Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5bc3665eb969d55941f958da6a3d13c244b9eb8ee809445f4a65b52931f858c
+oid sha256:0421aa29105f02d352b3e31dec1837b8b4c6b078120ab76e42ec9cf8461c1663
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c52c5a3f256efcce06dadccc2702edeef3814a5c812633b60970144030ebb435
+oid sha256:46462f547f758d2c2c12bf486d24e294ac00c4663f542674bb46aec4385a2083
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87951bd1d28cfc789427636c05788fc21db0e7e40be21589b4278413c44c66bd
+oid sha256:49644ad8f5452e53758ca52013eb3650a3941bcec6083d72c46c935a677f7d88
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec430a8fba90f7f39f74e916eb32712c363a0fd20bb4904251fce0eb82f2b9cf
+oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004886214541012532,
+  "epoch": 0.005700583631181287,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 12.932,
       "eval_steps_per_second": 1.617,
       "step": 54
+    },
+    {
+      "epoch": 0.005157670904402117,
+      "grad_norm": 1.517822504043579,
+      "learning_rate": 2.3256088156396868e-05,
+      "loss": 0.5922,
+      "step": 57
+    },
+    {
+      "epoch": 0.005429127267791703,
+      "grad_norm": 1.7860591411590576,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 0.437,
+      "step": 60
+    },
+    {
+      "epoch": 0.005700583631181287,
+      "grad_norm": 4.32674503326416,
+      "learning_rate": 1.8109066104575023e-05,
+      "loss": 0.5061,
+      "step": 63
+    },
+    {
+      "epoch": 0.005700583631181287,
+      "eval_loss": 0.4976564645767212,
+      "eval_runtime": 1439.5584,
+      "eval_samples_per_second": 12.93,
+      "eval_steps_per_second": 1.616,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.798615858741248e+16,
+  "total_flos": 9.098385168531456e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null