Training in progress, step 35, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba25ce0dda301f5b9245ffcd5e552cc74da84ce6b004f7e45385833a47405276
+oid sha256:d2c7f35f29a525d80d5567473a7c0098f9828232fe517e78985140bec04b4d5d
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41a4886fdba993fda8c37a853f6301d74e673e1ea3338429da8afe2ade262efe
+oid sha256:aebba54edf3d6e9652ae18e01a762cf89ccd12e3ada6bdca51e0606a9be6506c
 size 509176980

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae23c720e43827fac7ec9738d78285292b2b49a0ea5579feabe2dcfc07f544e5
+oid sha256:f4e8be85bff89c7cc936ed5348f3f2f54c4d981583d63142a6ffcbd0200af65f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d37b0dad6b9c48822da5c83a071d50252502799ad22c4c4907147ad4e4f8e2f4
+oid sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02564102564102564,
+  "epoch": 0.029914529914529916,
   "eval_steps": 5,
-  "global_step": 30,
+  "global_step": 35,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,6 +133,21 @@
       "eval_samples_per_second": 6.537,
       "eval_steps_per_second": 0.819,
       "step": 30
+    },
+    {
+      "epoch": 0.028205128205128206,
+      "grad_norm": 1.8765429258346558,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 2.1488,
+      "step": 33
+    },
+    {
+      "epoch": 0.029914529914529916,
+      "eval_loss": 0.5602862238883972,
+      "eval_runtime": 301.3722,
+      "eval_samples_per_second": 6.54,
+      "eval_steps_per_second": 0.82,
+      "step": 35
     }
   ],
   "logging_steps": 3,
@@ -152,7 +167,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.72814168653824e+16,
+  "total_flos": 9.01616530096128e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null