52b729ef470fa0ed35fdf6a0d34a1d19e
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf8e705be49471bb0c8b7ab4e2654c27c1bbbac7d427de970d6341d4d6a51632
+oid sha256:69b0bf7861f08e4352dac63f09fddd6dae58be12ccfacd2673ea034a1c7bbb52
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bd08400b897a4c94f407fc6f069e4949e235fcc43163cb517cd39dcd6f04847
+oid sha256:c4863ee1f3e4eb3a27956688d9477cddde272e35ff8d013a583ff2d67a2b5271
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00305a50c12f8c5ecbafd69a728a0a7449bc703aaaf50988de0f32f2f4bdb6e8
+oid sha256:37ef35c880ce179d87a8b718acaf0bfe99028fc0acc2a163aedf97a2066df701
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.36881268197994177,
+  "epoch": 0.37528307990941445,
   "eval_steps": 386,
-  "global_step": 285,
+  "global_step": 290,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2010,6 +2010,41 @@
       "learning_rate": 9.906423629072434e-05,
       "loss": 1.0889,
       "step": 285
+    },
+    {
+      "epoch": 0.3701067615658363,
+      "grad_norm": 0.8891452550888062,
+      "learning_rate": 9.905628060031605e-05,
+      "loss": 0.8847,
+      "step": 286
+    },
+    {
+      "epoch": 0.37140084115173083,
+      "grad_norm": 0.8682214021682739,
+      "learning_rate": 9.904829155617945e-05,
+      "loss": 0.9311,
+      "step": 287
+    },
+    {
+      "epoch": 0.3726949207376254,
+      "grad_norm": 1.2218021154403687,
+      "learning_rate": 9.904026916374636e-05,
+      "loss": 0.92,
+      "step": 288
+    },
+    {
+      "epoch": 0.3739890003235199,
+      "grad_norm": 1.0069034099578857,
+      "learning_rate": 9.903221342847125e-05,
+      "loss": 1.0061,
+      "step": 289
+    },
+    {
+      "epoch": 0.37528307990941445,
+      "grad_norm": 0.7723405361175537,
+      "learning_rate": 9.902412435583128e-05,
+      "loss": 0.8627,
+      "step": 290
     }
   ],
   "logging_steps": 1,
@@ -2029,7 +2064,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.186120939326669e+17,
+  "total_flos": 3.242017797911347e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null