Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d3b07bd310c2c77bf281dbf16a61be566959ba79626d5bb4239b5ccbd82a979
+oid sha256:b9a92c81ee72d6f4be19ae57715110ad33e86ad056a87f3794e3e880ad496dc7
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ae1ad81131d86ae05701f2915f8702dd6e795ee3ea134033f8ce212b8642cca
+oid sha256:96cbce9a2c261196cf00e628e7df8f9449dac405c5a464ba207ffc687ad6c685
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7508b824c8dad473e22c31032ece242e15353e035fff9b2306e9e0fda5e83d7a
+oid sha256:3f2fb4f7ac4aba23939631c9f9c91472fd4a574c3f2a85d4361636f72ca9b9a8
 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": 0.02500289385345526,
+  "epoch": 0.02917004282903114,
   "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": 24.814,
       "eval_steps_per_second": 3.103,
       "step": 54
+    },
+    {
+      "epoch": 0.026391943511980553,
+      "grad_norm": 0.449227899312973,
+      "learning_rate": 2.3256088156396868e-05,
+      "loss": 1.599,
+      "step": 57
+    },
+    {
+      "epoch": 0.027780993170505846,
+      "grad_norm": 0.443278431892395,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 1.4581,
+      "step": 60
+    },
+    {
+      "epoch": 0.02917004282903114,
+      "grad_norm": 0.468054860830307,
+      "learning_rate": 1.8109066104575023e-05,
+      "loss": 1.6188,
+      "step": 63
+    },
+    {
+      "epoch": 0.02917004282903114,
+      "eval_loss": 1.641588807106018,
+      "eval_runtime": 146.545,
+      "eval_samples_per_second": 24.825,
+      "eval_steps_per_second": 3.105,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.0184303635726336e+16,
+  "total_flos": 3.521502090834739e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null