Training in progress, step 480, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2e97ba536a9cf9f3cad84abf4746e0135e3d4b06fb5f603560779d86a93736f
+oid sha256:1149ac7d2e20a3329470bc1ff37dc81499b3a2cb0df815434dcf8dae04d7c3e3
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8595eb58b690d85cb1e767c686f29da9e28dd133d34215b62d1115350a069af0
+oid sha256:fdd9e444faaff4d97315caba29dfc8c642a3e55aa3d110711caa1e01bf50f4b7
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:338d183eae7b62e1d0bd6d80780849a4f9fd1da463f7c7dececa74af88cb940a
+oid sha256:ffef31896db6975b47a1bdf431486b1a47c0e23e76fe29d6042f106a12e8af6b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96a992901ca361b8095fa2f834dad606f97c4c02318aaff9cbbb3f96062de392
+oid sha256:84691b1971218726e113e2882d1da3f46cde022409a500bc85e18521371a8edd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.16457960644007155,
+  "epoch": 0.17173524150268335,
   "eval_steps": 500,
-  "global_step": 460,
+  "global_step": 480,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -375,14 +375,30 @@
       "loss": 0.4201,
       "num_input_tokens_seen": 306782,
       "step": 460
+    },
+    {
+      "epoch": 0.16815742397137745,
+      "grad_norm": 0.3007524013519287,
+      "learning_rate": 0.0001663685152057245,
+      "loss": 0.444,
+      "num_input_tokens_seen": 314243,
+      "step": 470
+    },
+    {
+      "epoch": 0.17173524150268335,
+      "grad_norm": 0.4292968809604645,
+      "learning_rate": 0.00016565295169946334,
+      "loss": 0.4089,
+      "num_input_tokens_seen": 319432,
+      "step": 480
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 306782,
+  "num_input_tokens_seen": 319432,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 6898443812499456.0,
+  "total_flos": 7182897640390656.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null