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:c4802a9d25e5d6b96bb9915dde0929892a9ce8afb6c6939475e92a3ed5da6d2b
+oid sha256:0efbae863edae5ba3468d772c19b58f9b7b9e98f002b3209ee94c356a252db42
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:658fdbaca5cc69e2f3bf5bcb4400224de0f54b0f7df96620141f7c8f1bd95ae0
+oid sha256:09284333f5f51c21344942adec586922f72e7780acb9b145f77b3010ac64283f
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7daa4ff2cd22518a8e024a0eefc50ce3cb169affaaeea31b23fe88881048fad
+oid sha256:89f0a3db0ff9d605cd3f535a9c581a546701adf2969dc1fad8a8f2bafec063c0
 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": 1.0956521739130434,
+  "epoch": 1.2521739130434781,
   "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": 36.209,
       "eval_steps_per_second": 4.853,
       "step": 63
+    },
+    {
+      "epoch": 1.1478260869565218,
+      "grad_norm": 0.38854989409446716,
+      "learning_rate": 1.56348351646022e-05,
+      "loss": 1.4154,
+      "step": 66
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.5519515872001648,
+      "learning_rate": 1.3263210930352737e-05,
+      "loss": 1.1699,
+      "step": 69
+    },
+    {
+      "epoch": 1.2521739130434781,
+      "grad_norm": 0.3825100362300873,
+      "learning_rate": 1.1020177413231334e-05,
+      "loss": 1.188,
+      "step": 72
+    },
+    {
+      "epoch": 1.2521739130434781,
+      "eval_loss": 0.9695695638656616,
+      "eval_runtime": 2.6795,
+      "eval_samples_per_second": 36.201,
+      "eval_steps_per_second": 4.852,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6581450047422464e+16,
+  "total_flos": 1.8932733953703936e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null