Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a4986982f1721b0d7826540a1e0b19de579da5982717b08a1786d66861ca6c9
+oid sha256:df32e16900e74a2b400c11092cb3f319df7453e4b67bfbf2d669e41f8c262a9e
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c43f52e944734165137cfe1749d4d4f1ca2f53a2a9aab6602a28897ea2ae869
+oid sha256:65e3e57d796c8e6a70cf4a65884ea63916ab3c4871675ef243b63c28f91f6626
 size 253144

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38b203c487a223bbc58ff68bdb5abcc1dc73df8232401ff6f5ebb4ec48efbf8d
+oid sha256:d6f8d91445b23c7a2b71c10f72fc68a8d50c4ad52ee6befbb53c1732cd7664d4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
+oid sha256:d37b0dad6b9c48822da5c83a071d50252502799ad22c4c4907147ad4e4f8e2f4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01754693805930865,
+  "epoch": 0.02105632567117038,
   "eval_steps": 5,
-  "global_step": 25,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -111,6 +111,28 @@
       "eval_samples_per_second": 457.536,
       "eval_steps_per_second": 57.192,
       "step": 25
+    },
+    {
+      "epoch": 0.018950693104053343,
+      "grad_norm": 0.14812299609184265,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 10.371,
+      "step": 27
+    },
+    {
+      "epoch": 0.02105632567117038,
+      "grad_norm": 0.16699759662151337,
+      "learning_rate": 5e-05,
+      "loss": 10.3651,
+      "step": 30
+    },
+    {
+      "epoch": 0.02105632567117038,
+      "eval_loss": 10.364386558532715,
+      "eval_runtime": 5.2274,
+      "eval_samples_per_second": 459.12,
+      "eval_steps_per_second": 57.39,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -130,7 +152,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2844541845504.0,
+  "total_flos": 3430182813696.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null