Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e4cede093a047dae1d9b39f98f01ebd38cf9627aaf8ecf1e2945971471563b4
+oid sha256:c421e1a1dbce79ef959f7a945483797a1c02477f356068cd68f5d77b142df12a
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f858b048df2c4990c74df403bfc1d645b453dacbbe71b54093671cdea7cfc9f
+oid sha256:4798491d1c7e06175a2a17926235d5ddc1417aae8adc96b638f9fb4ba519a95e
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:155906040ca3a73448d35f864001cf3a30094785911dc4949af7556c64d5da61
+oid sha256:779251727fe5ad39bf8f90a17ce5b55483cecb3499b5ce321aeb359460b9771f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aba7537afe16c3362d871f59e72c1a9387d8f379b5c058726a66f4dd3222a4f6
+oid sha256:d3e566edc54c1fce50b7e403fa263aeae9d08be1730260d50ef8cb07535b5ac9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1001788908765653,
+  "epoch": 0.1073345259391771,
   "eval_steps": 500,
-  "global_step": 280,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -231,14 +231,30 @@
       "loss": 0.4332,
       "num_input_tokens_seen": 187842,
       "step": 280
+    },
+    {
+      "epoch": 0.1037567084078712,
+      "grad_norm": 0.38877248764038086,
+      "learning_rate": 0.00017924865831842578,
+      "loss": 0.4248,
+      "num_input_tokens_seen": 194651,
+      "step": 290
+    },
+    {
+      "epoch": 0.1073345259391771,
+      "grad_norm": 0.30087631940841675,
+      "learning_rate": 0.00017853309481216458,
+      "loss": 0.4405,
+      "num_input_tokens_seen": 202203,
+      "step": 300
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 187842,
+  "num_input_tokens_seen": 202203,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 4223903236263936.0,
+  "total_flos": 4546831411943424.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null