Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5bced6ca480ef33b1cb74b00c751a6f535a8969dcdd0c74eedf8782812a1d3c
+oid sha256:cc21b67e8fec23b306d0603fa43b55459062f7957418aa4451d5883efbb99901
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ed812059a156c31476836d8d3f12eabb1871cc383f03968ef72e7d751a58c13
+oid sha256:846246aaf5644ab98b7169c2dfd942484b4a83d092e108253b67668baf8178eb
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9a5b42dad51d511437343ea310d2892091ea5aee07e1ab3e12b04c82cc6ef3b
+oid sha256:e9fbae9cd7d0713e49ff88bdcfccbbd0181426e1a39167aef21a10601416c2fc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e555b1173ceea1f11ca45539c0fe5856e7571df97c436cc742ba6deb19b07e97
+oid sha256:fd82e2c4dd46a0c4163e78a1bb05a9e321fb40a1c884136f2f4f92fe2449cbde
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8480565371024735,
+  "epoch": 1.028268551236749,
   "eval_steps": 4,
-  "global_step": 15,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -46,6 +46,14 @@
       "eval_samples_per_second": 537.74,
       "eval_steps_per_second": 67.218,
       "step": 12
+    },
+    {
+      "epoch": 0.9045936395759717,
+      "eval_loss": 10.95703125,
+      "eval_runtime": 0.2252,
+      "eval_samples_per_second": 532.843,
+      "eval_steps_per_second": 66.605,
+      "step": 16
     }
   ],
   "logging_steps": 10,
@@ -60,12 +68,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2575162146816.0,
+  "total_flos": 3086336655360.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null