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:f68589cc9e840a9d2cf1e9bbd7a73b257ada3360a9e37027ae511224563a5b21
+oid sha256:328e6219a84a1c5d014d73882c90e59b775009ebde96f422efd9a96131f10d74
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d62bd2094db4b5c03761e8383c99fead7d40d01106f96385073ec8f6a302edc4
+oid sha256:3493323eb6c6109718f564ec556625834692da58d518284df1e2fcb38c0d9b2f
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2b7e3f7f3d4cdab0671ff5feab74498bf3ca02bf473edcf2d1ddaa38062dddc
+oid sha256:49c809f327643e2371174055edbcb9fb814f0c6bc7665957ef69286f7e20857b
 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": 0.38848920863309355,
+  "epoch": 0.45323741007194246,
   "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": 12.086,
       "eval_steps_per_second": 1.549,
       "step": 54
+    },
+    {
+      "epoch": 0.41007194244604317,
+      "grad_norm": 2.020596504211426,
+      "learning_rate": 2.3256088156396868e-05,
+      "loss": 4.1487,
+      "step": 57
+    },
+    {
+      "epoch": 0.4316546762589928,
+      "grad_norm": 1.7905324697494507,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 4.1138,
+      "step": 60
+    },
+    {
+      "epoch": 0.45323741007194246,
+      "grad_norm": 2.2661585807800293,
+      "learning_rate": 1.8109066104575023e-05,
+      "loss": 4.1022,
+      "step": 63
+    },
+    {
+      "epoch": 0.45323741007194246,
+      "eval_loss": 1.0169346332550049,
+      "eval_runtime": 19.3659,
+      "eval_samples_per_second": 12.083,
+      "eval_steps_per_second": 1.549,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.246152907659674e+16,
+  "total_flos": 1.079303780475863e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null