Training in progress, step 560, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02ca0724696c0714678baa7c919014b6cf1f56a5d8f9a9076b8131ecb4e4820b
+oid sha256:a7af6ede55d0341241bc32219ef506f81ee7d0a6598b2c326b762b273b49ba7c
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c81ca955f4aa3495f958edfe9940021e3673d3e58c241146187bf4ccb7cc56df
+oid sha256:3d712e257f17863cb11322f71673372ff307ede78b55ed17a21b191a03b5a310
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f94817a11f2e5ac87d214de7bcbd2b4175429bcc3bf1d7ea823b2e61e3e96885
+oid sha256:813c071ac276f83e1b6d20b4afa7012ff50b1e905202a7b0d6045d0bc7d97762
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:857a28d74b36678189295e64a86a5f88d7b3dd82cb001caca49c082b46d9200f
+oid sha256:8fda21cee6c433e296b92e0e41eec8879af8f118fc5a2faf949201c0875cc586
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.19320214669051877,
+  "epoch": 0.2003577817531306,
   "eval_steps": 500,
-  "global_step": 540,
+  "global_step": 560,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -439,14 +439,30 @@
       "loss": 0.4314,
       "num_input_tokens_seen": 360961,
       "step": 540
+    },
+    {
+      "epoch": 0.1967799642218247,
+      "grad_norm": 0.30050089955329895,
+      "learning_rate": 0.00016064400715563507,
+      "loss": 0.4364,
+      "num_input_tokens_seen": 367083,
+      "step": 550
+    },
+    {
+      "epoch": 0.2003577817531306,
+      "grad_norm": 0.3418981432914734,
+      "learning_rate": 0.0001599284436493739,
+      "loss": 0.4329,
+      "num_input_tokens_seen": 373196,
+      "step": 560
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 360961,
+  "num_input_tokens_seen": 373196,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 8116738195212288.0,
+  "total_flos": 8391860138631168.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null