Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b71fa4a47f16b46a8c86f8d8d50bda09c8bbc253973511b3795ad06a53212de
+oid sha256:a8ae0fddeb97385aa03883fcbc498fda5736be4f0306d93a9900af415bd69a16
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd36019c99bab760d2f6232c35f277177dfa6942fa1745620851f7b531c3be5e
+oid sha256:b6000e372df741bde215fa18022b4a5beb5665d0634ee6fd5dd8221d78497189
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da3b6129e831c47a6467f131a5b1b2072abe28992de3c8472e36351dc361b224
+oid sha256:8618c1d522bdbe7e20f802ed7847a38fe3565451c3416fb01570415f3aeac52a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
+oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.030727960004877455,
+  "epoch": 0.035117668577002804,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 12.139,
       "eval_steps_per_second": 1.519,
       "step": 63
+    },
+    {
+      "epoch": 0.03219119619558591,
+      "grad_norm": 0.6118860840797424,
+      "learning_rate": 1.56348351646022e-05,
+      "loss": 0.7783,
+      "step": 66
+    },
+    {
+      "epoch": 0.033654432386294356,
+      "grad_norm": 0.4474002718925476,
+      "learning_rate": 1.3263210930352737e-05,
+      "loss": 0.7547,
+      "step": 69
+    },
+    {
+      "epoch": 0.035117668577002804,
+      "grad_norm": 0.5504525303840637,
+      "learning_rate": 1.1020177413231334e-05,
+      "loss": 0.8348,
+      "step": 72
+    },
+    {
+      "epoch": 0.035117668577002804,
+      "eval_loss": 0.7724781632423401,
+      "eval_runtime": 284.4582,
+      "eval_samples_per_second": 12.139,
+      "eval_steps_per_second": 1.519,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0275868791904666e+17,
+  "total_flos": 1.1708898113224704e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null