Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:436f46186eba9d1510f328b2ffce4c7d69d9534e97902df00d1a4e8f902332d0
+oid sha256:c4802a9d25e5d6b96bb9915dde0929892a9ce8afb6c6939475e92a3ed5da6d2b
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15d2e940a68ecfe14b7b3c177b7a8dcf75f25776a1a213689eda919d8b9ab6f3
+oid sha256:658fdbaca5cc69e2f3bf5bcb4400224de0f54b0f7df96620141f7c8f1bd95ae0
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5a26ea1faccd4215bd15b0527d8b346644a9264336caf450df2e26ee4b8ff64
+oid sha256:e7daa4ff2cd22518a8e024a0eefc50ce3cb169affaaeea31b23fe88881048fad
 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": 0.9391304347826087,
+  "epoch": 1.0956521739130434,
   "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": 36.252,
       "eval_steps_per_second": 4.859,
       "step": 54
+    },
+    {
+      "epoch": 0.991304347826087,
+      "grad_norm": 0.5368942618370056,
+      "learning_rate": 2.3256088156396868e-05,
+      "loss": 1.1923,
+      "step": 57
+    },
+    {
+      "epoch": 1.0434782608695652,
+      "grad_norm": 0.5342758893966675,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 1.0875,
+      "step": 60
+    },
+    {
+      "epoch": 1.0956521739130434,
+      "grad_norm": 0.4160667359828949,
+      "learning_rate": 1.8109066104575023e-05,
+      "loss": 1.3013,
+      "step": 63
+    },
+    {
+      "epoch": 1.0956521739130434,
+      "eval_loss": 0.9771125912666321,
+      "eval_runtime": 2.6789,
+      "eval_samples_per_second": 36.209,
+      "eval_steps_per_second": 4.853,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4238330321371136e+16,
+  "total_flos": 1.6581450047422464e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null