Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35709cb7b07996a79e104850f6768afe92ee428be97838e61476323e2492e002
+oid sha256:b9cdc6d6e806f829e185b7e1c91b7daca15d78a8cb474f568e08d774bdc47884
 size 130583912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c8bbbef019bc515beda45a1fc24a8a93203b069277e0ab01ff4d83e86ab36e3
+oid sha256:414882d77207fe8f45d43c14f1c95ea691fd5ed34c4290a0b1453ad34016b55b
 size 66578772

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5c481e576c17914176850df3536b890e82450a0d594ebd816a9f05f22a132bf
+oid sha256:85446ac734307ad4c1e230db7d5d6a8d6dac6e2bec648ba2b41d25022bee9cdf
 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": 0.24971098265895952,
+  "epoch": 0.29132947976878615,
   "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": 15.604,
       "eval_steps_per_second": 1.967,
       "step": 54
+    },
+    {
+      "epoch": 0.2635838150289017,
+      "grad_norm": 11.070029258728027,
+      "learning_rate": 2.3256088156396868e-05,
+      "loss": 8.5202,
+      "step": 57
+    },
+    {
+      "epoch": 0.2774566473988439,
+      "grad_norm": 14.184294700622559,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 9.3465,
+      "step": 60
+    },
+    {
+      "epoch": 0.29132947976878615,
+      "grad_norm": 11.007719993591309,
+      "learning_rate": 1.8109066104575023e-05,
+      "loss": 9.118,
+      "step": 63
+    },
+    {
+      "epoch": 0.29132947976878615,
+      "eval_loss": 2.174855947494507,
+      "eval_runtime": 23.3884,
+      "eval_samples_per_second": 15.606,
+      "eval_steps_per_second": 1.967,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.069630131811123e+16,
+  "total_flos": 8.24790182044631e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null