Training in progress, step 320, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c421e1a1dbce79ef959f7a945483797a1c02477f356068cd68f5d77b142df12a
+oid sha256:4d7c5c0bb66466d7e29226f80d5cc217cf4256670467b8a4081f5c23852a3af7
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4798491d1c7e06175a2a17926235d5ddc1417aae8adc96b638f9fb4ba519a95e
+oid sha256:a553c2eb71e73f0c1eda48c6b9ee7a1eaaa3208af2a76b8e5dbafcd6476db69a
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:779251727fe5ad39bf8f90a17ce5b55483cecb3499b5ce321aeb359460b9771f
+oid sha256:7f2a2d99c0e8f2ac5f91854c3cc393c4031b8b2b320bd2130073e550304e4d8b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3e566edc54c1fce50b7e403fa263aeae9d08be1730260d50ef8cb07535b5ac9
+oid sha256:7ae66eeabf39a4e204f66b969f521166fbc3f93e43500ebb37520ec3747848cb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1073345259391771,
+  "epoch": 0.11449016100178891,
   "eval_steps": 500,
-  "global_step": 300,
+  "global_step": 320,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,14 +247,30 @@
       "loss": 0.4405,
       "num_input_tokens_seen": 202203,
       "step": 300
+    },
+    {
+      "epoch": 0.11091234347048301,
+      "grad_norm": 0.33470776677131653,
+      "learning_rate": 0.00017781753130590342,
+      "loss": 0.4485,
+      "num_input_tokens_seen": 210364,
+      "step": 310
+    },
+    {
+      "epoch": 0.11449016100178891,
+      "grad_norm": 0.44205668568611145,
+      "learning_rate": 0.00017710196779964222,
+      "loss": 0.4431,
+      "num_input_tokens_seen": 217965,
+      "step": 320
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 202203,
+  "num_input_tokens_seen": 217965,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 4546831411943424.0,
+  "total_flos": 4901263130142720.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null